Prediction of postoperative intensive care unit admission with artificial intelligence models in non-small cell lung carcinoma
Abstract Background There is no standard practice for intensive care admission after non-small cell lung cancer surgery. In this study, we aimed to determine the need for intensive care admission after non-small cell lung cancer surgery with deep learning models. Methods The data of 953 patients who...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-04-01
|
| Series: | European Journal of Medical Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40001-025-02553-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849699082922098688 |
|---|---|
| author | Gizem Özçıbık Işık Burcu Kılıç Ezel Erşen Mehmet Kamil Kaynak Akif Turna Onur Sefa Özçıbık Tülay Yıldırım Hasan Volkan Kara |
| author_facet | Gizem Özçıbık Işık Burcu Kılıç Ezel Erşen Mehmet Kamil Kaynak Akif Turna Onur Sefa Özçıbık Tülay Yıldırım Hasan Volkan Kara |
| author_sort | Gizem Özçıbık Işık |
| collection | DOAJ |
| description | Abstract Background There is no standard practice for intensive care admission after non-small cell lung cancer surgery. In this study, we aimed to determine the need for intensive care admission after non-small cell lung cancer surgery with deep learning models. Methods The data of 953 patients who were operated for non-small cell lung cancer between January 2001 and 2023 was analyzed. Clinical, laboratory, respiratory, tumor’s radiological and surgical features were included as input data in the study. The outcome data was intensive care unit admission. Deep learning was performed with the Fully Connected Neural Network algorithm and k-fold cross validation method. Results The training accuracy value was 92.0%, the training F1 1 score of the algorithm was 86.7%, the training F1 0 value was 94.2%, and the training F1 average score was 90.5%. The test sensitivity value of the algorithm was 67.7%, the test positive predictive value was 84.0%, and the test accuracy value was 85.3%. Test F1 1 score was 75.0%, test F1 0 score was 89.5%, and test F1 average score was 82.3%. The AUC in the ROC curve created for the success analysis of the algorithm's test data was 0.83. Conclusions Using our method deep learning models predicted the need for intensive care unit admission with high success and confidence values. The use of artificial intelligence algorithms for the necessity of intensive care hospitalization will ensure that postoperative processes are carried out safely using objective decision mechanisms. Graphical Abstract |
| format | Article |
| id | doaj-art-e554b5e5222c415ea0df5add30a4851b |
| institution | DOAJ |
| issn | 2047-783X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | BMC |
| record_format | Article |
| series | European Journal of Medical Research |
| spelling | doaj-art-e554b5e5222c415ea0df5add30a4851b2025-08-20T03:18:42ZengBMCEuropean Journal of Medical Research2047-783X2025-04-013011810.1186/s40001-025-02553-zPrediction of postoperative intensive care unit admission with artificial intelligence models in non-small cell lung carcinomaGizem Özçıbık Işık0Burcu Kılıç1Ezel Erşen2Mehmet Kamil Kaynak3Akif Turna4Onur Sefa Özçıbık5Tülay Yıldırım6Hasan Volkan Kara7Department of Thoracic Surgery, Istanbul University Cerrahpasa-Cerrahpasa Medical SchoolDepartment of Thoracic Surgery, Istanbul University Cerrahpasa-Cerrahpasa Medical SchoolDepartment of Thoracic Surgery, Istanbul University Cerrahpasa-Cerrahpasa Medical SchoolDepartment of Thoracic Surgery, Istanbul University Cerrahpasa-Cerrahpasa Medical SchoolDepartment of Thoracic Surgery, Istanbul University Cerrahpasa-Cerrahpasa Medical SchoolDepartment of Computer Engineering, Bogazici University Bogazici UniversityDepartment of Electronics and Communications, Yildiz Technical UniversityDepartment of Thoracic Surgery, Istanbul University Cerrahpasa-Cerrahpasa Medical SchoolAbstract Background There is no standard practice for intensive care admission