Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts
IntroductionThe diagnosis and treatment of ankylosing spondylitis (AS) is a difficult task, especially in less developed countries without access to experts. To address this issue, a comprehensive artificial intelligence (AI) tool was created to help diagnose and predict the course of AS.MethodsIn t...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-02-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2023.1063633/full |
| _version_ | 1811168307757187072 |
|---|---|
| author | Hao Li Xiang Tao Tuo Liang Jie Jiang Jichong Zhu Shaofeng Wu Liyi Chen Zide Zhang Chenxing Zhou Xuhua Sun Shengsheng Huang Jiarui Chen Tianyou Chen Zhen Ye Wuhua Chen Hao Guo Yuanlin Yao Shian Liao Chaojie Yu Binguang Fan Yihong Liu Chunai Lu Junnan Hu Qinghong Xie Xiao Wei Cairen Fang Huijiang Liu Chengqian Huang Shixin Pan Xinli Zhan Chong Liu |
| author_facet | Hao Li Xiang Tao Tuo Liang Jie Jiang Jichong Zhu Shaofeng Wu Liyi Chen Zide Zhang Chenxing Zhou Xuhua Sun Shengsheng Huang Jiarui Chen Tianyou Chen Zhen Ye Wuhua Chen Hao Guo Yuanlin Yao Shian Liao Chaojie Yu Binguang Fan Yihong Liu Chunai Lu Junnan Hu Qinghong Xie Xiao Wei Cairen Fang Huijiang Liu Chengqian Huang Shixin Pan Xinli Zhan Chong Liu |
| author_sort | Hao Li |
| collection | DOAJ |
| description | IntroductionThe diagnosis and treatment of ankylosing spondylitis (AS) is a difficult task, especially in less developed countries without access to experts. To address this issue, a comprehensive artificial intelligence (AI) tool was created to help diagnose and predict the course of AS.MethodsIn this retrospective study, a dataset of 5389 pelvic radiographs (PXRs) from patients treated at a single medical center between March 2014 and April 2022 was used to create an ensemble deep learning (DL) model for diagnosing AS. The model was then tested on an additional 583 images from three other medical centers, and its performance was evaluated using the area under the receiver operating characteristic curve analysis, accuracy, precision, recall, and F1 scores. Furthermore, clinical prediction models for identifying high-risk patients and triaging patients were developed and validated using clinical data from 356 patients.ResultsThe ensemble DL model demonstrated impressive performance in a multicenter external test set, with precision, recall, and area under the receiver operating characteristic curve values of 0.90, 0.89, and 0.96, respectively. This performance surpassed that of human experts, and the model also significantly improved the experts' diagnostic accuracy. Furthermore, the model's diagnosis results based on smartphone-captured images were comparable to those of human experts. Additionally, a clinical prediction model was established that accurately categorizes patients with AS into high-and low-risk groups with distinct clinical trajectories. This provides a strong foundation for individualized care.DiscussionIn this study, an exceptionally comprehensive AI tool was developed for the diagnosis and management of AS in complex clinical scenarios, especially in underdeveloped or rural areas that lack access to experts. This tool is highly beneficial in providing an efficient and effective system of diagnosis and management. |
| first_indexed | 2024-04-10T16:23:58Z |
| format | Article |
| id | doaj.art-d62d0c35fcd84b1db721d91334499f01 |
| institution | Directory Open Access Journal |
| issn | 2296-2565 |
| language | English |
| last_indexed | 2024-04-10T16:23:58Z |
| publishDate | 2023-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj.art-d62d0c35fcd84b1db721d91334499f012023-02-09T09:16:53ZengFrontiers Media S.A.Frontiers in Public Health2296-25652023-02-011110.3389/fpubh.2023.10636331063633Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human expertsHao Li0Xiang Tao1Tuo Liang2Jie Jiang3Jichong Zhu4Shaofeng Wu5Liyi Chen6Zide Zhang7Chenxing Zhou8Xuhua Sun9Shengsheng Huang10Jiarui Chen11Tianyou Chen12Zhen Ye13Wuhua Chen14Hao Guo15Yuanlin Yao16Shian Liao17Chaojie Yu18Binguang Fan19Yihong Liu20Chunai Lu21Junnan Hu22Qinghong Xie23Xiao Wei24Cairen Fang25Huijiang Liu26Chengqian Huang27Shixin Pan28Xinli Zhan29Chong Liu30The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaGuangxi Medical University, Nanning, Guangxi, ChinaGuangxi Medical University, Nanning, Guangxi, ChinaGuangxi Medical University, Nanning, Guangxi, ChinaGuangxi Medical University, Nanning, Guangxi, ChinaGuangxi Medical University, Nanning, Guangxi, ChinaGuangxi Medical University, Nanning, Guangxi, ChinaOrthopaedics of The First People's Hospital of Nanning, Nanning, Guangxi, ChinaOrthopaedics of People's Hospital of Baise, Baise, Guangxi, ChinaOrthopaedics of Wuzhou Red Cross Hospital, Wuzhou, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaThe First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, ChinaIntroductionThe diagnosis and treatment of ankylosing spondylitis (AS) is a difficult task, especially in less developed countries without access to experts. To address this issue, a comprehensive artificial intelligence (AI) tool was created to help diagnose and predict the course of AS.MethodsIn this retrospective study, a dataset of 