Performance of HIV Infection Prediction Models in Men Who Have Sex with Men: A Systematic Review and Meta-Analysis

The predictive accuracy of machine learning for the risk of death in HIV patients: a systematic review and meta-analysis

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.

Balancing public health and privacy rights: a mixed-methods study on disclosure obligations of people living with HIV to their partners in China

BACKGROUND

In 2021, a Chinese court, based on the newly enacted Civil Code, first revoked a marriage license due to the spouse's failure to disclose their HIV infection before the marriage. This landmark case ignited a fresh debate on whether people living with HIV (PLHIV) have a legal duty to inform their spouses and sexual partners. Advances in medicine have partially isolated HIV transmission from sexual contact, extending the legal basis for the obligation to disclose beyond disease prevention. This study investigates some possibly unforeseen challenges for PLHIV in China to fulfill this duty, and the outcomes of their decisions in light of the government's goal to promote health.

METHODS

This study aims to provide a detailed examination of the legal provisions and practices concerning partner notification among PLHIV in China. A mixed-methods research approach was employed between 2019 and 2020, combining questionnaire surveys, in-depth interviews, and participatory observations. A total of 433 valid responses were obtained through a questionnaire posted on a Chinese online platform for PLHIV. Following the collection and random coding of the questionnaire data, 40 individuals living with HIV were selected for in-depth interviews. Subsequently, a six-month field investigation was conducted in Guan ai jia yuan (Caring Home) in Jinhua City to further explore this issue.

RESULTS

A considerable proportion of PLHIV exhibit a high rate of disclosure to their spouses (nearly 80%). In the context of sexual partners, 56% of PLHIV stated that their sexual partners were aware of their HIV infection. Whether married PLHIV disclosing to their spouses or unmarried/divorced PLHIV disclosing to sexual partners, however, a substantial majority expressed apprehension about the potential disruption to their relationships that the disclosure might cause. The sole exception was observed among married PLHIV in extramarital relationships who demonstrated a slightly diminished level of concern in this context. Reasons for non-disclosure predominantly included undetectable viral load and the adoption of protective measures.

DISCUSSION

This study reveals that a prevailing "HIV stigma" hinders PLHIV from voluntarily fulfilling the disclosure duties bestowed by Article 38 of the Regulations on the Prevention and Control of HIV/AIDS, and the unclear legal provisions of the new Civil Code play a significant role in this regard. Addressing this issue necessitates not only increasing societal tolerance toward PLHIV and reducing instances of social exclusion but also shifting the legal basis of disclosure duties from disease prevention to rights and obligations within the legal relationships of the parties involved. When it comes to the recipients of disclosure, for instance, it is crucial to differentiate between spouses and sexual partners. As for PLHIV failing to fulfill their disclosure duties, apart from interventions involving indirect notifications, the addition of further legal responsibilities may not be advisable. Intentional transmission actions, on the other hand, should still be subject to severe penalties.

CLINICAL TRIAL NUMBER

Not applicable.