Sign in Subscribe
Machine learning

Predicting Adverse Drug Reactions in HIV Patients Using Machine Learning Algorithms

Strategic Insights

— 1 min read

Researchers at the University of Gondar Comprehensive and Specialized Hospital in Ethiopia have made significant breakthroughs in predicting adverse drug reactions (ADRs) in HIV patients receiving antiretroviral therapy (ART). Through the use of machine learning algorithms, the team was able to identify the top predictors of ADRs, including CD4 count, age, duration on ART, and educational status. Their research aimed to address the pressing public health issue of diagnosing and treating HIV-positive individuals effectively.

Key Takeaways:

  • The study, published in Health Science Reports, used machine learning algorithms to predict ADRs in HIV patients receiving ART at the University of Gondar Comprehensive and Specialized Hospital in Ethiopia.
  • Among 5864 research participants, 3371 (64.04%) were female, and 1893 (35.06%) were male.
  • The random forest classifier performed better in predicting ADRs, with a sensitivity of 1.00, precision of 0.987, f1-score of 0.993, and AUC of 0.9989.
  • CD4 count was determined to be the most significant predictor feature, followed by male, younger age, longer duration on ART, not taking Co-trimoxazole preventive therapy (CPT), not taking TB (Tuberculosis) preventive therapy (TPT), secondary educational status, TDF-3TC-EFV, and low CD4 counts.
  • The study identified the top eight predictors of ADRs, which can help categorize HIV patients at high risk of ADRs and recognize predictive traits associated with ADRs.
  • The research has the potential to address the pressing public health issue of diagnosing and treating HIV-positive individuals effectively.

Statistics:

  • 3371 (64.04%) female participants out of 5864 research participants.
  • 1893 (35.06%) male individuals out of 5864 research participants.
  • Sensitivity: 1.00
  • Precision: 0.987
  • F1-score: 0.993
  • AUC: 0.9989

Sources:

  • Institute of Public Health Researchers Update Current Study Findings on HIV/AIDS (Machine Learning Algorithms for Adverse Drug Reactions Prediction and Identifying Its Determinants Among HIV Patients on Antiretroviral Therapy in the University ...). AIDS Weekly, October 13, 2025.
  • Machine Learning Algorithms for Adverse Drug Reactions Prediction and Identifying Its Determinants Among HIV Patients on Antiretroviral Therapy in the University of Gondar Comprehensive and Specialized Hospital, in Amhara Region, Ethiopia. Health Science Reports, 2025,8(10):n/a-n/a. (Health Science Reports - https://onlinelibrary.wiley.com/journal/23988835)

Read more