Rxivist logo

Identification of Key Influencers for Secondary Distribution of HIV Self-Testing among Chinese MSM: A Machine Learning Approach

By Fengshi JING, Yang Ye, Yi Zhou, Yuxin Ni, Xumeng Yan, Ying Lu, Jason J. Ong, Joseph D Tucker, Dan Wu, Yuan Xiong, Chen Xu, Xi He, Shanzi Huang, Xiaofeng Li, Hongbo Jiang, Cheng Wang, Wencan Dai, Liqun Huang, Wenhua Mei, Weibin Cheng, Qingpeng Zhang, Weiming Tang

Posted 20 Apr 2021
medRxiv DOI: 10.1101/2021.04.19.21255584

Abstract Background. HIV self-testing (HIVST) has been rapidly scaled up and additional strategies further expand testing uptake. Secondary distribution has people (indexes) apply for multiple kits and pass these kits to people (alters) in their social networks. However, identifying key influencers is difficult. This study aimed to develop an innovative ensemble machine learning approach to identify key influencers among Chinese men who have sex with men (MSM) for HIVST secondary distribution. Method. We defined three types of key influencers: 1) key distributors who can distribute more kits; 2) key promoters who can contribute to finding first-time testing alters; 3) key detectors who can help to find positive alters. Four machine learning models (logistic regression, support vector machine, decision tree, random forest) were trained to identify key influencers. An ensemble learning algorithm was adopted to combine these four models. Simulation experiments were run to validate our approach. Results. 309 indexes distributed kits to 269 alters. Our approach outperformed human identification (self-reported scales cut-off), exceeding by an average accuracy of 11.0%, could distribute 18.2% (95%CI: 9.9%-26.5%) more kits, find 13.6% (95%CI: 1.9%-25.3%) more first-time testing alters and 12.0% (95%CI: -14.7%-38.7%) more positive-testing alters. Our approach could also increase simulated intervention efficiency by 17.7% (95%CI: -3.5%-38.8%) than human identification. Conclusion. We built machine learning models to identify key influencers among Chinese MSM who were more likely to engage in HIVST secondary distribution.

Download data

  • Downloaded 195 times
  • Download rankings, all-time:
    • Site-wide: 161,700
    • In hiv aids: 164
  • Year to date:
    • Site-wide: 86,373
  • Since beginning of last month:
    • Site-wide: None

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

News