Tae Keun Yoo

Screening for Prediabetes Using Machine Learning Models

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.

A new severity predicting index for hemorrhagic shock using lactate concentration and peripheral perfusion in a rat model.

ABSTRACT Forty percent of trauma deaths are due to hemorrhage, with 33% to 56% occurring in the prehospital environment. This study proposes a new index (NI) based on the ratio of serum lactate concentration (LC) to peripheral perfusion (PP) as an indicator of hemorrhage-induced mortality during the prehospital stage. Thirty-six anesthetized rats were randomized into three groups according to volume of controlled blood loss. We measured heart rate (HR), systolic and diastolic blood pressures (SBP and DBP), mean arterial pressure (MAP), pulse pressure (PPR), respiration rate (RR), temperature (TEMP), LC, PP, shock index (SI = HR/SBP), and proposed the new hemorrhage-induced mortality index (NI = LC/PP). Peripheral perfusion, defined as peripheral tissue perfusion and skin microcirculation, was continuously monitored by laser Doppler flowmetry. All parameters were analyzed for changes between prehemorrhage and posthemorrhage to investigate the effects of hemorrhage on mortality. Areas under a receiver operating characteristic curve (AUCs) in descending order for NI, SI, PP, SBP, MAP, PPR, DBP, TEMP, LC, RR, and HR were 0.975, 0.941, 0.922, 0.919, 0.903, 0.884, 0.847, 0.816, 0.783, 0.744, and 0.672, respectively. The correlation coefficients with mortality for NI, SI, PP, SBP, MAP, PPR, DBP, TEMP, LC, RR, and HR were -0.818, -0.759, 0.726, 0.721, 0.694, 0.662, 0.597, 0.544, -0.487, 0.420, and -0.296, respectively, with the same order as the AUC. NI was shown to be an optimal independent mortality predictor on multivariable logistic regression analysis. In conclusion, the newly proposed hemorrhage-induced mortality index, based on blood lactate/PP ratio, was a better marker for predicting mortality in rats undergoing acute hemorrhage in comparison to the other parameters evaluated in this study.

Osteoporosis Risk Prediction for Bone Mineral Density Assessment of Postmenopausal Women Using Machine Learning

Purpose A number of clinical decision tools for osteoporosis risk assessment have been developed to select postmenopausal women for the measurement of bone mineral density. We developed and validated machine learning models with the aim of more accurately identifying the risk of osteoporosis in postmenopausal women compared to the ability of conventional clinical decision tools. Materials and Methods We collected medical records from Korean postmenopausal women based on the Korea National Health and Nutrition Examination Surveys. The training data set was used to construct models based on popular machine learning algorithms such as support vector machines (SVM), random forests, artificial neural networks (ANN), and logistic regression (LR) based on simple surveys. The machine learning models were compared to four conventional clinical decision tools: osteoporosis self-assessment tool (OST), osteoporosis risk assessment instrument (ORAI), simple calculated osteoporosis risk estimation (SCORE), and osteoporosis index of risk (OSIRIS). Results SVM had significantly better area under the curve (AUC) of the receiver operating characteristic than ANN, LR, OST, ORAI, SCORE, and OSIRIS for the training set. SVM predicted osteoporosis risk with an AUC of 0.827, accuracy of 76.7%, sensitivity of 77.8%, and specificity of 76.0% at total hip, femoral neck, or lumbar spine for the testing set. The significant factors selected by SVM were age, height, weight, body mass index, duration of menopause, duration of breast feeding, estrogen therapy, hyperlipidemia, hypertension, osteoarthritis, and diabetes mellitus. Conclusion Considering various predictors associated with low bone density, the machine learning methods may be effective tools for identifying postmenopausal women at high risk for osteoporosis.

