ABSTRACT
Background: Nivolumab is a human monoclonal antibody against programmed death-1 (PD-1) that blocks interactions of PD-1 with both PD-L1 and PD-L2 and upregulates tumor antigen-specific T cell to develop appropriate immune response against cancer cells. It has been approved by the US Food and Drug Administration (FDA) in the treatment of various malignancies including Hodgkin lymphoma (HL). Case Description: Our patient is a 75-year-old man diagnosed with nodular sclerosis HL. After relapse of disease on several lines of treatment including autologous stem cell transplant, Nivolumab was started as part of a clinical trial. Partial response (PR) was noted on nivolumab for a few years which was eventually discontinued due to disease progression. A few weeks later, the patient was noted to have a suspicious lesion on the right earlobe and another on the base of the tongue, which were pathologically diagnosed as Merkel cell carcinoma (MCC) and oropharyngeal squamous cell carcinoma (SCC), respectively. Conclusions: Immune checkpoint inhibitors (ICIs) like nivolumab have demonstrated anti-tumor efficacy in several cancers to date. We describe here a unique observation of nivolumab suppressing the growth of two separate malignancies apart from the primary malignancy, discontinuation of which has then contributed to their growth and subsequent diagnosis. Our case report showcases the broad activity of ICIs and brings attention to the possibility of uncovering new malignancies after discontinuation of ICIs in high-risk patients.
ABSTRACT
Background: Numerous deep learning-based survival models are being developed for various diseases, but those that incorporate both deep learning and transfer learning are scarce. Deep learning-based models may not perform optimally in real-world populations due to variations in variables and characteristics. Transfer learning, on the other hand, enables a model developed for one domain to be adapted for a related domain. Our objective was to integrate deep learning and transfer learning to create a multivariable survival model for lung cancer. Methods: We collected data from 601,480 lung cancer patients in the Surveillance, Epidemiology, and End Results (SEER) database and 4,512 lung cancer patients in the First Affiliated Hospital of Guangzhou Medical University (GYFY) database. The primary model was trained with the SEER database, internally validated with a dataset from SEER, and externally validated through transfer learning with the GYFY database. The performance of the model was compared with a traditional Cox model by C-indexes. We also explored the model's performance in the setting of missing data and generated the artificial intelligence (AI) certainty of the prediction. Results: The C-indexes in the training dataset (SEER full sample) with DeepSurv and Cox model were 0.792 (0.791-0.792) and 0.714 (0.713-0.715), respectively. The values were 0.727 (0.704-0.750) and 0.692 (0.666-0.718) after applying the trained model in the test dataset (GYFY). The AI certainty of the DeepSurv model output was from 0.98 to 1. For transfer learning through fine-tuning, the results showed that the test set could achieve a higher C-index (20% vs. 30% fine-tuning data) with more fine-tuning dataset. Besides, the DeepSurv model was more accurate than the traditional Cox model in predicting with missing data, after random data loss of 5%, 10%, 15%, 20%, and median fill-in missing values. Conclusions: The model outperformed the traditional Cox model, was robust with missing data and provided the AI certainty of prediction. It can be used for patient self-evaluation and risk stratification in clinical trials. Researchers can fine-tune the pre-trained model and integrate their own database to explore other prognostic factors.
