Machine learning-based prediction models in medical decision-making in kidney disease: patient, caregiver, and clinician perspectives on trust and appropriate use DOI
Jessica Sperling, Whitney Welsh,

Erin Haseley

et al.

Journal of the American Medical Informatics Association, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 14, 2024

Abstract Objectives This study aims to improve the ethical use of machine learning (ML)-based clinical prediction models (CPMs) in shared decision-making for patients with kidney failure on dialysis. We explore factors that inform acceptability, interpretability, and implementation ML-based CPMs among multiple constituent groups. Materials Methods collected analyzed qualitative data from focus groups varied end users, including: dialysis support providers (clinical additional such as clinic staff social workers); patients; patients’ caregivers (n = 52). Results Participants were broadly accepting CPMs, but concerns sources, included model, accuracy. Use was desired conjunction providers’ views explanations. Differences respondent types minimal overall most prevalent discussions CPM presentation model use. Discussion Conclusion Evidence acceptability usage provides use, numerous specific considerations construction, must be considered. There are steps could taken by scientists health systems engender is accepted users facilitates trust, there also ongoing barriers or challenges addressing desires contributes emerging literature mechanisms sharing complexities, including uncertainty regarding results, implications decision-making. It examines stakeholder providers, patients, provide can influence system a basis future research.

Language: Английский

Intervention mapping for systematic development of a community-engaged CVD prevention intervention in ethnic and racial sexual minority men with HIV DOI Creative Commons
Baram Kang,

Lauren Chin,

Marlene Camacho‐Rivera

et al.

Frontiers in Public Health, Journal Year: 2025, Volume and Issue: 13

Published: Feb. 26, 2025

Cardiovascular disease (CVD) is a leading cause of mortality in the United States, disproportionately affecting marginalized populations such as Black and Latinx sexual minority men with HIV. These individuals face heightened CVD risk due to chronic inflammation related HIV, side effects from treatment, intersecting social disadvantages, including stigma discrimination. Behavioral interventions specifically targeting these have been limited, insufficient uptake communities. This study used Intervention Mapping (IM) develop culturally tailored prevention intervention for IM systematic, theory- evidence-based framework health promotion program planning. We focused on first three six steps process: (1) assessing community needs through literature review, development, community-engaged research; (2) identifying outcomes logic model change; (3) selecting theory-based methods practical strategies design. The assessment revealed significant barriers cardiovascular health, medical distrust, stigma, lack access appropriate healthcare. change highlighted behavioral environmental determinants influencing specific performance objectives objectives. Strategies included leveraging eHealth technologies, avatar-led interactive videos, provide private, relevant education reduce like distrust. Community-based participatory were integral ensure was resonant acceptable. demonstrated use systematically findings highlight importance approaches developing historically populations. aimed address disparities empower them engage health-promoting behaviors, ultimately improving outcomes. Leveraging technology foster engagement providing support crucial elements intervention. insights gained may inform future efforts similar

Language: Английский

Citations

0
Fairness and inclusion methods for biomedical informatics research DOI
Shyam Visweswaran, Yuan Luo, Mor Peleg

et al.

Journal of Biomedical Informatics, Journal Year: 2024, Volume and Issue: 158, P. 104713 - 104713

Published: Aug. 24, 2024

Language: Английский

Citations

1
Machine learning-based prediction models in medical decision-making in kidney disease: patient, caregiver, and clinician perspectives on trust and appropriate use DOI
Jessica Sperling, Whitney Welsh,

Erin Haseley

et al.

Journal of the American Medical Informatics Association, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 14, 2024

Abstract Objectives This study aims to improve the ethical use of machine learning (ML)-based clinical prediction models (CPMs) in shared decision-making for patients with kidney failure on dialysis. We explore factors that inform acceptability, interpretability, and implementation ML-based CPMs among multiple constituent groups. Materials Methods collected analyzed qualitative data from focus groups varied end users, including: dialysis support providers (clinical additional such as clinic staff social workers); patients; patients’ caregivers (n = 52). Results Participants were broadly accepting CPMs, but concerns sources, included model, accuracy. Use was desired conjunction providers’ views explanations. Differences respondent types minimal overall most prevalent discussions CPM presentation model use. Discussion Conclusion Evidence acceptability usage provides use, numerous specific considerations construction, must be considered. There are steps could taken by scientists health systems engender is accepted users facilitates trust, there also ongoing barriers or challenges addressing desires contributes emerging literature mechanisms sharing complexities, including uncertainty regarding results, implications decision-making. It examines stakeholder providers, patients, provide can influence system a basis future research.

Language: Английский

Citations

0