Search Results (660)

Venous thromboembolism (VTE), comprising deep vein thrombosis and pulmonary embolism, is an important but under-recognised complication in neuromuscular diseases. In adults, emerging epidemiological data suggests increased VTE occurrence in conditions such as Amyotrophic Lateral Sclerosis, myotonic dystrophy, myasthenia gravis, inflammatory neuropathies, inflammatory myopathies, and POEMS syndrome. This heightened risk reflects not only disease-related immobility but also disorder-specific biological mechanisms, including inflammation, endothelial dysfunction and cardiomyopathy-related stasis. Therapies such as corticosteroids, IVIG-related hyperviscosity, long-term central venous access, perioperative immobility, critical illness, and complex orthopaedic procedures have prothrombotic effects. Despite this multifactorial risk profile, disease-specific guidance for thromboprophylaxis is lacking, and current practice relies heavily on extrapolation from general medical and surgical recommendations rather than data derived from neuromuscular cohorts. In children and adolescents, the VTE burden is less well-characterised, but events have been reported in Duchenne and Becker muscular dystrophy, congenital myopathies, and spinal muscular atrophy particularly with advanced motor impairment, severe cardiomyopathy, ventilatory insufficiency, and prolonged hospitalisation. Beyond venous events, selected neuromuscular disorders also exhibit increased arterial thrombosis risk. Myotonic dystrophy and dystrophinopathies are associated with cardiomyopathy and arrhythmia that predispose to systemic embolism and stroke, while inflammatory myopathies may demonstrate arterial events related to vasculitic or endothelial processes, although overall evidence remains limited. This review summarises available empirical and epidemiological evidence on venous and arterial thrombosis across adult and paediatric neuromuscular disorders, outlines disease-specific mechanistic pathways, examines treatment-related contributors, and highlights key evidence gaps that must be addressed to guide rational and targeted prophylaxis strategies in this complex, heterogeneous population. Full article

Background: The Global Positioning System (GPS) and wearable monitoring technologies are increasingly applied in sport science to quantify training load; however, data from female cross-country skiers in nations with emerging competitive programs remain scarce. This case series covering the complete national team roster analyzed the complete annual training cycle of the Korean women’s national cross-country skiing team (KCF) using GPS and heart rate-based wearable sensors. Methods: All three national team members were monitored throughout the 2022–2023 season (52 weeks), structured into General Preparation Period 1 (April–July), General Preparation Period 2 (August–November), and Competition Period (December–March). Individualized five-zone intensity thresholds were established through graded exercise testing on a roller ski treadmill with ventilatory threshold and blood lactate determination, independently assessed by two exercise physiologists (PhD level). Results: The total annual training volume was 667.72 h, comprising roller/on-snow skiing (54.0%), running (23.3%), and strength training (22.7%). The endurance-only intensity distribution demonstrated a polarized pattern (Zones 1–2: 91.5%). The total annual training distance reached 4673.30 km. The mean FIS points were 108.46 ± 38.60, and the mean VO₂max was 60.17 ± 6.11 mL·kg⁻¹·min⁻¹. Conclusions: When benchmarked against world-class female (WCF) standards (800–950 h annually), the overall training volume was approximately 18–30% lower. The relative strength training allocation (22.7%) exceeded typical WCF values (10–15%). These observations should be interpreted cautiously given the small sample size and cross-study comparison design, using published literature-based benchmarks. Full article

