Capitalizing on natural language processing (NLP) to automate the evaluation of coach implementation fidelity in guided digital cognitive-behavioral therapy (GdCBT)

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Standard

Capitalizing on natural language processing (NLP) to automate the evaluation of coach implementation fidelity in guided digital cognitive-behavioral therapy (GdCBT). / Zainal, Nur Hani; Eckhardt, Regina; Rackoff, Gavin N. et al.
in: Psychological Medicine, Jahrgang 55, e106, 02.04.2025.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Harvard

APA

Zainal, N. H., Eckhardt, R., Rackoff, G. N., Fitzsimmons-Craft, E. E., Rojas-Ashe, E., Barr Taylor, C., Funk, B., Eisenberg, D., Wilfley, D. E., & Newman, M. G. (2025). Capitalizing on natural language processing (NLP) to automate the evaluation of coach implementation fidelity in guided digital cognitive-behavioral therapy (GdCBT). Psychological Medicine, 55, Artikel e106. https://doi.org/10.1017/S0033291725000340

Vancouver

Zainal NH, Eckhardt R, Rackoff GN, Fitzsimmons-Craft EE, Rojas-Ashe E, Barr Taylor C et al. Capitalizing on natural language processing (NLP) to automate the evaluation of coach implementation fidelity in guided digital cognitive-behavioral therapy (GdCBT). Psychological Medicine. 2025 Apr 2;55:e106. doi: 10.1017/S0033291725000340

Bibtex

@article{3cce202d951741bf8ca36f669098de6a,
title = "Capitalizing on natural language processing (NLP) to automate the evaluation of coach implementation fidelity in guided digital cognitive-behavioral therapy (GdCBT)",
abstract = "Background As the use of guided digitally-delivered cognitive-behavioral therapy (GdCBT) grows, pragmatic analytic tools are needed to evaluate coaches' implementation fidelity. Aims We evaluated how natural language processing (NLP) and machine learning (ML) methods might automate the monitoring of coaches' implementation fidelity to GdCBT delivered as part of a randomized controlled trial. Method Coaches served as guides to 6-month GdCBT with 3,381 assigned users with or at risk for anxiety, depression, or eating disorders. CBT-trained and supervised human coders used a rubric to rate the implementation fidelity of 13,529 coach-to-user messages. NLP methods abstracted data from text-based coach-to-user messages, and 11 ML models predicting coach implementation fidelity were evaluated. Results Inter-rater agreement by human coders was excellent (intra-class correlation coefficient 980-.992). Coaches achieved behavioral targets at the start of the GdCBT and maintained strong fidelity throughout most subsequent messages. Coaches also avoided prohibited actions (e.g. reinforcing users' avoidance). Sentiment analyses generally indicated a higher frequency of coach-delivered positive than negative sentiment words and predicted coach implementation fidelity with acceptable performance metrics (e.g. area under the receiver operating characteristic curve [AUC] = 74.48%). The final best-performing ML algorithms that included a more comprehensive set of NLP features performed well (e.g. AUC = 76.06%). Conclusions NLP and ML tools could help clinical supervisors automate monitoring of coaches' implementation fidelity to GdCBT. These tools could maximize allocation of scarce resources by reducing the personnel time needed to measure fidelity, potentially freeing up more time for high-quality clinical care.",
keywords = "anxiety, depression, digital mental health intervention, eating disorders, guided internet-delivered cognitive-behavioral therapy, implementation fidelity, machine learning, natural language processing, Business informatics",
author = "Zainal, {Nur Hani} and Regina Eckhardt and Rackoff, {Gavin N.} and Fitzsimmons-Craft, {Ellen E.} and Elsa Rojas-Ashe and {Barr Taylor}, Craig and Burkhardt Funk and Daniel Eisenberg and Wilfley, {Denise E.} and Newman, {Michelle G.}",
note = "Publisher Copyright: {\textcopyright} The Author(s), 2025. Published by Cambridge University Press.",
year = "2025",
month = apr,
day = "2",
doi = "10.1017/S0033291725000340",
language = "English",
volume = "55",
journal = "Psychological Medicine",
issn = "0033-2917",
publisher = "Cambridge University Press",

}

RIS

TY - JOUR

T1 - Capitalizing on natural language processing (NLP) to automate the evaluation of coach implementation fidelity in guided digital cognitive-behavioral therapy (GdCBT)

AU - Zainal, Nur Hani

AU - Eckhardt, Regina

AU - Rackoff, Gavin N.

