Search Results (981)

Coastal reclaimed polders with shallow saline groundwater support intensive greenhouse horticulture but require timely diagnosis of root-zone water and salinity conditions. This study developed a compact Internet-of-Things (IoT) monitoring system based on the M5Stamp Pico microcontroller to acquire SDI-12 soil-sensor data, buffer records locally, and transfer them to a low-cost cloud dashboard. Outside-greenhouse validation showed high operational reliability, with a missing observation rate of only 0.9%, and acceptable agreement with a reference TDR100 for both volumetric water content (θ) and bulk electrical conductivity (EC_b). The system was then applied to ridge-position monitoring in a commercial pepper greenhouse on a coastal reclaimed polder. The ridge records captured depth-dependent infiltration and salinity redistribution under drip irrigation, together with contrasting responses between the cultivated layer and shallow groundwater. Potential-based interpretation indicated that the monitored ridge root zone was often not strongly limited by matric potential, whereas osmotic potential derived from pore-water salinity showed reduced water availability even when the soil remained relatively wet. These results demonstrate that continuous real-time monitoring at the ridge position can support diagnosis of root-zone stress and provide useful information for irrigation and fertigation management in salt-affected greenhouse soils. Full article

The deployment of Deep Learning (DL) for anomaly detection in Industrial IoT (IIoT) is critically hampered by the non-stationary nature of industrial data streams and the lack of forensic-grade explainability. This systematic review synthesizes 48 peer-reviewed studies (2021–2025) to quantify the performance collapse of static models under concept drift and to establish operational criteria distinguishing post hoc feature attribution (Type A XAI) from forensic root-cause diagnosis (Type B XAI). Our analysis reveals three critical findings: (1) static DL models suffer a 15–22% F1-score degradation across wastewater, manufacturing, and energy sectors when deployed in non-stationary environments, rendering them operationally non-viable without continuous adaptation; (2) the current literature remains saturated with Type A explainability (80% of corpus through 2023), creating a Forensic Gap where operators receive statistical correlations but lack actionable maintenance directives; and (3) emerging 2024–2025 research marks a paradigm shift toward Type B methodologies, yet no unified framework bridges real-time detection with deep causal reasoning. To address these gaps, we contribute the following: (1) a validated operational taxonomy (Cohen’s $\kappa =0.84$) with reproducible five-criterion rubric enabling forensic XAI classification; (2) the first quantitative synthesis of drift penalties in industrial deployments; and (3) a three-tier Edge-Cloud Forensic XAI architecture that achieves 70% communication payload reduction via compressed latent vectors while integrating tnGAN-based data imputation (handling 20–30% missing data) and physics-guided causal reasoning engines. Our framework decouples millisecond-level edge detection from 1–3 s cloud-based forensic diagnosis, ensuring both operational responsiveness and actionable industrial insight. We conclude that the future of safety-critical IIoT demands “Forensic-by-Design” architectures leveraging machine unlearning for drift adaptation and LLM-based natural language interfaces for operator-facing explanations, positioning Industry 5.0 to bridge the gap between algorithmic detection and human-centered decision support. Full article

Background/Objectives: Heart failure (HF) remains a major cause of global mortality and morbidity; it is, therefore, of paramount importance that diagnosis and prognostication are made timely in order to better improve outcomes and reduce healthcare expenditure. This research presents a novel predictive model of heart failure that combines clinical criteria with demographic factors in order to maximize predictive performance and act as a reliable tool for individualized healthcare intervention. Methods: Complex machine learning techniques, including decision trees, random forest, and deep learning, are applied in analyzing a large dataset of subjects with heart failure. We collected a diverse dataset comprising clinical indicators such as echocardiographic data, biomarkers, electrocardiogram (ECG) features, and demographic information. Data preprocessing techniques, such as feature normalization and handling of missing values, were applied to ensure the integrity and reliability of the dataset. Results: The results indicate that integrating both clinical indicators and demographic characteristics significantly improves the predictive power of the model, compared to models based on clinical indicators alone. Specifically, the hybrid model demonstrated a superior ability to predict short- and long-term outcomes in heart failure patients, offering enhanced accuracy in risk stratification and prognosis prediction. Conclusions: This research highlights the potential of artificial intelligence (AI) and machine learning in revolutionizing heart failure care by providing healthcare professionals with more accurate, data-driven decision support tools. The proposed model not only holds promise for clinical applications but also offers insights for future research into personalized medicine. Full article

