Development and Validation of an Insulin Resistance Predicting Model Using a Machine-Learning Approach in a Population-Based Cohort in Korea

Background: Insulin resistance is a common etiology of metabolic syndrome, but receiver operating characteristic (ROC) curve analysis shows a weak association in Koreans. Using a machine learning (ML) approach, we aimed to generate the best model for predicting insulin resistance in Korean adults aged > 40 of the Ansan/Ansung cohort using a machine learning (ML) approach. Methods: The demographic, anthropometric, biochemical, genetic, nutrient, and lifestyle variables of 8842 participants were included. The polygenetic risk scores (PRS) generated by a genome-wide association study were added to represent the genetic impact of insulin resistance. They were divided randomly into the training (n = 7037) and test (n = 1769) sets. Potentially important features were selected in the highest area under the curve (AUC) of the ROC curve from 99 features using seven different ML algorithms. The AUC target was ≥0.85 for the best prediction of insulin resistance with the lowest number of features. Results: The cutoff of insulin resistance defined with HOMA-IR was 2.31 using logistic regression before conducting ML. XGBoost and logistic regression algorithms generated the highest AUC (0.86) of the prediction models using 99 features, while the random forest algorithm generated a model with 0.82 AUC. These models showed high accuracy and k-fold values (>0.85). The prediction model containing 15 features had the highest AUC of the ROC curve in XGBoost and random forest algorithms. PRS was one of 15 features. The final prediction models for insulin resistance were generated with the same nine features in the XGBoost (AUC = 0.86), random forest (AUC = 0.84), and artificial neural network (AUC = 0.86) algorithms. The model included the fasting serum glucose, ALT, total bilirubin, HDL concentrations, waist circumference, body fat, pulse, season to enroll in the study, and gender. Conclusion: The liver function, regular pulse checking, and seasonal variation in addition to metabolic syndrome components should be considered to predict insulin resistance in Koreans aged over 40 years.

Download Full-text

Machine Learning-based in-hospital Mortality Prediction Models for Patients With Acute Coronary Syndrome

10.21203/rs.3.rs-134944/v1 ◽

2020 ◽

Author(s):

Jun Ke ◽

Yiwei Chen ◽

Xiaoping Wang ◽

Zhiyong Wu ◽

qiongyao Zhang ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Random Forest ◽

Hospital Mortality ◽

Operating Characteristic ◽

Prediction Models ◽

Characteristic Curve ◽

Multivariate Logistic Regression Analysis ◽

Hdl Cholesterol ◽

Coronary Syndrome

Abstract BackgroundThe purpose of this study is to identify the risk factors of in-hospital mortality in patients with acute coronary syndrome (ACS) and to evaluate the performance of traditional regression and machine learning prediction models.MethodsThe data of ACS patients who entered the emergency department of Fujian Provincial Hospital from January 1, 2017 to March 31, 2020 for chest pain were retrospectively collected. The study used univariate and multivariate logistic regression analysis to identify risk factors for in-hospital mortality of ACS patients. The traditional regression and machine learning algorithms were used to develop predictive models, and the sensitivity, specificity, and receiver operating characteristic curve were used to evaluate the performance of each model.ResultsA total of 7810 ACS patients were included in the study, and the in-hospital mortality rate was 1.75%. Multivariate logistic regression analysis found that age and levels of D-dimer, cardiac troponin I, N-terminal pro-B-type natriuretic peptide (NT-proBNP), lactate dehydrogenase (LDH), high-density lipoprotein (HDL) cholesterol, and calcium channel blockers were independent predictors of in-hospital mortality. The study found that the area under the receiver operating characteristic curve of the models developed by logistic regression, gradient boosting decision tree (GBDT), random forest, and support vector machine (SVM) for predicting the risk of in-hospital mortality were 0.963, 0.960, 0.963, and 0.959, respectively. Feature importance evaluation found that NT-proBNP, LDH, and HDL cholesterol were top three variables that contribute the most to the prediction performance of the GBDT model and random forest model.ConclusionsThe predictive model developed using logistic regression, GBDT, random forest, and SVM algorithms can be used to predict the risk of in-hospital death of ACS patients. Based on our findings, we recommend that clinicians focus on monitoring the changes of NT-proBNP, LDH, and HDL cholesterol, as this may improve the clinical outcomes of ACS patients.

