Academic Journal
Προβολή σε EDS

Predicting positive youth development among Chinese adolescents: A machine learning approach using multiwave longitudinal data.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Predicting positive youth development among Chinese adolescents: A machine learning approach using multiwave longitudinal data.
Συγγραφείς: Liu Z; Institute of Developmental Psychology, Beijing Normal University, Beijing, China., Lu Z; Institute of Developmental Psychology, Beijing Normal University, Beijing, China.; Department of Sociology, McGill University, Montréal, Canada., Wang Y; Department of Psychology, Hangzhou Normal University, Hangzhou, China., Lin D; Institute of Developmental Psychology, Beijing Normal University, Beijing, China.
Πηγή: Applied psychology. Health and well-being [Appl Psychol Health Well Being] 2026 Oct; Vol. 18 (5), pp. e70211.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Blackwell Country of Publication: England NLM ID: 101502957 Publication Model: Print Cited Medium: Internet ISSN: 1758-0854 (Electronic) Linking ISSN: 17580854 NLM ISO Abbreviation: Appl Psychol Health Well Being Subsets: MEDLINE
Imprint Name(s): Original Publication: Oxford : Blackwell
Ιατρικοί όροι (MeSH): Depression*/psychology , Loneliness*/psychology , Adolescent Development* , Boosting Machine Learning Algorithms* , Prediction Algorithms*, Adolescent ; Child ; Female ; Humans ; Male ; China ; Longitudinal Studies ; East Asian People
Περίληψη: Despite growing recognition that positive youth development (PYD) depends on the dynamic interaction of individual and ecological resources, existing studies rely on linear models that cannot capture high-dimensional, nonlinear predictor configurations. This study applied machine learning to four-wave longitudinal data from 5019 Chinese adolescents (ages 9-19) to identify the key predictors of PYD at T4 (controlling for prior PYD at T3), measured by the Chinese 4Cs model (Character, Competence, Confidence, Connection). We compared 12 algorithms; CatBoost achieved the best prediction ( INLINEMATH  = .816). SHAP analysis identified school psychological climate, depression, and parental loneliness as the top three predictors. Heterogeneity analyses revealed an age gradient: School climate dominated for primary and middle school students, whereas parental loneliness dominated for high school students. Student type analyses uncovered three distinct developmental pathways: an aspirational pathway characterized by social mobility belief for migrant children, a relational pathway characterized by parental loneliness for left-behind and urban children, and a clinical pathway characterized by depression for rural ordinary children. These findings provide empirical support for differentiated, context-sensitive intervention strategies targeting PYD across diverse Chinese adolescent populations.
(© 2026 International Association of Applied Psychology.)
References: Children (Basel). 2025 Aug 18;12(8):. (PMID: 40868534)
J Child Psychol Psychiatry. 2026 Jan;67(1):55-66. (PMID: 40757405)
J Sch Health. 2018 Feb;88(2):101-111. (PMID: 29333642)
Nat Mach Intell. 2020 Jan;2(1):56-67. (PMID: 32607472)
Appl Psychol Health Well Being. 2026 Oct;18(5):e70211. (PMID: 42698279)
Appl Psychol Health Well Being. 2025 Feb 25;17(1):e12624. (PMID: 39523935)
J Child Psychol Psychiatry. 2011 Oct;52(10):1052-62. (PMID: 21834918)
Scand J Psychol. 2024 Oct;65(5):858-869. (PMID: 38785185)
Bioinformatics. 2012 Jan 1;28(1):112-8. (PMID: 22039212)
Int J Environ Res Public Health. 2022 Jun 10;19(12):. (PMID: 35742383)
Front Psychol. 2024 Jul 02;15:1407338. (PMID: 39015327)
J Sch Health. 2017 Jan;87(1):71-80. (PMID: 27917486)
Adv Child Dev Behav. 2011;41:197-230. (PMID: 23259193)
J Educ Psychol. 2015 Feb 1;107(1):309-320. (PMID: 25937669)
J Youth Adolesc. 2024 Aug;53(8):1903-1917. (PMID: 38622470)
Depress Anxiety. 2003;18(2):76-82. (PMID: 12964174)
BMC Nurs. 2021 Jul 5;20(1):119. (PMID: 34225712)
Int J Adolesc Med Health. 2013;25(4):335-44. (PMID: 23612532)
