The Use of Machine Learning Techniques to Determine the Predictive Value of Inflammatory Biomarkers in the Development of Type 2 Diabetes Mellitus

2021 ◽  
Author(s):  
Rafael Garcia-Carretero ◽  
Luis Vigil-Medina ◽  
Oscar Barquero-Perez
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Predictive Value ◽  
Inflammatory Biomarkers ◽  
Machine Learning Techniques ◽  
Learning Techniques

scholarly journals Development of Type 2 Diabetes Mellitus Phenotyping Framework Using Expert Knowledge and Machine Learning Approach

2016 ◽  
Vol 11 (4) ◽  
pp. 791-799 ◽  
Author(s):  
Rina Kagawa ◽  
Yoshimasa Kawazoe ◽  
Yusuke Ida ◽  
Emiko Shinohara ◽  
Katsuya Tanaka ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Expert Knowledge ◽  
The Other ◽  
Learning Approach ◽  
Research Subjects ◽  
Machine Learning Approach

Background: Phenotyping is an automated technique that can be used to distinguish patients based on electronic health records. To improve the quality of medical care and advance type 2 diabetes mellitus (T2DM) research, the demand for T2DM phenotyping has been increasing. Some existing phenotyping algorithms are not sufficiently accurate for screening or identifying clinical research subjects. Objective: We propose a practical phenotyping framework using both expert knowledge and a machine learning approach to develop 2 phenotyping algorithms: one is for screening; the other is for identifying research subjects. Methods: We employ expert knowledge as rules to exclude obvious control patients and machine learning to increase accuracy for complicated patients. We developed phenotyping algorithms on the basis of our framework and performed binary classification to determine whether a patient has T2DM. To facilitate development of practical phenotyping algorithms, this study introduces new evaluation metrics: area under the precision-sensitivity curve (AUPS) with a high sensitivity and AUPS with a high positive predictive value. Results: The proposed phenotyping algorithms based on our framework show higher performance than baseline algorithms. Our proposed framework can be used to develop 2 types of phenotyping algorithms depending on the tuning approach: one for screening, the other for identifying research subjects. Conclusions: We develop a novel phenotyping framework that can be easily implemented on the basis of proper evaluation metrics, which are in accordance with users’ objectives. The phenotyping algorithms based on our framework are useful for extraction of T2DM patients in retrospective studies.

Prediction Model for Prevalence of Type-2 Diabetes Mellitus Complications Using Machine Learning Approach

2019 ◽  
pp. 103-116 ◽  
Author(s):  
Muhammad Younus ◽  
Md Tahsir Ahmed Munna ◽  
Mirza Mohtashim Alam ◽  
Shaikh Muhammad Allayear ◽  
Sheikh Joly Ferdous Ara
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Prediction Model ◽  
Learning Approach ◽  
Machine Learning Approach

scholarly journals IDENTIFICATION AND ASSESSMENT OF PREDIABETES-A RURAL INDIAN STUDY (A CORRELATIVE STUDY BETWEEN QUESTIONNAIRE AND BIOCHEMICAL ANALYSIS)

2020 ◽  
pp. 36-40
Author(s):  
VENKATESAN S. ◽  
SUSILA S. ◽  
SUTHANTHIRAN S. ◽  
MADHUSUDHAN S. ◽  
PAARI N.
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Risk Score ◽  
Predictive Value ◽  
Screening Tool ◽  
Diabetic Patients ◽  
Cross Sectional ◽  
Family History Of Diabetes

Objective: To identify and prevent the vulnerable prediabetic population becoming diabetic patients in the future using the Indian Diabetic Risk Score (IDRS) and to evaluate the performance of the IDRS questionnaire for detecting prediabetes and predicting the risk of Type 2 Diabetes Mellitus in Chidambaram rural Indian population. Methods: A cross-sectional descriptive study was carried out among patients attending a master health check-up of RMMCH hospital located at Chidambaram. The IDRS was calculated by using four simple measures of age, family history of diabetes, physical activity, and waist measurement. The relevant blood test, like Fasting plasma glucose (FBS), Glycated hemoglobin (HbA1C) test, were observed for identifying prediabetes. Subjects were classified as Normoglycemic, prediabetics, and diabetics based on the questionnaire and diagnostic criteria of the Indian Council of Medical Research (ICMR) guidelines. Results: In the study, sensitivity and specificity of IDRS score were found to be 84.21% and 63.4% respectively for detecting prediabetes in community with the positive predictive value of 51.6% and negative predictive value of 89.6% and prevalence of prediabetes in the Chidambaram rural population is 31.6% among the 60 participants. Conclusion: The Indian diabetic risk score questionnaire designed by Ma­dras diabetic research federation is a useful screening tool to identify unknown type 2 diabetes mellitus. The question­naire is a reliable, valuable, and easy to use screening tool which can be used in a primary care setup. 

