Research IT summer internship

An unexpected win during the pandemic

Research IT's first summer internship - in Big Data ML

Sep 17, 2021: Ms Sonam Welekar  joined us for a period of three months for an internship led by our NLP expert Dr. Jose Posada, now CS faculty in Universidad Del Norte in Barranquilla. We were delighted to be able to offer an internship, Research IT's first such offering, during the pandemic. 

Sonam took upon the task of a ML based re-classification of MyHealth messages.  MyHealth messages have exploded during the pandemic (100% increase in 2020 compared to 2019). Our physicians are seeing a deluge of text msgs in their inbox and they are spending 1-1.5 hrs everyday triaging/responding.  The current workflow classification of these messages e.g. patient advice or appointment request is imperfect. For example, when a patient asks for medical advice through a message, it is possible that at the same time she is asking for scheduling appointments also. Our physician community has expressed keen interest in AI based MyHealth msg classification to reduce the imperfection but to the best of our knowledge, no one had looked at the feasibility here before.

The dataset used for this research consisted of hospital-labeled (and de-identified with our TiDE pipeline) 45 million unique messages. The labeling represents whether the message belongs to categories such as scheduling requests, logistical, medical advice, medication renewal, and so forth. She used 140,000 messages for training the KNN classifier to classify messages in proper categories. The classifier was evaluated on 60,000 messages. Her research aimed to find the error rate in pre-labeled messages by performing an error analysis of the message classification model. The state-of-the-art Sentence BERT transformer from HuggingFace was used for text processing and feature extraction. From a scale perspective, this is by far the largest such study. She used our secure GCP workspace to do the analysis.

About Sonam Welekar

Sonam, a student at  San Jose State University MS CMPE program was one of ~650 applicants. We wish Sonam a wonderful career ahead.