Finding the Best Match — a Case Study on the (Text‑) Feature and Model Choice in Digital Mental Health Interventions

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Standard

Finding the Best Match — a Case Study on the (Text‑) Feature and Model Choice in Digital Mental Health Interventions. / Zantvoort, Kirsten; Scharfenberger, Jonas; Boß, Leif et al.
in: Journal of Healthcare Informatics Research, Jahrgang 7, Nr. 4, 00148, 12.2023, S. 447-479.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Harvard

APA

Vancouver

Bibtex

@article{c90d7531bb5b4c94911b929e62aade9b,
title = "Finding the Best Match — a Case Study on the (Text‑) Feature and Model Choice in Digital Mental Health Interventions",
abstract = "With the need for psychological help long exceeding the supply, finding ways ofscaling, and better allocating mental health support is a necessity. This paper contributes by investigating how to best predict intervention dropout and failure to allow for a need-based adaptation of treatment. We systematically compare the predictive power of different text representation methods (metadata, TF-IDF, sentiment and topic analysis, and word embeddings) in combination with supplementary numerical inputs (socio-demographic, evaluation, and closed-question data). Additionally, we address the research gap of which ML model types — ranging from linear to sophisticated deep learning models — are best suited for different features and outcome variables. To this end, we analyze nearly 16.000 open-text answers from 849 German-speaking users in a Digital Mental Health Intervention (DMHI) for stress. Our research proves that — contrary to previous findings — there is great promise in using neural network approaches on DMHI text data. We propose a task-specific LSTM-based model architecture to tackle the challenge of long input sequences and thereby demonstrate the potential of word embeddings (AUC scores of up to 0.7) forpredictions in DMHIs. Despite the relatively small data set, sequential deep learning models, on average, outperform simpler features such as metadata and bag-of-words approaches when predicting dropout. The conclusion is that user-generated text of the first two sessions carries predictive power regarding patients{\textquoteright} dropout and intervention failure risk. Furthermore, the match between the sophistication of features and models needs to be closely considered to optimize results, and additional nontext features increase prediction results.",
keywords = "E-mental health, Health care analytics, Machine learning, Natural language processing, Precision psychiatry",
author = "Kirsten Zantvoort and Jonas Scharfenberger and Leif Bo{\ss} and Dirk Lehr and Burkhardt Funk",
note = "Funding Information: Open Access funding enabled and organized by Projekt DEAL. The present study has been funded by Leuphana University. The original RCTs were funded by the European Union (project EFRE: CCI 2007DE161PR001). Publisher Copyright: {\textcopyright} 2023, The Author(s).",
year = "2023",
month = dec,
doi = "10.1007/s41666-023-00148-z",
language = "English",
volume = "7",
pages = "447--479",
journal = "Journal of Healthcare Informatics Research",
issn = "2509-498X",
publisher = "Springer International Publishing",
number = "4",

}

RIS

TY - JOUR

T1 - Finding the Best Match — a Case Study on the (Text‑) Feature and Model Choice in Digital Mental Health Interventions

AU - Zantvoort, Kirsten

AU - Scharfenberger, Jonas

AU - Boß, Leif

AU - Lehr, Dirk

AU - Funk, Burkhardt

N1 - Funding Information: Open Access funding enabled and organized by Projekt DEAL. The present study has been funded by Leuphana University. The original RCTs were funded by the European Union (project EFRE: CCI 2007DE161PR001). Publisher Copyright: © 2023, The Author(s).

PY - 2023/12

Y1 - 2023/12

N2 - With the need for psychological help long exceeding the supply, finding ways ofscaling, and better allocating mental health support is a necessity. This paper contributes by investigating how to best predict intervention dropout and failure to allow for a need-based adaptation of treatment. We systematically compare the predictive power of different text representation methods (metadata, TF-IDF, sentiment and topic analysis, and word embeddings) in combination with supplementary numerical inputs (socio-demographic, evaluation, and closed-question data). Additionally, we address the research gap of which ML model types — ranging from linear to sophisticated deep learning models — are best suited for different features and outcome variables. To this end, we analyze nearly 16.000 open-text answers from 849 German-speaking users in a Digital Mental Health Intervention (DMHI) for stress. Our research proves that — contrary to previous findings — there is great promise in using neural network approaches on DMHI text data. We propose a task-specific LSTM-based model architecture to tackle the challenge of long input sequences and thereby demonstrate the potential of word embeddings (AUC scores of up to 0.7) forpredictions in DMHIs. Despite the relatively small data set, sequential deep learning models, on average, outperform simpler features such as metadata and bag-of-words approaches when predicting dropout. The conclusion is that user-generated text of the first two sessions carries predictive power regarding patients’ dropout and intervention failure risk. Furthermore, the match between the sophistication of features and models needs to be closely considered to optimize results, and additional nontext features increase prediction results.

