A5085003054- Heart Failure Treatment and Management
- Cardiovascular Function and Risk Factors
- Ferroptosis and cancer prognosis
- Antiplatelet Therapy and Cardiovascular Diseases
- Gallbladder and Bile Duct Disorders
- Cardiovascular and exercise physiology
- Sepsis Diagnosis and Treatment
- Pancreatic and Hepatic Oncology Research
- Ovarian cancer diagnosis and treatment
- Traditional Chinese Medicine Studies
- Cardiac Imaging and Diagnostics
- Plant-based Medicinal Research
- Transplantation: Methods and Outcomes
- RNA modifications and cancer
- Mechanical Engineering and Vibrations Research
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Ginseng Biological Effects and Applications
- Artificial Intelligence in Healthcare
- Cardiac Health and Mental Health
- Cancer, Lipids, and Metabolism
- Renal Transplantation Outcomes and Treatments
- Cancer Immunotherapy and Biomarkers
- Organ Transplantation Techniques and Outcomes
- Machine Learning in Healthcare
University of Electronic Science and Technology of China
2022-2024
Tianjin Medical University
2022
There is a lack of tools for accurately identifying the risk readmission heart failure in elderly patients with arrhythmia. The aim this study was to establish and compare performance LACE [length stay ('L'), acute (emergent) admission ('A'), Charlson comorbidity index ('C') visits emergency department during previous 6 months ('E')] machine learning predicting 1 year
Background Short-term unplanned readmission is always neglected, especially for elderly patients with coronary heart disease (CHD). However, tools to predict are lacking. This study aimed establish the most effective predictive model 7-day in CHD using machine learning (ML) algorithms. Methods The detailed clinical data of were collected retrospectively. Five ML algorithms, including extreme gradient boosting (XGB), random forest, multilayer perceptron, categorical boosting, and logistic...
WHAT'S NEW?Few studies evaluated the readmissions for elderly patients with ischemic heart disease.Therefore, we developed a predictive model based on machine learning.The results showed that categorical boosting had better performance and good calibration in identifying 30-day 1-year disease.Meanwhile, found age-adjusted Charlson comorbidity index, brain natriuretic peptide, failure, cholesterol, free thyroxine, thymidine kinase 1, osmotic pressure red blood cell distribution width-standard...
This study aims to establish multiple ML models and compare their performance in predicting tacrolimus concentration for infant patients who received LDLT within 3 months after transplantation.Retrospectively collected basic information relevant biochemical indicators of included patients. CMIA was used determine C0 . PCR the donors' recipients' CYP3A5 genotypes. Multivariate stepwise regression analysis elimination covariates were selection. Thirteen machine learning algorithms applied...
Objective This study aimed to develop an adverse drug reactions (ADR) antecedent prediction system using machine learning algorithms provide the reference for security usage of Chinese herbal injections containing Panax notoginseng saponin in clinical practice. Design A nested case–control study. Setting National Center ADR Monitoring and Electronic Medical Record (EMR) system. Participants All patients were from five medical institutions Sichuan Province January 2010 December 2018. Main...
Exercise rehabilitation can improve the prognosis of patients with coronary heart disease. However, a bibliometric analysis global exercise for disease (CHD) research topic is lacking. This study investigated development trends and hotspots in field rehabilitation. CiteSpace software was used to analyze literature on therapy CHD Web Science Core Collection database. We analyzed data countries/institutions, journals, authors, keywords, cited references. A total 3485 peer-reviewed papers were...
This study aimed to develop and validate clinical nomograms for predicting progression-free survival (PFS) overall (OS) in unresectable ICC patients.
Background: Readmission of elderly angina patients has become a serious problem, with dearth available prediction tools for readmission assessment. The objective this study was to develop machine learning (ML) model that can predict 180-day all-cause patients. Methods: clinical data retrospectively collected. Five ML algorithms were used models. Area under the receiver operating characteristic curve (AUROC), area precision recall (AUPRC), and Brier score applied assess predictive...