A5008151644- Biomedical and Engineering Education
- Venous Thromboembolism Diagnosis and Management
- Antiplatelet Therapy and Cardiovascular Diseases
- Atrial Fibrillation Management and Outcomes
- Artificial Intelligence in Healthcare and Education
- Explainable Artificial Intelligence (XAI)
- Gene expression and cancer classification
- Adversarial Robustness in Machine Learning
- AI in cancer detection
- Trauma and Emergency Care Studies
- Traumatic Brain Injury and Neurovascular Disturbances
- Cancer-related molecular mechanisms research
- Artificial Intelligence in Healthcare
- Animal Virus Infections Studies
- MicroRNA in disease regulation
- Sepsis Diagnosis and Treatment
- Bioinformatics and Genomic Networks
- Advanced Neural Network Applications
University of Pittsburgh
2024-2025
University of Wyoming
2021
Shiraz University of Medical Sciences
2019
Predicting major bleeding in non-valvular atrial fibrillation (AF) patients on direct oral anticoagulants (DOACs) is crucial for personalized care. Alternatives like left appendage closure devices lower stroke risk with fewer non-procedural bleeds. This study compares machine learning (ML) models conventional scores (HAS-BLED, ORBIT, and ATRIA) predicting events requiring hospitalization AF DOACs at their index cardiologist visit. retrospective cohort used electronic health records from...
Traumatic brain injury (TBI), which occurs commonly worldwide, is among the more costly of health and socioeconomic problems. Accurate prediction favorable outcomes in severe TBI patients could assist with optimizing treatment procedures, predicting clinical outcomes, result substantial economic savings.In this study, we examined capability a machine learning-based model "favorable" or "unfavorable" after 6 months using only parameters measured on admission. Three models were developed...
Background: Breast cancer is the most common type of amongst women worldwide. Considering its high incidence, effective detection and prognosis this may have a significant effect on reducing expenditures. In study, we propose model to predict 60-month survivability in patients with breast investigate effects each feature obtained model. Methods: We base information gathered by Disease Research Center, Shiraz University Medical Sciences, Shiraz, Iran from 5673 cancer. The goal study was at...
Three important criteria of existing convolutional neural networks (CNNs) are (1) test-set accuracy; (2) out-of-distribution and (3) explainability. While these have been studied independently, their relationship is unknown. For example, do CNNs that a stronger performance also explainability? Furthermore, most prior feature-importance studies only evaluate methods on 2-3 common vanilla ImageNet-trained CNNs, leaving it unknown how generalize to other architectures training algorithms. Here,...
Accurately predicting major bleeding events in non-valvular atrial fibrillation (AF) patients on direct oral anticoagulants (DOACs) is crucial for personalized treatment and improving patient outcomes, especially with emerging alternatives like left appendage closure devices. The devices reduce stroke risk comparably but significantly fewer non-procedural events.
To challenge clinicians and informaticians to learn about potential sources of bias in medical machine learning models through investigation data predictions from an open-source severity illness score.
Comparison of gene expression algorithms may be beneficial for obtaining disease pattern or grouping patients based on the profile. The current study aimed to investigate whether knowledge within these data is able group ovarian cancer with similar pattern.Four different clustering methods were applied 20 genes 37 women cancer. All selected in this had prominent roles control activity immune system, as well chemotaxis, angiogenesis, apoptosis, and etc. such K-means, Hierarchical,...