1
|
Gutiérrez-Esparza G, Pulido T, Martínez-García M, Ramírez-delReal T, Groves-Miralrio LE, Márquez-Murillo MF, Amezcua-Guerra LM, Vargas-Alarcón G, Hernández-Lemus E. A machine learning approach to personalized predictors of dyslipidemia: a cohort study. Front Public Health 2023; 11:1213926. [PMID: 37799151 PMCID: PMC10548235 DOI: 10.3389/fpubh.2023.1213926] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2023] [Accepted: 08/23/2023] [Indexed: 10/07/2023] Open
Abstract
Introduction Mexico ranks second in the global prevalence of obesity in the adult population, which increases the probability of developing dyslipidemia. Dyslipidemia is closely related to cardiovascular diseases, which are the leading cause of death in the country. Therefore, developing tools that facilitate the prediction of dyslipidemias is essential for prevention and early treatment. Methods In this study, we utilized a dataset from a Mexico City cohort consisting of 2,621 participants, men and women aged between 20 and 50 years, with and without some type of dyslipidemia. Our primary objective was to identify potential factors associated with different types of dyslipidemia in both men and women. Machine learning algorithms were employed to achieve this goal. To facilitate feature selection, we applied the Variable Importance Measures (VIM) of Random Forest (RF), XGBoost, and Gradient Boosting Machine (GBM). Additionally, to address class imbalance, we employed Synthetic Minority Over-sampling Technique (SMOTE) for dataset resampling. The dataset encompassed anthropometric measurements, biochemical tests, dietary intake, family health history, and other health parameters, including smoking habits, alcohol consumption, quality of sleep, and physical activity. Results Our results revealed that the VIM algorithm of RF yielded the most optimal subset of attributes, closely followed by GBM, achieving a balanced accuracy of up to 80%. The selection of the best subset of attributes was based on the comparative performance of classifiers, evaluated through balanced accuracy, sensitivity, and specificity metrics. Discussion The top five features contributing to an increased risk of various types of dyslipidemia were identified through the machine learning technique. These features include body mass index, elevated uric acid levels, age, sleep disorders, and anxiety. The findings of this study shed light on significant factors that play a role in dyslipidemia development, aiding in the early identification, prevention, and treatment of this condition.
Collapse
Affiliation(s)
- Guadalupe Gutiérrez-Esparza
- Researcher for Mexico CONAHCYT, National Council of Humanities Sciences, and Technologies, Mexico City, Mexico
- Clinical Research, National Institute of Cardiology “Ignacio Chávez”, Mexico City, Mexico
| | - Tomas Pulido
- Clinical Research, National Institute of Cardiology “Ignacio Chávez”, Mexico City, Mexico
| | - Mireya Martínez-García
- Department of Immunology, National Institute of Cardiology “Ignacio Chávez”, Mexico City, Mexico
| | - Tania Ramírez-delReal
- Researcher for Mexico CONAHCYT, National Council of Humanities Sciences, and Technologies, Mexico City, Mexico
- Center for Research in Geospatial Information Sciences, Aguascalientes, Mexico
| | | | - Manlio F. Márquez-Murillo
- Department of Electrocardiology, National Institute of Cardiology “Ignacio Chávez”, Mexico City, Mexico
| | - Luis M. Amezcua-Guerra
- Department of Immunology, National Institute of Cardiology “Ignacio Chávez”, Mexico City, Mexico
| | - Gilberto Vargas-Alarcón
- Department of Molecular Biology and Endocrinology, National Institute of Cardiology “Ignacio Chávez”, Mexico City, Mexico
| | - Enrique Hernández-Lemus
- Computational Genomics Division, National Institute of Genomic Medicine, Mexico City, Mexico
- Center for Complexity Sciences, Universidad Nacional Autónoma de México, Mexico City, Mexico
| |
Collapse
|
2
|
Zhou W, Sun L, Zeng L, Wan L. Mediation of the association between sleep disorders and cardiovascular disease by depressive symptoms: An analysis of the National health and Nutrition Examination Survey (NHANES) 2017–2020. Prev Med Rep 2023; 33:102183. [DOI: 10.1016/j.pmedr.2023.102183] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2022] [Revised: 03/17/2023] [Accepted: 03/18/2023] [Indexed: 03/30/2023] Open
|
3
|
Muacevic A, Adler JR, Jacobs M, Miller D, Diah J, Desroches BR, Shields JM. Association of Height and Prevalence of Kidney Stones. Cureus 2022; 14:e32919. [PMID: 36699765 PMCID: PMC9872204 DOI: 10.7759/cureus.32919] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 12/25/2022] [Indexed: 12/26/2022] Open
Abstract
