Explore the vast range of titles available.

Cardiac auscultation is an accessible diagnostic screening tool that can help to identify patients with heart murmurs, who may need follow-up diagnostic screening and treatment for abnormal cardiac function. However, experts are needed to interpret the heart sounds, limiting the accessibility of cardiac auscultation in resource-constrained environments. Therefore, the George B. Moody PhysioNet Challenge 2022 invited teams to develop algorithmic approaches for detecting heart murmurs and abnormal cardiac function from phonocardiogram (PCG) recordings of heart sounds. For the Challenge, we sourced 5272 PCG recordings from 1452 primarily pediatric patients in rural Brazil, and we invited teams to implement diagnostic screening algorithms for detecting heart murmurs and abnormal cardiac function from the recordings. We required the participants to submit the complete training and inference code for their algorithms, improving the transparency, reproducibility, and utility of their work. We also devised an evaluation metric that considered the costs of screening, diagnosis, misdiagnosis, and treatment, allowing us to investigate the benefits of algorithmic diagnostic screening and facilitate the development of more clinically relevant algorithms. We received 779 algorithms from 87 teams during the Challenge, resulting in 53 working codebases for detecting heart murmurs and abnormal cardiac function from PCG recordings. These algorithms represent a diversity of approaches from both academia and industry, including methods that use more traditional machine learning techniques with engineered clinical and statistical features as well as methods that rely primarily on deep learning models to discover informative features. The use of heart sound recordings for identifying heart murmurs and abnormal cardiac function allowed us to explore the potential of algorithmic approaches for providing more accessible diagnostic screening in resource-constrained environments. The submission of working, open-source algorithms and the use of novel evaluation metrics supported the reproducibility, generalizability, and clinical relevance of the research from the Challenge.

Adverse posttraumatic neuropsychiatric sequelae are common after trauma. Early identification of individuals at risk for these outcomes could enable the deployment of preventive interventions to survivors at greatest risk. Smartphone keystroke biomarkers show promise in identifying individuals with neuropsychiatric symptoms; however, to our knowledge, no research has examined whether they can be used to identify symptoms in the aftermath of trauma. This study evaluates whether passively collected keystroke data from smartphone use in daily life could identify individuals with high symptom levels, as well as worsening or recovery of symptoms, after trauma exposure. Data from a diverse cohort of individuals presenting to 27 emergency departments after trauma were analyzed. Inclusion criteria were presenting to the emergency department within 72 hours of trauma, age 18-75, and the ability to speak and read English. Exclusion criteria were solid organ injury, significant hemorrhage, operative intervention, or likely admission for over 72 hours. Participants installed an app that passively collected keystroke data during use of any app on their smartphone, beginning in the emergency department. Participants also completed serial symptom assessments over 8 weeks after trauma exposure. A total of 3445 patients met study criteria, provided informed consent, and completed assessments in the emergency department. Of these, 1072 (mean age 40, SD 13; 616/1072, 57.46%, women; 565/1072, 52.71% non-Hispanic Black) installed the app on their Android smartphone and completed the 8-week assessment and were therefore included in analyses. Keystroke biomarkers related to typing speed, identified using bivariate linear mixed models controlling for false discovery rates, were associated with elevated pain, reexperiencing, and mental fatigue (absolute values of rs=0.22-0.25, Ps=.02). Separate change-of-operation and scrolling keystroke biomarkers were associated with increased reexperiencing symptoms (r=0.18, P=.047) and mental fatigue (rs=0.18-0.19, Ps=.031-.047). Further, changes in specific keystroke biomarkers were associated with worsening or recovery of pain (rs=0.07-0.10, Ps=.02), somatic symptoms (rs=0.02, Ps=.02), mental fatigue (rs=0.02-0.04, Ps=.02), sleep disturbance (absolute rs=0.07-0.09, Ps=.02), reexperiencing (rs=0.02-0.04, Ps=.02), and hyperarousal (rs=0.02-0.04, Ps=.02). In general, slower typing and scrolling speeds were associated with higher symptom levels, with small to medium effect sizes. Keystroke data passively collected via smartphone use may help identify individuals with significant or changing posttraumatic symptoms. Future research should continue to explore these keystroke biomarkers and whether they can be leveraged to connect vulnerable trauma survivors to appropriate services. Overall, these results add to the literature, indicating that passively collected keystroke data may help identify individuals with neuropsychiatric symptoms or changes and are, to our knowledge, the first to test whether keystroke biomarkers are useful in the aftermath of trauma. This represents a critical period during which preventive interventions could be deployed to reduce the long-term burden of trauma-related sequelae.

