A5082590468- Computational Drug Discovery Methods
- Pharmacovigilance and Adverse Drug Reactions
- AI in cancer detection
- Biomedical Text Mining and Ontologies
- Colorectal Cancer Screening and Detection
- Radiomics and Machine Learning in Medical Imaging
- Venous Thromboembolism Diagnosis and Management
- Acute Ischemic Stroke Management
- Machine Learning in Healthcare
- Shoulder Injury and Treatment
- Total Knee Arthroplasty Outcomes
- Topic Modeling
- Spectroscopy Techniques in Biomedical and Chemical Research
- Metabolomics and Mass Spectrometry Studies
- Machine Learning and Algorithms
- Image Processing Techniques and Applications
- Machine Learning and Data Classification
- Artificial Intelligence in Healthcare
- Acute Kidney Injury Research
- Plant-based Medicinal Research
- Drug-Induced Adverse Reactions
- Explainable Artificial Intelligence (XAI)
- Atrial Fibrillation Management and Outcomes
- Hepatitis C virus research
- Energy Load and Power Forecasting
China Pharmaceutical University
2015-2025
Zhejiang Lab
2023-2024
Tencent (China)
2024
Barro Colorado Island
2024
Guangxi Medical University
2010-2023
First Affiliated Hospital of GuangXi Medical University
2023
China United Network Communications Group (China)
2013-2022
Hunan University of Traditional Chinese Medicine
2021
Sichuan University of Science and Engineering
2021
Yibin University
2021
In this letter, a novel grasp detection neural network Squeeze-and-Excitation ResUNet (SE-ResUNet) is developed, where the residual block with channel attention integrated. The proposed framework can not only generate pose from RGB-D images, but also predict quality score of each pose. experimental results show that accuracy on Cornell dataset and Jacquard 98.2% 95.7%, respectively. And processing speed for images reach 30fps, which shows good real-time performance. comparison study, better...
We investigate the following data mining problem from computer-aided drug design: From a large collection of compounds, find those that bind to target molecule in as few iterations biochemical testing possible. In each iteration comparatively small batch compounds is screened for binding activity toward this target. employed so-called "active learning paradigm" Machine Learning selecting successive batches. Our main selection strategy based on maximum margin hyperplanegenerated by "Support...
We consider boosting algorithms that maintain a distribution over set of examples. At each iteration weak hypothesis is received and the updated. motivate these updates as minimizing relative entropy subject to linear constraints. For example AdaBoost constrains edge last w.r.t. updated be at most γ = 0. In some sense, "corrective" hypothesis. A cleaner method "totally corrective": edges all past hypotheses are constrained γ, where suitably adapted.Using new techniques, we prove same bounds...
Abstract Colorectal adenoma is a recognized precancerous lesion of colorectal cancer (CRC), and at least 80% cancers are malignantly transformed from it. Therefore, it essential to distinguish benign malignant adenomas in the early screening cancer. Many deep learning computational pathology studies based on whole slide images (WSIs) have been proposed. Most approaches require manual annotation regions WSIs, which time‐consuming labor‐intensive. This study proposes new approach, MIST –...
Altering a protein's function by changing its sequence allows natural proteins to be converted into useful molecular tools. Current protein engineering methods are limited lack of high throughput physical or computational tests that can accurately predict activity under conditions relevant final application. Here we describe new synthetic biology approach avoids these limitations combining gene synthesis with machine learning-based design algorithms.We selected 24 amino acid substitutions...
What is known and objective Drug-drug interactions (DDI) are frequent causes of adverse clinical drug reactions. Efforts have been directed at the early stage to achieve accurate identification DDI for safety assessments, including development in silico predictive methods. In particular, similarity-based methods developed assess with good accuracies, machine learning employed further extend range approaches. However, performance a method lower than expectations partly because use less...
Abstract Background Drug-induced interstitial lung disease (DIILD) is a severe adverse event leading to morbidity and mortality. This study evaluated the indicators of DIILD time-to-onset profiles following daily intake herbal drugs ( Scutellariae radix [“ogon” in Japanese], Bupleuri [“saiko” Pinelliae tuber [“hange” Japanese]) using Japanese Adverse Drug Event Report database. was defined accordance with Medical Dictionary for Regulatory Activities. Methods The database contained 830,079...
Background: Skin tumors affect many people worldwide, and surgery is the first treatment choice. Achieving precise preoperative planning navigation of intraoperative sampling remains a problem excessively reliant on experience surgeons, especially for Mohs malignant tumors. Materials Methods: To achieve sampling, we developed real-time augmented reality (AR) surgical system integrated with artificial intelligence (AI) to enhance three functions: AI-assisted tumor boundary segmentation,...
With the increasing variety of drugs, incidence adverse drug events (ADEs) is year by year. Massive numbers ADEs are recorded in electronic medical records and reaction (ADR) reports, which important sources potential ADR information. Meanwhile, it essential to make latent information automatically available for better postmarketing safety reevaluation pharmacovigilance.This study describes how identify ADR-related from Chinese ADE reports.Our established an efficient automated tool, named...
Oral anticoagulants (OAC) are essential in preventing stroke recurrence patients with ischemic (IS) and non-valvular atrial fibrillation (NVAF), though they carry a bleeding risk. Balancing the benefits risks of anticoagulant therapy determining optimal timing for initiation critical. This real-world study investigated OAC post-IS evaluated drug selection using data from National Health Medical Big Data (Eastern) Center, covering IS records 1564 hospitals Jiangsu (2018-2021). Using 1:1...