Background: Rapid etiological diagnosis of bacterial meningitis is crucial in children, as delays can lead to neurological sequelae. The BioFire FilmArray Meningitis/Encephalitis (ME) panel is widely used on cerebrospinal fluid (CSF), but its target spectrum may miss healthcare-associated or multidrug-resistant pathogens. We evaluated the diagnostic performance and stewardship-oriented clinical impact of off-label BioFire FilmArray Blood Culture Identification 2 (BCID2) testing on CSF from pediatric patients with suspected bacterial CNS infection and negative ME results. Methods: We retrospectively analyzed CSF samples collected between January 2023 and March 2025 at a tertiary pediatric hospital. In ME-negative cases with persistent suspicion and abnormal CSF parameters, BCID2 was performed off-label on residual CSF aliquots after routine testing, without additional sampling. We assessed pathogen detection, agreement with culture, resistance-gene identification, and documented stewardship actions. Results: Among 76 ME-negative CSF samples tested with BCID2, 23 (30.3%) were positive, all involving organisms not included in the ME panel. BCID2 was concordant with culture in 19/23 cases (82.6%); 4/23 (17.4%) were BCID2-positive/culture-negative, consistent with reduced culture sensitivity in frequently pretreated cases. Resistance genes (VIM, vanA/B, CTX-M) were detected in 30.4% of BCID2-positive samples. Overall agreement with culture was 94.7% (PPA 100%, NPA 93.0%). Escalation was documented in 13/23 episodes (56.5%), discontinuation in 2/23 (8.7%), and confirmation in 9/23 (39.1%), with no de-escalation events; clinical outcomes were not systematically available. Conclusions: In selected ME-negative pediatric cases with abnormal CSF profiles, BCID2 testing on residual CSF provided rapid, clinically meaningful microbiological information that may support antimicrobial optimization. Full article

To address the challenges of low diagnostic accuracy of constrained primary frequency regulating (PFR) capacity for coal-fired units due to complex and strongly coupled restricting factors, an intelligent diagnosis method based on an improved snake optimizer-based multi-label random forest classification algorithm is proposed. By analyzing the factors restricting PFR capability, a set of characterization parameters and constraint factors for unit regulating capacity is established. The snake optimizer is enhanced by introducing dynamic update mechanisms and novel search strategies to improve its convergence speed and accuracy. The improved algorithm is then applied to optimize the hyperparameters of the multi-label random forest algorithm, enabling online diagnosis of PFR capacity limitations. Simulation results demonstrate that the proposed algorithm exhibits superior convergence performance, with lower medians of false alarm rate and missing alarm rate across all labels, coupled with reduced result dispersion compared to alternative algorithms. Tests on real operational data show an average false alarm rate of 0.029% and an average missing alarm rate of 0.053 for all labels. The results indicate that the proposed method is feasible and effective, enabling accurate online diagnosis of constrained PFR capacity of coal-fired units. Full article

