State-of-the-art automatic atrial fibrillation (AF) detection models trained on RR-interval (RRI) features generally produce high performance on standard benchmark electrocardiogram (ECG) AF datasets. These models, however, result in a significantly high false positive rates (FPRs) when applied on ECG data collected under free-living ambulatory conditions and in the presence of non-AF arrhythmias. This paper proposes DeepAware, a novel hybrid model combining deep learning (DL) and context-aware heuristics (CAH), which reduces the FPR effectively and improves the AF detection performance on participant-operated ambulatory ECG from free-living conditions. It exploits the RRI and P-wave features, as well as the contextual features from the ambulatory ECG. DeepAware is shown to be very generalizable and superior to the state-of-the-art models when applied on unseen benchmark ECG AF datasets. Most importantly, the model is able to detect AF efficiently when applied on participant-operated ambulatory ECG recordings from free-living conditions and has achieved a sensitivity (Se), specificity (Sp), and accuracy (Acc) of 97.94%, 98.39%, 98.06%, respectively. Results also demonstrate the effect of atrial activity analysis (via P-waves detection) and CAH in reducing the FPR over the RRI features-based AF detection model. The proposed DeepAware model can substantially reduce the physician's workload of manually reviewing the false positives (FPs) and facilitate long-term ambulatory monitoring for early detection of AF.

Consumer‐grade optical heart rate (HR) sensors emerged as promising tools to monitor volume and intensity of physical activity (PA). However, no validation study of optical HR sensors included recent comprehensive validation recommendations, required for facilitating usage for medical purposes. Validity of HR data measured with four consumer‐grade optical sensors, the wrist‐worn Garmin Venu 2S and Polar Vantage M2, and the upper arm‐worn Polar Verity Sense and Scosche Rhythm24 were assessed in 32 participants over 24 h including various laboratory‐based and free‐living activities. Furthermore, validity of time at moderate or vigorous PA intensity zones was analyzed. A medical‐grade ECG served as a reference. Reliability was assessed by analyzing data of laboratory‐based activities during two visits. Across activities, the mean absolute percentage error ranged from 2.2% to 4.7% and intraclass correlation coefficients ranged from 0.91 to 0.98, indicating high validity for all optical sensors. All sensors validly detected time spent at moderate or vigorous intensities (mean error < 10%), except Polar M2 for moderate PA (mean error 12.8%) and Garmin V2 for vigorous PA (mean error −15.9%). Sensor day‐to‐day reliability was high, indicated by a mean absolute error of < 5 beats/min. Upper arm‐worn sensors consistently outperformed wrist‐worn sensors, particularly in activities involving increased arm movement and at higher intensities. Our findings identified an overall high validity of these four consumer‐grade optical HR sensors, also for assessing time spent at higher PA intensities. However, differences were observed between sensors regarding activity subtypes and intensity levels. These data support informed decisions when selecting optical sensors for PA monitoring and intervention.Trial Registration: The study was performed in compliance with the Declaration of Helsinki and its current amendments and was prospectively registered at ClinicalTrials.gov (ID NCT05525000).

Background: There has been a surge in the development of apps that aim to improve health, physical activity (PA), and well-being through behavior change. These apps often focus on creating a long-term and sustainable impact on the user. Just-in-time adaptive interventions (JITAIs) that are based on passive sensing of the user’s current context (eg, via smartphones and wearables) have been devised to enhance the effectiveness of these apps and foster PA. JITAIs aim to provide personalized support and interventions such as encouraging messages in a context-aware manner. However, the limited range of passive sensing capabilities often make it challenging to determine the timing and context for delivering well-accepted and effective interventions. Ecological momentary assessment (EMA) can provide personal context by directly capturing user assessments (eg, moods and emotions). Thus, EMA might be a useful complement to passive sensing in determining when JITAIs are triggered. However, extensive EMA schedules need to be scrutinized, as they can increase user burden. Objective: The aim of the study was to use machine learning to balance the feature set size of EMA questions with the prediction accuracy regarding of enacting PA. Methods: A total of 43 healthy participants (aged 19‐67 years) completed 4 EMA surveys daily over 3 weeks. These surveys prospectively assessed various states, including both motivational and volitional variables related to PA preparation (eg, intrinsic motivation, self-efficacy, and perceived barriers) alongside stress and mood or emotions. PA enactment was assessed retrospectively via EMA and served as the outcome variable. Results: The best-performing machine learning models predicted PA engagement with a mean area under the curve score of 0.87 (SD 0.02) in 5-fold cross-validation and 0.87 on the test set. Particularly strong predictors included self-efficacy, stress, planning, and perceived barriers, indicating that a small set of EMA predictors can yield accurate PA prediction for these participants. Conclusions: A small set of EMA-based features like self-efficacy, stress, planning, and perceived barriers can be enough to predict PA reasonably well and can thus be used to meaningfully tailor JITAIs such as sending well-timed and context-aware support messages.

BACKGROUND Advancements in technologies and increased adoption of wearables and smartphones by individuals have led to an abundance of patient-generated healthcare data. These data, when used effectively, could help to further augment the process of shared decision-making to enable patient-centred care. However, the possible utilization of patient-generated (health) data (PGHD) introduces complexities and challenges which warrant considering both health care professional and patient perspectives. OBJECTIVE Summarize the relevant works in the past 10 years from the perspectives of the key stakeholders – healthcare professionals (HCPs) and patients (PATs) - on potential barriers and enablers to the integration of PGHD for shared decision-making. By looking at both perspectives, we are able to identify the key challenges and opportunities with PGHD throughout the patient’s journey. METHODS Electronic searches were done 3 databases – PubMed, ACM Digital Library and IEEE. Enablers and barriers mentioned by the stakeholders in included papers were extracted. Thematic analysis was performed using a qualitative analysis software, MaxQDA. The six-stage workflow model initially proposed by West at al was used as a reference for deductive coding. Subsequently, considering barriers and enablers faced by both the HCPs and PATs uncovered various tensions and alignments of perspectives which could be addressed in future work and can inform concepts, designs and development in the area of PGHD for shared decision-making. RESULTS Fifty-three publications were included in the scoping review. Six main overarching themes for barriers and enablers were identified: 1) Patient-Provider Relationship, 2) Patient Characteristics, 3) Organizational Factors, 4) Medical Ethics and Law, 5) Data-driven workflow and 6) Design and Technology. The six-stage workflow was further expanded based on the new findings.to include four additional stages which include contextual considerations outside of traditional clinical environments. In addition to partially corroborating previously established barriers in the six-stage workflow model, several new barriers and enablers were identified throughout all stages. This model helps to further align needs of HCPs and PATs beyond the clinical setting and could benefit system designers who plan to integrate DHTs involving PGHD for shared decision making. CONCLUSIONS This scoping review demonstrates that there are several factors to consider for effectively integrating PGHD in health-related shared decision-making. Notably, such factors extend outside the boundaries of traditional clinical settings. Although there is agreement between HCPs and PATs on certain factors, there are also tensions to be addressed. Our findings suggest that apart from lifting the barriers to the integration of PGHD, there can be a role for digital health technologies in mediating alignment between HCPs and PATs on effectively using PGHD for SDM.