Machine Learning Algorithms Using Routinely Collected Data Do Not Adequately Predict Viremia to Inform Targeted Services in Postpartum Women Living With HIV.
Pamela M MurnaneJames AyiekoEric VittinghoffMonica GandhiChaplain KatumbiBeteniko MilalaCatherine NakayePeter KandaDhayendre MoodleyMandisa E NyatiAmy J LoftisMary G FowlerPat FlynnJudith S CurrierCraig R CohenPublished in: Journal of acquired immune deficiency syndromes (1999) (2022)
Using routinely collected data to predict viremia in >1300 postpartum women with HIV, we achieved moderate model discrimination, but insufficient to inform targeted adherence support. Psychosocial characteristics or objective adherence metrics may be required for improved prediction of viremia in this population.
Keyphrases
- machine learning
- big data
- electronic health record
- mental health
- cancer therapy
- healthcare
- antiretroviral therapy
- hiv infected
- hiv positive
- artificial intelligence
- primary care
- human immunodeficiency virus
- polycystic ovary syndrome
- deep learning
- hiv testing
- pregnant women
- metabolic syndrome
- data analysis
- skeletal muscle