Non-cognitive factors influencing early stroke symptom recognition among Korean working-class males with hypertension and diabetes: an integrated multi-output gradient boosting and logistic regression approach

This study aims to investigate the non-cognitive factors influencing the recognition of early stroke symptoms among Korean working class males with diabetes using an integrated machine learning approach combining Multi-Output Gradient Boosting and logistic regression models. Data from the Korea National Health and Nutrition Examination Survey (KNHANES) from 2016 to 2022 were utilized, including 4125 working class males with diabetes. Participants were divided into two groups based on their recognition of early stroke symptoms. The integrated machine learning model was trained on 80% of the dataset and tested on the remaining 20%. Key predictors were identified, and logistic regression analysis provided odds ratios (OR) and 95%confidence intervals (CI) for significant factors. The study found that 72% of participants recognized early stroke symptoms, while 28% did not. Significant predictors of non-recognition included younger age (β = −0.05, OR = 0.95, p < 0.01), higher Body Mass Index (BMI) (β = 0.12, OR = 1.13, p < 0.01), hypertension (β = 0.28, OR = 1.32, p < 0.01), elevated cholesterol (β = 0.03, OR = 1.03, p < 0.01) and triglycerides (β = 0.04, OR = 1.04, p < 0.01), depression (β = 0.25, OR = 1.28, p < 0.01), stress (β = 0.18, OR = 1.20, p < 0.01), smoking (β = 0.10, OR = 1.11, p < 0.01) and alcohol consumption (β = 0.08, OR = 1.08, p < 0.01). Positive factors included regular physical activity (β =−0.20, OR = 0.82, p < 0.01) and participation in diabetes education programs (β = −0.15, OR = 0.86, p < 0.01). The findings highlight the multifactorial nature of stroke symptom recognition and suggest that targeted interventions focusing on both physiological and psychological factors, as well as promoting healthy lifestyle behaviors, can significantly improve symptom recognition and health outcomes in working class males with diabetes.

Early stroke symptom recognition; Diabetic workers; Non-cognitive factors; Machine learning; Multi-output gradient boosting

[1] Hong KS, Bang OY, Kang DW, Yu KH, Bae HJ, Lee JS, et al. Stroke statistics in Korea: part I. Epidemiology and risk factors: a report from the Korean stroke society and clinical research center for stroke. Journal of Stroke. 2013; 15: 2–20.

[2] Han MK, Huh Y, Lee SB, Park JH, Lee JJ, Choi EA, et al.; Korean consortium for health and aging research. Prevalence of stroke and transient ischemic attack in Korean elders: findings from the Korean Longitudinal Study on Health and Aging (KLoSHA). Stroke. 2009; 40: 966–969.

[3] Lorber D. Importance of cardiovascular disease risk management in patients with type 2 diabetes mellitus. Diabetes, Metabolic Syndrome and Obesity. 2014; 7: 169–183.

[4] Pearlman DN, Affleck P, Goldman D. Disparities in awareness of the warning signs and symptoms of a heart attack and stroke among Rhode Island adults. Medicine & Health Rhode Island. 2011; 94: 183–185.

[5] Ma J, Zhang N, Xiao JY, Wang JX, Li X, Wang J, et al. Public awareness of acute myocardial infarction symptoms and emergency response in community residents. European Heart Journal. 2021; 42: ehab724.3133.

[6] Alharbi MF, Alanazi G, Almesned B, Alenazi Y, Alruwaili R, Alanazi W, et al. Public awareness of early symptoms of acute myocardial infarction in Arar, Saudi Arabia. International Journal of Medicine in Developing Countries. 2024; 8: 151–157.

[7] Ghanem N, Elshal A, Darwish SY, Emam M, ElWalili M, Mehanna R. Role of awareness activities in mega-events. European Heart Journal. 2021; 23: suab069.019.

[8] Uhland D. Evaluating the impact of a standardized education class on a person diagnosed with chronic kidney disease, stage IV. Himmelfarb Health Sciences Library. 2018; 1–37.

[9] Morrison S, Subrahmanian KN, Ali S, Osterberg L. Health outreach program to educate (HOPE) palo alto. Journal of Community Health. 2016; 41: 1047–1055.

[10] Myke-Mbata B, Dioka C, Meludu S, Adebisi SA, Oghagbon EK. Preponderance of increased glycosylated hemoglobin (HBA1c) and chronic disease in Nigerian adults. Journal of Diabetes Research. 2018; 2018: 1–8.

[11] Harini K, Rekha KKS. Evaluating performance of identifying at-risk students and learning achievement model using accuracy and f-measure by comparing logistic regression, generalized linear model and gradient boost machine algorithm. International Conference for Advancement in Technology. 2022; 4: 1–7.

[12] Balaji C, Chakkaravarthy A. Automatic identification of fake news circulation in social media using logistic regression over naïve bayes and XGBoost algorithm to improve accuracy. PURE Network Journals. 2022; 13: 654–660.

[13] Vivek R, R M. Analyze the lack of accuracy in loan prediction using logistic regression compared with random forest to improve accuracy. Eighth International Conference on Science Technology Engineering and Mathematics. 2023; 174: 1–5.

