A deep learning-based model (DeepMPM) to help predict survival in patients with malignant pleural mesothelioma

Our plain-English summary of A deep learning-based model (DeepMPM) to help predict survival in patients with malignant pleural mesothelioma, by W. Li, M. Zhang, S. Cai, et al (Translational Cancer Research, 2023).

The study

• Authors: W. Li, M. Zhang, S. Cai, S. Li, B. Yang, S. Zhou, Y. Pan, S. Xu
• Journal: Translational Cancer Research
• Published: 2023;12(10):2887-2897
• Cited by: 7 articles, as counted by NIH iCite
• Read it: PubMed · Publisher · Free full text

Abstract

Background: Malignant pleural mesothelioma (MPM) is a rare disease with limited treatment and poor prognosis, and a precise and reliable means to predicting MPM remains lacking for clinical use.

Methods: In the population-based cohort study, we collected clinical characteristics from the Surveillance, Epidemiology, and End Results (SEER) database. According to the time of diagnosis, the SEER data were divided into 2 cohorts: the training cohort (from 2010 to 2016) and the test cohort (from 2017 to 2019). The training cohort was used to train a deep learning-based predictive model derived from DeepSurv theory, which was validated by both the training and the test cohorts. All clinical characteristics were included and analyzed using Cox proportional risk regression or Kaplan-Meier curve to determine the risk factors and protective factors of MPM.

Results: The survival model included 3,130 cases (2,208 in the training cohort and 922 in the test cohort). As for model's performance, the area under the receiver operating characteristics curve (AUC) was 0.7037 [95% confidence interval (CI): 0.7030-0.7045] in the training cohort and 0.7076 (95% CI: 0.7067-0.7086) in the test cohort. Older age; male sex, sarcomatoid mesothelioma; and T4, N2, and M1 stage tended to be the risk factors for survival. Meanwhile, epithelioid mesothelioma, surgery, radiotherapy, and chemotherapy tended to be the protective factors. The median overall survival (OS) of patients who underwent surgery combined with radiotherapy was the longest, followed by those who underwent a combination of surgery, radiotherapy, and chemotherapy.

Conclusions: Our deep learning-based model precisely could predict the survival of patients with MPM; moreover, multimode combination therapy might provide more meaningful survival benefits.

2023 Translational Cancer Research. All rights reserved.

In plain English

This retrospective study used Surveillance, Epidemiology, and End Results (SEER) database records of 3,130 patients with malignant pleural mesothelioma. It did not examine asbestos exposure. The authors built a deep learning model (DeepMPM) that predicts survival from age, sex, history of malignancy, tumor subtype and stage, and treatment (surgery, radiotherapy, chemotherapy). They trained it on 2,208 patients diagnosed 2010 to 2016 and tested it on 922 diagnosed 2017 to 2019. Its AUC score (near 0.5 for a poor model, near 1 for an outstanding one) was 0.7037 (95% CI 0.7030 to 0.7045) for training and 0.7076 (95% CI 0.7067 to 0.7086) for testing. Across all patients, older age, male sex, sarcomatoid subtype and T4, N2 and M1 stage were identified as risk factors for poorer survival, and epithelioid subtype, surgery, radiotherapy and chemotherapy as protective factors. Surgery plus radiotherapy had the longest median survival (24 months). The authors concluded the model performed well and combination therapy might give more survival benefit than single therapy. They noted prospective data are needed and some factors, such as surgical methods, were missing.

We wrote this plain-English summary from the full article with the help of AI, and a second AI model checked each sentence against the article. It is not the authors' wording; the abstract and the article are their own account.