Low back pain is common in road cyclists and has been associated with prolonged lumbar flexion during cycling. The flexion–relaxation (FR) phenomenon reflects neuromuscular control of the lumbar spine, but its response to prolonged cycling under physiologically individualized conditions remains unclear. Thirty-one pain-free road cyclists completed a laboratory protocol in which exercise intensity was prescribed at 50% of the range between the first and second ventilatory thresholds (VT1 and VT2). Surface electromyography (sEMG) was recorded during trunk flexion extension tasks performed before and after a 60 min cycling trial. FR responses were characterized at both the individual and group levels using the flexion–relaxation ratio (FRR), descriptive classification of altered patterns, and exploratory estimates of mean change, effect size, and 95% confidence intervals. Four cyclists (12.9%; 95% CI: 3.6–29.8%) exhibited altered FR responses: three showed persistent alterations already present before cycling, and one showed an exercise-associated alteration. Group-level changes were minimal (effect sizes: −0.20 to 0.04). These findings suggest that prolonged cycling under controlled physiological load primarily reveals heterogeneous subject-specific neuromuscular patterns rather than a uniform average response. FR assessment using sEMG may therefore be useful as a complementary tool for identifying individual neuromuscular behavior in pain-free cyclists. Full article

Postoperative respiratory failure (PRF) remains a pervasive clinical challenge that substantially contributes to perioperative morbidity, mortality, and prolonged ICU stay. Although conventional oxygen therapy is often sufficient, a significant subset of high-risk patients requires escalation to advanced non-invasive support to avoid reintubation and invasive mechanical ventilation. Evidence from recent randomized trials, including the 2025 RENOVATE and Goret et al. studies, indicates that both non-invasive ventilation (NIV) and high-flow nasal oxygen (HFNO) reduce postoperative pulmonary complications and reintubation in selected high-risk populations. While NIV is preferred for hypercapnic ventilatory failure and is commonly used in selected high-risk cardiac surgery patients, HFNO offers comparable outcomes in pure hypoxemic failure with the added benefits of superior patient tolerance and a lower incidence of interface-related complications. Effective PRF management necessitates an individualized, physiology-based approach. By implementing a phenotype-driven algorithm that aligns device mechanics with the dominant pathophysiology, such as atelectasis versus pump failure, clinicians can optimize patient outcomes while minimizing the specific risks associated with delayed intubation. Full article

Background: The impact of cigarette smoking on cardiopulmonary function in elite athletes remains poorly characterised. This study aimed to evaluate the prevalence of smoking and its effects on pulmonary and exercise performance parameters among top-level competitors across different sport disciplines. Methods: 1005 Olympic-level athletes participating underwent comprehensive pre-participation screening, including spirometry and cardiopulmonary exercise testing (CPET). Smoking status was determined according to WHO definitions. Results: Among the 1005 athletes (53.4% males; mean age 26 ± 8.8 years), 117 (11.6%) were current smokers, predominantly males (70.9%). No smokers were identified among endurance athletes. Compared to non-smokers (n = 679), smokers were older (28 ± 5.8 vs. 25.5 ± 10.4 years, p = 0.026) and more frequently involved in mixed and skill disciplines (p = 0.043 and p = 0.006, respectively). In male smokers, spirometry revealed lower FVC (97.2 ± 10.3% vs. 101.1 ± 11.7%, p = 0.006), FEV₁ (97.3 ± 12.4% vs. 101.4 ± 10.3%, p = 0.002), and MVV (p = 0.010). CPET showed reduced functional capacity (W/kg, p < 0.0001), lower VO₂max (38.5 ± 7.8 vs. 42.2 ± 6.8 mL/min/kg, p < 0.0001), decreased O₂ pulse (p = 0.007) and lower first and second ventilatory thresholds (respectively p = 0.025; and p = 0.004), Similar but less pronounced reductions in VO₂max were found in female smokers (p = 0.003). Conclusions: Chronic smoking is associated with early spirometric and ventilatory impairments in elite athletes associated with lower aerobic capacity, despite their high levels of fitness. These effects are more marked in males, while females may exhibit partial protection. These findings highlight the importance of integrating smoking cessation and respiratory monitoring into athlete health programs. Full article

