Search for: All records

Abstract BackgroundAtrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and effective management are crucial. Importantly, obstructive sleep apnea is highly prevalent among AF patients (60–90%); therefore, electrocardiogram (ECG) analysis from polysomnography (PSG), a standard diagnostic tool for subjects with suspected sleep apnea, presents a unique opportunity for the early prediction of AF. Our goal is to identify individuals at a high risk of developing AF in the future from a single-lead ECG recorded during standard PSGs. MethodsWe analyzed 18,782 single-lead ECG recordings from 13,609 subjects at Massachusetts General Hospital, identifying AF presence using ICD-9/10 codes in medical records. Our dataset comprises 15,913 recordings without a medical record for AF and 2,056 recordings from patients who were first diagnosed with AF between 1 day to 15 years after the PSG recording. The PSG data were partitioned into training, validation, and test cohorts. In the first phase, a signal quality index (SQI) was calculated in 30-second windows and those with SQI<0.95 were removed. From each remaining window, 150 hand-crafted features were extracted from time, frequency, time-frequency domains, and phase-space reconstructions of the ECG. A compilation of 12 statistical features summarized these window-specific features per recording, resulting in 1,800 features. We then updated a pre-trained deep neural network and data from the PhysioNet Challenge 2021 using transfer-learning to discriminate between recordings with and without AF using the same Challenge data. The model was applied to the PSG ECGs in 16-second windows to generate the probability of AF for each window. From the resultant probability sequence, 13 statistical features were extracted. Subsequently, we trained a shallow neural network to predict future AF using the extracted ECG and probability features. ResultsOn the test set, our model demonstrated a sensitivity of 0.67, specificity of 0.81, and precision of 0.3 for predicting AF. Further, survival analysis for AF outcomes, using the log-rank test, revealed a hazard ratio of 8.36 (p-value of 1.93 × 10⁻⁵²). ConclusionsOur proposed ECG analysis method, utilizing overnight PSG data, shows promise in AF prediction despite a modest precision indicating the presence of false positive cases. This approach could potentially enable low-cost screening and proactive treatment for high-risk patients. Ongoing refinement, such as integrating additional physiological parameters could significantly reduce false positives, enhancing its clinical utility and accuracy. 

Abstract BackgroundThe expanding usage of complex machine learning methods such as deep learning has led to an explosion in human activity recognition, particularly applied to health. However, complex models which handle private and sometimes protected data, raise concerns about the potential leak of identifiable data. In this work, we focus on the case of a deep network model trained on images of individual faces. Materials and methodsA previously published deep learning model, trained to estimate the gaze from full-face image sequences was stress tested for personal information leakage by a white box inference attack. Full-face video recordings taken from 493 individuals undergoing an eye-tracking- based evaluation of neurological function were used. Outputs, gradients, intermediate layer outputs, loss, and labels were used as inputs for a deep network with an added support vector machine emission layer to recognize membership in the training data. ResultsThe inference attack method and associated mathematical analysis indicate that there is a low likelihood of unintended memorization of facial features in the deep learning model. ConclusionsIn this study, it is showed that the named model preserves the integrity of training data with reasonable confidence. The same process can be implemented in similar conditions for different models. 

Routine blood pressure (BP) measurement in pregnancy is commonly performed using automated oscillometric devices. Since no wireless oscillometric BP device has been validated in preeclamptic populations, a simple approach for capturing readings from such devices is needed, especially in low-resource settings where transmission of BP data from the field to central locations is an important mechanism for triage. To this end, a total of 8192 BP readings were captured from the Liquid Crystal Display (LCD) screen of a standard Omron M7 self-inflating BP cuff using a cellphone camera. A cohort of 49 lay midwives captured these data from 1697 pregnant women carrying singletons between 6 weeks and 40 weeks gestational age in rural Guatemala during routine screening. Images exhibited a wide variability in their appearance due to variations in orientation and parallax; environmental factors such as lighting, shadows; and image acquisition factors such as motion blur and problems with focus. Images were independently labeled for readability and quality by three annotators (BP range: 34–203 mm Hg) and disagreements were resolved. Methods to preprocess and automatically segment the LCD images into diastolic BP, systolic BP and heart rate using a contour-based technique were developed. A deep convolutional neural network was then trained to convert the LCD images into numerical values using a multi-digit recognition approach. On readable low- and high-quality images, this proposed approach achieved a 91% classification accuracy and mean absolute error of 3.19 mm Hg for systolic BP and 91% accuracy and mean absolute error of 0.94 mm Hg for diastolic BP. These error values are within the FDA guidelines for BP monitoring when poor quality images are excluded. The performance of the proposed approach was shown to be greatly superior to state-of-the-art open-source tools (Tesseract and the Google Vision API). The algorithm was developed such that it could be deployed on a phone and work without connectivity to a network. 

