Developing an Automated Assessment of In-session Patient Activation for Psychological Therapy: Codevelopment Approach
BackgroundPatient activation is defined as a patient’s confidence and perceived ability to manage their own health. Patient activation has been a consistent predictor of long-term health and care costs, particularly for people with multiple long-term health conditions. Howeve...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2022-11-01
|
| Series: | JMIR Medical Informatics |
| Online Access: | https://medinform.jmir.org/2022/11/e38168 |
| _version_ | 1797734689556922368 |
|---|---|
| author | Sam Malins Grazziela Figueredo Tahseen Jilani Yunfei Long Jacob Andrews Mat Rawsthorne Cosmin Manolescu Jeremie Clos Fred Higton David Waldram Daniel Hunt Elvira Perez Vallejos Nima Moghaddam |
| author_facet | Sam Malins Grazziela Figueredo Tahseen Jilani Yunfei Long Jacob Andrews Mat Rawsthorne Cosmin Manolescu Jeremie Clos Fred Higton David Waldram Daniel Hunt Elvira Perez Vallejos Nima Moghaddam |
| author_sort | Sam Malins |
| collection | DOAJ |
| description |
BackgroundPatient activation is defined as a patient’s confidence and perceived ability to manage their own health. Patient activation has been a consistent predictor of long-term health and care costs, particularly for people with multiple long-term health conditions. However, there is currently no means of measuring patient activation from what is said in health care consultations. This may be particularly important for psychological therapy because most current methods for evaluating therapy content cannot be used routinely due to time and cost restraints. Natural language processing (NLP) has been used increasingly to classify and evaluate the contents of psychological therapy. This aims to make the routine, systematic evaluation of psychological therapy contents more accessible in terms of time and cost restraints. However, comparatively little attention has been paid to algorithmic trust and interpretability, with few studies in the field involving end users or stakeholders in algorithm development.
ObjectiveThis study applied a responsible design to use NLP in the development of an artificial intelligence model to automate the ratings assigned by a psychological therapy process measure: the consultation interactions coding scheme (CICS). The CICS assesses the level of patient activation observable from turn-by-turn psychological therapy interactions.
MethodsWith consent, 128 sessions of remotely delivered cognitive behavioral therapy from 53 participants experiencing multiple physical and mental health problems were anonymously transcribed and rated by trained human CICS coders. Using participatory methodology, a multidisciplinary team proposed candidate language features that they thought would discriminate between high and low patient activation. The team included service-user researchers, psychological therapists, applied linguists, digital research experts, artificial intelligence ethics researchers, and NLP researchers. Identified language features were extracted from the transcripts alongside demographic features, and machine learning was applied using k-nearest neighbors and bagged trees algorithms to assess whether in-session patient activation and interaction types could be accurately classified.
ResultsThe k-nearest neighbors classifier obtained 73% accuracy (82% precision and 80% recall) in a test data set. The bagged trees classifier obtained 81% accuracy for test data (87% precision and 75% recall) in differentiating between interactions rated high in patient activation and those rated low or neutral.