Download Full-text

Development of an ensemble machine learning prognostic model to predict 60-day risk of major adverse cardiac events in adults with chest pain

10.1101/2021.03.08.21252615 ◽

2021 ◽

Author(s):

Chris J. Kennedy ◽

Dustin G. Mark ◽

Jie Huang ◽

Mark J. van der Laan ◽

Alan E. Hubbard ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Chest Pain ◽

Random Forest ◽

Decision Trees ◽

Low Risk ◽

Major Adverse Cardiac Events ◽

Risk Scores ◽

Cardiac Events ◽

Adverse Cardiac Events

Background: Chest pain is the second leading reason for emergency department (ED) visits and is commonly identified as a leading driver of low-value health care. Accurate identification of patients at low risk of major adverse cardiac events (MACE) is important to improve resource allocation and reduce over-treatment. Objectives: We sought to assess machine learning (ML) methods and electronic health record (EHR) covariate collection for MACE prediction. We aimed to maximize the pool of low-risk patients that are accurately predicted to have less than 0.5% MACE risk and may be eligible for reduced testing. Population Studied: 116,764 adult patients presenting with chest pain in the ED and evaluated for potential acute coronary syndrome (ACS). 60-day MACE rate was 1.9%. Methods: We evaluated ML algorithms (lasso, splines, random forest, extreme gradient boosting, Bayesian additive regression trees) and SuperLearner stacked ensembling. We tuned ML hyperparameters through nested ensembling, and imputed missing values with generalized low-rank models (GLRM). We benchmarked performance to key biomarkers, validated clinical risk scores, decision trees, and logistic regression. We explained the models through variable importance ranking and accumulated local effect visualization. Results: The best discrimination (area under the precision-recall [PR-AUC] and receiver operating characteristic [ROC-AUC] curves) was provided by SuperLearner ensembling (0.148, 0.867), followed by random forest (0.146, 0.862). Logistic regression (0.120, 0.842) and decision trees (0.094, 0.805) exhibited worse discrimination, as did risk scores [HEART (0.064, 0.765), EDACS (0.046, 0.733)] and biomarkers [serum troponin level (0.064, 0.708), electrocardiography (0.047, 0.686)]. The ensemble's risk estimates were miscalibrated by 0.2 percentage points. The ensemble accurately identified 50% of patients to be below a 0.5% 60-day MACE risk threshold. The most important predictors were age, peak troponin, HEART score, EDACS score, and electrocardiogram. GLRM imputation achieved 90% reduction in root mean-squared error compared to median-mode imputation. Conclusion: Use of ML algorithms, combined with broad predictor sets, improved MACE risk prediction compared to simpler alternatives, while providing calibrated predictions and interpretability. Standard risk scores may neglect important health information available in other characteristics and combined in nuanced ways via ML.

Download Full-text

Identification of Metabolic Syndrome Based on Anthropometric, Blood and Spirometric Risk Factors Using Machine Learning

Applied Sciences ◽

10.3390/app10217741 ◽

2020 ◽

Vol 10 (21) ◽

pp. 7741

Author(s):

Sang Yeob Kim ◽

Gyeong Hee Nam ◽

Byeong Mun Heo

Keyword(s):

