Survival analysis of patient groups defined by unsupervised machine learning clustering methods based on patient metabolomic data.

Purpose: Meta-analyses failed to accurately identify patients with non-metastatic breast cancer who are likely to benefit from chemotherapy, and metabolomics could provide new answers. In our previous published work, patients were clustered using five different unsupervised machine learning (ML) methods resulting in the identification of three clusters with distinct clinical and simulated survival data. The objective of this study was to evaluate the survival outcomes, with extended follow-up, using the same 5 different methods of unsupervised machine learning. Experimental design: Forty-nine patients, diagnosed between 2013 and 2016, with non-metastatic BC were included retrospectively. Median follow-up was extended to 85.8 months. 449 metabolites were extracted from tumor resection samples by combined Liquid chromatography-mass spectrometry (LC-MS). Survival analyses were reported grouping together Cluster 1 and 2 versus cluster 3. Bootstrap optimization was applied. Results: PCA k-means, K-sparse and Spectral clustering were the most effective methods to predict 2-year progression-free survival with bootstrap optimization (PFSb); as bootstrap example, with PCA k-means method, PFSb were 94% for cluster 1&2 versus 82% for cluster 3 (p = 0.01). PCA k-means method performed best, with higher reproducibility (mean HR=2 (95%CI [1.4-2.7]); probability of p ≤ 0.05 85%). Cancer-specific survival (CSS) and overall survival (OS) analyses highlighted a discrepancy between the 5 ML unsupervised methods. Conclusion: Our study is a proof-of-principle that it is possible to use unsupervised ML methods on metabolomic data to predict PFS survival outcomes, with the best performance for PCA k-means. A larger population study is needed to draw conclusions from CSS and OS analyses.