IEEE Access

The -Bonacci weighted sequence space {ell}(,) is introduced for [&ge;] 2, 1 [&le;] < {infty}, and > 0). It is proved to be a Banach space which is isometrically isomorphic to {ell}, with an unconditional Schauder basis. The space is also reflexive and uniformly convex. Its strict inclusion chain, continuous dual, and asymptotic truncation estimate of order - / are also established. Based on this framework, Scaled &#119898-BonacciNet is proposed as a lightweight CNN that rescales Fibonacci-Net channels using the dominant &#119898-Bonacci root and employs depth wise separable convolutions. Tribonacci-Net achieved 96.09% accuracy and a 0.9581 macro F1-score on the 15-class Brain MRI dataset using 0.85 million parameters and 0.366 GFLOPs. Pentanacci-Net attained 95.87% accuracy on the 44-class dataset while reducing parameters and FLOPs by 47.10% and 44.48%, respectively. On the CKD ultrasound dataset, Hexanacci-Net achieved 83.75% accuracy and a 0.7941 macro F1-score, with corresponding reductions of 50.37% and 45.10%. These findings support dominant-root scaling as a structured approach to lightweight CNN design.

Background: Lean Healthcare has been adopted as an approach to reducing waste, enhancing process efficiency, and optimizing clinical and administrative workflows. However, empirical evaluations aimed at establishing a causal relationship between Lean Healthcare interventions and outcomes remain limited. This evidence gap is particularly pronounced in the context of large-scale implementations in low- and middle-income countries, where more efficient allocation could yield substantial improvements in population health. Methods: We conducted an impact evaluation study employing a staggered difference-in-differences approach to estimate the effects of the Lean Healthcare in Emergency Departments (ED) initiative in the Brazilian context. The intervention was implemented between January 2017 and December 2025 across 309 hospitals. We analyzed hospital-level indicators of the number of hospitalizations and the average length of stay (in days) among patients admitted through urgent or emergency pathways. Results: Our estimates suggest that the intervention was associated with an average increase of 38.6 admissions per hospital per month (p = 0.033), corresponding to approximately a 5.9% increase relative to the monthly admission volume. We also observed a reduction of 0.184 days in the average length of stay (p = 0.058), equivalent to an approximately 3.0% decrease in hospitalization time. These effects exhibited distinct temporal dynamics: the effect on the number of hospitalizations emerged gradually and increased with the duration of the intervention, whereas the reduction in length of stay became evident earlier. Conclusion: This study provides evidence of a causal effect of Lean Healthcare implementation in emergency departments on operational performance. The simultaneous increase in admissions and reduction in length of stay suggests improved bed productivity and effective capacity without expanding physical infrastructure. These findings support the use of flow-management methodologies as an effective strategy for mitigating emergency department overcrowding while increasing service capacity.

Purpose To evaluate the external transportability of source-derived probability calibration for chest radiograph deep learning classifiers under distribution shift and determine its dependence on sample size and disease prevalence. Materials and Methods This retrospective secondary computational analysis of public, de-identified radiographic datasets involved no participant contact or new data collection. Cohort sizes were prespecified by availability without prospective power calculation: 106,686 NIH ChestX-ray14 images (29,323 patients; 1992-2015) for development and internal testing, 20,000 CheXpert images (20,000 patients; October 2002-July 2017), and 14,998 VinBigData images (2018-2020) for external testing. ResNet-18, DenseNet-121, and DeiT-Tiny classifiers for cardiomegaly and pleural effusion were trained across four patient fractions and three seeds (36 fits). Calibrators were fitted exclusively on NIH data. Twelve primary external Brier-score contrasts (temperature-scaled versus raw probabilities) were evaluated using paired cluster-bootstrapping with Holm adjustment. Results Temperature scaling reduced Brier scores in nine of 12 primary contrasts but worsened pleural effusion calibration on VinBigData across all architectures (Brier increases: ResNet-18, 0.001460 [95% CI: 0.001347, 0.001568]; DenseNet-121, 0.001193 [95% CI: 0.001109, 0.001274]; DeiT-Tiny, 0.000498 [95% CI: 0.000417, 0.000577]; all adjusted P=.006). Standardizing class weights to NIH prevalence reversed all CheXpert improvements. Although full versus 10% training improved external AUROC across all comparisons, DeiT-Tiny CheXpert pleural effusion Brier score worsened by 0.007039 despite a 0.032466 AUROC gain. At 80% selective image retention, calibrated ensembles retained only 12.3%-17.2% of VinBigData positive pleural effusion examinations. Conclusion Source-fitted calibration is not uniformly transportable across health systems, and discrimination gains do not guarantee calibrated probabilities. External evaluation must simultaneously assess probability reliability, prevalence shifts, and retained-case composition.