Int J Environ Res Public Health. 2022 Jan 18;19(3):. (PMID: 35162088)
BMC Psychol. 2025 Dec 9;14(1):45. (PMID: 41366508)
J Adolesc. 2025 Jan;97(1):180-195. (PMID: 39315619)
Appl Psychol Health Well Being. 2025 Feb;17(1):e12635. (PMID: 39668656)
Clin Transl Sci. 2024 Nov;17(11):e70056. (PMID: 39463176)
Soc Sci Med. 2015 May;132:261-9. (PMID: 25176335)
Health Psychol. 2000 Nov;19(6):586-92. (PMID: 11129362)
J Adolesc Health. 2021 Apr;68(4):676-682. (PMID: 33583684)
Nat Ment Health. 2024;2(10):1217-1230. (PMID: 39464304)
Lancet Psychiatry. 2025 Oct;12(10):723. (PMID: 40967722)
Child Dev. 2012 Jan-Feb;83(1):120-36. (PMID: 22181046)
Annu Rev Clin Psychol. 2021 May 7;17:521-549. (PMID: 33534615)
J Youth Adolesc. 1987 Dec;16(6):561-77. (PMID: 24277491)
Grant Information: 32471116 National Natural Science Foundation of China
Contributed Indexing: Keywords: Chinese adolescents; SHAP; heterogeneity analysis; longitudinal prediction; machine learning; positive youth development
Entry Date(s): Date Created: 20260905 Date Completed: 20260905 Latest Revision: 20260908
Update Code: 20260909
PubMed Central ID: PMC13545513
DOI: 10.1111/aphw.70211
PMID: 42698279
Βάση Δεδομένων: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=17580854&ISBN=&volume=18&issue=5&date=20261001&spage=e70211&pages=e70211&title=Applied psychology. Health and well-being&atitle=Predicting%20positive%20youth%20development%20among%20Chinese%20adolescents%3A%20A%20machine%20learning%20approach%20using%20multiwave%20longitudinal%20data.&aulast=Liu%20Z&id=DOI:10.1111/aphw.70211
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42698279
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Predicting positive youth development among Chinese adolescents: A machine learning approach using multiwave longitudinal data.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Liu+Z%22">Liu Z</searchLink>; Institute of Developmental Psychology, Beijing Normal University, Beijing, China.<br /><searchLink fieldCode="AU" term="%22Lu+Z%22">Lu Z</searchLink>; Institute of Developmental Psychology, Beijing Normal University, Beijing, China.; Department of Sociology, McGill University, Montréal, Canada.<br /><searchLink fieldCode="AU" term="%22Wang+Y%22">Wang Y</searchLink>; Department of Psychology, Hangzhou Normal University, Hangzhou, China.<br /><searchLink fieldCode="AU" term="%22Lin+D%22">Lin D</searchLink>; Institute of Developmental Psychology, Beijing Normal University, Beijing, China.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22101502957%22">Applied psychology. Health and well-being</searchLink> [Appl Psychol Health Well Being] 2026 Oct; Vol. 18 (5), pp. e70211.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Blackwell%22">Blackwell </searchLink><i>Country of Publication: </i>England <i>NLM ID: </i>101502957 <i>Publication Model: </i>Print <i>Cited Medium: </i>Internet <i>ISSN: </i>1758-0854 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2217580854%22">17580854 </searchLink><i>NLM ISO Abbreviation: </i>Appl Psychol Health Well Being <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: Oxford : Blackwell
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Depression%22">Depression*</searchLink>/<searchLink fieldCode="MM" term="%22Depression+psychology%22">psychology</searchLink> <br /><searchLink fieldCode="MM" term="%22Loneliness%22">Loneliness*</searchLink>/<searchLink fieldCode="MM" term="%22Loneliness+psychology%22">psychology</searchLink> <br /><searchLink fieldCode="MM" term="%22Adolescent+Development%22">Adolescent Development*</searchLink> <br /><searchLink fieldCode="MM" term="%22Boosting+Machine+Learning+Algorithms%22">Boosting Machine Learning Algorithms*</searchLink> <br /><searchLink fieldCode="MM" term="%22Prediction+Algorithms%22">Prediction Algorithms*</searchLink><br /><searchLink fieldCode="MH" term="%22Adolescent%22">Adolescent</searchLink> ; <searchLink fieldCode="MH" term="%22Child%22">Child</searchLink> ; <searchLink