Development and Comparison of Machine-learning Models for Predicting Prolonged Postoperative Length of Stay in Lung Cancer Patients Following Video-assisted Thoracoscopic Surgery

Overview

Journal Asia Pac J Oncol Nurs

Publisher Elsevier

Date 2024 May 29

PMID 38808011

Authors

Guolong Zhang

Xuanhui Liu

Yuning Hu

Qinchi Luo

Liang Ruan

Hongxia Xie

Yingchun Zeng

Affiliations

Soon will be listed here.

Abstract

Objective: This study aimed to develop models for predicting prolonged postoperative length of stay (PPOLOS) in lung cancer patients undergoing video-assisted thoracoscopic surgery (VATS) by utilizing machine-learning techniques. These models aim to offer valuable insights for clinical decision-making.

Methods: This retrospective cohort study analyzed a dataset of lung cancer patients who underwent VATS, identifying 25 numerical features and 45 textual features. Three classification machine-learning models were developed: XGBoost, random forest, and neural network. The performance of these models was evaluated based on accuracy (ACC) and area under the receiver operating characteristic curve, whereas the importance of variables was assessed using the feature importance parameter from the random forest model.

Results: Of the 6767 lung cancer patients, 1481 patients (21.9%) experienced a postoperative length of stay of > 4 days. The majority were male (4111, 60.8%), married (6246, 92.3%), and diagnosed with adenocarcinoma (4145, 61.3%). The Random Forest classifier exhibited superior prediction performance with an area under the curve (AUC) of 0.792 and ACC of 0.804. The calibration plot revealed that all three classifiers were in close alignment with the ideal calibration line, indicating high calibration reliability. The five most critical features identified were the following: surgical duration (0.116), age (0.066), creatinine (0.062), hemoglobin (0.058), and total protein (0.054).

Conclusions: This study developed and evaluated three machine-learning models for predicting PPOLOS in lung cancer patients undergoing VATS. The findings revealed that the Random Forest model is most accurately predicting the PPOLOS. Findings of this study enable the identification of crucial determinants and the formulation of targeted interventions to shorten the length of stay among lung cancer patients after VATS, which contribute to optimize the allocation of healthcare resources.

References

Grigor E, Ivanovic J, Anstee C, Zhang Z, Gilbert S, Maziak D . Impact of Adverse Events and Length of Stay on Patient Experience After Lung Cancer Resection. Ann Thorac Surg. 2017; 104(2):382-388. DOI: 10.1016/j.athoracsur.2017.05.025. View

Shen X, Zhou C, Hua Q, Yang L, Zhao W, Xu P . Impact of operation duration on short-term and long-term prognosis in patients undergoing radical colorectal surgery. J Cancer. 2022; 13(4):1160-1167. PMC: 8899385. DOI: 10.7150/jca.65817. View

von Meyenfeldt E, Hoeijmakers F, Marres G, van Thiel E, Marra E, Marang-van de Mheen P . Variation in length of stay after minimally invasive lung resection: a reflection of perioperative care routines?. Eur J Cardiothorac Surg. 2019; 57(4):747-753. DOI: 10.1093/ejcts/ezz303. View

Giambrone G, Smith M, Wu X, Gaber-Baylis L, Bhat A, Zabih R . Variability in length of stay after uncomplicated pulmonary lobectomy: is length of stay a quality metric or a patient metric?†. Eur J Cardiothorac Surg. 2016; 49(4):e65-71. PMC: 5006293. DOI: 10.1093/ejcts/ezv476. View

Zeleke A, Palumbo P, Tubertini P, Miglio R, Chiari L . Machine learning-based prediction of hospital prolonged length of stay admission at emergency department: a Gradient Boosting algorithm analysis. Front Artif Intell. 2023; 6:1179226. PMC: 10426288. DOI: 10.3389/frai.2023.1179226. View

Bargetzi L, Brack C, Herrmann J, Bargetzi A, Hersberger L, Bargetzi M . Nutritional support during the hospital stay reduces mortality in patients with different types of cancers: secondary analysis of a prospective randomized trial. Ann Oncol. 2021; 32(8):1025-1033. DOI: 10.1016/j.annonc.2021.05.793. View