Machine Learning ◽

Metabolic Syndrome ◽

Logistic Regression ◽

Prediction Model ◽

Prediction Models ◽

Strong Association ◽

Forced Expiratory Volume ◽

Binary Logistic Regression Analysis ◽

Cross Sectional Survey ◽

Cross Sectional

Metabolic syndrome (MS) is an aggregation of coexisting conditions that can indicate an individual’s high risk of major diseases, including cardiovascular disease, stroke, cancer, and type 2 diabetes. We conducted a cross-sectional survey to evaluate potential risk factor indicators by identifying relationships between MS and anthropometric and spirometric factors along with blood parameters among Korean adults. A total of 13,978 subjects were enrolled from the Korea National Health and Nutrition Examination Survey. Statistical analysis was performed using a complex sampling design to represent the entire Korean population. We conducted binary logistic regression analysis to evaluate and compare potential associations of all included factors. We constructed prediction models based on Naïve Bayes and logistic regression algorithms. The performance evaluation of the prediction model improved the accuracy with area under the curve (AUC) and calibration curve. Among all factors, triglyceride exhibited a strong association with MS in both men (odds ratio (OR) = 2.711, 95% confidence interval (CI) [2.328–3.158]) and women (OR = 3.515 [3.042–4.062]). Regarding anthropometric factors, the waist-to-height ratio demonstrated a strong association in men (OR = 1.511 [1.311–1.742]), whereas waist circumference was the strongest indicator in women (OR = 2.847 [2.447–3.313]). Forced expiratory volume in 6s and forced expiratory flow 25–75% strongly associated with MS in both men (OR = 0.822 [0.749–0.903]) and women (OR = 1.150 [1.060–1.246]). Wrapper-based logistic regression prediction model showed the highest predictive power in both men and women (AUC = 0.868 and 0.932, respectively). Our findings revealed that several factors were associated with MS and suggested the potential of employing machine learning models to support the diagnosis of MS.

Download Full-text

Predicting mortality in hemodialysis patients using machine learning analysis

Clinical Kidney Journal ◽

10.1093/ckj/sfaa126 ◽

2020 ◽

Author(s):

Victoria Garcia-Montemayor ◽

Alejandro Martin-Malo ◽

Carlo Barbieri ◽

Francesco Bellocchio ◽

Sagrario Soriano ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Random Forest ◽

Prediction Models ◽

Initial Period ◽

Area Under The Curve ◽

Mortality Prediction ◽

Machine Learning Techniques ◽

Prediction Of Mortality ◽

Mortality Prediction Models

Abstract Background Besides the classic logistic regression analysis, non-parametric methods based on machine learning techniques such as random forest are presently used to generate predictive models. The aim of this study was to evaluate random forest mortality prediction models in haemodialysis patients. Methods Data were acquired from incident haemodialysis patients between 1995 and 2015. Prediction of mortality at 6 months, 1 year and 2 years of haemodialysis was calculated using random forest and the accuracy was compared with logistic regression. Baseline data were constructed with the information obtained during the initial period of regular haemodialysis. Aiming to increase accuracy concerning baseline information of each patient, the period of time used to collect data was set at 30, 60 and 90 days after the first haemodialysis session. Results There were 1571 incident haemodialysis patients included. The mean age was 62.3 years and the average Charlson comorbidity index was 5.99. The mortality prediction models obtained by random forest appear to be adequate in terms of accuracy [area under the curve (AUC) 0.68–0.73] and superior to logistic regression models (ΔAUC 0.007–0.046). Results indicate that both random forest and logistic regression develop mortality prediction models using different variables. Conclusions Random forest is an adequate method, and superior to logistic regression, to generate mortality prediction models in haemodialysis patients.

Download Full-text

Association of Polygenetic Risk Scores Related to Immunity and Inflammation with Hyperthyroidism Risk and Interactions between the Polygenetic Scores and Dietary Factors in a Large Cohort

Journal of Thyroid Research ◽

10.1155/2021/7664641 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Mi Young Song ◽

Sunmin Park

Keyword(s):

