Early-warning of Cardiac Condition through Detection of Murmur in Heart Sound - A Case Study.

Cardiovascular disease, particularly Rheumatic Heart Disease (RHD), is one of the leading causes of death in many developing countries. RHD is manageable and treatable with early detection. However, multiple countries across the globe suffer from a scarcity of experienced physicians who can perform screening at large scales. Advancements in machine learning and signal processing have paved way for Phonocardiogram (PCG)-based automatic heart sound classification. The direct implication of such methods is that it is possible to enable a person without specialized training to detect potential cardiac conditions with just a digital stethoscope. Hospitalization or life-threatening situations can be dramatically reduced via such early screenings. Towards this, we conducted a case study amongst a population from a particular geography using machine learning and deep learning methods for the detection of murmur in heart sounds. The methodology consists of first pre-processing and identifying normal vs. abnormal heart sound signals using 3 state-of-the-art methods. The second step further identifies the murmur to be systolic or diastolic by capturing the auscultation location. Abnormal findings are then sent for early attention of clinicians for proper diagnosis. The case study investigates the efficacy of the automated method employed for early screening of potential RHD and initial encouraging results of the study are presented.

Racial disparity in the co-occurrence of depression and type 2 diabetes mellitus. An electronic medical record study involving African American and White Caucasian adults from the US.

INTRODUCTION: Depression and diabetes commonly co-exist, however the temporal trends in the bidirectional association of both diseases in different sociodemographic setting has not been explored. We investigated the trends in prevalence and likelihood of having either depression or type 2 diabetes (T2DM) in African American (AA, or black) and White Caucasians (WC, or white). METHODS: In this nationwide population-based study, the US Centricity Electronic Medical Records was used to establish cohorts of >2.5 million adults diagnosed with either T2DM or depression between 2006 and 2017. Logistic regression models were used to investigate ethnic differences in: (a) subsequent probability of depression in individuals with T2DM; and (b) subsequent probability of T2DM in individuals with depression; stratified by age and sex. RESULTS: A total of 920,771 (15 % black) adults were identified with T2DM and 1,801,679 (10 % black) with depression. AA diagnosed with T2DM were much younger (56 vs. 60 years) and had significantly lower prevalence of depression (17 vs. 28 %). AA diagnosed with depression were slightly younger (46 vs. 48 years) and had significantly higher prevalence of T2DM (21 % vs. 14 %). The prevalence of depression in T2DM increased from 12 % (11, 14) to 23 % (20, 23) in black and 26 (25, 26) to 32 (32, 33) in white. Depressive AA above 50 years recorded the highest adjusted probability of T2DM (men: 6.3 % (5.8, 7.0), women: 6.3 % (5.9, 6.7)), while diabetic white women below 50 years had the highest probability of depression (20.2 % (18.6, 22.0)). No significant ethnic difference in diabetes was observed for younger adults diagnosed with depression: black 3.1 % (2.7, 3.7); white 2.5 % (2.2, 2.7). CONCLUSIONS: We have observed significant difference in depression between AA and WC recently diagnosed with diabetes consistent across different demographics. Depression in people with diabetes is increasing with significantly higher values among white women younger than 50 years.