Artificial Intelligence and Modelling in Epidemiology Program, Melbourne Sexual Health Centre, Alfred Health, Melbourne, Australia.
School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia.
BMC Public Health. 2024 Nov 21;24(1):3236. doi: 10.1186/s12889-024-20688-2.
Early detection and treatment of HIV and sexually transmitted infections (STIs) are crucial for effective control. We previously developed MySTIRisk, an artificial intelligence-based risk tool that predicts the risk of HIV and STIs. We examined the attributes that encourage potential users to use it.
Between January and March 2024, we sent text message invitations to the Melbourne Sexual Health Centre (MSHC) attendees to participate in an online survey. We also advertised the survey on social media, the clinic's website, and posters in affiliated general practice clinics. This anonymous survey used a discrete choice experiment (DCE) to examine which MySTIRisk attributes would encourage potential users. We analysed the data using random parameters logit (RPL) and latent class analysis (LCA) models.
The median age of 415 participants was 31 years (interquartile range, 26-38 years), with a minority of participants identifying as straight or heterosexual (31.8%, n = 132). The choice to use MySTIRisk was most influenced by two attributes: cost and accuracy, followed by the availability of a pathology request form, level of anonymity, speed of receiving results, and whether the tool was a web or mobile application. LCA revealed two classes: "The Precisionists" (66.0% of respondents), who demanded high accuracy and "The Economists" (34.0% of respondents), who prioritised low cost. Simulations predicted a high uptake (97.7%) for a tool designed with the most preferred attribute levels, contrasting with lower uptake (22.3%) for the least preferred design.
Participants were more likely to use MySTIRisk if it was free, highly accurate, and could send pathology request forms. Tailoring the tool to distinct user segments could enhance its uptake and effectiveness in promoting early detection and prevention of HIV and STIs.
早期发现和治疗艾滋病毒和性传播感染(STI)对于有效控制至关重要。我们之前开发了基于人工智能的风险工具 MySTIRisk,用于预测艾滋病毒和 STI 的风险。我们研究了鼓励潜在用户使用它的属性。
在 2024 年 1 月至 3 月期间,我们向墨尔本性健康中心(MSHC)的与会者发送了短信邀请,邀请他们参加在线调查。我们还在社交媒体、诊所网站和附属全科诊所的海报上宣传了这项调查。这项匿名调查使用离散选择实验(DCE)来研究哪些 MySTIRisk 属性会鼓励潜在用户使用该工具。我们使用随机参数对数(RPL)和潜在类别分析(LCA)模型对数据进行分析。
415 名参与者的中位数年龄为 31 岁(四分位距,26-38 岁),少数参与者为异性恋或异性恋(31.8%,n=132)。选择使用 MySTIRisk 的最主要影响因素是成本和准确性,其次是提供病理学请求表、匿名程度、获得结果的速度以及该工具是网络应用程序还是移动应用程序。LCA 揭示了两个类别:“精度主义者”(66.0%的受访者),他们要求高度准确,“经济主义者”(34.0%的受访者),他们优先考虑低成本。模拟预测,如果设计的工具具有最受欢迎的属性水平,那么工具的使用率将会很高(97.7%),而如果设计的工具具有最不受欢迎的属性水平,那么工具的使用率将会很低(22.3%)。
如果 MySTIRisk 是免费的、高度准确的,并且可以发送病理学请求表,那么参与者更有可能使用它。根据不同的用户群体调整工具,可以提高其使用率和促进艾滋病毒和 STI 的早期发现和预防的有效性。