Next Article in Journal
From Cerebrovascular Injury to Vascular Cognitive Impairment and Dementia: Therapeutic Potential of Stem Cell-Derived Extracellular Vesicles
Previous Article in Journal
Prevalence of Functional Constipation in Children with Down Syndrome: A Study Conducted at a General Pediatrics Service
Previous Article in Special Issue
Intrathecal Therapies for Neurodegenerative Diseases: A Review of Current Approaches and the Urgent Need for Advanced Delivery Systems
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Biomedicines
Volume 14
Issue 1
10.3390/biomedicines14010159
biomedicines-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Editorial

Screen, Sample, Stratify: Biomarkers and Machine Learning Compress Dementia Pathways

by
Simone Battaglia
1,2 and
Masaru Tanaka
3,*
1
Faculty of Psychology, eCampus University, 22060 Novedrate, Italy
2
Department of Psychology, University of Turin, 10124 Turin, Italy
3
Danube Neuroscience Research Laboratory, HUN-REN-SZTE Neuroscience Research Group, Hungarian Research Network, University of Szeged (HUN-REN-SZTE), H-6725 Szeged, Hungary
*
Author to whom correspondence should be addressed.
Biomedicines 2026, 14(1), 159; https://doi.org/10.3390/biomedicines14010159
Submission received: 29 October 2025 / Revised: 16 December 2025 / Accepted: 24 December 2025 / Published: 12 January 2026
(This article belongs to the Special Issue Neurodegeneration in Cognitive Impairment and Mood Disorders for Experimental, Clinical, and Translational Neuropsychiatry—Second Edition)
Browse Figure
Versions Notes
Graphical Abstract

1. Vignette and Pressure Point

Late-life cognitive complaints seldom align with a single disease entity. Common neurodegenerative pathologies explain only a portion of decline, leaving substantial variance unresolved [1]. Biological aging processes—cellular senescence, inflammation, and mitochondrial dysfunction—form a shared substrate for cognitive vulnerability [2]. Depression further complicates attribution by accelerating biological aging, increasing dementia risk, and altering trajectories of attention, memory, and executive control [3,4,5,6,7]. Neuropsychiatric symptoms are frequent in mild cognitive impairment (MCI) and can precede progressive neurodegeneration [8]. Structural magnetic resonance imaging (MRI) highlights frontal and temporal atrophy with white matter injury in late-life depression [8]. Comparative imaging and genomic syntheses reveal convergence with MCI, preserving diagnostic ambiguity at first presentation [9].
At presentation, the differential is precarious. Dementia with Lewy bodies (DLB), Alzheimer’s disease (AD), and Parkinson’s disease dementia (PDD) share terrain yet diverge in attentional and visuospatial profiles, motor signs, and biomarkers, complicating early diagnosis [3,10,11]. Continuum models show heavier cerebral amyloid angiopathy, tau in DLB, and faster tempo than PDD, linking proteinopathy to vascular load [1,2]. Quantitative electroencephalography (EEG) and pragmatic prodromal algorithms improve separation from AD [12]. In multiple sclerosis (MS), fatigue, depression, and pain converge through shared inflammatory and network-level mechanisms, further blurring clinical attribution [4].
Nervous system disorders are now the leading cause of disability, with neurodegeneration driving escalating economic demand [1,4]. Uncertainty multiplies costs: impaired financial decision-making, caregiver strain, and post-stroke cognitive sequelae increase service use and dependency [1,2]. Pandemic disruptions and psychiatric cognitive impairment amplify system load, even when decline remains subjective [5,9]. This editorial adopts an integrative format to contextualize and connect the contributions of this Special Issue, highlighting shared mechanisms, diagnostic bottlenecks, and translational opportunities rather than providing an exhaustive review.

2. From Nosology to Mechanism: Rewiring Clinical Decisions

Guidelines have improved baseline practice, yet failure modes remain visible at precisely the points that matter, particularly in MCI, where heterogeneity and shifting thresholds produce discrepant classifications, high false negatives, and unstable diagnoses [13,14]. These instabilities dilute trials, defer counseling, and blur care pathways. Post-stroke cognitive impairment guidance still relies on thin evidence for prognosis and treatment, limiting timely intervention [15]. Prognostic factors such as anticholinergic burden are inconsistent, yielding low-certainty recommendations and weak individual prediction [16]. In major depressive disorder, cognitive dysfunction often persists despite symptomatic remission, while assessment remains uneven and understandardized, reducing actionable targets [16]. Latency to effective care also reflects adherence barriers in bipolar disorder, where multifactorial nonadherence undermines otherwise sound protocols [17]. Methodological upgrades are promising, including deep learning models for response prediction that could shorten decision cycles, but deployment requires calibration, transparency, and prospective validation [18,19,20].
Rewiring clinical decisions begins with shifting from static phenotypic labels to dynamic, mechanism-informed risk models. Transdiagnostic frameworks emphasize shared circuitry, trajectories, and prediction rather than category boundaries [21,22,23]. Precision medicine operationalizes this shift through multi-omics, biomarker panels, and data-driven stratification that personalize care pathways [16,24,25]. Mechanistic signal can be captured with EEG and machine learning for early diagnosis and prognosis in MCI and AD [4], complemented by digital phenotyping that yields explainable, longitudinal profiles [14,26]. Plasma biomarkers refine individual risk in prodromal states [27]. Network-based classifications and integrated neuroimaging–genetics approaches parse heterogeneity and nominate actionable subtypes in mood disorders and depression [28,29].

3. The Translational Corridor: Detection → Anchoring → Intervention

This corridor links rapid case finding to mechanism and then to action. We start with bedside triage and scalable blood biomarkers, where p tau217 and brief cognition guide rule-in or rule-out [30]. Visual queries in Lewy body disease (LBD), EEG signals, and fluorodeoxyglucose positron emission tomography (FDG-PET) sharpen early differentiation [31]. We then anchor risk in circuits and systems biology to define targets. Finally, calibrated models and task-coupled neuromodulation inform matched interventions and real clinic workflows.

3.1. Detection and Stratification

Early detection benefits from precise bedside triage. In this Special Issue, Balz et al. validate a revised Tracking Assessment of Cognition in Multiple Sclerosis (TRACK-MS) battery with improved sensitivity and specificity for cognitive impairment in multiple sclerosis, enabling rapid case finding and targeted referral [32]. Complementing this, Capogna et al. synthesize evidence on minor visual phenomena (MVP) in LBD, positioning brief visual queries as discriminative signals that precede fuller syndromic expression [33] (Table 1). Nuanced phenotyping remains essential given frequent Alzheimer’s co-pathology in LBD [34]. Short tools such as the ALBA instrument extend screening to nonspecialist settings, while EEG markers capture posterior network dysfunction that supports early differentiation [35,36]. When accessible, FDG-PET increases diagnostic accuracy over clinical assessment alone [37]. Translational LBD models underscore why phenotype-first gatekeeping accelerates the corridor from detection to intervention [38].
Along the corridor, rule-in and rule-out decisions increasingly rely on scalable blood biomarkers paired with genetic risk stratification [51,52]. Lai et al. synthesize convergent evidence that plasma phosphorylated tau 217 (p-tau217) leads Alzheimer’s pathology, with strong PET and cerebrospinal fluid (CSF) correlations and high accuracy on automated platforms across primary and secondary care [39]. Performance generalizes to Asian and South American cohorts, and a two-cutoff strategy improves clinical triage in subjective decline and MCI [53,54,55,56,57]. In parallel, Bao et al. present a clinical model that predicts the carriage of pathogenic or likely pathogenic variants in dementia with a positive family history, enabling targeted sequencing and counseling [40] (Table 1). Triggering receptor expressed on myeloid cells 2 (TREM2) risk and presenilin 1 (PSEN1) location shape trajectories and trial design [58,59]. Together, these tools reduce time to mechanism-informed care.
Algorithmic risk integration in Parkinson’s disease (PD) is moving from proof of concept to actionable triage. Mohammadi et al. report high discriminative performance using readily obtainable clinical variables and blood biomarkers, demonstrating that pragmatic Random Forest pipelines can flag early cognitive decline for intensified monitoring [41] (Table 1). Broader evidence shows that multimodal models that fuse clinical, CSF, imaging, and genetic features sharpen prediction and reveal the relevance of Alzheimer’s co-pathology [60,61,62,63]. Deep architectures improve sequential forecasting and event timing, from temporal models to disease progression frameworks [64,65]. Modality-specific pipelines add leverage: FDG-PET, sleep EEG, and dopamine transporter single photon emission computed tomography (DAT-SPECT) with cognitive scales enhance conversion prediction [66,67]. Meta-analyses underscore robust sensitivity and specificity across modalities, while highlighting the need for calibration, drift surveillance, and external validation before routine deployment [68,69].
Signals at the eye–brain interface justify targeted cognitive screening. Vision impairment is associated with decline, and glaucoma elevates dementia risk across subtypes [70,71]. Exfoliation glaucoma shows greater cognitive burden, with non-invasive biomarkers such as advanced glycation end products (AGEs) and carotenoids suggesting triage avenues [72,73]. Kadoh et al. demonstrate that patients with exfoliation glaucoma exhibit significantly lower Mini-Cog scores and higher fingertip AGE levels than those with primary open-angle glaucoma, highlighting AGE accumulation as a potential mechanistic and diagnostic bridge between ocular and cognitive dysfunction [42] (Table 1). Screen older adults with glaucoma, prioritizing normal tension, severe, or rapidly progressive disease, and those with optical coherence tomography angiography (OCTA) vessel density changes. Genetic and cortical links to AD strengthen timing for routine checks in this population [74,75].
A pragmatic triad is emerging for routine practice: rapid cognitive screening, blood panel, and composite risk trajectory. Plasma p-tau, amyloid beta 42 to 40 ratio (Aβ42/40), neurofilament light chain (NfL), and glial fibrillary acidic protein (GFAP) enable scalable rule-in and risk prediction across preclinical and prodromal states [76,77]. Two-step workflows that deploy p-tau217 first, reserving confirmatory tests for uncertain cases, reduce invasive procedures while preserving accuracy [78]. Composite models that fuse p-tau217 with brief cognition outperform single markers for MCI progression, and amyloid tau neurodegeneration framework (ATN) profiles plus demographics refine forecasts in unimpaired elders [77,79]. Outside AD, pairing blood NfL with MRI improves MS triage; trajectory clustering personalizes follow-up [80].
Generalizability hinges on context. Multicenter studies reveal site effects and training set bias that distort risk estimates unless explicitly modeled [81,82]. Demographic calibration is mandatory, as age, sex, ancestry, and education reweight signals across modalities [83,84]. Performance is stage contingent; tau-PET, MRI volumetry, EEG, and molecular imaging show shifting accuracy from preclinical states to MCI and dementia [85,86].