[14] Vasu VN, R S, S SM, Nelson M. Prediction of defective products using logistic regression algorithm against linear regression algorithm for better accuracy. International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies. 2022; 161–166.

[15] Vishnuvardhan T, Rama A. Comparison of accuracy rate in prediction of cardiovascular disease using random forest with logistic regression. Cardiometry. 2022; 25: 1526–1531.

[16] Azizov V, Mirzazade VA, Garibova C. The effect of structured training on blood pressure indicators in Type II diabetes mellitus patients having arterial hypertension. Vestnik Sankt-Peterburgskogo Universiteta—Meditsina. 2020; 13: 7–12. (In Russian)

[17] Harmawati H, Etriyanti E, Hardini S. Deteksi dini gejala awal stroke. Journal of Acute Stroke. 2021; 3: 186–189. (In Indonesian)

[18] Mszar R, Mahajan S, Valero-Elizondo J, Yahya T, Sharma R, Grandhi GR, et al. Association between sociodemographic determinants and disparities in stroke symptom awareness among us young adults. Stroke. 2020; 51: 3552–3561.

[19] Hosseininezhad M, Ebrahimi H, Seyedsaadat S, Bakhshayesh B, Asadi M, Ghayeghran A. Awareness toward stroke in a population-based sample of Iranian adults. Iranian Journal of Neurology. 2017; 16: 7–14.

[20] Jarou Z, Harris N, Gill L, Azizi M, Gabasha S, LaBril R. Public stroke knowledge: those most at risk, least able to identify symptoms. Medical Student Research Journal. 2013; 3: 003–008.

[21] Truelsen T, Krarup L. Stroke awareness in Denmark. Neuroepidemiology. 2010; 35: 165–170.

[22] Ojike N, Ravenell J, Seixas A, Masters-Israilov A, Rogers A, Jean-Louis G, et al. Racial disparity in stroke awareness in the US: an analysis of the 2014 national health interview survey. Journal of Neurology and Neurophysiology. 2016; 7: 365.

[23] Ellis C, Egede L. Stroke recognition among individuals with stroke risk factors. The American Journal of the Medical Sciences. 2009; 337: 5–10.

[24] Swartz RH, Bayley M, Lanctôt KL, Murray BJ, Cayley ML, Lien K, et al. Post-stroke depression, obstructive sleep apnea, and cognitive impairment: rationale for, and barriers to, routine screening. International Journal of Stroke. 2016; 11: 509–518.

[25] Lawrence M, Booth J, Mercer S, Crawford E. A systematic review of the benefits of mindfulness-based interventions following transient ischemic attack and stroke. International Journal of Stroke. 2013; 8: 465–474.

[26] Winstein CJ, Stein J, Arena R, Bates B, Cherney LR, Cramer SC, et al. Guidelines for adult stroke rehabilitation and recovery: a guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke. 2016; 47: 98–169.

[27] Fonarow GC, Calitz C, Arena R, Baase C, Isaac FW, Lloyd-Jones D, et al. Workplace wellness recognition for optimizing workplace health: a presidential advisory from the American Heart Association. Circulation. 2015; 131: 480–497.

[28] Yang X, Li Z, Sun J. Effects of cognitive behavioral therapy-based intervention on improving glycaemic, psychological, and physiological outcomes in adult patients with diabetes mellitus: a meta-analysis of randomized controlled trials. Frontiers in Psychiatry. 2020; 11: 711.

[29] Hinwood M, Ilicic M, Gyawali P, Coupland K, Kluge MG, Smith A, et al. Psychological stress management and stress reduction strategies for stroke survivors: a scoping review. Annals of Behavioral Medicine. 2023; 57: 111–130.

[30] Duque AS, Fernandes L, Correia AF, Calvinho I, Pinto M, Freitas P, et al. Awareness of stroke risk factors and warning signs and attitude to acute stroke. International Archives of Medicine. 2015; 8: 1–18.

[31] Oh GJ, Lee K, Kim K, Lee YH. Differences in the awareness of stroke symptoms and emergency response by occupation in the Korean general population. PLOS ONE. 2019; 14: e0218608.

[32] Wang C, Huang X, Xiang S, Lian XG, Yuan C, Jiang X, et al. The effect of an overall healthy lifestyle on early-onset stroke: a cross-sectional study. Annals of Palliative Medicine. 2020; 9: 2623–2630.

[33] Douma MJ, Aves T, Allan KS, Bendall JC, Berry DC, Chang WT, et al. First aid cooling techniques for heat stroke and exertional hyperthermia: a systematic review and meta-analysis. Resuscitation. 2020; 148: 173–190.

[34] Boltaevich UM, Umarovich AT. First AID for stroke. European Journal of Innovation in Nonformal Education. 2024; 4: 266–270.

[35] Landry KK, Alexander KS, Zakai N, Judd S, Kleindorfer D, Howard V, et al. Association of stroke risk biomarkers with stroke symptoms: the Reasons for Geographic and Racial Differences in Stroke cohort. Journal of Thrombosis and Haemostasis. 2017; 15: 21–27.