将人工智能性传播疾病症状检查工具用于麻疹检测:HeHealth 的经验。

IF 1.8 4区 医学 Q3 INFECTIOUS DISEASES
Sexual health Pub Date : 2024-05-01 DOI:10.1071/SH23197
Rayner Kay Jin Tan, Dilruk Perera, Salomi Arasaratnam, Yudara Kularathne
{"title":"将人工智能性传播疾病症状检查工具用于麻疹检测:HeHealth 的经验。","authors":"Rayner Kay Jin Tan, Dilruk Perera, Salomi Arasaratnam, Yudara Kularathne","doi":"10.1071/SH23197","DOIUrl":null,"url":null,"abstract":"<p><p>Artificial Intelligence (AI) applications have shown promise in the management of pandemics. In response to the global Monkeypox (Mpox) outbreak, the HeHealth.ai team leveraged an existing tool to screen for sexually transmitted diseases (STD) to develop a digital screening test for symptomatic Mpox using AI. Before the global Mpox outbreak, the team developed a smartphone app (HeHealth) where app users can use a smartphone to photograph their own penises to screen for symptomatic STD. The AI model initially used 5000 cases and a modified convolutional neural network to output prediction scores across visually diagnosable penis pathologies including syphilis, herpes simplex virus, and human papillomavirus. A total of about 22,000 users had downloaded the HeHealth app, and ~21,000 images were analysed using HeHealth AI technology. We then used formative research, stakeholder engagement, rapid consolidation images, a validation study, and implementation of the tool. A total of 1000 Mpox-related images had been used to train the Mpox symptom checker tool. Based on an internal validation, our digital symptom checker tool showed specificity of 87% and sensitivity of 90% for symptomatic Mpox. Several hurdles identified included issues of data privacy and security for app users, initial lack of data to train the AI tool, and the potential generalisability of input data. We offer several suggestions to help others get started on similar projects in emergency situations, including engaging a wide range of stakeholders, having a multidisciplinary team, prioritising pragmatism, as well as the concept that 'big data' in fact is made up of 'small data'.</p>","PeriodicalId":22165,"journal":{"name":"Sexual health","volume":"21 ","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Adapting an artificial intelligence sexually transmitted diseases symptom checker tool for Mpox detection: the HeHealth experience.\",\"authors\":\"Rayner Kay Jin Tan, Dilruk Perera, Salomi Arasaratnam, Yudara Kularathne\",\"doi\":\"10.1071/SH23197\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Artificial Intelligence (AI) applications have shown promise in the management of pandemics. In response to the global Monkeypox (Mpox) outbreak, the HeHealth.ai team leveraged an existing tool to screen for sexually transmitted diseases (STD) to develop a digital screening test for symptomatic Mpox using AI. Before the global Mpox outbreak, the team developed a smartphone app (HeHealth) where app users can use a smartphone to photograph their own penises to screen for symptomatic STD. The AI model initially used 5000 cases and a modified convolutional neural network to output prediction scores across visually diagnosable penis pathologies including syphilis, herpes simplex virus, and human papillomavirus. A total of about 22,000 users had downloaded the HeHealth app, and ~21,000 images were analysed using HeHealth AI technology. We then used formative research, stakeholder engagement, rapid consolidation images, a validation study, and implementation of the tool. A total of 1000 Mpox-related images had been used to train the Mpox symptom checker tool. Based on an internal validation, our digital symptom checker tool showed specificity of 87% and sensitivity of 90% for symptomatic Mpox. Several hurdles identified included issues of data privacy and security for app users, initial lack of data to train the AI tool, and the potential generalisability of input data. We offer several suggestions to help others get started on similar projects in emergency situations, including engaging a wide range of stakeholders, having a multidisciplinary team, prioritising pragmatism, as well as the concept that 'big data' in fact is made up of 'small data'.</p>\",\"PeriodicalId\":22165,\"journal\":{\"name\":\"Sexual health\",\"volume\":\"21 \",\"pages\":\"\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2024-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Sexual health\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1071/SH23197\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"INFECTIOUS DISEASES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sexual health","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1071/SH23197","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"INFECTIOUS DISEASES","Score":null,"Total":0}
引用次数: 0