Metabolic Syndrome ◽

Genome Wide Association Study ◽

Human Leukocyte ◽

Dietary Factors ◽

Risk Scores ◽

Nucleotide Polymorphisms ◽

Dietary Intakes ◽

Urban Hospital ◽

Coffee Intake ◽

A Genome

Graves’s disease and thyroiditis induce hyperthyroidism, the causes of which remain unclear, although they are involved with genetic and environmental factors. We aimed to evaluate polygenetic variants for hyperthyroidism risk and their interaction with metabolic parameters and nutritional intakes in an urban hospital-based cohort. A genome-wide association study (GWAS) of participants with (cases; n = 842) and without (controls, n = 38,799) hyperthyroidism was used to identify and select genetic variants. In clinical and lifestyle interaction with PRS, 312 participants cured of hyperthyroidism were excluded. Single nucleotide polymorphisms (SNPs) associated with gene-gene interactions were selected by hyperthyroidism generalized multifactor dimensionality reduction. Polygenic risk scores (PRSs) were generated by summing the numbers of selected SNP risk alleles. The best gene-gene interaction model included tumor-necrosis factor (TNF)_rs1800610, mucin 22 (MUC22)_rs1304322089, tribbles pseudokinase 2 (TRIB2)_rs1881145, cytotoxic T-lymphocyte-associated antigen 4 (CTLA4)_rs231775, lipoma-preferred partner (LPP)_rs6780858, and human leukocyte antigen (HLA)-J_ rs767861647. The PRS of the best model was positively associated with hyperthyroidism risk by 1.939-fold (1.317–2.854) after adjusting for covariates. PRSs interacted with age, metabolic syndrome, and dietary inflammatory index (DII), while hyperthyroidism risk interacted with energy, calcium, seaweed, milk, and coffee intake ( P < 0.05 ). The PRS impact on hyperthyroidism risk was observed in younger (<55 years) participants and adults without metabolic syndrome. PRSs were positively associated with hyperthyroidism risk in participants with low dietary intakes of energy (OR = 2.74), calcium (OR = 2.84), seaweed (OR = 3.43), milk (OR = 2.91), coffee (OR = 2.44), and DII (OR = 3.45). In conclusion, adults with high PRS involved in inflammation and immunity had a high hyperthyroidism risk exacerbated under low intakes of energy, calcium, seaweed, milk, or coffee. These results can be applied to personalized nutrition in a clinical setting.

Download Full-text

Prediction Models of Early Childhood Caries Based on Machine Learning Algorithms

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18168613 ◽

2021 ◽

Vol 18 (16) ◽

pp. 8613

Author(s):

You-Hyun Park ◽

Sung-Hwa Kim ◽

Yoon-Young Choi

Keyword(s):

Machine Learning ◽

Early Childhood ◽

Logistic Regression ◽

Random Forest ◽

Early Childhood Caries ◽

Prediction Models ◽

Risk Groups ◽

Machine Learning Algorithms ◽

Significant Difference ◽

Childhood Caries

In this study, we developed machine learning-based prediction models for early childhood caries and compared their performances with the traditional regression model. We analyzed the data of 4195 children aged 1–5 years from the Korea National Health and Nutrition Examination Survey data (2007–2018). Moreover, we developed prediction models using the XGBoost (version 1.3.1), random forest, and LightGBM (version 3.1.1) algorithms in addition to logistic regression. Two different methods were applied for variable selection, including a regression-based backward elimination and a random forest-based permutation importance classifier. We compared the area under the receiver operating characteristic (AUROC) values and misclassification rates of the different models and observed that all four prediction models had AUROC values ranging between 0.774 and 0.785. Furthermore, no significant difference was observed between the AUROC values of the four models. Based on the results, we can confirm that both traditional logistic regression and ML-based models can show favorable performance and can be used to predict early childhood caries, identify ECC high-risk groups, and implement active preventive treatments. However, further research is essential to improving the performance of the prediction model using recent methods, such as deep learning.

Download Full-text

Application of Data Mining Technology in Risk Prediction of Metabolic Syndrome in Oil Workers

10.21203/rs.3.rs-31038/v1 ◽

2020 ◽

Author(s):

Jie Wang ◽

Chao Li ◽

Jing Li ◽

Sheng Qin ◽

Chunlei Liu ◽

...

