1
|
Berezina TA, Berezin OO, Hoppe UC, Lichtenauer M, Berezin AE. Low Levels of Adropin Predict Adverse Clinical Outcomes in Outpatients with Newly Diagnosed Prediabetes after Acute Myocardial Infarction. Biomedicines 2024; 12:1857. [PMID: 39200321 PMCID: PMC11351681 DOI: 10.3390/biomedicines12081857] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2024] [Revised: 08/09/2024] [Accepted: 08/12/2024] [Indexed: 09/02/2024] Open
Abstract
Adropin-a multifunctional peptide with tissue-protective capacity that regulates energy homeostasis, sensitivity to insulin and inflammatory response-seems to show an inverse association with the presence of cardiovascular and renal diseases, obesity and diabetes mellitus in the general population. The purpose of the study is to elucidate whether adropin may be a plausible predictive biomarker for clinical outcomes in post-ST elevation of myocardial infarction (STEMI) patients with newly diagnosed prediabetes according to the American Diabetes Association criteria. A total of 1214 post-STEMI patients who received percutaneous coronary intervention were identified in a local database of the private hospital "Vita Center" (Zaporozhye, Ukraine). Between November 2020 and June 2024, we prospectively enrolled 498 patients with prediabetes in this open prospective cohort study and followed them for 3 years. The combined clinical endpoint at follow-up was defined as cardiovascular death due to acute myocardial infarction, heart failure, sudden death due to arrhythmia or cardiac surgery, and/or all-cause death. We identified 126 clinical events and found that serum levels of adropin < 2.15 ng/mL (area under the curve = 0.836; 95% confidence interval = 0.745-0.928; sensitivity = 84.9%; specificity = 72.7%; likelihood ratio = 3.11; p = 0.0001) predicted clinical outcomes. Multivariate logistic regression showed that a Gensini score ≥ 32 (Odds ratio [OR] = 1.07; p = 0.001), adropin ≤ 2.15 ng/mL (OR = 1.18; p = 0.001), use of SGLT2i (OR = 0.94; p = 0.010) and GLP-1 receptor agonist (OR = 0.95; p = 0.040) were independent predictors of clinical outcome. Kaplan-Meier plots showed that patients with lower adropin levels (≤2.15 ng/mL) had worse clinical outcomes compared to patients with higher adropin levels (>2.15 ng/mL). In conclusion, low levels of adropin (≤2.15 ng/mL) independently predicted clinical outcomes in post-STEMI patients with newly detected prediabetes and improved the discriminative ability of the Gensini score for 3-year follow-up events. Future clinical studies are needed to clarify whether adropin is a promising molecule to be incorporated into conventional risk scores for the prediction of MACCEs after STEMI.
Collapse
Affiliation(s)
- Tetiana A. Berezina
- Department of Internal Medicine and Nephrology, VitaCenter, 69000 Zaporozhye, Ukraine;
| | - Oleksandr O. Berezin
- Department of Alter Psychiatrie, Luzerner Psychiatrie AG, 4915 St. Urban, Switzerland;
| | - Uta C. Hoppe
- Department of Internal Medicine II, Division of Cardiology, Paracelsus Medical University, 5020 Salzburg, Austria; (U.C.H.); (M.L.)
| | - Michael Lichtenauer
- Department of Internal Medicine II, Division of Cardiology, Paracelsus Medical University, 5020 Salzburg, Austria; (U.C.H.); (M.L.)
| | - Alexander E. Berezin
- Department of Internal Medicine II, Division of Cardiology, Paracelsus Medical University, 5020 Salzburg, Austria; (U.C.H.); (M.L.)
