Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imagingResearch in context
Summary: Background: Identifying individuals at risk for severe mental illness (SMI) is crucial for prevention and early intervention strategies. While MRI shows potential for case identification even before illness onset, no practical model for mental health risk monitoring has been developed. Thi...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-04-01
|
| Series: | EBioMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352396423001068 |
| _version_ | 1797857715024822272 |
|---|---|
| author | Wenjing Zhang Chengmin Yang Zehong Cao Zhe Li Lihua Zhuo Youguo Tan Yichu He Li Yao Qing Zhou Qiyong Gong John A. Sweeney Feng Shi Su Lui |
| author_facet | Wenjing Zhang Chengmin Yang Zehong Cao Zhe Li Lihua Zhuo Youguo Tan Yichu He Li Yao Qing Zhou Qiyong Gong John A. Sweeney Feng Shi Su Lui |
| author_sort | Wenjing Zhang |
| collection | DOAJ |
| description | Summary: Background: Identifying individuals at risk for severe mental illness (SMI) is crucial for prevention and early intervention strategies. While MRI shows potential for case identification even before illness onset, no practical model for mental health risk monitoring has been developed. This study aims to develop an initial version of an efficient and practical model for mental health screening among at-risk populations. Methods: A deep learning model known as Multiple Instance Learning (MIL) was adopted to train and test a SMI detection model with clinical MRI scans of 14,915 patients with SMI (age 32.98 ± 12.01 years, 9102 women) and 4538 healthy controls (age 40.60 ± 10.95 years, 2424 women) in the primary dataset. Validation analysis was conducted in an independent dataset with 290 patients (age 28.08 ± 10.95 years, 169 women) and 310 healthy participants (age 33.55 ± 11.09 years, 165 women). Another three machine learning models of ResNet, DenseNet and EfficientNet were used for comparison. We also recruited 148 individuals receiving high-stress medical school education to characterize the potential real-world utility of the MIL model in detecting risk of mental illness. Findings: Similar performance of successful differentiation of individuals with SMI and healthy controls was observed for the MIL model (AUC: 0.82) and other models (ResNet, DenseNet, EfficientNet, 0.83, 0.81, and 0.80 respectively). MIL had better generalization in the validation test than other models (AUC: 0.82 vs 0.59, 0.66 and 0.59), and less drop-off in performance from 3.0T to 1.5T scanners. The MIL model did better in predicting clinician ratings of distress than self-ratings with questionnaires (84% vs 22%) in the medical student sample. Brain regions that contributed to SMI identification were mainly neocortical, including right precuneus, bilateral temporal regions, left precentral/postcentral gyrus, bilateral medial prefrontal cortex and right cerebellum. Interpretation: Our digital model based on brief clinical MRI protocols identified individual SMI patients with good accuracy and high sensitivity, suggesting that with incremental improvements the approach may offer potentially useful aid for early identification and intervention to prevent illness onset in vulnerable at-risk populations. Funding: This study was supported by the National Natural Science Foundation of China, National Key Technologies R&D Program of China, and Sichuan Science and Technology Program. |
| first_indexed | 2024-04-09T21:01:16Z |
| format | Article |
| id | doaj.art-d844de40f280413d9d4bd315ff36332a |
| institution | Directory Open Access Journal |
| issn | 2352-3964 |
| language | English |
| last_indexed | 2024-04-09T21:01:16Z |
| publishDate | 2023-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EBioMedicine |
| spelling | doaj.art-d844de40f280413d9d4bd315ff36332a2023-03-29T09:27:20ZengElsevierEBioMedicine2352-39642023-04-0190104541Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imagingResearch in contextWenjing Zhang0Chengmin Yang1Zehong Cao2Zhe Li3Lihua Zhuo4Youguo Tan5Yichu He6Li Yao7Qing Zhou8Qiyong Gong9John A. Sweeney10Feng Shi11Su Lui12Huaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, Department of Radiology, West China Hospital of Sichuan University, Chengdu, ChinaHuaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, Department of Radiology, West China Hospital of Sichuan University, Chengdu, ChinaDepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaMental Health Center and Psychiatric Laboratory, The State Key Laboratory of Biotherapy, West China Hospital of Sichuan University, Chengdu, ChinaDepartment of Radiology, The Third Hospital of Mianyang/Sichuan Mental Health Center, Mianyang, ChinaDepartment of Psychiatry, Zigong Fifth People's Hospital, Zigong, ChinaDepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaHuaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, Department of Radiology, West China Hospital of Sichuan University, Chengdu, ChinaDepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaHuaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, Department of Radiology, West China Hospital of Sichuan University, Chengdu, ChinaHuaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, Department of Radiology, West China Hospital of Sichuan