Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms
Abstract Associations between delirium and postoperative adverse events in cardiovascular surgery have been reported and the preoperative identification of high-risk patients of delirium is needed to implement focused interventions. We aimed to develop and validate machine learning models to predict...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-48418-5 |
| _version_ | 1827327313674502144 |
|---|---|
| author | Chie Nagata Masahiro Hata Yuki Miyazaki Hirotada Masuda Tamiki Wada Tasuku Kimura Makoto Fujii Yasushi Sakurai Yasuko Matsubara Kiyoshi Yoshida Shigeru Miyagawa Manabu Ikeda Takayoshi Ueno |
| author_facet | Chie Nagata Masahiro Hata Yuki Miyazaki Hirotada Masuda Tamiki Wada Tasuku Kimura Makoto Fujii Yasushi Sakurai Yasuko Matsubara Kiyoshi Yoshida Shigeru Miyagawa Manabu Ikeda Takayoshi Ueno |
| author_sort | Chie Nagata |
| collection | DOAJ |
| description | Abstract Associations between delirium and postoperative adverse events in cardiovascular surgery have been reported and the preoperative identification of high-risk patients of delirium is needed to implement focused interventions. We aimed to develop and validate machine learning models to predict post-cardiovascular surgery delirium. Patients aged ≥ 40 years who underwent cardiovascular surgery at a single hospital were prospectively enrolled. Preoperative and intraoperative factors were assessed. Each patient was evaluated for postoperative delirium 7 days after surgery. We developed machine learning models using the Bernoulli naive Bayes, Support vector machine, Random forest, Extra-trees, and XGBoost algorithms. Stratified fivefold cross-validation was performed for each developed model. Of the 87 patients, 24 (27.6%) developed postoperative delirium. Age, use of psychotropic drugs, cognitive function (Mini-Cog < 4), index of activities of daily living (Barthel Index < 100), history of stroke or cerebral hemorrhage, and eGFR (estimated glomerular filtration rate) < 60 were selected to develop delirium prediction models. The Extra-trees model had the best area under the receiver operating characteristic curve (0.76 [standard deviation 0.11]; sensitivity: 0.63; specificity: 0.78). XGBoost showed the highest sensitivity (AUROC, 0.75 [0.07]; sensitivity: 0.67; specificity: 0.79). Machine learning algorithms could predict post-cardiovascular delirium using preoperative data. Trial registration: UMIN-CTR (ID; UMIN000049390). |
| first_indexed | 2024-03-07T14:59:21Z |
| format | Article |
| id | doaj.art-56d527d90f1c4db7be0a34d9ab4f1ffa |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-07T14:59:21Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-56d527d90f1c4db7be0a34d9ab4f1ffa2024-03-05T19:13:47ZengNature PortfolioScientific Reports2045-23222023-11-011311810.1038/s41598-023-48418-5Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithmsChie Nagata0Masahiro Hata1Yuki Miyazaki2Hirotada Masuda3Tamiki Wada4Tasuku Kimura5Makoto Fujii6Yasushi Sakurai7Yasuko Matsubara8Kiyoshi Yoshida9Shigeru Miyagawa10Manabu Ikeda11Takayoshi Ueno12Division of Health Sciences, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineDepartment of Cardiovascular Surgery, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineSANKEN (The Institution of Scientific and Industrial Research), Osaka UniversityDivision of Health Sciences, Osaka University Graduate School of MedicineSANKEN (The Institution of Scientific and Industrial Research), Osaka UniversitySANKEN (The Institution of Scientific and Industrial Research), Osaka UniversityDivision of Health Sciences, Osaka University Graduate School of MedicineDepartment of Cardiovascular Surgery, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineDivision of Health Sciences, Osaka University Graduate School of MedicineAbstract Associations between delirium and postoperative adverse events in cardiovascular surgery have been reported and the preoperative identification of high-risk patients of delirium is needed to implement focused interventions. We aimed to develop and validate machine learning models to predict post-cardiovascular surgery delirium. Patients aged ≥ 40 years who underwent cardiovascular surgery at a single hospital were prospectively enrolled. Preoperative and intraoperative factors were assessed. Each patient was evaluated for postoperative delirium 7 days after surgery. We developed machine learning models using the Bernoulli naive Bayes, Support vector machine, Random forest, Extra-trees, and XGBoost algorithms. Stratified fivefold cross-validation was performed for each developed model. Of the 87 patients, 24 (27.6%) developed postoperative delirium. Age, use of psychotropic drugs, cognitive function (Mini-Cog < 4), index of activities of daily living (Barthel Index < 100), history of stroke or cerebral hemorrhage, and eGFR (estimated glomerular filtration rate) < 60 were selected to develop delirium prediction models. The Extra-trees model had the best area under the receiver operating characteristic curve (0.76 [standard deviation 0.11]; sensitivity: 0.63; specificity: 0.78). XGBoost showed the highest sensitivity (AUROC, 0.75 [0.07]; sensitivity: 0.67; specificity: 0.79). Machine learning algorithms could predict post-cardiovascular delirium using preoperative data. Trial registration: UMIN-CTR (ID; UMIN000049390).https://doi.org/10.1038/s41598-023-48418-5 |
| spellingShingle | Chie Nagata Masahiro Hata Yuki Miyazaki Hirotada Masuda Tamiki Wada Tasuku Kimura Makoto Fujii Yasushi Sakurai Yasuko Matsubara Kiyoshi Yoshida Shigeru Miyagawa Manabu Ikeda Takayoshi Ueno Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms Scientific Reports |
| title | Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms |
| title_full | Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms |
| title_fullStr | Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms |
| title_full_unstemmed | Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms |
| title_short | Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms |
| title_sort | development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms |
| url | https://doi.org/10.1038/s41598-023-48418-5 |
| work_keys_str_mv | AT chienagata developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT masahirohata developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT yukimiyazaki developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT hirotadamasuda developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT tamikiwada developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT tasukukimura developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT makotofujii developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT yasushisakurai developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT yasukomatsubara developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT kiyoshiyoshida developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT shigerumiyagawa developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT manabuikeda developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms AT takayoshiueno developmentofpostoperativedeliriumpredictionmodelsinpatientsundergoingcardiovascularsurgeryusingmachinelearningalgorithms |