Prevention of adverse HIV treatment outcomes: machine learning to enable proactive support of people at risk of HIV care disengagement in Tanzania.

Journal: BMJ open
PMID: 39317499

Abstract

OBJECTIVES: This study aimed to develop a machine learning (ML) model to predict disengagement from HIV care, high viral load or death among people living with HIV (PLHIV) with the goal of enabling proactive support interventions in Tanzania. The algorithm addressed common challenges when applying ML to electronic medical record (EMR) data: (1) imbalanced outcome distribution; (2) heterogeneity across multisite EMR data and (3) evolving virological suppression thresholds.

Authors

  • Zhongming Xie
    School of Public Health, University of California, Berkeley, California, USA.
  • Huiyu Hu
    School of Public Health, University of California, Berkeley, California, USA huiyuhu@berkeley.edu.
  • Jillian L Kadota
    School of Public Health, University of California, Berkeley, California, USA.
  • Laura J Packel
    School of Public Health, University of California, Berkeley, California, USA.
  • Matilda Mlowe
    Health for a Prosperous Nation, Dar es Salaam, Tanzania, United Republic of.
  • Sylvester Kwilasa
    United Republic of Tanzania Ministry of Health, Dodoma, Tanzania, United Republic of.
  • Werner Maokola
    United Republic of Tanzania Ministry of Health, Dodoma, Tanzania, United Republic of.
  • Siraji Shabani
    United Republic of Tanzania Ministry of Health, Dodoma, Tanzania, United Republic of.
  • Amon Sabasaba
    Health for a Prosperous Nation, Dar es Salaam, Tanzania, United Republic of.
  • Prosper F Njau
    United Republic of Tanzania Ministry of Health, Dodoma, Tanzania, United Republic of.
  • Jingshen Wang
    Division of Biostatistics, University of California, Berkeley, California, USA.
  • Sandra I McCoy
    School of Public Health, University of California, Berkeley, California, USA.

Keywords

External Resources

Popular Topics
Recent Journals