| |
Collapse
|
2
|
Mathur P, Rani V. Investigating microRNAs in diabetic cardiomyopathy as tools for early detection and therapeutics. Mol Cell Biochem 2023; 478:229-240. [PMID: 35779226 DOI: 10.1007/s11010-022-04473-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2021] [Accepted: 05/04/2022] [Indexed: 02/02/2023]
Abstract
To profile microRNAs population of glucose-induced cardiomyoblast cell line and identify the differentially expressed microRNAs and their role under pre-diabetes and diabetes condition in vitro. Rat fetal ventricular cardiomyoblast cell line H9c2 was treated with D-glucose to mimic pre-diabetic, diabetic, and high-glucose conditions. Alteration in cellular, nuclear morphology, and change in ROS generation was analyzed through fluorescent staining. Small RNA sequencing was performed using Illumina NextSeq 550 sequencer and was validated using stem-loop qRT-PCR. A large number (~ 100) differential miRNAs were detected in each treated samples as compared to control; however, a similar expression pattern was observed between pre-diabetes and diabetes conditions with the exception for miR-429, miR-101b-5p, miR-503-3p, miR-384-5p, miR-412-5p, miR-672-5p, and miR-532-3p. Functional annotation of differential expressed target genes revealed their involvement in significantly enriched key pathways associated with diabetic cardiomyopathy. For the first time, we report the differential expression of miRNAs (miR-1249, miR-3596d, miR- 3586-3p, miR-7b-3p, miR-191, miR-330-3p, miR-328a, let7i-5p, miR-146-3p, miR-26a-3p) in diabetes-induced cardiac cells. Hyperglycemia threatens the cell homeostasis by dysregulation of miRNAs that begins at a glucose level 10 mM and remains undetected. Analysis of differential expressed miRNAs in pre-diabetes and diabetes conditions and their role in regulatory mechanisms of diabetic cardiomyopathy holds high potential in the direction of using miRNAs as minimally invasive diagnostic and therapeutic tools.
Collapse
Affiliation(s)
- Priyanka Mathur
- Transcriptome Laboratory, Centre for Emerging Diseases, Department of Biotechnology, Jaypee Institute of Information Technology, A-10, Sector-62, Noida, Uttar Pradesh, 210309, India
| | - Vibha Rani
- Transcriptome Laboratory, Centre for Emerging Diseases, Department of Biotechnology, Jaypee Institute of Information Technology, A-10, Sector-62, Noida, Uttar Pradesh, 210309, India.
| |
Collapse
|
3
|
Gao S, Ma W, Huang S, Lin X, Yu M. Impact of prediabetes on long-term cardiovascular outcomes in patients with myocardial infarction with nonobstructive coronary arteries. Diabetol Metab Syndr 2021; 13:103. [PMID: 34560905 PMCID: PMC8464129 DOI: 10.1186/s13098-021-00721-9] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/12/2021] [Accepted: 09/13/2021] [Indexed: 11/29/2022] Open
Abstract
BACKGROUND Abnormal glucose metabolism including diabetes (DM) and prediabetes (pre-DM) have been reported as predictors of poorer outcomes after acute myocardial infarction (AMI). However, the prognostic value of pre-DM in patients with myocardial infarction with nonobstructive coronary arteries (MINOCA) remains unclear. METHODS A total of 1179 MINOCA patients were prospectively recruited and divided into normoglycemia (NG), pre-DM, and DM groups according to glycated hemoglobin (HbA1c) levels or past history. The primary endpoint was a composite of major adverse cardiovascular events (MACE), including all-cause death, nonfatal MI, nonfatal stroke, revascularization and hospitalization for unstable angina or heart failure. Kaplan-Meier and Cox regression analyses were performed. RESULTS Patients with pre-DM and DM had a significantly higher incidence of MACE compared with NG group (10.8%, 16.1%, 19.4%; p = 0.003) over the median follow-up of 41.7 months. After multivariate adjustment, both pre-DM and DM were significantly associated with an increased risk of MACE (NG as reference; pre-DM: 1.45, 95% CI 1.03-2.09, p = 0.042; DM: HR 1.79, 95% CI 1.20-2.66, p = 0.005). At subgroup analysis, pre-DM remained a robust risk factor of MACE compared to NG. In addition, pre-DM had a similar impact as DM on long-term prognosis in patients with MINOCA. CONCLUSIONS Pre-DM defined as raised HbA1c was associated with a poor prognosis in patients with MINOCA. Routine assessment of HbA1c enables an early recognition of pre-DM and thus may facilitate risk stratification in this specific population.
