Content Recommendation Systems in Web-Based Mental Health Care: Real-world Application and Formative Evaluation
BackgroundRecommender systems have great potential in mental health care to personalize self-guided content for patients, allowing them to supplement their mental health treatment in a scalable way. ObjectiveIn this paper, we describe and evaluate 2 knowledge-base...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2023-01-01
|
| Series: | JMIR Formative Research |
| Online Access: | https://formative.jmir.org/2023/1/e38831 |
| _version_ | 1797734517590458368 |
|---|---|
| author | Akhil Chaturvedi Brandon Aylward Setu Shah Grant Graziani Joan Zhang Bobby Manuel Emmanuel Telewa Stefan Froelich Olalekan Baruwa Prathamesh Param Kulkarni Watson Ξ Sarah Kunkle |
| author_facet | Akhil Chaturvedi Brandon Aylward Setu Shah Grant Graziani Joan Zhang Bobby Manuel Emmanuel Telewa Stefan Froelich Olalekan Baruwa Prathamesh Param Kulkarni Watson Ξ Sarah Kunkle |
| author_sort | Akhil Chaturvedi |
| collection | DOAJ |
| description |
BackgroundRecommender systems have great potential in mental health care to personalize self-guided content for patients, allowing them to supplement their mental health treatment in a scalable way.
ObjectiveIn this paper, we describe and evaluate 2 knowledge-based content recommendation systems as parts of Ginger, an on-demand mental health platform, to bolster engagement in self-guided mental health content.
MethodsWe developed two algorithms to provide content recommendations in the Ginger mental health smartphone app: (1) one that uses users' responses to app onboarding questions to recommend content cards and (2) one that uses the semantic similarity between the transcript of a coaching conversation and the description of content cards to make recommendations after every session. As a measure of success for these recommendation algorithms, we examined the relevance of content cards to users’ conversations with their coach and completion rates of selected content within the app measured over 14,018 users.
ResultsIn a real-world setting, content consumed in the recommendations section (or “Explore” in the app) had the highest completion rates (3353/7871, 42.6%) compared to other sections of the app, which had an average completion rate of 37.35% (21,982/58,614; P<.001). Within the app’s recommendations section, conversation-based content recommendations had 11.4% (1108/2364) higher completion rates per card than onboarding response-based recommendations (1712/4067; P=.003) and 26.1% higher than random recommendations (534/1440; P=.005). Studied via subject matter experts’ annotations, conversation-based recommendations had a 16.1% higher relevance rate for the top 5 recommended cards, averaged across sessions of varying lengths, compared to a random control (110 conversational sessions). Finally, it was observed that both age and gender variables were sensitive to different recommendation methods, with responsiveness to personalized recommendations being higher if the users were older than 35 years or identified as male.
ConclusionsRecommender systems can help scale and supplement digital mental health care with personalized content and self-care recommendations. Onboarding-based recommendations are ideal for “cold starting” the process of recommending content for new users and users that tend to use the app just for content but not for therapy or coaching. The conversation-based recommendation algorithm allows for dynamic recommendations based on information gathered during coaching sessions, which is a critical capability, given the changing nature of mental health needs during treatment. The proposed algorithms are just one step toward the direction of outcome-driven personalization in mental health. Our future work will involve a robust causal evaluation of these algorithms using randomized controlled trials, along with consumer feedback–driven improvement of these algorithms, to drive better clinical outcomes. |
| first_indexed | 2024-03-12T12:44:29Z |
| format | Article |
| id | doaj.art-6fc2365b15774061b55fcc2cb80c81d4 |
| institution | Directory Open Access Journal |
| issn | 2561-326X |
| language | English |
| last_indexed | 2024-03-12T12:44:29Z |
| publishDate | 2023-01-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Formative Research |
| spelling | doaj.art-6fc2365b15774061b55fcc2cb80c81d42023-08-28T23:27:44ZengJMIR PublicationsJMIR Formative Research2561-326X2023-01-017e3883110.2196/38831Content Recommendation Systems in Web-Based Mental Health Care: Real-world Application and Formative EvaluationAkhil Chaturvedihttps://orcid.org/0000-0001-7395-2801Brandon Aylwardhttps://orcid.org/0000-0002-5080-5574Setu Shahhttps://orcid.org/0000-0003-2951-2272Grant Grazianihttps://orcid.org/0000-0002-5313-5158Joan Zhanghttps://orcid.org/0000-0003-3511-2056Bobby Manuelhttps://orcid.org/0000-0003-2750-7015Emmanuel Telewahttps://orcid.org/0000-0003-4766-9636Stefan Froelichhttps://orcid.org/0000-0001-6161-7491Olalekan Baruwahttps://orcid.org/0000-0002-9089-0195Prathamesh Param Kulkarnihttps://orcid.org/0000-0003-3207-9449Watson Ξhttps://orcid.org/0000-0001-8354-5708Sarah