AU - Fitzsimmons-Craft, Ellen E.

AU - Rojas-Ashe, Elsa

AU - Barr Taylor, Craig

AU - Funk, Burkhardt

AU - Eisenberg, Daniel

AU - Wilfley, Denise E.

AU - Newman, Michelle G.

N1 - Publisher Copyright: © The Author(s), 2025. Published by Cambridge University Press.

PY - 2025/4/2

Y1 - 2025/4/2

N2 - Background As the use of guided digitally-delivered cognitive-behavioral therapy (GdCBT) grows, pragmatic analytic tools are needed to evaluate coaches' implementation fidelity. Aims We evaluated how natural language processing (NLP) and machine learning (ML) methods might automate the monitoring of coaches' implementation fidelity to GdCBT delivered as part of a randomized controlled trial. Method Coaches served as guides to 6-month GdCBT with 3,381 assigned users with or at risk for anxiety, depression, or eating disorders. CBT-trained and supervised human coders used a rubric to rate the implementation fidelity of 13,529 coach-to-user messages. NLP methods abstracted data from text-based coach-to-user messages, and 11 ML models predicting coach implementation fidelity were evaluated. Results Inter-rater agreement by human coders was excellent (intra-class correlation coefficient 980-.992). Coaches achieved behavioral targets at the start of the GdCBT and maintained strong fidelity throughout most subsequent messages. Coaches also avoided prohibited actions (e.g. reinforcing users' avoidance). Sentiment analyses generally indicated a higher frequency of coach-delivered positive than negative sentiment words and predicted coach implementation fidelity with acceptable performance metrics (e.g. area under the receiver operating characteristic curve [AUC] = 74.48%). The final best-performing ML algorithms that included a more comprehensive set of NLP features performed well (e.g. AUC = 76.06%). Conclusions NLP and ML tools could help clinical supervisors automate monitoring of coaches' implementation fidelity to GdCBT. These tools could maximize allocation of scarce resources by reducing the personnel time needed to measure fidelity, potentially freeing up more time for high-quality clinical care.

AB - Background As the use of guided digitally-delivered cognitive-behavioral therapy (GdCBT) grows, pragmatic analytic tools are needed to evaluate coaches' implementation fidelity. Aims We evaluated how natural language processing (NLP) and machine learning (ML) methods might automate the monitoring of coaches' implementation fidelity to GdCBT delivered as part of a randomized controlled trial. Method Coaches served as guides to 6-month GdCBT with 3,381 assigned users with or at risk for anxiety, depression, or eating disorders. CBT-trained and supervised human coders used a rubric to rate the implementation fidelity of 13,529 coach-to-user messages. NLP methods abstracted data from text-based coach-to-user messages, and 11 ML models predicting coach implementation fidelity were evaluated. Results Inter-rater agreement by human coders was excellent (intra-class correlation coefficient 980-.992). Coaches achieved behavioral targets at the start of the GdCBT and maintained strong fidelity throughout most subsequent messages. Coaches also avoided prohibited actions (e.g. reinforcing users' avoidance). Sentiment analyses generally indicated a higher frequency of coach-delivered positive than negative sentiment words and predicted coach implementation fidelity with acceptable performance metrics (e.g. area under the receiver operating characteristic curve [AUC] = 74.48%). The final best-performing ML algorithms that included a more comprehensive set of NLP features performed well (e.g. AUC = 76.06%). Conclusions NLP and ML tools could help clinical supervisors automate monitoring of coaches' implementation fidelity to GdCBT. These tools could maximize allocation of scarce resources by reducing the personnel time needed to measure fidelity, potentially freeing up more time for high-quality clinical care.

