1
|
Chang CC, Liu TC, Lu CJ, Chiu HC, Lin WN. Explainable machine learning model for identifying key gut microbes and metabolites biomarkers associated with myasthenia gravis. Comput Struct Biotechnol J 2024; 23:1572-1583. [PMID: 38650589 PMCID: PMC11035017 DOI: 10.1016/j.csbj.2024.04.025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2023] [Revised: 03/14/2024] [Accepted: 04/07/2024] [Indexed: 04/25/2024] Open
Abstract
Diagnostic markers for myasthenia gravis (MG) are limited; thus, innovative approaches are required for supportive diagnosis and personalized care. Gut microbes are associated with MG pathogenesis; however, few studies have adopted machine learning (ML) to identify the associations among MG, gut microbiota, and metabolites. In this study, we developed an explainable ML model to predict biomarkers for MG diagnosis. We enrolled 19 MG patients and 10 non-MG individuals. Stool samples were collected and microbiome assessment was performed using 16S rRNA sequencing. Untargeted metabolic profiling was conducted to identify fecal amplicon significant variants (ASVs) and metabolites. We developed an explainable ML model in which the top ASVs and metabolites are combined to identify the best predictive performance. This model uses the SHapley Additive exPlanations method to generate both global and personalized explanations. Fecal microbe-metabolite composition differed significantly between groups. The key bacterial families were Lachnospiraceae and Ruminococcaceae, and the top three features were Lachnospiraceae, inosine, and methylhistidine. An ML model trained with the top 1 % ASVs and top 15 % metabolites combined outperformed all other models. Personalized explanations revealed different patterns of microbe-metabolite contributions in patients with MG. The integration of the microbiota-metabolite features and the development of an explainable ML framework can accurately identify MG and provide personalized explanations, revealing the associations between gut microbiota, metabolites, and MG. An online calculator employing this algorithm was developed that provides a streamlined interface for MG diagnosis screening and conducting personalized evaluations.
Collapse
Affiliation(s)
- Che-Cheng Chang
- PhD Program in Nutrition and Food Science, Fu Jen Catholic University, New Taipei City, Taiwan
- Department of Neurology, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City, Taiwan
- Graduate Institute of Biomedical and Pharmaceutical Science, Fu Jen Catholic University, New Taipei City, Taiwan
| | - Tzu-Chi Liu
- Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City, Taiwan
| | - Chi-Jie Lu
- Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City, Taiwan
- Artificial Intelligence Development Center, Fu Jen Catholic University, New Taipei City, Taiwan
- Department of Information Management, Fu Jen Catholic University, New Taipei City, Taiwan
| | - Hou-Chang Chiu
- School of Medicine, Fu Jen Catholic University, New Taipei City, Taiwan
- Department of Neurology, Taipei Medical University, Shuang-Ho Hospital, New Taipei City, Taiwan
| | - Wei-Ning Lin
- PhD Program in Nutrition and Food Science, Fu Jen Catholic University, New Taipei City, Taiwan
- Graduate Institute of Biomedical and Pharmaceutical Science, Fu Jen Catholic University, New Taipei City, Taiwan
| |
Collapse
|
2
|
Zhou CM, Xue Q, Li H, Yang JJ, Zhu Y. A predictive model for post-thoracoscopic surgery pulmonary complications based on the PBNN algorithm. Sci Rep 2024; 14:7035. [PMID: 38528066 DOI: 10.1038/s41598-024-57700-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Accepted: 03/20/2024] [Indexed: 03/27/2024] Open
Abstract
We constructed an early prediction model for postoperative pulmonary complications after thoracoscopic surgery using machine learning and deep learning algorithms. The artificial intelligence prediction models were built in Python, primarily using artificial intelligencealgorithms including both machine learning and deep learning algorithms. Correlation analysis showed that postoperative pulmonary complications were positively correlated with age and surgery duration, and negatively correlated with serum albumin. Using the light gradient boosting machine(LGBM) algorithm, weighted feature engineering revealed that single lung ventilation duration, history of smoking, surgery duration, ASA score, and blood glucose were the main factors associated with postoperative pulmonary complications. Results of artificial intelligence algorithms for predicting pulmonary complications after thoracoscopy in the test group: In terms of accuracy, the two best algorithms were Logistic Regression (0.831) and light gradient boosting machine(0.827); in terms of precision, the two best algorithms were Gradient Boosting (0.75) and light gradient boosting machine (0.742); in terms of recall, the three best algorithms were gaussian naive bayes (0.581), Logistic Regression (0.532), and pruning Bayesian neural network (0.516); in terms of F1 score, the two best algorithms were LogisticRegression (0.589) and pruning Bayesian neural network (0.566); and in terms of Area Under Curve(AUC), the two best algorithms were light gradient boosting machine(0.873) and pruning Bayesian neural network (0.869). The results of this study suggest that pruning Bayesian neural network (PBNN) can be used to assess the possibility of pulmonary complications after thoracoscopy, and to identify high-risk groups prior to surgery.
