Employing a low-code machine learning approach to predict in-hospital mortality and length of stay in patients with community-acquired pneumonia
Abstract Community-acquired pneumonia (CAP) is associated with high mortality rates and often results in prolonged hospital stays. The potential of machine learning to enhance prediction accuracy in this context is significant, yet clinicians often lack the programming skills required for effective...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-82615-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559744025722880 |
|---|---|
| author | Hao Chen Shurui Zhang Hiromi Matsumoto Nanami Tsuchiya Chihiro Yamada Shunsuke Okasaki Atsushi Miyasaka Kentaro Yumoto Daiki Kanou Fumihiro Kashizaki Harumi Koizumi Kenichi Takahashi Masato Shimizu Nobuyuki Horita Takeshi Kaneko |
| author_facet | Hao Chen Shurui Zhang Hiromi Matsumoto Nanami Tsuchiya Chihiro Yamada Shunsuke Okasaki Atsushi Miyasaka Kentaro Yumoto Daiki Kanou Fumihiro Kashizaki Harumi Koizumi Kenichi Takahashi Masato Shimizu Nobuyuki Horita Takeshi Kaneko |
| author_sort | Hao Chen |
| collection | DOAJ |
| description | Abstract Community-acquired pneumonia (CAP) is associated with high mortality rates and often results in prolonged hospital stays. The potential of machine learning to enhance prediction accuracy in this context is significant, yet clinicians often lack the programming skills required for effective data mining. This study aimed to assess the effectiveness of a low-code approach for assisting clinicians with data mining for mortality and length of stay (LOS) prediction in patients with CAP. A retrospective study was conducted using a low-code platform and the PyCaret library in Google Colab on data from patients with community-acquired pneumonia (CAP) admitted between January 2013 and December 2021 to two medical facilities. Model performance was assessed using the area under the receiver operating characteristic curve (AUC) for mortality prediction and the R2 score for LOS prediction, with benchmarks set at AUC > 0.9 and R2 > 0.5. The Shapley Additive Explanations (SHAP) method was used for interpreting individual predictions. A total of 669 CAP patients were enrolled in the analysis.Fifteen models were evaluated for mortality prediction, and nineteen models were evaluated for LOS prediction utilizing the PyCaret library. The Light Gradient Boosting Machine model yielded the highest AUC (0.963) for mortality prediction. In predicting LOS, the Extratrees Regressor model achieved the highest R2 score of 0.585. Factors such as the severity of pneumonia and the Charlson Comorbidity Index (CCI) were significant factors influencing mortality. For the LOS, the CCI score, activities of daily living, and social support were significant predictors. The low-code approach enables medical professionals with limited technical expertise to effectively employ data science in their clinical decision-making process. This approach proved to be a valuable tool in the analysis of CAP patient data. |
| format | Article |
| id | doaj-art-75c5bbbddb3e43aeae2b9624d39de4bd |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-75c5bbbddb3e43aeae2b9624d39de4bd2025-01-05T12:15:28ZengNature PortfolioScientific Reports2045-23222025-01-0115111010.1038/s41598-024-82615-0Employing a low-code machine learning approach to predict in-hospital mortality and length of stay in patients with community-acquired pneumoniaHao Chen0Shurui Zhang1Hiromi Matsumoto2Nanami Tsuchiya3Chihiro Yamada4Shunsuke Okasaki5Atsushi Miyasaka6Kentaro Yumoto7Daiki Kanou8Fumihiro Kashizaki9Harumi Koizumi10Kenichi Takahashi11Masato Shimizu12Nobuyuki Horita13Takeshi Kaneko14Chemotherapy Center, Yokohama Minami Kyosai HospitalScientific Research Department, Msunhealth.Co., LTDDepartment of Pulmonology, Yokohama City UniversityDepartment of Respiratory, Yokohama Minami Kyosai HospitalDepartment of Respiratory, Yokohama Minami Kyosai HospitalDepartment of Respiratory, Yokohama Minami Kyosai HospitalDepartment of Respiratory, Yokohama Minami Kyosai HospitalDepartment of Respiratory, Yokohama Minami Kyosai HospitalDepartment of Respiratory, Yokohama Minami Kyosai HospitalDepartment of Respiratory, Yokohama Minami Kyosai HospitalDepartment of Respiratory, Yokohama Minami Kyosai HospitalDepartment of Respiratory, Yokohama Minami Kyosai HospitalDepartment of Cardiology, Yokohama Minami Kyosai HospitalChemotherapy Center, Yokohama City University HospitalDepartment of Pulmonology, Yokohama City UniversityAbstract Community-acquired pneumonia (CAP) is associated with high mortality rates and often results in prolonged hospital stays. The potential of machine learning to enhance