3.2. Mechanistic Anchors

Biondi et al. map structural alterations that track mood-related deficits in schizophrenia, sharpening the link between anatomy and affective symptomatology [43] (Table 1). Converging evidence positions endophenotypes as the translational bridge: they tie genetic risk to circuit dysfunction and clinical expression [87,88]. Thalamic reticular abnormalities offer a mechanistic anchor for attentional and mood disturbances, while large-scale network hypo-connectivity in high-risk states reinforces system-level vulnerability [89]. Electrophysiological signatures align with these structural findings and retain heritable signal [90]. Therapeutically, circuit-informed strategies matter: dorsolateral prefrontal stimulation reduces depressive symptoms, and emerging agents target GABAergic and glutamatergic nodes. Together, these anchors convert descriptive mood comorbidity into measurable, modifiable neural targets [91].
Plasticity and vascular integrity sit at the core of mechanism-first care [92]. Statsenko et al. distill hallmarks of brain plasticity into an operational scaffold that spans synaptic remodeling, glial–neuronal crosstalk, metabolic control, and structural adaptability, aligning with broader frameworks of neurodegenerative hallmarks and systems models of neurons, glia, extracellular matrix, and the neurovascular unit [44]. Complementing this axis, de Lima et al. map a triad that couples vascular impairment with muscle atrophy and cognitive decline, motivating integrative prevention and rehabilitation strategies [45] (Table 1). Blood–brain barrier breakdown emerges early and independently predicts decline, while neurovascular uncoupling implicates astrocytic and endothelial dysfunction in aging and AD [93,94]. Endothelial caveolae calibrate neurovascular coupling and energy delivery [95]. Translationally, inflammatory and blood–brain barrier (BBB) biomarkers anchor vascular cognitive impairment pipelines with clear clinical hooks [96].
Depression occupies multiple positions along the neurodegenerative arc: antecedent risk, prodromal signal, and consequence of progressive pathology. Papa et al. synthesize bidirectional, stage-dependent links and argue for longitudinal designs that disentangle trajectories and mechanisms [46] (Table 1). Converging evidence shows that late-life depression heightens conversion from subjective or mild impairment to dementia, with neuropsychiatric features sharpening risk stratification [97,98]. Biological pathways span stress hormones, cytokine signaling, and impaired neurogenesis that interface with Alzheimer pathophysiology [99,100,101]. Mild behavioral impairment further elevates risk, aligning affective dysregulation with early network disruption [102,103,104].
Longitudinal readouts should be coupled with circuit probes and vascular–muscle indices with plasticity markers, while transcranial magnetic stimulation (TMS) excitability and resting-state EEG track decline [105,106]. Hippocampal atrophy, arterial spin labeling magnetic resonance imaging (ASL MRI) or ultrasound metrics, and plasma panels, including NfL, GFAP, sphingosine 1 phosphate (S1P), and osteopontin, forecast progression across subjective cognitive decline (SCD), PD, and AD [107,108,109,110,111,112].

3.3. Intervention and Delivery

Intrathecal delivery is emerging as a pivotal route for mechanism-addressed neurotherapeutics in neurodegeneration [113]. Schreiner et al. synthesize the clinical rationale, showing how bypassing the BBB can accelerate target engagement while exposing persistent delivery gaps [47] (Table 1). Indications span proteins, antisense oligonucleotides, and gene therapies requiring reliable CSF exposure and parenchymal penetration [114]. Distribution is constrained by CSF dynamics, meningeal interfaces, and molecular size, demanding optimized physicochemistry and dosing schedules [115]. Device innovation is pressing: engineered catheters, controlled-release systems, and nanoporous implants enable intrathecal pseudodelivery and sustained gradients [113]. Nanomedicine and targeted nanoparticles promise better retention and tissue targeting yet face pharmacokinetic hurdles [116]. Quantitative, model-based design should guide trials and patient selection [117].
Targeted neuromodulation is converging on mechanism-guided, task-coupled protocols for post-ischemic cognitive recovery [118]. Markowska et al. map molecular alterations in the ischemic brain to stimulation-responsive pathways and advocate parameterized protocols with rational combination therapies [48] (Table 1). Meta-analyses show dorsolateral prefrontal tDCS and TMS improve cognition, with effects shaped by montage, dose, and task coupling [119,120]. Mechanistic bridges include the modulation of functional connectivity, synaptic plasticity, and brain-derived neurotrophic factor (BDNF), with convergent enhancements of long-term potentiation (LTP) and N-methyl-D-aspartate receptor (NMDAR) signaling in animal models [121]. Task-embedded designs matter: tDCS reshapes EEG during working memory, normalizes age-altered functional magnetic resonance imaging (fMRI) networks, and tunes functional near-infrared spectroscopy (fNIRS) hemodynamics [122]. Dual-site high-definition transcranial direct current stimulation (HD-tDCS) with TMS-EEG sharpens circuit-specific targeting [123].
Urological physiology is not peripheral to MS care—it interlocks with fatigue and mood outcomes. Jaekel et al. show that defined urodynamic abnormalities increase fatigue risk, motivating longitudinal assessment and targeted management [49] (Table 1). Symptom network analyses connect fatigue to specific depressive items and to urgency and voided volume, nominating shared intervention nodes [124]. Converging mechanisms include neuroinflammation and disrupted reward processing [124]. Care pathways should integrate bladder-focused therapy with exercise and mood treatment, supported by registry and longitudinal data showing bidirectional fatigue–depression effects and persistent undertreatment [49,124].
Peripheral proxy biomarkers attract clinical interest yet demand rigor. Carpita et al. report lower intra-platelet BDNF in adults with autism linked to symptom burden, underscoring age and methodological effects [50]. Meta-analyses show elevated peripheral BDNF, but heterogeneity and matrix differences persist (Table 1). Platelet count and preanalytical factors confound serum signals. Technical reviews emphasize assay standardization and replication before clinical translation [125].

4. Operationalization—Bottlenecks, Upgrades, Redesign, Practice Capsule, and Closeout

Operationalization turns intention into action across the corridor. We start by confronting credibility bottlenecks: p-tau217 assay standardization with transportable cutoffs; strict model calibration; cross-site robustness; alignment of patient reported outcomes (PROs) with mechanisms; and equitable access. Next come near term upgrades with explicit metrics, then a longer horizon redesign that uses endotype-stratified platform trials and regulatory grade qualification. A concise practice capsule guides use now versus caution, while the closeout codifies transportable thresholds and locked analyses [126,127].

4.1. Bottlenecks to Credibility

Bottlenecks to credibility begin at the bench. Plasma p-tau217 shows strong diagnostic promise, yet credibility depends on assay harmonization and transportable cutoffs that survive lot-to-lot drift, platform differences, and demographic shifts [128]. Reviews of p-tau217 and related epitopes argue for multi-cohort calibration anchored to CSF comparators and pathology, with predefined decision thresholds and proficiency testing to guard against silent misclassification [129]. In parallel, predictive models require rigorous calibration, not only high discrimination. Large neuroimaging and genetic benchmarks show that apparent accuracy collapses without external validation, well-specified calibration curves, and pre-registered analytic plans [130]. Thousands of individuals are typically needed to stabilize brain–behavior associations; smaller studies should preferentially report uncertainty, sensitivity to nuisance variance, and domain shift. Reproducible pipelines and site-robust components, as exemplified by automated independent component analysis (ICA) frameworks and multi-site bipolar MRI challenges, help contain scanner effects and analytic degrees of freedom, but they are not substitutes for cross-site replication with locked code and fixed thresholds.
Credibility also hinges on aligning what matters to patients with what models and biomarkers claim to measure. Work on neuropsychiatric outcomes after chimeric antigen receptor T cell therapy (CAR-T) and validated attribution algorithms in systemic autoimmune disease illustrate how carefully constructed patient-reported outcomes can be tied to mechanistic hypotheses and adjudicated endpoints. Embedding such PROs as co-primary readouts with p-tau217 and imaging markers can reveal when signals are clinically meaningful versus statistically convenient. Finally, equity is a methodological requirement. Dementia research and neurologic care remain unevenly distributed across regions and racial or ethnic groups. Without inclusive sampling frames, shared standards for data and assay exchange, and cost-sensitive deployment plans, calibrated models and cutoffs will amplify disparities rather than close them. Credibility therefore emerges from a linked agenda: standardize assays against common references, calibrate and externally validate models at scale, make analyses more robust against site effects, align PROs to mechanisms, and design access pathways that are fair by construction [131].

4.2. Near-Term Upgrades (12–24 mo) with Hard Metrics

A pragmatic path forward is a two-step workflow that separates case finding from confirmation. For Parkinson’s and multiple system atrophy (MSA), a first-stage digital or multimodal screen achieves high discrimination in external cohorts, with area under the curve (AUC) typically 0.85 to 0.94, and in some settings higher [132]. Adding a confirmatory, pathogenesis-based biomarker in step two tightens specificity and stabilizes net reclassification improvement (NRI) compared with usual care that relies on clinical judgment alone [133]. Proteomic and exosomal signatures, including neuronal and oligodendroglial α-synuclein assays, deliver validation sensitivities around 90 percent with comparable specificity, while proteomic panels refined in longitudinal registries push step two AUC toward 0.98. Parallel refinements in dementia triage matter for differential diagnosis. Protocolized screening for MVP combined with a structured cingulate island sign rating on FDG-PET reduces Lewy body misclassification, cuts false positives against AD, and prevents overcalling atypical parkinsonism when visual symptoms are the earliest clue.
Credibility then hinges on prospective calibration across at least three sites for both PD machine learning models and p-tau217. Targets should be explicit—area under the receiver operating characteristic curve (AUROC) at or above 0.75 with a calibration slope close to 1.0, intercept near 0, and decision curve net benefit that exceeds usual care across plausible thresholds. Achieving this requires a minimal multimodal panel that can survive real clinical constraints. A blood anchor such as p-tau217 or p-tau181, a brief cognitive composite, and a lightweight digital measure captured passively or in short tasks. Predefine acceptable operational metrics—missingness under 5 percent across sites, interclass correlation at or above 0.8 for repeated measures, cross cohort drift assessed quarterly, and lockbox external validation before any update. Evidence from wearables, metabolomics, and proteomics shows that heterogeneous signals outperform self-report and lifestyle alone, but only when device firmware, preprocessing, and batch correction are versioned and shared. With that discipline, the screen to confirm paradigm becomes an implementable service line rather than a single site curiosity.

