healthcare-datasets

A platform for analysis & development of machine learning models using large de-identified healthcare datasets.

A sophisticated smart symptom search engine

A curated list of awesome open source healthcare tools, algorithms, datasets and research papers.

Code for WWW2019 paper "A Hierarchical Attention Retrieval Model for Healthcare Question Answering"

Power Pop Health is a collection of content intended to simplify the process of ingesting and prepping Healthcare Open Data using Azure data tools and Power BI. Moving forward the overarching theme will be data related to Population Health, but other sources pertinent to Healthcare will also be included.

Embedded Vision for Baby Behavior Monitoring in IoT

Create a model to assess the likelihood of a death by heart failure event. This can be used to help hospitals in assessing the severity of patients with cardiovascular diseases.

CMSC389I Fall 2018 @ UMD

Data Science tutorials authored by me. Will be updated as I create them/learn them!

This is a repository of links and files with citations of available datasets.

Short scripts to demonstrate data available from MolecularMatch API (api key needed). Data includes clinical trials, drugs, publications, molecular information, bioinformatics, report generation and more.

Synthetic health dataset generator

A data parsing script and API providing UK Dictionary of Medicines and Devices (DM+D) data linked to the Global Trade Identification Number (GTIN) of a product.

A self-driven project utilizing ARIMA, Seq2Seq, and XGBoost to help design the COVID19 forecasting algorithm. Data sources are from Kaggle Competition and JHU CSSE.

Collecting dutch healthcare related opendataset & analyzing important factors for NL coronovirus infected number

COVID Immunity anonymized testing results registered to the IPFS for public healthcare use.

Apply Data Analytics Techniques on Autism dataset to discover hidden patterns that would be leveraged in decision making.

Predicting the readmission of Diabetic patients using Machine Learning based on various factors.

The PMC is able to pull up a patient's past medication history in order to analyze whether a new medication will cause adverse interactions with current medication.

Catalogo Veneto Prescrivibile in formato SQL

Gather, share and discover using GitHub to design innovative digital health solutions.

Search the www.myhospitals.gov.au site for relevant hospital details

Correlation analysis project to examine whether the lower income neighborhood more likely to be infected with COVID-19 in NYC.

A Spring Boot Application with a Thymeleaf Frontend. Java + Spring Boot framework. MVC and Data transfer Object Design Pattern DTOD), Using an open-source REST client - Spring REST template.

Tools to pull care and quality information from CQC website

Process chest x-ray image data, varified and labeled by medical professionals. Using TensorFlow and the Keras API, create and validate convolution neural networks that learn to recognize the presence of pneumonia in the lungs.

In December 2020, I compiled COVID data from a few different publicly available sources as part of a term project for a class in the Health Informatics and Analytics MSc program at the Tufts University School of Medicine: HIA 217 Multivariable Data Analysis and Visualization. I created a dataset using Python, accessing COVID-19 case and location data through APIs from the US Census and the COVID Tracking Project, and then performed a variety of time-series analysis using linear regression, chi squared tests, and data visualization using Seaborn and Matplotlib in Python and Tableau.