• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• 한국방사선학회논문지
• /
• 제5권1호
• /
• pp.19-25
• /
• 2011

광용적맥파(photoplethysmogram, PPG)는 심장의 수축과 이완으로 변화하는 혈액용적(blood volume)과 혈액내의 헤모글로빈에 흡수되는 빛의 양의 선형적 관계를 이용하여 신호를 획득하는 방법이다. 본 논문에서는 PPG 센서를 이용하여 질환 예측을 할 수 있는 시스템을 제안하였다. 본 시스템은 PPG 센서를 이용하여 심박수의 변이를 살펴볼 수 있는 심박수 변이 분석과 이전 심박수와 이후 심박수를 구분지어 그래프로 표현하는 심박수 분포를 보여준다. 또한 심박수를 스펙트럼 분석하여 자율신경계 균형도, 가속도 맥파로부터 혈관 상태를 분석하여 심혈관 질환을 조기 예측하는 개인용 컴퓨터 기반의 시스템을 설계하고 구현하였다.

• Korean Circulation Journal
• /
• 제53권5호
• /
• pp.331-343
• /
• 2023

Background and Objectives: The prognostic implication of right atrial (RA) and left atrial (LA) size for an immediate success of direct current cardioversion (DCCV) in atrial fibrillation (AF) remains unclear. This study aimed to compare RA and LA size for the prediction of DCCV success. Methods: Between 2012 and 2018, 734 consecutive outpatients were screened for our prospective registry. Each eligible patient received a medical history, blood analysis, and transthoracic echocardiography with a focus on indexed RA (iRA) area and LA volume (iLAV) prior to DCCV with up to three biphasic shocks (200-300-360 J) or additional administration of amiodarone or flecainide to restore sinus rhythm. Results: We enrolled 589 patients, and DCCV was in 89% (n=523) successful. Mean age was 68 ± 10 years, and 40% (n=234) had New York heart association class >II. A prevalence of the male sex (64%, n=376) and of persistent AF (86%, n=505) was observed. Although DCCV success was associated with female sex (odds ratio [OR], 1.88; 95% confidence interval [CI], 1.06-3.65), with absence of coronary heart disease and normal left ventricular function (OR, 2.24; 95% CI, 1.26-4.25), with short AF duration (OR, 1.93; 95% CI, 1.05-4.04) in univariable regression, only iRA area remained a stable and independent predictor of DCCV success (OR, 0.27; 95% CI, 0.12-0.69; area under the curve 0.71), but not iLAV size (OR, 1.16; 95% CI, 1.05-1.56) in multivariable analysis. Conclusions: iRA area is superior to iLAV for the prediction of immediate DCCV success in AF.

• Korean Circulation Journal
• /
• 제48권12호
• /
• pp.1148-1156
• /
• 2018

Background and Objectives: It is controversial that decreased left ventricular function could predict poststroke outcomes. The purpose of this study is to elucidate whether left ventricular ejection fraction (LVEF) can predict cardiovascular events and mortality in acute ischemic stroke (AIS) without atrial fibrillation (AF) and coronary heart disease (CHD). Methods: Transthoracic echocardiography was conducted consecutively in patients with AIS or transient ischemic attack at Soonchunhyang University Hospital between January 2008 and July 2016. The clinical data and echocardiographic LVEF of 1,465 patients were reviewed after excluding AF and CHD. Poststroke disability, major adverse cardiac events (MACE; nonfatal stroke, nonfatal myocardial infarction, and cardiovascular death) and all-cause mortality during 1 year after index stroke were prospectively captured. Cox proportional hazards regressions analysis were applied adjusting traditional risk factors and potential determinants. Results: The mean follow-up time was $259.9{\pm}148.8days$ with a total of 29 non-fatal strokes, 3 myocardial infarctions, 33 cardiovascular deaths, and 53 all-cause mortality. The cumulative incidence of MACE and all-cause mortality were significantly higher in the lowest LVEF (<55) group compared with the others (p=0.022 and 0.009). In prediction models, LVEF (per 10%) had hazards ratios of 0.54 (95% confidence interval [CI], 0.36-0.80, p=0.002) for MACE and 0.61 (95% CI, 0.39-0.97, p=0.037) for all-cause mortality. Conclusions: LVEF could be an independent predictor of cardiovascular events and mortality after AIS in the absence of AF and CHD.

• ETRI Journal
• /
• 제22권2호
• /
• pp.1-10
• /
• 2000

Pattern recognition is one of the most common problems encountered in engineering and scientific disciplines, which involves developing prediction or classification models from historic data or training samples. This paper introduces a new approach, called the Representational Capability (RC) algorithm, to handle pattern recognition problems using radial basis function (RBF) models. The RC algorithm has been developed based on the mathematical properties of the interpolation and design matrices of RBF models. The model development process based on this algorithm not only yields the best model in the sense of balancing its parsimony and generalization ability, but also provides insights into the design process by employing a design parameter (${\delta}$). We discuss the RC algorithm and its use at length via an illustrative example. In addition, RBF classification models are developed for heart disease diagnosis.

