scholarly journals Body fat predicts exercise capacity in persons with Type 2 Diabetes Mellitus: A machine learning approach

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0248039
Author(s):  
Tanmay Nath ◽  
Rexford S. Ahima ◽  
Prasanna Santhanam
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Type 2 Diabetes ◽  
Body Composition ◽  
Exercise Capacity ◽  
Body Fat ◽  
Baseline Data ◽  
Fat Percentage ◽  
Maximum Exercise

Diabetes mellitus is associated with increased cardiovascular disease (CVD) related morbidity, mortality and death. Exercise capacity in persons with type 2 diabetes has been shown to be predictive of cardiovascular events. In this study, we used the data from the prospective randomized LOOK AHEAD study and used machine learning algorithms to help predict exercise capacity (measured in Mets) from the baseline data that included cardiovascular history, medications, blood pressure, demographic information, anthropometric and Dual-energy X-Ray Absorptiometry (DXA) measured body composition metrics. We excluded variables with high collinearity and included DXA obtained Subtotal (total minus head) fat percentage and Subtotal lean mass (gms). Thereafter, we used different machine learning methods to predict maximum exercise capacity. The different machine learning models showed a strong predictive performance for both females and males. Our study shows that using baseline data from a large prospective cohort, we can predict maximum exercise capacity in persons with diabetes mellitus. We show that subtotal fat percentage is the most important feature for predicting the exercise capacity for males and females after accounting for other important variables. Until now, BMI and waist circumference were commonly used surrogates for adiposity and there was a relative under-appreciation of body composition metrics for understanding the pathophysiology of CVD. The recognition of body fat percentage as an important marker in determining CVD risk has prognostic implications with respect to cardiovascular morbidity and mortality.

scholarly journals Skinfold thickness and the incidence of type 2 diabetes mellitus and hypertension: an analysis of the PERU MIGRANT study

2019 ◽  
Vol 23 (1) ◽  
pp. 63-71 ◽  
Author(s):  
Andrea Ruiz-Alejos ◽  
Rodrigo M Carrillo-Larco ◽  
J Jaime Miranda ◽  
Robert H Gilman ◽  
Liam Smeeth ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Body Fat ◽  
Strong Association ◽  
Skinfold Thickness ◽  
Fat Percentage ◽  
Urban Migrants ◽  
Incidence Analysis

AbstractObjective:To determine the association between excess body fat, assessed by skinfold thickness, and the incidence of type 2 diabetes mellitus (T2DM) and hypertension (HT).Design:Data from the ongoing PERU MIGRANT Study were analysed. The outcomes were T2DM and HT, and the exposure was skinfold thickness measured in bicipital, tricipital, subscapular and suprailiac areas. The Durnin–Womersley formula and SIRI equation were used for body fat percentage estimation. Risk ratios and population attributable fractions (PAF) were calculated using Poisson regression.Setting:Rural (Ayacucho) and urban shantytown district (San Juan de Miraflores, Lima) in Peru.Participants:Adults (n 988) aged ≥30 years (rural, rural-to-urban migrants, urban) completed the baseline study. A total of 785 and 690 were included in T2DM and HT incidence analysis, respectively.Results:At baseline, age mean was 48·0 (sd 12·0) years and 47 % were males. For T2DM, in 7·6 (sd 1·3) years, sixty-one new cases were identified, overall incidence of 1·0 (95 % CI 0·8, 1·3) per 100 person-years. Bicipital and subscapular skinfolds were associated with 2·8-fold and 6·4-fold risk of developing T2DM. On the other hand, in 6·5 (sd 2·5) years, overall incidence of HT was 2·6 (95 % CI 2·2, 3·1) per 100 person-years. Subscapular and overall fat obesity were associated with 2·4- and 2·9-fold risk for developing HT. The PAF for subscapular skinfold was 73·6 and 39·2 % for T2DM and HT, respectively.Conclusions:We found a strong association between subscapular skinfold thickness and developing T2DM and HT. Skinfold assessment can be a laboratory-free strategy to identify high-risk HT and T2DM cases.

scholarly journals Longitudinally evaluated the relationship between body fat percentage and the risk for type 2 diabetes mellitus: Korean Genome and Epidemiology Study (KoGES)

2018 ◽  
Vol 178 (5) ◽  
pp. 513-521 ◽  
Author(s):  
Sung Keun Park ◽  
Jae-Hong Ryoo ◽  
Chang-Mo Oh ◽  
Joong-Myung Choi ◽  
Ju Young Jung
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Body Fat ◽  
Subgroup Analysis ◽  
Body Fat Percentage ◽  
Fat Percentage ◽  
Specific Level ◽  
Obese Population

Background Body fat plays the significant role in maintaining glucose homeostasis. However, it is not fully identified how body fat percentage (BF%) has an impact on the development of type 2 diabetes mellitus (T2DM). Thus, this study was to evaluate the incidental risk for T2DM according to BF% level. Methods In a community-based Korean cohort, 5972 Korean adults were divided into quintile groups by BF% and followed up for 10 years to monitor the development of T2DM. Cox proportional hazard model was used to evaluate the hazard ratios (HRs) for T2DM according to BF% quintile. Additionally, subgroup analysis was conducted by low and high level of BF% (cut-off: 25 in men and 35 in women) and body mass index (BMI). Results In adjusted model, compared to the BF% quintile 1 group, the risk for T2DM significantly increased over BF% of 22.8% in men and 32.9% in women (≥quintile 4). The level of BF% related to the increased risk for T2DM was lower in non-obese men (22.8%) than obese men (28.4%). In subgroup analysis, men with low BMI (<25) and high BF% (≥25) had the highest risk for T2DM than other subgroups (HRs: 1.83 (1.33–2.52)). However, this association did not show the statistical significance in women (HRs: 1.63 (0.98–2.72)). Conclusion The incidental risk for T2DM significantly increased over the specific level of BF%, which was lower in non-obese population than obese population. Gender difference was suggested in the incidental relationship between BF% and T2DM.

Insulin-resistant patients with type 2 diabetes mellitus have higher serum leptin levels independently of body fat mass

2002 ◽  
Vol 39 (3) ◽  
pp. 105-110 ◽  
Author(s):  
S. Fischer ◽  
M. Hanefeld ◽  
S. M. Haffner ◽  
C. Fusch ◽  
U. Schwanebeck ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Body Fat ◽  
Fat Mass ◽  
Body Fat Mass ◽  
Serum Leptin ◽  
Insulin Resistant

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.

Sign in / Sign up

Export Citation Format

Share Document