prediction accuracy in this context is significant, yet clinicians often lack the programming skills required for effective data mining. This study aimed to assess the effectiveness of a low-code approach for assisting clinicians with data mining for mortality and length of stay (LOS) prediction in patients with CAP. A retrospective study was conducted using a low-code platform and the PyCaret library in Google Colab on data from patients with community-acquired pneumonia (CAP) admitted between January 2013 and December 2021 to two medical facilities. Model performance was assessed using the area under the receiver operating characteristic curve (AUC) for mortality prediction and the R2 score for LOS prediction, with benchmarks set at AUC > 0.9 and R2 > 0.5. The Shapley Additive Explanations (SHAP) method was used for interpreting individual predictions. A total of 669 CAP patients were enrolled in the analysis.Fifteen models were evaluated for mortality prediction, and nineteen models were evaluated for LOS prediction utilizing the PyCaret library. The Light Gradient Boosting Machine model yielded the highest AUC (0.963) for mortality prediction. In predicting LOS, the Extratrees Regressor model achieved the highest R2 score of 0.585. Factors such as the severity of pneumonia and the Charlson Comorbidity Index (CCI) were significant factors influencing mortality. For the LOS, the CCI score, activities of daily living, and social support were significant predictors. The low-code approach enables medical professionals with limited technical expertise to effectively employ data science in their clinical decision-making process. This approach proved to be a valuable tool in the analysis of CAP patient data.https://doi.org/10.1038/s41598-024-82615-0Low-codingMachine learningPyCaretLength of stayMortalityArtificial intelligence |
| spellingShingle | Hao Chen Shurui Zhang Hiromi Matsumoto Nanami Tsuchiya Chihiro Yamada Shunsuke Okasaki Atsushi Miyasaka Kentaro Yumoto Daiki Kanou Fumihiro Kashizaki Harumi Koizumi Kenichi Takahashi Masato Shimizu Nobuyuki Horita Takeshi Kaneko Employing a low-code machine learning approach to predict in-hospital mortality and length of stay in patients with community-acquired pneumonia Scientific Reports Low-coding Machine learning PyCaret Length of stay Mortality Artificial intelligence |
| title | Employing a low-code machine learning approach to predict in-hospital mortality and length of stay in patients with community-acquired pneumonia |
| title_full | Employing a low-code machine learning approach to predict in-hospital mortality and length of stay in patients with community-acquired pneumonia |
| title_fullStr | Employing a low-code machine learning approach to predict in-hospital mortality and length of stay in patients with community-acquired pneumonia |
| title_full_unstemmed | Employing a low-code machine learning approach to predict in-hospital mortality and length of stay in patients with community-acquired pneumonia |
| title_short | Employing a low-code machine learning approach to predict in-hospital mortality and length of stay in patients with community-acquired pneumonia |
| title_sort | employing a low code machine learning approach to predict in hospital mortality and length of stay in patients with community acquired pneumonia |
| topic | Low-coding Machine learning PyCaret Length of stay Mortality Artificial intelligence |
| url | https://doi.org/10.1038/s41598-024-82615-0 |
| work_keys_str_mv | AT haochen employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT shuruizhang employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT hiromimatsumoto employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT nanamitsuchiya employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT chihiroyamada employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT shunsukeokasaki employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT atsushimiyasaka employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT kentaroyumoto employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT daikikanou employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT fumihirokashizaki employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT harumikoizumi employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT kenichitakahashi employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT masatoshimizu employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT nobuyukihorita employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia AT takeshikaneko employingalowcodemachinelearningapproachtopredictinhospitalmortalityandlengthofstayinpatientswithcommunityacquiredpneumonia |