Machine Learning for Prediction of Immunotherapy Efficacy in Non-Small Cell Lung Cancer from Simple Clinical and Biological Data

Abstract

Background: Immune checkpoint inhibitors (ICIs) are now a therapeutic standard in advanced non-small cell lung cancer (NSCLC), but strong predictive markers for ICIs efficacy are still lacking. We evaluated machine learning models built on simple clinical and biological data to individually predict response to ICIs.

Methods: Patients with metastatic NSCLC who received ICI in second line or later were included. We collected clinical and hematological data and studied the association of this data with disease control rate (DCR), progression free survival (PFS) and overall survival (OS). Multiple machine learning (ML) algorithms were assessed for their ability to predict response.

Results: Overall, 298 patients were enrolled. The overall response rate and DCR were 15.3% and 53%, respectively. Median PFS and OS were 3.3 and 11.4 months, respectively. In multivariable analysis, DCR was significantly associated with performance status (PS) and hemoglobin level (OR 0.58, p < 0.0001; OR 1.8, p < 0.001). These variables were also associated with PFS and OS and ranked top in random forest-based feature importance. Neutrophil-to-lymphocyte ratio was also associated with DCR, PFS and OS. The best ML algorithm was a random forest. It could predict DCR with satisfactory efficacy based on these three variables. Ten-fold cross-validated performances were: accuracy 0.68 ± 0.04, sensitivity 0.58 ± 0.08; specificity 0.78 ± 0.06; positive predictive value 0.70 ± 0.08; negative predictive value 0.68 ± 0.06; AUC 0.74 ± 0.03.

Conclusion: Combination of simple clinical and biological data could accurately predict disease control rate at the individual level.

Keywords: blood counts; lung cancer; machine learning; prediction; response; survival.

Figure 1

Exploratory data analysis. (A) Boxplots of continuous variables. (B) Barplots of categorical variables. BMI = body mass index, NLR = neutrophil-to-lymphocyte ratio, PLR = platelets-to-lymphocytes ratio, CR = complete response, PR = partial response, SD = stable disease and PD = progressive disease. Stars indicate statistical significance: **: p < 0.01, ***: p < 0.001, ****: p < 0.0001, n.s. = non-significant.

Figure 2

Variable selection. (A) Feature importance based on random forest classification and mean decrease in accuracy. (B) Accuracy score of incremental logistic regression models built on an increasing number of predictors (i.e., the first one contains only hemoglobin, the second hemoglobin and NLR, etc.). NLR = neutrophil-to-lymphocyte ratio. PLR = platelet-to-lymphocyte ratio. BMI = body mass index.

Figure 3

Machine learning algorithms predictive performances. (A) Receiver-operator curves for prediction on test sets from each fold of the outer cross-validation loop, for each model. AUC = area under the curve. (B) Precision (positive-predictive value)–recall (sensitivity) curves. (C) Main performance metrics for each algorithm. (D) Decision tree obtained after tuning and training. Each node shows: the predicted class (0 = PD, 1 = CR + PR + SD), the predicted probability of response and the percentage of total observations in the node.