4.3. Long-Horizon Redesign (3–5+ yrs)

A credible long-horizon redesign should center on endotype-stratified platform trials that co-test pharmacologic and device strategies in one adaptive architecture [134]. Intrathecal agents can be assigned to proteinopathy-enriched strata while non-invasive brain stimulation (NIBS) arms are personalized by network topology, symptom domain, and target engagement [135]. Entry, allocation, and graduation rules should be gated by regulatory-grade readouts. Plasma p-tau217, with validated cutoffs and longitudinal responsiveness, functions as a selection and monitoring surrogate, while digital phenotypes from brief cognitive panels and passively acquired behavior provide high-frequency safety and efficacy signals suitable for interim decisions. This pairing enables efficient enrichment, early futility stopping, and standardized evidence packages for regulators.
Prevention must shift to mechanism-first programs along the vascular–muscle–cognition axis by embedding exercise and nutrition interventions as default backbones in at-risk cohorts, anchoring endpoints to neural physiology, not only global cognition, and combining p-tau217 or related plasma markers with vascular metrics, sarcopenia indices, and brief digital cognition to link mechanistic engagement to clinical change. Multidomain trials already demonstrate that structured activity, diet, vascular risk control, and cognitive training yield measurable neural benefits; next-generation studies should hard-wire these components as shared control or background therapy across arms, with standardized target-engagement milestones and upgradeable intensity.
The final pillar is an interoperable data commons that stitches preclinical tasks to clinical readouts. Common data elements, FAIR metadata, and harmonized pipelines allow rodent or nonhuman primate assays of memory, motor control, and network plasticity to map onto human digital and imaging endpoints. Advanced analytics, including topological and representation learning, can preserve cross-species geometry while exposing mechanistic signatures that are invariant to platform and site. With this scaffold, signals discovered in models translate into prospectively testable biomarkers and outcomes, and negative findings retire non-performing mechanisms early rather than after years of costly drift.

4.4. Practice Capsule

TRACK-MS offers a rapid, validated cognitive tracking option for MS that rivals longer batteries while fitting real clinic constraints [136]. Structured visual queries for LBD, centered on the cingulate island sign rating on FDG-PET, improve diagnostic specificity and reduce miscalls against AD when applied with a brief symptom checklist. Context-validated p-tau217 on fully automated platforms now supports referral, triage, and longitudinal monitoring; analytical performance and cross-site accuracy meet the threshold for regulatory-grade decision support when paired with predefined cutoffs and periodic proficiency testing.
Use with caution: platelet BDNF fluctuates with platelet release dynamics, mood state, storage conditions, and comorbidity, which limits specificity for neurodegenerative indications; treat as a secondary signal. Site-specific machine learning without external calibration invites optimistic bias; require at least one independent cohort, calibration slope near 1.0, and net benefit beyond usual care before deployment. Watchlist: intrathecal delivery platforms remain promising for concentrated target engagement yet need safety gating, pharmacokinetic-pharmacodynamic bridging, and mechanistic futility stops. Combined NIBS plus pharmacology protocols merit structured exploration with endotype stratification, dose titration anchored to target engagement, and harmonized outcomes that capture both symptom change and network-level physiology [137].

4.5. Close—“The Corridor Contract”

One sentence delta: starting today, multicenter calibration is the default gatekeeper for any biomarker, imaging readout, or machine learning tool that moves beyond discovery into practice. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) showed how shared protocols and open repositories convert variability into signal, while Enhancing NeuroImaging Genetics through Meta-Analysis (ENIGMA) and related consortia proved that credible neuropsychiatry now depends on cross-site integration at scale. Harmonized MRI and PET methods, common data elements, and prospective proficiency testing have matured to the point that single site claims are insufficient. Multicenter validation of blood biomarkers such as neurofilament light underscores both feasibility and necessity, and reviews across modalities converge on the same conclusion.
Join a shared platform trial that couples endotype stratification with a standing calibration core. Contribute data under common elements, run locked analyses with preregistered decision thresholds, and adopt site readiness checks before enrollment. Imaging will follow harmonized acquisition and phantom procedures. Blood assays will use standardized materials and quarterly drift audits. Digital and ML endpoints will require external calibration curves and independent cohorts. The corridor is not merely a metaphor but a commitment to calibration over novelty, transportability over isolated performance, and integration over silos.

Author Contributions

Conceptualization, S.B. and M.T.; methodology, M.T.; software, M.T.; validation, S.B. and M.T.; formal analysis, S.B. and M.T.; investigation, S.B. and M.T.; resources, M.T.; data curation, M.T.; writing—original draft preparation, M.T.; writing—review and editing, S.B. and M.T.; visualization, M.T.; supervision, M.T.; project administration, S.B. and M.T.; funding acquisition, M.T. All authors have read and agreed to the published version of the manuscript.

Funding

This work was supported by the HUN-REN Hungarian Research Network funding to M.T. S.B. is supported by #NEXTGENERATIONEU (NGEU) and funded by the Ministry of University and Research (MUR), National Recovery and Resilience Plan (NRRP), project MNESYS (PE0000006)—a multiscale integrated approach to the study of the nervous system in health and disease (DN. 1553 11.10.2022)—and Bial Foundation, Portugal (235/22). The views and opinions expressed are solely those of the authors and do not necessarily reflect those of the European Union, nor can the European Union be held responsible for them.

Conflicts of Interest

The authors declare no conflicts of interest.

Abbreviations

The following abbreviations are used in this manuscript:
ADAlzheimer’s disease
ADNIAlzheimer’s Disease Neuroimaging Initiative
AGEsadvanced glycation end products
ASDautism spectrum disorder
ASL MRIarterial spin labeling magnetic resonance imaging
ATNamyloid tau neurodegeneration framework
AUCarea under the curve
AUROCarea under the receiver operating characteristic curve
Aβ42/40amyloid beta 42 to 40 ratio
BBBblood–brain barrier
BDNFbrain-derived neurotrophic factor
CAR-Tchimeric antigen receptor T cell therapy
CSFcerebrospinal fluid
DAT-SPECTdopamine transporter single photon emission computed tomography
DLBdementia with Lewy bodies
EEGelectroencephalography
ENIGMAEnhancing NeuroImaging Genetics through Meta-Analysis
FDG-PETfluorodeoxyglucose positron emission tomography
fMRIfunctional magnetic resonance imaging
fNIRSfunctional near-infrared spectroscopy
GFAPglial fibrillary acidic protein
HD-tDCShigh-definition transcranial direct current stimulation
ICAindependent component analysis
LBDLewy body disease
LTPlong-term potentiation
MCImild cognitive impairment
MRImagnetic resonance imaging
MSmultiple sclerosis
MSAmultiple system atrophy
MVPminor visual phenomena
NfLneurofilament light chain
NIBSnon-invasive brain stimulation
NMDARN-methyl-D-aspartate receptor
NRInet reclassification improvement
OCTAoptical coherence tomography angiography
p-tau217phosphorylated tau at threonine 217
PDParkinson’s disease
PDDParkinson’s disease dementia
PETpositron emission tomography
POAGprimary open-angle glaucoma
PROspatient reported outcomes
PSEN1presenilin 1
RFrandom forest
S1Psphingosine 1 phosphate
SCDsubjective cognitive decline
SCZschizophrenia
TRACK-MSTracking Assessment of Cognition in Multiple Sclerosis
tDCStranscranial direct current stimulation
TMStranscranial magnetic stimulation
TREM2triggering receptor expressed on myeloid cells 2

