I created Clinicle, a Wordle like medical semantic guessing game. Let me know what you think!

• clinical_embeddings

  2 14 10.0 Jupyter Notebook

  Pre-trained word embeddings using the text of published clinical case reports.

Yup. I use Python. I initially attempted to create my own language model and create my own embeddings, but my single NVIDIA GPU couldn't handle the volume. Instead, I found several great papers and github repos of previously developed medical concept embeddings. I ultimately used the Penn BioBERT Embeddings developed by the Weissman lab at the University of Pennsylvania. They used several approaches (word2vec, fastText, GloVe) trained on either 1. OpenAccess case reports only or 2. all OpenAccess publications. The best performing one for my use case was a 600-parameter word2vec model trained on OpenAccess case reports alone.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project