Collapse
Affiliation(s)
- Side Gao
- Department of Cardiology, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Bei Li Shi Rd 167, Beijing, 100037, PR China
| | - Wenjian Ma
- Department of Cardiology, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Bei Li Shi Rd 167, Beijing, 100037, PR China
| | - Sizhuang Huang
- Department of Cardiology, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Bei Li Shi Rd 167, Beijing, 100037, PR China
| | - Xuze Lin
- Department of Cardiology, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Bei Li Shi Rd 167, Beijing, 100037, PR China
| | - Mengyue Yu
- Department of Cardiology, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Bei Li Shi Rd 167, Beijing, 100037, PR China.
| |
Collapse
|
4
|
Wang H, Song Y, Tang X, Xu J, Jiang P, Jiang L, Gao Z, Chen J, Song L, Zhang Y, Zhao X, Qiao S, Yang Y, Gao R, Xu B, Yuan J, Gao L. Impact of unknown diabetes and prediabetes on clinical outcomes in "nondiabetic" Chinese patients after a primary coronary intervention. Nutr Metab Cardiovasc Dis 2020; 30:644-651. [PMID: 32143897 DOI: 10.1016/j.numecd.2019.11.013] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/15/2019] [Revised: 11/22/2019] [Accepted: 11/22/2019] [Indexed: 11/18/2022]
Abstract
BACKGROUND AND AIM To explore the prevalence of unknown diabetes (DM) or prediabetes (pre-DM) in "nondiabetic" patients and its association with 2-year clinical outcomes after primary percutaneous coronary intervention (PCI). METHODS AND RESULTS 5202 consecutive "nondiabetic" patients who underwent primary PCI at Fuwai Hospital from January to December 2013 were prospectively enrolled. The patients were grouped according to their glycemia status: unknown DM (HbA1c ≥ 47 mmol/L; FPG≥ 7.0 mmol/L), pre-DM (HbA1c 39-47 mmol/L; FPG: 5.6-6.9 mmol/L) and normoglycemia (NG, HbA1c < 39 mmol/L; FPG < 5.6 mmol/L). The main endpoint was 2-year major adverse cardiovascular events (MACE), including cardiac death, myocardial infarction, and target vessel revascularization. A total of 905 patients had unknown DM, and 3407 patients had pre-DM. Unknown DM and pre-DM were associated with aging (p < 0.001); a greater proportion of hypertension (p < 0.001), previous myocardial infarction (p < 0.001), and chronic kidney disease (p = 0.004). During the 2-year follow-up, the rate of MACE was significantly higher in the unknown DM and pre-DM groups than in the NG group (8.1% vs. 5.8% vs. 4.1%, respectively, p = 0.001). Multivariate analyses demonstrated that unknown DM was associated with a 1.9-fold higher event risk compared to NG (95% CI: 1.2-2.8). CONCLUSIONS The prevalence of abnormal glucose metabolism was high in "nondiabetic" Chinese PCI patients. Patients with unknown DM and pre-DM had higher event risks than those with NG. In "nondiabetes" patients requiring PCI, routine assessment of HbA1c and FPG appears to be of value to identify patients with an increased event risk.
Collapse
Affiliation(s)
- Huanhuan Wang
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Ying Song
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Xiaofang Tang
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Jingjing Xu
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Ping Jiang
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Lin Jiang
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Zhan Gao
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Jue Chen
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Lei Song
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Yin Zhang
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Xueyan Zhao
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Shubin Qiao
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Yuejin Yang
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Runlin Gao
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Bo Xu
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Jinqing Yuan
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China.
| | - Lijian Gao
- Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China.
| |
Collapse
|
5
|
Geng J, Zhang Y, Wang B, Xie J, Xu B, Li J. Glycosylated hemoglobin levels and clinical outcomes in nondiabetic patients with coronary artery disease: A meta-analysis. Medicine (Baltimore) 2017; 96:e6784. [PMID: 28445316 PMCID: PMC5413281 DOI: 10.1097/md.0000000000006784] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/07/2023] Open
Abstract
A number of studies assessed the prognostic value of HbA1c level in nondiabetic patients with coronary artery disease (CAD). The purpose of this meta-analysis was to assess the association between the HbA1c level and clinical outcomes.We searched PubMed, EMBASE, MEDLINE, and the Cochrane Library from their inception to 10 April 2016. Studies evaluated the outcomes according to HbA1c levels in CAD patients without diabetes mellitus were eligible.Twenty studies involving 22,428 patients were included. In nondiabetic patients with CAD, a high HbA1c level was associated with a higher rate of long-term death (odds ratio 1.76, 95% confidence interval 1.44-2.16, P < .001), and myocardial infarction (MI, odds ratio 1.69, 95% confidence interval 1.07-2.67, P = .026), but not a higher rate of early deaths (odds ratio 1.08, 95% confidence interval 0.92-1.27, P = .359). These findings for death remained the same after sensitivity analyses and the trim and fill method, but the risk difference for MI became nonsignificant after adjustment for potential publication bias.Elevated HbA1c level increased the risks of long-term mortality and MI, but not the risk for early deaths in nondiabetic patients with CAD. High-quality large-scale studies with less bias are needed to confirm these findings.
