Development of a Machine Learning-based Risk Model for Postoperative Complications of Lung Cancer Surgery

Overview

Journal Surg Today

Specialty General Surgery

Date 2024 Jun 19

PMID 38896280

Authors

Yuka Kadomatsu

Ryo Emoto

Yoko Kubo

Keita Nakanishi

Harushi Ueno

Taketo Kato

Shota Nakamura

Tetsuya Mizuno

Shigeyuki Matsui

Toyofumi Fengshi Chen-Yoshikawa

Affiliations

Soon will be listed here.

Abstract

Purpose: To develop a comorbidity risk score specifically for lung resection surgeries.

Methods: We reviewed the medical records of patients who underwent lung resections for lung cancer, and developed a risk model using data from 2014 to 2017 (training dataset), validated using data from 2018 to 2019 (validation dataset). Forty variables were analyzed, including 35 factors related to the patient's overall condition and five factors related to surgical techniques and tumor-related factors. The risk model for postoperative complications was developed using an elastic net regularized generalized linear model. The performance of the risk model was evaluated using receiver operating characteristic curves and compared with the Charlson Comorbidity Index (CCI).

Results: The rate of postoperative complications was 34.7% in the training dataset and 21.9% in the validation dataset. The final model consisted of 20 variables, including age, surgical-related factors, respiratory function tests, and comorbidities, such as chronic obstructive pulmonary disease, a history of ischemic heart disease, and 12 blood test results. The area under the curve (AUC) for the developed risk model was 0.734, whereas the AUC for the CCI was 0.521 in the validation dataset.

Conclusions: The new machine learning model could predict postoperative complications with acceptable accuracy.

Clinical Registration Number: 2020-0375.

Citing Articles

Enhancing Thoracic Surgery with AI: A Review of Current Practices and Emerging Trends.

Aleem M, Khan J, Younes A, Sabbah B, Saleh W, Migliore M Curr Oncol. 2024; 31(10):6232-6244.

PMID: 39451768 PMC: 11506543. DOI: 10.3390/curroncol31100464.

References

Chen-Yoshikawa T, Fukui T, Nakamura S, Ito T, Kadomatsu Y, Tsubouchi H . Current trends in thoracic surgery. Nagoya J Med Sci. 2020; 82(2):161-174. PMC: 7276403. DOI: 10.18999/nagjms.82.2.161. View

Medbery R, Fernandez F, Kosinski A, Tong B, Furnary A, Feng L . Costs Associated With Lobectomy for Lung Cancer: An Analysis Merging STS and Medicare Data. Ann Thorac Surg. 2020; 111(6):1781-1790. DOI: 10.1016/j.athoracsur.2020.08.073. View

Asban A, Chung S, Tresler M, Huilgol P, Xie R, Kirklin J . Hyperthyroidism is Underdiagnosed and Undertreated in 3336 Patients: An Opportunity for Improvement and Intervention. Ann Surg. 2018; 268(3):506-512. DOI: 10.1097/SLA.0000000000002922. View

Charlson M, Pompei P, Ales K, MacKenzie C . A new method of classifying prognostic comorbidity in longitudinal studies: development and validation. J Chronic Dis. 1987; 40(5):373-83. DOI: 10.1016/0021-9681(87)90171-8. View

Colinet B, Jacot W, Bertrand D, Lacombe S, Bozonnat M, Daures J . A new simplified comorbidity score as a prognostic factor in non-small-cell lung cancer patients: description and comparison with the Charlson's index. Br J Cancer. 2005; 93(10):1098-105. PMC: 2361505. DOI: 10.1038/sj.bjc.6602836. View

Gajra A . Assessment of comorbidity in lung cancer: How, why, and in whom?. J Geriatr Oncol. 2016; 7(2):64-7. DOI: 10.1016/j.jgo.2016.02.003. View

Sandfeld-Paulsen B, Meldgaard P, Aggerholm-Pedersen N . Comorbidity in Lung Cancer: A Prospective Cohort Study of Self-Reported versus Register-Based Comorbidity. J Thorac Oncol. 2017; 13(1):54-62. DOI: 10.1016/j.jtho.2017.10.002. View