Introduction: Giant retroperitoneal liposarcomas (GRPLs) are rare tumors that often reach considerable size before diagnosis due to their indolent growth and deep anatomical location. Surgery represents the only potentially curative treatment, yet recurrence rates remain high. While histological subtype is a recognized predictor of recurrence, the prognostic role of tumor size, particularly in giant tumors, remains controversial. This study evaluates the impact of tumor size and histological subtype on recurrence risk in a literature-based retrospective cohort. Materials and Methods: Data were extracted from a literature-based database of GRLPs published between 2004 and 2023. Only tumors >20 cm treated without positive surgical margins were included; patients receiving adjuvant therapy or with missing follow-up were excluded. Histological subtype (well-differentiated vs. other) was the main variable of interest. Recurrence-free survival (RFS) was defined as the primary endpoint and estimated using the Kaplan–Meier method. The association between histological subtype and recurrence risk was evaluated using a Cox proportional hazards model. A sensitivity analysis was performed to explore the potential interaction between tumor size and histological subtype. Results: Our final cohort yielded a total of 81 patients, of whom 47 (58%) had a well-differentiated GRLPs. The median tumor size was 38 cm and median follow-up was 16 months, with 24 recurrences observed. At 24 months, RFS was higher in well-differentiated tumors than in other histological subtypes (81% vs. 41%). In multivariable Cox analysis, histology was independently associated with recurrence risk (HR 3.2, 95% CI 1.28–8.17, p = 0.01), whereas tumor size showed no association with recurrence. Interaction analysis confirmed no differential effect of tumor size across histological subtypes. Conclusions: In this literature-based cohort of GRLPs treated with surgery, histological subtype independently predicted recurrence, whereas tumor size showed no prognostic value, either overall or within individual histological subtypes. Full article

Background/Objectives: Small-cell prostate cancer (SCPC) is a rare, aggressive variant of prostate cancer with poor prognosis, arising “de novo” or through lineage plasticity from conventional adenocarcinoma under androgen receptor-targeted therapies. Characterized by low PSA levels despite high tumor burden and visceral metastases, SCPC poses diagnostic challenges with conventional and PSMA-targeted imaging due to variable tracer uptake. This narrative review aims to evaluate the role of PET/CT tracers in clinical and preclinical settings for SCPC diagnosis, staging, and management. Methods: A systematic literature search was conducted on PubMed and Scopus up to December 2025 using terms “PET OR positron emission tomography AND prostate OR prostatic AND small-cell NOT non-small-cell”. Eight studies (five clinical, three preclinical) on the role of PET/CT imaging in SCPC were included and analyzed for study design, population, tracers, and findings, with comparative evaluation of diagnostic performance across PET tracers. Results: Clinical studies showed that ¹¹C-choline detects progression at low PSA but misses SCPC; ¹⁸F-FDG exhibited a high SUVmax value for distinguishing SCPC from adenocarcinomas with neuroendocrine differentiation, predicting poor survival; ⁶⁸Ga-DOTATATE identified NEPC/SCPC with promising prognostic/therapeutic value for selected cases. Preclinical models evaluated ⁸⁹Zr-tracers targeting DLL3 or CDCP1 (an antigen expressed in aggressive neuroendocrine tumours) and ¹⁸F-BnTP (a target of mitochondrial activity) in SCPC subtypes, focusing on translational imaging. Conclusions: From this review, although still based on limited literature evidence and mostly derived from retrospective and small SCPC sub-cohorts,¹⁸F-FDG PET/CT currently appears as the most reliable tracer for SCPC, aiding tumor detection and prognostication when PSMA/choline imaging fails. In the preclinical setting, DLL3/CDCP1-targeted agents emerge as promising theranostics tools. Multimodal imaging approach and prospective trials are needed for standardization and patient-based SCPC management. Full article

