Hee-Joon Park

Diagnostic Analysis of Patients with Essential Hypertension Using Association Rule Mining

Objectives The purpose of this study was to analyze the records of patients diagnosed with essential hypertension using association rule mining (ARM). Methods Patients with essential hypertension (ICD code, I10) were extracted from a hospitals data warehouse and a data mart constructed for analysis. Apriori modeling of the ARM method and web node in the Clementine 12.0 program were used to analyze patient data. Results Patients diagnosed with essential hypertension totaled 5,022 and the diagnostic data extracted from those patients numbered 53,994. As a result of the web node, essential hypertension, non-insulin dependent diabetes mellitus (NIDDM), and cerebral infarction were shown to be associated. Based on the results of ARM, NIDDM (support, 35.15%; confidence, 100%) and cerebral infarction (support, 21.21%; confidence, 100%) were determined to be important diseases associated with essential hypertension. Conclusions Essential hypertension was strongly associated with NIDDM and cerebral infarction. This study demonstrated the practicality of ARM in co-morbidity studies using a large clinic database.

Combination of Uric Acid and NT-ProBNP: A More Useful Prognostic Marker for Short-Term Clinical Outcomes in Patients with Acute Heart Failure

Background/Aims In patients with heart failure (HF), N-terminal prohormone brain natriuretic peptide (NT-ProBNP) is a standard prognostic indicator. In addition, uric acid (UA) was recently established as a prognostic marker for poor outcome in chronic HF. The aim of this study was to determine the combined role of UA and NT-ProBNP as prognostic markers for short-term outcomes of acute heart failure (AHF). Methods The levels of UA and NT-ProBNP were determined in 193 patients (age, 69 ± 13 years; 76 males) admitted with AHF. Patients were followed for 3 months and evaluated for cardiovascular events, defined as cardiac death and/or readmission for HF. Results Of the 193 patients, 23 (11.9%) died and 20 (10.4%) were readmitted for HF during the 3-month follow-up period. Based on univariate analysis, possible predictors of short-term cardiovascular events were high levels of UA and NT-ProBNP, low creatinine clearance, no angiotensin converting enzyme inhibitors or angiotensin receptor blockers, and old age. Multivariate Cox hazard analysis showed that UA levels were independently associated with increased incidence of cardiovascular events (hazard ratio, 1.115; 95% confidence interval, 1.006 to 1.235; p = 0.037). Kaplan-Meier survival analysis revealed that patients with UA levels > 8.0 mg/dL and NT-ProBNP levels > 4,210 pg/mL were at highest risk for cardiac events (p = 0.01). Conclusions The combination of UA and NT-ProBNP levels appears to be more useful than either marker alone as an independent predictor for short-term outcomes in patients with AHF.

Fuzzy discretization with spatial distribution of data and Its application to feature selection

In clinical data minig, choosing the optimal subset of features is such important, not only to reduce the computational complexity but also to improve the usefulness of the model constructed from the given data. Moreover the threshold values (i.e., cut-off points) of selected features are used in a clinical decision criteria of experts for differential diagnosis of diseases. In this paper, we propose a fuzzy discretization approach, which is evaluated by measuring the degree of separation of redundant attribute values in overlapping region, based on spatial distribution of data with continuous attributes. The weighted average of the redundant attribute values is then used to determine the threshold value for each feature and rough set theory is utilized to select a subset of relevant features from the overall features. To verify the validity of the proposed method, we compared experimental results, which applied to classification problem using 668 patients with a chief complaint of dyspnea, based on three discretization methods (i.e., equal-width, equal-frequency, and entropy-based) and proposed discretization method. From the experimental results, we confirm that the discretization methods with fuzzy partition give better results in two evaluation measures, average classification accuracy and G-mean, than those with hard partition.

Implementation of Binaural Communication Open Platform for Binaural Hearing Aids Developing

Recently, the performance of binaural hearing aids is rapidly improved with the technology advancement of wireless communication, digital signal processing, and integrated circuit design. However, the previous hearing aids developer platforms can`t be applied to binaural hearing aids developing, because it has no consideration for wireless communication and binaural hearing control. Also, the previous developer platforms are not easy to use for the algorithm development, because programming languages are limited. In this paper, we designed and implemented the open platform board for binaural hearing aids developing. The designed board can be programmed by general programming language and can be used wireless communication module. In order to verify the designed open platform board, we used the volume control algorithm using two open platform board. As a result of experiment, we verified the performance of designed and implemented open platform board that was successfully operated the binaural hearing control and the wireless communication.