Regular blood pressure (BP) monitoring in clinical and ambulatory settings plays a crucial role in the prevention, diagnosis, treatment, and management of cardiovascular diseases. Recently, the widespread adoption of ambulatory BP measurement devices has been predominantly driven by the increased prevalence of hypertension and its associated risks and clinical conditions. Recent guidelines advocate for regular BP monitoring as part of regular clinical visits or even at home. This increased utilization of BP measurement technologies has raised significant concerns regarding the accuracy of reported BP values across settings. In this survey, which focuses mainly on cuff-based BP monitoring technologies, we highlight how BP measurements can demonstrate substantial biases and variances due to factors such as measurement and device errors, demographics, and body habitus. With these inherent biases, the development of a new generation of cuff-based BP devices that use artificial intelligence (AI) has significant potential. We present future avenues where AI-assisted technologies can leverage the extensive clinical literature on BP-related studies together with the large collections of BP records available in electronic health records. These resources can be combined with machine learning approaches, including deep learning and Bayesian inference, to remove BP measurement biases and provide individualized BP-related cardiovascular risk indexes.

Differences in expressing facial emotions are broadly observed in people with cognitive impairment. However, these differences have been difficult to objectively quantify and systematically evaluate among people with cognitive impairment across disease etiologies and severity. Therefore, a computer vision-based deep learning model for facial emotion recognition trained on 400.000 faces was utilized to analyze facial emotions expressed during a passive viewing memory test. In addition, this study was conducted on a large number of individuals (n = 493), including healthy controls and individuals with cognitive impairment due to diverse underlying etiologies and across different disease stages. Diagnoses included subjective cognitive impairment, Mild Cognitive Impairment (MCI) due to AD, MCI due to other etiologies, dementia due to Alzheimer’s diseases (AD), and dementia due to other etiologies (e.g., Vascular Dementia, Frontotemporal Dementia, Lewy Body Dementia, etc.). The Montreal Cognitive Assessment (MoCA) was used to evaluate cognitive performance across all participants. A participant with a score of less than or equal to 24 was considered cognitively impaired (CI). Compared to cognitively unimpaired (CU) participants, CI participants expressed significantly less positive emotions, more negative emotions, and higher facial expressiveness during the test. In addition, classification analysis revealed that facial emotions expressed during the test allowed effective differentiation of CI from CU participants, largely independent of sex, race, age, education level, mood, and eye movements (derived from an eye-tracking-based digital biomarker for cognitive impairment). No screening methods reliably differentiated the underlying etiology of the cognitive impairment. The findings provide quantitative and comprehensive evidence that the expression of facial emotions is significantly different in people with cognitive impairment, and suggests this may be a useful tool for passive screening of cognitive impairment.

