Change in employment status and its causal effect on suicidal ideation and depressive symptoms: A marginal structural model with machine learning algorithms
OBJECTIVE: This study aimed to assess the causal effect of a change in employment status on suicidal ideation and depressive symptoms by applying marginal structural models (MSM) with machine-learning (ML) algorithms. METHODS: We analyzed data from the 8–15^th waves (2013–2020) of the Korean Welfare...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nordic Association of Occupational Safety and Health (NOROSH)
2024-04-01
|
| Series: | Scandinavian Journal of Work, Environment & Health |
| Subjects: | |
| Online Access: |
https://www.sjweh.fi/article/4150
|
| _version_ | 1797242610251726848 |
|---|---|
| author | Jaehong Yoon Ji-Hwan Kim Yeonseung Chung Jinsu Park Ja-Ho Leigh Seung-Sup Kim |
| author_facet | Jaehong Yoon Ji-Hwan Kim Yeonseung Chung Jinsu Park Ja-Ho Leigh Seung-Sup Kim |
| author_sort | Jaehong Yoon |
| collection | DOAJ |
| description | OBJECTIVE: This study aimed to assess the causal effect of a change in employment status on suicidal ideation and depressive symptoms by applying marginal structural models (MSM) with machine-learning (ML) algorithms. METHODS: We analyzed data from the 8–15^th waves (2013–2020) of the Korean Welfare Panel Study, a nationally representative longitudinal dataset. Our analysis included 13 294 observations from 3621 participants who had standard employment at baseline (2013–2019). Based on employment status at follow-up year (2014–2020), respondents were classified into two groups: (i) maintained standard employment (reference group), (ii) changed to non-standard employment. Suicidal ideation during the past year and depressive symptoms during the past week were assessed through self-report questionnaire. To apply the ML algorithms to the MSM, we conducted eight ML algorithms to build the propensity score indicating a change in employment status. Then, we applied the MSM to examine the causal effect by using inverse probability weights calculated based on the propensity score from ML algorithms. RESULTS: The random forest algorithm performed best among all algorithms, showing the highest area under the curve 0.702, 95% confidence interval (CI) 0.686–0.718. In the MSM with the random forest algorithm, workers who changed from standard to non-standard employment were 2.07 times more likely to report suicidal ideation compared to those who maintained standard employment (95% CI 1.16–3.70). A similar trend was observed in the analysis of depressive symptoms. CONCLUSIONS: This study found that a change in employment status could lead to a higher risk of suicidal ideation and depressive symptoms. |
| first_indexed | 2024-04-24T18:41:57Z |
| format | Article |
| id | doaj.art-5892c1db94c84c6c96c449a0caa59da0 |
| institution | Directory Open Access Journal |
| issn | 0355-3140 1795-990X |
| language | English |
| last_indexed | 2024-04-24T18:41:57Z |
| publishDate | 2024-04-01 |
| publisher | Nordic Association of Occupational Safety and Health (NOROSH) |
| record_format | Article |
| series | Scandinavian Journal of Work, Environment & Health |
| spelling | doaj.art-5892c1db94c84c6c96c449a0caa59da02024-03-27T11:01:38ZengNordic Association of Occupational Safety and Health (NOROSH)Scandinavian Journal of Work, Environment & Health0355-31401795-990X2024-04-0150321822710.5271/sjweh.41504150Change in employment status and its causal effect on suicidal ideation and depressive symptoms: A marginal structural model with machine learning algorithmsJaehong YoonJi-Hwan KimYeonseung ChungJinsu ParkJa-Ho LeighSeung-Sup Kim0Department of Environmental Health Sciences, Seoul National University, Room 718, Bldg 220, Gwanak-ro 1, Seoul 08826, Republic of Korea.OBJECTIVE: This study aimed to assess the causal effect of a change in employment status on suicidal ideation and depressive symptoms by applying marginal structural models (MSM) with machine-learning (ML) algorithms. METHODS: We analyzed data from the 8–15^th waves (2013–2020) of the Korean Welfare Panel Study, a nationally representative longitudinal dataset. Our analysis included 13 294 observations from 