NPJ Digital Medicine最新文献

Contactless heart rate (HR) monitoring demonstrates significant potential for mobile health and telemedicine, but current remote photoplethysmography (rPPG) approaches remain vulnerable to various noise sources. While existing research has emphasized signal-level enhancement, correcting erroneous HR estimates remains underexplored. We present a plug-and-play adaptive correction algorithm that leverages cardiac dynamics constraints, adjusting HR estimates based on physiological priors of HR elevation and recovery. By mapping HR frequencies to indices and applying adaptive corrections, our method significantly reduces measurement errors with minimal computational load, even under challenging conditions. Across three public datasets, the algorithm increased the proportion of accurate measurements (mean absolute error ≤ 10 beats per minute) from 46.26% to 84.14% (LGI-PPGI), 48.03% to 69.21% (BUAA-MIHR), and 92.22% to 96.67% (UBFC-rPPG), outperforming existing correction techniques. The lightweight design facilitates seamless edge-side integration, providing a scalable solution for enhancing the reliability of contactless HR monitoring in mobile and remote healthcare settings.

Despite its low diagnostic yield, endomyocardial biopsy (EMB) remains the gold standard for establishing a definitive diagnosis in many cardiomyopathies. We developed and validated a machine-learning-based score to predict the likelihood of diagnostic EMB using non-invasive data. We retrospectively analyzed 775 heart failure patients who underwent EMB. A random forest algorithm was selected for score development based on superior discriminative performance. The model was externally validated in an independent cohort (n = 171). The study population was predominantly male (72.1%), with half of the patients in NYHA class III-IV. EMB yielded a definitive diagnosis in 19.9% of cases, most commonly amyloidosis (50%). A predictive score (0-100 range) was derived from key non-invasive predictors. Right ventricular late gadolinium enhancement (LGE) on cardiac magnetic resonance emerged as the strongest predictor, followed by left ventricular and atrial LGE, NTproBNP levels, and renal function. The model demonstrated excellent discrimination, with an area under the curve of 0.92 (95% CI = 0.89-0.96) in cross-validation and 0.91 (95% CI = 0.86-0.98) in the testing set, with consistent performance on external validation (AUC 0.82, 95% CI = 0.76-0.89). This machine-learning-based score may provide a non-invasive tool to support EMB decision-making in clinical practice.

This Perspective introduces 'Hang Hao Meng', an AI-powered sleep health expert agent for comprehensive patient management. Leveraging large language models, multimodal analytics, and a digital-human interface, it delivers end-to-end services from screening to personalized treatment. Deployed at scale, the agent has provided triage for over four million individuals and completed 90,000+ screenings, demonstrating a scalable model for enhancing accessibility and personalized care in sleep medicine.

The clinical deployment of artificial intelligence (AI) solutions for assessing cardiovascular disease (CVD) risk in 12-lead electrocardiography (ECG) is hindered by limitations in interpretability and explainability. To address this, we present xGNN4MI, an open-source framework for graph neural networks (GNNs) in ECG modeling for interpretable CVD prediction. Our framework facilitates modeling clinically relevant spatial relationships between ECG leads and their temporal dynamics. We integrated explainable AI (XAI) and developed a task-specific XAI evaluation and visualization workflow to identify ECG leads crucial to the model's decision-making process, enabling a systematic comparison with established clinical knowledge. We evaluated xGNN4MI on two challenging tasks: diagnostic superclass classification and localization of myocardial infarction. Our findings show that the interpretable ECG-GNN models demonstrate good performance across the tasks. XAI analysis revealed clinically meaningful training effects, such as differentiating between anteroseptal and inferior myocardial infarction. Our work demonstrates the potential of ECG-GNNs for providing trustworthy and interpretable AI-based CVD diagnosis.