AB - With the need for psychological help long exceeding the supply, finding ways ofscaling, and better allocating mental health support is a necessity. This paper contributes by investigating how to best predict intervention dropout and failure to allow for a need-based adaptation of treatment. We systematically compare the predictive power of different text representation methods (metadata, TF-IDF, sentiment and topic analysis, and word embeddings) in combination with supplementary numerical inputs (socio-demographic, evaluation, and closed-question data). Additionally, we address the research gap of which ML model types — ranging from linear to sophisticated deep learning models — are best suited for different features and outcome variables. To this end, we analyze nearly 16.000 open-text answers from 849 German-speaking users in a Digital Mental Health Intervention (DMHI) for stress. Our research proves that — contrary to previous findings — there is great promise in using neural network approaches on DMHI text data. We propose a task-specific LSTM-based model architecture to tackle the challenge of long input sequences and thereby demonstrate the potential of word embeddings (AUC scores of up to 0.7) forpredictions in DMHIs. Despite the relatively small data set, sequential deep learning models, on average, outperform simpler features such as metadata and bag-of-words approaches when predicting dropout. The conclusion is that user-generated text of the first two sessions carries predictive power regarding patients’ dropout and intervention failure risk. Furthermore, the match between the sophistication of features and models needs to be closely considered to optimize results, and additional nontext features increase prediction results.

KW - E-mental health

KW - Health care analytics

KW - Machine learning

KW - Natural language processing

KW - Precision psychiatry

UR - http://www.scopus.com/inward/record.url?scp=85171458668&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/c1ccce9b-85a7-3e08-9249-6abbcf3b5023/

U2 - 10.1007/s41666-023-00148-z

DO - 10.1007/s41666-023-00148-z

M3 - Journal articles

C2 - 37927375

VL - 7

SP - 447

EP - 479

JO - Journal of Healthcare Informatics Research

JF - Journal of Healthcare Informatics Research

SN - 2509-498X

IS - 4

M1 - 00148

ER -

DOI

Zuletzt angesehen

Publikationen

  1. Democratization as Human Empowerment
  2. Conceptual and procedural mathematical knowledge of beginning mathematics majors and preservice teachers
  3. Crack propagation in as-extruded and heat-treated mg-dy-nd-zn-zr alloy explained by the effect of lpso structures and their micro-and nanohardness
  4. Exploring the institutionalization of corporate responsibility
  5. Effects of samarium content on microstructure and mechanical properties of Mg–0.5Zn–0.5Zr alloy
  6. Leverage points and levers of inclusive conservation in protected areas
  7. Communication
  8. Creativity in Spaces of Possibilities for Sustainable Urban Development
  9. Integrating Art and Education for Sustainable Development. A Transdisciplinary Working Process in the Context of Culture and Sustainability
  10. The Automated will
  11. Exploring the potential of using priority effects during ecological restoration to resist biological invasions in the neotropics
  12. Iconography on Scientific Instruments. Introduction
  13. To help or not to help an outgroup member
  14. Coauthoring collaborative strategy when voices are many and authority is ambiguous
  15. Bright Spots for Local WFD Implementation Through Collaboration with Nature Conservation Authorities?
  16. The end of certainties
  17. 11. Methoden-Muster
  18. Daniel Fiott (ed.), The csdp in 2020: The EU’s legacy and ambition in security and defence
  19. Genetically based differentiation in growth of multiple non-native plant species along a steep environmental gradient
  20. Self-efficacy, self-regulation and mathematics performance of competitive junior rowers vs. regular students
  21. Designing a global energy system based on 100% renewables for 2050 - GENeSYS-MOD