Diabetic retinopathy risk prediction for fundus examination using sparse learning: a cross-sectional study

BackgroundBlindness due to diabetic retinopathy (DR) is the major disability in diabetic patients. Although early management has shown to prevent vision loss, diabetic patients have a low rate of routine ophthalmologic examination. Hence, we developed and validated sparse learning models with the aim of identifying the risk of DR in diabetic patients.MethodsHealth records from the Korea National Health and Nutrition Examination Surveys (KNHANES) V-1 were used. The prediction models for DR were constructed using data from 327 diabetic patients, and were validated internally on 163 patients in the KNHANES V-1. External validation was performed using 562 diabetic patients in the KNHANES V-2. The learning models, including ridge, elastic net, and LASSO, were compared to the traditional indicators of DR.ResultsConsidering the Bayesian information criterion, LASSO predicted DR most efficiently. In the internal and external validation, LASSO was significantly superior to the traditional indicators by calculating the area under the curve (AUC) of the receiver operating characteristic. LASSO showed an AUC of 0.81 and an accuracy of 73.6% in the internal validation, and an AUC of 0.82 and an accuracy of 75.2% in the external validation.ConclusionThe sparse learning model using LASSO was effective in analyzing the epidemiological underlying patterns of DR. This is the first study to develop a machine learning model to predict DR risk using health records. LASSO can be an excellent choice when both discriminative power and variable selection are important in the analysis of high-dimensional electronic health records.

Effects of radiation emitted by WCDMA mobile phones on electromagnetic hypersensitive subjects

BackgroundWith the use of the third generation (3 G) mobile phones on the rise, social concerns have arisen concerning the possible health effects of radio frequency-electromagnetic fields (RF-EMFs) emitted by wideband code division multiple access (WCDMA) mobile phones in humans. The number of people with self-reported electromagnetic hypersensitivity (EHS), who complain of various subjective symptoms such as headache, dizziness and fatigue, has also increased. However, the origins of EHS remain unclear.MethodsIn this double-blind study, two volunteer groups of 17 EHS and 20 non-EHS subjects were simultaneously investigated for physiological changes (heart rate, heart rate variability, and respiration rate), eight subjective symptoms, and perception of RF-EMFs during real and sham exposure sessions. Experiments were conducted using a dummy phone containing a WCDMA module (average power, 24 dBm at 1950 MHz; specific absorption rate, 1.57 W/kg) within a headset placed on the head for 32 min.ResultsWCDMA RF-EMFs generated no physiological changes or subjective symptoms in either group. There was no evidence that EHS subjects perceived RF-EMFs better than non-EHS subjects.ConclusionsConsidering the analyzed physiological data, the subjective symptoms surveyed, and the percentages of those who believed they were being exposed, 32 min of RF radiation emitted by WCDMA mobile phones demonstrated no effects in either EHS or non-EHS subjects.

Simple Scoring System and Artificial Neural Network for Knee Osteoarthritis Risk Prediction: A Cross-Sectional Study

Background Knee osteoarthritis (OA) is the most common joint disease of adults worldwide. Since the treatments for advanced radiographic knee OA are limited, clinicians face a significant challenge of identifying patients who are at high risk of OA in a timely and appropriate way. Therefore, we developed a simple self-assessment scoring system and an improved artificial neural network (ANN) model for knee OA. Methods The Fifth Korea National Health and Nutrition Examination Surveys (KNHANES V-1) data were used to develop a scoring system and ANN for radiographic knee OA. A logistic regression analysis was used to determine the predictors of the scoring system. The ANN was constructed using 1777 participants and validated internally on 888 participants in the KNHANES V-1. The predictors of the scoring system were selected as the inputs of the ANN. External validation was performed using 4731 participants in the Osteoarthritis Initiative (OAI). Area under the curve (AUC) of the receiver operating characteristic was calculated to compare the prediction models. Results The scoring system and ANN were built using the independent predictors including sex, age, body mass index, educational status, hypertension, moderate physical activity, and knee pain. In the internal validation, both scoring system and ANN predicted radiographic knee OA (AUC 0.73 versus 0.81, p<0.001) and symptomatic knee OA (AUC 0.88 versus 0.94, p<0.001) with good discriminative ability. In the external validation, both scoring system and ANN showed lower discriminative ability in predicting radiographic knee OA (AUC 0.62 versus 0.67, p<0.001) and symptomatic knee OA (AUC 0.70 versus 0.76, p<0.001). Conclusions The self-assessment scoring system may be useful for identifying the adults at high risk for knee OA. The performance of the scoring system is improved significantly by the ANN. We provided an ANN calculator to simply predict the knee OA risk.

