Application of Predictive Modelling to Improve the Discharge Process in Hospitals
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: To find out the factors influencing discharge process turnaround time (TAT) and to accurately predict the dischargeprocess TAT. Methods: The discharge process of cardiology department inpatients in a tertiary care hospital wasmapped over a month. The likely factors influencing discharge TAT were tested for significance by ANOVA. Multiple linearregression (MLR) was used to predict the TAT. The sample was divided into testing and training sets for regression. A modelwas generated using the training set and compared with the testing set for accuracy. Results: After a process map was plotted,the significant factors influencing the TAT were identified to be the treating doctor, and pending evaluations on the dayof discharge. The MLR model was developed with Python libraries based on the two factors identified. The model predictedthe discharge TAT with a 69% R2 value and 32.4 minutes (standard error) on the testing set and a 77.3% R2 value and 26.7minutes (standard error) on the overall sample. Conclusions: This study was an initiation to find out factors influencing dischargeTAT and how those factors can be used to predict discharge in the hospital of interest. The study was validated andpredicted the TAT with 77% accuracy after the significant factors that affect the discharge process were identified.
Abstract
Objectives: To find out the factors influencing discharge process turnaround time (TAT) and to accurately predict the dischargeprocess TAT. Methods: The discharge process of cardiology department inpatients in a tertiary care hospital wasmapped over a month. The likely factors influencing discharge TAT were tested for significance by ANOVA. Multiple linearregression (MLR) was used to predict the TAT. The sample was divided into testing and training sets for regression. A modelwas generated using the training set and compared with the testing set for accuracy. Results: After a process map was plotted,the significant factors influencing the TAT were identified to be the treating doctor, and pending evaluations on the dayof discharge. The MLR model was developed with Python libraries based on the two factors identified. The model predictedthe discharge TAT with a 69% R2 value and 32.4 minutes (standard error) on the testing set and a 77.3% R2 value and 26.7minutes (standard error) on the overall sample. Conclusions: This study was an initiation to find out factors influencing dischargeTAT and how those factors can be used to predict discharge in the hospital of interest. The study was validated andpredicted the TAT with 77% accuracy after the significant factors that affect the discharge process were identified.
참고문헌 (21)
- Kaur H, "A study on discharge process of discharged patients of a multispecialty hospital Ludhiana", Int J Eng Manag Res, 7(3), pp.688~694 (2017)
- Maloney CG, "A tool for improving patient discharge process and hospital communication practices : the"Patient Tracker"", AMIA Annu Symp Proc, 2007, pp.493~497 (2007)
- Kripalani S, "Promoting effective transitions of care at hospital discharge : a review of key issues for hospitalists", J Hosp Med, 2(5), pp.314~323 (2007)
- Falvo T, "The opportunity loss of boarding admitted patients in the emergency department", Acad Emerg Med, 14(4), pp.332~337 (2007)
- Shukla K, "Predictive modelling for turn around time(TAT)of discharge process for insured patients in a corporate hospital of Pune city", J Health Manag, 20(1), pp.56~63 (2018)
- Dalal AK, "Lessons learned from implementation of a computerized application for pending tests at hospital discharge", J Hosp Med, 6(1), pp.16~21 (2011)
- "Statistical analysis of discharge data" (2019)[URL]
- McKinney W., "Python for data analysis: data wrangling with Pandas, NumPy, and IPython" (2012), O'Reilly Media
- Combes C, "Predicting hospital length of stay using regression models: Application to emergency department", Proceedings of the 10th International Conference on Modeling, Optimization &Simulation (MOSIM) (2014)
- Sullivan B, "An evaluation of physician predictions of discharge on a general medicine service", J Hosp Med, 10(12), pp.808~810 (2015)
- De Grood A, "A review of discharge-prediction processes in acute care hospitals", Healthc Policy, 12(2), pp.105~115 (2016)
- Pandis N, "Multiple linear regression analysis", Am J Orthod Dentofacial Orthop, 149(4), pp.581~ (2016)
- Thorpe KE, "The use of regression analysis to determine hospital payment : the case of Medicare's indirect teaching adjustment", Inquiry, 25(2), pp.219~231 (1988)
- "Residual analysis in regression" (2020)[URL]
- Smith PF, "A comparison of random forest regression and multiple linear regression for prediction in neuroscience", J Neurosci Methods, 220(1), pp.85~91 (2013)
- Edelman ER, "Improving the prediction of total surgical procedure time using linear regression modeling", Front Med(Lausanne), 4, pp.85~ (2017)
- Bouphan P, "Factors affecting the research for solving health problem of health personnel at subdistrict health promoting hospitals", Procedia Soc Behav Sci, 237, pp.1097~1104 (2017)
- Freburger JK, "Analysis of the relationship between the utilization of physical therapy services and outcomes for patients with acute stroke", Phys Ther, 79(10), pp.906~918 (1999)
- Stephen O, "An efficient deep learning approach to pneumonia classification in healthcare", J Healthc Eng, 2019, pp.4180949~ (2019)
- Kaymak S, "Classification of diseases on chest X-rays using deep learning", 13th International Conference on Theory and Applications of Fuzzy Systems and Soft Computing, pp.516~523 (2018), Springer
- Davenport T, "The potential for artificial intelligence in healthcare", Future Healthc J, 6(2), pp.94~98 (2019)