NPJ Digital Medicine最新文献

Hypomimia is a prominent, levodopa-responsive symptom in Parkinson’s disease (PD). In our study, we aimed to distinguish ON and OFF dopaminergic medication state in a cohort of PD patients, analyzing their facial videos with a unique, interpretable Dual Stream Transformer model. Our approach integrated two streams of data: facial frame features and optical flow, processed through a transformer-based architecture. Various configurations of embedding dimensions, dense layer sizes, and attention heads were examined to enhance model performance. The final model, trained on 183 PD patients, attained an accuracy of 86% in differentiating between ON- and OFF-medication state. Moreover, uniform classification performance (up to 88%) was obtained across various stages of PD severity, as expressed by the Hoehn and Yahr (H&Y) scale. These values highlight the potential of our model as a non-invasive, cost-effective instrument for clinicians to remotely and accurately detect patients’ response to treatment from early to more advanced PD stages.

The climate crisis underscores the need for weather-based predictive analytics in healthcare, as weather factors contribute to ~11% of the global stroke burden. Therefore, we developed machine learning models using locoregional weather data to forecast daily acute ischemic stroke (AIS) admissions. An AIS cohort of 7914 patients admitted between 2015 and 2021 at the tertiary University Medical Center Mannheim, Germany, with a 600,000-population catchment area, was geospatially matched to German Weather Service data. Poisson regression, boosted generalized additive models, support vector machines, random forest, and extreme gradient boosting (XGB) were evaluated within a time-stratified nested cross-validation framework. XGB performed best (mean absolute error: 1.21 cases/day). Maximum air pressure was the top predictor, with temperature exhibiting a bimodal link. Cold and heat stressor days (T_{min_lag3} < −2 °C; T_perceived < −1.4 °C; T_{min_lag7} > 15 °C) and stormy conditions (wind gusts > 14 m/s) increased stroke admissions. This generalizable framework could aid real-time hospital planning, effective care and forecasting of various weather-related disease burdens.

Extreme heat events pose a significant health threat to vulnerable populations such as the elderly and those living with disease. Recent extreme heat events highlight that heat-related mortality often occurs indoors, urging a need to better understand how at-risk populations physiologically and behaviorally respond in their natural environment. However, a low-cost and scalable all-in-one solution to comprehensively monitor individuals during periods of extreme heat does not presently exist. We developed HeatSuite, a fully data-governed multimodal sensor platform, that can monitor the local environmental conditions, and physiological and behavioural responses, of free-living individuals. Compliance to the platform was assessed over 28 days among 21 older individuals living in low-income housing (70 ± 7 y, body mass index: 28.7 ± 6.3). Moderate (>77%) to near optimal (94%) compliance was observed among the physiological and perceptual metrics obtained. In conclusion, HeatSuite is an effective and comprehensive solution for at-home monitoring of at-risk populations.

The rapid increase in patient portal messaging has heightened the workload for primary care physicians (PCPs), contributing to burnout. The use of generative artificial intelligence (AI) to draft responses to patient messages has shown promise in reducing cognitive burden, yet there is still much unknown about the safety and perceptions of using AI drafts. This cross-sectional simulation study assessed whether PCPs could identify and correct errors in AI-generated draft responses to patient portal messages. Twenty practicing PCPs reviewed 18 patient portal messages, four of which contained errors categorized as objective inaccuracies or potentially harmful omissions. Each error was insufficiently addressed by 13–15 participants, and 35–45% of erroneous drafts were submitted entirely unedited. While 80% of participants agreed AI drafts reduced cognitive workload and 75% found them safe, uncorrected errors highlight patient safety risks, underscoring the need for improved design, training, and error-detection mechanisms for AI tools.

Accurate assessment of progression and disease course in multiple sclerosis (MS) is vital for timely and appropriate clinical intervention. The gradual transition from relapsing-remitting MS (RRMS) to secondary progressive MS (SPMS) is often diagnosed retrospectively with a typical delay of three years. To address this diagnostic delay, we developed a predictive model that uses electronic health records to distinguish between RRMS and SPMS at each individual visit. To enable reliable predictions, conformal prediction was implemented at the individual patient level with a confidence of 93%. Our model accurately predicted the change in diagnosis from RRMS to SPMS for patients who transitioned during the study period. Additionally, we identified new patients who, with high probability, are in the transition phase but have not yet received a clinical diagnosis. Our methodology aids in monitoring MS progression and proactively identifying transitioning patients. An anonymized model is available at https://msp-tracker.serve.scilifelab.se/.