Osteoporosis risk prediction using machine learning and conventional methods

A number of clinical decision tools for osteoporosis risk assessment have been developed to select postmenopausal women for the measurement of bone mineral density. We developed and validated machine learning models with the aim of more accurately identifying the risk of osteoporosis in postmenopausal women, and compared with the ability of a conventional clinical decision tool, osteoporosis self-assessment tool (OST). We collected medical records from Korean postmenopausal women based on the Korea National Health and Nutrition Surveys (KNHANES V-1). The training data set was used to construct models based on popular machine learning algorithms such as support vector machines (SVM), random forests (RF), artificial neural networks (ANN), and logistic regression (LR) based on various predictors associated with low bone density. The learning models were compared with OST. SVM had significantly better area under the curve (AUC) of the receiver operating characteristic (ROC) than ANN, LR, and OST. Validation on the test set showed that SVM predicted osteoporosis risk with an AUC of 0.827, accuracy of 76.7%, sensitivity of 77.8%, and specificity of 76.0%. We were the first to perform comparisons of the performance of osteoporosis prediction between the machine learning and conventional methods using population-based epidemiological data. The machine learning methods may be effective tools for identifying postmenopausal women at high risk for osteoporosis.

Comparison of survival predictions for rats with hemorrhagic shocks using an artificial neural network and support vector machine

Hemorrhagic shock is the cause of one third of deaths resulting from injury in the world. Early diagnosis of hemorrhagic shock makes it possible for physicians to treat patients successfully. The objective of this study was to select an optimal survival prediction model using physiological parameters from rats during our hemorrhagic experiment. These physiological parameters were used for the training and testing of survival prediction models using an artificial neural network (ANN) and support vector machine (SVM). To avoid over-fitting, we chose the optimal survival prediction model according to performance measured by a 5-fold cross validation method. We selected an ANN with three hidden neurons and one hidden layer and an SVM with Gaussian kernel function as a trained survival prediction model. For the ANN model, the sensitivity, specificity, and accuracy of survival prediction were 97.8 ± 3.3 %, 96.3 ± 2.7 %, and 96.8 ± 1.7 %, respectively. For the SVM model, the sensitivity, specificity, and accuracy were 97.5 ± 2.9 %, 99.3 ± 1.1 %, and 98.5 ± 1.2 %, respectively. SVM was preferable to ANN for the survival prediction.

Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database

Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen’s kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals.

Multicategory classification of 11 neuromuscular diseases based on microarray data using support vector machine

We applied multicategory machine learning methods to classify 11 neuromuscular disease groups and one control group based on microarray data. To develop multicategory classification models with optimal parameters and features, we performed a systematic evaluation of three machine learning algorithms and four feature selection methods using three-fold cross validation and a grid search. This study included 114 subjects of 11 neuromuscular diseases and 31 subjects of a control group using microarray data with 22,283 probe sets from the National Center for Biotechnology Information (NCBI). We obtained an accuracy of 100%, relative classifier information (RCI) of 1.0, and a kappa index of 1.0 by applying the models of support vector machines one-versus-one (SVM-OVO), SVM one-versus-rest (OVR), and directed acyclic graph SVM (DAGSVM), using the ratio of genes between categories to within-category sums of squares (BW) feature selection method. Each of these three models selected only four features to categorize the 12 groups, resulting in a time-saving and cost-effective strategy for diagnosing neuromuscular diseases. In addition, a gene symbol, SPP1 was selected as the top-ranked gene by the BW method. We confirmed relationships between the gene (SPP1) and Duchenne muscular dystrophy (DMD) from a previous study. With our models as clinically helpful tools, neuromuscular diseases could be classified quickly using a computer, thereby giving a time-saving, cost-effective, and accurate diagnosis.