Cardiovascular diseases (CVD) are rising in India resulting in major health system challenges. Eighteen primary health centre (PHC) clusters in rural Andhra Pradesh were randomised over three, 6-month steps to an intervention comprising: (1) household CVD risk assessments by village-based community health workers (CHWs) using a mobile tablet device; (2) electronic referral and clinical decision support for PHC doctors; and (3) a tracking system for follow-up care. Independent data collectors screened people aged ≥ 40 years in 54 villages serviced by the PHCs to create a high CVD risk cohort (based on WHO risk charts and blood pressure thresholds). Randomly selected, independent samples, comprising 15% of this cohort, were reviewed at each 6-month step. The primary outcome was the proportion meeting systolic blood pressure (SBP) targets (<140mmHg). Eight-four percent of the eligible population (n = 62,254) were assessed at baseline (18.4% at high CVD risk). Of those at high risk, 75.3% were followed up over two years. CHWs screened 85.9% of the baseline cohort and doctors followed up 70.0% of all high risk referrals. There was no difference in the proportion of people achieving SBP targets (41.2% vs 39.2%; adjusted odds ratio (OR) 1.01 95% CI 0.76-1.35) or receiving BP-lowering medications in the intervention vs control periods respectively. There was a high discordance in risk scores generated by independent data collectors and CHWs, resulting in only 37.2% of the evaluation cohort exposed to the intervention. This discordance was mainly driven by fluctuating BP values (both normal variability and marked seasonal variations). In the pre-specified high risk concordant subgroup, there was greater use of BP-lowering medications in the intervention period (54.3% vs 47.9%, OR 1.22, 95% CI 1.03-1.44) but no impact on BP control. The strategy was well implemented with increased treatment rates among high risk individuals assessed by CHWs, however effects on BP were not demonstrated. Use of guideline-recommended BP thresholds for identifying high risk individuals substantially affected the reproducibility of risk assessment, and thus the ability to reliably evaluate the effectiveness of the intervention. In addition, unanticipated seasonal variation in BP in the context of a stepped-wedge trial highlights the inherent risks of this study design. Clinical Trials Registry of India CTRI/2013/06/ 003753.

Schizophrenia is a severe psychiatric disorder that causes significant social and functional impairment. Currently, the diagnosis of schizophrenia is based on information gleaned from the patient's self-report, what the clinician observes directly, and what the clinician gathers from collateral informants, but these elements are prone to subjectivity. Utilizing computer vision to measure facial expressions is a promising approach to adding more objectivity in the evaluation and diagnosis of schizophrenia. We conducted a systematic review using PubMed and Google Scholar. Relevant publications published before (including) December 2021 were identified and evaluated for inclusion. The objective was to conduct a systematic review of computer vision for facial behavior analysis in schizophrenia studies, the clinical findings, and the corresponding data processing and machine learning methods. Seventeen studies published between 2007 to 2021 were included, with an increasing trend in the number of publications over time. Only 14 articles used interviews to collect data, of which different combinations of passive to evoked, unstructured to structured interviews were used. Various types of hardware were adopted and different types of visual data were collected. Commercial, open-access, and in-house developed models were used to recognize facial behaviors, where frame-level and subject-level features were extracted. Statistical tests and evaluation metrics varied across studies. The number of subjects ranged from 2-120, with an average of 38. Overall, facial behaviors appear to have a role in estimating diagnosis of schizophrenia and psychotic symptoms. When studies were evaluated with a quality assessment checklist, most had a low reporting quality. Despite the rapid development of computer vision techniques, there are relatively few studies that have applied this technology to schizophrenia research. There was considerable variation in the clinical paradigm and analytic techniques used. Further research is needed to identify and develop standardized practices, which will help to promote further advances in the field.

We present an interpretable machine learning algorithm called ‘eARDS’ for predicting ARDS in an ICU population comprising COVID-19 patients, up to 12-hours before satisfying the Berlin clinical criteria. The analysis was conducted on data collected from the Intensive care units (ICU) at Emory Healthcare, Atlanta, GA and University of Tennessee Health Science Center, Memphis, TN and the Cerner ® Health Facts Deidentified Database, a multi-site COVID-19 EMR database. The participants in the analysis consisted of adults over 18 years of age. Clinical data from 35,804 patients who developed ARDS and controls were used to generate predictive models that identify risk for ARDS onset up to 12-hours before satisfying the Berlin criteria. We identified salient features from the electronic medical record that predicted respiratory failure among this population. The machine learning algorithm which provided the best performance exhibited AUROC of 0.89 (95% CI = 0.88–0.90), sensitivity of 0.77 (95% CI = 0.75–0.78), specificity 0.85 (95% CI = 085–0.86). Validation performance across two separate health systems (comprising 899 COVID-19 patients) exhibited AUROC of 0.82 (0.81–0.83) and 0.89 (0.87, 0.90). Important features for prediction of ARDS included minimum oxygen saturation (SpO 2 ), standard deviation of the systolic blood pressure (SBP), O 2 flow, and maximum respiratory rate over an observational window of 16-hours. Analyzing the performance of the model across various cohorts indicates that the model performed best among a younger age group (18–40) (AUROC = 0.93 [0.92–0.94]), compared to an older age group (80+) (AUROC = 0.81 [0.81–0.82]). The model performance was comparable on both male and female groups, but performed significantly better on the severe ARDS group compared to the mild and moderate groups. The eARDS system demonstrated robust performance for predicting COVID19 patients who developed ARDS at least 12-hours before the Berlin clinical criteria, across two independent health systems.