5389 pelvic radiographs (PXRs) from patients treated at a single medical center between March 2014 and April 2022 was used to create an ensemble deep learning (DL) model for diagnosing AS. The model was then tested on an additional 583 images from three other medical centers, and its performance was evaluated using the area under the receiver operating characteristic curve analysis, accuracy, precision, recall, and F1 scores. Furthermore, clinical prediction models for identifying high-risk patients and triaging patients were developed and validated using clinical data from 356 patients.ResultsThe ensemble DL model demonstrated impressive performance in a multicenter external test set, with precision, recall, and area under the receiver operating characteristic curve values of 0.90, 0.89, and 0.96, respectively. This performance surpassed that of human experts, and the model also significantly improved the experts' diagnostic accuracy. Furthermore, the model's diagnosis results based on smartphone-captured images were comparable to those of human experts. Additionally, a clinical prediction model was established that accurately categorizes patients with AS into high-and low-risk groups with distinct clinical trajectories. This provides a strong foundation for individualized care.DiscussionIn this study, an exceptionally comprehensive AI tool was developed for the diagnosis and management of AS in complex clinical scenarios, especially in underdeveloped or rural areas that lack access to experts. This tool is highly beneficial in providing an efficient and effective system of diagnosis and management.https://www.frontiersin.org/articles/10.3389/fpubh.2023.1063633/fullartificial intelligencedeep learningmachine learningankylosing spondylitispelvic radiograph |
| spellingShingle | Hao Li Xiang Tao Tuo Liang Jie Jiang Jichong Zhu Shaofeng Wu Liyi Chen Zide Zhang Chenxing Zhou Xuhua Sun Shengsheng Huang Jiarui Chen Tianyou Chen Zhen Ye Wuhua Chen Hao Guo Yuanlin Yao Shian Liao Chaojie Yu Binguang Fan Yihong Liu Chunai Lu Junnan Hu Qinghong Xie Xiao Wei Cairen Fang Huijiang Liu Chengqian Huang Shixin Pan Xinli Zhan Chong Liu Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts Frontiers in Public Health artificial intelligence deep learning machine learning ankylosing spondylitis pelvic radiograph |
| title | Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts |
| title_full | Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts |
| title_fullStr | Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts |
| title_full_unstemmed | Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts |
| title_short | Comprehensive AI-assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts |
| title_sort | comprehensive ai assisted tool for ankylosing spondylitis based on multicenter research outperforms human experts |
| topic | artificial intelligence deep learning machine learning ankylosing spondylitis pelvic radiograph |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2023.1063633/full |
| work_keys_str_mv | AT haoli comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT xiangtao comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT tuoliang comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT jiejiang comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT jichongzhu comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT shaofengwu comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT liyichen comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT zidezhang comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT chenxingzhou comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT xuhuasun comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT shengshenghuang comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT jiaruichen comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT tianyouchen comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT zhenye comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT wuhuachen comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT haoguo comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT yuanlinyao comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT shianliao comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT chaojieyu comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT binguangfan comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT yihongliu comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT chunailu comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT junnanhu comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT qinghongxie comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT xiaowei comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT cairenfang comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT huijiangliu comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT chengqianhuang comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT shixinpan comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT xinlizhan comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts AT chongliu comprehensiveaiassistedtoolforankylosingspondylitisbasedonmulticenterresearchoutperformshumanexperts |