1
|
Bittencourt JAS, Sousa CM, Santana EEC, de Moraes YAC, Carneiro ECRDL, Fontes AJC, Chagas LAD, Melo NAC, Pereira CL, Penha MC, Pires N, Araujo E, Barros AKD, Nascimento MDDSB. Prediction of metabolic syndrome and its associated risk factors in patients with chronic kidney disease using machine learning techniques. J Bras Nefrol 2024; 46:e20230135. [PMID: 39133895 PMCID: PMC11318987 DOI: 10.1590/2175-8239-jbn-2023-0135en] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2023] [Accepted: 06/05/2024] [Indexed: 08/15/2024] Open
Abstract
INTRODUCTION Chronic kidney disease (CKD) and metabolic syndrome (MS) are recognized as public health problems which are related to overweight and cardiometabolic factors. The aim of this study was to develop a model to predict MS in people with CKD. METHODS This was a prospective cross-sectional study of patients from a reference center in São Luís, MA, Brazil. The sample included adult volunteers classified according to the presence of mild or severe CKD. For MS tracking, the k-nearest neighbors (KNN) classifier algorithm was used with the following inputs: gender, smoking, neck circumference, and waist-to-hip ratio. Results were considered significant at p < 0.05. RESULTS A total of 196 adult patients were evaluated with a mean age of 44.73 years, 71.9% female, 69.4% overweight, and 12.24% with CKD. Of the latter, 45.8% had MS, the majority had up to 3 altered metabolic components, and the group with CKD showed statistical significance in: waist circumference, systolic blood pressure, diastolic blood pressure, and fasting blood glucose. The KNN algorithm proved to be a good predictor for MS screening with 79% accuracy and sensitivity and 80% specificity (area under the ROC curve - AUC = 0.79). CONCLUSION The KNN algorithm can be used as a low-cost screening method to evaluate the presence of MS in people with CKD.
Collapse
Affiliation(s)
- Jalila Andréa Sampaio Bittencourt
- Universidade Federal do Maranhão, Departamento de Engenharia
Eletrônica, Laboratório de Processamento da Informação Biológica, São Luiz, MA,
Brazil
| | - Carlos Magno Sousa
- Universidade Federal do Maranhão, Departamento de Ciência da
Computação, Laboratório de Aquisição e Processamento de Sinais, São Luiz, MA,
Brazil
| | - Ewaldo Eder Carvalho Santana
- Universidade Federal do Maranhão, Departamento de Ciência da
Computação, Laboratório de Aquisição e Processamento de Sinais, São Luiz, MA,
Brazil
| | - Yuri Armin Crispim de Moraes
- Universidade Federal do Maranhão, Departamento de Engenharia
Eletrônica, Laboratório de Processamento da Informação Biológica, São Luiz, MA,
Brazil
| | | | - Ariadna Jansen Campos Fontes
- Universidade Federal do Maranhão, Centro de Ciências Biológicas e da
Saúde, Laboratório de Imunofisiologia, São Luiz, MA, Brazil
| | - Lucas Almeida das Chagas
- Universidade Federal de São Paulo, Escola Paulista de Medicina,
Departamento de Obstetrícia, São Paulo, SP, Brazil
| | - Naruna Aritana Costa Melo
- Universidade Federal do Maranhão, Laboratório de Ciências
Biológicas, Laboratório de Genética e Biologia Molecular, São Luiz, MA,
Brazil
| | - Cindy Lima Pereira
- Universidade Federal do Maranhão, Departamento de Engenharia
Eletrônica, Laboratório de Processamento da Informação Biológica, São Luiz, MA,
Brazil
| | - Margareth Costa Penha
- Universidade Ceuma, Departamento de Biomedicina, Laboratório de
Ciências Biomédicas, São Luiz, MA, Brazil
| | - Nilviane Pires
- Universidade Federal do Maranhão, Departamento de Engenharia
Eletrônica, Laboratório de Processamento da Informação Biológica, São Luiz, MA,
Brazil
| | - Edward Araujo
- Universidade Federal de São Paulo, Escola Paulista de Medicina,
Departamento de Obstetrícia, São Paulo, SP, Brazil
| | - Allan Kardec Duailibe Barros
- Universidade Federal do Maranhão, Departamento de Engenharia
Eletrônica, Laboratório de Processamento da Informação Biológica, São Luiz, MA,
Brazil
| | | |
Collapse
|
2
|
Moustakim R, Mziwira M, El Ayachi M, Belahsen R. Association of Metabolic Syndrome and Chronic Kidney Disease in Moroccan Adult Population. Metab Syndr Relat Disord 2021; 19:460-468. [PMID: 34432550 DOI: 10.1089/met.2020.0117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022] Open
Abstract
Background: Metabolic syndrome (MetS) is a cluster of cardiovascular risk factors that may promote the development of chronic kidney disease (CKD). The aim of this research was to determine the prevalence of MetS and its components and, to study their association with CKD among Moroccan adult population living in an agricultural province. Materials and Methods: The study involved 210 adult participants of 18 and over years, of both sexes, sampled from urban and rural areas of Sidi Bennour province in Morocco. Systolic and diastolic blood pressure, weight, height, and waist circumference were measured and body mass index (BMI) was calculated. Blood total cholesterol, triglycerides, glucose, and serum creatinine were determined. Subsequent glomerular filtration rate (GFR) was estimated by the modification of diet in renal disease formula and the CKD was defined by an estimated GFR (eGFR) <60 mL/min/1.73 m2. The diagnosis of MetS was based on the National Cholesterol Education Program/Adult Treatment Panel (NCEP ATP III) report. Results: The mean age of the participants was 54.18 ± 13.45 years, the prevalence of MetS and CKD were 38% and 4.4%, respectively. Abdominal obesity was the strongest risk factor of MetS among the studied population (71%), followed by increased fasting plasma glucose (40.5%), high blood pressure (35.2%), hypercholesterolemia (31.0%), and hypertriglyceridemia (23.8%). The prevalence of these comorbid factors increased with age (P = 0.000), BMI (P = 0.000), and decreased with education level (P = 0.012). The presence of MetS was significantly associated with decreased eGFR (P = 0.022), hence the prevalence of CKD was markedly greater in subjects with MetS than those without. Conclusions: Our finding indicates that MetS is a serious public health problem in the study population and that its individual components are involved in decreasing the eGFR and the progression of renal dysfunction. The study results support the need of the development of a strategy to control and prevent worsening of the MetS individual components and development of CKD.