The Global Initiative on Artificial Intelligence for Health (GI-AI4H), established by the World Health Organization, serves to harmonize governance standards for artificial intelligence (AI). The GI-AI4H spearheads novel on-the-ground efforts, especially in low- and middle-income countries, to advance ethical, regulatory, implementation, and operational dimensions of global governance for health AI. The GI-AI4H’s efforts across the United Nations drives safe, ethical, equitable, and sustainable health AI use for the global community.

Neurostimulation for cardiovascular control faces challenges due to the lack of predictive modeling for stimulus-driven dynamic responses, which is crucial for precise neuromodulation via quality feedback. We address this by employing a digital twin approach that leverages computational mechanisms underlying neuro-hemodynamic responses during neurostimulation. Our results emphasize the computational role of the nucleus tractus solitarius (NTS) in the brainstem in determining these responses. The intrinsic neural circuit within the NTS harbors collective dynamics residing in a low-dimensional latent space, which effectively captures stimulus-driven hemodynamic perturbations. Building on this, we developed a digital twin framework for individually optimized predictive modeling of neuromodulatory outcomes. This framework potentially enables the design of closed-loop neurostimulation systems for precise hemodynamic control. Consequently, our digital twin based on neural computation mechanisms marks an advancement in the artificial regulation of internal organs, paving the way for precise translational medicine to treat chronic diseases.

Understanding reasons for treatment switching is of significant medical interest, but these factors are often only found in unstructured clinical notes and can be difficult to extract. We evaluated the zero-shot abilities of GPT-4 and eight other open-source large language models (LLMs) to extract contraceptive switching information from 1964 clinical notes derived from the UCSF Information Commons dataset. GPT-4 extracted the contraceptives started and stopped at each switch with microF1 scores of 0.85 and 0.88, respectively, compared to 0.81 and 0.88 for the best open-source model. When evaluated by clinical experts, GPT-4 extracted reasons for switching with an accuracy of 91.4% (2.2% hallucination rate). Transformer-based topic modeling identified patient preference, adverse events, and insurance coverage as key reasons. These findings demonstrate the value of LLMs in identifying complex treatment factors and provide insights into reasons for contraceptive switching in real-world settings.

Virtual walking has the potential to be an adjunct to traditional physical therapy. This scoping review aims to synthesize evidence on the characteristics, effectiveness, feasibility, and neurological mechanism of virtual walking interventions on health-related outcomes. Articles in English were retrieved from twelve databases (January 2014–October 2024). Thirteen interventional studies were included, focusing on three types of virtual walking: passive observing moving (71.4%), arm swing locomotion (21.5%), and foot tracking locomotion (7.1%). Most studies (84.6%) involved individuals with spinal cord injuries, while the remaining studies focused on lower back pain (7.7%) and lower limb pain (7.7%). Over 70% of studies lasted 11–20 min, 1–5 weekly sessions for 10–14 days. Statistically significant findings included pain reduction (84.6%), improved physical function (mobility and muscle strength), and reduced depression. Mild adverse effects (fatigue and dizziness) were transient. Neurological evidence indicates somatosensory cortex activation during virtual walking, possibly linked to neuropathic pain.

The COVID-19 pandemic accelerated the adoption of telehealth and remote monitoring in obstetric care. This study assessed pregnant patients’ perceptions before and after using a novel non-invasive fetal electrocardiogram (NI-FECG) device. The trial is prospectively registered on the Australia New Zealand Clinical Trials Registry (ANZCTRN12621001260819; submitted June 9th, 2021; approved September 17th, 2021). Seventy participants from 36 weeks’ gestation completed pre- and post-use surveys. Interest in continuous and home fetal monitoring was high (79% and 90%, respectively). Post-use, 89% reported satisfaction; over 90% comfortable wearing and removing the sensor. Extended use was acceptable to 76%, and only 3% reported high skin irritation. Sentiment analysis highlighted themes of reassurance, convenience, and reduced anxiety. Some suggested smaller, wireless design. Analysis by natural language processing and clustering provided deeper insights. Findings support strong interest in at-home fetal monitoring; further refinement and education are needed to enhance acceptability. Future research should assess long-term effects on anxiety and clinical outcomes.