摘要

人工智能(AI)应用在大流行病管理方面大有可为。在应对全球猴痘(Mpox)疫情时,HeHealth.ai 团队利用现有的性传播疾病(STD)筛查工具,开发了一种利用人工智能进行的无症状猴痘数字筛查测试。在全球痘病爆发之前,该团队开发了一款智能手机应用程序(HeHealth),应用程序用户可以使用智能手机拍摄自己的阴茎,以筛查有症状的性传播疾病。人工智能模型最初使用了5000个病例和一个改进的卷积神经网络来输出可视诊断阴茎病变的预测分数,包括梅毒、单纯疱疹病毒和人类乳头瘤病毒。共有约 22,000 名用户下载了 HeHealth 应用程序,使用 HeHealth 人工智能技术分析了约 21,000 张图像。然后,我们进行了形成性研究、利益相关者参与、快速整合图像、验证研究,并实施了该工具。总共有 1000 张与麻疹相关的图片被用于训练麻疹症状检查工具。根据内部验证,我们的数字症状检查工具对有症状的水痘显示出 87% 的特异性和 90% 的灵敏度。我们发现的几个障碍包括应用程序用户的数据隐私和安全问题、最初缺乏训练人工智能工具的数据以及输入数据的潜在通用性。我们提出了一些建议,以帮助其他人在紧急情况下开始类似的项目,包括让广泛的利益相关者参与进来、组建多学科团队、优先考虑实用性,以及 "大数据 "实际上是由 "小数据 "组成的概念。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Adapting an artificial intelligence sexually transmitted diseases symptom checker tool for Mpox detection: the HeHealth experience.

Artificial Intelligence (AI) applications have shown promise in the management of pandemics. In response to the global Monkeypox (Mpox) outbreak, the HeHealth.ai team leveraged an existing tool to screen for sexually transmitted diseases (STD) to develop a digital screening test for symptomatic Mpox using AI. Before the global Mpox outbreak, the team developed a smartphone app (HeHealth) where app users can use a smartphone to photograph their own penises to screen for symptomatic STD. The AI model initially used 5000 cases and a modified convolutional neural network to output prediction scores across visually diagnosable penis pathologies including syphilis, herpes simplex virus, and human papillomavirus. A total of about 22,000 users had downloaded the HeHealth app, and ~21,000 images were analysed using HeHealth AI technology. We then used formative research, stakeholder engagement, rapid consolidation images, a validation study, and implementation of the tool. A total of 1000 Mpox-related images had been used to train the Mpox symptom checker tool. Based on an internal validation, our digital symptom checker tool showed specificity of 87% and sensitivity of 90% for symptomatic Mpox. Several hurdles identified included issues of data privacy and security for app users, initial lack of data to train the AI tool, and the potential generalisability of input data. We offer several suggestions to help others get started on similar projects in emergency situations, including engaging a wide range of stakeholders, having a multidisciplinary team, prioritising pragmatism, as well as the concept that 'big data' in fact is made up of 'small data'.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Sexual health
Sexual health 医学-传染病学
CiteScore
2.30
自引率
12.50%
发文量
121
审稿时长
6-12 weeks
期刊介绍: Sexual Health publishes original and significant contributions to the fields of sexual health including HIV/AIDS, Sexually transmissible infections, issues of sexuality and relevant areas of reproductive health. This journal is directed towards those working in sexual health as clinicians, public health practitioners, researchers in behavioural, clinical, laboratory, public health or social, sciences. The journal publishes peer reviewed original research, editorials, review articles, topical debates, case reports and critical correspondence. Officially sponsored by: The Australasian Chapter of Sexual Health Medicine of RACP Sexual Health Society of Queensland Sexual Health is the official journal of the International Union against Sexually Transmitted Infections (IUSTI), Asia-Pacific, and the Asia-Oceania Federation of Sexology.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信