Beyond electronic health record data: leveraging natural language processing and machine learning to uncover cognitive insights from patient-nurse verbal communications.

Maryam Zolnoori^1,2,3, Ali Zolnour¹, Sasha Vergez³, Sridevi Sridharan³, Ian Spens³, Maxim Topaz^1,2,3,4, James M Noble^1,5, Suzanne Bakken^2,4,6, Julia Hirschberg⁷, Kathryn Bowles^3,8, Nicole Onorato³, Margaret V McDonald³

¹Columbia University Irving Medical Center, New York, NY 10032, United States.

²School of Nursing, Columbia University, New York, NY 10032, United States.

³Center for Home Care Policy & Research, VNS Health, New York, NY 10017, United States.

⁴Data Science Institute, Columbia University, New York, NY 10027, United States.

⁵Department of Neurology, Taub Institute for Research on Alzheimer's Disease and the Aging Brain, GH Sergievsky Center, Columbia University, New York, NY 10032, United States.

⁶Department of Biomedical Informatics, Columbia University, New York, NY 10032, United States.

⁷Department of Computer Science, Columbia University, New York, NY 10027, United States.

⁸University of Pennsylvania School of Nursing, Philadelphia, PA 19104, United States.

PubMed PMC DOI PDF

Abstract

BACKGROUND: Mild cognitive impairment and early-stage dementia significantly impact healthcare utilization and costs, yet more than half of affected patients remain underdiagnosed. This study leverages audio-recorded patient-nurse verbal communication in home healthcare settings to develop an artificial intelligence-based screening tool for early detection of cognitive decline. OBJECTIVE: To deve…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

NIH Funding

Grant #10748410
Development of a Screening Algorithm for Timely Identification of Patients with Mild Cognitive Impairment and Early Dementia in Home Healthcare
COLUMBIA UNIVERSITY HEALTH SCIENCES
$115,139 (FY2024)
Grant #11101347
Penn Artificial Intelligence and Technology Collaboratory for Healthy Aging
UNIVERSITY OF PENNSYLVANIA
$3,965,972 (FY2025)
Grant #11171621
Development of a Screening Algorithm for Timely Identification of Patients with Mild Cognitive Impairment and Early Dementia in Home Healthcare
COLUMBIA UNIVERSITY HEALTH SCIENCES
$244,006 (FY2025)
Grant #11377535
Development of a Screening Algorithm for Timely Identification of Patients with Mild Cognitive Impairment and Early Dementia in Home Healthcare
COLUMBIA UNIVERSITY HEALTH SCIENCES
$248,983 (FY2026)

Other Funding

NIA NIH HHS(P30 AG066462)
United States
NIA NIH HHS(P30 AG073105)
United States
NIA NIH HHS(R00 AG076808)
United States
NIA NIH HHS(P30AG073105)
United States
NIA NIH HHS(K99 AG076808)
United States
Development of a screening algorithm for timely identification of patients with mild cognitive impairment and early dementia in home healthcare(K99AG076808)

MeSH Terms

Humans0Natural Language Processing*Electronic Health Records*Machine Learning*Male0Female0Aged0Cognitive Dysfunction*Nurse-Patient Relations*Algorithms0Middle Aged0Aged, 80 and over0Early Diagnosis0Communication*Home Care Services0

Keywords

cognitive impairmenthome healthcaremachine learningnatural language processingpatient-nurse verbal communicationscreening algorithms

Article Info

PMID: 39667364
PMCID: PMC11756603
DOI: 10.1093/jamia/ocae300
Received: July 10, 2024
Accepted: November 21, 2024

How to Cite

Zolnoori M et al. Beyond electronic health record data: leveraging natural language processing and machine learning to uncover cognitive insights from patient-nurse verbal communications. J Am Med Inform Assoc2025;32(2):328-340. doi:10.1093/jamia/ocae300

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.