Dissertation/ Thesis
Risk Factors for Suicidal Behaviour Among Canadian Civilians and Military Personnel: A Recursive Partitioning Approach
| العنوان: | Risk Factors for Suicidal Behaviour Among Canadian Civilians and Military Personnel: A Recursive Partitioning Approach |
|---|---|
| المؤلفون: | Rusu, Corneliu |
| Thesis Advisors: | Colman, Ian |
| بيانات النشر: | Université d'Ottawa / University of Ottawa, 2018. |
| سنة النشر: | 2018 |
| المجموعة: | Université d'Ottawa |
| مصطلحات موضوعية: | Models of suicidal behaviour, Conditional inference random forests, Canadian Community Health Survey - Mental Health, Canadian Armed Forces Mental Health Survey, Random forests, Machine learning, Variable selection, Recursive partitioning |
| الوصف: | Background: Suicidal behaviour is a major public health problem that has not abated over the past decade. Adopting machine learning algorithms that allow for combining risk factors that may increase the predictive accuracy of models of suicide behaviour is one promising avenue toward effective prevention and treatment. Methods: We used Canadian Community Health Survey – Mental Health and Canadian Forces Mental Health Survey to build conditional inference random forests models of suicidal behaviour in Canadian general population and Canadian Armed Forces. We generated risk algorithms for suicidal behaviour in each sample. We performed within- and between-sample validation and reported the corresponding performance metrics. Results: Only a handful of variables were important in predicting suicidal behaviour in Canadian general population and Canadian Armed Forces. Each model’s performance on within-sample validation was satisfactory, with moderate to high sensitivity and high specificity, while the performance on between-sample validation was conditional on the size and heterogeneity of the training sample. Conclusion: Using conditional inference random forest methodology on large nationally representative mental health surveys has the potential of generating models of suicidal behaviour that not only reflect its complex nature, but indicate that the true positive cases are likely to be captured by this approach. |
| Original Identifier: | oai:ruor.uottawa.ca:10393/37371 |
| نوع الوثيقة: | Thesis |
| وصف الملف: | application/pdf |
| اللغة: | English |
| DOI: | 10.20381/ruor-21640 |
| الاتاحة: | http://hdl.handle.net/10393/37371 |
| رقم الانضمام: | edsndl.uottawa.ca.oai.ruor.uottawa.ca.10393.37371 |
| قاعدة البيانات: | Networked Digital Library of Theses & Dissertations |
| ResultId |
1 |
|---|---|
| Header |
edsndl Networked Digital Library of Theses & Dissertations edsndl.uottawa.ca.oai.ruor.uottawa.ca.10393.37371 818 3 Dissertation/ Thesis dissertation 818.374694824219 |
| PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsndl&AN=edsndl.uottawa.ca.oai.ruor.uottawa.ca.10393.37371&custid=s6537998&authtype=sso |
| FullText |
Array
(
[Availability] => 0
)
Array ( [0] => Array ( [Url] => http://hdl.handle.net/10393/37371# [Name] => EDS - Networked Digital Library of Theses & Dissertations [Category] => fullText [Text] => View record in Networked Digital Library of Theses & Dissertations [MouseOverText] => View record in Networked Digital Library of Theses & Dissertations ) ) |
| Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => Risk Factors for Suicidal Behaviour Among Canadian Civilians and Military Personnel: A Recursive Partitioning Approach
)
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Rusu%2C+Corneliu%22">Rusu, Corneliu</searchLink> ) Array ( [Name] => Author [Label] => Thesis Advisors [Group] => Au [Data] => Colman, Ian ) Array ( [Name] => Publisher [Label] => Publisher Information [Group] => PubInfo [Data] => Université d'Ottawa / University of Ottawa, 2018. ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2018 ) Array ( [Name] => Subset [Label] => Collection [Group] => HoldingsInfo [Data] => Université d'Ottawa ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22Models+of+suicidal+behaviour%22">Models of suicidal behaviour</searchLink><br /><searchLink fieldCode="DE" term="%22Conditional+inference+random+forests%22">Conditional inference random forests</searchLink><br /><searchLink fieldCode="DE" term="%22Canadian+Community+Health+Survey+-+Mental+Health%22">Canadian Community Health Survey - Mental Health</searchLink><br /><searchLink fieldCode="DE" term="%22Canadian+Armed+Forces+Mental+Health+Survey%22">Canadian Armed Forces Mental Health Survey</searchLink><br /><searchLink fieldCode="DE" term="%22Random+forests%22">Random forests</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Variable+selection%22">Variable selection</searchLink><br /><searchLink fieldCode="DE" term="%22Recursive+partitioning%22">Recursive partitioning</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => Background: Suicidal behaviour is a major public health problem that has not abated over the past decade. Adopting machine learning algorithms that allow for combining risk factors that may increase the predictive accuracy of models of suicide behaviour is one promising avenue toward effective prevention and treatment. Methods: We used Canadian Community Health Survey – Mental Health and Canadian Forces Mental Health Survey to build conditional inference random forests models of suicidal behaviour in Canadian general population and Canadian Armed Forces. We generated risk algorithms for suicidal behaviour in each sample. We performed within- and between-sample validation and reported the corresponding performance metrics. Results: Only a handful of variables were important in predicting suicidal behaviour in Canadian general population and Canadian Armed Forces. Each model’s performance on within-sample validation was satisfactory, with moderate to high sensitivity and high specificity, while the performance on between-sample validation was conditional on the size and heterogeneity of the training sample. Conclusion: Using conditional inference random forest methodology on large nationally representative mental health surveys has the potential of generating models of suicidal behaviour that not only reflect its complex nature, but indicate that the true positive cases are likely to be captured by this approach. ) Array ( [Name] => AN [Label] => Original Identifier [Group] => ID [Data] => oai:ruor.uottawa.ca:10393/37371 ) Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => Thesis ) Array ( [Name] => Format [Label] => File Description [Group] => SrcInfo [Data] => application/pdf ) Array ( [Name] => Language [Label] => Language [Group] => Lang [Data] => English ) Array ( [Name] => DOI [Label] => DOI [Group] => ID [Data] => 10.20381/ruor-21640 ) Array ( [Name] => URL [Label] => Availability [Group] => URL [Data] => http://hdl.handle.net/10393/37371 ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsndl.uottawa.ca.oai.ruor.uottawa.ca.10393.37371 ) |
| RecordInfo |
Array
(
[BibEntity] => Array
(
[Identifiers] => Array
(
[0] => Array
(
[Type] => doi
[Value] => 10.20381/ruor-21640
)
)
[Languages] => Array
(
[0] => Array
(
[Text] => English
)
)
[Subjects] => Array
(
[0] => Array
(
[SubjectFull] => Models of suicidal behaviour
[Type] => general
)
[1] => Array
(
[SubjectFull] => Conditional inference random forests
[Type] => general
)
[2] => Array
(
[SubjectFull] => Canadian Community Health Survey - Mental Health
[Type] => general
)
[3] => Array
(
[SubjectFull] => Canadian Armed Forces Mental Health Survey
[Type] => general
)
[4] => Array
(
[SubjectFull] => Random forests
[Type] => general
)
[5] => Array
(
[SubjectFull] => Machine learning
[Type] => general
)
[6] => Array
(
[SubjectFull] => Variable selection
[Type] => general
)
[7] => Array
(
[SubjectFull] => Recursive partitioning
[Type] => general
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Risk Factors for Suicidal Behaviour Among Canadian Civilians and Military Personnel: A Recursive Partitioning Approach
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Rusu, Corneliu
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 05
[M] => 04
[Type] => published
[Y] => 2018
)
)
[Identifiers] => Array
(
[0] => Array
(
[Type] => issn-locals
[Value] => edsndl
)
)
)
)
)
)
)
|
| IllustrationInfo |