Brunelli A, Salati M, Rocco G, Varela G, Van Raemdonck D, Decaluwe H . European risk models for morbidity (EuroLung1) and mortality (EuroLung2) to predict outcome following anatomic lung resections: an analysis from the European Society of Thoracic Surgeons database. Eur J Cardiothorac Surg. 2016; 51(3):490-497. DOI: 10.1093/ejcts/ezw319. View

Endo S, Ikeda N, Kondo T, Nakajima J, Kondo H, Yokoi K . Model of lung cancer surgery risk derived from a Japanese nationwide web-based database of 78 594 patients during 2014-2015. Eur J Cardiothorac Surg. 2017; 52(6):1182-1189. PMC: 5848741. DOI: 10.1093/ejcts/ezx190. View

10.

Fernandez F, Kosinski A, Burfeind W, Park B, DeCamp M, Seder C . The Society of Thoracic Surgeons Lung Cancer Resection Risk Model: Higher Quality Data and Superior Outcomes. Ann Thorac Surg. 2016; 102(2):370-7. PMC: 5016798. DOI: 10.1016/j.athoracsur.2016.02.098. View

11.

Meyer A, Zverinski D, Pfahringer B, Kempfert J, Kuehne T, Sundermann S . Machine learning for real-time prediction of complications in critical care: a retrospective study. Lancet Respir Med. 2018; 6(12):905-914. DOI: 10.1016/S2213-2600(18)30300-X. View

12.

Viswanathan V, Toro P, Corredor G, Mukhopadhyay S, Madabhushi A . The state of the art for artificial intelligence in lung digital pathology. J Pathol. 2022; 257(4):413-429. PMC: 9254900. DOI: 10.1002/path.5966. View

13.

Zhong Y, She Y, Deng J, Chen S, Wang T, Yang M . Deep Learning for Prediction of N2 Metastasis and Survival for Clinical Stage I Non-Small Cell Lung Cancer. Radiology. 2021; 302(1):200-211. DOI: 10.1148/radiol.2021210902. View

14.

Endo S, Ikeda N, Kondo T, Nakajima J, Kondo H, Yokoi K . Development of an annually updated Japanese national clinical database for chest surgery in 2014. Gen Thorac Cardiovasc Surg. 2016; 64(10):569-76. PMC: 5035318. DOI: 10.1007/s11748-016-0697-1. View

15.

Kozower B, Sheng S, OBrien S, Liptay M, Lau C, Jones D . STS database risk models: predictors of mortality and major morbidity for lung cancer resection. Ann Thorac Surg. 2010; 90(3):875-81. DOI: 10.1016/j.athoracsur.2010.03.115. View

16.

Kadomatsu Y, Nakamura S, Ueno H, Goto M, Ozeki N, Fukumoto K . Prognostic Value of Uncertain Resection for Overall Survival in Non-small Cell Lung Cancer. Ann Thorac Surg. 2021; 114(4):1262-1268. DOI: 10.1016/j.athoracsur.2021.07.087. View

17.

Varma S, Simon R . Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics. 2006; 7:91. PMC: 1397873. DOI: 10.1186/1471-2105-7-91. View

18.

Rogers M, Janjua H, Fishberger G, Harish A, Sujka J, Toloza E . A machine learning approach to high-risk cardiac surgery risk scoring. J Card Surg. 2022; 37(12):4612-4620. DOI: 10.1111/jocs.17110. View

19.

Zhang K, Ye B, Wu L, Ni S, Li Y, Wang Q . Machine learning‑based prediction of survival prognosis in esophageal squamous cell carcinoma. Sci Rep. 2023; 13(1):13532. PMC: 10439907. DOI: 10.1038/s41598-023-40780-8. View

20.

Seastedt K, Moukheiber D, Mahindre S, Thammineni C, Rosen D, Watkins A . A scoping review of artificial intelligence applications in thoracic surgery. Eur J Cardiothorac Surg. 2021; 61(2):239-248. PMC: 8932394. DOI: 10.1093/ejcts/ezab422. View