References

  1. Gonzales, M.M.; Garbarino, V.R.; Pollet, E.; Palavicini, J.P.; Kellogg, D.L., Jr.; Kraig, E.; Orr, M.E. Biological aging processes underlying cognitive decline and neurodegenerative disease. J. Clin. Investig. 2022, 132, e158453. [Google Scholar] [CrossRef]
  2. Martínez-Cué, C.; Rueda, N. Cellular Senescence in Neurodegenerative Diseases. Front. Cell. Neurosci. 2020, 14, 16. [Google Scholar] [CrossRef]
  3. Marawi, T.; Ainsworth, N.J.; Zhukovsky, P.; Rashidi-Ranjbar, N.; Rajji, T.K.; Tartaglia, M.C.; Voineskos, A.N.; Mulsant, B.H. Brain-cognition relationships in late-life depression: A systematic review of structural magnetic resonance imaging studies. Transl. Psychiatry 2023, 13, 284. [Google Scholar] [CrossRef]
  4. Rashidi-Ranjbar, N.; Miranda, D.; Butters, M.A.; Mulsant, B.H.; Voineskos, A.N. Evidence for Structural and Functional Alterations of Frontal-Executive and Corticolimbic Circuits in Late-Life Depression and Relationship to Mild Cognitive Impairment and Dementia: A Systematic Review. Front. Neurosci. 2020, 14, 253. [Google Scholar] [CrossRef]
  5. Ren, Z.; Nie, L.; Du, Y.; Liu, J. Intertwined depressive and cognitive trajectories and the risk of dementia and death in older adults: A competing risk analysis. Gen. Psychiatry 2024, 37, e101156. [Google Scholar] [CrossRef]
  6. Battaglia, S.; Nazzi, C.; Thayer, J.F. Genetic differences associated with dopamine and serotonin release mediate fear-induced bradycardia in the human brain. Transl. Psychiatry 2024, 14, 24. [Google Scholar] [CrossRef]
  7. Nazzi, C.; Avenanti, A.; Battaglia, S. The Involvement of Antioxidants in Cognitive Decline and Neurodegeneration: Mens Sana in Corpore Sano. Antioxidants 2024, 13, 701. [Google Scholar] [CrossRef]
  8. Martin, E.; Velayudhan, L. Neuropsychiatric Symptoms in Mild Cognitive Impairment: A Literature Review. Dement. Geriatr. Cogn. Disord. 2020, 49, 146–155. [Google Scholar] [CrossRef] [PubMed]
  9. Zhao, L.; Niu, L.; Dai, H.; Lee, T.M.C.; Huang, R.; Zhang, R. A comparative meta-analysis of structural magnetic resonance imaging studies and gene expression profiles revealing the similarities and differences between late life depression and mild cognitive impairment. Psychol. Med. 2024, 54, 4264–4273. [Google Scholar] [CrossRef] [PubMed]
  10. Kaup, A.R.; Byers, A.L.; Falvey, C.; Simonsick, E.M.; Satterfield, S.; Ayonayon, H.N.; Smagula, S.F.; Rubin, S.M.; Yaffe, K. Trajectories of Depressive Symptoms in Older Adults and Risk of Dementia. JAMA Psychiatry 2016, 73, 525–531. [Google Scholar] [CrossRef]
  11. Tanaka, M. Parkinson’s Disease: Bridging Gaps, Building Biomarkers, and Reimagining Clinical Translation. Cells 2025, 14, 1161. [Google Scholar] [CrossRef]
  12. Muhammad, T.; Meher, T. Association of late-life depression with cognitive impairment: Evidence from a cross-sectional study among older adults in India. BMC Geriatr. 2021, 21, 364. [Google Scholar] [CrossRef]
  13. Milner, T.; Brown, M.R.G.; Jones, C.; Leung, A.W.S.; Brémault-Phillips, S. Multidimensional digital biomarker phenotypes for mild cognitive impairment: Considerations for early identification, diagnosis and monitoring. Front. Digit. Health 2024, 6, 1265846. [Google Scholar] [CrossRef] [PubMed]
  14. Alfalahi, H.; Dias, S.B.; Khandoker, A.H.; Chaudhuri, K.R.; Hadjileontiadis, L.J. A scoping review of neurodegenerative manifestations in explainable digital phenotyping. NPJ Parkinsons Dis. 2023, 9, 49. [Google Scholar] [CrossRef]
  15. Xie, Y.; Nahab, F.; Ge, Y.; Wu, Y.; Saurman, J.; Yang, C.; Hu, X. Abstract WP175: Predicting Post-Stroke Cognitive Impairment (PSCI) Using Multiple Machine Learning Approaches. Stroke 2025, 56, AWP175. [Google Scholar] [CrossRef]
  16. Stolfi, F.; Abreu, H.; Sinella, R.; Nembrini, S.; Centonze, S.; Landra, V.; Brasso, C.; Cappellano, G.; Rocca, P.; Chiocchetti, A. Omics approaches open new horizons in major depressive disorder: From biomarkers to precision medicine. Front. Psychiatry 2024, 15, 1422939. [Google Scholar] [CrossRef] [PubMed]
  17. Roefs, A.; Fried, E.I.; Kindt, M.; Martijn, C.; Elzinga, B.; Evers, A.W.M.; Wiers, R.W.; Borsboom, D.; Jansen, A. A new science of mental disorders: Using personalised, transdiagnostic, dynamical systems to understand, model, diagnose and treat psychopathology. Behav. Res. Ther. 2022, 153, 104096. [Google Scholar] [CrossRef]
  18. Qin, Z.; Li, Y.; Song, X.; Chai, L. Classification of Neuropsychiatric Disorders via Brain-Region-Selected Graph Convolutional Network. IEEE Trans. Neural Syst. Rehabil. Eng. 2025, 33, 1664–1672. [Google Scholar] [CrossRef]
  19. Tanaka, M.; Battaglia, S. From Biomarkers to Behavior: Mapping the Neuroimmune Web of Pain, Mood, and Memory. Biomedicines 2025, 13, 2226. [Google Scholar] [CrossRef]
  20. Tanaka, M. Special Issue “Translating Molecular Psychiatry: From Biomarkers to Personalized Therapies”. Int. J. Mol. Sci. 2025, 26, 238. [Google Scholar] [CrossRef] [PubMed]
  21. McGorry, P.D.; Hartmann, J.A.; Spooner, R.; Nelson, B. Beyond the “at risk mental state” concept: Transitioning to transdiagnostic psychiatry. World Psychiatry 2018, 17, 133–142. [Google Scholar] [CrossRef]
  22. Koike, S. Transdiagnostic approach for neuropsychiatric symptoms using neuroimage. Psychiatry Clin. Neurosci. 2025, 79, 137. [Google Scholar] [CrossRef] [PubMed]
  23. Battaglia, S.; Servajean, P.; Friston, K.J. The paradox of the self-studying brain. Phys. Life Rev. 2025, 52, 197–204. [Google Scholar] [CrossRef]
  24. Tanaka, M.; Vécsei, L. From Microbial Switches to Metabolic Sensors: Rewiring the Gut-Brain Kynurenine Circuit. Biomedicines 2025, 13, 2020. [Google Scholar] [CrossRef]
  25. Tanaka, M. From Serendipity to Precision: Integrating AI, Multi-Omics, and Human-Specific Models for Personalized Neuropsychiatric Care. Biomedicines 2025, 13, 167. [Google Scholar] [CrossRef]
  26. Parsa, M.; Rad, H.Y.; Vaezi, H.; Hossein-Zadeh, G.A.; Setarehdan, S.K.; Rostami, R.; Rostami, H.; Vahabie, A.H. EEG-based classification of individuals with neuropsychiatric disorders using deep neural networks: A systematic review of current status and future directions. Comput. Methods Programs Biomed. 2023, 240, 107683. [Google Scholar] [CrossRef]
  27. Wang, K.; Adjeroh, D.A.; Fang, W.; Walter, S.M.; Xiao, D.; Piamjariyakul, U.; Xu, C. Comparison of Deep Learning and Traditional Machine Learning Models for Predicting Mild Cognitive Impairment Using Plasma Proteomic Biomarkers. Int. J. Mol. Sci. 2025, 26, 2428. [Google Scholar] [CrossRef]
  28. Lalousis, P.A.; Schmaal, L.; Wood, S.J.; Reniers, R.; Barnes, N.M.; Chisholm, K.; Griffiths, S.L.; Stainton, A.; Wen, J.; Hwang, G.; et al. Neurobiologically Based Stratification of Recent-Onset Depression and Psychosis: Identification of Two Distinct Transdiagnostic Phenotypes. Biol. Psychiatry 2022, 92, 552–562. [Google Scholar] [CrossRef] [PubMed]
  29. Tanaka, M. Beyond the boundaries: Transitioning from categorical to dimensional paradigms in mental health diagnostics. Adv. Clin. Exp. Med. 2024, 33, 1295–1301. [Google Scholar] [CrossRef] [PubMed]
  30. Therriault, J.; Janelidze, S.; Benedet, A.L.; Ashton, N.J.; Arranz Martínez, J.; Gonzalez-Escalante, A.; Bellaver, B.; Alcolea, D.; Vrillon, A.; Karim, H.; et al. Diagnosis of Alzheimer’s disease using plasma biomarkers adjusted to clinical probability. Nat. Aging 2024, 4, 1529–1537. [Google Scholar] [CrossRef]
  31. Peraza, L.R.; Cromarty, R.; Kobeleva, X.; Firbank, M.J.; Killen, A.; Graziadio, S.; Thomas, A.J.; O’Brien, J.T.; Taylor, J.P. Electroencephalographic derived network differences in Lewy body dementia compared to Alzheimer’s disease patients. Sci. Rep. 2018, 8, 4637. [Google Scholar] [CrossRef] [PubMed]
  32. Balz, L.T.; Uttner, I.; Taranu, D.; Erhart, D.K.; Fangerau, T.; Jung, S.; Schreiber, H.; Senel, M.; Vardakas, I.; Lulé, D.E.; et al. Sensitivity and Specificity of a Revised Version of the TRACK-MS Screening Battery for Early Detection of Cognitive Impairment in Patients with Multiple Sclerosis. Biomedicines 2025, 13, 1902. [Google Scholar] [CrossRef]
  33. Capogna, E.; Pollarini, V.; Quinzi, A.; Guidi, L.; Sambati, L.; Criante, M.S.; Mengoli, E.; Venneri, A.; Lodi, R.; Tonon, C.; et al. Minor Visual Phenomena in Lewy Body Disease: A Systematic Review. Biomedicines 2025, 13, 1152. [Google Scholar] [CrossRef]
  34. Bussè, C.; Mitolo, M.; Mozzetta, S.; Venneri, A.; Cagnin, A. Impact of Lewy bodies disease on visual skills and memory abilities: From prodromal stages to dementia. Front. Psychiatry 2024, 15, 1461620. [Google Scholar] [CrossRef]