Objective: The aim of the current study was to evaluate the feasibility of a multi-channel distributed wearable ultrasound (D-WUS) system capable of simultaneously probing dynamic muscle activity across multiple anatomical sites to assess neuromuscular coordination during physical activity. Methods: Twenty NCAA Division I women athletes (8 with prior knee injury) performed countermovement jumps (CMJs) on dual force plates while wearing a four-channel D-WUS system targeting the vastus lateralis (VL) and vastus medialis oblique (VMO) in both limbs. Real-time M-mode ultrasound data were processed using a composite factorization approach integrating nonnegative matrix factorization and principal component analysis (CF-PCA) to extract dominant muscle-contraction patterns. Correlation and timing metrics between VL and VMO were compared across injury status. Results: CMJ performance metrics (jump height, RSImod) did not differ between groups (p > 0.05). However, D-WUS revealed significant differences in muscle coordination in the right limb: VL-VMO correlation (p = 0.029) and timing symmetry (p = 0.019) were reduced in participants with prior knee injury; left-limb differences were not significant. Right-limb timing symmetry was negatively correlated with SMFA score (rho = -0.48, p = 0.033). Functional survey scores (SMFA) also differed significantly (p = 0.001), while VISA-P scores did not. Conclusion: These preliminary findings provide feasibility-level evidence that distributed wearable ultrasound can detect limb-specific neuromuscular coordination differences not reflected in force-plate biomechanics, motivating larger prospective studies to establish reliability and clinical utility. Significance: With further validation, this approach may offer a scalable, objective means of monitoring muscle contraction during rehabilitation.

Patients with implantable cardioverter-defibrillators (ICDs) often are excluded from receiving CMR scans at 3.0T due to ICD-induced image artifacts. This work aims to transfer sequence protocols established for CMR imaging in the presence of ICDs at 1.5T to a first human application at 3.0T. All measurements were performed on a clinical 3T MRI scanner. Phantom measurements were used to establish and optimize wideband PSIR LGE imaging at 3.0T. Volunteer measurements with externally placed ICDs were used for optimization of CINE imaging and wideband PSIR imaging. Thirdly, patients with implanted ICD were examined with the optimized protocols. Human measurements showed that SA stacks obtained with spoiled GRE after contrast agent showed a markedly lower artifact burden than the conventional approach. For scar imaging, a wideband PSIR with a bandwidth of 3kHz and a frequency offset of +750Hz allowed a sufficient suppression of relevant artifacts in the majority of scans. No strong correlation between the image quality and the distance between the cardiac silhouette and the device was detected. The presented work shows the feasibility of clinical cardiac MRI at 3.0T including GRE-CINE and wideband PSIR-LGE for patients with ICDs.

Background and Objective: The volume of patient portal messages has grown substantially and artificial intelligence (AI) can support clinical staff and improve the timeliness of patient care. Our objective is to test if an AI tool for managing the electronic inbox In-Basket reduces response times to patient portal messages in neurology. Methods: We conducted an implementation study from January to May 2026 in the neurology department at two clinical sites within a regional medical system. A single AI tool was implemented to auto-categorize and auto-route all patient messages received in the electronic inbox. The tool also generates optional draft replies to messages. Primary process measures were the median weekly time (hours) from message creation to the first action and to closure. Impact was analyzed using a controlled interrupted time-series (ITS) design, comparing message-volume-matched control divisions. Results: Among 24,142 messages analyzed, pre-intervention median weekly time to first action was 11.3 hours [IQR: 5.6, 15.1] (Site A) and 16.1 hours [IQR: 13.8, 19.0] (Site B), falling post-intervention to 1.0 hour [IQR: 0, 3.1] (Site A) and 0.6 hours [IQR: 0.2, 2.4] (Site B). Controlled interrupted time-series analysis showed a significant immediate differential level change in median weekly hours to first action at Site A (-92.5%, 95% CI: -97.5% to -78.0%), and a significant downward trend at Site B (-43.5%, 95% CI: -65.2% to -8.2%). Changes in time to closure were directionally favorable but not statistically significant at either site. There was low use of the generated draft replies, only 0.5% at Site A and 3% at Site B. Discussion: Implementation of AI-assisted message categorization and routing was associated with a substantially reduced initial action time for patient In-Basket messages in Epilepsy. The utilization of AI-generated draft-replies to messages was low. These findings support the feasibility and effectiveness of AI-augmented workflows to improve inbox management.