Introduction and objectives Nephrolithiasis is universally understood to be a multifactorial disease resulting from genetic and environmental factors including gender, diet, calcium, and uric acid excretion. Notably, several of these factors may be related to body habitus. Because men are more likely to develop kidney stones and on average have a larger body size, height may be an important risk factor for stone formation. Several studies have demonstrated that short adult stature is associated with numerous conditions such as hypertension, hypercholesterolemia, and cardiovascular diseases. However, other studies have demonstrated otherwise. Additionally, stones have been shown to be correlated with a high body mass index (BMI). This is likely due to dietary factors. Although height is a component of BMI, there is minimal literature regarding the relationship of height to stone prevalence adjusting for weight. Methods We aimed to examine whether short adult height is associated with the development of kidney stones using a population-based cohort of the National Center for Health Statistics. Data was gathered from National Health and Nutrition Examination Surveys (NHANES) "Kidney Conditions - Urology" and "Weight History" questionnaire datasets from March 2017 to March 2020 along with demographic data. Logistic regression analysis was used to determine an association between current self-reported height (inches) and if the participant has ever had kidney stones, controlling for weight, gender, age, race, educational level, and marital status. Results We found that those who were shorter had higher odds of reporting a history of stones (OR: 1.017; 95%CI: 1.005-1.028). This association was found after controlling for covariates such as age, gender, race, education, and weight. In addition, the male gender and Hispanic race had higher odds of reporting a history of stones (OR: 1.43 and 1.073, respectively). Conclusion Our results suggest that short height is related to the prevalence of kidney stones independent of weight, age, gender, and race. This supports previous literature indicating height to be a component of renal disease.
Collapse
|
4
|
Müller SM, Floris J, Rohrmann S, Staub K, Matthes KL. Body height among adult male and female Swiss Health Survey participants in 2017: Trends by birth years and associations with self-reported health status and life satisfaction. Prev Med Rep 2022; 29:101980. [PMID: 36161131 PMCID: PMC9502675 DOI: 10.1016/j.pmedr.2022.101980] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2021] [Revised: 09/02/2022] [Accepted: 09/02/2022] [Indexed: 11/25/2022] Open
Abstract
Increase in average body height had slowed down from around the 1970s birth cohorts. Women and men with tertiary education levels were taller than participants holding other education levels. Taller participants were less overweighted and were more satisfied with their lives than shorter participants. Taller participants had better overall health than shorter participants. Taller men were more likely to have lower back pain than shorter men.
The increase in adult height for 150 years is linked to overall improvements in nutrition, hygiene, and living standards. Height is positively associated with general health and success on various levels (e.g. quality of life, earnings or happiness). The aim of this study was to investigate whether different subgroups show different trends across birth cohorts. We wanted to know whether taller individuals considered themselves as healthier and their quality of life as better than shorter individuals. We included 19,435 participants from the Swiss population-based Health Survey 2017. GAM were used to assess nonlinear associations between height and birth year. Multinomial logistic regression was used to predict probabilities of self-rated health in relation to height. The increase in average height slows down from the 1970s birth cohorts. Participants with parents from Central/Northern/Western Europe (men 177.9 cm, women: 165.1 cm) or Eastern Europe (men 178.7 cm, women: 165.7 cm) were taller than participants with parents from South America (men 174.3 cm, women: 161. cm) and Asia (men 173.2 cm, women: 160.1 cm). Participants with tertiary education were taller than participants from education levels (mean difference men: 4.5 cm, women: 5.0 cm). Height was positively associated with self-declared aspects of health and life satisfaction. These results support the conclusion that body height as a co-factor of health aspects should be considered in public health research. Although adult body height can no longer be influenced, nutritional status and thus also healthy growth can be influenced in childhood by public health programs, by eliminating social inequalities, and by strengthen healthy living conditions.
