• Genomics & Informatics
• /
• v.14 no.4
• /
• pp.149-159
• /
• 2016

With the success of the genome-wide association studies (GWASs), many candidate loci for complex human diseases have been reported in the GWAS catalog. Recently, many disease prediction models based on penalized regression or statistical learning methods were proposed using candidate causal variants from significant single-nucleotide polymorphisms of GWASs. However, there have been only a few systematic studies comparing existing methods. In this study, we first constructed risk prediction models, such as stepwise linear regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN), using a GWAS chip and GWAS catalog. We then compared the prediction accuracy by calculating the mean square error (MSE) value on data from the Korea Association Resource (KARE) with body mass index. Our results show that SLR provides a smaller MSE value than the other methods, while the numbers of selected variables in each model were similar.

• Clinical and Experimental Pediatrics
• /
• v.58 no.7
• /
• pp.251-255
• /
• 2015

Purpose: The widespread introduction of bacterial conjugate vaccines has decreased the risk of cerebrospinal fluid (CSF) pleocytosis due to bacterial meningitis (BM) in children. However, most patients with CSF pleocytosis are hospitalized and treated with parenteral antibiotics for several days. The bacterial meningitis score (BMS) is a validated multivariate model derived from a pediatric population in the postconjugate vaccine era and has been evaluated in several studies. In the present study, we examined the usefulness of BMS in South Korean patients. Methods: This study included 1,063 patients with CSF pleocytosis aged between 2 months and 18 years. The BMS was calculated for all patients, and the sensitivity and negative predictive value (NPV) of the test were evaluated. Results: Of 1,063 patients, 1,059 (99.6%) had aseptic meningitis (AM). Only four patients (0.4%) had BM. The majority of patients (98%) had a BMS of ${\leq}1$, indicating a diagnosis of AM. The BMS was 0 in 635 patients (60%) and 1 in 405 patients (38%). All four BM patients had a BMS of ${\geq}4$. Conclusion: To our knowledge, this is the first study to investigate the diagnostic strength of the BMS in South Korea. In our study, the BMS showed 100% sensitivity and 100% NPV. Therefore, we believe that the BMS is a good clinical prediction rule to identify children with CSF pleocytosis who are at a risk of BM.

• Genomics & Informatics
• /
• v.14 no.4
• /
• pp.138-148
• /
• 2016

The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which has been a big hurdle in building risk prediction models. Recently, many statistical approaches based on penalized regression have been developed to solve the "large p and small n" problem. In this report, we evaluated the performance of several statistical methods for predicting a binary trait: stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN). We first built a prediction model by combining variable selection and prediction methods for type 2 diabetes using Affymetrix Genome-Wide Human SNP Array 5.0 from the Korean Association Resource project. We assessed the risk prediction performance using area under the receiver operating characteristic curve (AUC) for the internal and external validation datasets. In the internal validation, SLR-LASSO and SLR-EN tended to yield more accurate predictions than other combinations. During the external validation, the SLR-SLR and SLR-EN combinations achieved the highest AUC of 0.726. We propose these combinations as a potentially powerful risk prediction model for type 2 diabetes.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.222-232
• /
• 2015

In this paper, we propose a dual-phase approach to improve the process of heart disease prediction in a mobile environment. Firstly, only the confident frequent rules are extracted from a patient's clinical information. These are then used to foretell the possibility of the presence of heart disease. However, in some cases, subjects cannot describe exactly what has happened to them or they may have a silent disease - in which case it won't be possible to detect any symptoms at this stage. To address these problems, data records collected over a long period of time of a patient's heart rate variability (HRV) are used to predict whether the patient is suffering from heart disease. By analyzing HRV patterns, doctors can determine whether a patient is suffering from heart disease. The task of collecting HRV patterns is done by an online artificial neural network, which as well as learning knew knowledge, is able to store and preserve all previously learned knowledge. An experiment is conducted to evaluate the performance of the proposed heart disease prediction process under different settings. The results show that the process's performance outperforms existing techniques such as that of the self-organizing map and gas neural growing in terms of classification and diagnostic accuracy, and network structure.

• Science of Emotion and Sensibility
• /
• v.10 no.2
• /
• pp.147-154
• /
• 2007

Electrocardiogram(ECG) being the recording of the heart's electrical activity provides valuable clinical information about heart's status. Many researches have been pursued for heart disease diagnosis using ECG so far. However, electrocardio-graph uses foreign diagnosis algorithm in the con due to inaccuracy of domestic diagnosis results for a heart disease. This paper proposes ST-segment extraction technique diagnosing heart disease parameter from raw ECG data. As the ST-segment is used for prediction of Coronary Artery Disease, we can predict heart disease using classification approach in data mining technique. We can also predict patient's clinical characterization from patient clinical data.

