Home Healthcare, Hospice, and Information Technology Innovations Conference

Innovations in Home Healthcare, Hospice, and Information Technology

A forum towards achieving evidence-based diffusion and implementation of innovations

H3IT: Home Healthcare, Hospice, and Information Technology Conference Chicago, IL, 2016

Natural Language Processing and Speech

Recognition: Technology Overview and Potential

Applications in Homecare

Maxim Topaz, PhD, MA, RN

1, 2

and Li Zhou, MD, PhD

1, 2, 3

T

he presentation will discuss several emerging methodologies that have a potential to significantly enhance the

meaningful use of clinical data. First, each technology (natural language processing and speech recognition) will

be briefly introduced with conceptual and practical key concepts. Then, we will overview several recent projects

that use natural language processing to extract meaning from free text clinical narratives, including depression

detection, heart failure self-management status extraction, and using socio-behavioral characteristics to improve readmission

predication models, among others. Applications and unexplored venues of natural language processing in homecare will b e

highlighted. We will also review the emerging field of speech recognition and discuss its various potential applications in

homecare, including automated interaction with the patient or tools to facilitate workflows and make clinician’s work more

efficient. Examples throughout the presentation will use projects conducted by Drs. L. Zhou and M. Topaz with MTERMS- a

natural language processing engine developed at the Harvard Medical School and Brigham Women’s Health Hospital (Boston,

USA).

1

Brigham and Women’s Hospital, Boston, USA

2

Harvard Medical School, Boston, USA

3

eCare, Clinical Informatics, Partners Healthcare, Boston, USA

Copyright © 2016 by Maryland Health Information Technology LLC — Creative Commons License cbnd 38