Machine Learning-Assisted Recurrence Prediction for Patients With Early-Stage Non-Small-Cell Lung Cancer

Abstract

Purpose: Stratifying patients with cancer according to risk of relapse can personalize their care. In this work, we provide an answer to the following research question: How to use machine learning to estimate probability of relapse in patients with early-stage non-small-cell lung cancer (NSCLC)?

Materials and methods: For predicting relapse in 1,387 patients with early-stage (I-II) NSCLC from the Spanish Lung Cancer Group data (average age 65.7 years, female 24.8%, male 75.2%), we train tabular and graph machine learning models. We generate automatic explanations for the predictions of such models. For models trained on tabular data, we adopt SHapley Additive exPlanations local explanations to gauge how each patient feature contributes to the predicted outcome. We explain graph machine learning predictions with an example-based method that highlights influential past patients.

Results: Machine learning models trained on tabular data exhibit a 76% accuracy for the random forest model at predicting relapse evaluated with a 10-fold cross-validation (the model was trained 10 times with different independent sets of patients in test, train, and validation sets, and the reported metrics are averaged over these 10 test sets). Graph machine learning reaches 68% accuracy over a held-out test set of 200 patients, calibrated on a held-out set of 100 patients.

Conclusion: Our results show that machine learning models trained on tabular and graph data can enable objective, personalized, and reproducible prediction of relapse and, therefore, disease outcome in patients with early-stage NSCLC. With further prospective and multisite validation, and additional radiological and molecular data, this prognostic model could potentially serve as a predictive decision support tool for deciding the use of adjuvant treatments in early-stage lung cancer.

FIG 1.

Diagram representing the prediction pipeline from the database, through criteria and features, models training, features ablation, evaluation until predicting, and explaining. CHT-RT, chemotherapy-radiotherapy; SHAP, SHapley Additive exPlanations.

FIG 2.

Diagram of the clinical data modeled as a knowledge graph. ALK IHQ, anaplastic lymphoma kinase immunohistochemistry; ECOG, Eastern Cooperative Oncology Group; EGFR, epidermal growth factor receptor.

FIG 3.

Explanations provided by the pipeline for the two models for the same patient. (A) Tabular model with 75% accuracy, trained over 1,348 patients. SHAP explanation with a waterfall plot of features contributing to the prediction, red increasing the prediction score and blue decreasing. (B) Graph machine learning model with 68% accuracy trained over 1,348 patients. Example-based explanation. (1) Prediction summary for selected patients including predicted risk, number of similar examples, and number of training cases. (2) Retrieved exemplary cases, that is, influential patients. (3) Commonalities and differences between the patient being predicted and the selected influential patient retrieved by the example-based explanation method. (a) Venn diagram view. (b) Table view. AI, artificial intelligence; ECOG, Eastern Cooperative Oncology Group; COPD, chronic obstructive pulmonary disease; HTA, high blood pressure; SHAP, SHapley Additive exPlanations.