Develop an Artificial Intelligence-powered Smartphone App AICaries for Caries Detection in Children

开发人工智能驱动的智能手机应用程序 AICaries，用于儿童龋齿检测

• 批准号: 10331877
• 负责人: Kevin Fiscella
• 金额: $ 23.1万
• 依托单位: UNIVERSITY OF ROCHESTER
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-02-01 至 2023-01-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10331877
• 关键词: Address; Advisory Committees; Algorithms; American; Archives; Artificial Intelligence; Caregivers; Caries prevention; Cellular Phone; Child; Childhood; Chronic; Chronic Disease; Clinical; Clinical Trials; Coupled; Data; Data Analyses; Databases; Dental; Dental Care; Dental Clinics; Dental Hygiene; Dental caries; Dentists; Detection; Development; Diabetes Mellitus; Diagnosis; Diet; Disease; Early Diagnosis; Education; Family; Family Caregiver; Feedback; Future; Goals; Health; Healthcare; Healthcare Systems; Image; Individual; Knowledge; Life Style; Long-Term Effects; Low income; Methods; Minority; Modification; Monitor; Oral; Oral health; Parents; Patient Education; Patients; Performance; Population; Positioning Attribute; Preschool Child; Prevention; Prevention strategy; Preventive; Procedures; Process; Quality of life; Reporting; Research; Risk; Risk Assessment; Risk Factors; Sensitivity and Specificity; Severities; System; Technology; Testing; Tooth structure; Training; Underserved Population; Work; acceptability and feasibility; community based participatory research; community engagement; computer science; computerized; detection sensitivity; early childhood; education resources; empowered; field study; health literacy; improved; indexing; innovation; lower income families; mHealth; microbial; multidisciplinary; novel; pandemic disease; performance tests; population based; prototype; recruit; restorative treatment; satisfaction; skills; smartphone Application; success; tool; usability

Project Summary Early childhood caries (ECC) is the most common chronic childhood disease, with nearly 1.8 billion new cases per year globally. ECC afflicts approximately 55% of low-income and minority US preschool children, resulting in harmful short- and long-term effects on health and quality of life. The current biomedical approach to control the ECC pandemic has had limited success. It primarily focuses on restorative procedures rather than population-wide preventive strategies. Clinical evidence shows that caries is reversible if detected and addressed in its early stages. However, many low-income US children often have poor access to pediatric dental services. In this underserved group, dental caries is often diagnosed at a late stage when extensive restorative treatment is needed. We believe that with more than 85% of lower-income Americans owning a smartphone, mHealth tools hold great promise to achieve patient-driven early detection and risk control of ECC. Our long-term goal is to develop strategies that use mHealth tools to achieve early detection and prevention of ECC at a broad population base. Our previous innovative work has led to a novel prototype of an artificial intelligence (AI) -powered smartphone app, AICaries, to be used by children's parents/caregivers. This AICaries app prototype offers a) AI-powered caries detection using photos of children's teeth taken by the parents' smartphones, b) interactive caries risk assessment, and c) personalized education on reducing children's ECC risk. The preliminary AI- powered caries detection module demonstrated a satisfactory sensitivity and specificity for front teeth caries detection, using 6,895 annotated tooth images from 1,277 photos. We have recently built an archive of > 100,000 high-quality intra-oral photos that is ready to be used for finalizing the development of a reliable automatic detection algorithm. The immediate objectives of the study are - AIM 1: complete the development of AICaries smartphone app, maximize its caries detection performance, and achieve a caries detection sensitivity and specificity that are comparable to trained dental practitioners; AIM 2: employ a community-based participatory research strategy to conduct moderated testing and refinement of the app usability, and non-moderated field testing of the app feasibility/acceptability. Our multidisciplinary team is well-positioned for proposal success with needed expertise in computer science, AI imaging recognition, oral health care, mHealth, disparity research, patient education and community engagement. The AICaries app could facilitate early detection of ECC for many underserved US children, who often have poor access to pediatric dental services. Using AICaries, parents can use their regular smartphones to take photo of their children’s teeth and detect ECC aided by AICaries, so that they can actively seek treatment for their children at an early and reversible stage of ECC. Using AICaries, parents can also obtain essential knowledge on reducing their children's caries risk. Data from this R21 will support a R01 clinical trial that evaluates the real-world impact of using this innovative smartphone app on early detection and prevention of ECC among low-income children.

