Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jan 14, 2025
Date Accepted: May 8, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Development and Spatial External Validation of A Prediction Model of Survival in People Living with HIV/AIDS (PLWHA) after Highly Active Anti-Retroviral Therapy (HAART) in China: Based on Random Survival Forest Analysis
ABSTRACT
Background:
Due to compromised immune systems, people living with HIV/AIDS (PLWHA) are at an increased risk of opportunistic infections and deaths.
Objective:
The aim of this study was to develop and spatial externally validate a predictive model for the survival of PLWHA following the initiation of highly active anti-retroviral therapy (HAART) in China.
Methods:
This retrospective cohort study used data from the HIV/AIDS epidemic surveillance system of the National Center for AIDS/STD Control and Prevention, China CDC. The training set and the validation set included PLWHA from Nanjing and Nantong city, respectively. The prediction model was developed by the random survival forest (RSF), and its performance was evaluated against the Cox model (benchmark model), by area under the curve (AUC), consistency index (C index), calibration curves, integrated brier score (iBS) and decision curve analysis (DCA) curve.
Results:
A total of 8,960 patients were eligible for this study, consisting of 5,261 cases in training set (mean [SD] age 32.39 [13.30] years; male 4,891 [92.97%] patients) and 3,699 cases in validation set (mean [SD] age 43.31 [14.18] years; male 869 [83.39%] patients). The RSF model was developed based on the top 7 variables ranked by the variable importance, including hemoglobin, age at HAART treatment, infection route, white blood cell count, education level, blood glucose, and the CD4 count prior to HARRT. The RSF model exhibited good performance, with an iBS of 0.129 in the training set and 0.113 in the validation set, and a C index of 0.896 (95% CI: 0.884 - 0.908) in the training set and 0.756 (95% CI: 0.730 - 0.782) in the validation set, respectively. The iAUC was 0.918 (95% CI: 0.905 - 0.930) for the training set and 0.750 (95% CI: 0.724 - 0.776) for the validation set. Using the Cox model as the benchmark model, the variables included in the RSF model yielded iBS of 0.172 and 0.115, C index of 0.828 (95% CI: 0.812 - 0.844) and 0.742 (95% CI: 0.714 - 0.770), and iAUC of 0.871 (95% CI: 0.855 - 0.887) and 0.740 (95% CI: 0.711 - 0.768) for the training and validation sets, respectively.
Conclusions:
The RSF model outperformed the Cox model in predicting the survival outcomes of PLWHA in China and having a remarkable prognostic stratification.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.