1
|
Lee CY, Chuang YS, Kor CT, Lin YT, Tsao YH, Lin PR, Hsieh HM, Shen MC, Wang YL, Fang TJ, Liu YT. Development of a Predictive Model for Potentially Inappropriate Medications in Older Patients with Cardiovascular Disease. Drugs Aging 2024; 41:675-683. [PMID: 38937426 PMCID: PMC11322215 DOI: 10.1007/s40266-024-01127-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 05/27/2024] [Indexed: 06/29/2024]
Abstract
BACKGROUND Older patients with cardiovascular disease (CVD) are highly susceptible to adverse drug reactions due to age-related physiological changes and the presence of multiple comorbidities, polypharmacy, and potentially inappropriate medications (PIMs). OBJECTIVE This study aimed to develop a predictive model to identify the use of PIMs in older patients with CVD. METHODS Data from 2012 to 2021 from the Changhua Christian Hospital Clinical Research Database (CCHRD) and the Kaohsiung Medical University Hospital Research Database (KMUHRD) were analyzed. Participants over the age of 65 years with CVD diagnoses were included. The CCHRD data were randomly divided into a training set (80% of the database) and an internal validation set (20% of the database), while the KMUHRD data served as an external validation set. The training set was used to construct the prediction models, and both validation sets were used to validate the proposed models. RESULTS A total of 48,569 patients were included. Comprehensive data analysis revealed significant associations between the use of PIMs and clinical factors such as total cholesterol, glycated hemoglobin (HbA1c), creatinine, and uric acid levels, as well as the presence of diabetes, hypertension, and cerebrovascular accidents. The predictive models demonstrated moderate power, indicating the importance of these factors in assessing the risk of PIMs. CONCLUSIONS This study developed predictive models that improve understanding of the use of PIMs in older patients with CVD. These models may assist clinicians in making informed decisions regarding medication safety.
Collapse
Affiliation(s)
- Chun-Ying Lee
- Department of Family Medicine, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan
- Research Center for Precision Environmental Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Yun-Shiuan Chuang
- Department of Family Medicine, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan
- Research Center for Precision Environmental Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
- Center for Big Data Research, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Chew-Teng Kor
- Big Data Center, Changhua Christian Hospital, Changhua, Taiwan
| | - Yi-Ting Lin
- Department of Family Medicine, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan
- Research Center for Precision Environmental Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
- Center for Big Data Research, Kaohsiung Medical University, Kaohsiung, Taiwan
- Faculty of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Yu-Hsiang Tsao
- Department of Public Health, College of Health Sciences, Kaohsiung Medical University, Kaohsiung, Taiwan
- Division of Medical Statistics and Bioinformatics, Department of Medical Research, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan
| | - Pei-Ru Lin
- Big Data Center, Changhua Christian Hospital, Changhua, Taiwan
| | - Hui-Min Hsieh
- Center for Big Data Research, Kaohsiung Medical University, Kaohsiung, Taiwan
- Department of Public Health, College of Health Sciences, Kaohsiung Medical University, Kaohsiung, Taiwan
- Division of Medical Statistics and Bioinformatics, Department of Medical Research, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan
- Department of Medical Research, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan
- Department of Community Medicine, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Mei-Chiou Shen
- Department of Pharmacy, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Ya-Ling Wang
- Department of Pharmacy, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung, Taiwan
| | - Tzu-Jung Fang
- School of Medicine, College of Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan
- Division of Geriatrics and Gerontology, Department of Internal Medicine, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan
| | - Yen-Tze Liu
- Big Data Center, Changhua Christian Hospital, Changhua, Taiwan.
- Department of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung, Taiwan.
- Department of Family Medicine, Changhua Christian Hospital, Changhua, 500, Taiwan.
- Graduate Institute of Clinical Medicine, College of Medicine, National Chung Hsing University, Taichung, Taiwan.
