JMIR Cardio最新文献

Unlabelled: Electrocardiography is an essential tool in the arsenal of medical professionals, Traditionally, patients have been required to meet health care practitioners in person to have an electrocardiogram (ECG) recorded and interpreted. This may result in paroxysmal arrhythmias being missed, as well as decreased patient convenience, and thus reduced uptake. The advent of wearable ECG devices built into consumer smartwatches has allowed unparalleled access to ECG monitoring for patients. Not only are these modern devices more portable than traditional Holter monitors, but with the addition of artificial intelligence (AI)-led rhythm interpretation, diagnostic accuracy is improved greatly when compared with conventional ECG-machine interpretation. The improved wearability may also translate into increased rates of detected arrhythmias. Despite the many positives, wearable ECG technology brings with it its own challenges. Diagnostic accuracy, managing patient expectations and limitations, and incorporating home ECG monitoring into clinical guidelines have all arisen as challenges for the modern clinician. Decentralized monitoring and patient alerts to supposed arrhythmias have the potential to increase patient anxiety and health care visitations (and therefore costs). To better obtain meaningful data from these devices, provide optimal patient care, and provide meaningful explanations to patients, providers need to understand the basic sciences underpinning these devices, how these relate to the surface ECG, and the implications in diagnostic accuracy. This review article examines the underlying physiological principles of electrocardiography, as well as examines how wearable ECGs have changed the clinical landscape today, where their limitations lie, and what clinicians can expect in the future with their increasing use.

Background: Hypertension is a leading cause of cardiovascular disease and premature death worldwide, and it puts a heavy burden on the healthcare system. Therefore, it is very important to detect and evaluate hypertension and related cardiovascular events to enable early prevention, detection, and management. Hypertension can be detected in a timely manner with cardiac signals, such as through an electrocardiogram (ECG) and photoplethysmogram (PPG) , which can be observed via wearable sensors. Most previous studies predicted hypertension from ECG and PPG signals with extracted features that are correlated with hypertension. However, correlation is sometimes unreliable and may be affected by confounding factors .

Objective: The aim of this study was to investigate the feasibility of predicting the risk of hypertension by exploring features that are causally related to hypertension via causal inference methods. Additionally, we paid special attention to and verified the reliability and effectiveness of causality compared to correlation.

Methods: We used a large public dataset from the Aurora Project , which was conducted by Microsoft Research. The dataset included diverse individuals who were balanced in terms of gender, age, and the condition of hypertension, with their ECG and PPG signals simultaneously acquired with wrist -worn wearable devices. We first extracted 205 features from the ECG and PPG signals, calculated 6 statistical metrics for these 205 features, and selected some valuable features out of the 205 features under each statistical metric. Then, 6 causal graphs of the selected features for each kind of statistical metric and hypertension were constructed with the equivalent greedy search algorithm. We further fused the 6 causal graphs into 1 causal graph and identified features that were causally related to hypertension from the causal graph . Finally, we used these features to detect hypertension via machine learning algorithms.

Results: We validated the proposed method on 405 subjects. We identified 24 causal features that were associated with hypertension. The causal features could detect hypertension with an accuracy of 89%, precision of 92 % , and recall of 82%, which outperformed detection with correlation features (accuracy of 85%, precision of 88 % , and recall of 77%).

Conclusions: The results indicated that the causal inference -based approach can potentially clarify the mechanism of hypertension detection with noninvasive signals and effectively detect hypertension. It also reveal ed that causality can be more reliable and effective than correlation for hypertension detection and other application scenarios.

Background: Medication nonadherence remains a significant challenge in the management of chronic conditions, often leading to suboptimal treatment outcomes and increased health care costs. Innovative interventions that address the underlying factors contributing to nonadherence are needed. Gamified mobile apps have shown promise in promoting behavior change and engagement.

Objective: This pilot study aimed to evaluate the efficacy and usability of a gamified mobile app that used a narrative storytelling approach to enhance medication adherence among patients following acute coronary syndrome (ACS). The study aimed to assess changes in participants' beliefs about medication and self-reported adherence before and after the intervention. Additionally, user feedback regarding the narrative component of the app was gathered.

Methods: Overall, 18 patients who recently experienced ACS were recruited for a 1-month intervention using the gamified app. Participants' beliefs about medication and self-reported adherence were assessed using standardized scales pre- and postintervention. The app's usability was also evaluated through a postintervention questionnaire. Statistical analyses were performed to determine the significance of changes in belief and adherence scores.

Results: Although 33% (6/18) of the participants did not use the intervention more than once, the remaining 12 remained engaged during the 30 days of the study. The results did not indicate a significant improvement in participants' beliefs about medication following the intervention. However, self-reported adherence significantly improved (P<.05) after the intervention with a mean score going from 29.1 (SD 6.9) to 32.4 (SD 5.6), with participants demonstrating a greater self-efficacy to their prescribed medication regimen. However, the results did not indicate a significant improvement in participants' beliefs about medication. With a mean average score of 80.6, the usability evaluation indicates a good usability rating for the gamified app. However, the narrative storytelling component of the app was not favored by the participants, as indicated by their feedback.

Conclusions: This pilot study suggests that a gamified mobile app using narration may effectively enhance medication self-efficacy and positively influence patients' beliefs about medication following ACS. However, the narrative component of the app did not receive favorable feedback from participants. Future research should focus on exploring alternative methods to engage participants in the app's narrative elements while maintaining the positive impact on adherence and beliefs about medication observed in this study.