  35. Delgado-Álvarez, A.; Delgado-Alonso, C.; Goudsmit, M.; Gil, M.J.; Díez-Cirarda, M.; Valles-Salgado, M.; Montero-Escribano, P.; Hernández-Lorenzo, L.; Matías-Guiu, J.; Matias-Guiu, J.A. Validation of a brief cross-cultural cognitive screening test in Multiple Sclerosis. Mult. Scler. Relat. Disord. 2022, 67, 104091. [Google Scholar] [CrossRef] [PubMed]
  36. Firbank, M.J.; Collerton, D.; Morgan, K.D.; Schumacher, J.; Donaghy, P.C.; O’Brien, J.T.; Thomas, A.; Taylor, J.P. Functional connectivity in Lewy body disease with visual hallucinations. Eur. J. Neurol. 2024, 31, e16115. [Google Scholar] [CrossRef]
  37. D’Antonio, F.; Boccia, M.; Di Vita, A.; Suppa, A.; Fabbrini, A.; Canevelli, M.; Caramia, F.; Fiorelli, M.; Guariglia, C.; Ferracuti, S.; et al. Visual hallucinations in Lewy body disease: Pathophysiological insights from phenomenology. J. Neurol. 2022, 269, 3636–3652. [Google Scholar] [CrossRef]
  38. Boschen, S.L.; Mukerjee, A.A.; Faroqi, A.H.; Rabichow, B.E.; Fryer, J. Research models to study lewy body dementia. Mol. Neurodegener. 2025, 20, 46. [Google Scholar] [CrossRef]
  39. Lai, R.; Li, B.; Bishnoi, R. P-tau217 as a Reliable Blood-Based Marker of Alzheimer’s Disease. Biomedicines 2024, 12, 1836. [Google Scholar] [CrossRef]
  40. Bao, J.; Qiu, Y.; Wang, T.; Shang, L.; Chu, S.; Jin, W.; Wang, W.; Jiang, Y.; Li, B.; Huang, Y.; et al. Predictive Accuracy of a Clinical Model for Carriage of Pathogenic/Likely Pathogenic Variants in Patients with Dementia and a Positive Family History at PUMCH. Biomedicines 2025, 13, 1235. [Google Scholar] [CrossRef] [PubMed]
  41. Mohammadi, R.; Ng, S.Y.E.; Tan, J.Y.; Ng, A.S.L.; Deng, X.; Choi, X.; Heng, D.L.; Neo, S.; Xu, Z.; Tay, K.Y.; et al. Machine Learning for Early Detection of Cognitive Decline in Parkinson’s Disease Using Multimodal Biomarker and Clinical Data. Biomedicines 2024, 12, 2758. [Google Scholar] [CrossRef]
  42. Kadoh, Y.; Kubota, S.; Shimomine, S.; Tanito, M. Exploring Cognitive Impairments Associated with Primary Open-Angle Glaucoma and Exfoliation Glaucoma. Biomedicines 2024, 12, 1706. [Google Scholar] [CrossRef]
  43. Biondi, M.; Marino, M.; Mantini, D.; Spironelli, C. Brain Structural Alterations Underlying Mood-Related Deficits in Schizophrenia. Biomedicines 2025, 13, 736. [Google Scholar] [CrossRef]
  44. Statsenko, Y.; Kuznetsov, N.V.; Ljubisaljevich, M. Hallmarks of Brain Plasticity. Biomedicines 2025, 13, 460. [Google Scholar] [CrossRef] [PubMed]
  45. de Lima, E.P.; Tanaka, M.; Lamas, C.B.; Quesada, K.; Detregiachi, C.R.P.; Araújo, A.C.; Guiguer, E.L.; Catharin, V.; de Castro, M.V.M.; Junior, E.B.; et al. Vascular Impairment, Muscle Atrophy, and Cognitive Decline: Critical Age-Related Conditions. Biomedicines 2024, 12, 2096. [Google Scholar] [CrossRef]
  46. Papa, D.; Ingenito, A.; von Gal, A.; De Pandis, M.F.; Piccardi, L. Relationship Between Depression and Neurodegeneration: Risk Factor, Prodrome, Consequence, or Something Else? A Scoping Review. Biomedicines 2025, 13, 1023. [Google Scholar] [CrossRef] [PubMed]
  47. Schreiner, T.G.; Menéndez-González, M.; Schreiner, O.D.; Ciobanu, R.C. Intrathecal Therapies for Neurodegenerative Diseases: A Review of Current Approaches and the Urgent Need for Advanced Delivery Systems. Biomedicines 2025, 13, 2167. [Google Scholar] [CrossRef]
  48. Markowska, A.; Tarnacka, B. Molecular Changes in the Ischemic Brain as Non-Invasive Brain Stimulation Targets-TMS and tDCS Mechanisms, Therapeutic Challenges, and Combination Therapies. Biomedicines 2024, 12, 1560. [Google Scholar] [CrossRef]
  49. Jaekel, A.K.; Watzek, J.; Nielsen, J.; Butscher, A.L.; Bitter, J.; von Danwitz, M.; Zöhrer, P.I.; Knappe, F.; Kirschner-Hermanns, R.; Knüpfer, S.C. The Impact of Urodynamic Findings on Fatigue and Depression in People with Multiple Sclerosis. Biomedicines 2025, 13, 601. [Google Scholar] [CrossRef]
  50. Carpita, B.; Nardi, B.; Bonelli, C.; Pascariello, L.; Massimetti, G.; Cremone, I.M.; Pini, S.; Palego, L.; Betti, L.; Giannaccini, G.; et al. Platelet Levels of Brain-Derived Neurotrophic Factor in Adults with Autism Spectrum Disorder: Is There a Specific Association with Autism Spectrum Psychopathology? Biomedicines 2024, 12, 1529. [Google Scholar] [CrossRef] [PubMed]
  51. Ramanan, V.K.; Gebre, R.K.; Graff-Radford, J.; Hofrenning, E.; Algeciras-Schimnich, A.; Figdore, D.J.; Lowe, V.J.; Mielke, M.M.; Knopman, D.S.; Ross, O.A.; et al. Genetic risk scores enhance the diagnostic value of plasma biomarkers of brain amyloidosis. Brain 2023, 146, 4508–4519. [Google Scholar] [CrossRef] [PubMed]
  52. AlMansoori, M.E.; Jemimah, S.; Abuhantash, F.; AlShehhi, A. Predicting early Alzheimer’s with blood biomarkers and clinical features. Sci. Rep. 2024, 14, 6039. [Google Scholar] [CrossRef]
  53. Dyer, A.; Dolphin, H.; Morrison, L.; O’Connor, A.; Sedgwick, G.; Young, C.; Killeen, E.; Gallagher, C.; McFeely, A.; Connolly, E. Plasma P-tau217 Demonstrates Excellent Diagnostic and Prognostic Performance as a Blood-Based Biomarker for Alzheimer Disease in Older Adults. Age Ageing 2024, 53, afae178.001. [Google Scholar]
  54. Pandey, N.; Yang, Z.; Cieza, B.; Reyes-Dumeyer, D.; Kang, M.S.; Montesinos, R.; Soto-Añari, M.; Custodio, N.; Honig, L.S.; Tosto, G. Plasma phospho-tau217 as a predictive biomarker for Alzheimer’s disease in a large south American cohort. Alzheimers Res. Ther. 2025, 17, 1. [Google Scholar] [CrossRef] [PubMed]
  55. Wang, S.; Liu, D.; Li, H.; Jia, X.; Zhou, H.; Yu, W.; Li, T.; Pan, L.; Chen, B.; Wang, Y.; et al. Assessing diagnostic performance of plasma biomarkers in Alzheimer’s disease versus cognitively unimpaired individuals: P-tau217 emerges as the optimal marker in Chinese cohorts. Front. Aging Neurosci. 2025, 17, 1554805. [Google Scholar] [CrossRef]
  56. Grande, G.; Valletta, M.; Rizzuto, D.; Xia, X.; Qiu, C.; Orsini, N.; Dale, M.; Andersson, S.; Fredolini, C.; Winblad, B.; et al. Blood-based biomarkers of Alzheimer’s disease and incident dementia in the community. Nat. Med. 2025, 31, 2027–2035. [Google Scholar] [CrossRef] [PubMed]
  57. Milà-Alomà, M.; Ashton, N.J.; Shekari, M.; Salvadó, G.; Ortiz-Romero, P.; Montoliu-Gaya, L.; Benedet, A.L.; Karikari, T.K.; Lantero-Rodriguez, J.; Vanmechelen, E.; et al. Plasma p-tau231 and p-tau217 as state markers of amyloid-β pathology in preclinical Alzheimer’s disease. Nat. Med. 2022, 28, 1797–1801. [Google Scholar] [CrossRef] [PubMed]
  58. Bartoletti-Stella, A.; Tarozzi, M.; Mengozzi, G.; Asirelli, F.; Brancaleoni, L.; Mometto, N.; Stanzani-Maserati, M.; Baiardi, S.; Linarello, S.; Spallazzi, M.; et al. Dementia-related genetic variants in an Italian population of early-onset Alzheimer’s disease. Front. Aging Neurosci. 2022, 14, 969817. [Google Scholar] [CrossRef]
  59. Schultz, S.A.; Liu, L.; Schultz, A.P.; Fitzpatrick, C.D.; Levin, R.; Bellier, J.P.; Shirzadi, Z.; Joseph-Mathurin, N.; Chen, C.D.; Benzinger, T.L.S.; et al. γ-Secretase activity, clinical features, and biomarkers of autosomal dominant Alzheimer’s disease: Cross-sectional and longitudinal analysis of the Dominantly Inherited Alzheimer Network observational study (DIAN-OBS). Lancet Neurol. 2024, 23, 913–924. [Google Scholar] [CrossRef]
  60. Almgren, H.; Camacho, M.; Hanganu, A.; Kibreab, M.; Camicioli, R.; Ismail, Z.; Forkert, N.D.; Monchi, O. Machine learning-based prediction of longitudinal cognitive decline in early Parkinson’s disease using multimodal features. Sci. Rep. 2023, 13, 13193. [Google Scholar] [CrossRef]
  61. Schrag, A.; Siddiqui, U.F.; Anastasiou, Z.; Weintraub, D.; Schott, J.M. Clinical variables and biomarkers in prediction of cognitive impairment in patients with newly diagnosed Parkinson’s disease: A cohort study. Lancet Neurol. 2017, 16, 66–75. [Google Scholar] [CrossRef]
  62. Caspell-Garcia, C.; Simuni, T.; Tosun-Turgut, D.; Wu, I.W.; Zhang, Y.; Nalls, M.; Singleton, A.; Shaw, L.A.; Kang, J.H.; Trojanowski, J.Q.; et al. Multiple modality biomarker prediction of cognitive impairment in prospectively followed de novo Parkinson disease. PLoS ONE 2017, 12, e0175674. [Google Scholar] [CrossRef]
  63. Bäckström, D.; Granåsen, G.; Mo, S.J.; Riklund, K.; Trupp, M.; Zetterberg, H.; Blennow, K.; Forsgren, L.; Domellöf, M.E. Prediction and early biomarkers of cognitive decline in Parkinson disease and atypical parkinsonism: A population-based study. Brain Commun. 2022, 4, fcac040. [Google Scholar] [CrossRef]