Collapse
Affiliation(s)
| | - Joël Floris
- Institute of Evolutionary Medicine, University of Zurich, Switzerland.,Department of History, University of Zurich, Switzerland
| | - Sabine Rohrmann
- Epidemiology, Biostatistics, and Prevention Institute, University of Zurich, Switzerland.,Swiss School of Public Health (SSPH+), Zurich, Switzerland
| | - Kaspar Staub
- Institute of Evolutionary Medicine, University of Zurich, Switzerland.,Swiss School of Public Health (SSPH+), Zurich, Switzerland
| | | |
Collapse
|
5
|
Your height affects your health: genetic determinants and health-related outcomes in Taiwan. BMC Med 2022; 20:250. [PMID: 35831902 PMCID: PMC9281111 DOI: 10.1186/s12916-022-02450-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Accepted: 06/22/2022] [Indexed: 11/24/2022] Open
Abstract
BACKGROUND Height is an important anthropometric measurement and is associated with many health-related outcomes. Genome-wide association studies (GWASs) have identified hundreds of genetic loci associated with height, mainly in individuals of European ancestry. METHODS We performed genome-wide association analyses and replicated previously reported GWAS-determined single nucleotide polymorphisms (SNPs) in the Taiwanese Han population (Taiwan Biobank; n = 67,452). A genetic instrument composed of 251 SNPs was selected from our GWAS, based on height and replication results as the best-fit polygenic risk score (PRS), in accordance with the clumping and p-value threshold method. We also examined the association between genetically determined height (PRS251) and measured height (phenotype). We performed observational (phenotype) and genetic PRS251 association analyses of height and health-related outcomes. RESULTS GWAS identified 6843 SNPs in 89 genomic regions with genome-wide significance, including 18 novel loci. These were the most strongly associated genetic loci (EFEMP1, DIS3L2, ZBTB38, LCORL, HMGA1, CS, and GDF5) previously reported to play a role in height. There was a positive association between PRS251 and measured height (p < 0.001). Of the 14 traits and 49 diseases analyzed, we observed significant associations of measured and genetically determined height with only eight traits (p < 0.05/[14 + 49]). Height was positively associated with body weight, waist circumference, and hip circumference but negatively associated with body mass index, waist-hip ratio, body fat, total cholesterol, and low-density lipoprotein cholesterol (p < 0.05/[14 + 49]). CONCLUSIONS This study contributes to the understanding of the genetic features of height and health-related outcomes in individuals of Han Chinese ancestry in Taiwan.
Collapse
|
6
|
Sheng B, Zhao Q, Ma M, Zhang J. An inverse association of weight and the occurrence of asymptomatic gallbladder stone disease in hypercholesterolemia patients: a case-control study. Lipids Health Dis 2020; 19:228. [PMID: 33097057 PMCID: PMC7585169 DOI: 10.1186/s12944-020-01402-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2020] [Accepted: 10/14/2020] [Indexed: 12/12/2022] Open
Abstract
Background Despite the fact that the majority of gallstones formed in the gallbladder are mainly composed of cholesterol, as they are formed from cholesterol-supersaturated bile, and hypercholesterolemia is a common metabolic disorder, which is closely related to cardiac, hepatic, renal and other oxidative damage inflammation and necrosis, there is still no consensus regarding the contribution of blood serum lipids in the pathogenesis of gallbladder stone disease (GSD). This study aimed to investigate the relationship between hypercholesterolemia and the risk of new-onset asymptomatic GSD, and to determine the prevalence of factors associated with new-onset asymptomatic GSD in patients with hypercholesterolemia. Methods In this study, 927 Chinese patients with new-onset asymptomatic gallstone disease and 845 healthy controls were enrolled starting from August 2012. Patients were matched for age, gender, race, occupation, systolic blood pressure, diastolic blood pressure, and fasting blood glucose levels (FBG). Body mass index (BMI), nonalcoholic fatty liver disease (NAFLD) and serum lipids indexes were compared and the relationships between BMI, blood lipid and gallbladder stone hazards were examined by logistic multivariate regression models. Results The result showed a significantly higher morbidity with GSD in hypercholesterolemia than non-hypercholesterolemia patients (Χ2 = 17.211, P < 0.001). Of hypercholesterolemia patients, low density lipoprotein (OR = 1.493, P = 0.029) and NAFLD (OR = 2.723, P = 0.022) were significant risk factors for GSD, while being male (OR = 0.244, P = 0.033), weight (OR = 0.961, P = 0.022), high density lipoprotein (OR = 0.305, P < 0.001), and FBG (OR = 0.687, P = 0.034) were significantly negatively correlated with GSD in univariate analysis. Multivariate logistic regression indicated weakly positive correlations with NAFLD (OR = 3.284, P = 0.054), and significant negative correlations with weight (OR = 0.930, P = 0.018), HDL-c (OR = 0.144, P < 0.001), and GSD. Conclusion Hypercholesterolemia acts as an independent risk factor for new-onset asymptomatic GSD, while obesity and NAFLD are synergistic factors. Interestingly, it is first reported that elevated weight was inversely associated with GSD in patients with hypercholesterolemia. The results of this study suggest that effective control of hyperlipidemia is of greater significance than weight loss, which might make the situation worse, in the prevention of GSD in obese patients with hyperlipidemia.