KW - anxiety

KW - depression

KW - digital mental health intervention

KW - eating disorders

KW - guided internet-delivered cognitive-behavioral therapy

KW - implementation fidelity

KW - machine learning

KW - natural language processing

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=105001856822&partnerID=8YFLogxK

U2 - 10.1017/S0033291725000340

DO - 10.1017/S0033291725000340

M3 - Journal articles

C2 - 40170669

AN - SCOPUS:105001856822

VL - 55

JO - Psychological Medicine

JF - Psychological Medicine

SN - 0033-2917

M1 - e106

ER -

DOI

Zuletzt angesehen

Aktivitäten

  1. Der strafrechtliche, haftungsrechtliche und klinische Schutz von Körper und Leben des Ungeborenen am Beispiel des Berliner Zwillingsfalls (LG Berlin v. 19.11.2019, 532 Ks 7/16)
  2. Towards a fully-automated adaptive e-learning environment: A predictive model for difficulty generating factors in gap-filling activities that target English tense-aspect-mood
  3. Wie wirken sich berufliche Gratifikationskrisen auf die Gesundheit von Schulleitungen aus? Untersuchung des Zusammenhangs vom Effort-Reward Imbalance (ERI) Modell und Burnout
  4. Klimawandel und Küstenschutz: Müssen sich Wissenschaft und Gesellschaft wandeln? Ergebnisse einer Diskursstudie unter den Akteuren des Küstenschutzes in der Ems-Dollart-Region
  5. Erfassung von Belastungs- und Burnout-Erleben parallel zu einem Screening psychischer Störungen im Internet: Möglichkeiten und Grenzen am Beispiel des "Stress-Monitors" (Vortrag)
  6. Rigor und Relevanz in der Sozial-ökologischen Forschung (SÖF) – Herausforderungen für die BWL am Beispiel das Projekts BiNKA – Bildung für Nachhaltigen Konsum durch Achtsamkeitstraining
  7. UV photodegradation of trimipramine under different environmental variables and chemical nature of aqueous solution - biodegradation and LC-MSn characterization of the formed transformation products
  8. Gelingensbedinungen inklusiven naturwissenschaftlichen Unterrichts in der Primar- und Sekundarstufe I: Erfahrungen, Potenziale und Herausforderungen im Umgang mit unterschiedlichen Lernvoraussetzungen
  9. Effects of an online- and video-based learning environment on pre-service teachers’ self-efficacy beliefs, attitudes towards inclusion and knowledge of inclusive education during practical school experiences
  10. Berufliche Bildung als subpolitische Resonanz- und Entfremdungserfahrung im Kontext der Großen Transformation zur nachhaltigen Wirtschaft und Gesellschaft als subpolitische Resonanz- und Entfremdungserfahrung?
  11. „Aus dem Denkraum der Naturalisierungsstrategie ausbrechen“: herrschende ökonomische Begriffe hinterfragen und neu besetzen und Commons und Care: das Verhältnis von Sozialstaat und Commons unter die Lupe nehmen
  12. Biodegradability of cytostatic drugs: Cyclophosphamide, 5-Fluorouracil and Methotrexate and their photo-transformation resulting from treatment with UV and simulated sunlight radiation products in Closed Bottle Test
  13. Plenary Speaker at the 2022 5th IEEE International Conference on Information Communication and Signal Processing (ICICSP 2022). Plenary entitled "Soft Optimal Computing Techniques to Identify and Control Surface Roughness in Manufacturing".
  14. Resonanzräume des Subpolitischen in der wirtschaftsberuflichen Bildung: Die Konstruktion lebenswelt-transzendenter Lernaufgaben vor dem Hintergrund der „Großen Transformation“ zur nachhaltigen Wirtschaft und Gesellschaft (Vortrag im Rahmen der Jahrestagung der Sektion Berufs- und Wirtschaftspädagogik der DGfE)