This research examines the roles of health literacy, health numeracy, and trust in doctor on: (1) patient anxiety when consulting a doctor; (2) frequency of physician consultations; and (3) patient subjective well‐being (SWB). Our sample consisted of 4,040 adults representative of the United States in terms of age, income, and education, but equally split among White/Caucasian (50%) and Black/African American (50%) respondents. We found that functional and communicative health literacy and trust in doctor have linear and curvilinear relationships with anxiety when consulting a doctor. Health numeracy had no effect. Anxiety when consulting a doctor was associated with a lower number of physician consultations and lower SWB. We observed direct linear effects of health literacy, health numeracy, and trust in doctor on frequency of physician consultations and SWB, as well as some curvilinear effects. We found a negative relationship between health numeracy and SWB. We discuss implications of these findings for health and public policy. 

Background Cardiovascular disease (CVD) disparities are a particularly devastating manifestation of health inequity. Despite advancements in prevention and treatment, CVD is still the leading cause of death in the United States. Additionally, research indicates that African American (AA) and other ethnic-minority populations are affected by CVD at earlier ages than white Americans. Given that AAs are the fastest-growing population of smartphone owners and users, mobile health (mHealth) technologies offer the unparalleled potential to prevent or improve self-management of chronic disease among this population. Objective To address the unmet need for culturally tailored primordial prevention CVD–focused mHealth interventions, the MOYO app was cocreated with the involvement of young people from this priority community. The overall project aims to develop and evaluate the effectiveness of a novel smartphone app designed to reduce CVD risk factors among urban-AAs, 18-29 years of age. Methods The theoretical underpinning will combine the principles of community-based participatory research and the agile software development framework. The primary outcome goals of the study will be to determine the usability, acceptability, and functionality of the MOYO app, and to build a cloud-based data collection infrastructure suitable for digital epidemiology in a disparity population. Changes in health-related parameters over a 24-week period as determined by both passive (eg, physical activity levels, sleep duration, social networking) and active (eg, use of mood measures, surveys, uploading pictures of meals and blood pressure readings) measures will be the secondary outcome. Participants will be recruited from a majority AA “large city” school district, 2 historically black colleges or universities, and 1 urban undergraduate college. Following baseline screening for inclusion (administered in person), participants will receive the beta version of the MOYO app. Participants will be monitored during a 24-week pilot period. Analyses of varying data including social network dynamics, standard metrics of activity, percentage of time away from a given radius of home, circadian rhythm metrics, and proxies for sleep will be performed. Together with external variables (eg, weather, pollution, and socioeconomic indicators such as food access), these metrics will be used to train machine-learning frameworks to regress them on the self-reported quality of life indicators. Results This 5-year study (2015-2020) is currently in the implementation phase. We believe that MOYO can build upon findings of classical epidemiology and longitudinal studies like the Jackson Heart Study by adding greater granularity to our knowledge of the exposures and behaviors that affect health and disease, and creating a channel for outreach capable of launching interventions, clinical trials, and enhancements of health literacy. Conclusions The results of this pilot will provide valuable information about community cocreation of mHealth programs, efficacious design features, and essential infrastructure for digital epidemiology among young AA adults. International Registered Report Identifier (IRRID) DERR1-10.2196/16699