Uncertainty-aware model triage for HIV-1 INSTIs phenotypic resistance in global populations
Abstract
Background: As WHO expands dolutegravir (DTG) globally, non-B HIV-1 subtypes prevalent in low- and middle-income countries (LMICs) introduce cross-resistance risks driven by natural polymorphisms. Traditional rule-based genotypic algorithms falter to resolve high-dimensional epistatic interactions, exacerbating subtype biases and threatening virologic suppression. We developed a transparent AI tool to deal with these health inequalities.
Methods: Following TRIPOD+AI guidelines, we conducted a retrospective study constructing a multi-task attention network (MTL-Attention) to predict phenotypic cross-resistance to five integrase inhibitors from HIV-1 sequences. Monte Carlo Dropout was integrated to quantify epistemic uncertainty, establishing a “system deferral” mechanism. Epidemiological generalizability, along with fairness, was externally validated on a real-world cohort of 19,350 diverse sequences from the LANL database.
Results: MTL-Attention achieved an AUC of 0.955 for DTG and 1.000 for cabotegravir (CAB). Decision curve analysis confirmed a positive net clinical benefit across 0% to 80%. In the LANL cohort, epistemic uncertainty variance exhibited robust cross-domain stability between B and LMIC-prevalent non-B subtypes (Mann-Whitney U test, P = 0.999). Crucially, large-scale screening identified an 11.57% cryptic phenotypic drift in DTG and an 18.65% predicted baseline resistance rate against CAB among global non-B strains.
Conclusions: MTL-Attention provides a low-bias solution for predicting HIV-1 phenotypic cross-resistance. When translated into a Web CDSS, it delivers a low-cost computational triage tool designed for LMICs hospitals. To advance public health, we recommend implementing this human-in-the-loop AI workflow to reduce clinical automation bias, optimize equitable allocation of high-value antiretrovirals, and strengthen worldwide surveillance systems for emerging resistant variants.
Key messages: • A novel uncertainty-aware AI tool enables low-cost computational triage for HIV-1 cross-resistance, mitigating clinical automation bias and ensuring equitable patient safety in resource-limited LMICs.
• Real-world deployment identified an 11.57% cryptic phenotypic drift for dolutegravir and 18.65% baseline resistance to cabotegravir among global non-B subtypes, warning public health systems.
Related
- Probe-level performance of Xpert MTB/RIF versus phenotypic culture for rifampicin resistance detection and a triage algorithm based on 3,360 clinical specimens in China.
- HIV resistance in patients with virological failure to single tablet regimen: Roles of second generation integrase strand transfer inhibitors (INSTIs)
- Creating order in the uncertainty of childbirth: A qualitative study of obstetric admission and triage practices in rural Malawi
- Phenotypic Characterization of Multidrug-Resistant Pseudomonas aeruginosa Isolated From Patients With Ventilator-Associated Pneumonia: Insights Into Resistance Mechanisms and Biofilm Formation
- Phenotypic Antimicrobial Resistance Patterns in E. coli, Salmonella, and Enterobacter Species Isolated from Broiler Chicken Meat in Mzimba, Malawi: Insights from the Multiple Antibiotic Resistance Index.
BibTeX
@article{li2026uncertaintyaware,
title = {{Uncertainty-aware model triage for HIV-1 INSTIs phenotypic resistance in global populations}},
author = {MM Li and DF Yuan and YY Liu and J Zhu and SS Liu and NN Peng and XY Zhu and QJ Qian and YQ Yin and B Wang},
journal = {The European Journal of Public Health},
year = {2026},
month = oct,
doi = {10.1093/eurpub/ckag169.451},
url = {https://doi.org/10.1093/eurpub/ckag169.451},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - Uncertainty-aware model triage for HIV-1 INSTIs phenotypic resistance in global populations
AU - MM Li
AU - DF Yuan
AU - YY Liu
AU - J Zhu
AU - SS Liu
AU - NN Peng
AU - XY Zhu
AU - QJ Qian
AU - YQ Yin
AU - B Wang
PY - 2026
DA - 2026/10/01
JO - The European Journal of Public Health
DO - 10.1093/eurpub/ckag169.451
UR - https://doi.org/10.1093/eurpub/ckag169.451
AB - Background: As WHO expands dolutegravir (DTG) globally, non-B HIV-1 subtypes prevalent in low- and middle-income countries (LMICs) introduce cross-resistance risks driven by natural polymorphisms. Traditional rule-based genotypic algorithms falter to resolve high-dimensional epistatic interactions, exacerbating subtype biases and threatening virologic suppression. We developed a transparent AI tool to deal with these health inequalities. Methods: Following TRIPOD+AI guidelines, we conducted a retrospective study constructing a multi-task attention network (MTL-Attention) to predict phenotypic cross-resistance to five integrase inhibitors from HIV-1 sequences. Monte Carlo Dropout was integrated to quantify epistemic uncertainty, establishing a “system deferral” mechanism. Epidemiological generalizability, along with fairness, was externally validated on a real-world cohort of 19,350 diverse sequences from the LANL database. Results: MTL-Attention achieved an AUC of 0.955 for DTG and 1.000 for cabotegravir (CAB). Decision curve analysis confirmed a positive net clinical benefit across 0% to 80%. In the LANL cohort, epistemic uncertainty variance exhibited robust cross-domain stability between B and LMIC-prevalent non-B subtypes (Mann-Whitney U test, P = 0.999). Crucially, large-scale screening identified an 11.57% cryptic phenotypic drift in DTG and an 18.65% predicted baseline resistance rate against CAB among global non-B strains. Conclusions: MTL-Attention provides a low-bias solution for predicting HIV-1 phenotypic cross-resistance. When translated into a Web CDSS, it delivers a low-cost computational triage tool designed for LMICs hospitals. To advance public health, we recommend implementing this human-in-the-loop AI workflow to reduce clinical automation bias, optimize equitable allocation of high-value antiretrovirals, and strengthen worldwide surveillance systems for emerging resistant variants. Key messages: • A novel uncertainty-aware AI tool enables low-cost computational triage for HIV-1 cross-resistance, mitigating clinical automation bias and ensuring equitable patient safety in resource-limited LMICs. • Real-world deployment identified an 11.57% cryptic phenotypic drift for dolutegravir and 18.65% baseline resistance to cabotegravir among global non-B subtypes, warning public health systems.
SN - 1101-1262
SN - 1464-360X
ER -