Collapse
Affiliation(s)
- Cheng-Mao Zhou
- Big Data and Artificial Intelligence Research Group, Department of Anaesthesiology, Central People's Hospital of Zhanjiang, Zhanjiang, Guangdong, China.
- Big Data and Artificial Intelligence Research Group, Department of Anesthesiology, Pain and Perioperative Medicine, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
| | - Qiong Xue
- Big Data and Artificial Intelligence Research Group, Department of Anesthesiology, Pain and Perioperative Medicine, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - HuiJuan Li
- Big Data and Artificial Intelligence Research Group, Department of Anesthesiology, Pain and Perioperative Medicine, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Jian-Jun Yang
- Big Data and Artificial Intelligence Research Group, Department of Anesthesiology, Pain and Perioperative Medicine, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
| | - Yu Zhu
- Big Data and Artificial Intelligence Research Group, Department of Anaesthesiology, Central People's Hospital of Zhanjiang, Zhanjiang, Guangdong, China.
- Big Data and Artificial Intelligence Research Group, Department of Anesthesiology, Pain and Perioperative Medicine, First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China.
| |
Collapse
|
3
|
Tan M, Xiao Y, Jing F, Xie Y, Lu S, Xiang M, Ren H. Evaluating machine learning-enabled and multimodal data-driven exercise prescriptions for mental health: a randomized controlled trial protocol. Front Psychiatry 2024; 15:1352420. [PMID: 38287940 PMCID: PMC10822920 DOI: 10.3389/fpsyt.2024.1352420] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 01/02/2024] [Indexed: 01/31/2024] Open
Abstract
Background Mental illnesses represent a significant global health challenge, affecting millions with far-reaching social and economic impacts. Traditional exercise prescriptions for mental health often adopt a one-size-fits-all approach, which overlooks individual variations in mental and physical health. Recent advancements in artificial intelligence (AI) offer an opportunity to tailor these interventions more effectively. Objective This study aims to develop and evaluate a multimodal data-driven AI system for personalized exercise prescriptions, targeting individuals with mental illnesses. By leveraging AI, the study seeks to overcome the limitations of conventional exercise regimens and improve adherence and mental health outcomes. Methods The study is conducted in two phases. Initially, 1,000 participants will be recruited for AI model training and testing, with 800 forming the training set, augmented by 9,200 simulated samples generated by ChatGPT, and 200 as the testing set. Data annotation will be performed by experienced physicians from the Department of Mental Health at Guangdong Second Provincial General Hospital. Subsequently, a randomized controlled trial (RCT) with 40 participants will be conducted to compare the AI-driven exercise prescriptions against standard care. Assessments will be scheduled at 6, 12, and 18 months to evaluate cognitive, physical, and psychological outcomes. Expected outcomes The AI-driven system is expected to demonstrate greater effectiveness in improving mental health outcomes compared to standard exercise prescriptions. Personalized exercise regimens, informed by comprehensive data analysis, are anticipated to enhance participant adherence and overall mental well-being. These outcomes could signify a paradigm shift in exercise prescription for mental health, paving the way for more personalized and effective treatment modalities. Registration and ethical approval This is approved by Human Experimental Ethics Inspection of Guangzhou Sport University, and the registration is under review by ChiCTR.
