Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy

Abstract

(1) Background: In advanced non-small cell lung cancer (aNSCLC), programmed death ligand 1 (PD-L1) remains the only biomarker for candidate patients to immunotherapy (IO). This study aimed at using artificial intelligence (AI) and machine learning (ML) tools to improve response and efficacy predictions in aNSCLC patients treated with IO. (2) Methods: Real world data and the blood microRNA signature classifier (MSC) were used. Patients were divided into responders (R) and non-responders (NR) to determine if the overall survival of the patients was likely to be shorter or longer than 24 months from baseline IO. (3) Results: One-hundred sixty-four out of 200 patients (i.e., only those ones with PD-L1 data available) were considered in the model, 73 (44.5%) were R and 91 (55.5%) NR. Overall, the best model was the linear regression (RL) and included 5 features. The model predicting R/NR of patients achieved accuracy ACC = 0.756, F1 score F1 = 0.722, and area under the ROC curve AUC = 0.82. LR was also the best-performing model in predicting patients with long survival (24 months OS), achieving ACC = 0.839, F1 = 0.908, and AUC = 0.87. (4) Conclusions: The results suggest that the integration of multifactorial data provided by ML techniques is a useful tool to select NSCLC patients as candidates for IO.

Multi-Omics Approaches for the Prediction of Clinical Endpoints after Immunotherapy in Non-Small Cell Lung Cancer: A Comprehensive Review

“…Interestingly, high ICI scores were associated with the activation of the T-cell and B-cell receptor signaling pathways and natural killer cell–mediated cytotoxicity. Using RNA expression levels and a machine learning approach, gene expression levels were proven to be superior and independent or complementary from PD-L1 expression [ 75 , 76 ]. When developing predictive models, SCC and ADK are often considered together.…”

Application of several machine learning algorithms for the prediction of afatinib treatment outcome in advanced‐stage EGFR‐mutated non‐small‐cell lung cancer

“…The sequential minimal optimization algorithm, invented by John Platt, was applied to the SVM, (6) boosting is an ensemble meta-algorithm that combines several rough and moderately inaccurate models. The C50 R package contains the C5.0 classification model, which was used to optimize the predictive value with 100 trials of boosting interactions, (7) bagging, also known as bootstrap aggregation, is another ensemble meta-algorithm. This algorithm reduces the variance within a noisy dataset.…”

“…Another study, combining four clinical and 40 radiomic features, suggested the role of the ML approach in identifying the histologic subtypes of lung cancer 6 . The ML algorithm may also help clinicians select appropriate candidates for immune checkpoint inhibitors 7 . In terms of risk stratification, an ML model that derived 34 features predicted recurrence and overall survival (OS) more accurately compared to the TNM staging system 8 …”

“… 6 The ML algorithm may also help clinicians select appropriate candidates for immune checkpoint inhibitors. 7 In terms of risk stratification, an ML model that derived 34 features predicted recurrence and overall survival (OS) more accurately compared to the TNM staging system. 8 …”

“…6 The ML algorithm may also help clinicians select appropriate candidates for immune checkpoint inhibitors. 7 In terms of risk stratification, an ML model that derived 34 features predicted recurrence and overall survival (OS) more accurately compared to the TNM staging system. 8 This study aimed to evaluate the performance of several ML algorithms in predicting the outcome of afatinib treatment in patients with advanced EGFR-mutated NSCLC in South Korea, using data collected from multiple medical centers.…”