Rett syndrome, a rare genetic neurodevelopmental disorder in humans, does not have an effective cure. However, multiple therapies and medications exist to treat symptoms and improve patients’ quality of life. As research continues to discover and evaluate new medications for Rett syndrome patients, there remains a lack of objective physiological and motor activity-based (physio-motor) biomarkers that enable the measurement of the effect of these medications on the change in patients’ Rett syndrome severity. In our work, using a commercially available wearable chest patch, we recorded simultaneous electrocardiogram and three-axis acceleration from 20 patients suffering from Rett syndrome along with the corresponding Clinical Global Impression—Severity score, which measures the overall disease severity on a 7-point Likert scale. We derived physio-motor features from these recordings that captured heart rate variability, activity metrics, and the interactions between heart rate and activity. Further, we developed machine learning (ML) models to classify high-severity Rett patients from low-severity Rett patients using the derived physio-motor features. For the best-trained model, we obtained a pooled area under the receiver operating curve equal to 0.92 via a leave-one-out-patient cross-validation approach. Finally, we computed the feature popularity scores for all the trained ML models and identified physio-motor biomarkers for Rett syndrome.

Background: Atrial fibrillation (AFib) detection via mobile ECG devices is promising, but algorithms often struggle to generalize across diverse datasets and platforms, limiting their real-world applicability. Objective: This study aims to develop a robust, generalizable AFib detection approach for mobile ECG devices using crowdsourced algorithms. Methods: We developed a voting algorithm using random forest, integrating six open-source AFib detection algorithms from the PhysioNet Challenge. The algorithm was trained on an AliveCor dataset and tested on two disjoint AliveCor datasets and one Apple Watch dataset. Results: The voting algorithm outperformed the base algorithms across all metrics: the average of sensitivity (0.884), specificity (0.988), PPV (0.917), NPV (0.985), and F1-score (0.943) on all datasets. It also demonstrated the least variability among datasets, signifying its highest robustness and effectiveness in diverse data environments. Moreover, it surpassed Apple’s algorithm on all metrics and showed higher specificity but lower sensitivity than AliveCor’s Kardia algorithm. Conclusions: This study demonstrates the potential of crowdsourced, multi-algorithmic strategies in enhancing AFib detection. Our approach shows robust cross-platform performance, addressing key generalization challenges in AI-enabled cardiac monitoring and underlining the potential for collaborative algorithms in wearable monitoring devices.

The non-contact patient monitoring paradigm moves patient care into their homes and enables long-term patient studies. The challenge, however, is to make the system non-intrusive, privacy-preserving, and low-cost. To this end, we describe an open-source edge computing and ambient data capture system, developed using low-cost and readily available hardware. We describe five applications of our ambient data capture system. Namely: (1) Estimating occupancy and human activity phenotyping; (2) Medical equipment alarm classification; (3) Geolocation of humans in a built environment; (4) Ambient light logging; and (5) Ambient temperature and humidity logging. We obtained an accuracy of 94% for estimating occupancy from video. We stress-tested the alarm note classification in the absence and presence of speech and obtained micro averaged F1 scores of 0.98 and 0.93, respectively. The geolocation tracking provided a room-level accuracy of 98.7%. The root mean square error in the temperature sensor validation task was 0.3°C and for the humidity sensor, it was 1% Relative Humidity. The low-cost edge computing system presented here demonstrated the ability to capture and analyze a wide range of activities in a privacy-preserving manner in clinical and home environments and is able to provide key insights into the healthcare practices and patient behaviors.