A machine learning approach to predict e-cigarette use and dependence among Ontario youth.

Jiamin Shi, Rui Fu, Hayley Hamilton, Michael Chaiton
Author Information
  1. Jiamin Shi: Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada.
  2. Rui Fu: Institute for Mental Health Policy Research, Centre for Addiction and Mental Health, Toronto, Ontario, Canada.
  3. Hayley Hamilton: Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada.
  4. Michael Chaiton: Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada.

Abstract

INTRODUCTION: We developed separate random forest algorithms to predict e-cigarette (vaping) ever use and daily use among Ontario youth, and subsequently examined predictor importance and statistical interaction.
METHODS: This cross-sectional study used a representative sample of Ontario elementary and high school students in 2019 (N = 6471). Vaping frequency over the last 12 months was used to define ever-vaping and daily vaping. We considered a large set of individual characteristics as potential correlates for ever-vaping (176 variables) and daily vaping (179 variables). Using cross-validation, we developed random forest algorithms and evaluated model performance based on the C-index, a measure to assess the discriminatory ability of a model, for both outcomes. Further, the top 10 correlates were identified by relative importance score calculation and their interaction with sociodemographic characteristics.
RESULTS: There were 2064 (31.9%) ever-vapers, and 490 (7.6%) of the respondents were daily users. The random forest algorithms for both outcomes achieved high performance, with C-index over 0.90. The top 10 correlates of daily vaping included use of caffeine, cannabis and tobacco, source and type of e-cigarette and absence in last 20 school days. Those of ever-vaping included school size, use of alcohol, cannabis and tobacco; 9 of the top 10 ever-vaping correlates demonstrated interactions with ethnicity.
CONCLUSION: Machine learning is a promising methodology for identifying the risks of ever-vaping and daily vaping. Furthermore, it enables the identification of important correlates and the assessment of complex intersections, which may inform future longitudinal studies to customize public health policies for targeted population subgroups.

Keywords

References

  1. World Neurosurg. 2018 Jan;109:476-486.e1 [PMID: 28986230]
  2. JAMA. 2018 Apr 3;319(13):1317-1318 [PMID: 29532063]
  3. Tob Control. 2021 Aug 27;: [PMID: 34452986]
  4. Biomed J. 2021 Jun;44(3):252-259 [PMID: 33039378]
  5. Drug Alcohol Depend. 2020 Nov 1;216:108320 [PMID: 33039921]
  6. Cleve Clin J Med. 2019 Dec;86(12):789-798 [PMID: 31821136]
  7. Can J Cardiol. 2021 Sep;37(9):1322-1331 [PMID: 33276049]
  8. Health Psychol. 2000 Nov;19(6):586-92 [PMID: 11129362]
  9. J Med Internet Res. 2016 Dec 16;18(12):e323 [PMID: 27986644]
  10. BMJ. 2019 Jun 20;365:l2219 [PMID: 31221636]
  11. Am J Prev Med. 2016 Nov;51(5):767-778 [PMID: 27180028]
  12. Pain Med. 2017 Jan 1;18(1):107-115 [PMID: 27252307]
  13. JAMA Pediatr. 2014 Jul;168(7):610-7 [PMID: 24604023]
  14. BMC Med Inform Decis Mak. 2018 Dec 12;18(Suppl 4):122 [PMID: 30537977]
  15. Drug Alcohol Depend. 2018 Jul 1;188:60-63 [PMID: 29753155]
  16. Sci Rep. 2017 Mar 10;7:43955 [PMID: 28281663]
  17. JAMA Netw Open. 2020 Feb 5;3(2):e1921513 [PMID: 32074292]
  18. Dig Dis Sci. 2019 Aug;64(8):2078-2087 [PMID: 31055722]
  19. Front Aging Neurosci. 2017 Oct 06;9:329 [PMID: 29056906]
  20. Nicotine Tob Res. 2015 Feb;17(2):186-92 [PMID: 25332459]
  21. Addict Behav. 2017 Mar;66:55-59 [PMID: 27875790]
  22. Paediatr Child Health. 2020 Jun;25(Suppl 1):S16-S20 [PMID: 33390752]
  23. Nicotine Tob Res. 2021 Jan 7;23(1):115-123 [PMID: 32208484]
  24. Nature. 2019 Aug;572(7767):116-119 [PMID: 31367026]
  25. J Clin Med. 2021 Mar 02;10(5): [PMID: 33801175]
  26. Tob Use Insights. 2020 Dec 28;13:1179173X20977486 [PMID: 33447117]
  27. Law Hum Behav. 2005 Oct;29(5):615-20 [PMID: 16254746]

MeSH Term

Adolescent
Cross-Sectional Studies
Electronic Nicotine Delivery Systems
Humans
Machine Learning
Ontario
Vaping

Word Cloud

Created with Highcharts 10.0.0vapingdailyuseever-vapingcorrelatesOntariorandomforestalgorithmse-cigaretteyouthschooltop10learningdevelopedpredictamongimportanceinteractionusedhighlastcharacteristicsvariablesmodelperformanceC-indexoutcomesincludedcannabistobaccomachineINTRODUCTION:separateeversubsequentlyexaminedpredictorstatisticalMETHODS:cross-sectionalstudyrepresentativesampleelementarystudents2019N=6471Vapingfrequency12monthsdefineconsideredlargesetindividualpotential176179Usingcross-validationevaluatedbasedmeasureassessdiscriminatoryabilityidentifiedrelativescorecalculationsociodemographicRESULTS:2064319%ever-vapers49076%respondentsusersachieved090caffeinesourcetypeabsence20dayssizealcohol9demonstratedinteractionsethnicityCONCLUSION:MachinepromisingmethodologyidentifyingrisksFurthermoreenablesidentificationimportantassessmentcomplexintersectionsmayinformfuturelongitudinalstudiescustomizepublichealthpoliciestargetedpopulationsubgroupsapproachdependencesmoking

Similar Articles

Cited By (8)