Background: Cost-effectiveness analyses (CEA) built on simulation models are usually delivered through project-specific scripts. Each new model, and often each new question, rebuilds the same scaffolding: parameter management, calibration, base-case analysis, sensitivity analysis and export. This is costly, and is where traceability between an estimate and the model version producing it is lost. We present THALASSA, a web application providing this infrastructure once, for any model satisfying a small programming contract. Methods: A simulation model is connected by one file implementing a fixed contract of R functions that determine its behaviour. THALASSA exposes the complete CEA workflow in a browser: a generated overview of the connected model, parameter editing, calibration, base-case comparison with the efficiency curve, and deterministic and probabilistic sensitivity analysis at a willingness-to-pay threshold, each with timestamped file export carrying the parameter values it was run with. Every session is bound to a repository version, so results carry their generating model version. Results: We demonstrate THALASSA on two public models of contrasting difficulty: a simple tutorial model and a generic cancer screening model with two competing natural-history pathways and a 21-dimensional calibration deliberately built to be more complex. Both ran on the same unmodified setup, implementing the same contract, with no code changes. Conclusions: Separating analysis infrastructure from model logic makes the CEA workflow reusable across projects and reproducible by construction. A modelling team can move from a versioned repository to audit-ready, exportable CEA outputs without writing analysis code. The integration effort does not grow with model size and one installation serves unrelated projects.

Background: Conventional performance metrics do not indicate whether artificial intelligence (AI)-platforms and radiologists are right or wrong on the same examinations, nor whether their non-agreement is more often beneficial or harmful. Objective: To develop, illustrate, and apply directional metrics quantifying non-agreement between radiologists and AI-platforms against a common reference standard, and to adapt a fragility-based framework for quantifying the statistical robustness of these metrics. Methods: We defined Positive Non-Agreement (PNA, AI-platform correct, radiologist incorrect), Negative Non-Agreement (NNA, radiologist correct, AI-platform incorrect), and Net Non-Agreement (NENA, their difference). Metrics were illustrated in three hypothetical scenarios of 1,000 examinations each and applied to three previously published AI-radiologist studies on pulmonary embolism and mammography. Bootstrap confidence intervals were calculated, and a reclassification fragility index (FI) quantified the minimum case reclassification needed to remove statistical support for NENA's direction. Results: In illustration, NENA was positive in two scenarios and negative in one. In the three published studies, NENA ranged from -4.18% to +10.74% and decreased consistently with increasing radiologist experience (junior residents, +6.27%; consultants, +1.45%), a gradient driven primarily by declining PNA with modest increase in NNA. The reclassification FI was defined for all three illustrative scenarios (range, 0.10%-1.70%) and for six of the seven comparisons from these studies (range, 0.34%-4.31%), but not for the weakest comparison, whose confidence interval for NENA included zero. Conclusions: PNA, NNA, and NENA provide a directional, case-level complement to conventional performance metrics for AI-radiologist non-agreement. The accompanying reclassification FI offers a statistically grounded, generalizable method for quantifying their robustness.

