Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Formative Research

Date Submitted: Oct 22, 2021
Date Accepted: Jan 26, 2022

The final, peer-reviewed published version of this preprint can be found here:

The Value of Extracting Clinician-Recorded Affect for Advancing Clinical Research on Depression: Proof-of-Concept Study Applying Natural Language Processing to Electronic Health Records

Panaite V, Devendorf AR, Finch D, Bouayad L, Luther S, Schultz S

The Value of Extracting Clinician-Recorded Affect for Advancing Clinical Research on Depression: Proof-of-Concept Study Applying Natural Language Processing to Electronic Health Records

JMIR Form Res 2022;6(5):e34436

DOI: 10.2196/34436

PMID: 35551066

PMCID: 9136653

The value of extracting clinician recorded affect for advancing depression clinical research: A proof of concept applying NLP to electronic health records and future directions

  • Vanessa Panaite; 
  • Andrew R. Devendorf; 
  • Dezon Finch; 
  • Lina Bouayad; 
  • Stephen Luther; 
  • Susan Schultz

ABSTRACT

Background:

Affective characteristics are associated with depression severity, course, and outcomes.

Objective:

In the current paper we propose an information extraction vocabulary used to pilot the feasibility and reliability of identifying clinician recorded patient affective states in clinical notes from electronic health records (EHRs).

Methods:

Affect and mood were annotated in 149 clinical notes of 109 patients by two independent coders across three pilots. Intercoder discrepancies were settled by a third coder. This reference annotation set was used to test a proof of concept NLP system using a Named Entity Recognition approach.

Results:

Concepts were frequently addressed in templated format and free text in clinical notes. Annotated data demonstrated that affective characteristics were identified in 88% of the notes; mood was identified in 97% of the notes. The intercoder reliability was consistently good across the pilots (Inter-Annotator Agreement (IAA) > 70%). The final NLP system showed good reliability with the final reference annotation set: mood IAA = 85.8%; affect IAA = 80.9%.

Conclusions:

Affect and mood can be reliably identified in clinician reports and are good targets for NLP. We discuss several next steps to expand on this proof of concept and the value of this research for depression clinical research.


 Citation

Please cite as:

Panaite V, Devendorf AR, Finch D, Bouayad L, Luther S, Schultz S

The Value of Extracting Clinician-Recorded Affect for Advancing Clinical Research on Depression: Proof-of-Concept Study Applying Natural Language Processing to Electronic Health Records

JMIR Form Res 2022;6(5):e34436

DOI: 10.2196/34436

PMID: 35551066

PMCID: 9136653

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.