ConclusionsCoproduced language features identified through a multidisciplinary collaboration can be used to discriminate among psychological therapy session contents based on patient activation among patients experiencing multiple long-term physical and mental health conditions. |
| first_indexed | 2024-03-12T12:48:01Z |
| format | Article |
| id | doaj.art-fceb39ff93094fb8905a1f3ef033aaf0 |
| institution | Directory Open Access Journal |
| issn | 2291-9694 |
| language | English |
| last_indexed | 2024-03-12T12:48:01Z |
| publishDate | 2022-11-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Medical Informatics |
| spelling | doaj.art-fceb39ff93094fb8905a1f3ef033aaf02023-08-28T23:15:00ZengJMIR PublicationsJMIR Medical Informatics2291-96942022-11-011011e3816810.2196/38168Developing an Automated Assessment of In-session Patient Activation for Psychological Therapy: Codevelopment ApproachSam Malinshttps://orcid.org/0000-0001-9570-186XGrazziela Figueredohttps://orcid.org/0000-0003-4094-7680Tahseen Jilanihttps://orcid.org/0000-0002-2676-4143Yunfei Longhttps://orcid.org/0000-0002-4407-578XJacob Andrewshttps://orcid.org/0000-0001-8408-5782Mat Rawsthornehttps://orcid.org/0000-0002-7481-693XCosmin Manolescuhttps://orcid.org/0000-0003-2779-574XJeremie Closhttps://orcid.org/0000-0003-4280-5993Fred Higtonhttps://orcid.org/0000-0001-5861-6359David Waldramhttps://orcid.org/0000-0001-9075-927XDaniel Hunthttps://orcid.org/0000-0003-0755-7015Elvira Perez Vallejoshttps://orcid.org/0000-0002-0258-9440Nima Moghaddamhttps://orcid.org/0000-0002-8657-4341 BackgroundPatient activation is defined as a patient’s confidence and perceived ability to manage their own health. Patient activation has been a consistent predictor of long-term health and care costs, particularly for people with multiple long-term health conditions. However, there is currently no means of measuring patient activation from what is said in health care consultations. This may be particularly important for psychological therapy because most current methods for evaluating therapy content cannot be used routinely due to time and cost restraints. Natural language processing (NLP) has been used increasingly to classify and evaluate the contents of psychological therapy. This aims to make the routine, systematic evaluation of psychological therapy contents more accessible in terms of time and cost restraints. However, comparatively little attention has been paid to algorithmic trust and interpretability, with few studies in the field involving end users or stakeholders in algorithm development. ObjectiveThis study applied a responsible design to use NLP in the development of an artificial intelligence model to automate the ratings assigned by a psychological therapy process measure: the consultation interactions coding scheme (CICS). The CICS assesses the level of patient activation observable from turn-by-turn psychological therapy interactions. MethodsWith consent, 128 sessions of remotely delivered cognitive behavioral therapy from 53 participants experiencing multiple physical and mental health problems were anonymously transcribed and rated by trained human CICS coders. Using participatory methodology, a multidisciplinary team proposed candidate language features that they thought would discriminate between high and low patient activation. The team included service-user researchers, psychological therapists, applied linguists, digital research experts, artificial intelligence ethics researchers, and NLP researchers. Identified language features were extracted from the transcripts alongside demographic features, and machine learning was applied using k-nearest neighbors and bagged trees algorithms to assess whether in-session patient activation and interaction types could be accurately classified. ResultsThe k-nearest neighbors classifier obtained 73% accuracy (82% precision and 80% recall) in a test data set. The bagged trees classifier obtained 81% accuracy for test data (87% precision and 75% recall) in differentiating between interactions rated high in patient activation and those rated low or neutral. ConclusionsCoproduced language features identified through a multidisciplinary collaboration can be used to discriminate among psychological therapy session contents based on patient activation among patients experiencing multiple long-term physical and mental health conditions.https://medinform.jmir.org/2022/11/e38168 |
| spellingShingle | Sam Malins Grazziela Figueredo Tahseen Jilani Yunfei Long Jacob Andrews Mat Rawsthorne Cosmin Manolescu Jeremie Clos Fred Higton David Waldram Daniel Hunt Elvira Perez Vallejos Nima Moghaddam Developing an Automated Assessment of In-session Patient Activation for Psychological Therapy: Codevelopment Approach JMIR Medical Informatics |
| title | Developing an Automated Assessment of In-session Patient Activation for Psychological Therapy: Codevelopment Approach |
| title_full | Developing an Automated Assessment of In-session Patient Activation for Psychological Therapy: Codevelopment Approach |
| title_fullStr | Developing an Automated Assessment of In-session Patient Activation for Psychological Therapy: Codevelopment Approach |
| title_full_unstemmed | Developing an Automated Assessment of In-session Patient Activation for Psychological Therapy: Codevelopment Approach |
| title_short | Developing an Automated Assessment of In-session Patient Activation for Psychological Therapy: Codevelopment Approach |
| title_sort | developing an automated assessment of in session patient activation for psychological therapy codevelopment approach |
| url | https://medinform.jmir.org/2022/11/e38168 |
| work_keys_str_mv | AT sammalins developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT grazzielafigueredo developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT tahseenjilani developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT yunfeilong developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT jacobandrews developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT matrawsthorne developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT cosminmanolescu developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT jeremieclos developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT fredhigton developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT davidwaldram developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT danielhunt developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT elviraperezvallejos developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach AT nimamoghaddam developinganautomatedassessmentofinsessionpatientactivationforpsychologicaltherapycodevelopmentapproach |