Accurate coronary artery segmentation is essential for diagnosis and interventional planning, but conventional U-shaped networks often miss thin, low-contrast vessels and break vessel continuity. We propose Inverted Pyramid-Shaped Multi-resolution U-Net (IPSM-UNet), a dual U-Net++ architecture with multi-resolution feature interaction, feature aggregation, and layer-wise deep supervision. The method is evaluated on DRIVE, CHASE_DB1, DCA1, and an internal coronary angiography dataset. IPSM-UNet achieves competitive or better performance across datasets, including F1 = 0.8310 and Acc = 0.9707 on DRIVE, Se = 0.8792 and Acc = 0.9745 on CHASE_DB1, F1 = 0.8043 and Acc = 0.9793 on DCA1, and Se = 0.8741, F1 = 0.8590, and Acc = 0.9879 on the internal dataset. IPSM-UNet improves vessel continuity and overall segmentation quality, particularly for small-caliber vessels, and supports downstream coronary analysis. Full article

The diagnosis of missing seedlings in high-density drill-seeded crops is often hindered by the strong coupling between visual perception and diagnostic rules, which leads to an irreversible cascade amplification of underlying missed detection errors. To address this dilemma, this paper proposes a “Perception–Topology” collaborative decoupling framework oriented toward row structure perception. In the perception phase, a row-structure-enhanced detection model (RS-YOLO) is constructed. It integrates Space-to-Depth (SPD) conversion, a Selective Frequency-domain Aggregation Module (SFAM), and a Row-Structure Attention Mechanism (RSM) to effectively suppress tire rut interference and explicitly reinforce the spatial topological priors of crops. In the diagnostic phase, an Adaptive Intra-row Gap Analysis (AIGA) algorithm is proposed. By utilizing a dynamic median intra-plant spacing scale and core canopy geometric pruning, this algorithm fundamentally reformulates missing seedling diagnosis into a physical interruption metric of one-dimensional graph connectivity. Evaluated on a finely reconstructed UAV-based sorghum imagery dataset, RS-YOLO achieved a significant improvement of 2.7% in precision and 3.2% in recall over the baseline model, providing a structure-aligned, high-confidence input for the diagnostic process. Based on this perceptual foundation, the AIGA algorithm ultimately achieved a diagnostic precision of 96.11% and a recall of 91.48% without the need for negative sample annotations. This framework effectively severs the propagation chain of perceptual errors, providing a noise-robust and highly physically interpretable new paradigm for the automated inspection of field population structures. Full article

Intelligent detection in modern manufacturing, healthcare, process industries, and structural monitoring is fundamentally enabled by heterogeneous sensor systems. Rather than being viewed as a purely image-centered recognition task, intelligent detection is more appropriately formulated as a sensor-driven state inference problem in which sensing physics, signal quality, temporal synchronization, modality availability, and deployment conditions jointly determine what can be reliably detected, localized, interpreted, and acted upon. Against this background, this review provides a structured synthesis of the field through three coupled dimensions, namely methods, systems, and governance, and organizes the literature around four recurring engineering components: signal unification, representation unification, alignment mechanisms, and robustness mechanisms. Using a structured review protocol with explicit source selection, screening, and study coding, the paper traces the methodological evolution from traditional feature-engineering and model-based pipelines to deep learning for visual, temporal, multimodal, generative, and mechanism-constrained sensing, and further to foundation-model-based and multimodal sensor intelligence. Cross-domain evidence is synthesized from industrial defect detection, fault diagnosis, remaining useful life prediction, non-destructive testing, structural health monitoring, medical lesion analysis, and process monitoring. The review argues that recent progress has substantially strengthened learned representations, multimodal interaction, and semantic extensibility, but has not removed persistent constraints arising from domain shift, missing modalities, calibration instability, privacy-preserving collaboration, and edge-side resource limits. Accordingly, the central challenge is no longer how to optimize isolated detection models, but how to build sensor-enabled intelligent systems that remain physically grounded, trustworthy, transferable, and maintainable under real operational conditions. On this basis, the paper concludes by identifying future directions in mechanism-aware modeling, trustworthy evaluation, missing-modality-robust multimodal systems, privacy-preserving cross-site collaboration, and edge-native lifecycle-aware deployment. Full article

