Hak Jin Kim

Deep Learning-Based Dynamic Risk Prediction of Venous Thromboembolism for Patients With Ovarian Cancer in Real-World Settings From Electronic Health Records

PURPOSE Patients with epithelial ovarian cancer (EOC) have an elevated risk for venous thromboembolism (VTE). To assess the risk of VTE, models were developed by statistical or machine learning algorithms. However, few models have accommodated deep learning (DL) algorithms in realistic clinical settings. We aimed to develop a predictive DL model, exploiting rich information from electronic health records (EHRs), including dynamic clinical features and the presence of competing risks. METHODS We extracted EHRs of 1,268 patients diagnosed with EOC from January 2007 through December 2017 at the National Cancer Center, Korea. DL survival networks using fully connected layers, temporal attention, and recurrent neural networks were adopted and compared with multi-perceptron–based classification models. Prediction accuracy was independently validated in the data set of 423 patients newly diagnosed with EOC from January 2018 to December 2019. Personalized risk plots displaying the individual interval risk were developed. RESULTS DL-based survival networks achieved a superior area under the receiver operating characteristic curve (AUROC) between 0.95 and 0.98 while the AUROC of classification models was between 0.85 and 0.90. As clinical information benefits the prediction accuracy, the proposed dynamic survival network outperformed other survival networks for the test and validation data set with the highest time-dependent concordance index (0.974, 0.975) and lowest Brier score (0.051, 0.049) at 6 months after a cancer diagnosis. Our visualization showed that the interval risk fluctuating along with the changes in longitudinal clinical features. CONCLUSION Adaption of dynamic patient clinical features and accounting for competing risks from EHRs into the DL algorithms demonstrated VTE risk prediction with high accuracy. Our results show that this novel dynamic survival network can provide personalized risk prediction with the potential to assist risk-based clinical intervention to prevent VTE among patients with EOC.

Incidence of venous thromboembolism after standard treatment in patients with epithelial ovarian cancer in Korea

AbstractBackgroundVenous thromboembolism (VTE) is a hospital‐associated severe complication that may adversely affect patient prognosis. In this study, we evaluated the incidence of VTE and its risk factors in patients with epithelial ovarian cancer (EOC).MethodsWe retrospectively analyzed the electronic health record data of 1268 patients with EOC who received primary treatment at the National Cancer Center, Korea between January 2007 and December 2017 to identify patients who developed VTE. Demographic, clinical, and surgical characteristics of these patients were ascertained. Competing risks analyses were performed to estimate the cumulative incidence of VTE according to the treatment type. The associations between putative risk factors and the incidence of VTE were evaluated using the Fine–Gray regression models accounting for competing risks of death.ResultsVTE was the most prevalent cardiovascular event, found in 9.6% (n = 122) of all patients. Of these VTE events, 115 (94.3%) occurred within 2 years of EOC diagnosis. Advanced cancer stage at diagnosis (distant vs. localized, hazards ratio [HR])= 14.49, p = 0.015) and extended hospital stay (≥15 days, HR =3.87, p = 0.004) were associated with the incidence of VTE. There was no significant difference in the cumulative incidence of VTE between primary cytoreductive surgery followed by adjuvant chemotherapy and neoadjuvant chemotherapy followed by interval cytoreductive surgery (HR =0.81, p = 0.390).ConclusionsApproximately 10% of patients with EOC were diagnosed with VTE, which was the most common cardiovascular disease found in this study. The assessment of VTE risks in patients with advanced‐stage EOC with an extended hospital stay is needed to facilitate adequate prophylactic treatment.