Background/Objectives: Positive end-expiratory pressure (PEEP) is a standardized component of the invasive mechanical ventilation (IMV) settings to improve oxygenation; however, its physiological effects in patients with no documented prior lung disease remain poorly defined. This study evaluated the impact of moderate PEEP variations on macrohemodynamic parameters, gas exchange, and driving pressure (ΔP). Methods: This single-arm, non-randomized, crossover study included adult intensive care unit (ICU) patients with no documented prior lung disease during the early phase of IMV. Sequential PEEP levels of 6, 8, and 10 cmH₂O were applied for 30 min each within the first 24 h of ICU admission, while all other ventilatory parameters were kept constant. Arterial blood gases [partial pressure of oxygen (PaO₂), partial pressure of carbon dioxide (PaCO₂), and arterial oxygen saturation (SaO₂)], oxygenation index [PaO₂/fraction of inspired oxygen (FiO₂)], systolic, diastolic, and mean arterial pressures, ΔP, and static compliance (Cstat) were measured. Friedman and Mann–Whitney U tests were used, with adjustment for multiple comparisons. Results: A total of 150 patients were enrolled (64.7% male). The observed mortality rate was 53.3%; however, mortality was not defined as a primary or secondary outcome, and was used only as a grouping variable for comparative analyses. Intraindividual comparison across PEEP levels of 6, 8, and 10 cmH₂O showed small but significant reductions in systolic and mean arterial pressure at higher PEEP (p-value < 0.05), with Bonferroni-adjusted significance for PEEP 6 vs. 10. No significant differences were observed in oxygenation (SaO₂, PaO₂, and PaO₂/FiO₂), PaCO₂, ΔP, or Cstat. These results suggest that moderate PEEP changes produced limited macrohemodynamic effects without relevant impact on gas exchange or respiratory mechanics. Overall, no clinically relevant or statistically significant differences were observed in gas exchange, macrohemodynamic parameters, ΔP, or Cstat across PEEP levels when mortality was used as the grouping variable. Among survivors, higher PEEP was associated with modest reductions in systolic and mean arterial pressures and higher PaCO₂ values; however, these findings did not translate into consistent physiological benefits. Conclusions: In mechanically ventilated patients with no documented prior lung disease, PEEP may exert divergent effects on macrohemodynamics, gas exchange, and ΔP, supporting a cautious and individualized approach to PEEP selection in this population. Full article

Background/Objectives: Breathing efficiency and stability depend on the integrated function of biochemical, biomechanical, and psychophysiological processes across the unified upper and lower airway. Clinical interventions often address these domains in isolation, which may limit treatment outcomes. The primary objective of this article is to present Integrative Breathing Therapy (IBT) as a clinically applicable, multidimensional framework for training unified airway function. A secondary objective is to illustrate how this framework can inform clinical reasoning in orofacial myology and behavioural management of obstructive sleep apnea. Method: This article presents a clinical synthesis of physiological theory, neuroplasticity research, and applied breathing therapy to describe the theoretical and clinical foundations underpinning the Integrative Breathing Therapy (IBT) framework. Multidimensional phenotyping is used to organise dominant biochemical, biomechanical, and psychophysiological contributors to breathing inefficiency, with obstructive sleep apnea presented as a clinical example. Results: This synthesis outlines a unified airway model linking multidimensional phenotyping to targeted intervention selection. The IBT framework provides a structured approach for integrating biomechanical coordination, ventilatory control, and psychophysiological regulation within clinical practice. The obstructive sleep apnea exemplar demonstrates how phenotype-informed mapping can support clinical reasoning and guide individualised intervention strategies within OM and related behavioural approaches. Conclusions: Integrative Breathing Therapy offers a clinically grounded, multidimensional model for functional breathing optimisation that aligns unified airway training with principles of neural adaptation and systems-based clinical reasoning. This framework supports phenotype-guided clinical decision-making and provides a coherent structure for addressing breathing inefficiency and airway instability across a range of clinical populations, including those treated with orofacial myology and behavioural OSA therapies. Full article