Large language models (LLMs) are increasingly evaluated for clinical tasks, but safe use requires reliable uncertainty estimates as well as high accuracy. We tested eight general-purpose LLMs on 100 validated neurology board-style multiple-choice questions and compared three confidence signals: self-reported confidence, critique-implied confidence from an independent model instance, and consistency-based confidence from repeated sampling. Accuracy varied from 45% (Llama 3.1 8B) to 92% (Gemini 3 Flash/Pro), but confidence was generally overestimated, particularly in lower-accuracy models. Consistency-based confidence provided the best discrimination between correct and incorrect answers (pooled AUROC 0.74), outperforming self-report, although calibration differences between methods were not significant. Calibration should therefore be reported alongside accuracy when clinical LLMs are evaluated.

BACKGROUND Timely cause-of-death (COD) information guides health policy, yet many deaths in low- and middle-income countries are not medically certified. In Africa, fewer than 10% of deaths are. Verbal autopsy (VA) yields a structured symptom questionnaire and a free-text narrative. Mortality surveillance increasingly records the narrative alongside the questionnaire, but the algorithms used to produce VA-based statistics were designed for structured responses only, so narratives inform physician COD assignment but do not contribute to algorithmic COD assignment. We evaluated whether supervised models could use both modalities to improve COD assignment. METHODS We analyzed 4,999 VA records for deaths at ages 12 years or older from a national sample of registered deaths in South Africa (RSA), using physician-assigned CODs as the reference standard. We trained unimodal and multimodal pipelines on the labelled records: pretrained language models (PLMs) fine-tuned on narratives alone, machine learning (ML) models on structured responses alone, and the two combined at the data, feature, and decision levels. We also prompted a locally deployed generative large language model (LLM) on the same unimodal and multimodal inputs, without parameter updates. All were compared with InSilicoVA, the operational comparator representing current automated practice. We evaluated individual-level assignment, population-level agreement, calibration, and generalization across provinces in RSA, reporting these metrics rather than ranking pipelines on any one of them. RESULTS Every supervised pipeline improved on InSilicoVA by 8.5-15.9 percentage points in top-1 accuracy and 3.5-7.1 points in cause-specific mortality fraction (CSMF) accuracy. The narrative and structured pipelines performed similarly in aggregate but differed by cause: 63.9% of deaths received identical predictions, 11.6% were correct only from the narrative pipeline, and 13.6% only from the questionnaire pipeline, with the narrative pipeline more accurate for noncommunicable causes and the questionnaire pipeline for communicable causes. Against the unimodal approaches, the decision-fusion pipelines added 4.2-5.4 percentage points in top-1 accuracy, concentrated in the most common causes, whereas feature fusion with cross-modal attention improved the less common causes, adding 6.6 points (95% CI, 1.7-11.5) in balanced accuracy and 5.5 points (95% CI, 0.6-10.3) in macro F1. Feature fusion reached the highest CSMF accuracy (95.7%). Paired differences from the better unimodal representative ranged from -0.2 to +3.4 points, with all intervals including zero. The LLM exceeded InSilicoVA on individual-level metrics and reached the highest balanced accuracy of any pipeline (60.6%), while the supervised pipelines retained higher CSMF accuracy. Supervised pipelines had lower expected calibration error than InSilicoVA. Supervised gains held across all nine held-out provinces, including every top-1 comparison and nearly every macro F1 and CSMF comparison. CONCLUSIONS PLMs using narratives alone substantially improved on current best practice and matched ML pipelines using structured responses, while multiple multimodal strategies produced further gains in individual COD assignment. The zero-shot LLM showed particular strength on rare causes, whereas supervised pipelines better recovered the population cause distribution. These findings support incorporating narratives as a core input to automated VA systems and evaluating representative fusion strategies for the intended output. External validation across settings and age groups will support broader implementation.

