Literature DB >> 35738008

Natural Language Processing and Psychosis: On the Need for Comprehensive Psychometric Evaluation.

Alex S Cohen1,2, Zachary Rodriguez1,2, Kiara K Warren1, Tovah Cowan1, Michael D Masucci1, Ole Edvard Granrud1, Terje B Holmlund3, Chelsea Chandler4,5, Peter W Foltz4,5, Gregory P Strauss6.   

Abstract

BACKGROUND AND HYPOTHESIS: Despite decades of "proof of concept" findings supporting the use of Natural Language Processing (NLP) in psychosis research, clinical implementation has been slow. One obstacle reflects the lack of comprehensive psychometric evaluation of these measures. There is overwhelming evidence that criterion and content validity can be achieved for many purposes, particularly using machine learning procedures. However, there has been very little evaluation of test-retest reliability, divergent validity (sufficient to address concerns of a "generalized deficit"), and potential biases from demographics and other individual differences. STUDY
DESIGN: This article highlights these concerns in development of an NLP measure for tracking clinically rated paranoia from video "selfies" recorded from smartphone devices. Patients with schizophrenia or bipolar disorder were recruited and tracked over a week-long epoch. A small NLP-based feature set from 499 language samples were modeled on clinically rated paranoia using regularized regression. STUDY
RESULTS: While test-retest reliability was high, criterion, and convergent/divergent validity were only achieved when considering moderating variables, notably whether a patient was away from home, around strangers, or alone at the time of the recording. Moreover, there were systematic racial and sex biases in the model, in part, reflecting whether patients submitted videos when they were away from home, around strangers, or alone.
CONCLUSIONS: Advancing NLP measures for psychosis will require deliberate consideration of test-retest reliability, divergent validity, systematic biases and the potential role of moderators. In our example, a comprehensive psychometric evaluation revealed clear strengths and weaknesses that can be systematically addressed in future research.
© The Author(s) 2022. Published by Oxford University Press on behalf of the Maryland Psychiatric Research Center. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  bias; machine learning; paranoia; psychometrics; psychosis; reliability; validity

Mesh:

Year:  2022        PMID: 35738008      PMCID: PMC9434462          DOI: 10.1093/schbul/sbac051

Source DB:  PubMed          Journal:  Schizophr Bull        ISSN: 0586-7614            Impact factor:   7.348


  59 in total

1.  Why Psychiatry Needs Data Science and Data Science Needs Psychiatry: Connecting With Technology.

Authors:  John Torous; Justin T Baker
Journal:  JAMA Psychiatry       Date:  2016-01       Impact factor: 21.596

2.  Advancing ambulatory biobehavioral technologies beyond "proof of concept": Introduction to the special section.

Authors:  Alex S Cohen
Journal:  Psychol Assess       Date:  2019-03

3.  Updating verbal fluency analysis for the 21st century: Applications for psychiatry.

Authors:  Terje B Holmlund; Jian Cheng; Peter W Foltz; Alex S Cohen; Brita Elvevåg
Journal:  Psychiatry Res       Date:  2019-02-07       Impact factor: 3.222

4.  Has the generalized deficit become the generalized criticism?

Authors:  Michael F Green; William P Horan; Catherine A Sugar
Journal:  Schizophr Bull       Date:  2012-12-12       Impact factor: 9.306

5.  Statistical learning theory for high dimensional prediction: Application to criterion-keyed scale development.

Authors:  Benjamin P Chapman; Alexander Weiss; Paul R Duberstein
Journal:  Psychol Methods       Date:  2016-07-25

6.  Problems in the measurement of cognitive deficit.

Authors:  L J Chapman; J P Chapman
Journal:  Psychol Bull       Date:  1973-06       Impact factor: 17.737

7.  Extending the usefulness of the verbal memory test: The promise of machine learning.

Authors:  Chelsea Chandler; Terje B Holmlund; Peter W Foltz; Alex S Cohen; Brita Elvevåg
Journal:  Psychiatry Res       Date:  2021-01-19       Impact factor: 3.222

8.  Digital phenotyping of negative symptoms: the relationship to clinician ratings.

Authors:  Alex S Cohen; Elana Schwartz; Thanh P Le; Tovah Cowan; Brian Kirkpatrick; Ian M Raugh; Gregory P Strauss
Journal:  Schizophr Bull       Date:  2021-01-23       Impact factor: 9.306

9.  Quantified language connectedness in schizophrenia-spectrum disorders.

Authors:  A E Voppel; J N de Boer; S G Brederoo; H G Schnack; Iec Sommer
Journal:  Psychiatry Res       Date:  2021-07-22       Impact factor: 3.222

10.  Latent semantic variables are associated with formal thought disorder and adaptive behavior in older inpatients with schizophrenia.

Authors:  Katherine Holshausen; Philip D Harvey; Brita Elvevåg; Peter W Foltz; Christopher R Bowie
Journal:  Cortex       Date:  2013-02-19       Impact factor: 4.027

View more
  4 in total

1.  Natural Language Processing: Its Potential Role in Clinical Care and Clinical Research.

Authors:  Stephen R Marder
Journal:  Schizophr Bull       Date:  2022-09-01       Impact factor: 7.348

2.  Translating Natural Language Processing into Mainstream Schizophrenia Assessment.

Authors:  Brita Elvevåg; Alex S Cohen
Journal:  Schizophr Bull       Date:  2022-09-01       Impact factor: 7.348

3.  What's That Noise? Interpreting Algorithmic Interpretation of Human Speech as a Legal and Ethical Challenge.

Authors:  Mathias K Hauglid
Journal:  Schizophr Bull       Date:  2022-09-01       Impact factor: 7.348

4.  Improving the Applicability of AI for Psychiatric Applications through Human-in-the-loop Methodologies.

Authors:  Chelsea Chandler; Peter W Foltz; Brita Elvevåg
Journal:  Schizophr Bull       Date:  2022-09-01       Impact factor: 7.348

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.