Hemoptysis is a potentially life-threatening phenomenon with a wide range of underlying causes. While most episodes are linked to common conditions such as infections, malignancy, or pulmonary embolism, a proportion of cases are due to unusual and often unexpected etiologies. This narrative review summarizes published case reports, series, and observational studies describing rare causes of hemoptysis, including vascular malformations, congenital anomalies, benign tumors, systemic diseases, and unusual infections. These conditions are frequently overlooked, which may delay recognition and appropriate management. The reviewed examples highlight the variety of diagnostic challenges and the broad spectrum of therapeutic strategies that may be required, ranging from endovascular procedures and surgery to targeted medical therapy. Despite advances in diagnostic methods, a subset of patients remain classified as having idiopathic or cryptogenic hemoptysis. For this reason, clinicians should keep a broad differential diagnosis in mind and remain aware of rare but clinically important entities. Awareness of these uncommon presentations and individualized patient management are essential for improving outcomes and avoiding missed critical diagnoses. Full article

Retinopathy of Prematurity (ROP) affects preterm infants worldwide, involving abnormal development of retinal blood vessels associated with supplemental oxygen use in neonatal care. Although there have been strides in identifying at-risk infants, implementing early screening, updating disease criteria through the International Classification of Retinopathy of Prematurity (ICROP), and developing new therapies, ROP remains a leading cause of preventable blindness. As preterm birth survival rates rise, the incidence of ROP continues to increase and is projected to rise even in countries with abundant resources and well-established care programs. Improving ROP care requires global standardization of screening, diagnosis, and management to prevent missed diagnoses and minimize outcome variability. Intravitreal anti-vascular endothelial growth factor (VEGF) injections are changing the landscape of ROP management, but longitudinal research is needed to determine their long-term safety in preterm infants. Effective ROP management relies on teamwork across disciplines and open communication with parents. Given that parents are lifelong caregivers of a child who may be affected by ROP-related vision impairment, including them in the care team and encouraging psychosocial support is vital. Socioeconomic disparities and limited access to ROP-trained ophthalmologists exacerbate disease burden, underscoring the need for innovative solutions to improve access to care. This perspective emphasizes the importance of globally standardizing ROP prevention and care, noting that efforts are still incomplete, equitable access has not been realized, and the long-term role of anti-VEGF agents in ROP treatment remains unclear. Full article

Background and Clinical Significance: Alpha-1 antitrypsin deficiency (AATD) is an autosomal codominant disorder caused by pathogenic variants in the SERPINA1 gene, resulting in reduced circulating alpha-1 antitrypsin (AAT) or production of dysfunctional protein. AAT is the principal inhibitor of neutrophil elastase, and its deficiency leads to unchecked proteolytic activity, progressive destruction of lung parenchyma, and increased susceptibility to infections. Severe deficiency, particularly in individuals homozygous for the Z allele (PI*ZZ), predisposes to early-onset panacinar emphysema, chronic airflow obstruction, and liver disease. Despite its clinical relevance, AATD remains markedly underdiagnosed and is frequently misclassified as smoking-related chronic obstructive pulmonary disease (COPD), delaying access to disease-modifying therapy, genetic counselling, and preventive strategies. Early recognition is therefore essential to improve outcomes. Case Presentation: We report the case of a 68-year-old ex-smoker with a long-standing diagnosis of “COPD” who presented with acute-on-chronic type 2 respiratory failure and community-acquired pneumonia. Spirometry revealed severe airflow obstruction, and high-resolution computed tomography demonstrated extensive basilar panlobular emphysema, raising suspicion for AATD. Serum AAT concentration was critically low at 26.8 mg·dL⁻¹, and isoelectric focusing confirmed a PI*ZZ phenotype. Next-generation sequencing identified homozygosity for the SERPINA1 c.1096G>A (Z) variant, with no additional pathogenic alleles. Cascade family screening revealed multiple heterozygous PI*MZ relatives. Before augmentation therapy could be initiated, the patient developed severe Legionella pneumophila pneumonia with secondary bacterial superinfection, progressing to refractory septic shock and death. Conclusions: This case illustrates how AATD can masquerade as smoking-related COPD for years, leading to missed opportunities for timely intervention. It underscores the importance of testing all adults with COPD or refractory asthma at least once, regardless of age or smoking history. Early diagnosis enables initiation of augmentation therapy, targeted vaccination, lifestyle modification, and genetic counselling, ultimately improving prognosis and reducing preventable morbidity and mortality. Full article