• Journal of the Korean Institute of Gas
• /
• v.13 no.5
• /
• pp.20-25
• /
• 2009

Low explosion limits of flammable liquid mixtures can be calculated with the appropriate use of the fundamental laws of Raoult, Dalton, Le Chatelier and activity coefficient models. In this paper, Raoult's law, van Laar equation and Wilson equation are shown to be applicable for the prediction of the lower explosion limits for ethylacetate+ethanol and ethanol+toluene systems. The calculated values based on Raoult's law were found to be better than those based on van Laar and Wilson equations.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.717-722
• /
• 2004

This paper presents fuzzy rules to predict diagnosis of Wisconsin breast cancer using neural network with weighted fuzzy membership functions (NNWFM). NNWFM is capable of self-adapting weighted membership functions to enhance accuracy in prediction from the given clinical training data. n set of small, medium, and large weighted triangular membership functions in a hyperbox are used for representing n set of featured input. The membership functions are randomly distributed and weighted initially, and then their positions and weights are adjusted during learning. After learning, prediction rules are extracted directly from the enhanced bounded sums of n set of weighted fuzzy membership functions. Two number of prediction rules extracted from NNWFM outperforms to the current published results in number of rules and accuracy with 99.41%.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.25 no.1
• /
• pp.138-143
• /
• 2011

In spite of abundant clinical resources of stroke patients, the objective and logical data analyses or diagnostic systems were not established in oriental medicine. As a part of researches for standardization and objectification of differentiation of syndromes for stroke, in this present study, we tried to develop the statistical diagnostic tool discriminating the 4 subtypes of syndrome differentiation using the essential indices considering the sex. Discriminant analysis was carried out using clinical data collected from 1,448 stroke patients who was identically diagnosed for the syndrome differentiation subtypes diagnosed by two clinical experts with more than 3 year experiences. Empirical discriminant model(V) for different sex was constructed using 61 significant symptoms and sign indices selected by stepwise selection. We comparison. We make comparison a between discriminant model(V) and discriminant model(IV) using 33 significant symptoms and sign indices selected by stepwise selection. Development of statistical diagnostic tool discriminating 4 subtypes by sex : The discriminant model with the 24 significant indices in women and the 19 significant indices in men was developed for discriminating the 4 subtypes of syndrome differentiation including phlegm-dampness, qi-deficiency, yin-deficiency and fire-heat. Diagnostic accuracy and prediction rate of syndrome differentiation by sex : The overall diagnostic accuracy and prediction rate of 4 syndrome differentiation subtypes using 24 symptom and sign indices was 74.63%(403/540) and 68.46%(89/130) in women, 19 symptom and sign indices was 72.05%(446/619) and 70.44%(112/159) in men. These results are almost same as those of that the overall diagnostic accuracy(73.68%) and prediction rate(70.59%) are analyzed by the discriminant model(IV) using 33 symptom and sign indices selected by stepwise selection. Considering sex, the statistical discriminant model(V) with significant 24 symptom and sign indices in women and 19 symptom and sign indices in men, instead of 33 indices would be used in the field of oriental medicine contributing to the objectification of syndrome differentiation with parsimony rule.

• The KIPS Transactions:PartD
• /
• v.15D no.6
• /
• pp.767-776
• /
• 2008

Microarray technology is extensively being used in experimental molecular biology field. Microarray experiments generate quantitative expression measurements for thousands of genes simultaneously, which is useful for the phenotype classification of many diseases. One of the two major problems in microarray data classification is that the number of genes exceeds the number of tissue samples. The other problem is that current methods generate classifiers that are accurate but difficult to interpret. Our paper addresses these two problems. We performed a direct integration of individual microarrays with same biological objectives by transforming an expression value into a rank value within a sample and generated rank-comparison decision rules with variable number of genes for cancer classification. Our classifier is an ensemble method which has k top scoring decision rules. Each rule contains a number of genes, a relationship among involved genes, and a class label. Current classifiers which are also ensemble methods consist of k top scoring decision rules. However these classifiers fix the number of genes in each rule as a pair or a triple. In this paper we generalized the number of genes involved in each rule. The number of genes in each rule is in the range of 2 to N respectively. Generalizing the number of genes increases the robustness and the reliability of the classifier for the class prediction of an independent sample. Also our classifier is readily interpretable, accurate with small number of genes, and shed a possibility of the use in a clinical setting.

• Journal of Veterinary Clinics
• /
• v.19 no.3
• /
• pp.312-315
• /
• 2002

Diagnostic tests often require the determination of cut-off values that discriminate uninfected from infected individuals. The receiver operating characteristic (ROC) curve has been frequently used to attain this purpose and gives a representation of diagnostic accuracy (sensitivity and specificity) of a prediction model when varying the cut-point of a decision rule on a whole spectrum. We have written and tested a visual basic application program in EXCEL for maximum likelihood estimation of a binormal ROC curve, which also computes univariate statistics of a diagnostic test employed. Examples applying for computed tomographic images in radiology and methicillin-resistant Staphylococcus aureus research are given to illustrate this approach. This stand-alone module is available from the first author on request.