Deep-learning-based survival prediction of patients with cutaneous malignant melanoma

Abstract

BackgroundThis study obtained data on patients with cutaneous malignant melanoma (CMM) from the Surveillance, Epidemiology, and End Results (SEER) database, and used a deep learning and neural network (DeepSurv) model to predict the survival rate of patients with CMM and evaluate its effectiveness.MethodsWe collected information on patients with CMM between 2004 and 2015 from the SEER database. We then randomly divided the patients into training and testing cohorts at a 7:3 ratio. The likelihood that patients with CMM will survive was forecasted using the DeepSurv model, and its results were compared with those of the Cox proportional-hazards (CoxPH) model. The calibration curves, time-dependent area under the receiver operating characteristic curve (AUC), and concordance index (C-index) were used to assess the prediction abilities of the model.ResultsThis study comprised 37,758 patients with CMM: 26,430 in the training cohort and 11,329 in the testing cohort. The CoxPH model demonstrated that the survival of patients with CMM was significantly influenced by age, sex, marital status, summary stage, surgery, radiotherapy, chemotherapy, postoperative lymph node dissection, tumor size, and tumor extension. The C-index of the CoxPH model was 0.875. We also constructed the DeepSurv model using the data from the training cohort, and its C-index was 0.910. We examined how well the aforementioned two models predicted outcomes. The 1-, 3-, and 5-year AUCs were 0.928, 0.837, and 0.855, respectively, for the CoxPH model, and 0.971, 0.947, and 0.942 for the DeepSurv model. The DeepSurv model presented a greater predictive effect on patients with CMM, and its reliability was better than that of the CoxPH model according to both the AUC value and the calibration curve.ConclusionThe DeepSurv model, which we developed based on the data of patients with CMM in the SEER database, was found to be more effective than the CoxPH model in predicting the survival time of patients with CMM.

Interpreting Machine Learning Models for Survival Analysis: A Study of Cutaneous Melanoma Using the SEER Database

“…The values obtained are 0.787, 0.798 0.796 and 0.802 for the CoxPH, RSF, DeepSurv and DeepHit respectively. In [12], the c-index of CoxPH and DeepSurv are better than ours, being 0.875 and 0.91 respectively. The difference could be explained due to the variation of the data between both data extraction processes.…”

“…Following the same selection criteria as in [12], we obtain the baseline dataset, which contains 34929 individuals. Table 1 describes all the criteria applied to obtain it.…”

“…The test dataset is hidden to account for the final metrics. Since SEER database is updated periodically, the number of individuals may vary across data extraction processes (note that the number of individuals obtained in [12] is equal to 37758, where 26430 individuals are part of the training dataset and 11329 are part of the test dataset).…”

“…An example of this fact is a recent work [12] where the authors use a deep learning model which overtakes the CoxPH model, using the Surveillance, Epidemiology, and End Results database [8] (SEER) to model the cutaneous malignant melanoma. The authors use the CoxPH model, which provides a c-index of 0.875 and train a DeepSurv neural network which achieves a c-index of 0.91.…”

Comparison of deep learning‐based recurrence‐free survival with random survival forest and Cox proportional hazard models in Stage‐I NSCLC patients

“…While She et al, 22 focused on a comprehensive analysis of consecutive cases involving newly diagnosed Stages I–IV NSCLC, our study specifically concentrated on patients within Stage I. In their recent study, Yu et al, 23 acquired patient data concerning cutaneous malignant melanoma (CMM) from the Surveillance, Epidemiology, and End Results database. They employed DeepSurv model to forecast the survival rates of CMM patients and assess the model's efficacy.…”