Methods: In a cohort of 1144 Lung Adenocarcinoma (LUAD) and Lung Squamous Cell Carcinoma (LSCC) patients, we studied the number of missense mutations (hereafter, the Total Mutational Load TML) and distribution of clinical variables, for diferent classes of patients. Using the TML and diferent sets of clinical variables (tumour stage, age, sex, smoking status, and packs of cigarettes smoked per year), we built Random Forest classifcation models that calculate the likelihood of developing metastasis.
Results: We found that LC patients diferent in age, smoking status, and tumour type had signifcantly diferent mean TMLs. Although TML was an informative feature, its efect was secondary to the "tumour stage" feature. However, its contribution to the classifcation is not redundant with the latter; models trained using both TML and tumour stage performed better than models trained using only one of these variables. We found that models trained in the entire dataset (i.e., without using dimensionality reduction techniques) and without resampling achieved the highest perfor‐ mance, with an F1 score of 0.64 (95%CrI [0.62, 0.66]).
Conclusions: Clinical variables and TML should be considered together when assessing the likelihood of LC patients progressing to metastatic states, as the information these encode is not redundant. Altogether, we provide new evi‐ dence of the need for comprehensive diagnostic tools for metastasis.