Collapse
Affiliation(s)
- Binwu Sheng
- Department of Geriatric Surgery, the First Affiliated Hospital of Xi'an Jiaotong University, 277 West Yanta Road, Xi'an, 710061, China.
| | - Qingbin Zhao
- Department of Geriatric, the First Affiliated Hospital of Xi'an Jiaotong University, 277 West Yanta Road, Xi'an, 710061, China
| | - Mao Ma
- Department of Geriatric Surgery, the First Affiliated Hospital of Xi'an Jiaotong University, 277 West Yanta Road, Xi'an, 710061, China
| | - Jianqin Zhang
- Department of Nutrition, The Fourth People's Hospital of Shaanxi, No. 512, Xianning East Road, Xi'an, 710043, China.
| |
Collapse
|
7
|
Hong YA, Han KD, Yun JS, Sil ES, Ko SH, Chung S. Short adult height increases the risk of end-stage renal disease in type 2 diabetes. Endocr Connect 2020; 9:912-921. [PMID: 33069158 PMCID: PMC7583136 DOI: 10.1530/ec-20-0319] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/09/2020] [Accepted: 09/02/2020] [Indexed: 12/05/2022]
Abstract
OBJECTIVE Although short adult height has been associated with an increasing variety of diseases and all-cause death, no reliable data exist on the association between adult height and end-stage renal disease (ESRD) in diabetic patients. We investigated the relationship between short adult height, development of ESRD, and mortality in type 2 diabetes mellitus (DM). METHODS This nationwide population-based cohort study analyzed clinical data from a total of 2,621,907 subjects aged ≥30 years with type 2 DM between January 1, 2009 and December 31, 2012, using the National Health Insurance Database in Korea. RESULTS During a 6.9-year follow-up period, 220,457 subjects (8.4%) died, and 28,704 subjects (1.1%) started dialysis. Short adult height significantly increased the incidence of ESRD and all-cause mortality in the overall cohort analysis. In multivariable Cox models, hazard ratios (HR) for the development of ESRD comparing the highest and lowest quartiles of adult height were 0.86 (95% CI 0.83-0.89). All-cause mortality also decreased with the highest height compared to patients with the lowest height, after fully adjusting for confounding variables (HR 0.79, 95% CI 0.78-0.81). Adult height had an inverse relationship to newly diagnosed ESRD (male: HR 0.86, 95% CI 0.83-0.90, female: HR 0.84, 95% CI 0.79-0.90) and all-cause mortality (male: HR 0.81, 95% CI 0.79-0.82, female: HR 0.80, 95% CI 0.78-0.82). CONCLUSIONS Short adult height is strongly associated with the increased risk of ESRD development and all-cause mortality in type 2 DM.
Collapse
Affiliation(s)
- Yu Ah Hong
- Division of Nephrology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea
| | - Kyung-Do Han
- Department of Statistics and Actuarial Science, Soongsil University, Seoul, Republic of Korea
| | - Jae-Seung Yun
- Division of Endocrinology and Metabolism, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea
| | - Eun Sil Sil
- Division of Nephrology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea
| | - Seung-Hyun Ko
- Division of Endocrinology and Metabolism, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea
- Correspondence should be addressed to S-H Ko or S Chung: or
| | - Sungjin Chung
- Division of Nephrology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea
- Correspondence should be addressed to S-H Ko or S Chung: or
| |
Collapse
|