Background: Artificial intelligence (AI) may improve electrocardiographic differentiation of Takotsubo syndrome from acute anterior ST-segment elevation myocardial infarction (STEMI), but its impact on human diagnostic performance, the added value of visual explanations, and differences by reader background and experience remain uncertain. Methods: Using 12-lead electrocardiogram (ECG) images from two hospitals, we developed and externally validated an ensemble of three deep learning models after self-supervised pretraining and fine-tuning. The diagnostic task used ECGs recorded within 14 days after symptom onset, regardless of reperfusion status. We conducted a four-phase reader study. Phases 1-3 compared unaided interpretation, a reference sheet, and additional AI assistance. In Phase 4, readers evaluated a new ECG set after randomization to reference-sheet support alone, with AI predictions, or with AI predictions plus gradient-weighted class activation mapping (Grad-CAM) heatmaps. Diagnostic correctness was analyzed using generalized linear mixed-effects models. Exploratory analyses examined differences by cardiologist status and experience. Results: Development and external-validation cohorts, including healthy controls, comprised 832 and 95 participants, respectively. For Takotsubo-STEMI discrimination, external-validation accuracy was 0.914, with areas under the receiver operating characteristic and precision-recall curves of 0.970 and 0.984. Seventy healthcare providers completed the reader study. The estimated probability of correct diagnosis increased from 0.632 without assistance to 0.864 with AI assistance (odds ratio [OR], 3.71; P<0.001). In randomized Phase 4, AI assistance improved accuracy vs reference-sheet support alone (OR, 4.28; 95% CI, 3.08-5.95; P<0.001), and Grad-CAM provided additional benefit (OR, 1.53; 95% CI, 1.04-2.25; P=0.033). Exploratory analyses showed greater improvement among less experienced readers; with AI assistance, non-cardiologists outperformed cardiologists. AI-assisted readers remained less accurate overall than the model alone. Conclusions: An ECG image-based ensemble differentiated Takotsubo syndrome from anterior STEMI and improved reader accuracy. Visual explanations provided additional benefit, while experience-related differences highlight the importance of effective human-AI interaction.

Longitudinal clinical cohorts contain heterogeneous progression patterns that are obscured by coarse diagnostic labels. Discovering these latent progression phenotypes requires models that distinguish patients not only by their outcomes, but also by how their clinical trajectories evolve. This paper proposes TRACE, an interpretable temporal phenotyping method that enables the learning of outcome-informed progression phenotypes from longitudinal trajectories. TRACE combines a trajectory- and outcome-aware contrastive objective with a probabilistic predictive phenotype layer, encouraging phenotypes to capture progression structure while remaining predictive of diagnostic state. A dual-attention mechanism further supports interpretation by identifying the visits and clinical variables most associated with each phenotype assignment. TRACE is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort for cognitive disease modeling, showing improved performance in both diagnostic prediction and phenotype discovery compared with other temporal phenotyping baselines. Finally, by allowing the number of phenotypes to exceed the diagnostic labels, TRACE enables discovering additional progression patterns that are not captured by labels defined a priori.

Background: School-based implementation of robot-assisted walking may support increased physical and social participation for children with physical disabilities, but evidence from an adequately powered trial is needed. This pilot study evaluated implementation strategies and study procedures to inform a future definitive trial. Methods: Participants were randomized to 12-weeks of robot-assisted walking or control, with subsequent crossover to the other condition. In the intervention arm, targeted dose was 75 minutes of robot-assisted walking, spread across three days/week. Implementation strategies for the child's classroom team included educational materials, centralized technical assistance, school champions, and on-going training. Implementation strategy evaluation focused on intervention protocol feasibility (i.e., weekly device use, troubleshooting) and fidelity (documentation of implementation strategy modifications). Preliminary estimates participation goal changes were obtained using the Canadian Occupational Performance Measure (COPM) 'Performance' scale (/10). Results: Eight children with neurodevelopmental physical disabilities participated (mean age 3.5, SD 0.5 years). Device use varied from 2.1 to 4.3 days/week (median 3.3) with a range of 48 to 96 minutes/week (median 80). Target use of >= 3 days/week was achieved for 66% of weeks and met the >=75-minute target for 33% of weeks. Troubleshooting occurred in 18.5% of sessions. Two implementation strategies were modified to improve feasibility. COPM mean change was 3.56 (SD 1.07) for robot-assisted walking and 2.11 (SD 2.41) for control (dz=0.74). Conclusions: This pilot study provided preliminary evidence regarding both the feasibility of robot-assisted walking implementation in schools and its potential effectiveness for children with physical disabilities. Findings support progression to a definitive trial.

