Prediction Models for Suicide Attempts among Adolescents Using Machine Learning Techniques
Objective: Suicide attempts (SAs) in adolescents are difficult to predict although it is a leading cause of death among adolescents. This study aimed to develop and evaluate SA prediction models based on six different machine learning (ML) algorithms for Korean adolescents using data from online surveys.
Methods: Data were extracted from the 2011-2018 Korea Youth Risk Behavior Survey (KYRBS), an ongoing annual national survey. The participants comprised 468,482 nationally representative adolescents from 400 middle and 400 high schools, aged 12 to 18. The models were trained using several classic ML methods and then tested on internal and external independent datasets; performance metrics were calculated. Data analysis was performed from March 2020 to June 2020.
Results: Among the 468,482 adolescents included in the analysis, 15,012 cases (3.2%) were identified as having made an SA. Three features (suicidal ideation, suicide planning, and grade) were identified as the most important predictors. The performance of the six ML models on the internal testing dataset was good, with both the area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) ranging from 0.92 to 0.94. Although the AUROC of all models on the external testing dataset (2018 KYRBS) ranged from 0.93 to 0.95, the AUPRC of the models was approximately 0.5.
Conclusion: The developed and validated SA prediction models can be applied to detect high risks of SA. This approach could facilitate early intervention in the suicide crisis and may ultimately contribute to suicide prevention for adolescents.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:20 |
|---|---|
| Enthalten in: |
Clinical psychopharmacology and neuroscience : the official scientific journal of the Korean College of Neuropsychopharmacology - 20(2022), 4 vom: 30. Nov., Seite 609-620 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Lim, Jae Seok [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Adolescents |
|---|
| Anmerkungen: |
Date Revised 02.12.2022 published: Print Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.9758/cpn.2022.20.4.609 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM347783139 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM347783139 | ||
| 003 | DE-627 | ||
| 005 | 20231226034645.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.9758/cpn.2022.20.4.609 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1159.xml |
| 035 | |a (DE-627)NLM347783139 | ||
| 035 | |a (NLM)36263637 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Lim, Jae Seok |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Prediction Models for Suicide Attempts among Adolescents Using Machine Learning Techniques |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 02.12.2022 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Objective: Suicide attempts (SAs) in adolescents are difficult to predict although it is a leading cause of death among adolescents. This study aimed to develop and evaluate SA prediction models based on six different machine learning (ML) algorithms for Korean adolescents using data from online surveys | ||
| 520 | |a Methods: Data were extracted from the 2011-2018 Korea Youth Risk Behavior Survey (KYRBS), an ongoing annual national survey. The participants comprised 468,482 nationally representative adolescents from 400 middle and 400 high schools, aged 12 to 18. The models were trained using several classic ML methods and then tested on internal and external independent datasets; performance metrics were calculated. Data analysis was performed from March 2020 to June 2020 | ||
| 520 | |a Results: Among the 468,482 adolescents included in the analysis, 15,012 cases (3.2%) were identified as having made an SA. Three features (suicidal ideation, suicide planning, and grade) were identified as the most important predictors. The performance of the six ML models on the internal testing dataset was good, with both the area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) ranging from 0.92 to 0.94. Although the AUROC of all models on the external testing dataset (2018 KYRBS) ranged from 0.93 to 0.95, the AUPRC of the models was approximately 0.5 | ||
| 520 | |a Conclusion: The developed and validated SA prediction models can be applied to detect high risks of SA. This approach could facilitate early intervention in the suicide crisis and may ultimately contribute to suicide prevention for adolescents | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Adolescents | |
| 650 | 4 | |a Attempted suicide | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Suicide | |
| 700 | 1 | |a Yang, Chan-Mo |e verfasserin |4 aut | |
| 700 | 1 | |a Baek, Ju-Won |e verfasserin |4 aut | |
| 700 | 1 | |a Lee, Sang-Yeol |e verfasserin |4 aut | |
| 700 | 1 | |a Kim, Bung-Nyun |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Clinical psychopharmacology and neuroscience : the official scientific journal of the Korean College of Neuropsychopharmacology |d 2011 |g 20(2022), 4 vom: 30. Nov., Seite 609-620 |w (DE-627)NLM225213141 |x 1738-1088 |7 nnns |
| 773 | 1 | 8 | |g volume:20 |g year:2022 |g number:4 |g day:30 |g month:11 |g pages:609-620 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.9758/cpn.2022.20.4.609 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 20 |j 2022 |e 4 |b 30 |c 11 |h 609-620 | ||