MenglinLu / Patient-representation-based-on-statistics
基于MIMICIII临床数据库,对传统基于简单统计特征的患者表示进行改进,使用遗传算法获取重要统计特征对患者进行表示,基于StackIng的模型Super Learner预测患者进入ICU24时后的死亡率,与包括疾病严重程度评分以及基于简单统计特征的患者表示构成的baseline进行对比,AUC平均提高0.05。
☆13Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for Patient-representation-based-on-statistics
- Using traditional machine learning and deep learning methods to predict stuff from TCGA pathology slides.☆18Updated 6 years ago
- ☆21Updated 3 years ago
- Radiomics Analysis for Prediction of EGFR Mutations and Ki-67 Proliferation Index in Patients with Non-Small Cell Lung Cancer☆14Updated 2 years ago
- ☆14Updated last year
- Multivariable Mendelian randomization to investigate the independent effects of smoking and alcohol on risk of head and neck cancer☆31Updated 4 years ago
- 🫀 Code for "Neural network-based integration of polygenic and clinical information: Development and validation of a prediction model for…☆13Updated 2 years ago
- We used different machine learning approaches to build models for detecting and visualizing important prognostic indicators of breast can…☆12Updated 4 years ago
- DCAP:Integrating multi-omics data with deep learning for predicting cancer prognosis