Collapse
Affiliation(s)
- Jin Geng
- Department of Cardiology, Huai’an First People's Hospital, Nanjing Medical University
| | - Yanchun Zhang
- Department of Cardiology, Huai’an Second People's Hospital, The Affiliated Huai’an Hospital of Xuzhou Medical University
| | - Bingjian Wang
- Department of Cardiology, Huai’an First People's Hospital, Nanjing Medical University
| | - Jun Xie
- Department of Cardiology, Drum Tower Hospital, Nanjing Medical University, Nanjing
| | - Biao Xu
- Department of Cardiology, Drum Tower Hospital, Nanjing Medical University, Nanjing
| | - Ju Li
- Department of Rheumatology, Huai’an First People's Hospital, Nanjing Medical University, Huai’an, Jiangsu, China
| |
Collapse
|
6
|
Teeuw WJ, Kosho MXF, Poland DCW, Gerdes VEA, Loos BG. Periodontitis as a possible early sign of diabetes mellitus. BMJ Open Diabetes Res Care 2017; 5:e000326. [PMID: 28316794 PMCID: PMC5337701 DOI: 10.1136/bmjdrc-2016-000326] [Citation(s) in RCA: 48] [Impact Index Per Article: 6.9] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/14/2016] [Revised: 12/10/2016] [Accepted: 12/17/2016] [Indexed: 12/21/2022] Open
Abstract
OBJECTIVE The early diagnosis of (pre)diabetes mellitus is essential for the prevention of diabetes complications. It has been suggested that gum disease (periodontitis) might be an early complication of diabetes and may be a useful risk indicator for diabetes screening. Therefore, a dental office could be a good location for screening for (pre)diabetes in patients with periodontitis using a validated glycated hemoglobin (HbA1c) dry spot analysis. RESEARCH DESIGN AND METHODS A total of 313 individuals from a university dental clinic participated. From 126 patients with mild/moderate periodontitis, 78 patients with severe periodontitis and 109 subjects without periodontitis, HbA1c values were obtained by the analysis of dry blood spots. Differences in mean HbA1c values and the prevalence of (pre)diabetes between the groups were analyzed. RESULTS The mild/moderate and severe periodontitis groups showed significantly higher HbA1c values (6.1%±1.4% (43 mmol/mol±15 mmol/mol) and 6.3%±1.3% (45 mmol/mol±15 mmol/mol), respectively) compared with the control group (5.7%±0.7% (39 mmol/mol±8 mmol/mol), p=0.003). In addition, according to the American Diabetes Association (ADA) guidelines for diagnosis, there was a significant over-representation of subjects with suspected diabetes (23% and 14%) and pre-diabetes (47% and 46%) in the severe periodontitis group and mild/moderate periodontitis groups, respectively, compared with the control group (10% and 37%, p=0.010). Notably, 18.1% of patients with suspected new diabetes were found among subjects with severe periodontitis compared with 9.9% and 8.5% among subjects with mild/moderate periodontitis and controls, respectively (p=0.024). CONCLUSIONS The dental office, with particular focus on patients with severe periodontitis, proved to be a suitable location for screening for (pre)diabetes; a considerable number of suspected new diabetes cases were identified. The early diagnosis and treatment of (pre)diabetes help to prevent more severe complications and benefit the treatment of periodontitis.