Introduction: Congenital central hypoventilation syndrome (CCHS) is a rare disorder characterized by an impaired ventilatory response to hypercapnia and hypoxia, particularly during sleep, and frequently associated with autonomic dysfunction. It is caused by pathogenic variants in the PHOX2B gene. Although CCHS is typically diagnosed in the neonatal period, milder forms may present later in infancy or childhood, often triggered by respiratory infections. Case presentation: We report the case of 16-month-old male diagnosed with CCHS following an episode of hypoxemic–hypercapnic respiratory failure during respiratory syncytial virus (RSV) infection. His medical history included neonatal respiratory distress requiring oxygen therapy and recurrent wheezing. At 15 months, he developed acute respiratory distress with severe hypercapnia (PaCO₂ 70 mmHg), requiring admission to the Pediatric Intensive Care Unit and invasive mechanical ventilation. Persistent sleep-related hypercapnia and hypoxemia prompted evaluation for central hypoventilation, confirmed by means of transcutaneous capnography and nocturnal pulse oximetry. Genetic testing revealed a de novo nonsense mutation in exon 1 of PHOX2B (p.Tyr14Ter). Brain magnetic resonance imaging showed diffuse white matter changes suggestive of gliosis. Further investigations identified early-onset systemic hypertension, requiring antihypertensive therapy. The patient was discharged on nocturnal non-invasive ventilation and enrolled in a neurodevelopmental rehabilitation program. Conclusions: This case highlights the phenotypic variability of CCHS and the importance of considering this diagnosis in children presenting with unexplained hypercapnia and sleep-related hypoxemia. It underscores the need for comprehensive autonomic evaluation, including blood pressure monitoring. The p.Tyr14Ter variant may allow partial protein function, potentially accounting for the relatively mild phenotype. Full article

Objectives: To confirm the utility of barometric whole-body plethysmography (BWBP) as a non-invasive, clinical diagnostic test for brachycephalic obstructive airway syndrome (BOAS) in cats. Methods: Client-owned cats belonging to brachycephalic breeds were enrolled and classified into two clinical severity grades of upper airway obstruction (UAO). Brachycephalic cats with high-grade UAO severity (Brachy-H-UAO) represented those with clinically evident effects on clinical signs or physical examination findings, whereas brachycephalic cats with low-grade UAO severity (Brachy-L-UAO) represented those without clinically evident problems. A group of non-brachycephalic (NB) cats that were respiratory disease-free and with neither a history of cardiac or systemic diseases nor exposure to cigarette smoke was used as the control group. Cats were placed in the BWBP chamber, and breathing signals were obtained after an adaptation period in a quiet and silent environment. The ventilatory variables obtained were respiratory rate (RR; [bpm]), tidal and minute volume per kilogram bodyweight (MV/BW and TV/BW; [mL/kg]), inspiratory (Ti; [s]) and expiratory (Te; [s]) intervals, airway obstruction index enhanced pause (Penh), and peak inspiratory and expiratory flows per kilogram (PIF and PEF; [mL/s/kg]). Results: Forty-three client-owned cats (11 Brachy-H-UAO, 7 Brachy-L-UAO, and 25 NB) were included. Brachycephalic cats (Brachy-H-UAO: 311 mL/kg; Brachy-L-UAO: 253 mL/kg) showed significantly lower median MV/BW than NB cats (503 mL/kg) (p = 0.01). Brachy-H-UAO cats demonstrated significantly higher median PEF/PIF ratios (Brachy-H-UAO: 1.46, minimum–maximum 0.82–2.48; Brachy-L-UAO: 0.76, 0.52–1.11; NB: 0.73, 0.56–1.00) and Penh (Brachy-H-UAO: 2.37, minimum–maximum 0.57–23.82; Brachy-L-UAO: 0.57, 0.27–1.11; NB: 0.53, 0.21–0.68) than Brachy-L-UAO and NB cats (p < 0.001). No significant differences were observed among the three groups for RR, TV/BW, Ti, Te, or Te/Ti. Conclusions and Relevance: Cats affected by BOAS demonstrate impaired ventilatory function, with reduced minute ventilation and a distinctive flow pattern and parameters reflecting limited inspiratory flow and increased upper airway resistance. BWBP can serve as a useful tool to diagnose and characterize the severity of BOAS in cats. Full article

