NPJ Digital Medicine最新文献

The quality of healthcare services is influenced by a multitude of unpredictable events. Changes in patient clinical conditions and challenges in service organization are only some of the vivid examples that can make the management in healthcare difficult. Estimating patient journeys, known as clinical pathways (CPs), can support care providers in resource planning and enhancing service efficiency. This study presents a decision support system to assist clinicians in predicting CPs and outcomes for patients with traumatic brain injuries (TBIs). This machine learning framework employs an optimal decision tree next to a Markov-based trace clustering as predictive model components. A Shapely value approach extract knowledge of features contribution at both individual and population levels. The proposed approach is validated through a real-life event data, demonstrating high accuracy and providing insights into the rationale behind specific CP predictions which facilitate the adoption of machine learning models in clinical settings.

Heart failure (HF) is a highly heterogeneous condition, and current methods struggle to synthesize extensive clinical data for personalized care. Using data from 343 HF patients, we developed mechanistic computational models of the cardiovascular system to create digital twins. These twins, consisting of optimized measurable and unmeasurable parameters alongside simulations of cardiovascular function, provided comprehensive representations of individual disease states. Unsupervised machine learning applied to digital twin-derived features identified interpretable phenogroups and mechanistic drivers of cardiovascular death risk. Incorporating these features into prognostic AI models improved performance, transferability, and interpretability compared to models using only clinical variables. This framework demonstrates potential to enhance prognosis and guide therapy, paving the way for more precise, individualized HF management.

With rapidly evolving artificial intelligence solutions, healthcare organizations need an implementation roadmap. A “clinical trials” informed approach can promote safe and impactful implementation of artificial intelligence. This framework includes four phases: (1) Safety; (2) Efficacy; (3) Effectiveness and comparison to an existing standard; and (4) Monitoring. Combined with inter-institutional collaboration and national funding support, this approach will advance safe, usable, effective, and equitable deployments of artificial intelligence in healthcare.

Despite the high accuracy of AI-based automated analysis of 12-lead ECG images for classification of cardiac conditions, clinical integration of such tools is hindered by limited interpretability of model recommendations. We aim to demonstrate the feasibility of a generic, clinical resource interpretability tool for AI models analyzing digitized 12-lead ECG images. To this end, we utilized the sensitivity of the Jacobian matrix to compute the gradient of the classifier for each pixel and provide medical relevance interpretability. Our methodology was validated using a dataset consisting of 79,226 labeled scanned ECG images, 11,316 unlabeled and 1807 labeled images obtained via mobile camera in clinical settings. The tool provided interpretability for both morphological and arrhythmogenic conditions, highlighting features in terms understandable to physician. It also emphasized significant signal features indicating the absence of certain cardiac conditions. High correlation was achieved between our method of interpretability and gold standard interpretations of 3 electrophysiologists.

Critically ill children who require inter-hospital transfers to paediatric intensive care units are sicker than other admissions and have higher mortality rates. Current transport practice primarily relies on early clinical assessments within the initial hours of transport. Real-time mortality risk during transport is lacking due to the absence of data-driven assessment tools. Addressing this gap, our research introduces the PROMPT (Patient-centred Real-time Outcome monitoring and Mortality PredicTion), an explainable end-to-end machine learning pipeline to forecast 30-day mortality risks. The PROMPT integrates continuous time-series vital signs and medical records with episode-specific transport data to provide real-time mortality prediction. The results demonstrated that with PROMPT, both the random forest and logistic regression models achieved the best performance with AUROC 0.83 (95% CI: 0.79–0.86) and 0.81 (95% CI: 0.76–0.85), respectively. The proposed model has demonstrated proof-of-principle in predicting mortality risk in transported children and providing individual-level model interpretability during inter-hospital transports.

Pulsed radio frequency energy (PRFE) therapy is a non-invasive, electromagnetic field-based treatment modality successfully used in clinical applications. However, conventional PRFE devices are often bulky, expensive, and require extended treatment durations, limiting patient adherence and efficacy. Here, we present a lightweight, cost-effective wearable PRFE system consisting of a flexible electronic bandage and a smartphone. The bandage, mainly composed of an NFC Frequency Doubler (NFD) and a Radiofrequency Energy Radiator (RER), is powered and administered by the smartphone to generate 27.12 MHz radio wave pulses, for simplified, smartphone-enabled PRFE therapy. Its ultra-flexible, battery-free design supports personalized wound care at a low-cost (<US$1). Both electromagnetic field simulation and measurement demonstrated that the proposed PRFE bandage achieves the field strength of clinical-grade PRFE equipment. In rat full-thickness wound models, PRFE therapy improved wound closure rates by ~20%, with enhanced re-epithelialization and angiogenesis compared to controls.

Distributed learning enables collaborative machine learning model training without requiring cross-institutional data sharing, thereby addressing privacy concerns. However, local quality control variability can negatively impact model performance while systematic human visual inspection is time-consuming and may violate the goal of keeping data inaccessible outside acquisition centers. This work proposes a novel self-supervised method to identify and eliminate harmful data during distributed learning model training fully-automatically. Harmful data is defined as samples that, when included in training, increase misdiagnosis rates. The method was tested using neuroimaging data from 83 centers for Parkinson’s disease classification with simulated inclusion of a few harmful data samples. The proposed method reliably identified harmful images, with centers providing only harmful datasets being easier to identify than single harmful images within otherwise good datasets. While only evaluated using neuroimaging data, the presented method is application-agnostic and presents a step towards automated quality control in distributed learning.

Depression in older adults is often underdiagnosed and has been linked to adverse outcomes, including motor vehicle crashes. With a growing population of older drivers in the United States, innovations in screening methods are needed to identify older adults at greatest risk of decline. This study used machine learning techniques to analyze real-world naturalistic driving data to identify depression status in older adults and examined whether specific demographics and medications improved model performance. We analyzed two years of GPS data from 157 older adults, including 81 with major depressive disorder, using XGBoost and logistic regression models. The top-performing model achieved an area under the curve of 0.86 with driving features combined with total medication use. These findings suggest that naturalistic driving data holds high potential as a functional digital neurobehavioral marker for AI identifying depression in older adults on a national scale, thereby ensuring equitable access to treatment.