Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population

Choe, Eun Kyung; Rhee, Hwanseok; Lee, Seungjae; Shin, Eun-Soon; Oh, Seung-Won; Lee, Jong-Eun; Choi, Seung Ho

doi:10.5808/gi.2018.16.4.e31

Cited by 36 publications

(48 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature search returned 7744 results after removing duplicates. We reviewed 362 full texts, of which 110 studies met inclusion criteria (28‐30, 33‐138). See Fig.…”

Section: Resultsmentioning

confidence: 99%

Cardiometabolic risk prediction algorithms for young people with psychosis: a systematic review and exploratory analysis

Perry

Upthegrove

Crawford

et al. 2020

Acta Psychiatr Scand

View full text Add to dashboard Cite

Objective Cardiometabolic risk prediction algorithms are common in clinical practice. Young people with psychosis are at high risk for developing cardiometabolic disorders. We aimed to examine whether existing cardiometabolic risk prediction algorithms are suitable for young people with psychosis. Methods We conducted a systematic review and narrative synthesis of studies reporting the development and validation of cardiometabolic risk prediction algorithms for general or psychiatric populations. Furthermore, we used data from 505 participants with or at risk of psychosis at age 18 years in the ALSPAC birth cohort, to explore the performance of three algorithms (QDiabetes, QRISK3 and PRIMROSE) highlighted as potentially suitable. We repeated analyses after artificially increasing participant age to the mean age of the original algorithm studies to examine the impact of age on predictive performance. Results We screened 7820 results, including 110 studies. All algorithms were developed in relatively older participants, and most were at high risk of bias. Three studies (QDiabetes, QRISK3 and PRIMROSE) featured psychiatric predictors. Age was more strongly weighted than other risk factors in each algorithm. In our exploratory analysis, calibration plots for all three algorithms implied a consistent systematic underprediction of cardiometabolic risk in the younger sample. After increasing participant age, calibration plots were markedly improved. Conclusion Existing cardiometabolic risk prediction algorithms cannot be recommended for young people with or at risk of psychosis. Existing algorithms may underpredict risk in young people, even in the face of other high‐risk features. Recalibration of existing algorithms or a new tailored algorithm for the population is required.

show abstract

“…The literature search returned 7744 results after removing duplicates. We reviewed 362 full texts, of which 110 studies met inclusion criteria (28‐30, 33‐138). See Fig.…”

Section: Resultsmentioning

confidence: 99%

Cardiometabolic risk prediction algorithms for young people with psychosis: a systematic review and exploratory analysis

Perry

Upthegrove

Crawford

et al. 2020

Acta Psychiatr Scand

View full text Add to dashboard Cite

show abstract

“…Thus, it is hoped that if future studies are conducted with a good design and focus on the effect of gender, we could gain more favorable results. Also, we can develop prediction models such as Choe et al 42 in Korea, for metabolic status in obese or overweight woman in our population, if dietary and alcohols consumption data are included.…”

Section: Discussionmentioning

confidence: 99%

Genetic markers and continuity of healthy metabolic status: Tehran cardio-metabolic genetic study (TCGS)

Ahangar

Javanrouh

Daneshpour

et al. 2020

Sci Rep

View full text Add to dashboard Cite

obese individuals can be categorized as "healthy obese" (MHo) and "unhealthy obese" (MUo) based on the presence or absence of metabolic abnormality. this study sets out to assess potential genetic causes behind persistence of healthy metabolic status in individuals categorized as "healthy obese". This study was conducted in the framework of the Tehran cardio-metabolic genetic study (TCGS). 766 MHO subjects at the start of the study followed up 15 years for occurrence of metabolic unhealthy status. these two groups (persistent MHo, MUo) were compared regarding the presence or absence of 16 single nucleotide polymorphisms (SNPs) identified as being associated with obesity phenotype in previous studies. We used logistic regression model for assessing the association between MHo/ MUO with candidate SNPs. By the end of the follow up, 206 (27%) were categorized as the persistent MHO and 560 (73%) as MUO groups. Considering interaction effect between some SNP and sex, a sex stratification analysis was applied. When the analysis was performed by gender, rs1121980 associated with a decrease, and rs7903146 with an increase in the likelihood of persistent MHO individuals. Another analysis was separately performed on postmenopausal women from both groups; it showed that rs13107325 was associated with an increase in the likelihood of persistent MHO status in this subgroup of woman. In all cases, the markers had dominant inheritance. This findings suggest that the expression of some genetic markers are associated with persistence of healthy metabolic status, in female obese individuals. Obesity and overweight have a clear association with long-term morbidity and mortality 1,2. There is a wide range of heterogeneity among obese individuals with the combination of obesity and metabolic status causing a wide spectrum of obesity phenotypes 3,4. Prevalence of "healthy obese" is reported to be between 9 and 34% in different populations depending on various definitions of metabolic healthy status 5-8. Whether "healthy obese" has a benign course is controversial and different studies have reported varying results 9-12. Some studies have shown that this obesity phenotype is a dynamic entity and in cohort studies up to 50% of individuals who were "healthy obese" turned into "unhealthy obese" at the end of the follow-up period 5-8. Some studies have assessed the predictors of changes in metabolic health in healthy obese individuals. Achilike et al. 13 suggested that lipid profile and insulin resistance predict the metabolic status in obesity. Appleton et al. 6 reported that younger age and lower waist circumference (WC) at baseline of obese individuals were significantly associated with maintaining the metabolic healthy state in a longitudinal follow-up. In addition, a study on Tehranian healthy abdominal obese individuals showed that baseline hypertriglyceridemia, low HDL-C, and HOMA-IR were independent predictors of metabolic changes in this population 5. However, it has been known that obesity and the resulting metabolic abnormality a...

