1
|
Li Y, Feng Y, He Q, Ni Z, Hu X, Feng X, Ni M. The predictive accuracy of machine learning for the risk of death in HIV patients: a systematic review and meta-analysis. BMC Infect Dis 2024; 24:474. [PMID: 38711068 PMCID: PMC11075245 DOI: 10.1186/s12879-024-09368-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2024] [Accepted: 04/30/2024] [Indexed: 05/08/2024] Open
Abstract
BACKGROUND Early prediction of mortality in individuals with HIV (PWH) has perpetually posed a formidable challenge. With the widespread integration of machine learning into clinical practice, some researchers endeavor to formulate models predicting the mortality risk for PWH. Nevertheless, the diverse timeframes of mortality among PWH and the potential multitude of modeling variables have cast doubt on the efficacy of the current predictive model for HIV-related deaths. To address this, we undertook a systematic review and meta-analysis, aiming to comprehensively assess the utilization of machine learning in the early prediction of HIV-related deaths and furnish evidence-based support for the advancement of artificial intelligence in this domain. METHODS We systematically combed through the PubMed, Cochrane, Embase, and Web of Science databases on November 25, 2023. To evaluate the bias risk in the original studies included, we employed the Predictive Model Bias Risk Assessment Tool (PROBAST). During the meta-analysis, we conducted subgroup analysis based on survival and non-survival models. Additionally, we utilized meta-regression to explore the influence of death time on the predictive value of the model for HIV-related deaths. RESULTS After our comprehensive review, we analyzed a total of 24 pieces of literature, encompassing data from 401,389 individuals diagnosed with HIV. Within this dataset, 23 articles specifically delved into deaths during long-term follow-ups outside hospital settings. The machine learning models applied for predicting these deaths comprised survival models (COX regression) and other non-survival models. The outcomes of the meta-analysis unveiled that within the training set, the c-index for predicting deaths among people with HIV (PWH) using predictive models stands at 0.83 (95% CI: 0.75-0.91). In the validation set, the c-index is slightly lower at 0.81 (95% CI: 0.78-0.85). Notably, the meta-regression analysis demonstrated that neither follow-up time nor the occurrence of death events significantly impacted the performance of the machine learning models. CONCLUSIONS The study suggests that machine learning is a viable approach for developing non-time-based predictions regarding HIV deaths. Nevertheless, the limited inclusion of original studies necessitates additional multicenter studies for thorough validation.
Collapse
Affiliation(s)
- Yuefei Li
- Public Health, Xinjiang Medical University, Urumqi, Xinjiang, 830011, China
| | - Ying Feng
- Urumqi Maternal and Child Health Hospital, Urumqi, Xinjiang, 830000, China
| | - Qian He
- Public Health, Xinjiang Medical University, Urumqi, Xinjiang, 830011, China
| | - Zhen Ni
- STD/HIV Prevention and Control Center, Xinjiang Uighur Autonomous Region Center for Disease Control and Prevention, No. 138 Jianquan 1st Street, Tianshan District, Urumqi, Xinjiang, 830002, China
| | - Xiaoyuan Hu
- STD/HIV Prevention and Control Center, Xinjiang Uighur Autonomous Region Center for Disease Control and Prevention, No. 138 Jianquan 1st Street, Tianshan District, Urumqi, Xinjiang, 830002, China
| | - Xinhuan Feng
- Clinical Laboratory, Second People's Hospital of Yining, Yining, Xinjiang, 835000, China
| | - Mingjian Ni
- STD/HIV Prevention and Control Center, Xinjiang Uighur Autonomous Region Center for Disease Control and Prevention, No. 138 Jianquan 1st Street, Tianshan District, Urumqi, Xinjiang, 830002, China.
| |
Collapse
|
2
|
Rungmaitree S, Aurpibul L, Best BM, Li X, Warshaw MG, Wan H, Tobin NH, Jumes P, Leavitt R, McCarthy K, Scheckter R, Ounchanum P, Violari A, Teppler H, Campbell H, Krotje C, Townley E, Moye J, Melvin AJ. Efficacy, Safety, and Tolerability of Doravirine/Lamivudine/Tenofovir Disoproxil Fumarate Fixed-Dose Combination Tablets in Adolescents Living With HIV: Results Through Week 96 from IMPAACT 2014. J Pediatric Infect Dis Soc 2023; 12:602-609. [PMID: 37815035 DOI: 10.1093/jpids/piad078] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/24/2023] [Accepted: 09/27/2023] [Indexed: 10/11/2023]
Abstract
BACKGROUND IMPAACT 2014 study is a phase I/II, multicenter, open-label, nonrandomized study of doravirine (DOR) co-formulated with lamivudine (3TC) and tenofovir disoproxil fumarate (TDF) as fixed-dose combination (DOR FDC) in adolescents with HIV-1. We report the efficacy, safety, and tolerability of DOR FDC through 96 weeks. METHODS Participants were adolescents aged 12 to <18 years who weighed at least 45 kg and who were either antiretroviral (ARV)-naïve or virologically suppressed without documented resistance mutations to DOR/3TC/TDF. The efficacy endpoint was the proportion of participants with HIV-1 RNA <40 copies/mL assessed at weeks 48 and 96 using the observed failure approach. Safety and tolerability outcomes were incidence of adverse events (AEs) and treatment discontinuations. RESULTS A total of 45 adolescents, median age 15 (range, 12-17) years, 58% females, were enrolled and 2 (4.4%) participants were ARV naïve. Of the 45 participants, 42 (93.3%) completed the study and 41 (91.1%) completed the study treatment. At week 48, 41/42 (97.6%; 95% confidence interval [CI], 87.4-99.9) and week 96, 37/40 (92.5%; 95% CI, 79.6-98.4) participants had achieved or maintained HIV-1 RNA <40 copies/mL. There were no treatment-related discontinuations due to AEs and no drug-related AEs ≥grade 3 or deaths. CONCLUSIONS We found once-daily dosing of DOR FDC to be safe and well tolerated for maintaining viral suppression through 96 weeks in adolescents living with HIV-1.
Collapse
Affiliation(s)
- Supattra Rungmaitree
- Department of Pediatrics, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Linda Aurpibul
- Research Institute for Health Sciences, Chiang Mai University, Chiang Mai, Thailand
| | - Brookie M Best
- Skaggs School of Pharmacy and Pharmaceutical Sciences and Pediatrics Department, School of Medicine-Rady Children's Hospital San Diego, University of California San Diego, San Diego, California, USA
| | - Xiang Li
- Frontier Science Technology and Research Foundation, Madison, Wisconsin, USA
| | - Meredith G Warshaw
- Center for Biostatistics in AIDS Research, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, USA
| | - Hong Wan
- Merck & Co., Inc., Rahway, New Jersey, USA
| | - Nicole H Tobin
- Department of Pediatrics, Division of Pediatric Infectious Diseases, David Geffen School of Medicine, University of California, Los Angeles, California, USA
| | | | | | | | | | | | - Avy Violari
- Perinatal HIV Research Unit, University of the Witwatersrand, Johannesburg, South Africa
| | | | | | | | | | | | - Ann J Melvin
- Department of Pediatrics, Division of Pediatric Infectious Disease, University of Washington and Seattle Children's Research Institute, Seattle, Washington, USA
| |
Collapse
|