Keyword(s):

Metabolic Syndrome ◽

Random Forest ◽

Risk Prediction ◽

Roc Curve ◽

Prediction Models ◽

Prediction Performance ◽

Random Forest Model ◽

Forest Model ◽

The Metabolic Syndrome ◽

Oil Workers

Abstract Background. The prevalence of metabolic syndrome continues to rise sharply worldwide, seriously threatening people's health.In this paper, three kinds of risk prediction models applicable to the metabolic syndrome of oil workers were established, and the optimal models were found through comparison. The optimal model can be used to identify people at high risk of metabolic syndrome as early as possible, to predict their risk, and to persuade them to change their adverse lifestyle so as to slow down and reduce the incidence of metabolic syndrome.Methods. A total of 1,468 workers from an oil company who participated in occupational health physical examination from April 2017 to October 2018 were included in this study. We established the Logistic regression model, the random forest model and the convolutional neural network model, and compared the prediction performance of the models according to the F1 score, sensitivity, accuracy and other indicators of the three models.Results. The results showed that the accuracy of the three models in the training set was 83.45%, 94.21% and 86.34%, the sensitivity was 78.47%, 94.62% and 81.30%, the F1 score was 0.79, 0.93 and 0.83, and the area under the ROC curve was 0.894, 0.987 and 0.935, respectively. In the test set, the accuracy was 76.72%, 80.66% and 78.69%, the sensitivity was 70.00%, 77.50% and 68.33%, the F1 score was 0.70, 0.76 and 0.71, and the area under the ROC curve was 0.797, 0.861 and 0.855, respectively.Conclusions. The study showed that the prediction performance of random forest model is better than other models, and the model has higher application value, which can better predict the risk of metabolic syndrome in oil workers, and provide corresponding theoretical basis for the health management of oil workers.

Download Full-text

Comparison of Machine Learning With Logistic Regression for Prediction of Chronic Kidney Disease in the Thai Adult Population

Ramathibodi Medical Journal ◽

10.33165/rmj.2021.44.4.250334 ◽

2021 ◽

Vol 44 (4) ◽

pp. 1-12

Author(s):

Ratchainant Thammasudjarit ◽

Punnathorn Ingsathit ◽

Sigit Ari Saputro ◽

Atiporn Ingsathit ◽

Ammarin Thakkinstian

Keyword(s):

Neural Network ◽

Machine Learning ◽

Chronic Kidney Disease ◽

Logistic Regression ◽

Random Forest ◽

Kidney Disease ◽

Decision Tree ◽

Prediction Model ◽

Prediction Models ◽

The Neural Network

Background: Chronic kidney disease (CKD) takes huge amounts of resources for treatments. Early detection of patients by risk prediction model should be useful in identifying risk patients and providing early treatments. Objective: To compare the performance of traditional logistic regression with machine learning (ML) in predicting the risk of CKD in Thai population. Methods: This study used Thai Screening and Early Evaluation of Kidney Disease (SEEK) data. Seventeen features were firstly considered in constructing prediction models using logistic regression and 4 MLs (Random Forest, Naïve Bayes, Decision Tree, and Neural Network). Data were split into train and test data with a ratio of 70:30. Performances of the model were assessed by estimating recall, C statistics, accuracy, F1, and precision. Results: Seven out of 17 features were included in the prediction models. A logistic regression model could well discriminate CKD from non-CKD patients with the C statistics of 0.79 and 0.78 in the train and test data. The Neural Network performed best among ML followed by a Random Forest, Naïve Bayes, and a Decision Tree with the corresponding C statistics of 0.82, 0.80, 0.78, and 0.77 in training data set. Performance of these corresponding models in testing data decreased about 5%, 3%, 1%, and 2% relative to the logistic model by 2%. Conclusions: Risk prediction model of CKD constructed by the logit equation may yield better discrimination and lower tendency to get overfitting relative to ML models including the Neural Network and Random Forest.