Large language models (LLMs) show promising diagnostic and triage performance, yet direct comparisons with healthcare professionals (HCPs) and collaborative effects remain limited. We conducted a systematic review and meta-analysis of studies (January 2020 to September 2025) comparing the diagnostic or triage accuracy of LLMs, HCPs, or their collaboration across seven databases. Studies using multiple-choice formats rather than open diagnostic generation were excluded. We extracted top-1, top-3, top-5, and top-10 diagnostic and triage accuracies and pooled results using multilevel random-effects models to account for nested observations. Of 10,398 studies screened, 50 met criteria, evaluating 25 different LLMs across diverse medical specialties. The relative diagnostic accuracy of LLMs versus HCPs progressively improved from 0.89 (95% CI, 0.79-1.00) for top-1 to 0.91 (0.83-1.00) for top-3, 1.04 (0.89-1.22) for top-5, and 1.17 (0.87-1.57) for top-10 diagnoses, with significant model variability. LLM-assisted HCPs outperformed HCPs alone, with relative diagnostic accuracy of 1.13 (1.00-1.27) for top-1, 1.11 (1.01-1.23) for top-3, 1.42 (1.16-1.73) for top-5, and 1.33 (0.94-1.87) for top-10 diagnoses. Triage accuracy was similar between LLMs and HCPs (1.01 [0.94-1.09]). These findings show potential for LLM integration but methodological flaws in studies necessitate rigorous real-world evaluation before clinical implementation.

Intracranial aneurysms (IAs) are life-threatening vascular conditions requiring accurate risk assessment to guide treatment. Hemodynamic biomarkers such as wall shear stress and oscillatory shear index are promising predictors of rupture risk but remain underused clinically due to the high computational cost of traditional CFD methods. We propose a physics-constrained graph neural network (GNN) framework trained on high-fidelity CFD data to predict full 3D, time-resolved hemodynamic fields throughout the cardiac cycle. Our model incorporates enhanced node features and physics-based constraints to capture complex spatio-temporal flow behavior in near real time. It generalizes to varying inflow conditions and unseen patient-specific geometries with no fine-tuning. Additionally, we release a benchmark dataset of 105 patient-derived aneurysm geometries with CFD fields to support the machine learning (ML) community. This is the first GNN model applied to transient 3D aneurysmal flow prediction, paving the way for rapid, AI-driven hemodynamic analysis toward risk stratification and treatment planning.

Wearable electroencephalography (EEG) devices are miniaturized, portable, and wireless systems for long-term brain monitoring, demonstrating significant potential as accessible mild cognitive impairment (MCI) screening tools based on objective neurophysiological biomarkers. However, their performance in MCI detection remains unclear, and their translation to real-world applications faces several challenges. This study aimed to comprehensively evaluate wearable EEG for MCI detection, identify key characteristics that optimize classification performance and usability, and address gaps in effective design implementation. We conducted a systematic search across seven databases, screening 1562 records and analyzing 21 studies that examined 16 distinct wearable EEG devices for MCI detection. The results revealed considerable variation in classification accuracy (range: 46-95%). A system-level analysis of the entire wearable EEG system and data flow identified seven critical factors that optimize the trade-off between diagnostic performance, portability, and affordability: (1) moderate channel density; (2) frontal and parietal electrode placement; (3) elderly-friendly multi-domain cognitive tasks; (4) adaptive signal preprocessing; (5) multi-domain feature extraction; (6) ensemble classifiers; and (7) multimodal integration. Additionally, methodological considerations for future wearable EEG-based MCI detection research include: (1) standardize MCI diagnostic frameworks; (2) increase sample diversity; (3) optimizing device usability and technical specifications; (4) standardize recording protocols; (5) harmonizing data processing pipelines; (6) validate in real-world settings; (7) assess cost-effectiveness; and (8) implement comprehensive reporting guidelines. These insights enable further translational applications of wearable EEG-based MCI detection and provide a foundation for developing user-friendly systems that could transform early cognitive impairment screening in community and primary care settings.