Cardiac and Inflammatory Biomarkers Are Associated with Worsening Renal Outcomes in Patients with Type 2 Diabetes Mellitus: Observations from SAVOR-TIMI 53

2019 ◽  
Vol 65 (6) ◽  
pp. 781-790 ◽  
Author(s):  
Thomas A Zelniker ◽  
David A Morrow ◽  
Ofri Mosenzon ◽  
Yared Gurmu ◽  
Kyungah Im ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Renal Function ◽  
High Risk ◽  
High Sensitivity ◽  
Inflammatory Biomarkers ◽  
P Values ◽  
Hs Crp

Abstract BACKGROUND Cardiac and renal diseases commonly occur with bidirectional interactions. We hypothesized that cardiac and inflammatory biomarkers may assist in identification of patients with type 2 diabetes mellitus (T2DM) at high risk of worsening renal function. METHODS In this exploratory analysis from SAVOR-TIMI 53, concentrations of high-sensitivity cardiac troponin T (hs-TnT), N-terminal pro–B-type natriuretic peptide (NT-proBNP), and high-sensitivity C-reactive protein (hs-CRP) were measured in baseline serum samples of 12310 patients. The primary end point for this analysis was a ≥40% decrease in estimated glomerular filtration rate (eGFR) at end of treatment (EOT) at a median of 2.1 years. The relationships between biomarkers and the end point were modeled using adjusted logistic and Cox regression. RESULTS After multivariable adjustment including baseline renal function, each biomarker was independently associated with an increased risk of ≥40% decrease in eGFR at EOT [Quartile (Q) Q4 vs Q1: hs-TnT adjusted odds ratio (OR), 5.63 (3.49–9.10); NT-proBNP adjusted OR, 3.53 (2.29–5.45); hs-CRP adjusted OR, 1.84 (95% CI, 1.27–2.68); all P values ≤0.001]. Furthermore, each biomarker was independently associated with higher risk of worsening of urinary albumin-to-creatinine ratio (UACR) category (all P values ≤0.002). Sensitivity analyses in patients without heart failure and eGFR >60 mL/min provided similar results. In an adjusted multimarker model, hs-TnT and NT-proBNP remained significantly associated with both renal outcomes (all P values <0.01). CONCLUSIONS hs-TnT, NT-proBNP, and hs-CRP were each associated with worsening of renal function [reduction in eGFR (≥40%) and deterioration in UACR class] in high-risk patients with T2DM. Patients with high cardiac or inflammatory biomarkers should be treated not only for their risk of cardiovascular outcomes but also followed for renal deterioration.

Synergistic Effect of Low Neutrophil–Lymphocyte Ratio With Physical Activity on Quality of Life in Type 2 Diabetes Mellitus: A Community-Based Study

2020 ◽  
Vol 22 (3) ◽  
pp. 378-387 ◽  
Author(s):  
Yohanes Andy Rias ◽  
Maria Dyah Kurniasari ◽  
Victoria Traynor ◽  
Shu Fen Niu ◽  
Bayu Satria Wiratama ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Physical Activity ◽  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Synergistic Effect ◽  
Inflammatory Biomarkers ◽  
Neutrophil Lymphocyte Ratio

Background: Physical inactivity and Type 2 diabetes mellitus (T2DM)–associated inflammatory biomarkers are correlated with poor quality of life (QoL). However, no study has investigated the synergistic effect of physical activity (PA) and lower neutrophil–lymphocyte ratio (NLR) on QoL. Objective: We examined the independent and synergistic effects of PA and inflammatory biomarkers on three domains of QoL in T2DM. Methods: This cross-sectional study included 294 patients with T2DM from community clinics in Indonesia. The 36-item Short Form Survey and a questionnaire about PA engagement were used to measure QoL and metabolic equivalent of task (MET)-hr/week, respectively. Inflammatory biomarkers were measured in fasting blood. Adjusted coefficients β and 95% confidence interval (CI) were estimated using multiple linear regression. The synergistic effect was analyzed using additive interaction for linear regression. Results: Patients with PA ≥ 7.5 MET-hr/week exhibited significantly higher total QoL (β = 8.41, 95% CI = [6.04, 10.78]) and physical component score (PCS; β = 13.90, 95% CI = [10.52, 17.29]) than those with PA < 7.5 MET-hr/week. Patients with NLR < 1.940 had significantly higher total QoL (β = 4.76, 95% CI = [3.41, 6.11]), mental component score (MCS; β = 2.62, 95% CI = [0.75, 4.49]), and PCS (β = 6.89, 95% CI = [4.97, 8.82]) than patients with NLR ≥ 1.940. PA ≥ 7.5 MET-hr/week and NLR < 1.940 exhibited a synergistic effect on total QoL, MCS, and PCS. Conclusions: High PA level and low NLR had a positive synergistic effect on QoL among patients with T2DM.

Sign in / Sign up

Export Citation Format

Share Document