1
|
Liu CL, Lee MH, Hsueh SN, Chung CC, Lin CJ, Chang PH, Luo AC, Weng HC, Lee YH, Dai MJ, Tsai MJ. A bagging approach for improved predictive accuracy of intradialytic hypotension during hemodialysis treatment. Comput Biol Med 2024; 172:108244. [PMID: 38457931 DOI: 10.1016/j.compbiomed.2024.108244] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Revised: 02/24/2024] [Accepted: 03/04/2024] [Indexed: 03/10/2024]
Abstract
The primary objective of this study is to enhance the prediction accuracy of intradialytic hypotension in patients undergoing hemodialysis. A significant challenge in this context arises from the nature of the data derived from the monitoring devices and exhibits an extreme class imbalance problem. Traditional predictive models often display a bias towards the majority class, compromising the accuracy of minority class predictions. Therefore, we introduce a method called UnderXGBoost. This novel methodology combines the under-sampling, bagging, and XGBoost techniques to balance the dataset and improve predictive accuracy for the minority class. This method is characterized by its straightforward implementation and training efficiency. Empirical validation in a real-world dataset confirms the superior performance of UnderXGBoost compared to existing models in predicting intradialytic hypotension. Furthermore, our approach demonstrates versatility, allowing XGBoost to be substituted with other classifiers and still producing promising results. Sensitivity analysis was performed to assess the model's robustness, reinforce its reliability, and indicate its applicability to a broader range of medical scenarios facing similar challenges of data imbalance. Our model aims to enable medical professionals to provide preemptive treatments more effectively, thereby improving patient care and prognosis. This study contributes a novel and effective solution to a critical issue in medical prediction, thus broadening the application spectrum of predictive modeling in the healthcare domain.
Collapse
Affiliation(s)
- Chien-Liang Liu
- Department of Industrial Engineering and Management, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd. East Dist., Hsinchu, 30010, Taiwan, ROC.
| | - Min-Hsuan Lee
- Department of Industrial Engineering and Management, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd. East Dist., Hsinchu, 30010, Taiwan, ROC
| | - Shan-Ni Hsueh
- Department of Industrial Engineering and Management, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd. East Dist., Hsinchu, 30010, Taiwan, ROC
| | - Chia-Chen Chung
- Department of Industrial Engineering and Management, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd. East Dist., Hsinchu, 30010, Taiwan, ROC
| | - Chun-Ju Lin
- Industrial Technology Research Institute, 195, Sec. 4, Chung Hsing Rd., Chutung, Hsinchu County, 310401, Taiwan, ROC
| | - Po-Han Chang
- Industrial Technology Research Institute, 195, Sec. 4, Chung Hsing Rd., Chutung, Hsinchu County, 310401, Taiwan, ROC
| | - An-Chun Luo
- Industrial Technology Research Institute, 195, Sec. 4, Chung Hsing Rd., Chutung, Hsinchu County, 310401, Taiwan, ROC
| | - Hsuan-Chi Weng
- Industrial Technology Research Institute, 195, Sec. 4, Chung Hsing Rd., Chutung, Hsinchu County, 310401, Taiwan, ROC
| | - Yu-Hsien Lee
- Industrial Technology Research Institute, 195, Sec. 4, Chung Hsing Rd., Chutung, Hsinchu County, 310401, Taiwan, ROC
| | - Ming-Ji Dai
- Industrial Technology Research Institute, 195, Sec. 4, Chung Hsing Rd., Chutung, Hsinchu County, 310401, Taiwan, ROC
| | - Min-Juei Tsai
- Department of Nephrology, Chang-Hua Hospital, Ministry of Health and Welfare, Changhua, No. 80, Sec. 2, Zhongzheng Rd., Puxin Township, Changhua County, 513007, Taiwan, ROC.
| |
Collapse
|
2
|
Abstract
Coronary artery bypass graft (CABG) operations consume more health care resources than any other single procedure. The objective of this study was to develop a computer simulation model that can be used to predict costs and patient outcomes of CABG surgery. The analysis is based on a systems dynamic model developed using STELLA software. Two sets of data from Medicare patients who underwent CABG operations at Methodist Hospital of Indiana were used to construct and validate the model. The model predictions of length of hospital stay, use of specialists in caring for patients, costs and postoperative functional status are reasonably close to actual data on patients who underwent CABG surgery. The analysis indicates the most important factors affecting costs and outcomes are gender, age, whether or not the surgery is a reoperation and whether the patient experiences postoperative complications. The model can be used to predict costs and outcomes for a patient population from a small set of preoperative characteristics (i.e., age, gender, DRG, whether the surgery is a reoperation, and the patient's operative status). A second potential use of the model is to answer clinical questions such as do the costs and risks of CABG operations outweigh the benefits for patients with certain risk factors.
Collapse
Affiliation(s)
- James G Anderson
- Department of Sociology and Anthropology, Purdue University, West Lafayette, IN 47907, USA.
| | | | | | | | | |
Collapse
|
3
|
Abstract
Few clinicians in the United States use computers during patient encounters and many still worry that computers will depersonalize their interactions with patients. This case study describes patient and clinician reactions to a computer-based health appraisal system. Findings showed no difference in any aspect of patient satisfaction between computer and non-computer groups. Use of a computer in the consulting room neither depersonalized nor enhanced patient satisfaction. Clinicians (in this case, nurse practitioners and physician assistants) were willing to use the system, which they perceived as having benefits for patient care, but were concerned about the increased time required for exams, effort required to learn the system while still interacting appropriately with the patient, increased monitoring of their performance, and other organizational issues. Clinicians who used the system showed a higher tolerance for uncertainty and communicated more frequently with each other and with others throughout the department. Implementation was slowed by the need to demonstrate the monetary value of the system.
Collapse
Affiliation(s)
- C E Aydin
- Cedars-Sinai Medical Center, Burns & Allen Research Institute, Los Angeles, CA 90048, USA.
| | | | | | | | | |
Collapse
|