Unsupervised deep learning of electrocardiograms enables scalable human disease profiling.

The 12-lead electrocardiogram (ECG) is inexpensive and widely available. Whether conditions across the human disease landscape can be detected using the ECG is unclear. We developed a deep learning denoising autoencoder and systematically evaluated associations between ECG encodings and ~1,600 Phecode-based diseases in three datasets separate from model development, and meta-analyzed the results.

Reliability of an "At-Home" Method for Monitoring Resting and Reactive Autonomic Nervous System Activity in Children: A Pilot Study.

Background: Heart rate variability (HRV), an index of the functional status of the autonomic nervous system (ANS), provides an opportunity for early detection of ANS dysfunction. Lower resting, vagally related HRV parameters are associated with increased risk of physical and mental illness. External factors influencing the ANS, such as the testing environment, may impact the interpretation of HRV.

Characteristics and Attitudes of Wearable Device Users and Nonusers in a Large Health Care System.

Background: Consumer wearable devices with health and wellness features are increasingly common and may enhance disease detection and management. Yet studies informing relationships between wearable device use, attitudes toward device data, and comprehensive clinical profiles are lacking.

Methods And Results: WATCH-IT (Wearable Activity Tracking for Comprehensive Healthcare-Integrated Technology) studied adults receiving longitudinal primary or ambulatory cardiovascular care in the Mass General Brigham health care system from January 2010 to July 2021.

Feasibility of an electronic fluid balance chart to detect and understand the significance of oliguric acute kidney injury in a general ward setting: a prospective observational cohort study.

Background: Outside critical care environments, few studies have assessed the significance of oliguric acute kidney injury (AKI). This study investigated the feasibility of an electronic fluid balance chart to diagnose oliguric AKI. Data were used to determine if oliguric AKI was met earlier than creatinine AKI and to establish outcomes of those who developed AKI.

The Hospital to Home study (H2H): smartwatch technology-enabled rehabilitation following hip fracture in older adults, a feasibility non-randomised trial.

Introduction: Hip fractures are associated with significant morbidity and mortality. This study assessed the feasibility of smartwatches supporting rehabilitation post-surgical fixation.

Methods: This UK-based non-randomised intervention study recruited patients who had sustained a hip fracture (age ≥65 and Abbreviated Mental Test Score ≥8/10), following surgical fixation, at one hospital to the intervention group, and at a second hospital to a usual care group.