What the study did and found

• Design: Retrospective population-based cohort study using a cancer registry database. It developed and validated a deep learning survival prediction model (based on DeepSurv) and added Cox regression and Kaplan-Meier survival analysis.
• Who was studied: 3,130 patients with malignant pleural mesothelioma from the SEER 17 Registries database. The training cohort had 2,208 patients diagnosed 2010 to 2016 and the test cohort had 922 diagnosed 2017 to 2019. Median age was 73 years in the training cohort and 74 in the test cohort. Males were 78.62% of the training cohort and 76.79% of the test cohort. Follow-up cutoff was December 31, 2019.
• Exposure: No asbestos exposure was studied. The predictors were clinical features: age, sex, history of malignancy, pathology (epithelioid, sarcomatoid, biphasic), TNM stage (AJCC seventh edition), surgery, radiotherapy and chemotherapy.
• Main results:
  • DeepMPM had an AUC of 0.7037 (95% CI: 0.7030 to 0.7045) in the training cohort and 0.7076 (95% CI: 0.7067 to 0.7086) in the test cohort.
  • Median survival time was 10 months in the training cohort and 8 months in the test cohort.
  • In Cox regression on all patients, age (HR 1.02; 95% CI: 1.01 to 1.02; p less than 0.001) and male sex (HR 1.17; 95% CI: 1.06 to 1.29; p=0.002) were identified as risk factors.
  • Sarcomatoid mesothelioma (HR 1.46; 95% CI: 1.28 to 1.67), T4 (HR 1.28; 95% CI: 1.16 to 1.43), N2 (HR 1.36; 95% CI: 1.23 to 1.49) and M1 (HR 1.48; 95% CI: 1.33 to 1.64) were identified as risk factors, each with p less than 0.001.
  • Epithelioid mesothelioma (HR 0.59; 95% CI: 0.53 to 0.66), surgery (HR 0.75; 95% CI: 0.69 to 0.82), radiotherapy (HR 0.71; 95% CI: 0.63 to 0.80) and chemotherapy (HR 0.61; 95% CI: 0.56 to 0.66) were identified as protective factors, each with p less than 0.001.
  • In Kaplan-Meier analysis, median overall survival was longest with surgery plus radiotherapy (24 months). Next came surgery plus radiotherapy plus chemotherapy (20 months), then surgery plus chemotherapy (19 months). Median overall survival with any single treatment was less than 1 year.
• The authors' conclusion: The authors concluded that their deep learning prediction tool performed well in predicting survival of patients with malignant pleural mesothelioma. They also concluded that multimode combination therapy might confer greater survival benefits than single-mode therapy.
• Limitations the authors state:
  • The SEER database lacked variables that might affect prognosis, such as surgical methods, chemotherapy schemes, lung function and biomarkers.
  • Large-scale prospective multicenter data are needed to verify the findings.
  • The finding that surgery combined with radiotherapy may be a better choice needs validation in prospective clinical trials.

Topics

Medical terms in this study, explained in our Lexicon: Pleural Mesothelioma, Prognosis, Cohort Study, Epidemiology, SEER, Kaplan-Meier Curve, confidence interval, Sarcomatoid.

Related studies

• Construction of Asbestos Slate Deep-Learning Training-Data Model Based on Drone Images — S.C. Baek, K.H. Lee, et al. (2023)
• Cancer-Associated Fibroblasts Influence Survival in Pleural Mesothelioma: Digital Gene Expression Analysis and Supervised Machine Learning Model — S. Borchert, A. Mathilakathu, et al. (2023)
• Deep learning-based classification of mesothelioma improves prediction of patient outcome — P. Courtiol, C. Maussion, et al. (2019)
• Fully automated volumetric measurement of malignant pleural mesothelioma by deep learning AI: validation and comparison with modified RECIST response criteria — A.C. Kidd, O. Anderson, et al. (2022)
• Accelerating Whole-Body Diffusion-weighted MRI with Deep Learning-based Denoising Image Filters — K. Zormpas-Petridis, N. Tunariu, et al. (2021)
• Deep-learning based classification distinguishes sarcomatoid malignant mesotheliomas from benign spindle cell mesothelial proliferations — J.R. Naso, A.B. Levine, et al. (2021)

Browse more research in Translational Cancer Research, or return to medical research.