Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluation
Abstract Background Predicting the length of stay in advance will not only benefit the hospitals both clinically and financially but enable healthcare providers to better decision-making for improved quality of care. More importantly, understanding the length of stay of severe patients who require g...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-11-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-024-02755-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846158455929307136 |
|---|---|
| author | Ha Na Cho Imjin Ahn Hansle Gwon Hee Jun Kang Yunha Kim Hyeram Seo Heejung Choi Minkyoung Kim Jiye Han Gaeun Kee Seohyun Park Tae Joon Jun Young-Hak Kim |
| author_facet | Ha Na Cho Imjin Ahn Hansle Gwon Hee Jun Kang Yunha Kim Hyeram Seo Heejung Choi Minkyoung Kim Jiye Han Gaeun Kee Seohyun Park Tae Joon Jun Young-Hak Kim |
| author_sort | Ha Na Cho |
| collection | DOAJ |
| description | Abstract Background Predicting the length of stay in advance will not only benefit the hospitals both clinically and financially but enable healthcare providers to better decision-making for improved quality of care. More importantly, understanding the length of stay of severe patients who require general anesthesia is key to enhancing health outcomes. Objective Here, we aim to discover how machine learning can support resource allocation management and decision-making resulting from the length of stay prediction. Methods A retrospective cohort study was conducted from January 2018 to October 2020. A total cohort of 240,000 patients’ medical records was collected. The data were collected exclusively for preoperative variables to accurately analyze the predictive factors impacting the postoperative length of stay. The main outcome of this study is an analysis of the length of stay (in days) after surgery until discharge. The prediction was performed with ridge regression, random forest, XGBoost, and multi-layer perceptron neural network models. Results The XGBoost resulted in the best performance with an average error within 3 days. Moreover, we explain each feature’s contribution over the XGBoost model and further display distinct predictors affecting the overall prediction outcome at the patient level. The risk factors that most importantly contributed to the stay after surgery were as follows: a direct bilirubin laboratory test, department change, calcium chloride medication, gender, and diagnosis with the removal of other organs. Our results suggest that healthcare providers take into account the risk factors such as the laboratory blood test, distributing patients, and the medication prescribed prior to the surgery. Conclusion We successfully predicted the length of stay after surgery and provide explainable models with supporting analyses. In summary, we demonstrate the interpretation with the XGBoost model presenting insights on preoperative features and defining higher risk predictors to the length of stay outcome. Our development in explainable models supports the current in-depth knowledge for the future length of stay prediction on electronic medical records that aids the decision-making and facilitation of the operation department. |
| format | Article |
| id | doaj-art-72ffbb8457ca404c8c786fa897a15423 |
| institution | Kabale University |
| issn | 1472-6947 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj-art-72ffbb8457ca404c8c786fa897a154232024-11-24T12:29:02ZengBMCBMC Medical Informatics and Decision Making1472-69472024-11-0124111610.1186/s12911-024-02755-1Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluationHa Na Cho0Imjin Ahn1Hansle Gwon2Hee Jun Kang3Yunha Kim4Hyeram Seo5Heejung Choi6Minkyoung Kim7Jiye Han8Gaeun Kee9Seohyun Park10Tae Joon Jun11Young-Hak Kim12Division of Cardiology, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of MedicineDepartment of Medical Science, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of MedicineDepartment of Medical Science, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of MedicineDivision of Cardiology, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of MedicineDepartment of Medical Science, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of MedicineDepartment of Medical Science, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of MedicineDepartment of Medical Science, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of MedicineDepartment of Medical Science, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of MedicineDepartment of Medical Science, Asan Medical Center, Asan Medical Institute of Convergence Science and Technology, University of Ulsan College of MedicineDivision of Cardiology, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of MedicineDivision of Cardiology, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of MedicineBig Data Research Center, Asan Institute for Life Sciences, Asan Medical CenterDivision of Cardiology, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of MedicineAbstract Background Predicting the length of stay in advance will not only benefit the hospitals both clinically and financially but enable healthcare providers to better decision-making for improved quality of care. More importantly, understanding the length of stay of severe patients who require general anesthesia is key to enhancing health outcomes. Objective Here, we aim to discover how machine learning can support resource allocation management and decision-making resulting from the length of stay prediction. Methods A retrospective cohort study was conducted from January 2018 to October 2020. A total cohort of 240,000 patients’ medical records was collected. The data were collected exclusively for preoperative variables to accurately analyze the predictive factors impacting the postoperative length of stay. The main outcome of this study is an analysis of the length of stay (in days) after surgery until discharge. The prediction was performed with ridge regression, random forest, XGBoost, and multi-layer perceptron neural network models. Results The XGBoost resulted in the best performance with an average error within 3 days. Moreover, we explain each feature’s contribution over the XGBoost model and further display distinct predictors affecting the overall prediction outcome at the patient level. The risk factors that most importantly contributed to the stay after surgery were as follows: a direct bilirubin laboratory test, department change, calcium chloride medication, gender, and diagnosis with the removal of other organs. Our results suggest that healthcare providers take into account the risk factors such as the laboratory blood test, distributing patients, and the medication prescribed prior to the surgery. Conclusion We successfully predicted the length of stay after surgery and provide explainable models with supporting analyses. In summary, we demonstrate the interpretation with the XGBoost model presenting insights on preoperative features and defining higher risk predictors to the length of stay outcome. Our development in explainable models supports the current in-depth knowledge for the future length of stay prediction on electronic medical records that aids the decision-making and facilitation of the operation department.https://doi.org/10.1186/s12911-024-02755-1Machine learningHealthcare managementPredictive analysisDecision support system |
| spellingShingle | Ha Na Cho Imjin Ahn Hansle Gwon Hee Jun Kang Yunha Kim Hyeram Seo Heejung Choi Minkyoung Kim Jiye Han Gaeun Kee Seohyun Park Tae Joon Jun Young-Hak Kim Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluation BMC Medical Informatics and Decision Making Machine learning Healthcare management Predictive analysis Decision support system |
| title | Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluation |
| title_full | Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluation |
| title_fullStr | Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluation |
| title_full_unstemmed | Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluation |
| title_short | Explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients: machine learning model development and evaluation |
| title_sort | explainable predictions of a machine learning model to forecast the postoperative length of stay for severe patients machine learning model development and evaluation |
| topic | Machine learning Healthcare management Predictive analysis Decision support system |
| url | https://doi.org/10.1186/s12911-024-02755-1 |
| work_keys_str_mv | AT hanacho explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT imjinahn explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT hanslegwon explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT heejunkang explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT yunhakim explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT hyeramseo explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT heejungchoi explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT minkyoungkim explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT jiyehan explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT gaeunkee explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT seohyunpark explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT taejoonjun explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation AT younghakkim explainablepredictionsofamachinelearningmodeltoforecastthepostoperativelengthofstayforseverepatientsmachinelearningmodeldevelopmentandevaluation |