# Distant Metastatic Pattern and Its Prognostic Significance in Malignant Pleural Mesothelioma: A Population‐Based Study Based on a Machine Learning Model

## TL;DR

This study uses machine learning to analyze metastatic patterns in malignant pleural mesothelioma and identifies risk factors that affect patient survival.

## Contribution

A population-based machine learning model is developed to predict metastatic progression and survival in malignant pleural mesothelioma.

## Key findings

- Distant metastasis reduces median overall survival from 10.5 to 7 months in MPM patients.
- Sarcomatoid histology, T4 stage, N1+ nodal involvement, and bilateral disease are key predictors of metastatic spread.
- The contralateral lung is the most common metastatic site, and lymph node metastasis has a better prognosis than metastasis to other organs.

## Abstract

Malignant pleural mesothelioma (MPM) is an insidious and aggressive tumor, often hindering timely clinical interventions. Despite its clinical relevance, epidemiological research focusing on MPM metastases remains limited.

We conducted a retrospective review of MPM cases with site‐specific metastasis records from the Surveillance, Epidemiology, and End Results (SEER) between 2010 and 2019. Propensity Score Matching was employed to minimize bias between distant metastasis and non‐distant metastasis groups. A prognostic model for predicting overall survival was established using clinical variables derived from Lasso regression. Variable importance for survival outcomes was estimated using the Random Survival Forests algorithm. The performance of the nomogram was evaluated using the receiver operating characteristic (ROC) curves and calibration plots.

The presence of distant metastasis significantly reduced median overall survival from 10.5 to 7 months, with further detriment observed in cases with sarcomatoid histology and without chemotherapy intervention. Multivariable analysis identified sarcomatoid subtype, T4 stage, N1+ nodal involvement, and bilateral disease as significant predictors of increased metastatic potential. Histology, surgery, and metastasis status emerged as the top three clinical variables influencing survival. The nomogram demonstrated strong discrimination and calibration for predicting the 1‐year and 3‐year overall survival in both training and validation cohorts. The contralateral lung was the most frequent site of distant metastasis, with lymph node metastasis presenting a significantly better prognosis than that observed in patients with metastases to other organs.

The large population‐based analysis provides a comprehensive characterization of site‐specific metastases in MPM. The identified risk factors can help stratify patients at higher risk for metastatic progression and support early, targeted clinical decision‐making.

The presence of distant metastasis significantly reduced the median overall survival in patients with malignant pleural mesothelioma (MPM). Histologic subtype, T‐stage, N‐stage, and tumor laterality are independent risk factors for metastatic spread. Multivariable analysis highlights sarcomatoid histology, T4 stage, N1+ nodal involvement, and bilateral disease as key predictors of increased metastatic potential. The contralateral lung is the most frequent metastatic site, while solitary lymph node metastasis is associated with a comparatively favorable prognosis.