  64. Platero, C.; Pineda-Pardo, J. Temporal ordering of cognitive impairment in Parkinson’s disease patients based on disease progression models. Park. Relat. Disord. 2024, 129, 107184. [Google Scholar] [CrossRef]
  65. Ostertag, C.; Visani, M.; Urruty, T.; Beurton-Aimar, M. Long-term cognitive decline prediction based on multi-modal data using Multimodal3DSiameseNet: Transfer learning from Alzheimer’s disease to Parkinson’s disease. Int. J. Comput. Assist. Radiol. Surg. 2023, 18, 809–818. [Google Scholar] [CrossRef]
  66. Wang, Y.; Ning, H.; Ren, J.; Pan, C.; Yu, M.; Xue, C.; Wang, X.; Zhou, G.; Chen, Y.; Liu, W. Integrated Clinical Features with Plasma and Multi-modal Neuroimaging Biomarkers to Diagnose Mild Cognitive Impairment in Early Drug-Naive Parkinson’s Disease. ACS Chem. Neurosci. 2022, 13, 3523–3533. [Google Scholar] [CrossRef]
  67. Gorji, A.; Fathi Jouzdani, A. Machine learning for predicting cognitive decline within five years in Parkinson’s disease: Comparing cognitive assessment scales with DAT SPECT and clinical biomarkers. PLoS ONE 2024, 19, e0304355. [Google Scholar] [CrossRef] [PubMed]
  68. Aarsland, D.; Batzu, L.; Halliday, G.M.; Geurtsen, G.J.; Ballard, C.; Ray Chaudhuri, K.; Weintraub, D. Parkinson disease-associated cognitive impairment. Nat. Rev. Dis. Primers 2021, 7, 47. [Google Scholar] [CrossRef]
  69. Aarsland, D.; Creese, B.; Politis, M.; Chaudhuri, K.R.; Ffytche, D.H.; Weintraub, D.; Ballard, C. Cognitive decline in Parkinson disease. Nat. Rev. Neurol. 2017, 13, 217–231. [Google Scholar] [CrossRef] [PubMed]
  70. Crump, C.; Sundquist, J.; Sieh, W.; Sundquist, K. Risk of Alzheimer’s Disease and Related Dementias in Persons with Glaucoma: A National Cohort Study. Ophthalmology 2024, 131, 302–309. [Google Scholar] [CrossRef] [PubMed]
  71. Rahmati, M.; Smith, L.; Lee, H.; Boyer, L.; Fond, G.; Yon, D.K.; Lee, H.; Soysal, P.; Udeh, R.; Dolja-Gore, X.; et al. Associations between vision impairment and eye diseases with dementia, dementia subtypes and cognitive impairment: An umbrella review. Ageing Res. Rev. 2024, 101, 102523. [Google Scholar] [CrossRef]
  72. Takayanagi, Y.; Kadoh, Y.; Sasaki, J.; Obana, A.; Tanito, M. Association between Skin Carotenoid Levels and Cognitive Impairment Screened by Mini-Cog in Patients with Glaucoma. Curr. Issues Mol. Biol. 2024, 46, 6940–6950. [Google Scholar] [CrossRef]
  73. Kadoh, Y.; Takayanagi, Y.; Sasaki, J.; Tanito, M. Fingertip-Measured Skin Carotenoids and Advanced Glycation End Product Levels in Glaucoma. Antioxidants 2022, 11, 1138. [Google Scholar] [CrossRef]
  74. Wang, X.; Chen, W.; Zhao, W.; Miao, M. Risk of glaucoma to subsequent dementia or cognitive impairment: A systematic review and meta-analysis. Aging Clin. Exp. Res. 2024, 36, 172. [Google Scholar] [CrossRef] [PubMed]
  75. Lee, C.S.; Larson, E.B.; Gibbons, L.E.; Lee, A.Y.; McCurry, S.M.; Bowen, J.D.; McCormick, W.C.; Crane, P.K. Associations between recent and established ophthalmic conditions and risk of Alzheimer’s disease. Alzheimers Dement. 2019, 15, 34–41. [Google Scholar] [CrossRef]
  76. Chatterjee, P.; Pedrini, S.; Doecke, J.D.; Thota, R.; Villemagne, V.L.; Doré, V.; Singh, A.K.; Wang, P.; Rainey-Smith, S.; Fowler, C.; et al. Plasma Aβ42/40 ratio, p-tau181, GFAP, and NfL across the Alzheimer’s disease continuum: A cross-sectional and longitudinal study in the AIBL cohort. Alzheimers Dement. 2023, 19, 1117–1134. [Google Scholar] [CrossRef]
  77. Park, M.K.; Ahn, J.; Kim, Y.J.; Lee, J.W.; Lee, J.C.; Hwang, S.J.; Kim, K.C. Predicting Longitudinal Cognitive Decline and Alzheimer’s Conversion in Mild Cognitive Impairment Patients Based on Plasma Biomarkers. Cells 2024, 13, 1085. [Google Scholar] [CrossRef] [PubMed]
  78. Ossenkoppele, R.; Salvadó, G.; Janelidze, S.; Pichet Binette, A.; Bali, D.; Karlsson, L.; Palmqvist, S.; Mattsson-Carlgren, N.; Stomrud, E.; Therriault, J.; et al. Plasma p-tau217 and tau-PET predict future cognitive decline among cognitively unimpaired individuals: Implications for clinical trials. Nat. Aging 2025, 5, 883–896. [Google Scholar] [CrossRef] [PubMed]
  79. Pichet Binette, A.; Palmqvist, S.; Bali, D.; Farrar, G.; Buckley, C.J.; Wolk, D.A.; Zetterberg, H.; Blennow, K.; Janelidze, S.; Hansson, O. Combining plasma phospho-tau and accessible measures to evaluate progression to Alzheimer’s dementia in mild cognitive impairment patients. Alzheimers Res. Ther. 2022, 14, 46. [Google Scholar] [CrossRef]
  80. Huang, K.L.; Hsiao, I.T.; Huang, C.W.; Huang, C.G.; Chang, H.I.; Huang, S.H.; Lin, K.J.; Ma, M.C.; Huang, C.C.; Chang, C.C. The Taiwan-ADNI workflow toward integrating plasma p-tau217 into prediction models for the risk of Alzheimer’s disease and tau burden. Alzheimers Dement. 2025, 21, e14297. [Google Scholar] [CrossRef]
  81. Vermeulen, R.J.; Andersson, V.; Banken, J.; Hannink, G.; Govers, T.M.; Rovers, M.M.; Rikkert, M. Limited generalizability and high risk of bias in multivariable models predicting conversion risk from mild cognitive impairment to dementia: A systematic review. Alzheimers Dement. 2025, 21, e70069. [Google Scholar] [CrossRef]
  82. Wang, X.; Zhou, S.; Ye, N.; Li, Y.; Zhou, P.; Chen, G.; Hu, H. Predictive models of Alzheimer’s disease dementia risk in older adults with mild cognitive impairment: A systematic review and critical appraisal. BMC Geriatr. 2024, 24, 531. [Google Scholar] [CrossRef] [PubMed]
  83. Losinski, G.M.; Key, M.N.; Vidoni, E.D.; Clutton, J.; Morris, J.K.; Burns, J.M.; Watts, A. APOE4 and chronic health risk factors are associated with sex-specific preclinical Alzheimer’s disease neuroimaging biomarkers. Front. Glob. Womens Health 2025, 6, 1531062. [Google Scholar] [CrossRef] [PubMed]
  84. Rahman, A.; Schelbaum, E.; Hoffman, K.; Diaz, I.; Hristov, H.; Andrews, R.; Jett, S.; Jackson, H.; Lee, A.; Sarva, H.; et al. Sex-driven modifiers of Alzheimer risk: A multimodality brain imaging study. Neurology 2020, 95, e166–e178. [Google Scholar] [CrossRef] [PubMed]
  85. Ding, H.; Mandapati, A.; Hamel, A.P.; Karjadi, C.; Ang, T.F.A.; Xia, W.; Au, R.; Lin, H. Multimodal Machine Learning for 10-Year Dementia Risk Prediction: The Framingham Heart Study. J. Alzheimers Dis. 2023, 96, 277–286. [Google Scholar] [CrossRef]
  86. Wang, J.; Knol, M.J.; Tiulpin, A.; Dubost, F.; de Bruijne, M.; Vernooij, M.W.; Adams, H.H.H.; Ikram, M.A.; Niessen, W.J.; Roshchupkin, G.V. Gray Matter Age Prediction as a Biomarker for Risk of Dementia. Proc. Natl. Acad. Sci. USA 2019, 116, 21213–21218. [Google Scholar] [CrossRef]
  87. Braff, D.L. The importance of endophenotypes in schizophrenia research. Schizophr. Res. 2015, 163, 1–8. [Google Scholar] [CrossRef]
  88. Greenwood, T.A.; Shutes-David, A.; Tsuang, D.W. Endophenotypes in Schizophrenia: Digging Deeper to Identify Genetic Mechanisms. J. Psychiatry Brain Sci. 2019, 4, e190005. [Google Scholar] [CrossRef]
  89. Liu, Z.; Palaniyappan, L.; Wu, X.; Zhang, K.; Du, J.; Zhao, Q.; Xie, C.; Tang, Y.; Su, W.; Wei, Y.; et al. Resolving heterogeneity in schizophrenia through a novel systems approach to brain structure: Individualized structural covariance network analysis. Mol. Psychiatry 2021, 26, 7719–7731. [Google Scholar] [CrossRef]
  90. Owens, E.M.; Bachman, P.; Glahn, D.C.; Bearden, C.E. Electrophysiological Endophenotypes for Schizophrenia. Harv. Rev. Psychiatry 2016, 24, 129–147. [Google Scholar] [CrossRef]
  91. Martos, D.; Lőrinczi, B.; Szatmári, I.; Vécsei, L.; Tanaka, M. Decoupling Behavioral Domains via Kynurenic Acid Analog Optimization: Implications for Schizophrenia and Parkinson’s Disease Therapeutics. Cells 2025, 14, 973. [Google Scholar] [CrossRef]
  92. Figueiredo Godoy, A.C.; Frota, F.F.; Araújo, L.P.; Valenti, V.E.; Pereira, E.; Detregiachi, C.R.P.; Galhardi, C.M.; Caracio, F.C.; Haber, R.S.A.; Fornari Laurindo, L.; et al. Neuroinflammation and Natural Antidepressants: Balancing Fire with Flora. Biomedicines 2025, 13, 1129. [Google Scholar] [CrossRef]
  93. Mekala, A.; Qiu, H. Interplay Between Vascular Dysfunction and Neurodegenerative Pathology: New Insights into Molecular Mechanisms and Management. Biomolecules 2025, 15, 712. [Google Scholar] [CrossRef]
  94. Tarantini, S.; Tran, C.H.T.; Gordon, G.R.; Ungvari, Z.; Csiszar, A. Impaired neurovascular coupling in aging and Alzheimer’s disease: Contribution of astrocyte dysfunction and endothelial impairment to cognitive decline. Exp. Gerontol. 2017, 94, 52–58. [Google Scholar] [CrossRef]
