EUVIMEDObjevte EUVIMED
QuerschnittstudieFall-Kontroll-StudieStudienprotokollOpen access

Developing a Multimodal Screening Algorithm for Mild Cognitive Impairment and Early Dementia in Home Health Care: Protocol for a Cross-Sectional Case-Control Study Using Speech Analysis, Large Language Models, and Electronic Health Records

Entwicklung eines multimodalen Screening-Algorithmus für leichte kognitive Beeinträchtigung und frühe Demenz in der häuslichen Gesundheitsversorgung: Protokoll einer Querschnitts-Fall-Kontroll-Studie mit Sprachanalyse, Large Language Models und elektronischen Gesundheitsakten

Maryam Zolnoori iD

JMIR Research Protocols · 2026-02-02 · 15 · e82731

DOI: 10.2196/82731 ↗

Auf einen Blick

Das Protokoll beschreibt einen multimodalen Ansatz zur Erkennung von MCI-ED in der häuslichen Gesundheitsversorgung. Erste Daten deuten auf die Machbarkeit der Datenerhebung und Verarbeitung hin.

Fragestellung

Wie lässt sich MCI-ED in der häuslichen Gesundheitsversorgung durch die Kombination von Sprache, Textdaten und OASIS-Variablen screenen?

Methode

Laufende Querschnitts-Fall-Kontroll-Studie bei Erwachsenen ≥60 Jahre in HHC; EHR-Vorscreening, klinische kognitive Beurteilung, 3 aufgezeichnete Begegnungen pro Person, ML mit stratifizierter nested Cross-Validation.

Ergebnisse

Zwischen Februar 2024 und Juli 2025 wurden 114 HHC-Patient:innen untersucht: 55 MCI-ED-Fälle und 59 kognitiv normale Kontrollen. Multimodale Modelle übertrafen in explorativen Analysen Einzelquellen-Modelle.

Schlussfolgerung der Autor:innen

Das Protokoll beschreibt einen reproduzierbaren multimodalen Rahmen zum MCI-ED-Screening in HHC mit Routinedaten. Erste Ergebnisse sprechen für die Machbarkeit und für den möglichen Nutzen der Kombination der Datenquellen.

Kernaussagen

  • 114 HHC-Patient:innen wurden untersucht; 55 Fälle und 59 Kontrollen
  • Multimodale Modelle schnitten explorativ besser ab als Einzelquellen-Modelle
  • Das Verfahren nutzt Sprache, klinische Notizen und OASIS-Variablen

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Querschnittstudie in JMIR Research Protocols, published online on 2026-02-02. Written by Maryam Zolnoori. Institution: Columbia University Irving Medical Center, New York, NY, United States. Major MEDLINE topics: Cognitive Dysfunction, Dementia, Mass Screening. Cited 3 times so far (Crossref); 122 references. The full text is freely available in PubMed Central. Funded by: NIA NIH HHS.

Auf einen BlickAbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Mild cognitive impairment and early dementia (MCI-ED) are frequently unrecognized in routine care, particularly in home health care (HHC), where clinical decisions are made under time constraints and cognitive status may be incompletely documented. Federally mandated HHC assessments, such as the Outcome and Assessment Information Set (OASIS), capture health and functional status but may miss subtle early cognitive changes. Speech, language, and interactional patterns during routine patient-nurse communication, together with information embedded in unstructured clinical notes, may provide complementary signals for earlier identification.

Objective

This protocol describes the development and evaluation of a multimodal screening approach for identifying MCI-ED in HHC by integrating (1) speech and interaction features from routine patient-nurse encounters (verbal communication), (2) large language model–based extraction of MCI-ED–related information from HHC notes and encounter transcripts, and (3) structured variables from OASIS.

Methods

This ongoing cross-sectional case-control study is being conducted in collaboration with VNS Health (formerly Visiting Nurse Service of New York). Eligible participants are adults aged ≥60 years receiving HHC services. Case/control assignment uses a 2-stage process: electronic health record (EHR) prescreening followed by clinician-reviewed cognitive assessment (Montreal Cognitive Assessment and Clinical Dementia Rating) for consented participants without an existing mild cognitive impairment diagnosis. For Aim 1, each participant contributes 3 audio-recorded routine patient-nurse encounters linked to EHR data, including OASIS and free-text clinical notes.

Aim

1 extracts acoustic, linguistic, emotional, and interactional features from patient-nurse verbal communication.

Aim

2 uses a schema-guided large language model pipeline to extract and normalize MCI-ED–related symptoms, lifestyle risk factors, and communication deficits from HHC notes and encounter transcripts, supported by a human-annotated gold-standard dataset.

Aim

3 integrates speech, extracted text variables, and OASIS predictors using supervised machine learning with stratified nested cross-validation; evaluation will include discrimination, calibration, and subgroup performance checks across race, sex, and age.

Results

Between February 2024 and July 2025, a total of 114 HHC patients completed study-administered cognitive assessments and were classified as 55 MCI-ED cases and 59 cognitively normal controls. Audio-recorded patient-nurse encounters had a median duration of 19 (IQR 12-23) minutes and a median of 56 (IQR 31-80) utterances per encounter; nurses contributed more words than patients (median 842, IQR 461-1218 vs median 589, IQR 303-960). In exploratory feasibility analyses, multimodal models integrating speech, interactional features, and structured EHR/OASIS variables outperformed single-source models.

Conclusions

This protocol describes a reproducible multimodal framework for MCI-ED screening in HHC using routinely generated data streams. Initial implementation results support feasibility of data collection and end-to-end processing and suggest potential value of integrating interactional speech features with clinical text and OASIS variables. Final model evaluation, subgroup analyses, and validation will follow the prespecified analytic procedures on the finalized study dataset. International Registered Report Identifier (IRRID) DERR1-10.2196/82731

Subjects

MeSH terms (MEDLINE)

Cognitive DysfunctionDementiaMass ScreeningHumansCross-Sectional StudiesCase-Control StudiesElectronic Health RecordsLarge Language ModelsHome Care ServicesAlgorithmsSpeechFemaleMaleAged

Author keywords

dementiafairnesshome health carelarge language modelsmild cognitive impairmentmultimodal fusionnatural language processingscreeningspeech analysis

Authors and institutions

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

ORCID profiles: Maryam Zolnoori

Funding

  • NIA NIH HHS

Cite

APA

Zolnoori, M. (2026). Developing a Multimodal Screening Algorithm for Mild Cognitive Impairment and Early Dementia in Home Health Care: Protocol for a Cross-Sectional Case-Control Study Using Speech Analysis, Large Language Models, and Electronic Health Records. JMIR Research Protocols, 15, e82731. https://doi.org/10.2196/82731

Vancouver

Zolnoori M. Developing a Multimodal Screening Algorithm for Mild Cognitive Impairment and Early Dementia in Home Health Care: Protocol for a Cross-Sectional Case-Control Study Using Speech Analysis, Large Language Models, and Electronic Health Records. JMIR Research Protocols. 2026;15:e82731. doi:10.2196/82731

BibTeX
@article{Zolnoori2026,
  author = {Zolnoori, Maryam},
  title = {Developing a Multimodal Screening Algorithm for Mild Cognitive Impairment and Early Dementia in Home Health Care: Protocol for a Cross-Sectional Case-Control Study Using Speech Analysis, Large Language Models, and Electronic Health Records},
  journal = {JMIR Research Protocols},
  year = {2026},
  volume = {15},
  pages = {e82731},
  doi = {10.2196/82731}
}
Start for free →