Computed tomography (CT) interpretation requires recognition of the anatomical level of each slice. Classification may facilitate preprocessing and AI-assisted fracture diagnosis. We developed deep learning models to classify craniofacial CT slices into six anatomical categories. A total of 11,769 images were collected from a multicenter database involving 10 Japanese university hospitals and the public Head-Neck-Radiomics-HN1 dataset. Patients were divided into training (70%) and evaluation (30%) sets. Five CNN architectures were trained from scratch, and hard- and soft-voting ensembles were evaluated. Individual-model accuracy ranged from 94.72% to 96.09%; the hard-voting ensemble achieved 96.46% accuracy (Cohen's k = 0.954). Although performance differed among individual models (Cochran's Q = 99.29, p < 0.001), the ensemble did not significantly outperform EfficientNetV2B1 (McNemar's p = 0.163). Errors occurred mainly between adjacent anatomical regions. Deep learning can classify craniofacial CT slices accurately and may support automated dataset organization and AI-assisted fracture diagnosis. External validation is needed.

Objectives To evaluate discrepancies between radiologists and referring physicians in the interpretation of diagnostic probabilities conveyed by common Japanese expressions used in radiology reports. Materials and Methods Fifteen expressions commonly used to convey diagnostic probabilities in radiology reports were selected by five attending radiologists. An anonymous online survey was distributed to 26 radiologists and 33 referring physicians at a single institution. Participants assigned a diagnostic probability (from 0% to 100% in 10% increments) to each expression. Differences in median probabilities between radiologists and referring physicians were analyzed using the Mann-Whitney U test. Variability in interpretation was assessed using interquartile range (IQR), with IQR [&ge;] 30% defined as substantial variability. Results All radiologists (26/26) and 97% of referring physicians (32/33) completed the survey. Seven of the 15 expressions showed statistically significant differences in interpretation between radiologists and referring physicians: "c/w" (80% vs. 60%; p = 0.031), the Japanese equivalents of "present" (100% vs. 100%; p = 0.024), "suspect of" (80% vs. 70%; p = 0.007), "possibly" (50% vs. 70%; p < 0.001), "unlikely" (10% vs. 10%; p = 0.022), "cannot be ruled out" (25% vs. 40%; p < 0.001), and "not inconsistent with" (80% vs. 90%; p = 0.008). Substantial variability in interpretation (IQR [&ge;] 30%) was observed for four expressions: "cannot be ruled out" (IQR, 10%-40%), "s/o" (IQR, 60%-90%), "c/w" (IQR, 50%-90%), and "not inconsistent with" (IQR, 70%-100%). Conclusion This study revealed that nearly half of the Japanese expressions commonly used to convey diagnostic probabilities were interpreted differently by radiologists and referring physicians. These discrepancies highlight the need for a standardized lexicon to improve clarity and consistency in radiology reporting.

Background: Self-supervised learning may improve segmentation when labelled data are limited, but its benefit may depend on model and initialisation strategy. This study evaluated in-domain masked-reconstruction pretraining across limited annotation budgets. Methods: The International Skin Imaging Collaboration (ISIC) 2016 development set was partitioned into 765 images for self-supervised pretraining, 94 for fine-tuning and 41 for validation. Five nested annotation budgets (12-94 images) and five seeds were evaluated on the 379-image test set. A custom U-Net compared random and in-domain self-supervised initialisation; a ResNet-34 U-Net compared random, ImageNet, in-domain self-supervised and sequential ImageNet-to-self-supervised initialisation. Models trained with 94 labelled images were evaluated without adaptation on ISIC 2017. A separate experiment examined restoration-based pretraining. Results: In the custom U-Net, self-supervised pretraining achieved higher mean Dice than random initialisation at all five budgets, including 0.664 versus 0.615 with 12 labels and 0.811 versus 0.768 with 94 labels. Seed-level 95% confidence intervals for paired differences excluded zero at 47 and 94 labels but not at the other budgets. With 47 labels, the self-supervised model achieved mean Dice of 0.789, compared with 0.768 for random initialisation with 94 labels. In ResNet-34, ImageNet initialisation achieved higher mean Dice than in-domain self-supervised pretraining at all five budgets, and adding self-supervised pretraining after ImageNet reduced mean Dice at four of five budgets. All six 94-label configurations achieved lower mean Dice on ISIC 2017 than ISIC 2016. In the restoration experiment, mean Dice was 0.686 with random initialisation and 0.638-0.642 following pretraining. Conclusions: In-domain masked-reconstruction pretraining improved mean Dice relative to random initialisation in the custom U-Net, but not consistently in the ResNet-34 U-Net, where ImageNet initialisation performed better at every budget. Adding self-supervised pretraining after ImageNet provided no consistent gain. These findings are specific to the dermoscopic lesion-segmentation experiments and do not establish melanoma-specific diagnostic or clinical performance.

