| | | 20,000+ Fresh Resumes Monthly | |
|
|
| |
Click here or scroll down to respond to this candidateCandidate's Name
Indianapolis, IN PHONE NUMBER AVAILABLEEMAIL AVAILABLEProfessional SummaryEnthusiastic and detail-oriented Health Care Data Analyst with a strong passion for leveraging data to improve healthcare outcomes.EducationIndiana University - Indianapolis, INMasters in Health InformaticsSRM Institute of Technology - Chennai, IndiaBachelor of Dental SurgerySkillsLanguages: Python, SQL, R, HTML, CSSTools: PowerBI, Excel, MySQLPlatforms: PyCharm, Jupyter, Visual Studio CodeWork HistoryGraduate Research Assistant 01/2024 to 05/2024Luddy School of Informatics, Indiana University - Indianapolis, IN Conducted comprehensive research on more than 300 current AI technologies in mental health, specifically focusing on applications for dementia, anxiety, and depression. Analyzed extensive datasets from mental health studies to evaluate the effectiveness of existing robotic AI solutions. Identified patterns and trends in data related to patient outcomes. Prepared detailed reports and visualizations to communicate findings and recommendations to stakeholders. Professional ProjectsUtilizing Language Models to Predict Drug-Target Interactions Developed a Siamese Neural Network model to predict drug-target interactions, leveraging SMILES for drug encoding and single-letter amino acid representation for proteins. Integrated and preprocessed datasets (DAVIS, BindingDB, BIOSNAP), developed and trained the model using Python and PyTorch on an NVIDIA Tesla V100 GPU, evaluated model performance using AUROC and AUPRC metrics, analyzed results, and prepared comprehensive reports. Achieved superior AUPRC metrics in Cold Drug, Cold Target, and Cold Binding scenarios and com- petitive AUROC scores compared to the DLM-DTI model. Technologies: PyTorch, NVIDIA Tesla V100 GPU, SMILES, ChemBERTa, ProtBERT, datasets from DAVIS, BindingDB, and BIOSNAP.Comprehensive Predictive Modeling in Healthcare Developed advanced predictive models for various healthcare domains, including autism spectrum disorder(ASD), homicide data analysis, and Alzheimers disease stage classification. Utilized Logistic Regression, SVM, KNN, Random Forest, and Decision Tree Classifiers, achieving high predictive accuracies: 99 Technologies: Google Colab, Jupyter, MATLAB, Seaborn, TensorFlow, Python, Scikit-Learn, Pandas, and NumPy.Machine Learning Project: Predicting Diabetes Status Analyzed lab results from Iraqi patients using 12 machine learning models. Top performers were Random Forest, XGBoost, and Bagging Classifier, achieving 99 Employed statistical methods and non-parametric testing to identify influential factors for diabetes. Technologies: Google Colab, Jupyter, MATLAB, Seaborn, TensorFlow, Python, RStudio, Data Visualiza- tion.1 |