  95. Duong, M.T.; Nasrallah, I.M.; Wolk, D.A.; Chang, C.C.Y.; Chang, T.Y. Cholesterol, Atherosclerosis, and APOE in Vascular Contributions to Cognitive Impairment and Dementia (VCID): Potential Mechanisms and Therapy. Front. Aging Neurosci. 2021, 13, 647990. [Google Scholar] [CrossRef] [PubMed]
  96. Rundek, T.; Tolea, M.; Ariko, T.; Fagerli, E.A.; Camargo, C.J. Vascular Cognitive Impairment (VCI). Neurotherapeutics 2022, 19, 68–88. [Google Scholar] [CrossRef] [PubMed]
  97. Steenland, K.; Karnes, C.; Seals, R.; Carnevale, C.; Hermida, A.; Levey, A. Late-life depression as a risk factor for mild cognitive impairment or Alzheimer’s disease in 30 US Alzheimer’s disease centers. J. Alzheimers Dis. 2012, 31, 265–275. [Google Scholar] [CrossRef]
  98. Wang, S.M.; Han, K.D.; Kim, N.Y.; Um, Y.H.; Kang, D.W.; Na, H.R.; Lee, C.U.; Lim, H.K. Late-life depression, subjective cognitive decline, and their additive risk in incidence of dementia: A nationwide longitudinal study. PLoS ONE 2021, 16, e0254639. [Google Scholar] [CrossRef] [PubMed]
  99. Linnemann, C.; Lang, U.E. Pathways Connecting Late-Life Depression and Dementia. Front. Pharmacol. 2020, 11, 279. [Google Scholar] [CrossRef]
  100. Huang, Y.Y.; Gan, Y.H.; Yang, L.; Cheng, W.; Yu, J.T. Depression in Alzheimer’s Disease: Epidemiology, Mechanisms, and Treatment. Biol. Psychiatry 2024, 95, 992–1005. [Google Scholar] [CrossRef]
  101. Tanaka, M.; Battaglia, S. Dualistic Dynamics in Neuropsychiatry: From Monoaminergic Modulators to Multiscale Biomarker Maps. Biomedicines 2025, 13, 1456. [Google Scholar] [CrossRef]
  102. Invernizzi, S.; Simoes Loureiro, I.; Kandana Arachchige, K.G.; Lefebvre, L. Late-Life Depression, Cognitive Impairment, and Relationship with Alzheimer’s Disease. Dement. Geriatr. Cogn. Disord. 2021, 50, 414–424. [Google Scholar] [CrossRef]
  103. Galts, C.P.C.; Bettio, L.E.B.; Jewett, D.C.; Yang, C.C.; Brocardo, P.S.; Rodrigues, A.L.S.; Thacker, J.S.; Gil-Mohapel, J. Depression in neurodegenerative diseases: Common mechanisms and current treatment options. Neurosci. Biobehav. Rev. 2019, 102, 56–84. [Google Scholar] [CrossRef] [PubMed]
  104. Szabó, Á.; Galla, Z.; Spekker, E.; Martos, D.; Szűcs, M.; Fejes-Szabó, A.; Fehér, Á.; Takeda, K.; Ozaki, K.; Inoue, H.; et al. Behavioral Balance in Tryptophan Turmoil: Regional Metabolic Rewiring in Kynurenine Aminotransferase II Knockout Mice. Cells 2025, 14, 1711. [Google Scholar] [CrossRef] [PubMed]
  105. Chou, Y.H.; Sundman, M.; Ton That, V.; Green, J.; Trapani, C. Cortical excitability and plasticity in Alzheimer’s disease and mild cognitive impairment: A systematic review and meta-analysis of transcranial magnetic stimulation studies. Ageing Res. Rev. 2022, 79, 101660. [Google Scholar] [CrossRef]
  106. McMackin, R.; Muthuraman, M.; Groppa, S.; Babiloni, C.; Taylor, J.P.; Kiernan, M.C.; Nasseroleslami, B.; Hardiman, O. Measuring network disruption in neurodegenerative diseases: New approaches using signal analysis. J. Neurol. Neurosurg. Psychiatry 2019, 90, 1011–1020. [Google Scholar] [CrossRef]
  107. Sanchez, E.; Coughlan, G.T.; Wilkinson, T.; Ramirez, J.; Mirza, S.S.; Baril, A.A.; Dilliott, A.A.; Frank, A.; Lang, A.E.; Hassan, A.; et al. Association of Plasma Biomarkers with Longitudinal Atrophy and Microvascular Burden on MRI Across Neurodegenerative and Cerebrovascular Diseases. Neurology 2025, 104, e213438. [Google Scholar] [CrossRef]
  108. Giacomucci, G.; Mazzeo, S.; Bagnoli, S.; Ingannato, A.; Leccese, D.; Berti, V.; Padiglioni, S.; Galdo, G.; Ferrari, C.; Sorbi, S.; et al. Plasma neurofilament light chain as a biomarker of Alzheimer’s disease in Subjective Cognitive Decline and Mild Cognitive Impairment. J. Neurol. 2022, 269, 4270–4280. [Google Scholar] [CrossRef] [PubMed]
  109. Ebenau, J.L.; Pelkmans, W.; Verberk, I.M.W.; Verfaillie, S.C.J.; van den Bosch, K.A.; van Leeuwenstijn, M.; Collij, L.E.; Scheltens, P.; Prins, N.D.; Barkhof, F.; et al. Association of CSF, Plasma, and Imaging Markers of Neurodegeneration with Clinical Progression in People with Subjective Cognitive Decline. Neurology 2022, 98, e1315–e1326. [Google Scholar] [CrossRef]
  110. Xie, L.; Das, S.R.; Wisse, L.E.M.; Ittyerah, R.; de Flores, R.; Shaw, L.M.; Yushkevich, P.A.; Wolk, D.A. Baseline structural MRI and plasma biomarkers predict longitudinal structural atrophy and cognitive decline in early Alzheimer’s disease. Alzheimers Res. Ther. 2023, 15, 79. [Google Scholar] [CrossRef]
  111. Mengel, D.; Soter, E.; Ott, J.M.; Wacker, M.; Leyva, A.; Peters, O.; Hellmann-Regen, J.; Schneider, L.-S.; Wang, X.; Priller, J. Blood biomarkers confirm subjective cognitive decline (SCD) as a distinct molecular and clinical stage within the NIA-AA framework of Alzheimer’ s disease. Mol. Psychiatry 2025, 30, 3150–3159. [Google Scholar] [CrossRef] [PubMed]
  112. Jenkins, T.M.; Alix, J.J.P.; Fingret, J.; Esmail, T.; Hoggard, N.; Baster, K.; McDermott, C.J.; Wilkinson, I.D.; Shaw, P.J. Longitudinal multi-modal muscle-based biomarker assessment in motor neuron disease. J. Neurol. 2020, 267, 244–256. [Google Scholar] [CrossRef]
  113. Manuel, M.G.; Tamba, B.I.; Leclere, M.; Mabrouk, M.; Schreiner, T.G.; Ciobanu, R.; Cristina, T.Z. Intrathecal Pseudodelivery of Drugs in the Therapy of Neurodegenerative Diseases: Rationale, Basis and Potential Applications. Pharmaceutics 2023, 15, 768. [Google Scholar] [CrossRef]
  114. Bennett, C.F.; Krainer, A.R.; Cleveland, D.W. Antisense Oligonucleotide Therapies for Neurodegenerative Diseases. Annu. Rev. Neurosci. 2019, 42, 385–406. [Google Scholar] [CrossRef]
  115. Fowler, M.J.; Cotter, J.D.; Knight, B.E.; Sevick-Muraca, E.M.; Sandberg, D.I.; Sirianni, R.W. Intrathecal drug delivery in the era of nanomedicine. Adv. Drug Deliv. Rev. 2020, 165, 77–95. [Google Scholar] [CrossRef]
  116. Dhariwal, R.; Jain, M.; Mir, Y.R.; Singh, A.; Jain, B.; Kumar, P.; Tariq, M.; Verma, D.; Deshmukh, K.; Yadav, V.K.; et al. Targeted drug delivery in neurodegenerative diseases: The role of nanotechnology. Front. Med. 2025, 12, 1522223. [Google Scholar] [CrossRef] [PubMed]
  117. Schmitz, N.; Abdelmageed, M.M.; Monine, M.; Xu, Y. Trends in First-in-Human Studies for Intrathecal Antisense Oligonucleotides: Insights from 2010 to 2024. J. Clin. Pharmacol. 2025, 65, 1065–1075. [Google Scholar] [CrossRef]
  118. Han, K.; Liu, J.; Tang, Z.; Su, W.; Liu, Y.; Lu, H.; Zhang, H. Effects of excitatory transcranial magnetic stimulation over the different cerebral hemispheres dorsolateral prefrontal cortex for post-stroke cognitive impairment: A systematic review and meta-analysis. Front. Neurosci. 2023, 17, 1102311. [Google Scholar] [CrossRef] [PubMed]
  119. Begemann, M.J.; Brand, B.A.; Ćurčić-Blake, B.; Aleman, A.; Sommer, I.E. Efficacy of non-invasive brain stimulation on cognitive functioning in brain disorders: A meta-analysis. Psychol. Med. 2020, 50, 2465–2486. [Google Scholar] [CrossRef]
  120. Battaglia, S.; Fazio, C.D.; Borgomaneri, S.; Avenanti, A. Cortisol Imbalance and Fear Learning in PTSD: Therapeutic Approaches to Control Abnormal Fear Responses. Curr. Neuropharmacol. 2025, 23, 835–846. [Google Scholar] [CrossRef]
  121. Fisicaro, F.; Lanza, G.; Grasso, A.A.; Pennisi, G.; Bella, R.; Paulus, W.; Pennisi, M. Repetitive transcranial magnetic stimulation in stroke rehabilitation: Review of the current evidence and pitfalls. Ther. Adv. Neurol. Disord. 2019, 12, 1756286419878317. [Google Scholar] [CrossRef]
  122. Yang, C.; Zhang, T.; Huang, K.; Xiong, M.; Liu, H.; Wang, P.; Zhang, Y. Increased both cortical activation and functional connectivity after transcranial direct current stimulation in patients with post-stroke: A functional near-infrared spectroscopy study. Front. Psychiatry 2022, 13, 1046849. [Google Scholar] [CrossRef]
  123. Hill, A.T.; Rogasch, N.C.; Fitzgerald, P.B.; Hoy, K.E. Effects of single versus dual-site High-Definition transcranial direct current stimulation (HD-tDCS) on cortical reactivity and working memory performance in healthy subjects. Brain Stimul. 2018, 11, 1033–1043. [Google Scholar] [CrossRef]
  124. Jaekel, A.K.; Watzek, J.; Nielsen, J.; Butscher, A.L.; Zöhrer, P.; Schmitz, F.; Kirschner-Hermanns, R.K.M.; Knüpfer, S.C. Neurogenic Lower Urinary Tract Symptoms, Fatigue, and Depression-Are There Correlations in Persons with Multiple Sclerosis? Biomedicines 2023, 11, 2193. [Google Scholar] [CrossRef]
  125. Polacchini, A.; Metelli, G.; Francavilla, R.; Baj, G.; Florean, M.; Mascaretti, L.G.; Tongiorgi, E. A method for reproducible measurements of serum BDNF: Comparison of the performance of six commercial assays. Sci. Rep. 2015, 5, 17989. [Google Scholar] [CrossRef] [PubMed]