Objective: To identify risk factors for progression to sepsis in patients with non-ventilator hospital-acquired pneumonia (NV-HAP) and to develop a practical nomogram for individualized risk assessment in this population. Methods: We retrospectively screened 408 hospitalized patients with hospital-acquired pneumonia at Peking University Third Hospital between January 2017 and December 2021. After excluding patients with an unclear diagnosis date or missing critical variables required for SOFA score calculation, 368 eligible patients with NV-HAP were included and randomly divided into a training cohort (n = 260) and an internal validation cohort (n = 108). An independent temporal validation cohort of 68 patients admitted between January 2022 and December 2022 at the same center was further used for temporal validation. Univariable and multivariable logistic regression analyses with backward stepwise selection were performed in the training cohort to identify predictors associated with progression to sepsis. A nomogram was then constructed based on the final model and evaluated by discrimination, calibration, and decision curve analysis. Results: A total of 368 patients were included in the model development dataset. The final multivariable model retained six predictors: male sex (OR = 2.393, 95% CI: 1.333–4.296), diabetes (OR = 2.205, 95% CI: 1.126–4.319), coagulation dysfunction (OR = 3.327, 95% CI: 1.726–6.413), PaO₂/FiO₂ (OR = 0.955 per 10-unit increase, 95% CI: 0.912–1.001), platelet count (OR = 0.900 per 10 × 10⁹/L increase, 95% CI: 0.853–0.949), and bilirubin (OR = 1.176 per 1 μmol/L increase, 95% CI: 1.100–1.258). The nomogram showed acceptable performance, with an apparent C-index of 0.809 and a bootstrap-corrected C-index of 0.792 in the training cohort. The C-index was 0.750 (95% CI: 0.658–0.841) in the internal validation cohort and 0.754 (95% CI: 0.639–0.870) in the temporal validation cohort. Calibration analysis showed acceptable agreement between predicted and observed probabilities, and decision curve analysis indicated a positive net clinical benefit across clinically relevant threshold probabilities. Conclusions: In patients with NV-HAP, male sex, diabetes, coagulation dysfunction, lower PaO₂/FiO₂, lower platelet count, and higher bilirubin were associated with progression to sepsis. The developed nomogram showed acceptable discrimination, calibration, and clinical utility, and may serve as a practical tool for early individualized risk stratification in patients with NV-HAP. Full article

Despite serological evidence of tick-borne encephalitis virus (TBEV) circulation in Belgian animals since 2007, confirmed autochthonous human infection was only first documented in 2020. We review the current national epidemiologic situation and investigate a household cluster of confirmed autochthonous cases identified in 2025. A cohabiting couple experienced a near-simultaneous onset of meningoencephalitis and tested positive for TBEV-specific IgM and IgG, with confirmation by PRNT90. One patient reported a recent tick bite, and both patients reported consumption of unpasteurized milk and goat cheese, suggesting possible alimentary transmission. The identification of Case 2, who lacked neurological symptoms at presentation and was only tested due to the index case, illustrates the risk of missed diagnoses and supports the notion that human TBEV infection is likely underdiagnosed in Belgium. These findings underscore the need to increase clinical awareness, strengthen surveillance, and reinforce prevention strategies. TBE should be considered in the differential diagnosis of patients presenting with non-specific fever or neurological syndromes such as meningoencephalitis, particularly during the spring-to-autumn tick activity season. Full article