A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study

TL;DR

This paper introduces a hybrid CNN-RNN model for lung cancer survival analysis that outperforms human prediction and is validated on external data, enhancing early intervention strategies.

Contribution

The study develops and validates a novel hybrid CNN-RNN approach for survival prediction in lung cancer screening, integrating imaging and follow-up data.

Findings

Hybrid model achieves 0.76 AUC in mortality prediction.

Model outperforms human experts in cardiovascular mortality prediction.

Incorporating follow-up history improves survival prediction accuracy.

Abstract

In this study, we present a hybrid CNN-RNN approach to investigate long-term survival of subjects in a lung cancer screening study. Subjects who died of cardiovascular and respiratory causes were identified whereby the CNN model was used to capture imaging features in the CT scans and the RNN model was used to investigate time series and thus global information. The models were trained on subjects who underwent cardiovascular and respiratory deaths and a control cohort matched to participant age, gender, and smoking history. The combined model can achieve an AUC of 0.76 which outperforms humans at cardiovascular mortality prediction. The corresponding F1 and Matthews Correlation Coefficient are 0.63 and 0.42 respectively. The generalisability of the model is further validated on an 'external' cohort. The same models were applied to survival analysis with the Cox Proportional Hazard model. It was demonstrated that incorporating the follow-up history can lead to improvement in survival prediction. The Cox neural network can achieve an IPCW C-index of 0.75 on the internal dataset and 0.69 on an external dataset. Delineating imaging features associated with long-term survival can help focus preventative interventions appropriately, particularly for under-recognised pathologies thereby potentially reducing patient morbidity.