fieldCode="MH" term="%22Female%22">Female</searchLink> ; <searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Male%22">Male</searchLink> ; <searchLink fieldCode="MH" term="%22China%22">China</searchLink> ; <searchLink fieldCode="MH" term="%22Longitudinal+Studies%22">Longitudinal Studies</searchLink> ; <searchLink fieldCode="MH" term="%22East+Asian+People%22">East Asian People</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Despite growing recognition that positive youth development (PYD) depends on the dynamic interaction of individual and ecological resources, existing studies rely on linear models that cannot capture high-dimensional, nonlinear predictor configurations. This study applied machine learning to four-wave longitudinal data from 5019 Chinese adolescents (ages 9-19) to identify the key predictors of PYD at T4 (controlling for prior PYD at T3), measured by the Chinese 4Cs model (Character, Competence, Confidence, Connection). We compared 12 algorithms; CatBoost achieved the best prediction ( INLINEMATH  = .816). SHAP analysis identified school psychological climate, depression, and parental loneliness as the top three predictors. Heterogeneity analyses revealed an age gradient: School climate dominated for primary and middle school students, whereas parental loneliness dominated for high school students. Student type analyses uncovered three distinct developmental pathways: an aspirational pathway characterized by social mobility belief for migrant children, a relational pathway characterized by parental loneliness for left-behind and urban children, and a clinical pathway characterized by depression for rural ordinary children. These findings provide empirical support for differentiated, context-sensitive intervention strategies targeting PYD across diverse Chinese adolescent populations.<br /> (© 2026 International Association of Applied Psychology.)
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Children (Basel). 2025 Aug 18;12(8):. (PMID: <searchLink fieldCode="PM" term="%2240868534%22">40868534)</searchLink><br />J Child Psychol Psychiatry. 2026 Jan;67(1):55-66. (PMID: <searchLink fieldCode="PM" term="%2240757405%22">40757405)</searchLink><br />J Sch Health. 2018 Feb;88(2):101-111. (PMID: <searchLink fieldCode="PM" term="%2229333642%22">29333642)</searchLink><br />Nat Mach Intell. 2020 Jan;2(1):56-67. (PMID: <searchLink fieldCode="PM" term="%2232607472%22">32607472)</searchLink><br />Appl Psychol Health Well Being. 2026 Oct;18(5):e70211. (PMID: <searchLink fieldCode="PM" term="%2242698279%22">42698279)</searchLink><br />Appl Psychol Health Well Being. 2025 Feb 25;17(1):e12624. (PMID: <searchLink fieldCode="PM" term="%2239523935%22">39523935)</searchLink><br />J Child Psychol Psychiatry. 2011 Oct;52(10):1052-62. (PMID: <searchLink fieldCode="PM" term="%2221834918%22">21834918)</searchLink><br />Scand J Psychol. 2024 Oct;65(5):858-869. (PMID: <searchLink fieldCode="PM" term="%2238785185%22">38785185)</searchLink><br />Bioinformatics. 2012 Jan 1;28(1):112-8. (PMID: <searchLink fieldCode="PM" term="%2222039212%22">22039212)</searchLink><br />Int J Environ Res Public Health. 2022 Jun 10;19(12):. (PMID: <searchLink fieldCode="PM" term="%2235742383%22">35742383)</searchLink><br />Front Psychol. 2024 Jul 02;15:1407338. (PMID: <searchLink fieldCode="PM" term="%2239015327%22">39015327)</searchLink><br />J Sch Health. 2017 Jan;87(1):71-80. (PMID: <searchLink fieldCode="PM" term="%2227917486%22">27917486)</searchLink><br />Adv Child Dev Behav. 2011;41:197-230. (PMID: <searchLink fieldCode="PM" term="%2223259193%22">23259193)</searchLink><br />J Educ Psychol. 2015 Feb 1;107(1):309-320. (PMID: <searchLink fieldCode="PM" term="%2225937669%22">25937669)</searchLink><br />J Youth Adolesc. 2024 Aug;53(8):1903-1917. (PMID: <searchLink fieldCode="PM" term="%2238622470%22">38622470)</searchLink><br />Depress Anxiety. 2003;18(2):76-82. (PMID: <searchLink fieldCode="PM" term="%2212964174%22">12964174)</searchLink><br />BMC Nurs. 2021 Jul 5;20(1):119. (PMID: <searchLink fieldCode="PM" term="%2234225712%22">34225712)</searchLink><br />Int J Adolesc Med Health. 