Remmie.ai: a deep learning diagnostic assistance engine for ear-nose-throat diseases

Remmie.ai：耳鼻喉疾病深度学习诊断辅助引擎

• 批准号: 10602813
• 负责人: Jane Zhang
• 金额: $ 34.99万
• 依托单位: REMMIE, INC.
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-12-01 至 2023-11-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10602813
• 关键词: Academy; Acute; Address; Adult; Age; Age Years; Algorithms; American; Antibiotic Therapy; Antibiotics; Architecture; Artificial Intelligence platform; Blinded; Caregivers; Caring; Certification; Child; Child Support; Childhood; Classification; Clinic; Clinic Visits; Clinical; Collaborations; Computer software; Country; Coupled; Custom; Data; Data Set; Databases; Development; Devices; Diagnosis; Diagnostic; Disease; Drainage procedure; Ear; Earache; Early Diagnosis; Economic Burden; Ensure; Family; Feedback; Fever; Future; Health Care Costs; Health Insurance Portability and Accountability Act; Healthcare; Healthcare Systems; Home; Image; Income; Infection; Institutional Review Boards; Label; Libraries; Liquid substance; Machine Learning; Malleus; Medicine; Modeling; Monitor; Nose; Otitis Media; Otolaryngologist; Otolaryngology; Otoscopes; Outcome; Patient imaging; Patient observation; Patients; Pediatric Hospitals; Pediatrics; Persons; Pharmaceutical Preparations; Pharyngeal structure; Phase; Physicians; Positioning Attribute; Process; Protocols documentation; Provider; Recommendation; Recurrence; Resource-limited setting; Resources; Secure; Specialist; Structure; Supervision; Surveys; Symptoms; System; Technology; Telemedicine; Testing; Text; Time; Tissues; Training; Tube; Tympanic membrane; Tympanostomy Tube Insertions; Validation; Visit; Visual; Work; accurate diagnosis; age group; artificial intelligence algorithm; burden of illness; care burden; care providers; clinical diagnosis; clinical diagnostics; clinical efficacy; convolutional neural network; cost; deep learning; disability; ear infection; efficacy study; experience; experimental study; hearing impairment; improved; infection management; machine learning algorithm; middle ear; mobile application; neural network algorithm; novel; pediatrician; portability; prevent; recurrent infection; research and development; response; success; symptom management; technological innovation; telehealth; tool; transfer learning; usability; user-friendly; ventilation; virtual visit

PROJECT SUMMARY Otitis media (OM) is experienced by five out of six children before their third birthday, and 30-40% suffer recurring infections, leading to 16 million annual episodes in the US. Ear infections are the primary reason for antibiotic prescription for children under 6 years, are the second most common cause of hearing loss, and can lead to lifelong sequelae. Diagnosis depends upon in-person clinic visits and visual examination by care providers, at great inconvenience to patients and caregivers and at significant cost to the healthcare system, estimated at $4 billion per year. Although the majority of OM cases resolve within a week and symptoms may be managed by over-the-counter medications,10-20% do not, requiring additional antibiotic treatment or, in extreme cases, tympanostomy tube insertion to provide ventilation to the middle ear and aid in fluid drainage. Another compounding factor is limited access to otolaryngologists for accurate diagnosis and infection management. The expansion of telehealth has the potential to address this need with rapid, convenient, and affordable, but to date, there are no platforms to support and facilitate effective virtual visits for OM diagnosis. The first Specific Aim of this Phase I proposal involves building a comprehensive database of several thousand images of eardrums from patients with or without acute OM, with associated clinical diagnostic labels to, in Specific Aim 2, train a novel custom machine learning algorithm, Remmie.ai. A convolutional neural network will be developed to classify images of eardrums paired with text description of symptoms. Image classification will be improved through data augmentation, and the custom Remmie.ai architecture built through transfer learning of a publicly available training model. Unblinded labels will be compared to the algorithm readout as blinded testing data are loaded into Remmie.ai to ensure convergence of accuracy and validation for classification of acute OM versus normal eardrums. In Specific Aim 3, the Remmie.at platform, coupled with a handheld “portable otoscope” for imaging patients’ eardrums and a user-friendly mobile device application, will be tested by end-user physicians to derive feedback on the usability of the device and software. The outcome will be a novel tool for both patients and caregivers to monitor otolaryngic diseases, specifically acute OM, based on patient-provided images and symptoms, and diagnosis, aided by the proprietary Remmie.ai algorithm.

项目摘要 中耳炎（OM）是经历了五出六名儿童在他们的第三个生日，30-40%的人患有 复发性感染，导致美国每年发生1600万次感染。耳朵感染是导致 6岁以下儿童的抗生素处方，是听力损失的第二大常见原因， 导致终身后遗症。诊断取决于亲自到诊所就诊和护理人员的目视检查 提供者，给患者和护理人员带来极大的不便，并给医疗保健系统带来巨大的成本， 估计每年40亿美元。虽然大多数OM病例在一周内消退，症状可能 可以通过非处方药管理，10-20%不需要，需要额外的抗生素治疗，或者， 在极端情况下，插入鼓膜造口管，为中耳提供通风，并帮助引流液体。 另一个复杂的因素是获得耳鼻喉科医生的准确诊断和感染有限 管理远程医疗的扩展有可能通过快速、方便和 虽然价格实惠，但迄今为止，还没有平台支持和促进有效的虚拟访问，以进行OM诊断。 第一阶段提案的第一个具体目标是建立一个包含数千个数据的综合数据库， 患有或不患有急性OM的患者的鼓膜图像，以及相关的临床诊断标签， 具体目标2，训练一种新颖的自定义机器学习算法Remmie. ai。卷积神经网络 将被开发来分类与症状的文本描述配对的鼓膜图像。图像分类 将通过数据扩充和通过传输构建的自定义Remmie.ai架构来改进 学习公开可用的培训模型。将揭盲标签与算法读数进行比较， 将盲态测试数据加载到Remmie.ai中，以确保准确性和验证的收敛， 急性OM与正常鼓膜的分类。在具体目标3中，Remmie.at平台与 用于对患者鼓膜进行成像的手持“便携式耳镜”和用户友好的移动终端应用程序将 由最终用户医生进行测试，以获得有关器械和软件可用性的反馈。成果 将成为患者和护理人员监测耳鼻喉科疾病，特别是急性OM， 基于患者提供的图像和症状以及诊断，并在专有的Remmie.ai 算法