3621 participants who had standard employment at baseline (2013–2019). Based on employment status at follow-up year (2014–2020), respondents were classified into two groups: (i) maintained standard employment (reference group), (ii) changed to non-standard employment. Suicidal ideation during the past year and depressive symptoms during the past week were assessed through self-report questionnaire. To apply the ML algorithms to the MSM, we conducted eight ML algorithms to build the propensity score indicating a change in employment status. Then, we applied the MSM to examine the causal effect by using inverse probability weights calculated based on the propensity score from ML algorithms. RESULTS: The random forest algorithm performed best among all algorithms, showing the highest area under the curve 0.702, 95% confidence interval (CI) 0.686–0.718. In the MSM with the random forest algorithm, workers who changed from standard to non-standard employment were 2.07 times more likely to report suicidal ideation compared to those who maintained standard employment (95% CI 1.16–3.70). A similar trend was observed in the analysis of depressive symptoms. CONCLUSIONS: This study found that a change in employment status could lead to a higher risk of suicidal ideation and depressive symptoms. https://www.sjweh.fi/article/4150 suicideeffectemployment statusdepressive symptomsuicidal ideationprecarious workmachine learningmarginal structural modelalgorithmsocial epidemiologyinverse probability weight |
| spellingShingle | Jaehong Yoon Ji-Hwan Kim Yeonseung Chung Jinsu Park Ja-Ho Leigh Seung-Sup Kim Change in employment status and its causal effect on suicidal ideation and depressive symptoms: A marginal structural model with machine learning algorithms Scandinavian Journal of Work, Environment & Health suicide effect employment status depressive symptom suicidal ideation precarious work machine learning marginal structural model algorithm social epidemiology inverse probability weight |
| title | Change in employment status and its causal effect on suicidal ideation and depressive symptoms: A marginal structural model with machine learning algorithms |
| title_full | Change in employment status and its causal effect on suicidal ideation and depressive symptoms: A marginal structural model with machine learning algorithms |
| title_fullStr | Change in employment status and its causal effect on suicidal ideation and depressive symptoms: A marginal structural model with machine learning algorithms |
| title_full_unstemmed | Change in employment status and its causal effect on suicidal ideation and depressive symptoms: A marginal structural model with machine learning algorithms |
| title_short | Change in employment status and its causal effect on suicidal ideation and depressive symptoms: A marginal structural model with machine learning algorithms |
| title_sort | change in employment status and its causal effect on suicidal ideation and depressive symptoms a marginal structural model with machine learning algorithms |
| topic | suicide effect employment status depressive symptom suicidal ideation precarious work machine learning marginal structural model algorithm social epidemiology inverse probability weight |
| url |
https://www.sjweh.fi/article/4150
|
| work_keys_str_mv | AT jaehongyoon changeinemploymentstatusanditscausaleffectonsuicidalideationanddepressivesymptomsamarginalstructuralmodelwithmachinelearningalgorithms AT jihwankim changeinemploymentstatusanditscausaleffectonsuicidalideationanddepressivesymptomsamarginalstructuralmodelwithmachinelearningalgorithms AT yeonseungchung changeinemploymentstatusanditscausaleffectonsuicidalideationanddepressivesymptomsamarginalstructuralmodelwithmachinelearningalgorithms AT jinsupark changeinemploymentstatusanditscausaleffectonsuicidalideationanddepressivesymptomsamarginalstructuralmodelwithmachinelearningalgorithms AT jaholeigh changeinemploymentstatusanditscausaleffectonsuicidalideationanddepressivesymptomsamarginalstructuralmodelwithmachinelearningalgorithms AT seungsupkim changeinemploymentstatusanditscausaleffectonsuicidalideationanddepressivesymptomsamarginalstructuralmodelwithmachinelearningalgorithms |