Developing a Machine Learning–Based Automated Patient Engagement Estimator for Telehealth: Algorithm Development and Validation Study
BackgroundPatient engagement is a critical but challenging public health priority in behavioral health care. During telehealth sessions, health care providers need to rely predominantly on verbal strategies rather than typical nonverbal cues to effectively engage patients. He...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2025-01-01
|
| Series: | JMIR Formative Research |
| Online Access: | https://formative.jmir.org/2025/1/e46390 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592925367730176 |
|---|---|
| author | Pooja Guhan Naman Awasthi Kathryn McDonald Kristin Bussell Gloria Reeves Dinesh Manocha Aniket Bera |
| author_facet | Pooja Guhan Naman Awasthi Kathryn McDonald Kristin Bussell Gloria Reeves Dinesh Manocha Aniket Bera |
| author_sort | Pooja Guhan |
| collection | DOAJ |
| description |
BackgroundPatient engagement is a critical but challenging public health priority in behavioral health care. During telehealth sessions, health care providers need to rely predominantly on verbal strategies rather than typical nonverbal cues to effectively engage patients. Hence, the typical patient engagement behaviors are now different, and health care provider training on telehealth patient engagement is unavailable or quite limited. Therefore, we explore the application of machine learning for estimating patient engagement. This can assist psychotherapists in the development of a therapeutic relationship with the patient and enhance patient engagement in the treatment of mental health conditions during tele–mental health sessions.
ObjectiveThis study aimed to examine the ability of machine learning models to estimate patient engagement levels during a tele–mental health session and understand whether the machine learning approach could support therapeutic engagement between the client and psychotherapist.
MethodsWe proposed a multimodal learning-based approach. We uniquely leveraged latent vectors corresponding to affective and cognitive features frequently used in psychology literature to understand a person’s level of engagement. Given the labeled data constraints that exist in health care, we explored a semisupervised learning solution. To support the development of similar technologies for telehealth, we also plan to release a dataset called Multimodal Engagement Detection in Clinical Analysis (MEDICA). This dataset includes 1229 video clips, each lasting 3 seconds. In addition, we present experiments conducted on this dataset, along with real-world tests that demonstrate the effectiveness of our method.
ResultsOur algorithm reports a 40% improvement in root mean square error over state-of-the-art methods for engagement estimation. In our real-world tests on 438 video clips from psychotherapy sessions with 20 patients, in comparison to prior methods, positive correlations were observed between psychotherapists’ Working Alliance Inventory scores and our mean and median engagement level estimates. This indicates the potential of the proposed model to present patient engagement estimations that align well with the engagement measures used by psychotherapists.
ConclusionsPatient engagement has been identified as being important to improve therapeutic alliance. However, limited research has been conducted to measure this in a telehealth setting, where the therapist lacks conventional cues to make a confident assessment. The algorithm developed is an attempt to model person-oriented engagement modeling theories within machine learning frameworks to estimate the level of engagement of the patient accurately and reliably in telehealth. The results are encouraging and emphasize the value of combining psychology and machine learning to understand patient engagement. Further testing in the real-world setting is necessary to fully assess its usefulness in helping therapists gauge patient engagement during online sessions. However, the proposed approach and the creation of the new dataset, MEDICA, open avenues for future research and the development of impactful tools for telehealth. |
| format | Article |
| id | doaj-art-5b6f828149624f16a1502f3be22bd092 |
| institution | Kabale University |
| issn | 2561-326X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Formative Research |
| spelling | doaj-art-5b6f828149624f16a1502f3be22bd0922025-01-20T21:00:37ZengJMIR PublicationsJMIR Formative Research2561-326X2025-01-019e4639010.2196/46390Developing a Machine Learning–Based Automated Patient Engagement Estimator for Telehealth: Algorithm Development and Validation StudyPooja Guhanhttps://orcid.org/0000-0003-1551-8163Naman Awasthihttps://orcid.org/0000-0001-6036-076XKathryn McDonaldhttps://orcid.org/0009-0007-0589-4946Kristin Bussellhttps://orcid.org/0000-0002-3128-0178Gloria Reeveshttps://orcid.org/0000-0001-8070-673XDinesh Manochahttps://orcid.org/0000-0001-7047-9801Aniket Berahttps://orcid.org/0000-0002-0182-6985 BackgroundPatient engagement is a critical but challenging public health priority in behavioral health care. During telehealth sessions, health care providers need to rely predominantly on verbal strategies rather than typical