Background. Real-world 12-lead electrocardiograms (ECGs) often have missing or corrupted leads. A deep-learning classifier can be prepared for this by random lead masking during training, or by injecting clinical knowledge, for example by pulling its attention towards the leads that guidelines use for each diagnosis. Whether this knowledge adds robustness beyond masking is unknown. Methods. Pre-registered comparison of three arms sharing one network (per-lead 1D-ResNet encoder and per-diagnosis attention over the 12 leads): standard training (M0); random whole-lead masking (M1); masking plus a Kullback-Leibler penalty pulling attention towards a fixed guideline-derived key-lead map (M2, guideline-based attention guidance). Six diagnoses; five seeds per arm. Development on PTB-XL (21,799 ECGs); single sealed evaluation on PTB-XL fold 10 (2,198 ECGs) and on CODE-15% (233,204 exams, external validation). Primary endpoint: AUROC difference M2 - M1, averaged over first-degree AV block, right and left bundle branch block and atrial fibrillation and over 1 to 6 lost (zeroed) leads, with a patient-level paired BCa bootstrap 95% confidence interval. Results. The guidance did not change robustness: {Delta}AUROC -0.0010 (95% CI -0.0033 to +0.0006), an interval entirely within the pre-specified +-0.02 margin; the result was unchanged with another bootstrap seed, other interval methods and leave-one-diagnosis-out analyses. Masking improved AUROC: M1 - M0 = +0.0134 (95% CI +0.0102 to +0.0172) when one key lead was lost, and the number of lost leads tolerated before AUROC fell by more than 0.02 rose from 7 (M0) to 10 (M1). M2 attention matched the map and M2 was non-inferior on intact ECGs, but its calibration slope was lower for all six diagnoses in both datasets. M2 lost slightly more when all key leads were lost together (-0.0067) and gained only when one to three leads remained (exploratory; AUROC 0.9408 vs 0.9210 with 11 leads lost). CODE-15% reproduced every pattern (primary -0.0007, 95% CI -0.0011 to -0.0003). Conclusions. Random lead masking suffices to make an ECG classifier robust to missing leads; adding guideline knowledge aligns attention with clinical criteria but adds no robustness and worsens calibration. Guideline-aligned attention should not be taken as evidence of robustness.

Aims: Myocardial strain enables sensitive assessment of cardiac function, but its clinical application has largely focused on individual chambers or selected patient populations. We evaluated the feasibility and clinical relevance of fully automated multi-chamber strain assessment in consecutive patients undergoing routine transthoracic echocardiography (TTE). Methods and results: This retrospective study included 8,350 consecutive adults undergoing TTE. A hospital-wide artificial intelligence (AI)-based system automatically measured left ventricular (LV) global longitudinal strain (LVGLS), left atrial (LA) reservoir strain (LASr), and right ventricular (RV) free-wall strain (RVFWS). AI-derived LVGLS was available from at least one apical view in 97.1% of patients and from all three views in 94.8%; LASr and RVFWS were available in 94.1% and 94.5%, respectively, resulting in complete multi-chamber strain assessment in 90.3%. Strain measures showed modest correlations with conventional chamber-specific echocardiographic parameters and differential associations with clinical outcomes. Gaussian mixture modeling identified three distinct clusters characterized by preserved multi-chamber function, RV-dominant dysfunction, and pan-chamber dysfunction. Compared with the preserved cluster, pan-chamber dysfunction was associated with the highest risk of all-cause death or heart failure hospitalization (adjusted hazard ratio, 3.44; 95% CI, 2.43-4.88; P<0.001). Prognostic associations remained evident in patients with LV ejection fraction (LVEF) [&ge;]50%, and cluster assignment provided incremental prognostic information beyond clinical factors, LVEF, and RV fractional area change. Conclusions: Fully automated multi-chamber strain assessment was feasible in a large consecutive TTE cohort. Integrating strain across cardiac chambers may provide complementary functional characterization and identify clinically relevant clusters with prognostic information beyond conventional assessment.