Backround and Objectives: Basketball performance is shaped by repeated high-intensity actions interspersed with brief recovery. Conventional continuous or strictly incremental testing may not fully capture short active-recovery dynamics relevant to stop-and-go sports. Material and Methods: This study applied a VT₂-referenced progressive–intermittent treadmill protocol and focused on 60-s active-recovery kinetics to describe effort tolerance in an applied basketball setting. Basketball players from Mureș County completed anthropometry (24 h pre-test, fasted) and a single laboratory visit. Pre-test training and diet were standardized for 48 h (submaximal training; predominantly carbohydrate intake). CPET was performed in 3-min stages (6.5 km·h⁻¹ start; +0.7 km·h⁻¹ per stage) and stopped at RER = 1.00 and/or blood lactate = 4.0 mmol·L⁻¹ (operational VT2). After 3 min active recovery, participants completed six 60-s high-speed bouts separated by 60-s active recovery intervals (AR1–AR6), with intensities prescribed at 120–180% of VT2-derived speed, followed by an 8-min active recovery. For each AR interval, linear regression over 0–60 s yielded slopes for VO₂, VO₂/HR, VCO₂, V̇E, VE/VO₂, VE/VCO₂, and PetCO₂. Results: VT₁ was determined at 2.29 m·s⁻¹ (VO₂ 32 mL·min⁻¹·kg⁻¹) and VT2 at 3.07 m·s⁻¹ (VO₂ 42 mL·min⁻¹·kg⁻¹). Maximal intermittent speed was 5.33 m·s⁻¹ (VO₂ 45.5 mL·min⁻¹·kg⁻¹; RER 1.06; PetCO₂ 38 mmHg). VO₂ differed across successive bouts (p = 0.0001), while PetCO₂ showed a small downward drift across repetitions. Peak indices (max speed, VE/VCO₂max, PetCO₂max, VEmax) were associated with phase-specific recovery slopes across early, mid, and late recovery periods (false discovery rate–adjusted correlations). Lactate decreased over 8 min, but lactate change rates were not associated with peak indices. Conclusions: The VT₂-referenced progressive–intermittent protocol appears feasible in basketball players and provides phase-dependent recovery information that complements conventional peak CPET outcomes, with potential relevance for applied team settings. Full article

Background and Objectives: Cross-country skiing requires high levels of upper-body strength and efficient respiratory function to sustain performance during sport-specific movements. This study aimed to examine the effects of an eight-week ski ergometer-based training program on upper-extremity isokinetic muscle strength and pulmonary function in competitive cross-country skiers. Materials and Methods: A total of 20 cross-country skiers voluntarily participated in the study (experimental group: n = 10, control group: n = 10). The research was conducted using a quasi-experimental controlled design. During the eight-week training period, the experimental group performed ski ergometer training three times per week at an intensity of 80–90% of maximal heart rate, with a target distance of 2.5 km per session, in addition to their regular training program. Measurements were obtained before and after the intervention. Results: Following the ski ergometer training period, significant increases were observed in FVC (F = 18.565, p < 0.001, ηp² = 0.508) and FEV₁ (F = 8.789, p = 0.008, ηp² = 0.328), which were associated with enhanced respiratory muscle endurance and ventilatory capacity. Regarding the isokinetic strength parameters, the DPPE60 variable showed significant main effects of time (F = 33.770, p < 0.001, ηp² = 0.652) and time × group interaction (F = 18.590, p < 0.001, ηp² = 0.508), indicating higher upper-extremity strength values across the measurement period. Additionally, strong positive correlations were found between dominant and nondominant limbs (r = 0.79–0.92; p < 0.05), indicating balanced bilateral strength development and high neuromuscular coordination. Conclusions: Ski ergometer-based training was associated with improvements in upper-extremity peak power (DPPE60) and ventilatory capacity (FVC) beyond general training-related adaptations. These findings suggest that SkiErg training may be a useful complementary method for enhancing selected performance-related physiological parameters in cross-country skiers. Full article

