Yang Jiang, Hanyu Jiang, Jing Zhang, Tao Chen, Ying Li, Yuehua Zhou, Youxin Chen, Fusheng Li
{"title":"开发机器学习模型,培训初级眼科医生诊断临床前角膜炎","authors":"Yang Jiang, Hanyu Jiang, Jing Zhang, Tao Chen, Ying Li, Yuehua Zhou, Youxin Chen, Fusheng Li","doi":"10.3389/fmed.2024.1458356","DOIUrl":null,"url":null,"abstract":"PurposeThis study aims to evaluate the diagnostic performance of a machine learning model (ML model) to train junior ophthalmologists in detecting preclinical keratoconus (PKC).MethodsA total of 1,334 corneal topography images (The Pentacam HR system) from 413 keratoconus eyes, 32 PKC eyes and 222 normal eyes were collected. Five junior ophthalmologists were trained and annotated the images with or without the suggestions proposed by the ML model. The diagnostic performance of PKC was evaluated among three groups: junior ophthalmologist group (control group), ML model group and ML model-training junior ophthalmologist group (test group).ResultsThe accuracy of the ML model between the eyes of patients with KC and NEs in all three clinics (99% accuracy, area under the receiver operating characteristic (ROC) curve AUC of 1.00, 99% sensitivity, 99% specificity) was higher than that for Belin-Ambrósio enhanced ectasia display total deviation (BAD-D) (86% accuracy, AUC of 0.97, 97% sensitivity, 69% specificity). The accuracy of the ML model between eyes with PKC and NEs in all three clinics (98% accuracy, AUC of 0.96, 98% sensitivity, 98% specificity) was higher than that of BAD-D (69% accuracy, AUC of 0.73, 67% sensitivity, 69% specificity). The diagnostic accuracy of PKC was 47.5% (95%CI, 0.5–71.6%), 100% (95%CI, 100–100%) and 94.4% (95%CI, 14.7–94.7%) in the control group, ML model group and test group. With the assistance of the proposed ML model, the diagnostic accuracy of junior ophthalmologists improved with statistical significance (<jats:italic>p</jats:italic> &lt; 0.05). According to the questionnaire of all the junior ophthalmologists, the average score was 4 (total 5) regarding to the comprehensiveness that the AI model has been in their keratoconus diagnosis learning; the average score was 4.4 (total 5) regarding to the convenience that the AI model has been in their keratoconus diagnosis learning.ConclusionThe proposed ML model provided a novel approach for the detection of PKC with high diagnostic accuracy and assisted to improve the performance of junior ophthalmologists, resulting especially in reducing the risk of missed diagnoses.","PeriodicalId":12488,"journal":{"name":"Frontiers in Medicine","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The development of a machine learning model to train junior ophthalmologists in diagnosing the pre-clinical keratoconus\",\"authors\":\"Yang Jiang, Hanyu Jiang, Jing Zhang, Tao Chen, Ying Li, Yuehua Zhou, Youxin Chen, Fusheng Li\",\"doi\":\"10.3389/fmed.2024.1458356\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"PurposeThis study aims to evaluate the diagnostic performance of a machine learning model (ML model) to train junior ophthalmologists in detecting preclinical keratoconus (PKC).MethodsA total of 1,334 corneal topography images (The Pentacam HR system) from 413 keratoconus eyes, 32 PKC eyes and 222 normal eyes were collected. Five junior ophthalmologists were trained and annotated the images with or without the suggestions proposed by the ML model. The diagnostic performance of PKC was evaluated among three groups: junior ophthalmologist group (control group), ML model group and ML model-training junior ophthalmologist group (test group).ResultsThe accuracy of the ML model between the eyes of patients with KC and NEs in all three clinics (99% accuracy, area under the receiver operating characteristic (ROC) curve AUC of 1.00, 99% sensitivity, 99% specificity) was higher than that for Belin-Ambrósio enhanced ectasia display total deviation (BAD-D) (86% accuracy, AUC of 0.97, 97% sensitivity, 69% specificity). The accuracy of the ML model between eyes with PKC and NEs in all three clinics (98% accuracy, AUC of 0.96, 98% sensitivity, 98% specificity) was higher than that of BAD-D (69% accuracy, AUC of 0.73, 67% sensitivity, 69% specificity). The diagnostic accuracy of PKC was 47.5% (95%CI, 0.5–71.6%), 100% (95%CI, 100–100%) and 94.4% (95%CI, 14.7–94.7%) in the control group, ML model group and test group. With the assistance of the proposed ML model, the diagnostic accuracy of junior ophthalmologists improved with statistical significance (<jats:italic>p</jats:italic> &lt; 0.05). According to the questionnaire of all the junior ophthalmologists, the average score was 4 (total 5) regarding to the comprehensiveness that the AI model has been in their keratoconus diagnosis learning; the average score was 4.4 (total 5) regarding to the convenience that the AI model has been in their keratoconus diagnosis learning.ConclusionThe proposed ML model provided a novel approach for the detection of PKC with high diagnostic accuracy and assisted to improve the performance of junior ophthalmologists, resulting especially in reducing the risk of missed diagnoses.