Stroke is a leading cause of mortality and disability in Uganda, with a prevalence of approximately 2.5% and a 25-30% 30-day mortality rate, exacerbated by limited access to predictive tools and advanced diagnostics. Machine learning (ML) offers potential for early stroke risk stratification, but its application in resource-constrained settings like Uganda requires tailored models and rigorous performance evaluation, as well as assessment of misclassification patterns. This study aimed to develop and internally validate an ML-based predictive model for stroke using clinical and socio-demographic characteristics among patients at Mulago National Referral Hospital (MNRH) and residents of Wakiso District, Uganda, identify key predictors and assess misclassification patterns to enhance targeted prevention. A retrospective case-control study utilized secondary data from 1,016 participants (254 stroke cases, 762 controls) across three prior studies conducted between 2006 and 2015. Eight ML algorithms were evaluated using 5-fold cross-validation, with performance metrics including accuracy, sensitivity, positive predictive value, F1-score, and area under receiver operator characteristics curve (AU-ROC). McNemars test compared model classification performance of the top 2 models. Feature importance identified key predictors, and misclassification patterns were analyzed using classification matrix and line graphs. The Random Forest (RF) model achieved the highest performance (95.18% accuracy, 90.10% F1-score, 97% AU-ROC). McNemars test confirmed RFs superior classification (p=0.01). Age, systolic blood pressure, total cholesterol, and waist-hip ratio were the top drivers of RF stroke predictions. RF misclassified 8.3% of stroke cases and 3.3% of non-stroke cases, due to overlaps in risk profiles (e.g., lower cholesterol, systolic blood pressure and age in false negatives). The RF model demonstrates strong potential for stroke risk prediction in Uganda, leveraging routine data to prioritize high-risk individuals. Misclassification analysis highlights areas for model refinement, supporting its potential for integration into clinical workflows for early intervention and stroke prevention in resource-limited settings. Future external validation across diverse populations is recommended.

Objectives: Women's empowerment is a key determinant of health and well-being and may shape how women access and benefit from publicly-funded health insurance (PFHI). We aimed to examine whether different levels of women's empowerment were associated with 1) verification in India's PFHI Pradhan Mantri Jan Arogya Yojana (PM-JAY), 2) outpatient care utilization, and 3) resultant out-of-pocket expenditure. Design: We conducted a cross-sectional observational study. We analyzed data from a household survey, created a composite empowerment index using structural equation models, and used multivariate regression models to test associations between women's empowerment and the outcome variables. Setting: The study was conducted between December 2019 and February 2020 among PM-JAY eligible households in six Indian states (Bihar, Chhattisgarh, Gujarat, Meghalaya, Tamil Nadu, and Uttar Pradesh). Participants: 14,378 women across the six states. Results: Three main findings emerged: First, high levels of women's empowerment were associated with higher odds of completing PM-JAY verification (AOR: 1.22, 95% CI: 1.09-1.36). Second, women's empowerment was not associated with outpatient service utilization. And third, either medium levels of empowerment (coef = -0.49, p = 0.020) or PM-JAY verification (coef = -0.37, p = 0.034) was associated with lower OOPE for outpatient services. Women who had both, PM-JAY verification and medium levels of empowerment, experienced higher OOPE (coef = 0.45, p = 0.058). Conclusions: Women's empowerment is an important factor related with PM-JAY verification, but not with outpatient service use. OOPE varied depending on whether women were both empowered and PM-JAY verified or not. Our results suggest that institutional and structural barriers may play a greater role in healthcare access than individual factors pertaining to empowerment alone. Achieving equitable access therefore requires gender-responsive systems that reduce administrative barriers and support women in navigating the healthcare pathway. Our findings highlight the importance of integrating outpatient care into PM-JAY to increase financial protection, streamlining verification processes to improve women's engagement with PM-JAY and the broader health system, and advancing health financing reforms that better support women.