Deep learning predicts immune checkpoint inhibitor-related pneumonitis from pretreatment computed tomography images

Abstract

Immune checkpoint inhibitors (ICIs) have revolutionized the treatment of lung cancer, including both non-small cell lung cancer and small cell lung cancer. Despite the promising results of immunotherapies, ICI-related pneumonitis (ICIP) is a potentially fatal adverse event. Therefore, early detection of patients at risk for developing ICIP before the initiation of immunotherapy is critical for alleviating future complications with early interventions and improving treatment outcomes. In this study, we present the first reported work that explores the potential of deep learning to predict patients who are at risk for developing ICIP. To this end, we collected the pretreatment baseline CT images and clinical information of 24 patients who developed ICIP after immunotherapy and 24 control patients who did not. A multimodal deep learning model was constructed based on 3D CT images and clinical data. To enhance performance, we employed two-stage transfer learning by pre-training the model sequentially on a large natural image dataset and a large CT image dataset, as well as transfer learning. Extensive experiments were conducted to verify the effectiveness of the key components used in our method. Using five-fold cross-validation, our method accurately distinguished ICIP patients from non-ICIP patients, with area under the receiver operating characteristic curve of 0.918 and accuracy of 0.920. This study demonstrates the promising potential of deep learning to identify patients at risk for developing ICIP. The proposed deep learning model enables efficient risk stratification, close monitoring, and prompt management of ICIP, ultimately leading to better treatment outcomes.

Common methodological pitfalls in ICI pneumonitis risk prediction studies

“…2/50 studies additionally developed a risk prediction model after risk factor identification from clinical data ( 10 , 11 ). The remaining study focused on risk prediction model development (with clinical and imaging data) and did not investigate the significance of individual risk factors ( 12 ).…”

“…A total of 3 studies attempted to develop risk prediction models ( 10 – 12 ). All of them focused on any-grade ICI pneumonitis and used data collected from the their authors’ affiliated institutions, which were all in China ( Figure 2A ).…”

“…A meta-analysis published in 2022 summarized the odds ratios from 35 studies between 2000 and 2022 and identified several risk factors that have significant pooled effect ( Table 1 ) ( 8 ). Three studies aimed at building risk prediction models for ICI pneumonitis in human were also published in the same year ( 10 – 12 ). Chao et al.…”

“…In contrast, Tan et al. trained a deep neural network on 48 subjects to combine pre-ICI imaging and clinical data, which represents the first application of modern machine learning techniques for ICI pneumonitis risk prediction ( 12 ).…”

Advances in CT features and radiomics of checkpoint inhibitor-related pneumonitis: A short review

“…Finally, contrast learning was used to mine high-performance imaging feature models. Using five-fold cross-validation, the model was able to accurately predict CIP patients and non-ICIP patients with an AUC of 0.918 and an accuracy of 0.920 ( 23 ). This study strongly indicates that deep learning has great potential for identifying patients at risk of developing CIP.…”