\",\"PeriodicalId\":12488,\"journal\":{\"name\":\"Frontiers in Medicine\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.3389/fmed.2024.1458356\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MEDICINE, GENERAL & INTERNAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3389/fmed.2024.1458356","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
The development of a machine learning model to train junior ophthalmologists in diagnosing the pre-clinical keratoconus
PurposeThis study aims to evaluate the diagnostic performance of a machine learning model (ML model) to train junior ophthalmologists in detecting preclinical keratoconus (PKC).MethodsA total of 1,334 corneal topography images (The Pentacam HR system) from 413 keratoconus eyes, 32 PKC eyes and 222 normal eyes were collected. Five junior ophthalmologists were trained and annotated the images with or without the suggestions proposed by the ML model. The diagnostic performance of PKC was evaluated among three groups: junior ophthalmologist group (control group), ML model group and ML model-training junior ophthalmologist group (test group).ResultsThe accuracy of the ML model between the eyes of patients with KC and NEs in all three clinics (99% accuracy, area under the receiver operating characteristic (ROC) curve AUC of 1.00, 99% sensitivity, 99% specificity) was higher than that for Belin-Ambrósio enhanced ectasia display total deviation (BAD-D) (86% accuracy, AUC of 0.97, 97% sensitivity, 69% specificity). The accuracy of the ML model between eyes with PKC and NEs in all three clinics (98% accuracy, AUC of 0.96, 98% sensitivity, 98% specificity) was higher than that of BAD-D (69% accuracy, AUC of 0.73, 67% sensitivity, 69% specificity). The diagnostic accuracy of PKC was 47.5% (95%CI, 0.5–71.6%), 100% (95%CI, 100–100%) and 94.4% (95%CI, 14.7–94.7%) in the control group, ML model group and test group. With the assistance of the proposed ML model, the diagnostic accuracy of junior ophthalmologists improved with statistical significance (p < 0.05). According to the questionnaire of all the junior ophthalmologists, the average score was 4 (total 5) regarding to the comprehensiveness that the AI model has been in their keratoconus diagnosis learning; the average score was 4.4 (total 5) regarding to the convenience that the AI model has been in their keratoconus diagnosis learning.ConclusionThe proposed ML model provided a novel approach for the detection of PKC with high diagnostic accuracy and assisted to improve the performance of junior ophthalmologists, resulting especially in reducing the risk of missed diagnoses.
期刊介绍:
Frontiers in Medicine publishes rigorously peer-reviewed research linking basic research to clinical practice and patient care, as well as translating scientific advances into new therapies and diagnostic tools. Led by an outstanding Editorial Board of international experts, this multidisciplinary open-access journal is at the forefront of disseminating and communicating scientific knowledge and impactful discoveries to researchers, academics, clinicians and the public worldwide.
In addition to papers that provide a link between basic research and clinical practice, a particular emphasis is given to studies that are directly relevant to patient care. In this spirit, the journal publishes the latest research results and medical knowledge that facilitate the translation of scientific advances into new therapies or diagnostic tools. The full listing of the Specialty Sections represented by Frontiers in Medicine is as listed below. As well as the established medical disciplines, Frontiers in Medicine is launching new sections that together will facilitate
- the use of patient-reported outcomes under real world conditions
- the exploitation of big data and the use of novel information and communication tools in the assessment of new medicines
- the scientific bases for guidelines and decisions from regulatory authorities
- access to medicinal products and medical devices worldwide
- addressing the grand health challenges around the world