项目摘要 儿童早期龋病(ECC)是最常见的儿童慢性疾病，有近18亿新病例 每年在全球范围内。ECC困扰着大约55%的低收入和少数族裔美国学龄前儿童，结果 对健康和生活质量的短期和长期有害影响。当前的生物医学控制方法 ECC大流行取得的成功有限。它主要关注恢复性程序，而不是 全民预防战略。临床证据表明，如果被发现和解决，龋齿是可逆的。 在它的早期阶段。然而，许多低收入的美国儿童往往无法获得儿科牙科服务。 在这一缺乏服务的群体中，龋齿通常在晚期被诊断出来，当时需要广泛的恢复性治疗。 是必要的。我们认为，由于超过85%的低收入美国人拥有智能手机，mHealth Tools 大有希望实现以患者为主导的ECC早期发现和风险控制。我们的长期目标是 制定使用mHealth工具的策略，在广大人群中实现早期发现和预防ECC 基地。我们之前的创新工作导致了一个由人工智能(AI)驱动的新原型 智能手机应用程序AICary，供孩子的父母/照顾者使用。此AICary应用程序原型提供了) 使用父母智能手机拍摄的儿童牙齿照片的人工智能支持的龋齿检测，b)交互式 龋齿风险评估，以及c)关于降低儿童ECC风险的个性化教育。初步的人工智能- 电动龋齿检测模块对前牙龋病的敏感性和特异性均令人满意 检测，使用了1,277张照片中的6895张带注释的牙齿图像。我们最近建立了一份10万英镑的档案 高质量的口腔内照片，准备用于最终确定开发的可靠的自动 检测算法。这项研究的近期目标是：目标1：完成急性龋齿的发展 智能手机应用程序，最大限度地提高其龋齿检测性能，实现龋病检测灵敏度和 与训练有素的牙医相媲美的专业性；目标2：采用以社区为基础的参与式 研究战略，对应用程序的可用性和非适度领域进行适度测试和改进 测试应用程序的可行性/可接受性。我们的多学科团队已经做好了计划的准备 在计算机科学、人工智能成像识别、口腔保健、mHealth、 差异研究、患者教育和社区参与。AICary应用程序可以帮助提早 为许多服务不足的美国儿童检测ECC，他们往往很难获得儿童牙科服务 服务。使用AICary，父母可以用他们的普通智能手机给孩子的牙齿拍照，并 在AICars的帮助下检测ECC，以便他们能够积极地为他们的孩子寻求早期和可逆的治疗 ECC阶段。使用AICary，父母还可以获得减少孩子龋齿的基本知识 风险。此R21的数据将支持R01临床试验，以评估使用这一创新技术的实际影响 低收入儿童早期发现和预防ECC的智能手机应用程序。

项目成果

Artificial intelligence-powered smartphone application, AICaries, improves at-home dental caries screening in children: Moderated and unmoderated usability test

人工智能驱动的智能手机应用程序 AICaries 改善了儿童家庭龋齿筛查：有节制和无节制的可用性测试

• DOI: 10.1371/journal.pdig.0000046
• 发表时间: 2022
• 期刊: PLOS Digital Health
• 作者: Al-Jallad, Nisreen;Ly-Mapes, Oriana;Hao, Peirong;Ruan, Jinlong;Ramesh, Ashwin;Luo, Jiebo;Wu, Tong Tong;Dye, Timothy;Rashwan, Noha;Ren, Johana
• 通讯作者: Ren, Johana