Collapse
Affiliation(s)
| | - Yanning Xiao
- China Swimming College, Beijing Sport University, Beijing, China
- China’s National Artistic Swimming Team, Beijing, China
- Institute of Physical Education, Sichuan University, Chengdu, China
| | - Fengshi Jing
- Faculty of Data Science, City University of Macau, Taipa, Macao SAR, China
- Project-China, School of Medicine, The University of North Carolina, Chapel Hill, NC, United States
- College of Business, City University of Hong Kong, Hong Kong, Hong Kong SAR, China
| | - Yewei Xie
- Programme in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
| | - Sanmei Lu
- South China Agricultural University, Guangzhou, China
| | | | - Hao Ren
- Institute for Healthcare Artificial Intelligence Application, Guangdong Second Provincial General Hospital, Guangzhou, China
| |
Collapse
|
4
|
Gao T, Ren H, He S, Liang D, Xu Y, Chen K, Wang Y, Zhu Y, Dong H, Xu Z, Chen W, Cheng W, Jing F, Tao X. Development of an interpretable machine learning-based intelligent system of exercise prescription for cardio-oncology preventive care: A study protocol. Front Cardiovasc Med 2023; 9:1091885. [PMID: 38106819 PMCID: PMC10722170 DOI: 10.3389/fcvm.2022.1091885] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Accepted: 12/12/2022] [Indexed: 12/19/2023] Open
Abstract
Background Cardiovascular disease (CVD) and cancer are the first and second causes of death in over 130 countries across the world. They are also among the top three causes in almost 180 countries worldwide. Cardiovascular complications are often noticed in cancer patients, with nearly 20% exhibiting cardiovascular comorbidities. Physical exercise may be helpful for cancer survivors and people living with cancer (PLWC), as it prevents relapses, CVD, and cardiotoxicity. Therefore, it is beneficial to recommend exercise as part of cardio-oncology preventive care. Objective With the progress of deep learning algorithms and the improvement of big data processing techniques, artificial intelligence (AI) has gradually become popular in the fields of medicine and healthcare. In the context of the shortage of medical resources in China, it is of great significance to adopt AI and machine learning methods for prescription recommendations. This study aims to develop an interpretable machine learning-based intelligent system of exercise prescription for cardio-oncology preventive care, and this paper presents the study protocol. Methods This will be a retrospective machine learning modeling cohort study with interventional methods (i.e., exercise prescription). We will recruit PLWC participants at baseline (from 1 January 2025 to 31 December 2026) and follow up over several years (from 1 January 2027 to 31 December 2028). Specifically, participants will be eligible if they are (1) PLWC in Stage I or cancer survivors from Stage I; (2) aged between 18 and 55 years; (3) interested in physical exercise for rehabilitation; (4) willing to wear smart sensors/watches; (5) assessed by doctors as suitable for exercise interventions. At baseline, clinical exercise physiologist certificated by the joint training program (from 1 January 2023 to 31 December 2024) of American College of Sports Medicine and Chinese Association of Sports Medicine will recommend exercise prescription to each participant. During the follow-up, effective exercise prescription will be determined by assessing the CVD status of the participants. Expected outcomes This study aims to develop not only an interpretable machine learning model to recommend exercise prescription but also an intelligent system of exercise prescription for precision cardio-oncology preventive care. Ethics This study is approved by Human Experimental Ethics Inspection of Guangzhou Sport University. Clinical trial registration http://www.chictr.org.cn, identifier ChiCTR2300077887.
Collapse
Affiliation(s)
- Tianyu Gao
- School of Physical Education, Jinan University, Guangzhou, China
| | - Hao Ren
- Institute for Healthcare Artificial Intelligence Application, Guangdong Second Provincial General Hospital, Guangzhou, China
- Faculty of Data Science, City University of Macau, Macao, Macao SAR, China
| | - Shan He
- Guangzhou Sport University, Guangzhou, China
| | - Deyi Liang
- Guangdong Women and Children Hospital, Guangzhou, China
| | - Yuming Xu
- Division of Physical Education, Guangdong University of Finance and Economics, Guangzhou, China
- School of Education, City University of Macau, Macao, Macao SAR, China
| | - Kecheng Chen
- School of Data Science, City University of Hong Kong, Hong Kong, Hong Kong SAR, China
| | - Yufan Wang
- Department of Industrial Engineering and Management, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - Yuxin Zhu
- Syns Institute of Educational Research, Hong Kong, Hong Kong SAR, China
| | - Heling Dong
- School of Physical Education, Jinan University, Guangzhou, China
| | - Zhongzhi Xu
- School of Public Health, Sun Yat-Sen University, Guangzhou, China
| | - Weiming Chen
- Department of Health Medicine, Guangdong Second Provincial General Hospital, Guangzhou, China
| | - Weibin Cheng
- Institute for Healthcare Artificial Intelligence Application, Guangdong Second Provincial General Hospital, Guangzhou, China
- School of Data Science, City University of Hong Kong, Hong Kong, Hong Kong SAR, China
| | - Fengshi Jing
- Institute for Healthcare Artificial Intelligence Application, Guangdong Second Provincial General Hospital, Guangzhou, China
- Faculty of Data Science, City University of Macau, Macao, Macao SAR, China
- UNC Project-China, UNC Global, School of Medicine, The University of North Carolina, Chapel Hill, NC, United States
| | - Xiaoyu Tao
- Zhuhai College of Science and Technology, Zhuhai, China
- ZCST Health and Medicine Industry Research Institute, Zhuhai, China
| |
Collapse
|