Download Full-text

Predictors of remission from body dysmorphic disorder after internet-delivered cognitive behavior therapy: a machine learning approach

10.31234/osf.io/eqcdx ◽

2019 ◽

Author(s):

Oskar Flygare ◽

Jesper Enander ◽

Erik Andersson ◽

Brjánn Ljótsson ◽

Volen Z Ivanov ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Random Forests ◽

Clinical Utility ◽

Body Dysmorphic Disorder ◽

Prediction Models ◽

Behavioral Therapy ◽

Learning Approach ◽

Learning Approaches ◽

Machine Learning Approach

**Background:** Previous attempts to identify predictors of treatment outcomes in body dysmorphic disorder (BDD) have yielded inconsistent findings. One way to increase precision and clinical utility could be to use machine learning methods, which can incorporate multiple non-linear associations in prediction models. **Methods:** This study used a random forests machine learning approach to test if it is possible to reliably predict remission from BDD in a sample of 88 individuals that had received internet-delivered cognitive behavioral therapy for BDD. The random forest models were compared to traditional logistic regression analyses. **Results:** Random forests correctly identified 78% of participants as remitters or non-remitters at post-treatment. The accuracy of prediction was lower in subsequent follow-ups (68%, 66% and 61% correctly classified at 3-, 12- and 24-month follow-ups, respectively). Depressive symptoms, treatment credibility, working alliance, and initial severity of BDD were among the most important predictors at the beginning of treatment. By contrast, the logistic regression models did not identify consistent and strong predictors of remission from BDD. **Conclusions:** The results provide initial support for the clinical utility of machine learning approaches in the prediction of outcomes of patients with BDD. **Trial registration:** ClinicalTrials.gov ID: NCT02010619.

Download Full-text

Development of Prediction Models Using Machine Learning Algorithms for Girls with Suspected Central Precocious Puberty: Retrospective Study (Preprint)

10.2196/preprints.11728 ◽

2018 ◽

Author(s):

Liyan Pan ◽

Guangjian Liu ◽

Xiaojian Mao ◽

Huixian Li ◽

Jiexin Zhang ◽

...

Keyword(s):

Machine Learning ◽

Retrospective Study ◽

Random Forest ◽

Precocious Puberty ◽

Prediction Models ◽

Central Precocious Puberty ◽

Machine Learning Algorithms ◽

Stimulation Test ◽

Gnrh Analogue ◽

Prediction Probability

BACKGROUND Central precocious puberty (CPP) in girls seriously affects their physical and mental development in childhood. The method of diagnosis—gonadotropin-releasing hormone (GnRH)–stimulation test or GnRH analogue (GnRHa)–stimulation test—is expensive and makes patients uncomfortable due to the need for repeated blood sampling. OBJECTIVE We aimed to combine multiple CPP–related features and construct machine learning models to predict response to the GnRHa-stimulation test. METHODS In this retrospective study, we analyzed clinical and laboratory data of 1757 girls who underwent a GnRHa test in order to develop XGBoost and random forest classifiers for prediction of response to the GnRHa test. The local interpretable model-agnostic explanations (LIME) algorithm was used with the black-box classifiers to increase their interpretability. We measured sensitivity, specificity, and area under receiver operating characteristic (AUC) of the models. RESULTS Both the XGBoost and random forest models achieved good performance in distinguishing between positive and negative responses, with the AUC ranging from 0.88 to 0.90, sensitivity ranging from 77.91% to 77.94%, and specificity ranging from 84.32% to 87.66%. Basal serum luteinizing hormone, follicle-stimulating hormone, and insulin-like growth factor-I levels were found to be the three most important factors. In the interpretable models of LIME, the abovementioned variables made high contributions to the prediction probability. CONCLUSIONS The prediction models we developed can help diagnose CPP and may be used as a prescreening tool before the GnRHa-stimulation test.

Download Full-text