Background/Objectives: Preterm infants with respiratory distress syndrome (RDS) require mechanical ventilation but risk lung injury This study compared neurally adjusted ventilatory assist (NAVA) with conventional modes regarding respiratory mechanics and clinical outcomes. Methods: We analyzed data from 79 preterm infants born at <32 weeks gestation who were invasively ventilated for RDS and classified into three groups: NAVA (n = 26), volume-targeted (VT; n = 29), and pressure-controlled (PC; n = 24). Respiratory parameters for 6 h post-surfactant administration and clinical outcomes were evaluated. Results: Baseline characteristics were similar across groups. The NAVA group demonstrated the most rapid reduction in peak inspiratory pressure over 6 h (F = 4.125, p = 0.023) and the fastest increase in dynamic compliance during the first 4 h (F = 3.273, p = 0.048). Respiratory rates were significantly lower with NAVA than with VT or PC modes, while tidal volumes were significantly higher in PC than in NAVA or VT modes. Invasive mechanical ventilation duration was shorter in NAVA (3.0 [0.9–4.9] days) than in PC modes (15.1 [0.3–38.5] days, p = 0.031), whereas not significantly different from that in VT modes (3.8 [0.9–13.4] days). While bronchopulmonary dysplasia or death was lower in NAVA (19.2%) than in PC modes (41.7%), the difference was not statistically significant (p = 0.092). Conclusions: NAVA resulted in the fastest reduction in ventilator-delivered pressure and earlier improvement in dynamic compliance while maintaining respiratory rates within physiological ranges and was associated with shorter ventilation duration than PC modes. However, VT modes achieved comparable respiratory parameters and ventilation durations to those achieved using NAVA. Full article

Background and Objectives: Dual bronchodilation in chronic obstructive pulmonary disease (COPD) has demonstrated beneficial effects on health-related quality of life (HRQoL) and exercise-related outcomes. Real-world evidence in treatment-naïve COPD remains limited. Materials and Methods: Forty-six COPD patients and 23 age-, gender-, BMI-, and cardiovascular comorbidity–matched controls underwent spirometry, plethysmography, symptom-limited incremental cardiopulmonary exercise testing (CPET), and the 36-item Short-Form Health Survey (SF-36). Following baseline assessment, COPD patients received tiotropium/olodaterol as part of routine practice. Thirty-two patients underwent repeated examinations at 12 weeks. Baseline differences between the COPD and control groups were assessed, and longitudinal changes in pulmonary function, CPET, and SF-36 were evaluated in COPD patients. Results: Compared with controls, COPD patients had lower peak oxygen uptake (VO₂; 17.4 ± 4.4 vs. 22.8 ± 4.5 mL/kg/min, p < 0.001) and oxygen pulse (11.5 ± 3.5 vs. 14.0 ± 2.4 mL/beat, p = 0.003), failed to reach 80% of predicted values, and exhibited worse ventilatory efficiency (p < 0.001). SF-36 scores in the COPD group were lower across all domains. After 12 weeks of tiotropium/olodaterol, pulmonary function improved significantly. CPET was performed at comparable efforts at both visits. Peak VO₂ increased from 70 ± 15 to 75 ± 16% predicted (p = 0.044), and peak oxygen pulse from 74 ± 16 to 79 ± 16% predicted (p = 0.015). VE/MVV decreased from 0.77 ± 0.23 to 0.69 ± 0.15 (p = 0.03). Higher baseline VE/MVV predicted a larger improvement after treatment (B = 0.71, p < 0.001), while beta-blocker use had no effect on the change of VE/MVV. SF-36 physical functioning and health change scores improved (both p < 0.01). Conclusions: At diagnosis, COPD was associated with impaired exercise physiology and reduced HRQoL. Dual bronchodilation improved exercise responses and perceived physical functioning. Beta-blocker use was not associated with changes in breathing reserve, supporting the use of cardioselective agents when indicated. Full article

