Identifying Prognostic Groups Using Machine Learning Tools in Patients Undergoing Chemoradiation for Inoperable Locally Advanced Nonsmall Cell Lung Carcinoma

Abstract

Introduction Unresectable stage III nonsmall cell lung cancer (NSCLC) continues to have dismal 5-year overall survival (OS) rate. However, a subset of the patients treated with chemoradiation show significantly better outcome. Prediction of treatment outcome can be improved by utilizing machine learning tools, such as cluster analysis (CA), and is capable of identifying complex interactions among many variables. We have utilized CA to identify a cluster with good prognosis within stage III NSCLC. Materials and Methods Retrospective analysis of treatment outcomes was done for 92 patients who underwent chemoradiation for inoperable locally advanced NSCLC from 2012 to 2018. Using various patient- and treatment-related variables, an exploratory factor analysis was performed to extract factors with eigenvalue > 1. An appropriate number of homogeneous groups were identified using agglomerative hierarchical cluster analysis. Further K-mean cluster analysis was applied to classify each patient into their homogeneous clusters. The newly formed cluster variable was used as an independent variable to estimate survival over time using Kaplan–Meier method. Results With a median follow-up of 18 months, median OS was 14 months. Using CA, three prognostic clusters were obtained. Cluster 2 with 36 patients had a median OS of 36 months, whereas Cluster 1 with 34 patients had a median OS of 20 months (p = 0.004). Conclusion A cluster could thus be identified with a relatively good prognosis within stage III NSCLC. Using CA, we have attempted to create a model which may provide more specific prognostic information in addition to that provided by tumor node metastasis-based models.

Keywords

• chemoradiation
• machine learning
• nonsmall cell lung carcinoma