Segmentation of patients with small cell lung cancer into responders and non-responders using the optimal cross-validation technique

TL;DR

This paper introduces a new machine learning method to better classify small cell lung cancer patients into responders and non-responders, improving treatment decisions.

Contribution

A novel data-driven cutoff selection method using optimal cross-validation for patient segmentation in cancer treatment.

Findings

The novel method produced significantly different survival outcomes between responders and non-responders (p-value 0.009).

The standard cutoff of 0.5 failed to show significant survival differences (p-value 0.194).

The new method outperformed traditional approaches in segmenting patients for treatment decisions.

Abstract

The timing of treating cancer patients is an essential factor in the efficacy of treatment. So, patients who will not respond to current therapy should receive a different treatment as early as possible. Machine learning models can be built to classify responders and nonresponders. Such classification models predict the probability of a patient being a responder. Most methods use a probability threshold of 0.5 to convert the probabilities into binary group membership. However, the cutoff of 0.5 is not always the optimal choice.

In this study, we propose a novel data-driven approach to select a better cutoff value based on the optimal cross-validation technique. To illustrate our novel method, we applied it to three clinical trial datasets of small-cell lung cancer patients. We used two different datasets to build a scoring system to segment patients. Then the models were applied to segment patients into the test data.

We found that, in test data, the predicted responders and non-responders had significantly different long-term survival outcomes. Our proposed novel method segments patients better than the standard approach using a cutoff of 0.5. Comparing clinical outcomes of responders versus non-responders, our novel method had a p-value of 0.009 with a hazard ratio of 0.668 for grouping patients using the Cox proportion hazard model and a p-value of 0.011 using the accelerated failure time model which approved a significant difference between responders and non-responders. In contrast, the standard approach had a p-value of 0.194 with a hazard ratio of 0.823 using the Cox proportion hazard model and a p-value of 0.240 using the accelerated failure time model indicating the responders and non-responders do not differ significantly in survival.

In summary, our novel prediction method can successfully segment new patients into responders and non-responders. Clinicians can use our prediction to decide if a patient should receive a different treatment or stay with the current treatment.

The online version contains supplementary material available at 10.1186/s12874-024-02185-7.

Figures