nonverbal cues to effectively engage patients. Hence, the typical patient engagement behaviors are now different, and health care provider training on telehealth patient engagement is unavailable or quite limited. Therefore, we explore the application of machine learning for estimating patient engagement. This can assist psychotherapists in the development of a therapeutic relationship with the patient and enhance patient engagement in the treatment of mental health conditions during tele–mental health sessions. ObjectiveThis study aimed to examine the ability of machine learning models to estimate patient engagement levels during a tele–mental health session and understand whether the machine learning approach could support therapeutic engagement between the client and psychotherapist. MethodsWe proposed a multimodal learning-based approach. We uniquely leveraged latent vectors corresponding to affective and cognitive features frequently used in psychology literature to understand a person’s level of engagement. Given the labeled data constraints that exist in health care, we explored a semisupervised learning solution. To support the development of similar technologies for telehealth, we also plan to release a dataset called Multimodal Engagement Detection in Clinical Analysis (MEDICA). This dataset includes 1229 video clips, each lasting 3 seconds. In addition, we present experiments conducted on this dataset, along with real-world tests that demonstrate the effectiveness of our method. ResultsOur algorithm reports a 40% improvement in root mean square error over state-of-the-art methods for engagement estimation. In our real-world tests on 438 video clips from psychotherapy sessions with 20 patients, in comparison to prior methods, positive correlations were observed between psychotherapists’ Working Alliance Inventory scores and our mean and median engagement level estimates. This indicates the potential of the proposed model to present patient engagement estimations that align well with the engagement measures used by psychotherapists. ConclusionsPatient engagement has been identified as being important to improve therapeutic alliance. However, limited research has been conducted to measure this in a telehealth setting, where the therapist lacks conventional cues to make a confident assessment. The algorithm developed is an attempt to model person-oriented engagement modeling theories within machine learning frameworks to estimate the level of engagement of the patient accurately and reliably in telehealth. The results are encouraging and emphasize the value of combining psychology and machine learning to understand patient engagement. Further testing in the real-world setting is necessary to fully assess its usefulness in helping therapists gauge patient engagement during online sessions. However, the proposed approach and the creation of the new dataset, MEDICA, open avenues for future research and the development of impactful tools for telehealth.https://formative.jmir.org/2025/1/e46390 |
| spellingShingle | Pooja Guhan Naman Awasthi Kathryn McDonald Kristin Bussell Gloria Reeves Dinesh Manocha Aniket Bera Developing a Machine Learning–Based Automated Patient Engagement Estimator for Telehealth: Algorithm Development and Validation Study JMIR Formative Research |
| title | Developing a Machine Learning–Based Automated Patient Engagement Estimator for Telehealth: Algorithm Development and Validation Study |
| title_full | Developing a Machine Learning–Based Automated Patient Engagement Estimator for Telehealth: Algorithm Development and Validation Study |
| title_fullStr | Developing a Machine Learning–Based Automated Patient Engagement Estimator for Telehealth: Algorithm Development and Validation Study |
| title_full_unstemmed | Developing a Machine Learning–Based Automated Patient Engagement Estimator for Telehealth: Algorithm Development and Validation Study |
| title_short | Developing a Machine Learning–Based Automated Patient Engagement Estimator for Telehealth: Algorithm Development and Validation Study |
| title_sort | developing a machine learning based automated patient engagement estimator for telehealth algorithm development and validation study |
| url | https://formative.jmir.org/2025/1/e46390 |
| work_keys_str_mv | AT poojaguhan developingamachinelearningbasedautomatedpatientengagementestimatorfortelehealthalgorithmdevelopmentandvalidationstudy AT namanawasthi developingamachinelearningbasedautomatedpatientengagementestimatorfortelehealthalgorithmdevelopmentandvalidationstudy AT kathrynmcdonald developingamachinelearningbasedautomatedpatientengagementestimatorfortelehealthalgorithmdevelopmentandvalidationstudy AT kristinbussell developingamachinelearningbasedautomatedpatientengagementestimatorfortelehealthalgorithmdevelopmentandvalidationstudy AT gloriareeves developingamachinelearningbasedautomatedpatientengagementestimatorfortelehealthalgorithmdevelopmentandvalidationstudy AT dineshmanocha developingamachinelearningbasedautomatedpatientengagementestimatorfortelehealthalgorithmdevelopmentandvalidationstudy AT aniketbera developingamachinelearningbasedautomatedpatientengagementestimatorfortelehealthalgorithmdevelopmentandvalidationstudy |