Machine learning algorithms for predicting smokeless tobacco status among women in Northeastern States, India

Singh, Kh. Jitenkumar; Meitei, A. Jiran; Alee, Nongzaimayum Tawfeeq; Kriina, Mosoniro; Haobijam, Nirendrakumar Singh

doi:10.1007/s13198-022-01720-3

Cited by 1 publication

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the high accuracy value obtained with the RF algorithm, this value can be improved using different algorithms. This result supports the findings obtained from previous studies conducted by Singh et al (2022) On the other hand, there have been some limitations concerning attributes used in the analyses. Some important questions could not be included, such as parents' smoking status and the resident type of the respondents in the analyses.…”

Section: Discussionsupporting

confidence: 90%

“…According to a study by Jitenkumar Singh, Jiran Meitei, Alee, Kriina, and Haobijam (2022), the RF algorithm was superior and performed much better in predicting the status of smokeless tobacco use in women from northeastern Indian states than the other ML algorithms. It is thought that the research will make an important contribution to the literature as one of the examples showing how machine learning algorithms can be applied in the classification of health-related events.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid machine learning approach in predicting smoking behaviour: The case of Turkey

Tezcan,

Karahan Adalı,

Özyurt Serim

2023

bmij

View full text Add to dashboard Cite

This study aims to analyze the smoking behaviour of people aged 15 and older in Turkey using supervised and unsupervised machine learning methods. In this study, C4.5 and Random Forest (RF) were trained to predict smoking behaviour, and an apriori algorithm was used to detect associations. Sensitivity, specificity, accuracy, positive predicted value (PPV), and f-measure were used to compare the performances of the supervised models. The Turkey Health Interview Survey 2019 was used with a sample size of 17084 to predict smoking behaviour and determine the factors affecting smoking. Data analysis and performance evaluation were performed with R programming language by RStudio. By association rules, gender, age, and alcohol consumption are the most representative attributes of smoking behaviour. Associations were determined on smoking, non-smoking and quit-smoking behaviour. Also, it has been seen that the RF algorithm has better results than the C4.5 algorithm. It’s preferred to use the RF model, which had better performance with an accuracy of 0.909, a specificity of 0.965, a sensitivity of 0.782, a PPV of 0.908, and an f-measure of 0.840 for predicting smoking behaviour. This study contributes to the literature covering the most comprehensive national health survey data and using machine learning methods on this data in Turkey. Also, it indicates that machine learning methods can be used to analyze such datasets.

show abstract

Section: Discussionsupporting

confidence: 90%

Section: Literature Reviewmentioning

confidence: 99%