  126. Brum, W.S.; Cullen, N.C.; Janelidze, S.; Ashton, N.J.; Zimmer, E.R.; Therriault, J.; Benedet, A.L.; Rahmouni, N.; Tissot, C.; Stevenson, J.; et al. A two-step workflow based on plasma p-tau217 to screen for amyloid β positivity with further confirmatory testing only in uncertain cases. Nat. Aging 2023, 3, 1079–1090. [Google Scholar] [CrossRef]
  127. Therriault, J.; Brum, W.S.; Trudel, L.; Macedo, A.C.; Bitencourt, F.V.; Martins-Pfeifer, C.C.; Nakouzi, M.; Pola, I.; Wong, M.; Kac, P.R.; et al. Blood phosphorylated tau for the diagnosis of Alzheimer’s disease: A systematic review and meta-analysis. Lancet Neurol. 2025, 24, 740–752. [Google Scholar] [CrossRef]
  128. Palmqvist, S.; Warmenhoven, N.; Anastasi, F.; Pilotto, A.; Janelidze, S.; Tideman, P.; Stomrud, E.; Mattsson-Carlgren, N.; Smith, R.; Ossenkoppele, R.; et al. Plasma phospho-tau217 for Alzheimer’s disease diagnosis in primary and secondary care using a fully automated platform. Nat. Med. 2025, 31, 2036–2043. [Google Scholar] [CrossRef] [PubMed]
  129. Teunissen, C.E.; Kolster, R.; Triana-Baltzer, G.; Janelidze, S.; Zetterberg, H.; Kolb, H.C. Plasma p-tau immunoassays in clinical research for Alzheimer’s disease. Alzheimers Dement. 2025, 21, e14397. [Google Scholar] [CrossRef]
  130. Birkenbihl, C.; Emon, M.A.; Vrooman, H.; Westwood, S.; Lovestone, S.; Hofmann-Apitius, M.; Fröhlich, H. Differences in cohort study data affect external validation of artificial intelligence models for predictive diagnostics of dementia—Lessons for translation into clinical practice. EPMA J. 2020, 11, 367–376. [Google Scholar] [CrossRef] [PubMed]
  131. Therriault, J.; Ashton, N.J.; Pola, I.; Triana-Baltzer, G.; Brum, W.S.; Di Molfetta, G.; Arslan, B.; Rahmouni, N.; Tissot, C.; Servaes, S.; et al. Comparison of two plasma p-tau217 assays to detect and monitor Alzheimer’s pathology. EBioMedicine 2024, 102, 105046. [Google Scholar] [CrossRef]
  132. Sun, Y.M.; Wang, Z.Y.; Liang, Y.Y.; Hao, C.W.; Shi, C.H. Digital biomarkers for precision diagnosis and monitoring in Parkinson’s disease. NPJ Digit. Med. 2024, 7, 218. [Google Scholar] [CrossRef] [PubMed]
  133. Dutta, S.; Hornung, S.; Kruayatidee, A.; Maina, K.N.; Del Rosario, I.; Paul, K.C.; Wong, D.Y.; Duarte Folle, A.; Markovic, D.; Palma, J.A.; et al. α-Synuclein in blood exosomes immunoprecipitated using neuronal and oligodendroglial markers distinguishes Parkinson’s disease from multiple system atrophy. Acta Neuropathol. 2021, 142, 495–511. [Google Scholar] [CrossRef] [PubMed]
  134. Paganoni, S.; Berry, J.D.; Quintana, M.; Macklin, E.; Saville, B.R.; Detry, M.A.; Chase, M.; Sherman, A.V.; Yu, H.; Drake, K.; et al. Adaptive Platform Trials to Transform Amyotrophic Lateral Sclerosis Therapy Development. Ann. Neurol. 2022, 91, 165–175. [Google Scholar] [CrossRef]
  135. Battaglia, S.; Andero, R.; Thayer, J.F. Translational cross-species evidence of heart-related dynamics in threat learning. Neurosci. Biobehav. Rev. 2025, 176, 106273. [Google Scholar] [CrossRef]
  136. Taranu, D.; Tumani, H.; Holbrook, J.; Tumani, V.; Uttner, I.; Fissler, P. The TRACK-MS Test Battery: A Very Brief Tool to Track Multiple Sclerosis-Related Cognitive Impairment. Biomedicines 2022, 10, 2975. [Google Scholar] [CrossRef]
  137. Tanaka, M.; He, Z.; Han, S.; Battaglia, S. Editorial: Noninvasive brain stimulation: A promising approach to study and improve emotion regulation. Front. Behav. Neurosci. 2025, 19, 1633936. [Google Scholar] [CrossRef] [PubMed]
Table 1. Corridors for early dementia pathways. This table organizes the Special Issue contributions along three translational corridors—Detection and Stratification, Mechanistic Anchors, and Intervention and Delivery—highlighting how each compresses the path from diagnosis to mechanism-informed care.
Table 1. Corridors for early dementia pathways. This table organizes the Special Issue contributions along three translational corridors—Detection and Stratification, Mechanistic Anchors, and Intervention and Delivery—highlighting how each compresses the path from diagnosis to mechanism-informed care.
CorridorSub-domainStudy/Paper (Short)Population/ContextModality/ApproachPrimary ContributionRef.
3.1. Detection and StratificationPhenotypic triage instrumentsTRACK-MS bedside screenMSBrief cognitive batteryHigher sensitivity/specificity for early MS cognitive impairment → rapid case finding/referral[32]
LBD minor visual phenomena (MVP)LBDSymptom questionnaire/synthesisValidates brief visual queries as early discriminants preceding syndromic expression[33]
Biomarker rule-in/rule-outPlasma p-tau217AD (primary/secondary care)Blood biomarker (automated platforms)Strong CSF/PET correlations; two-cutoff triage improves accuracy and scalability[39]
Variant-carrier dementia modelFamilial dementia clinicClinical risk model for geneticsPredicts carriage of pathogenic/likely pathogenic variants to target sequencing/counseling[40]
Algorithmic risk integrationML for PD cognitive declinePDRF using clinical + blood markersHigh discrimination for early decline; pragmatic pipeline for intensified monitoring[41]
Cross-domain signalsGlaucoma–cognition interfacePOAG and exfoliation glaucomaNeuro-ophthalmic/cognitive profilingIdentifies glaucoma-linked cognitive burden and screening “who/when” cues[42]
3.2. Mechanistic AnchorsCircuit-level endophenotypesMood-linked deficits in SCZSCZStructural MRI, systems/circuit readoutsMaps anatomy tied to affective symptoms; endophenotype bridge to mechanisms[43]
Systems biology axesHallmarks of brain plasticityCross-diagnosticConceptual/mechanistic synthesisOperational scaffold of plasticity (synaptic, glial–neuronal, metabolic, structural)[44]
Vascular–muscle–cognition couplingAging/cognitive declineVascular and sarcopenia metricsTriad linking vascular impairment, muscle atrophy, and cognitive loss; clinical hooks[45]
Affective staging continuumDepression vs. neurodegenerationLate-life and prodromal statesScoping synthesisPositions depression as risk/prodrome/consequence; emphasizes longitudinal designs[46]
3.3. Intervention and DeliveryRoute-of-delivery innovationIntrathecal neurotherapeuticsNeurodegenerationCSF delivery science/devicesDefines indications, CSF dynamics limits, and device/nanomedicine gaps[47]
Targeted neuromodulation mappingTMS/tDCS × molecular change × tasksPost-ischemic cognitive recoveryNIBS with task couplingParameterized, mechanism-guided protocols; connectivity/plasticity bridges[48]
Symptom network → target translationMS urodynamics → fatigue/depression careMSUrodynamics + symptom networksUrodynamic abnormalities predict fatigue; integrates bladder, exercise, mood care[49]
Peripheral proxy biomarkersPlatelet BDNF in ASDAutism (adults)Platelet/serum BDNFLinks intra-platelet BDNF to symptom burden; flags assay/processing pitfalls[50]
AD, Alzheimer’s disease; ASD, autism spectrum disorder; BDNF, brain-derived neurotrophic factor; CSF, cerebrospinal fluid; LBD, Lewy body disease; ML, machine learning; MRI, magnetic resonance imaging; MS, multiple sclerosis; MVP, minor visual phenomena; NIBS, non-invasive brain stimulation; PD, Parkinson’s disease; PET, positron emission tomography; POAG, primary open-angle glaucoma; p-tau217, phosphorylated tau at threonine 217; RF, random forest; SCZ, schizophrenia; tDCS, transcranial direct current stimulation; TMS, transcranial magnetic stimulation; TRACK-MS, Tracking Assessment of Cognition in Multiple Sclerosis.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Battaglia, S.; Tanaka, M. Screen, Sample, Stratify: Biomarkers and Machine Learning Compress Dementia Pathways. Biomedicines 2026, 14, 159. https://doi.org/10.3390/biomedicines14010159

AMA Style

Battaglia S, Tanaka M. Screen, Sample, Stratify: Biomarkers and Machine Learning Compress Dementia Pathways. Biomedicines. 2026; 14(1):159. https://doi.org/10.3390/biomedicines14010159

Chicago/Turabian Style

Battaglia, Simone, and Masaru Tanaka. 2026. "Screen, Sample, Stratify: Biomarkers and Machine Learning Compress Dementia Pathways" Biomedicines 14, no. 1: 159. https://doi.org/10.3390/biomedicines14010159

APA Style

Battaglia, S., & Tanaka, M. (2026). Screen, Sample, Stratify: Biomarkers and Machine Learning Compress Dementia Pathways. Biomedicines, 14(1), 159. https://doi.org/10.3390/biomedicines14010159

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop