Exploring timely and safe discharge from ICU: a comparative study of machine learning predictions and clinical practices
Abstract Background The discharge practices from the intensive care unit exhibit heterogeneity and the recognition of eligible patients for discharge is often delayed. Recognizing the importance of safe discharge, which aims to minimize readmission and mortality, we developed a dynamic machine-learn...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Intensive Care Medicine Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40635-025-00717-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586170734739456 |
|---|---|
| author | Chao Ping Wu Rachel Benish Shirley Alex Milinovich Kaiyin Liu Eduardo Mireles-Cabodevila Hassan Khouli Abhijit Duggal Anirban Bhattacharyya |
| author_facet | Chao Ping Wu Rachel Benish Shirley Alex Milinovich Kaiyin Liu Eduardo Mireles-Cabodevila Hassan Khouli Abhijit Duggal Anirban Bhattacharyya |
| author_sort | Chao Ping Wu |
| collection | DOAJ |
| description | Abstract Background The discharge practices from the intensive care unit exhibit heterogeneity and the recognition of eligible patients for discharge is often delayed. Recognizing the importance of safe discharge, which aims to minimize readmission and mortality, we developed a dynamic machine-learning model. The model aims to accurately identify patients ready for discharge, offering a comparison of its effectiveness with physician decisions in terms of safety and discrepancies in discharge readiness assessment. Methods This retrospective study uses data from patients in the medical ICU from 2015-to-2019 to develop ML models. The models were based on dynamic ICU-readily available features such as hourly vital signs, laboratory results, and interventions and were developed using various ML algorithms. The primary outcome was the hourly prediction of ICU discharge without readmission or death within 72 h post-discharge. These outcomes underwent subsequent validation within a distinct cohort from the year 2020. Additionally, the models’ performance was assessed in comparison to physician judgments, with any discrepancies between the two carefully analyzed. Result In the 2015-to-2019 cohort, the study included 17,852 unique ICU admissions. The LightGBM model outperformed other algorithms, achieving a AUROC of 0.91 (95%CI 0.9–0.91) and performance was held in the 2020 validation cohort (n = 509) with an AUROC of 0.85 (95%CI 0.84–0.85). The calibration result showed Brier score of 0.254 (95%CI 0.253–0.255). The physician agreed with the models’ discharge-readiness prediction in 84.5% of patients. In patients discharged by physicians but not deemed ready by our model, the relative risk of 72-h post-ICU adverse outcomes was 2.32 (95% CI 1.1–4.9). Furthermore, the model predicted patients’ readiness for discharge between 5 (IQR: 2–13.5) and 9 (IQR: 3–17) hours earlier in our selected thresholds. Conclusion The study underscores the potential of ML models in predicting patient discharge readiness, mirroring physician behavior closely while identifying eligible patients earlier. It also highlights ML models can serve as a promising screening tool to enhance ICU discharge, presenting a pathway toward more efficient and reliable critical care decision-making. |
| format | Article |
| id | doaj-art-ff7bfc5ef1404e89a16adb238cd03bf0 |
| institution | Kabale University |
| issn | 2197-425X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Intensive Care Medicine Experimental |
| spelling | doaj-art-ff7bfc5ef1404e89a16adb238cd03bf02025-01-26T12:10:18ZengSpringerOpenIntensive Care Medicine Experimental2197-425X2025-01-0113111010.1186/s40635-025-00717-zExploring timely and safe discharge from ICU: a comparative study of machine learning predictions and clinical practicesChao Ping Wu0Rachel Benish Shirley1Alex Milinovich2Kaiyin Liu3Eduardo Mireles-Cabodevila4Hassan Khouli5Abhijit Duggal6Anirban Bhattacharyya7Cleveland ClinicCleveland ClinicCleveland ClinicCleveland ClinicCleveland ClinicCleveland ClinicCleveland ClinicMayo ClinicAbstract Background The discharge practices from the intensive care unit exhibit heterogeneity and the recognition of eligible patients for discharge is often delayed. Recognizing the importance of safe discharge, which aims to minimize readmission and mortality, we developed a dynamic machine-learning model. The model aims to accurately identify patients