University, Chengdu, China; Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, OH, USADepartment of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China; Corresponding author. No. 701 Yunjin Road, Xuhui District, Shanghai 200232, China.Huaxi MR Research Center (HMRRC), Functional and Molecular Imaging Key Laboratory of Sichuan Province, Department of Radiology, West China Hospital of Sichuan University, Chengdu, China; Corresponding author. No. 37 Guoxue Xiang, Chengdu 610041, China.Summary: Background: Identifying individuals at risk for severe mental illness (SMI) is crucial for prevention and early intervention strategies. While MRI shows potential for case identification even before illness onset, no practical model for mental health risk monitoring has been developed. This study aims to develop an initial version of an efficient and practical model for mental health screening among at-risk populations. Methods: A deep learning model known as Multiple Instance Learning (MIL) was adopted to train and test a SMI detection model with clinical MRI scans of 14,915 patients with SMI (age 32.98 ± 12.01 years, 9102 women) and 4538 healthy controls (age 40.60 ± 10.95 years, 2424 women) in the primary dataset. Validation analysis was conducted in an independent dataset with 290 patients (age 28.08 ± 10.95 years, 169 women) and 310 healthy participants (age 33.55 ± 11.09 years, 165 women). Another three machine learning models of ResNet, DenseNet and EfficientNet were used for comparison. We also recruited 148 individuals receiving high-stress medical school education to characterize the potential real-world utility of the MIL model in detecting risk of mental illness. Findings: Similar performance of successful differentiation of individuals with SMI and healthy controls was observed for the MIL model (AUC: 0.82) and other models (ResNet, DenseNet, EfficientNet, 0.83, 0.81, and 0.80 respectively). MIL had better generalization in the validation test than other models (AUC: 0.82 vs 0.59, 0.66 and 0.59), and less drop-off in performance from 3.0T to 1.5T scanners. The MIL model did better in predicting clinician ratings of distress than self-ratings with questionnaires (84% vs 22%) in the medical student sample. Brain regions that contributed to SMI identification were mainly neocortical, including right precuneus, bilateral temporal regions, left precentral/postcentral gyrus, bilateral medial prefrontal cortex and right cerebellum. Interpretation: Our digital model based on brief clinical MRI protocols identified individual SMI patients with good accuracy and high sensitivity, suggesting that with incremental improvements the approach may offer potentially useful aid for early identification and intervention to prevent illness onset in vulnerable at-risk populations. Funding: This study was supported by the National Natural Science Foundation of China, National Key Technologies R&D Program of China, and Sichuan Science and Technology Program.http://www.sciencedirect.com/science/article/pii/S2352396423001068Severe mental illnessNeuroimagingIndividual diagnosisMultiple instance learningScreening |
| spellingShingle | Wenjing Zhang Chengmin Yang Zehong Cao Zhe Li Lihua Zhuo Youguo Tan Yichu He Li Yao Qing Zhou Qiyong Gong John A. Sweeney Feng Shi Su Lui Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imagingResearch in context EBioMedicine Severe mental illness Neuroimaging Individual diagnosis Multiple instance learning Screening |
| title | Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imagingResearch in context |
| title_full | Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imagingResearch in context |
| title_fullStr | Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imagingResearch in context |
| title_full_unstemmed | Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imagingResearch in context |
| title_short | Detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imagingResearch in context |
| title_sort | detecting individuals with severe mental illness using artificial intelligence applied to magnetic resonance imagingresearch in context |
| topic | Severe mental illness Neuroimaging Individual diagnosis Multiple instance learning Screening |
| url | http://www.sciencedirect.com/science/article/pii/S2352396423001068 |
| work_keys_str_mv | AT wenjingzhang detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT chengminyang detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT zehongcao detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT zheli detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT lihuazhuo detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT youguotan detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT yichuhe detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT liyao detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT qingzhou detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT qiyonggong detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT johnasweeney detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT fengshi detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext AT sului detectingindividualswithseverementalillnessusingartificialintelligenceappliedtomagneticresonanceimagingresearchincontext |