Cheng H, Chen B, Soleas I, Ferko N, Cameron C, Hinoul P . Prolonged Operative Duration Increases Risk of Surgical Site Infections: A Systematic Review. Surg Infect (Larchmt). 2017; 18(6):722-735. PMC: 5685201. DOI: 10.1089/sur.2017.089. View

Xia C, Dong X, Li H, Cao M, Sun D, He S . Cancer statistics in China and United States, 2022: profiles, trends, and determinants. Chin Med J (Engl). 2022; 135(5):584-590. PMC: 8920425. DOI: 10.1097/CM9.0000000000002108. View

. Global cancer burden growing, amidst mounting need for services. Saudi Med J. 2024; 45(3):326-327. PMC: 11115397. View

10.

Guerrera F, Olland A, Ruffini E, Falcoz P . VATS lobectomy open lobectomy for early-stage lung cancer: an endless question-are we close to a definite answer?. J Thorac Dis. 2020; 11(12):5616-5618. PMC: 6988071. DOI: 10.21037/jtd.2019.12.19. View

11.

Tran K, Kondrashova O, Bradley A, Williams E, Pearson J, Waddell N . Deep learning in cancer diagnosis, prognosis and treatment selection. Genome Med. 2021; 13(1):152. PMC: 8477474. DOI: 10.1186/s13073-021-00968-x. View

12.

De Rosa S, Greco M, Rauseo M, Annetta M . The Good, the Bad, and the Serum Creatinine: Exploring the Effect of Muscle Mass and Nutrition. Blood Purif. 2023; 52(9-10):775-785. PMC: 10623400. DOI: 10.1159/000533173. View

13.

Dexter E, Attwood K, Demmy T, Yendamuri S . Does Operative Duration of Lobectomy for Early Lung Cancer Increase Perioperative Morbidity?. Ann Thorac Surg. 2022; 114(3):941-947. PMC: 9381650. DOI: 10.1016/j.athoracsur.2022.01.040. View

14.

Hebuterne X, Lemarie E, Michallet M, de Montreuil C, Schneider S, Goldwasser F . Prevalence of malnutrition and current use of nutrition support in patients with cancer. JPEN J Parenter Enteral Nutr. 2014; 38(2):196-204. DOI: 10.1177/0148607113502674. View

15.

Farjah F, Lou F, Rusch V, Rizk N . The quality metric prolonged length of stay misses clinically important adverse events. Ann Thorac Surg. 2012; 94(3):881-7. DOI: 10.1016/j.athoracsur.2012.04.082. View

16.

Lin K, Hu Y, Kong G . Predicting in-hospital mortality of patients with acute kidney injury in the ICU using random forest model. Int J Med Inform. 2019; 125:55-61. DOI: 10.1016/j.ijmedinf.2019.02.002. View

17.

Jo Y, Han J, Park H, Jung H, Lee J, Jung J . Prediction of Prolonged Length of Hospital Stay After Cancer Surgery Using Machine Learning on Electronic Health Records: Retrospective Cross-sectional Study. JMIR Med Inform. 2021; 9(2):e23147. PMC: 7939945. DOI: 10.2196/23147. View

18.

Kong W, Wang H, Chen Y, Xie J, Huang B, Fang L . Association between length of stay and postoperative survival in patients with lung cancer: a propensity score matching analysis based on National Cancer Database. J Thorac Dis. 2023; 15(4):1785-1793. PMC: 10183490. DOI: 10.21037/jtd-23-407. View

19.

Chen W, Yu Z, Zhang Y, Liu H . Comparison of cost effectiveness between video-assisted thoracoscopic surgery (vats) and open lobectomy: a retrospective study. Cost Eff Resour Alloc. 2021; 19(1):55. PMC: 8400899. DOI: 10.1186/s12962-021-00307-2. View

20.

Picard K, Mager D, Richard C . The Impact of Protein Type on Phosphorus Intake, Serum Phosphate Concentrations, and Nutrition Status in Adults with Chronic Kidney Disease: A Critical Review. Adv Nutr. 2021; 12(6):2099-2111. PMC: 8634523. DOI: 10.1093/advances/nmab062. View