ready for discharge, offering a comparison of its effectiveness with physician decisions in terms of safety and discrepancies in discharge readiness assessment. Methods This retrospective study uses data from patients in the medical ICU from 2015-to-2019 to develop ML models. The models were based on dynamic ICU-readily available features such as hourly vital signs, laboratory results, and interventions and were developed using various ML algorithms. The primary outcome was the hourly prediction of ICU discharge without readmission or death within 72 h post-discharge. These outcomes underwent subsequent validation within a distinct cohort from the year 2020. Additionally, the models’ performance was assessed in comparison to physician judgments, with any discrepancies between the two carefully analyzed. Result In the 2015-to-2019 cohort, the study included 17,852 unique ICU admissions. The LightGBM model outperformed other algorithms, achieving a AUROC of 0.91 (95%CI 0.9–0.91) and performance was held in the 2020 validation cohort (n = 509) with an AUROC of 0.85 (95%CI 0.84–0.85). The calibration result showed Brier score of 0.254 (95%CI 0.253–0.255). The physician agreed with the models’ discharge-readiness prediction in 84.5% of patients. In patients discharged by physicians but not deemed ready by our model, the relative risk of 72-h post-ICU adverse outcomes was 2.32 (95% CI 1.1–4.9). Furthermore, the model predicted patients’ readiness for discharge between 5 (IQR: 2–13.5) and 9 (IQR: 3–17) hours earlier in our selected thresholds. Conclusion The study underscores the potential of ML models in predicting patient discharge readiness, mirroring physician behavior closely while identifying eligible patients earlier. It also highlights ML models can serve as a promising screening tool to enhance ICU discharge, presenting a pathway toward more efficient and reliable critical care decision-making.https://doi.org/10.1186/s40635-025-00717-zMachine learningCritical careICU discharge practiceDecision support in ICU discharge |
| spellingShingle | Chao Ping Wu Rachel Benish Shirley Alex Milinovich Kaiyin Liu Eduardo Mireles-Cabodevila Hassan Khouli Abhijit Duggal Anirban Bhattacharyya Exploring timely and safe discharge from ICU: a comparative study of machine learning predictions and clinical practices Intensive Care Medicine Experimental Machine learning Critical care ICU discharge practice Decision support in ICU discharge |
| title | Exploring timely and safe discharge from ICU: a comparative study of machine learning predictions and clinical practices |
| title_full | Exploring timely and safe discharge from ICU: a comparative study of machine learning predictions and clinical practices |
| title_fullStr | Exploring timely and safe discharge from ICU: a comparative study of machine learning predictions and clinical practices |
| title_full_unstemmed | Exploring timely and safe discharge from ICU: a comparative study of machine learning predictions and clinical practices |
| title_short | Exploring timely and safe discharge from ICU: a comparative study of machine learning predictions and clinical practices |
| title_sort | exploring timely and safe discharge from icu a comparative study of machine learning predictions and clinical practices |
| topic | Machine learning Critical care ICU discharge practice Decision support in ICU discharge |
| url | https://doi.org/10.1186/s40635-025-00717-z |
| work_keys_str_mv | AT chaopingwu exploringtimelyandsafedischargefromicuacomparativestudyofmachinelearningpredictionsandclinicalpractices AT rachelbenishshirley exploringtimelyandsafedischargefromicuacomparativestudyofmachinelearningpredictionsandclinicalpractices AT alexmilinovich exploringtimelyandsafedischargefromicuacomparativestudyofmachinelearningpredictionsandclinicalpractices AT kaiyinliu exploringtimelyandsafedischargefromicuacomparativestudyofmachinelearningpredictionsandclinicalpractices AT eduardomirelescabodevila exploringtimelyandsafedischargefromicuacomparativestudyofmachinelearningpredictionsandclinicalpractices AT hassankhouli exploringtimelyandsafedischargefromicuacomparativestudyofmachinelearningpredictionsandclinicalpractices AT abhijitduggal exploringtimelyandsafedischargefromicuacomparativestudyofmachinelearningpredictionsandclinicalpractices AT anirbanbhattacharyya exploringtimelyandsafedischargefromicuacomparativestudyofmachinelearningpredictionsandclinicalpractices |