Publikationen

  1. Marcel Baumann: Zwischenwelten: Weder Krieg noch Frieden. Über den konstruktiven Umgang mit Gewaltphänomenen im Prozess der Konflikttransformation. Wiesbaden 2008: VS Verlag
  2. Untersuchungen von Transfereffekten musikalischer Angebote. Ergebnisse aus der Studie Wirkungen und langfristige Effekte musikalischer Angebote (WilmA-Teilprojekt Transfer)
  3. Lernen aus Fehlern anhand eines fallbasierten Curriculums im medizinischen Querschnittsbereich Gesundheitssysteme/Gesundheitsökonomie und öffentliche Gesundheitspflege
  4. Food Retailers as Mediating Gatekeepers between Farmers and Consumers in the Supply Chain of Animal Welfare Meat - Studying Retailers’ Motives in Marketing Pasture-Based Beef
  5. Verlängerung der Nutzungsdauer für den derivativen Geschäfts- oder Firmenwert und selbst erstellte immaterielle Anlagegüter durch das Bilanzrichtlinie-Umsetzungsgesetz (BilRUG)
  6. Der Erwerb professioneller Handlungskompetenz von Sachunterrichtsstudierenden im Kontext von Bildung für nachhaltige Entwicklung – Kompetenzerwerb durch transdisziplinäre Projektarbeit
  7. Schriftliche Stellungnahme für den Innenausschuss des Hessischen Landtagszum Gesetzentwurf der Hessischen Landesregierung für ein Gesetz zur Änderung des Hessischen Spielbankengesetzes
  8. Welcome Mr Chance. Methodological considerations concerning the quality of empirical research in educational science based on a recent study on violence published by Heitmeyer et al (1995)
  9. Rezension zu Thomas Haigh, Mark Priestley, Crispin Rope, ENIAC in Action: Making and Remaking the Modern Computer, (History of Computing) Cambridge/London: MIT Press 2016. 341 S., ISBN 978‐0‐2620‐3398‐5.
  10. Peter Neumann/Denise Renger (Hrsg) Sachunmittelbare Demokratie im interdisziplinären und internationalen Kontext 2008/09 (Nomos). Christina Eder Direkte Demokratie auf subnationaler Ebene. (Nomos)
  11. Stefan Welling, Andreas Breiter & Arne Hendrik Schulz (2015): Mediatisierte Organisationswelten in Schulen. Wie der Medienwandel die Kommunikation in den Schulen verändert. Wiesbaden: Springer VS
  12. The aftermath of colonization and forms of transactions between agriculture and industry - Exchange relations between industrialized and developing countries in the world economy of tobacco
  13. Alan L. Carsud and Malin Braennback (eds), Understanding the entrepreneurial mind: Opening the black box. International Studies in Entrepreneurship, Vol. 24. Heidelberg: Springer, 2009. 340 pp. ISBN 9781441904423.
  14. Analyzing multivariate dynamics using cross-recurrence quantification analysis (CRQA), diagonal-cross-recurrence profiles (DCRP), and multidimensional recurrence quantification analysis (MdRQA) - A tutorial in R
  15. Characterization of photo-transformation products of the antibiotic drug Ciprofloxacin with liquid chromatography-tandem mass spectrometry in combination with accurate mass determination using an LTQ-Orbitrap
  16. Erfassung der gesundheitsfördernden Schule: Erste methodische Erfahrungen mit dem SEP-Modul „Gesundheitsförderung“ im Rahmen der Evaluation des Landesprogramms für eine gute gesunde Schule im Land Brandenburg
  17. „also habe ich mich entschieden, mich nicht zu entscheiden“ Biografische Bildungsentscheidungen als Nicht-Entscheidungen in Lebensgeschichten junger Frauen mit Migrationshintergrund in Deutschland und Frankreich
  18. Berechnung von Eisen(III)hydroxid-Bildungsraten aus Redoxpotentialmessungem - Vergleich mit Untersuchungen zum Eisen-Schwefel-Redoxsystem in den thermischen Energiespeicheranlagen der Parlamentsbauten am Berliner Spreebogen
  19. Pflichtteilsrecht als Teil des ordre public? – „Recht zu erben“ und Grenzen seiner Durchsetzung - Entscheidung des Österreichischen Obersten Gerichtshofs vom 25. Februar 2021 und Entscheidung des Bundesgerichtshofs vom 29. Juni 2022
  20. Julian von Oppen: Flucht, Migration und pädagogische Organisationen. Zur Bedeutung von kultureller Differenz in der Sozialen Arbeit mit unbegleiteten minderjährigen Geflüchteten. Weinheim: Beltz Juventa 2018,204 Seiten; ISBN 978-3-7799-3840-8
  21. Rezension von Sylwia Adamczak-Krystofowicz: Fremdsprachliches Hörverstehen im Erwachsenenalter. Theoretische und empirische Grundlagen zur adressatengerechten und integrativen Förderung der Hörverstehenskompetenz am Beispiel Deutsch als Fremdsprache in Polen.