1
|
Zantvoort K, Scharfenberger J, Boß L, Lehr D, Funk B. Finding the Best Match - a Case Study on the (Text-)Feature and Model Choice in Digital Mental Health Interventions. JOURNAL OF HEALTHCARE INFORMATICS RESEARCH 2023; 7:447-479. [PMID: 37927375 PMCID: PMC10620349 DOI: 10.1007/s41666-023-00148-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2022] [Accepted: 08/29/2023] [Indexed: 11/07/2023]
Abstract
With the need for psychological help long exceeding the supply, finding ways of scaling, 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) for predictions 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 non-text features increase prediction results. Supplementary Information The online version contains supplementary material available at 10.1007/s41666-023-00148-z.
Collapse
Affiliation(s)
- Kirsten Zantvoort
- Institute of Information Systems, Leuphana University, Lüneburg, Germany
| | | | - Leif Boß
- Institute of Psychology, Leuphana University, Lüneburg, Germany
| | - Dirk Lehr
- Institute of Psychology, Leuphana University, Lüneburg, Germany
| | - Burkhardt Funk
- Institute of Information Systems, Leuphana University, Lüneburg, Germany
| |
Collapse
|
2
|
Miner AS, Fleming SL, Haque A, Fries JA, Althoff T, Wilfley DE, Agras WS, Milstein A, Hancock J, Asch SM, Stirman SW, Arnow BA, Shah NH. A computational approach to measure the linguistic characteristics of psychotherapy timing, responsiveness, and consistency. NPJ MENTAL HEALTH RESEARCH 2022; 1:19. [PMID: 38609510 PMCID: PMC10956022 DOI: 10.1038/s44184-022-00020-9] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/12/2022] [Accepted: 10/18/2022] [Indexed: 04/14/2024]
Abstract
Although individual psychotherapy is generally effective for a range of mental health conditions, little is known about the moment-to-moment language use of effective therapists. Increased access to computational power, coupled with a rise in computer-mediated communication (telehealth), makes feasible the large-scale analyses of language use during psychotherapy. Transparent methodological approaches are lacking, however. Here we present novel methods to increase the efficiency of efforts to examine language use in psychotherapy. We evaluate three important aspects of therapist language use - timing, responsiveness, and consistency - across five clinically relevant language domains: pronouns, time orientation, emotional polarity, therapist tactics, and paralinguistic style. We find therapist language is dynamic within sessions, responds to patient language, and relates to patient symptom diagnosis but not symptom severity. Our results demonstrate that analyzing therapist language at scale is feasible and may help answer longstanding questions about specific behaviors of effective therapists.
Collapse
Affiliation(s)
- Adam S Miner
- Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA.
- Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA.
| | - Scott L Fleming
- Department of Biomedical Data Science, Stanford University, Stanford, CA, USA
- Department of Computer Science, Stanford University, Stanford, CA, USA
| | - Albert Haque
- Department of Computer Science, Stanford University, Stanford, CA, USA
| | - Jason A Fries
- Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA
| | - Tim Althoff
- Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA
| | - Denise E Wilfley
- Departments of Psychiatry, Medicine, Pediatrics, and Psychological & Brain Sciences, Washington University in St. Louis, St. Louis, MO, USA
| | - W Stewart Agras
- Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA
| | - Arnold Milstein
- Clinical Excellence Research Center, Stanford University, Stanford, CA, USA
| | - Jeff Hancock
- Department of Communication, Stanford University, Stanford, CA, USA
| | - Steven M Asch
- VA Palo Alto Health Care System, Palo Alto, CA, USA
- Division of Primary Care and Population Health, Stanford University School of Medicine, Stanford, CA, USA
| | - Shannon Wiltsey Stirman
- Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA
- VA Palo Alto Health Care System, Palo Alto, CA, USA
- National Center for Posttraumatic Stress Disorders, Dissemination and Training Division, VA Palo Alto Healthcare System, Menlo Park, CA, USA
| | - Bruce A Arnow
- Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA
| | - Nigam H Shah
- Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA
- Department of Biomedical Data Science, Stanford University, Stanford, CA, USA
- Clinical Excellence Research Center, Stanford University, Stanford, CA, USA
- Technology and Digital Solutions, Stanford Healthcare, Stanford, CA, USA
| |
Collapse
|
3
|
Corcoran CM, Cecchi GA. Using Language Processing and Speech Analysis for the Identification of Psychosis and Other Disorders. BIOLOGICAL PSYCHIATRY: COGNITIVE NEUROSCIENCE AND NEUROIMAGING 2020; 5:770-779. [PMID: 32771179 DOI: 10.1016/j.bpsc.2020.06.004] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/16/2020] [Revised: 06/09/2020] [Accepted: 06/09/2020] [Indexed: 01/12/2023]
Abstract
Increasingly, data-driven methods have been implemented to understand psychopathology. Language is the main source of information in psychiatry and represents "big data" at the level of the individual. Language and behavior are amenable to computational natural language processing (NLP) analytics, which may help operationalize the mental status examination. In this review, we highlight the application of NLP to schizophrenia and its risk states as an exemplar of its use, operationalizing tangential and concrete speech as reductions in semantic coherence and syntactic complexity, respectively. Other clinical applications are reviewed, including forecasting suicide risk and detecting intoxication. Challenges and future directions are discussed, including biomarker development, harmonization, and application of NLP more broadly to behavior, including intonation/prosody, facial expression and gesture, and the integration of these in dyads and during discourse. Similar NLP analytics can also be applied beyond humans to behavioral motifs across species, important for modeling psychopathology in animal models. Finally, clinical neuroscience can inform the development of artificial intelligence.
Collapse
Affiliation(s)
- Cheryl Mary Corcoran
- Icahn School of Medicine at Mount Sinai, New York; James J. Peters Veterans Administration Medical Center, Bronx.
| | - Guillermo A Cecchi
- Thomas J. Watson Research Center, IBM Corporation, Yorktown Heights, New York
| |
Collapse
|
4
|
Ben-Zeev D, Buck B, Kopelovich S, Meller S. A technology-assisted life of recovery from psychosis. NPJ SCHIZOPHRENIA 2019; 5:15. [PMID: 31534139 PMCID: PMC6751211 DOI: 10.1038/s41537-019-0083-y] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Received: 08/12/2019] [Accepted: 08/29/2019] [Indexed: 12/21/2022]
Abstract
Developments in digital health technologies have the potential to expedite and strengthen the path towards recovery for people with psychosis. This perspective piece provides a snapshot of how a range of digital technologies can be deployed to support a young adult’s efforts to cope with schizophrenia-spectrum illness. In conjunction with a day in the life of this individual, we provide examples of innovations in digital health research designed for this clinical population, as well as brief summaries of the evidence supporting the usability, feasibility, or effectiveness of each approach. From early detection to ongoing symptom management and vocational rehabilitation, this day-in-the-life vignette provides an overview of the ways in which digital health innovations could be used in concert to augment, scaffold, and enhance schizophrenia-spectrum illness management and recovery.
Collapse
Affiliation(s)
- Dror Ben-Zeev
- Department of Psychiatry and Behavioral Sciences, University of Washington School of Medicine, Seattle, WA, USA.
| | - Benjamin Buck
- Department of Psychiatry and Behavioral Sciences, University of Washington School of Medicine, Seattle, WA, USA
| | - Sarah Kopelovich
- Department of Psychiatry and Behavioral Sciences, University of Washington School of Medicine, Seattle, WA, USA
| | - Suzanne Meller
- Department of Psychiatry and Behavioral Sciences, University of Washington School of Medicine, Seattle, WA, USA
| |
Collapse
|