Clinical stage of acquired immunodeficiency syndrome in HIV-positive patients impacts the quality of the touch ECG recordings

Using Minimum Redundancy Maximum Relevance Algorithm to Select Minimal Sets of Heart Rate Variability Parameters for Atrial Fibrillation Detection

Heart rate is quite regular during sinus (normal) rhythm (SR) originating from the sinus node. In contrast, heart rate is usually irregular during atrial fibrillation (AF). Complete atrioventricular block with an escape rhythm, ventricular pacing, or ventricular tachycardia are the most common exceptions when heart rate may be regular in AF. Heart rate variability (HRV) is the variation in the duration of consecutive cardiac cycles (RR intervals). We investigated the utility of HRV parameters for automated detection of AF with machine learning (ML) classifiers. The minimum redundancy maximum relevance (MRMR) algorithm, one of the most effective algorithms for feature selection, helped select the HRV parameters (including five original), best suited for distinguishing AF from SR in a database of over 53,000 60 s separate electrocardiogram (ECG) segments cut from longer (up to 24 h) ECG recordings. HRV parameters entered the ML-based classifiers as features. Seven different, commonly used classifiers were trained with one to six HRV-based features with the highest scores resulting from the MRMR algorithm and tested using the 5-fold cross-validation and blindfold validation. The best ML classifier in the blindfold validation achieved an accuracy of 97.2% and diagnostic odds ratio of 1566. From all studied HRV features, the top three HRV parameters distinguishing AF from SR were: the percentage of successive RR intervals differing by at least 50 ms (pRR50), the ratio of standard deviations of points along and across the identity line of the Poincare plots, respectively (SD2/SD1), and coefficient of variation-standard deviation of RR intervals divided by their mean duration (CV). The proposed methodology and the presented results of the selection of HRV parameters have the potential to develop practical solutions and devices for automatic AF detection with minimal sets of simple HRV parameters. Using straightforward ML classifiers and the extremely small sets of simple HRV features, always with pRR50 included, the differentiation of AF from sinus rhythms in the 60 s ECGs is very effective.

The role of digital health in palliative care for people living with HIV in sub-Saharan Africa: A systematic review

Background

In 2018, 26.6 million people were living with HIV in sub-Saharan Africa. Palliative care services are recommended for people living with HIV at all stages from diagnosis through to end-of-life. However, the provision of palliative care in sub-Saharan Africa is limited, leading to little or no access for the majority of patients. Digital technologies in sub-Saharan Africa present an opportunity to improve access to palliative care for people living with HIV in the region. This review synthesised literature on digital health interventions for palliative care for people living with HIV in sub-Saharan Africa and assessed their effects on patient outcomes.

Methods

Literature searches were conducted in MEDLINE, Embase, PsycINFO and Global Health. Inclusion and exclusion criteria were applied. Two independent reviewers conducted study screening, data extraction and quality appraisal. A narrative synthesis was performed to draw together and report findings across heterogeneous studies. Reporting of this review follows the Preferred Reporting Items for Systematic Review and Meta-Analysis checklist.

Results

Out of 4117 records, 25 studies were included, covering 3592 people living with HIV, across 21 countries. Studies included three randomised controlled trials, three qualitative, three pre- and post-test, two observational, two case series, six cross-sectional and six mixed methods studies. Telemedicine was the most reported digital health intervention, with 12 studies demonstrating the effectiveness of digital health interventions.

Conclusion

Emerging evidence suggests digital health interventions can be effective in facilitating patient-provider communication and health professional decision-making as a part of palliative care for people living with HIV. There is a need for further development and evaluation of digital health interventions alongside determining optimal approaches to their implementation as a part of palliative care provision in sub-Saharan Africa.