A New Method for Non-Invasive Measurement of Skin in the Low Frequency Range

Objectives The purpose of our study was to estimate skin structure and conductivity distribution in a cross section of local tissue using non-invasive measurement of impedance data. The present study was designed to evaluate the efficiency of skin depth information through computer simulations. The multilayer tissue model was composed of epidermis, dermis tissues, and subcutaneous. Methods In this study, electrical characteristics of skin models were used for conductivity of 0.13 S/m, 0.26 S/m, 0.52 S/m, permittivity of 94,000 F/m, and a frequency of 200 Hz. The effect of the new method was assessed by computer simulations using three-electrode methods. A non-invasive electrical impedance method has been developed for analysis using computer simulation and a skin electrical model with low frequency range. Using the three-electrode method differences through the potentials between measurement electrodes and reference electrodes can be easily detected. The Cole electrical impedance model, which is better suited for skin was used in this study. Results In this study, experiments using three-electrode methods were described by computer simulation based on a simple model. This electrical impedance model was fitted and developed in comparison with our model for measurement of skin impedance. Conclusions The proposed electrical model for skin is suitable for use in interpretation of changes in impedance characterization of the skin. Using the computer simulation method, information on skin impedance depth can be more accurately developed and predicted.

Comparison of long-term outcomes following sirolimus-eluting stent vs paclitaxel-eluting stent implantation in patients with long calcified coronary lesions.

Although previously reported studies on coronary calcification mainly focused on its presence or absence in discrete focal target lesions, calcified coronary lesions (CCL) angiographically present as diffuse long lesions in some patients. The aim of our study was to evaluate the long‐term efficacy of sirolimus‐eluting stents (SES) and paclitaxel‐eluting stents (PES) on long CCL.

Implementation of automatic external defibrillator using real time ventricular fibrillation detecting algorithm based on time domain analysis

Abstract The increase in mortality associated with arrhythmia is an inevitable problem of modern society such as westernized eating habits and an increase in stress due to industrialization, and the related social costs are increasing. In this regard, the supply of automatic external defibrillator (AED) used outside hospitals is increasing mainly in public institutions, and AED is a medical practice performed by non-medical personnel. Therefore, studies on arrhythmia detection algorithm to make accurate clinical judgment for proper use are increasing. In this paper, we propose a time domain analysis method to detect arrhythmia in real time and implement AED by porting it to programmable gate array and digital signal processor. The analysis of the phase domain improves the detection rate of R-peak using the differentiated electrocardiogram (ECG) waveform rather than the existing ECG waveform and makes it easy to distinguish the normal ECG from the arrhythmia signal in the phase domain. The proposed algorithm was verified by simulation using Labview and ModelSim, and it was verified that the proposed algorithm works effectively by performing animal experiments using the implemented AED.

Implementation of adjustive latency compensation in a binaural hearing aid to prevent latency due to wireless transmission for using with multi-media devices

Binaural hearing aid has become an important topic in recent research on hearing aids. It employs two hearing aids, one for each ear. However, a short latency between the outputs of the two hearing aids will occur owing to the wireless data transmission between two aids. In this study, an adjustive latency compensation was designed and implemented in a binaural hearing aids to prevent the latency. It includes a static part for the basic transmission time, and the length of an adjustive part can be adjusted depending on the transmission time change caused by a transmission failed. Therefore, a time measurement program with real time clock was designed to measure the time of every data package transmission. As the experimental results show, the proposed compensation is able to ensure synchronisation between the two hearing aids even when a transient failure in the wireless communication between two hearing aids occurred.

Implemented a wireless communication system for VGA capsule endoscope

Recently, several medical devices that use wireless communication are under development. In this paper, the small size frequency shift keying (FSK) transmitter and a monofilar antenna for the capsule endoscope, enabling the medical device to transmit VGA-size images of the intestine. To verify the functionality of the proposed wireless communication system, computer simulations and animal experiments were performed with the implemented capsule endoscope that includes the proposed wireless communication system. Several fundamental experiments are carried out using the implemented transmitter and antenna, and animal in-vivo experiments were performed to verify VGA image transmission.

Decision method for rule-based physical activity status using rough sets

This paper presents an accelerometer based system for physical activity decision that are capable of recognizing three different types of physical activities, i.e., standing, walking and running, using by rough sets. To collect physical acceleration data, we developed the body sensor node which consists of two custom boards for physical activity monitoring applications, a wireless sensor node and an accelerometer sensor module. The physical activity decision is based on the acceleration data collected from body sensor node attached on the user`s chest. We proposed a method to classify physical activities using rough sets which can be generated rules as attributes of the preprocessed data and by constructing a new decision table, rules reduction. Our experimental results have successfully validated that performance of the rule patterns after removing the redundant attribute values are better and exactly same compare with before.