| |
Collapse
|
2
|
Li X, Liu W, Kong W, Zhao W, Wang H, Tian D, Jiao J, Yu Z, Liu S. Prediction of outpatient waiting time: using machine learning in a tertiary children's hospital. Transl Pediatr 2023; 12:2030-2043. [PMID: 38130586 PMCID: PMC10730972 DOI: 10.21037/tp-23-58] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/01/2023] [Accepted: 08/18/2023] [Indexed: 12/23/2023] Open
Abstract
Background Accurately predicting waiting time for patients is crucial for effective hospital management. The present study examined the prediction of outpatient waiting time in a Chinese pediatric hospital through the use of machine learning algorithms. If patients are informed about their waiting time in advance, they can make more informed decisions and better plan their visit on the day of admission. Methods First, a novel classification method for the outpatient clinic in the Chinese pediatric hospital was proposed, which was based on medical knowledge and statistical analysis. Subsequently, four machine learning algorithms [linear regression (LR), random forest (RF), gradient boosting decision tree (GBDT), and K-nearest neighbor (KNN)] were used to construct prediction models of the waiting time of patients in four department categories. Results The three machine learning algorithms outperformed LR in the four department categories. The optimal model for Internal Medicine Department I was the RF model, with a mean absolute error (MAE) of 5.03 minutes, which was 47.60% lower than that of the LR model. The optimal model for the other three categories was the GBDT model. The MAE of the GBDT model was decreased by 28.26%, 35.86%, and 33.10%, respectively compared to that of the LR model. Conclusions Machine learning can predict the outpatient waiting time of pediatric hospitals well and ease patient anxiety when waiting in line without medical appointments. This study offers key insights into enhancing healthcare services and reaffirms the dedication of Chinese pediatric hospitals to providing efficient and patient-centric care.
Collapse
Affiliation(s)
- Xiaoqing Li
- Hainan Branch, Shanghai Children’s Medical Center, School of Medicine, Shanghai Jiao Tong University, Sanya, China
- School of Public Health, Shanghai Jiao Tong University, Shanghai, China
| | - Weiyu Liu
- Center for Biomedical Data Science, Institute of Translational Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Weiming Kong
- Center for Biomedical Data Science, Institute of Translational Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Wenqing Zhao
- Division of Information Department, Shanghai Children’s Medical Center, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Hansong Wang
- Division of Hospital Management, Shanghai Children’s Medical Center, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Dan Tian
- Division of Hospital Management, Shanghai Children’s Medical Center, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Jiali Jiao
- Center for Biomedical Data Science, Institute of Translational Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Zhangsheng Yu
- Center for Biomedical Data Science, Institute of Translational Medicine, Shanghai Jiao Tong University, Shanghai, China
- Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, China
- SJTU-Yale Joint Center for Biostatistics and Data Science, Shanghai Jiao Tong University, Shanghai, China
- Clinical Research Institute, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Shijian Liu
- Hainan Branch, Shanghai Children’s Medical Center, School of Medicine, Shanghai Jiao Tong University, Sanya, China
- School of Public Health, Shanghai Jiao Tong University, Shanghai, China
| |
Collapse
|
3
|
林 工, 滕 飞, 胡 巧, 金 朝, 徐 珽, Haibo Z. [Knowledge Graph-Based Prediction of Potentially Inappropriate Medication]. SICHUAN DA XUE XUE BAO. YI XUE BAN = JOURNAL OF SICHUAN UNIVERSITY. MEDICAL SCIENCE EDITION 2023; 54:884-891. [PMID: 37866942 PMCID: PMC10579076 DOI: 10.12182/20230960108] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Subscribe] [Scholar Register] [Received: 06/05/2023] [Indexed: 10/24/2023]
Abstract
Objective To improve the accuracy of potentially inappropriate medication (PIM) prediction, a PIM prediction model that combines knowledge graph and machine learning was proposed. Methods Firstly, based on Beers criteria 2019 and using the knowledge graph as the basic structure, a PIM knowledge representation framework with logical expression capabilities was constructed, and a PIM inference process was implemented from patient information nodes to PIM nodes. Secondly, a machine learning prediction model for each PIM label was established based on the classifier chain algorithm, to learn the potential feature associations from the data. Finally, based on a threshold of sample size, a portion of reasoning results from the knowledge graph was used as output labels on the classifier chain to enhance the reliability of the prediction results of low-frequency PIMs. Results 11 741 prescriptions from 9 medical institutions in Chengdu were used to evaluate the effectiveness of the model. Experimental results show that the accuracy of the model for PIM quantity prediction is 98.10%, the F1 is 93.66%, the Hamming loss for PIM multi-label prediction is 0.06%, and the macroF1 is 66.09%, which has higher prediction accuracy than the existing models. Conclusion The method proposed has better prediction performance for potentially inappropriate medication and significantly improves the recognition of low-frequency PIM labels.
Collapse
Affiliation(s)
- 工钞 林
- 西南交通大学计算机与人工智能学院 (成都 611756)School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China
| | - 飞 滕
- 西南交通大学计算机与人工智能学院 (成都 611756)School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China
| | - 巧织 胡
- 西南交通大学计算机与人工智能学院 (成都 611756)School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China
| | - 朝辉 金
- 西南交通大学计算机与人工智能学院 (成都 611756)School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China
| | - 珽 徐
- 西南交通大学计算机与人工智能学院 (成都 611756)School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China
| | - Zhang Haibo
- 西南交通大学计算机与人工智能学院 (成都 611756)School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China
| |
Collapse
|