Machine Learning in Cardiology: A Potential Real-World Solution in Low- and Middle-Income Countries.

Artificial intelligence (AI) and machine learning (ML) is a promising field of cardiovascular medicine. Many AI tools have been shown to be efficacious with a high level of accuracy. Yet, their use in real life is not well established. In the era of health technology and data science, it is crucial to consider how these tools could improve healthcare delivery. This is particularly important in countries with limited resources, such as low- and middle-income countries (LMICs). LMICs have many barriers in the care continuum of cardiovascular diseases (CVD), and big portion of these barriers come from scarcity of resources, mainly financial and human power constraints. AI/ML could potentially improve healthcare delivery if appropriately applied in these countries. Expectedly, the current literature lacks original articles about AI/ML originating from these countries. It is important to start early with a stepwise approach to understand the obstacles these countries face in order to develop AI/ML-based solutions. This could be detrimental to many patients' lives, in addition to other expected advantages in other sectors, including the economy sector. In this report, we aim to review what is known about AI/ML in cardiovascular medicine, and to discuss how it could benefit LMICs.

A Nationwide Virtual Research Education Program for Medical Students in Pakistan: Methodological Framework, Feasibility Testing, and Outcomes.

Introduction: Equipping young medical trainees with fundamental research skills can be a promising strategy to address the need for professionals who can understand and responsibly communicate evolving scientific evidence during a pandemic. Despite an ardent interest to partake in research, most educational institutions in Pakistan and other low-middle income countries have not yet adopted a comprehensive strategy for research skills education. The authors aimed to design and assess the feasibility of implementing the first nation-wide virtual research workshop for medical students in Pakistan. Methods: The course "Beginners Guide to Research," designed as a nation-wide virtual research workshop series, was conducted for medical students across Pakistan in June 2020. Four interactive live workshops took place online on alternate days from June 22nd, 2020, to June 27th, 2020, each lasting 1-2 h. Outcomes included: (i) reach, (ii) efficacy as indexed by pre-post change in score pertaining to knowledge and application of research and (iii) self-rated perceptions about understanding of research on a Likert scale. Results: 3,862 participants enrolled from 41 cities and 123 institutions. Enrolled participants belonged to the following provinces: Sindh (n = 1,852, 48.0%), Punjab (n = 1,767, 45.8%), Khyber Pakhtunkhwa (n = 109, 2.8%), Azad Jammu and Kashmir (n = 84, 2.2%) Balochistan (n = 42, 1.1%). We also saw a few registrations from international students (n = 8, 0.2%). Mean (SD) age of enrolled medical students was 21.1 (2.1) years, 2,453 (63.5%) participants were female and 2,394 (62.0%) were from private-sector medical colleges. Two thousand ninety-three participants participants filled out all four pre-test and post-test forms. The total median knowledge score improved from 39.7 to 60.3% with the highest improvements in concepts of research bioethics and literature search (p < 0.001) with greater change for females compared to males (+20.6 vs. +16.2%, p < 0.001) and private institutions compared to public ones (+16.2 vs. +22.1%, p < 0.001). Conclusion: The overwhelming enrollment and significant improvement in learning outcomes (>50% of baseline) indicate feasibility of a medical student-led research course during a pandemic, highlighting its role in catering to the research needs in the LMICs.

Health-related quality of life in postcardiac interventional catheterization patients with congenital heart disease: a mixed-methods study protocol from Pakistan

IntroductionImprovement in health-related quality of life (HRQoL) has been reported in patients with congenital heart disease treated with interventional cardiac catheterization;however, there is a significant dearth of literature from low/middle-income countries (LMICs) about this aspect. Multiple factors like sociodemographic and cultural differences, variable procedural outcomes due to lack of technical expertise and limited resources and inconsistent postprocedure follow-up may affect HRQoL in LMICs. This protocol paper aims to describe the study methodology to determine the HRQoL and its predictors in patients who have undergone interventional cardiac catheterization. Conclusions from this protocol study will help prepare a holistic approach to delivering care to patients in low-resource settings.Methods and analysisA mixed-methods study design will be used. The quantitative arm will compare the HRQoL of these postcardiac interventional catheterization patients with their age-matched healthy siblings to identify the HRQoL predictors, whereas the qualitative arm will further explore the experiences of these patients and parents. A minimum number of 108 patients of age 2 years and above, at least 6 months postinterventional catheterization follow-up and ability to understand Urdu/English will be enrolled. PedsQL 4.0 Generic Core Scales, PedsQL Cognitive Functioning Scale and PedsQL 3.0 Cardiac Module will be used. The Student’s t-test will analyse the difference in the means of HRQoL between patients and siblings. Multiple regression will identify HRQoL predictors. A subsample of enrolled patients and parents will be interviewed and analysed using directed content analysis (a qualitative component of the study).Ethics and disseminationEthics approval has been obtained from Ethics Review Committee of The Aga Khan University, Pakistan (ERC #2020-3456-11808). Study findings will be published in peer-reviewed journals and presented at conferences.