Objective: To investigate the epidemiology, clinical characteristics, and potential risk factors of chronic cough following SARS-CoV-2 infection. Methods: A total of 1434 patients with post-COVID-19 cough were categorized into acute, subacute, and chronic subgroups by cough duration, with clinical data analyzed across subgroups. Questionnaire surveys were conducted in chronic cough patients, followed by an 18–21-month follow-up. Results: 1. Significant intergroup differences were observed among the three groups in: the number of patients with rhinitis and/or pharyngitis history, cough with chest tightness, cough with pharyngeal symptoms, and sensitivity to irritating odors and cold air. 2. The chronic group had a significantly lower platelet count but higher eosinophil and basophil percentages than the acute group. 3. The chronic group showed significantly lower values than the subacute group in multiple pulmonary function indices: FVC, FEV1, FEV1/FVC, PEF, MEF25, MEF75, MEF50, MMEF75/25, MEF75%, MEF50%, MEF25%, MMEF75/25%, DLCO, and DLCO%. 4. Chest CT findings: the chronic group had significantly lower rates of infected lesions, cord-like opacities, and ground-glass shadows than the acute group, but a higher rate of micro-nodules than the subacute group. 5. At follow-up, the cough and non-cough groups differed significantly in nighttime cough scores and the proportion of cough with chest tightness, as well as in pulmonary function parameters: FVC, FEV1, PEF, PEF%, MEF75, DLCO, RV% and TLC. 6. Binary logistic regression analysis identified the nocturnal cough symptom score and cough accompanied by chest tightness as independent factors influencing persistent cough 18–21 months after SARS-CoV-2 infection. Conclusions: Patients with pre-existing upper airway inflammation, laryngeal symptoms, chemical hypersensitivity, elevated eosinophil/basophil percentages, and pulmonary micro-nodules are more likely to develop chronic post-COVID cough, presenting with partial ventilatory impairment and diffusing capacity impairments. Full article

Background: In critically ill patients, tracheostomy decisions are driven by heterogeneous and dynamic clinical trajectories, and no universally accepted scoring system exists to reliably predict tracheostomy requirement. An accurate and interpretable prediction model could help earlier decision-making and potentially reduce prolonged mechanical ventilation (MV) and failed weaning. Methods: In this retrospective study, data from 6507 mechanically ventilated intensive care unit (ICU) patients were analyzed using an electronic clinical decision support system; 1049 patients required tracheostomy and 5458 did not. The primary outcome was the prediction of tracheostomy occurrence during ICU stay based on invasive mechanical ventilation (IMV) parameters obtained within the first five days. The secondary outcome was the identification of the most influential parameters guiding tracheostomy decision-making during early IMV. Ten machine learning algorithms were developed using an 80/20 train–test split. Model performance was assessed using discrimination, calibration, and clinical performance metrics. Explainability was evaluated using SHapley Additive exPlanations (SHAP) analysis. Results: Among all models, Gradient Boosting demonstrated strong discrimination and calibration performance (AUROC 0.92, AUPRC 0.56, specificity 97%, F1 score 0.46, Brier score 0.078). In the Gradient Boosting model, feature importance analysis demonstrated that secretion count was the strongest predictor of tracheostomy requirement, accounting for 14.72% of the model’s predictive contribution. This was followed by lactate level (6.12%), arterial pH (3.74%), and peak airway pressure (3.57%). SHAP-based analyses consistently identified secretion count as the strongest predictor of tracheostomy requirement, followed by lactate level, Glasgow Coma Scale (GCS), and arterial pH. In addition, SHAP provided clinically interpretable insights into the direction and magnitude of the effects of individual predictors. Conclusions: Machine learning models integrating early-phase ventilatory and physiological data may enable clinically meaningful prediction of tracheostomy requirement. The combination of strong performance and explainability suggests potential utility as a decision-support tool in critically ill patients requiring prolonged MV. Full article