after non-small cell lung cancer surgery. In this study, we aimed to determine the need for intensive care admission after non-small cell lung cancer surgery with deep learning models. Methods The data of 953 patients who were operated for non-small cell lung cancer between January 2001 and 2023 was analyzed. Clinical, laboratory, respiratory, tumor’s radiological and surgical features were included as input data in the study. The outcome data was intensive care unit admission. Deep learning was performed with the Fully Connected Neural Network algorithm and k-fold cross validation method. Results The training accuracy value was 92.0%, the training F1 1 score of the algorithm was 86.7%, the training F1 0 value was 94.2%, and the training F1 average score was 90.5%. The test sensitivity value of the algorithm was 67.7%, the test positive predictive value was 84.0%, and the test accuracy value was 85.3%. Test F1 1 score was 75.0%, test F1 0 score was 89.5%, and test F1 average score was 82.3%. The AUC in the ROC curve created for the success analysis of the algorithm's test data was 0.83. Conclusions Using our method deep learning models predicted the need for intensive care unit admission with high success and confidence values. The use of artificial intelligence algorithms for the necessity of intensive care hospitalization will ensure that postoperative processes are carried out safely using objective decision mechanisms. Graphical Abstracthttps://doi.org/10.1186/s40001-025-02553-zArtificial IntelligenceIntensive care unitNon-small cell lung cancer |
| spellingShingle | Gizem Özçıbık Işık Burcu Kılıç Ezel Erşen Mehmet Kamil Kaynak Akif Turna Onur Sefa Özçıbık Tülay Yıldırım Hasan Volkan Kara Prediction of postoperative intensive care unit admission with artificial intelligence models in non-small cell lung carcinoma European Journal of Medical Research Artificial Intelligence Intensive care unit Non-small cell lung cancer |
| title | Prediction of postoperative intensive care unit admission with artificial intelligence models in non-small cell lung carcinoma |
| title_full | Prediction of postoperative intensive care unit admission with artificial intelligence models in non-small cell lung carcinoma |
| title_fullStr | Prediction of postoperative intensive care unit admission with artificial intelligence models in non-small cell lung carcinoma |
| title_full_unstemmed | Prediction of postoperative intensive care unit admission with artificial intelligence models in non-small cell lung carcinoma |
| title_short | Prediction of postoperative intensive care unit admission with artificial intelligence models in non-small cell lung carcinoma |
| title_sort | prediction of postoperative intensive care unit admission with artificial intelligence models in non small cell lung carcinoma |
| topic | Artificial Intelligence Intensive care unit Non-small cell lung cancer |
| url | https://doi.org/10.1186/s40001-025-02553-z |
| work_keys_str_mv | AT gizemozcıbıkisık predictionofpostoperativeintensivecareunitadmissionwithartificialintelligencemodelsinnonsmallcelllungcarcinoma AT burcukılıc predictionofpostoperativeintensivecareunitadmissionwithartificialintelligencemodelsinnonsmallcelllungcarcinoma AT ezelersen predictionofpostoperativeintensivecareunitadmissionwithartificialintelligencemodelsinnonsmallcelllungcarcinoma AT mehmetkamilkaynak predictionofpostoperativeintensivecareunitadmissionwithartificialintelligencemodelsinnonsmallcelllungcarcinoma AT akifturna predictionofpostoperativeintensivecareunitadmissionwithartificialintelligencemodelsinnonsmallcelllungcarcinoma AT onursefaozcıbık predictionofpostoperativeintensivecareunitadmissionwithartificialintelligencemodelsinnonsmallcelllungcarcinoma AT tulayyıldırım predictionofpostoperativeintensivecareunitadmissionwithartificialintelligencemodelsinnonsmallcelllungcarcinoma AT hasanvolkankara predictionofpostoperativeintensivecareunitadmissionwithartificialintelligencemodelsinnonsmallcelllungcarcinoma |