show abstract

“…Distinguishing between these groups of MetS might be necessary because of the potential management implications [11]. But, without a validated special test, it may not be possible to detect or suspect MetS in nonobese individuals and those patients who may not be otherwise suspected to have it [10]. Individuals with nonobese MetS may have relatively low perception of risk of MetS, and may be missed by clinicians (because they may not be considered high risk) [10].…”

Section: Discussionmentioning

confidence: 99%

“…But, without a validated special test, it may not be possible to detect or suspect MetS in nonobese individuals and those patients who may not be otherwise suspected to have it [10]. Individuals with nonobese MetS may have relatively low perception of risk of MetS, and may be missed by clinicians (because they may not be considered high risk) [10]. Similarly, in obese patients, MetS can be used as a marker indicating increase need of intervention to reduce subsequent risk of CVD and T2DM.…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, abdominal obesity is generally presumed to be central to the diagnosis of MetS, but, not all individuals with obesity have MetS and vice versa [9]. Without a valid test, it may not be possible to detect or suspect MetS in nonobese individuals [10]. Identifying the subset of individuals (both obese and nonobese) with MetS is necessary and could have implications on subsequent management approach [11].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Risk models and scores for metabolic syndrome: a systematic review

Ibrahim

Pang

Pappas

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Metabolic syndrome - ‘a clustering of risk factors which includes hypertension, central obesity, impaired glucose metabolism with insulin resistance, and dyslipidaemia’ is linked with increased risk of CVD, T2DM and all-cause mortality. Despite the high number of models and scores for assessing the risk of developing MetS, there is hardly any used in research or practical setting. Hence, we conducted a systematic review to determine the performance of risk models and scores for predicting MetS.Methods: Following the methods proposed by EPPI-Centre, we systematically searched MEDLINE, CINAHL, PUBMED and Web of Science to identify studies that either derive or validate risk models or scores for predicting the risk of MetS. Search was originally done in September 2018 and updated in September 2020. Data concerning models’ statistical properties as well as details of internal or external validations were extracted. Tables were used to compare various components of models and statistical properties. Finally, PROBAST was used to assess the methodological quality (risk of bias) of included studies.Results: A total of 27 studies reporting about the development, validation or both of MetS risk models were included. There is significant heterogeneity between studies in terms of geography/demographics, data type and methodological approach. Majority of the models or risk scores were developed or validated using data from cross-sectional studies, or routine data. Various combinations of risk factors (predictors) were considered significant in the respective final model. Similarly, different criteria were used in the diagnosis of MetS, but, NCEP criteria including its modified versions were by far the most widely used (32.5%). There is generally poor reporting quality across the studies, especially concerning statistical data. Any form of internal validation is either not conducted, or not reported in nearly a fifth of the studies. Only two (2) risk models or scores were externally validatedConclusions: There is an abundance of MetS models in the literature. But, their usefulness is doubtful, due to limitations in methodology, poor reporting and lack of external validation and impact studies. Therefore, researchers in the future should focus more on externally validating/ applying such models in a different setting.Protocol:The protocol of this study can be found at https://bmjopen.bmj.com/content/9/9/e027326PROSPERO registration number CRD42019139326

show abstract

Metabolic Syndrome Prediction Using Machine Learning Models with Genetic and Clinical Information from a Nonobese Healthy Population

Cited by 36 publications

References 42 publications

Cardiometabolic risk prediction algorithms for young people with psychosis: a systematic review and exploratory analysis

Cardiometabolic risk prediction algorithms for young people with psychosis: a systematic review and exploratory analysis

Genetic markers and continuity of healthy metabolic status: Tehran cardio-metabolic genetic study (TCGS)

Risk models and scores for metabolic syndrome: a systematic review

Contact Info

Product

Resources

About