Machine learning identifies a COVID-19-specific phenotype in university students using a mental health app
Background: Advances in smartphone technology have allowed people to access mental healthcare via digital apps from wherever and whenever they choose. University students experience a high burden of mental health concerns. Although these apps improve mental health symptoms, user engagement has remai...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | Internet Interventions |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214782923000660 |
| _version_ | 1797405428613644288 |
|---|---|
| author | Artur Shvetcov Alexis Whitton Suranga Kasturi Wu-Yi Zheng Joanne Beames Omar Ibrahim Jin Han Leonard Hoon Kon Mouzakis Sunil Gupta Svetha Venkatesh Helen Christensen Jill Newby |
| author_facet | Artur Shvetcov Alexis Whitton Suranga Kasturi Wu-Yi Zheng Joanne Beames Omar Ibrahim Jin Han Leonard Hoon Kon Mouzakis Sunil Gupta Svetha Venkatesh Helen Christensen Jill Newby |
| author_sort | Artur Shvetcov |
| collection | DOAJ |
| description | Background: Advances in smartphone technology have allowed people to access mental healthcare via digital apps from wherever and whenever they choose. University students experience a high burden of mental health concerns. Although these apps improve mental health symptoms, user engagement has remained low. Studies have shown that users can be subgrouped based on unique characteristics that just-in-time adaptive interventions (JITAIs) can use to improve engagement. To date, however, no studies have examined the effect of the COVID-19 pandemic on these subgroups. Objective: Here, we sought to examine user subgroup characteristics across three COVID-19-specific timepoints: during lockdown, immediately following lockdown, and three months after lockdown ended. Methods: To do this, we used a two-step machine learning approach combining unsupervised and supervised machine learning. Results: We demonstrate that there are three unique subgroups of university students who access mental health apps. Two of these, with either higher or lower mental well-being, were defined by characteristics that were stable across COVID-19 timepoints. The third, situational well-being, had characteristics that were timepoint-dependent, suggesting that they are highly influenced by traumatic stressors and stressful situations. This subgroup also showed feelings and behaviours consistent with burnout. Conclusions: Overall, our findings clearly suggest that user subgroups are unique: they have different characteristics and therefore likely have different mental healthcare goals. Our findings also highlight the importance of including questions and additional interventions targeting traumatic stress(ors), reason(s) for use, and burnout in JITAI-style mental health apps to improve engagement. |
| first_indexed | 2024-03-09T03:10:48Z |
| format | Article |
| id | doaj.art-429743ec694443cda57208b36ff8f042 |
| institution | Directory Open Access Journal |
| issn | 2214-7829 |
| language | English |
| last_indexed | 2024-03-09T03:10:48Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Internet Interventions |
| spelling | doaj.art-429743ec694443cda57208b36ff8f0422023-12-04T05:21:56ZengElsevierInternet Interventions2214-78292023-12-0134100666Machine learning identifies a COVID-19-specific phenotype in university students using a mental health appArtur Shvetcov0Alexis Whitton1Suranga Kasturi2Wu-Yi Zheng3Joanne Beames4Omar Ibrahim5Jin Han6Leonard Hoon7Kon Mouzakis8Sunil Gupta9Svetha Venkatesh10Helen Christensen11Jill Newby12Black Dog Institute, UNSW, Sydney, NSW, Australia; Corresponding author.Black Dog Institute, UNSW, Sydney, NSW, AustraliaBlack Dog Institute, UNSW, Sydney, NSW, AustraliaBlack Dog Institute, UNSW, Sydney, NSW, AustraliaBlack Dog Institute, UNSW, Sydney, NSW, AustraliaBlack Dog Institute, UNSW, Sydney, NSW, AustraliaBlack Dog Institute, UNSW, Sydney, NSW, AustraliaApplied Artificial Intelligence Institute, Deakin University, Geelong, VIC, AustraliaApplied Artificial Intelligence Institute, Deakin University, Geelong, VIC, AustraliaApplied Artificial Intelligence Institute, Deakin University, Geelong, VIC, AustraliaApplied Artificial Intelligence Institute, Deakin University, Geelong, VIC, AustraliaBlack Dog Institute, UNSW, Sydney, NSW, AustraliaBlack Dog Institute, UNSW, Sydney, NSW, AustraliaBackground: Advances in smartphone technology have allowed people to access mental healthcare via digital apps from wherever and whenever they choose. University students experience a high burden of mental health concerns. Although these apps improve mental health symptoms, user engagement has remained low. Studies have shown that users can be subgrouped based on unique characteristics that just-in-time adaptive interventions (JITAIs) can use to improve engagement. To date, however, no studies have examined the effect of the COVID-19 pandemic on these subgroups. Objective: Here, we sought to examine user subgroup characteristics across three COVID-19-specific timepoints: during lockdown, immediately following lockdown, and three months after lockdown ended. Methods: To do this, we used a two-step machine learning approach combining unsupervised and supervised machine learning. Results: We demonstrate that there are three unique subgroups of university students who access mental health apps. Two of these, with either higher or lower mental well-being, were defined by characteristics that were stable across COVID-19 timepoints. The third, situational well-being, had characteristics that were timepoint-dependent, suggesting that they are highly influenced by traumatic stressors and stressful situations. This subgroup also showed feelings and behaviours consistent with burnout. Conclusions: Overall, our findings clearly suggest that user subgroups are unique: they have different characteristics and therefore likely have different mental healthcare goals. Our findings also highlight the importance of including questions and additional interventions targeting traumatic stress(ors), reason(s) for use, and burnout in JITAI-style mental health apps to improve engagement.http://www.sciencedirect.com/science/article/pii/S2214782923000660Artificial intelligenceMachine learningUniversity studentsMental healthMobile applications |
| spellingShingle | Artur Shvetcov Alexis Whitton Suranga Kasturi Wu-Yi Zheng Joanne Beames Omar Ibrahim Jin Han Leonard Hoon Kon Mouzakis Sunil Gupta Svetha Venkatesh Helen Christensen Jill Newby Machine learning identifies a COVID-19-specific phenotype in university students using a mental health app Internet Interventions Artificial intelligence Machine learning University students Mental health Mobile applications |
| title | Machine learning identifies a COVID-19-specific phenotype in university students using a mental health app |
| title_full | Machine learning identifies a COVID-19-specific phenotype in university students using a mental health app |
| title_fullStr | Machine learning identifies a COVID-19-specific phenotype in university students using a mental health app |
| title_full_unstemmed | Machine learning identifies a COVID-19-specific phenotype in university students using a mental health app |
| title_short | Machine learning identifies a COVID-19-specific phenotype in university students using a mental health app |
| title_sort | machine learning identifies a covid 19 specific phenotype in university students using a mental health app |
| topic | Artificial intelligence Machine learning University students Mental health Mobile applications |
| url | http://www.sciencedirect.com/science/article/pii/S2214782923000660 |
| work_keys_str_mv | AT arturshvetcov machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT alexiswhitton machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT surangakasturi machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT wuyizheng machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT joannebeames machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT omaribrahim machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT jinhan machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT leonardhoon machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT konmouzakis machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT sunilgupta machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT svethavenkatesh machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT helenchristensen machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp AT jillnewby machinelearningidentifiesacovid19specificphenotypeinuniversitystudentsusingamentalhealthapp |