Collapse
Affiliation(s)
- Rachida Moustakim
- Laboratory of Biotechnology, Biochemistry and Nutrition, Training and Research Unit on Nutrition and Food Sciences, Faculty of Sciences, Chouaib Doukkali University, El Jadida, Morocco
| | - Mohamed Mziwira
- Laboratory of Biotechnology, Biochemistry and Nutrition, Training and Research Unit on Nutrition and Food Sciences, Faculty of Sciences, Chouaib Doukkali University, El Jadida, Morocco.,Higher Normal School of Hassan II University, Casablanca, Morocco
| | - Mohammed El Ayachi
- Laboratory of Biotechnology, Biochemistry and Nutrition, Training and Research Unit on Nutrition and Food Sciences, Faculty of Sciences, Chouaib Doukkali University, El Jadida, Morocco
| | - Rekia Belahsen
- Laboratory of Biotechnology, Biochemistry and Nutrition, Training and Research Unit on Nutrition and Food Sciences, Faculty of Sciences, Chouaib Doukkali University, El Jadida, Morocco
| |
Collapse
|
3
|
Bakhshayeshkaram M, Heydari ST, Honarvar B, Keshani P, Roozbeh J, Dabbaghmanesh MH, Lankarani KB. Incidence of metabolic syndrome and determinants of its progression in Southern Iran: A 5-year longitudinal follow-up study. JOURNAL OF RESEARCH IN MEDICAL SCIENCES 2020; 25:103. [PMID: 33824668 PMCID: PMC8019129 DOI: 10.4103/jrms.jrms_884_19] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/01/2019] [Revised: 04/18/2020] [Accepted: 07/09/2020] [Indexed: 02/05/2023]
Abstract
Background Metabolic syndrome (MetS) is a cluster of conditions increasing the risk of serious diseases. This study aimed to define the predictors of MetS incident in a community-based cohort in Southern Iran, during a mean follow-up period of 5.1 years. Materials and Methods During the mean follow-up period of 5.1 years, a cohort study was conducted on 819 Iranian adults aged ≥18 years at baseline and followed to determine the incidence and predictors of MetS progression in Shiraz, a main urban region in the southern part of Iran. The International Diabetes Federation Guideline was used to detect the MetS. Multiple Cox's proportional hazards models were also used to estimate the predictors of new-onset MetS. Results The prevalence of MetS was 25.9% at baseline, and the overall incidence of subsequent MetS was 5.45% (95% confidence interval [CI]: 4.47-6.59). The incidence of MetS was significantly higher in women (7.12% [95% CI: 5.52-9.05]) than in men (3.92% [95% CI: 2.80-5.34]). Moreover, it increased by 5.02 (95% CI, 3.75-6.58) among individuals who had one metabolic component and by 12.65 (95% CI, 9.72-16.18) for those who had three or more components (P < 0001). The incidence of MetS was also analyzed using the multiple Cox's proportional hazards model for potential risk factors, and it was revealed that female gender (hazard ratio [HR] 2.45; 95% CI: 1.33, 4.50; P = 0.004), higher body mass index (HR 3.13; 95% CI: 1.43.6.84; P = 0.012), increased abdominal obesity (HR 1.45; 95% CI 0.85, 2.46; P = 0.045), smoking (HR 4.79; 95% CI 2.09, 10.97; P < 0.001), and lower high-density lipoprotein (HR 0.53; 95% CI: 0.29, 1.00; P = 0.044) significantly predicted the onset of MetS at baseline; however, age, systolic and diastolic blood pressure, serum uric acid, fasting blood glucose, cholesterol, triglyceride and creatinine, estimated glomerular filtration rate, marital status, level of education, and level of physical activity did not independently predict the onset of MetS when other covariates were considered. Conclusion This study showed the high-incidence rates of MetS in males and females residing in Southern Iran. Therefore, the prevention through community-based lifestyle modification should be implemented to reduce the burden of MetS and its complications.
Collapse
Affiliation(s)
- Marzieh Bakhshayeshkaram
- Shiraz Health Policy Research Center, Institute of Health, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Sayed Taghi Heydari
- Department of Biostatistics, Shiraz Health Policy Research Center, Institute of Health, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Behnam Honarvar
- Department of Public and Community Medicine, Shiraz Health Policy Research Center, Institute of Health, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Parisa Keshani
- Department of Nutrition, Shiraz HIV/AIDS Research Center, Institute of Health, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Jamshid Roozbeh
- Department of Internal Medicine, Nephrologist, Shiraz Nephro-Urology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Mohammad Hossein Dabbaghmanesh
- Department of Internal Medicine, Endocrinologist, Shiraz Endocrinology and Metabolism Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Kamran Bagheri Lankarani
- Department of Internal Medicine, Gastroenterologist, Shiraz Health Policy Research Center, Institute of Health, Shiraz University of Medical Sciences, Shiraz, Iran
| |
Collapse
|