Collapse
Affiliation(s)
- Wijnand J Teeuw
- Department of Periodontology, Academic Centre for Dentistry Amsterdam (ACTA), University of Amsterdam and VU University, Amsterdam, The Netherlands
| | - Madeline X F Kosho
- Department of Periodontology, Academic Centre for Dentistry Amsterdam (ACTA), University of Amsterdam and VU University, Amsterdam, The Netherlands
| | - Dennis C W Poland
- Department of Clinical Chemistry, MC Slotervaart, Amsterdam, The Netherlands
| | - Victor E A Gerdes
- Department of Vascular Medicine, Academic Medical Center (AMC), University of Amsterdam, Amsterdam, The Netherlands
- Department of Internal Medicine, MC Slotervaart, Amsterdam, The Netherlands
| | - Bruno G Loos
- Department of Periodontology, Academic Centre for Dentistry Amsterdam (ACTA), University of Amsterdam and VU University, Amsterdam, The Netherlands
| |
Collapse
|
7
|
Arvia C, Siciliano V, Chatzianagnostou K, Laws G, Quinones Galvan A, Mammini C, Berti S, Molinaro S, Iervasi G. Conventional insulin vs insulin infusion therapy in acute coronary syndrome diabetic patients. World J Diabetes 2014; 5:562-568. [PMID: 25126402 PMCID: PMC4127591 DOI: 10.4239/wjd.v5.i4.562] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/23/2013] [Revised: 01/22/2014] [Accepted: 05/19/2014] [Indexed: 02/05/2023] Open
Abstract
AIM: To evaluate the impact on glucose variability (GLUCV) of an nurse-implemented insulin infusion protocol when compared with a conventional insulin treatment during the day-to-day clinical activity.
METHODS: We enrolled 44 type 2 diabetic patients (n = 32 males; n = 12 females) with acute coronary syndrome (ACS) and randomy assigned to standard a subcutaneous insulin treatment (n = 23) or a nurse-implemented continuous intravenous insulin infusion protocol (n = 21). We utilized some parameters of GLUCV representing well-known surrogate markers of prognosis, i.e., glucose standard deviation (SD), the mean daily δ glucose (mean of daily difference between maximum and minimum glucose), and the coefficient of variation (CV) of glucose, expressed as percent glucose (SD)/glucose (mean).
RESULTS: At the admission, first fasting blood glucose, pharmacological treatments (insulin and/or anti-diabetic drugs) prior to entering the study and basal glycated hemoglobin (HbA1c) were observed in the two groups treated with subcutaneous or intravenous insulin infusion, respectively. When compared with patients submitted to standard therapy, insulin-infused patients showed both increased first 24-h (median 6.9 mmol/L vs 5.7 mmol/L P < 0.045) and overall hospitalization δ glucose (median 10.9 mmol/L vs 9.3 mmol/L, P < 0.028), with a tendency to a significant increase in first 24-h glycaemic CV (23.1% vs 19.6%, P < 0.053). Severe hypoglycaemia was rare (14.3%), and it was observed only in 3 patients receiving insulin infusion therapy. HbA1c values measured during hospitalization and 3 mo after discharge did not differ in the two groups of treatment.
CONCLUSION: Our pilot data suggest that no real benefit in terms of GLUCV is observed when routinely managing blood glucose by insulin infusion therapy in type 2 diabetic ACS hospitalized patients in respect to conventional insulin treatment
Collapse
|
8
|
Screening for prediabetes using machine learning models. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2014; 2014:618976. [PMID: 25165484 PMCID: PMC4140121 DOI: 10.1155/2014/618976] [Citation(s) in RCA: 50] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/28/2014] [Accepted: 07/08/2014] [Indexed: 12/30/2022]
Abstract
The global prevalence of diabetes is rapidly increasing. Studies support the necessity of screening and interventions for prediabetes, which could result in serious complications and diabetes. This study aimed at developing an intelligence-based screening model for prediabetes. Data from the Korean National Health and Nutrition Examination Survey (KNHANES) were used, excluding subjects with diabetes. The KNHANES 2010 data (n = 4685) were used for training and internal validation, while data from KNHANES 2011 (n = 4566) were used for external validation. We developed two models to screen for prediabetes using an artificial neural network (ANN) and support vector machine (SVM) and performed a systematic evaluation of the models using internal and external validation. We compared the performance of our models with that of a screening score model based on logistic regression analysis for prediabetes that had been developed previously. The SVM model showed the areas under the curve of 0.731 in the external datasets, which is higher than those of the ANN model (0.729) and the screening score model (0.712), respectively. The prescreening methods developed in this study performed better than the screening score model that had been developed previously and may be more effective method for prediabetes screening.
Collapse
|