A warning model for predicting patient admissions to the intensive care unit (ICU) following surgery

Abstract Background Postoperative admission to the ICU for surgical patients is a significant burden in nursing care, and there is currently a lack of corresponding assessment tools. Methods Clinical information of patients was extracted from the VitalDB database. LASSO regression and random forest...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Li, Hongye He, Linjun Xiang, Yongxiang Wang
Format: Article
Language:English
Published: BMC 2025-06-01
Series:Perioperative Medicine
Subjects:
Online Access:https://doi.org/10.1186/s13741-025-00544-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849469851050967040
author Li Li
Hongye He
Linjun Xiang
Yongxiang Wang
author_facet Li Li
Hongye He
Linjun Xiang
Yongxiang Wang
author_sort Li Li
collection DOAJ
description Abstract Background Postoperative admission to the ICU for surgical patients is a significant burden in nursing care, and there is currently a lack of corresponding assessment tools. Methods Clinical information of patients was extracted from the VitalDB database. LASSO regression and random forest algorithms were used to screen clinical variables related to postoperative ICU admission. Subsequently, the effectiveness of logistic regression, random forest, support vector machine, and multi-layer perceptron algorithms was compared using ROC curves. After selecting the best algorithm, postoperative ICU admission probability prediction nomogram was constructed. Results This study identified 18 clinical factors that influence postoperative ICU admission. The factors influencing patient outcomes include three physiological characteristics: age, weight, and gender; five preoperative laboratory tests:platelet count, prothrombin time(%),activated partial thromboplastin time, albumin, and blood urea nitrogen; and seven intraoperative anesthesia details: anesthesia duration, propofol dosing during surgery, midazolam dosing during surgery, phenylephrine dosing during surgery, calcium chloride dosing during surgery, American Society of Anesthesiologists (ASA) classification, and anesthesia method. Additionally, three other factors are considered: whether the surgery is classified as an emergency, the department category, and the type of surgery. The logistic regression model developed using these 18 variables was identified as the most effective predictive model for postoperative ICU admission, achieving an ROC AUC of 0.925. Conclusion The postoperative admission warning model constructed in this study can effectively predict the probability of patients being admitted to the ICU after surgery, providing a corresponding management tool for postoperative care in surgical patients.
format Article
id doaj-art-65dabf47ccd44a2fb8bcfa5c124974cd
institution Kabale University
issn 2047-0525
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series Perioperative Medicine
spelling doaj-art-65dabf47ccd44a2fb8bcfa5c124974cd2025-08-20T03:25:19ZengBMCPerioperative Medicine2047-05252025-06-0114111410.1186/s13741-025-00544-6A warning model for predicting patient admissions to the intensive care unit (ICU) following surgeryLi Li0Hongye He1Linjun Xiang2Yongxiang Wang3Nursing Department, The Third Xiangya Hospital, Central South UniversitySecond Xiangya Hospital, Central South UniversityNursing Department, The Third Xiangya Hospital, Central South UniversitySecond Xiangya Hospital, Central South UniversityAbstract Background Postoperative admission to the ICU for surgical patients is a significant burden in nursing care, and there is currently a lack of corresponding assessment tools. Methods Clinical information of patients was extracted from the VitalDB database. LASSO regression and random forest algorithms were used to screen clinical variables related to postoperative ICU admission. Subsequently, the effectiveness of logistic regression, random forest, support vector machine, and multi-layer perceptron algorithms was compared using ROC curves. After selecting the best algorithm, postoperative ICU admission probability prediction nomogram was constructed. Results This study identified 18 clinical factors that influence postoperative ICU admission. The factors influencing patient outcomes include three physiological characteristics: age, weight, and gender; five preoperative laboratory tests:platelet count, prothrombin time(%),activated partial thromboplastin time, albumin, and blood urea nitrogen; and seven intraoperative anesthesia details: anesthesia duration, propofol dosing during surgery, midazolam dosing during surgery, phenylephrine dosing during surgery, calcium chloride dosing during surgery, American Society of Anesthesiologists (ASA) classification, and anesthesia method. Additionally, three other factors are considered: whether the surgery is classified as an emergency, the department category, and the type of surgery. The logistic regression model developed using these 18 variables was identified as the most effective predictive model for postoperative ICU admission, achieving an ROC AUC of 0.925. Conclusion The postoperative admission warning model constructed in this study can effectively predict the probability of patients being admitted to the ICU after surgery, providing a corresponding management tool for postoperative care in surgical patients.https://doi.org/10.1186/s13741-025-00544-6ICU admissionMachine learningNomogramClinical Decision TreeNursing care
spellingShingle Li Li
Hongye He
Linjun Xiang
Yongxiang Wang
A warning model for predicting patient admissions to the intensive care unit (ICU) following surgery
Perioperative Medicine
ICU admission
Machine learning
Nomogram
Clinical Decision Tree
Nursing care
title A warning model for predicting patient admissions to the intensive care unit (ICU) following surgery
title_full A warning model for predicting patient admissions to the intensive care unit (ICU) following surgery
title_fullStr A warning model for predicting patient admissions to the intensive care unit (ICU) following surgery
title_full_unstemmed A warning model for predicting patient admissions to the intensive care unit (ICU) following surgery
title_short A warning model for predicting patient admissions to the intensive care unit (ICU) following surgery
title_sort warning model for predicting patient admissions to the intensive care unit icu following surgery
topic ICU admission
Machine learning
Nomogram
Clinical Decision Tree
Nursing care
url https://doi.org/10.1186/s13741-025-00544-6
work_keys_str_mv AT lili awarningmodelforpredictingpatientadmissionstotheintensivecareuniticufollowingsurgery
AT hongyehe awarningmodelforpredictingpatientadmissionstotheintensivecareuniticufollowingsurgery
AT linjunxiang awarningmodelforpredictingpatientadmissionstotheintensivecareuniticufollowingsurgery
AT yongxiangwang awarningmodelforpredictingpatientadmissionstotheintensivecareuniticufollowingsurgery
AT lili warningmodelforpredictingpatientadmissionstotheintensivecareuniticufollowingsurgery
AT hongyehe warningmodelforpredictingpatientadmissionstotheintensivecareuniticufollowingsurgery
AT linjunxiang warningmodelforpredictingpatientadmissionstotheintensivecareuniticufollowingsurgery
AT yongxiangwang warningmodelforpredictingpatientadmissionstotheintensivecareuniticufollowingsurgery