AI for Care Planning Support
AI for Care Planning Support

Abstract: 

Effective care planning requires care managers to understand patient health status and needs in order to deliver appropriate patient support via outreach, assessment, education, coaching, and behavioral and social service referrals. The proliferation of healthcare data across the care continuum, including massive volumes of clinical free text documents, creates a significant challenge for individual care managers, but a major opportunity for advanced clinical analytics. Novel Artificial Intelligence (AI)-driven solutions can help optimize care planning, reducing inefficiency and increasing focus on the most salient information, leading to improved patient outcomes while lowering administrative costs. In recent years, deep learning techniques have demonstrated superior performance over traditional machine learning (ML) techniques for various general-domain natural language processing (NLP) tasks, e.g., language modeling, parts-of-speech (POS) tagging, named entity recognition, paraphrase identification, sentiment analysis, and text summarization. Clinical documents pose unique challenges compared to general-domain text due to the widespread use of acronyms and non-standard clinical jargon, inconsistent data structure and organization, redundancy of data across limited interoperable tools, and the requirement for rigorous de-identification and anonymization to ensure patient data privacy. In this talk, I will present a brief overview of deep learning and its applications to NLP problems in general, followed by several deep learning-based clinical natural language processing use cases developed in our organization as part of the advanced care planning initiatives.

Bio: 

Sadid Hasan is the Senior Director of Artificial Intelligence at CVS Health, where he leads the team responsible for Aetna’s AI-based clinical care initiatives. Prior to CVS Health, he was the Technical Lead of the AI Group at Philips Research, where his work focused on solving various clinical Natural Language Processing (NLP) problems with Deep Learning. Previously, Sadid was a Post Doctoral Fellow at the Department of Mathematics and Computer Science, University of Lethbridge, Canada, from where he obtained his PhD. in Computer Science with a focus in NLP and Machine Learning. Sadid has over 40 patents pending and 70 peer-reviewed publications in the top NLP/Machine Learning venues, where he also regularly serves as a program committee member/area chair including AAAI, ACL, IJCAI, NeurIPS, ICML, ICLR, EMNLP, COLING, NAACL, AMIA, JAIR, etc.