Kunklehttps://orcid.org/0000-0002-6368-0205 BackgroundRecommender systems have great potential in mental health care to personalize self-guided content for patients, allowing them to supplement their mental health treatment in a scalable way. ObjectiveIn this paper, we describe and evaluate 2 knowledge-based content recommendation systems as parts of Ginger, an on-demand mental health platform, to bolster engagement in self-guided mental health content. MethodsWe developed two algorithms to provide content recommendations in the Ginger mental health smartphone app: (1) one that uses users' responses to app onboarding questions to recommend content cards and (2) one that uses the semantic similarity between the transcript of a coaching conversation and the description of content cards to make recommendations after every session. As a measure of success for these recommendation algorithms, we examined the relevance of content cards to users’ conversations with their coach and completion rates of selected content within the app measured over 14,018 users. ResultsIn a real-world setting, content consumed in the recommendations section (or “Explore” in the app) had the highest completion rates (3353/7871, 42.6%) compared to other sections of the app, which had an average completion rate of 37.35% (21,982/58,614; P<.001). Within the app’s recommendations section, conversation-based content recommendations had 11.4% (1108/2364) higher completion rates per card than onboarding response-based recommendations (1712/4067; P=.003) and 26.1% higher than random recommendations (534/1440; P=.005). Studied via subject matter experts’ annotations, conversation-based recommendations had a 16.1% higher relevance rate for the top 5 recommended cards, averaged across sessions of varying lengths, compared to a random control (110 conversational sessions). Finally, it was observed that both age and gender variables were sensitive to different recommendation methods, with responsiveness to personalized recommendations being higher if the users were older than 35 years or identified as male. ConclusionsRecommender systems can help scale and supplement digital mental health care with personalized content and self-care recommendations. Onboarding-based recommendations are ideal for “cold starting” the process of recommending content for new users and users that tend to use the app just for content but not for therapy or coaching. The conversation-based recommendation algorithm allows for dynamic recommendations based on information gathered during coaching sessions, which is a critical capability, given the changing nature of mental health needs during treatment. The proposed algorithms are just one step toward the direction of outcome-driven personalization in mental health. Our future work will involve a robust causal evaluation of these algorithms using randomized controlled trials, along with consumer feedback–driven improvement of these algorithms, to drive better clinical outcomes.https://formative.jmir.org/2023/1/e38831 |
| spellingShingle | Akhil Chaturvedi Brandon Aylward Setu Shah Grant Graziani Joan Zhang Bobby Manuel Emmanuel Telewa Stefan Froelich Olalekan Baruwa Prathamesh Param Kulkarni Watson Ξ Sarah Kunkle Content Recommendation Systems in Web-Based Mental Health Care: Real-world Application and Formative Evaluation JMIR Formative Research |
| title | Content Recommendation Systems in Web-Based Mental Health Care: Real-world Application and Formative Evaluation |
| title_full | Content Recommendation Systems in Web-Based Mental Health Care: Real-world Application and Formative Evaluation |
| title_fullStr | Content Recommendation Systems in Web-Based Mental Health Care: Real-world Application and Formative Evaluation |
| title_full_unstemmed | Content Recommendation Systems in Web-Based Mental Health Care: Real-world Application and Formative Evaluation |
| title_short | Content Recommendation Systems in Web-Based Mental Health Care: Real-world Application and Formative Evaluation |
| title_sort | content recommendation systems in web based mental health care real world application and formative evaluation |
| url | https://formative.jmir.org/2023/1/e38831 |
| work_keys_str_mv | AT akhilchaturvedi contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT brandonaylward contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT setushah contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT grantgraziani contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT joanzhang contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT bobbymanuel contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT emmanueltelewa contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT stefanfroelich contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT olalekanbaruwa contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT prathameshparamkulkarni contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT watsonx contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation AT sarahkunkle contentrecommendationsystemsinwebbasedmentalhealthcarerealworldapplicationandformativeevaluation |