Establishment of predictive nomogram and web-based survival risk calculator for malignant pleural mesothelioma: A SEER database analysis

Our plain-English summary of Establishment of predictive nomogram and web-based survival risk calculator for malignant pleural mesothelioma: A SEER database analysis, by S. Chen, W. Yu, S. Shao, et al (Frontiers in Oncology, 2022).

The study

• Authors: S. Chen, W. Yu, S. Shao, J. Xiao, H. Bai, Y. Pu, M. Li
• Journal: Frontiers in Oncology
• Published: 2022;12:1027149
• Cited by: 11 articles, as counted by NIH iCite
• Read it: PubMed · Publisher · Free full text

Abstract

Background: Malignant pleural mesothelioma (MPM) is an uncommon condition with limited available therapies and dismal prognoses. The purpose of this work was to create a multivariate clinical prognostic nomogram and a web-based survival risk calculator to forecast patients' prognoses.

Methods: Using a randomization process, training and validation groups were created for a retrospective cohort study that examined the Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2015 for individuals diagnosed with MPM (7:3 ratio). Overall survival (OS) and cancer-specific survival (CSS) were the primary endpoints. Clinical traits linked to OS and CSS were identified using Least Absolute Shrinkage and Selection Operator (LASSO) Cox regression analysis, which was also utilized to develop nomogram survival models and online survival risk calculators. By charting the receiver operating characteristic (ROC), consistency index (C-index), calibration curve, and decision curve analysis (DCA), the model's performance was assessed. The nomogram was used to classify patients into various risk categories, and the Kaplan-Meier method was used to examine each risk group's survival rate.

Results: The prognostic model comprised a total of 1978 patients. For the total group, the median OS and CSS were 10 (9.4-10.5) and 11 (9.4-12.6) months, respectively. As independent factors for OS and CSS, age, gender, insurance, histology, T stage, M stage, surgery, and chemotherapy were chosen. The calibration graphs demonstrated good concordance. In the training and validation groups, the C-indices for OS and CSS were 0.729, 0.717, 0.711, and 0.721, respectively. Our nomogram produced a greater clinical net benefit than the AJCC 7th edition, according to DCA and ROC analysis. According to the cut-off values of 171 for OS and 189 for CSS of the total scores from our nomogram, patients were classified into two risk groups. The P-value < 0.001 on the Kaplan-Meier plot revealed a significant difference in survival between the two patient groups.

Conclusions: Patient survival in MPM was correctly predicted by the risk evaluation model. This will support clinicians in the practice of individualized medicine.

Copyright © 2022 Chen, Yu, Shao, Xiao, Bai, Pu and Li.

In plain English

This study used the US SEER cancer registry to build a tool estimating survival in malignant pleural mesothelioma. It included 1978 patients diagnosed from 2010 to 2015, split at random into a training group (1385) and a validation group (593). The study did not examine asbestos exposure; it used clinical details from the registry. Eight factors were linked to overall and cancer-specific survival: age, gender, histology, insurance, T stage, M stage, surgery and chemotherapy. Histology (tumor cell type) was most strongly associated. Median overall survival for all patients was 10 months (reported interval 9.5 to 10.5). The tool's accuracy score (C-index) for overall survival was 0.729 in the training group and 0.717 in the validation group, higher than the TNM staging system (0.611 and 0.595). In the low-risk group, patients given radiotherapy had median overall survival of 18 months versus 14 months without it. The authors said this needs verification because few patients had radiotherapy. The authors concluded their models predicted survival with good accuracy. They noted that key data, such as performance score and treatment details, 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 analysis of a US cancer registry database (SEER), used to develop and internally validate a survival prediction model (nomogram) and web-based calculator
• Who was studied: 1978 patients with malignant pleural mesothelioma in the SEER database, diagnosed 2010 to 2015, randomly split into a training group (1385) and a validation group (593). Most were over 65 (73.5%), male (78.1%) and white (90.2%).
• Exposure: No asbestos exposure or fiber data were studied. The variables were clinical and demographic: age, sex, race, marital status, insurance, grade, tumor side, AJCC 7th edition T, N and M stage and stage group, and treatment (surgery, chemotherapy, radiation).
• Main results:
  • In the total population, median overall survival was 10 months (9.5 to 10.5) and median cancer-specific survival was 11 months (9.4 to 12.6).
  • Eight factors were identified as independent predictors in both the overall survival and cancer-specific survival models: age, gender, histology, insurance, T stage, M stage, surgery and chemotherapy.
  • Histological type had the strongest association with prognosis. It was followed by M stage, age, insurance, chemotherapy, T stage, surgery and gender.
  • For overall survival, the nomogram's C-index was 0.729 in the training group and 0.717 in the validation group. The TNM staging system scored 0.611 (training) and 0.595 (validation).
  • For cancer-specific survival, the nomogram's C-index was 0.711 versus 0.592 for TNM staging in the training group, and 0.721 versus 0.639 in the validation group.
  • Patients were split into high-risk and low-risk groups at cut-offs of 171 points (overall survival model) and 189 points (cancer-specific survival model). Survival differed significantly between the two risk groups (P less than 0.001).
  • In the low-risk group, patients who received radiotherapy had longer survival than those who did not. Median overall survival was 18 versus 14 months (P=0.017) and median cancer-specific survival 18 versus 15 months (P=0.037). In the high-risk group, there was no statistically significant difference.
• The authors' conclusion: The authors concluded that multiple clinical factors independently affect overall and cancer-specific survival in malignant pleural mesothelioma. They stated that they built and validated prediction models with good accuracy.
• Limitations the authors state:
  • The analysis was retrospective, and patients missing from the SEER database were not included, which could have caused sampling error.
  • Important clinical details were missing from the SEER registry: performance score, radiation dose and target area, chemotherapy cycles and regimens, and second-line therapy.
  • Some collinearity among the variables in the model may have led to overfitting.
  • The apparent radiotherapy benefit in low-risk patients needs further verification because few patients received radiotherapy.
  • Further data are needed to confirm the validity and applicability of the nomogram.

Topics

Medical terms in this study, explained in our Lexicon: Pleural Mesothelioma, SEER, Cohort Study, Epidemiology, Overall Survival, Histology, Chemotherapy, AJCC.

Related studies

• Establishment and validation of nomograms to predict survival probability of advanced malignant pleural mesothelioma based on the SEER database and a Chinese medical institution — X. Zhang, L. Chang, et al. (2023)
• Survival prediction in peritoneal mesothelioma: a nomogram based on SEER data and a Chinese cohort — Y. Fang, M. Xiang, et al. (2024)
• Survival analysis via nomogram of surgical patients with malignant pleural mesothelioma in the Surveillance, Epidemiology, and End Results database — M. Zhuo, Q. Zheng, et al. (2019)
• Incidence, Survival Analysis and Future Perspective of Primary Peritoneal Mesothelioma (PPM): A Population-Based Study from SEER Database — A. Ullah, A. Waheed, et al. (2022)
• Risk of mesothelioma following external beam radiotherapy for prostate cancer: a cohort analysis of SEER database — A. Farioli, F.S. Violante, et al. (2013)
• Radiation-induced mesothelioma among long-term solid cancer survivors: a longitudinal analysis of SEER database — A. Farioli, M. Ottone, et al. (2016)

Browse more research in Frontiers in Oncology, or return to medical research.