Prognostic difference between surgery and external radiation in patients with stage I liver cancer based on competitive risk model and conditional survival rate.

PURPOSE: This study aimed to assess the difference in prognosis of patients with early-stage liver cancer after surgery or external radiation. METHODS: Between 2010 and 2015, 2155 patients with AJCC 7th stage I liver cancer were enrolled in the SEER database. Among these, 1972 patients had undergone surgery and 183 had undergone external beam radiation. The main research endpoints were overall survival (OS) and disease-specific survival (DSS). The competitive risk model was used to calculate the risk ratio of liver cancer-specific deaths when there was a competitive risk. Propensity Score Matching (PSM) method using a 1:1 ratio was used to match confounders such as sex, age, and treatment method. Conditional survival was dynamically assessed for patient survival after surgery or external radiation. RESULTS: Multivariate analysis of the competitive risk model showed that age, disease diagnosis time, grade, and treatment [surgery and external beam radiation therapy (EBRT)] were independent prognostic factors for patients with hepatocellular carcinoma. Surgery had a higher survival improvement rate than that of EBRT. As the survival of patients with liver cancer increased, the survival curve of surgery declined more slowly than that of radiotherapy patients and stabilized around 3 years after surgery. The survival curve of radiotherapy patients significantly dropped within 4 years and then stabilized. CONCLUSION: Surgery was better than EBRT for patients with stage I liver cancer. Close follow-up was required for 3 years after surgery or 4 years after external radiation. This study can help clinicians make better informed clinical decisions.

Cooperative dual medical ontology representation learning for clinical assisted decision-making.

OBJECTIVE: Predicting clinical events and providing assisted decision-making using Electronic Health Records (EHRs) play a central role in personalized healthcare. Despite the promising performance achieved for diagnosis and procedure predictions, most of the existing predictive models regard different medical codes as the same type and generally ignore the dependence between diagnoses and procedures in patients' admission history. To address these issues, we propose an end-to-end cooperative dual medical ontology representation learning framework for clinical assisted decision-making. MATERIALS AND METHODS: The framework consists of two primary modules: (1) dual medical ontology representation learning to facilitate the learning of medical concepts and (2) task dependent multi-task prediction to capture the correlation between diagnoses and procedures in patients' admission history. We evaluate our method with EHRs from the MIMIC-III Clinical Database, covering 6321 patients and 16335 visits. RESULTS: Experiments conducted on the MIMIC-III dataset show that the proposed model achieves the best performance, with a top-20 accuracy of 58.20% for diagnosis prediction and a top-20 accuracy of 75.85% for procedure prediction. In addition, a series of experimental analyses and case studies further illustrate the excellent performance of our model. CONCLUSION: We propose an end-to-end cooperative dual medical ontology representation learning framework, which achieves superior performance on multi-task diagnosis and procedure predictions. The source code is available at https://github.com/mhxu1998/CoDMO.

CED: A case-level explainable paramedical diagnosis via AdaGBDT.

OBJECTIVE: The rapid growth of medical data has greatly promoted the wide exploitation of machine learning for paramedical diagnosis. Inversely proportional to their performance, most machine learning models generally suffer from the lack of explainability, especially the local explainability of the model, that is, the case-specific explainability. MATERIALS AND METHODS: In this paper, we proposed a GBDT (Gradient Boosting Decision Tree)-based explainable model for case-specific paramedical diagnostics, and mainly make the following contributions: (1) an adaptive gradient boosting decision tree (AdaGBDT) model is proposed to boost the path-mining for decision effectively; (2) to learn a case-specific feature importance embedding for a specific patient, the bi-side mutual information is applied to characterize the backtracking on the decision path; (3) through the collaborative decision-making by globally explainable AdaGBDT with case-based reasoning (CBR) in the case-specific metric space, some hard cases can be identified by the means of visualized interpretation. The performance of our model is evaluated on the Wisconsin diagnostic breast cancer dataset and the UCI heart disease dataset. RESULTS: Experiments conducted on two datasets show that our AdaGBDT achieves the best performance, with the F1-value of 0.9647 and 0.8405 respectively. Moreover, a series of experimental analyses and case studies further illustrate the excellent performance of feature importance embedding. CONCLUSION: The proposed case-specific explainable paramedical diagnosis via AdaGBDT has excellent predictive performance, with both promising case-level and consistent global explainability.