Could the underlying biological basis of prognostic radiomics and deep learning signatures be explored in patients with lung cancer? A systematic review

Abstract

Objectives: To summarize the underlying biological correlation of prognostic radiomics and deep learning signatures in patients with lung cancer and evaluate the quality of available studies.

Methods: This study examined databases including the PubMed, Embase, Web of Science Core Collection, and Cochrane Library, for studies that elaborated on the underlying biological correlation with prognostic radiomics and deep learning signatures based on CT or PET/CT for predicting the prognosis in patients with lung cancer. Information about the patient and radiogenomic analyses was extracted for the included studies. The Radiomics Quality Score (RQS) and the Prediction Model Risk of Bias Assessment Tool were used to assess the quality of these studies.

Results: Twelve studies were included with 7,338 patients from 2014 to 2022. All studies except for one were retrospective. Supervised machine learning was adopted in six studies, and the remaining used unsupervised machine learning methods. Gene sequencing and histopathological data were analyzed by 83.33% and 16.67% of the included studies, respectively. Gene set enrichment analysis and correlation analysis were most used to explore the biological meaning of prognostic signatures. The median RQS for supervised learning articles was 13.5 (range 12-19) and 7.0 (range 5-14) for unsupervised learning articles. The studies included in this report were assessed to have high risk of bias overall.

Conclusion: The biological basis for the interpretability of data-driven models mainly focused on genomics and histopathological factors, and it may improve the prognosis of lung cancer with more proper biological interpretation in the future.

Keywords: Biological meaning; Lung Neoplasms; Prognosis; Radiomics; Systematic review.