2013;25(4):335-44. (PMID: <searchLink fieldCode="PM" term="%2223612532%22">23612532)</searchLink><br />Int J Environ Res Public Health. 2022 Jan 18;19(3):. (PMID: <searchLink fieldCode="PM" term="%2235162088%22">35162088)</searchLink><br />BMC Psychol. 2025 Dec 9;14(1):45. (PMID: <searchLink fieldCode="PM" term="%2241366508%22">41366508)</searchLink><br />J Adolesc. 2025 Jan;97(1):180-195. (PMID: <searchLink fieldCode="PM" term="%2239315619%22">39315619)</searchLink><br />Appl Psychol Health Well Being. 2025 Feb;17(1):e12635. (PMID: <searchLink fieldCode="PM" term="%2239668656%22">39668656)</searchLink><br />Clin Transl Sci. 2024 Nov;17(11):e70056. (PMID: <searchLink fieldCode="PM" term="%2239463176%22">39463176)</searchLink><br />Soc Sci Med. 2015 May;132:261-9. (PMID: <searchLink fieldCode="PM" term="%2225176335%22">25176335)</searchLink><br />Health Psychol. 2000 Nov;19(6):586-92. (PMID: <searchLink fieldCode="PM" term="%2211129362%22">11129362)</searchLink><br />J Adolesc Health. 2021 Apr;68(4):676-682. (PMID: <searchLink fieldCode="PM" term="%2233583684%22">33583684)</searchLink><br />Nat Ment Health. 2024;2(10):1217-1230. (PMID: <searchLink fieldCode="PM" term="%2239464304%22">39464304)</searchLink><br />Lancet Psychiatry. 2025 Oct;12(10):723. (PMID: <searchLink fieldCode="PM" term="%2240967722%22">40967722)</searchLink><br />Child Dev. 2012 Jan-Feb;83(1):120-36. (PMID: <searchLink fieldCode="PM" term="%2222181046%22">22181046)</searchLink><br />Annu Rev Clin Psychol. 2021 May 7;17:521-549. (PMID: <searchLink fieldCode="PM" term="%2233534615%22">33534615)</searchLink><br />J Youth Adolesc. 1987 Dec;16(6):561-77. (PMID: <searchLink fieldCode="PM" term="%2224277491%22">24277491)</searchLink>
– Name: GrantInfo
  Label: Grant Information
  Group: Grant
  Data: 32471116 National Natural Science Foundation of China
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>Chinese adolescents; SHAP; heterogeneity analysis; longitudinal prediction; machine learning; positive youth development
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260905 <i>Date Completed: </i>20260905 <i>Latest Revision: </i>20260908
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260909
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13545513
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1111/aphw.70211
– Name: AN
  Label: PMID
  Group: ID
  Data: 42698279
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42698279
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/aphw.70211
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: e70211
    Subjects:
      – SubjectFull: Adolescent
        Type: general
      – SubjectFull: Child
        Type: general
      – SubjectFull: Female
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Male
        Type: general
      – SubjectFull: China
        Type: general
      – SubjectFull: Longitudinal Studies
        Type: general
      – SubjectFull: East Asian People
        Type: general
      – SubjectFull: Depression psychology
        Type: general
      – SubjectFull: Loneliness psychology
        Type: general
      – SubjectFull: Adolescent Development
        Type: general
      – SubjectFull: Boosting Machine Learning Algorithms
        Type: general
      – SubjectFull: Prediction Algorithms
        Type: general
    Titles:
      – TitleFull: Predicting positive youth development among Chinese adolescents: A machine learning approach using multiwave longitudinal data.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Liu Z
      – PersonEntity:
          Name:
            NameFull: Lu Z
      – PersonEntity:
          Name:
            NameFull: Wang Y
      – PersonEntity:
          Name:
            NameFull: Lin D
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: 2026 Oct
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1758-0854
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: Applied psychology. Health and well-being
              Type: main
ResultId 1