# An Integrated Clinical‐Radiomics‐Deep Learning Model Based on 18F‐FDG PET/CT for Predicting EGFR Mutation Status in Lung Adenocarcinoma

## TL;DR

This study developed a model combining clinical data, radiomic features, and deep learning to predict EGFR mutation status in lung cancer patients using PET/CT scans.

## Contribution

The novel contribution is the integration of clinical, radiomic, and deep learning features to improve EGFR mutation prediction accuracy.

## Key findings

- The CRD model achieved an AUC of 0.821, outperforming clinical and clinical-radiomics models.
- Calibration and decision curve analyses confirmed the model's robustness and clinical utility.
- A nomogram based on the CRD model enables individualized risk prediction of EGFR mutation.

## Abstract

An integrated model combining clinical variables, radiomic features, and deep learning was developed to predict EGFR mutation status in patients with lung adenocarcinoma based on pretreatment 18F‐FDG PET/CT imaging.

In this retrospective study, data from 218 patients—including PET/CT images, EGFR mutation status, and clinical characteristics—were analyzed. Three predictive models were constructed: a clinical model (C), a clinical‐radiomics model (CR), and a clinical‐radiomics‐deep learning model (CRD).

The CRD model integrated screened clinical features, as well as ConvNext‐based deep learning scores and radiomic scores selected via LASSO regression. It exhibited significantly superior predictive performance to the C model (AUC = 0.599; DeLong test: Z = –3.522, p < 0.001, corrected p = 0.001) and the CR model (AUC = 0.739; DeLong test: Z = –2.197, p = 0.028, corrected p = 0.028), with an AUC of 0.821 for the CRD model. Calibration curves and decision curve analysis confirmed its robustness and potential clinical benefit. A nomogram based on the CRD model was established, enabling individualized risk prediction of EGFR mutation.

This study highlights the potential of integrating clinical, radiomic, and deep learning features as a noninvasive approach for accurately predicting EGFR mutation status in lung adenocarcinoma.