• 대한한의진단학회지
• /
• 제15권2호
• /
• pp.175-190
• /
• 2011

Objectives: Even though there has been no consensus on the concept of viscera organ between the oriental and western medicine, we tried to investigate the correlation between clinical biomarkers of five Jang and chronological age and develop the models for predicting five Jang biological ages by statistical analysis. Methods: We obtained data from about 120,000 subjects who visited health promotion centers for health promotion and disease prevention from January 2004 to June 2009. Participants were included if they were over 20 years old, and excluded if reported to have cardiovascular disease or other serious medical illness such as cancer, malignant hypertension, uncontrolled diabetes, cardiopulmonary insufficiency, liver disease, pancreatic disease or renal disease. Among the clinical biomarkers obtained, we selected the biomarkers which were associated with the function of 5 Jang in previous studies, or showed statistically significant correlation with age. Multiple regression models were used for building prediction models of biological age after adjusting for potential confounders for men and women, respectively. Pearson correlation coefficient was calculated to examine the linear relationship between age and various biomarkers, and multiple regression analysis was used for building the prediction models of five Jang biological ages for men and women, respectively. All statistical data analysis was performed by using SPSS Version 12.0 software and statistical significance was obtained if p<0.05. Results: For males, the best models were developed using 12, 2, 8, 3, and 4 biomarkers for predicting biological ages of heart, lung, liver, pancreas, and kidney, respectively (R2 = 0.57, 0.43, 0.11, 0.24, and 0.93, respectively). Similar to males, for the females, 10, 2, 8, 3, and 4 biomarkers were selected as the models respectively (R2 = 0.76, 0.44, 0.14, 0.38, and 0.89, respectively). Conclusions: As we have developed for the first time the models for predicting five Jang biological ages with common clinical biomarkers, it is expected that these models may be used as clinical supplementary tools in the evaluation of aging status and functional decline of five Jang according to age in health promotion centers and private clinics. At the same time, it is considered that the use as objective tools to evaluate aging status and functional decline of each Jang.

• Annals of Clinical Neurophysiology
• /
• 제6권1호
• /
• pp.26-30
• /
• 2004

Background: Electrophysiologic study accurately predicts the degree of degenerated motor axons but cannot give precise information on the type of injury that occurred in Bell's palsy. Because of these limitation for prognostic prediction in Bell's palsy, we evaluated divergence of electrophysiological time course for the purpose of presuming the type of injury in Bell's palsy. Methods: We did bilateral facial nerve conduction studies in 103 Bell's palsy patients, who visited to Han-Gang sacred heart hospital from 1998 to 2001. We compared the CMAP amplitude of disease site with that of normal site and suggested that decremental CMAP amplitude ratio (percentage) as a degree of denervation of affected facial nerve. Then we demonstrated the time course of denervation percentage. After defining normal range of CMAP amplitude difference from normal control group, we also evaluated if distinct time course of early minimal denervation is present. Results: Our results show that time course of the denervation in early stage of Bell's palsy reflect various injury type such as axonotmesis, neurotmesis or other unidentified type. We cannot identify the distinct time course of early minimal denervation. Conclusions: The time course as well as the maximal value of denervation are the best prognostic guidelines in Bell' s palsy. So repeated serial electrophysiologic test are inevitable to assess prognosis. As an another topic, early minimal denervation for prognostic prediction deserve to be evaluated as a future work up for prognostic prediction.

• Clinical and Experimental Pediatrics
• /
• 제52권1호
• /
• pp.129-132
• /
• 2009

저자들은 청색증과 끙끙거림, 심비대로 전원되어 심장 초음파 검사에서 좌심실에 발생한 단독 심실 비치밀화증을 가진 신생아 1예를 경험하였다. 환자에서 측정한 NT pro-BNP는 높았고, 수유 곤란과 빈호흡을 동반한 심부전 증상이 있었다. 심부전증에 대한 치료에도 불구하고 주기적으로 시행한 NT pro-BNP가 더 높아지면서 환자에게서 급성 심정지가 발생하였고, 심폐소생술 이후 NT pro-BNP가 다시 낮아지면서 심부전 등의 증상은 호전을 보였다. 심초음파 검사와 함께 NT pro-BNP를 주기적으로 검사해 보는 것이 병의 경과를 예측하는데 도움이 될 수 있을 것이다.

• Journal of Chest Surgery
• /
• 제17권4호
• /
• pp.644-656
• /
• 1984

In Tetralogy of Fallot, the most common congenital cyanotic heart disease, the mortality is decreasing continuously with adequate type and timing of operation. At S.N.U.H., 195 patients were operated from January 1982 to December 1983 and 176 patients among them were analysed in the view of pre-operative pulmonary arterial condition measured by cardiac cineangiogram. The most common associated anomaly was PFO and ASD and they did not affect the postoperative course and mortality. The overall mortality rate was 8.5% in 1982 and 6.8% in 1983 but under 2 years of age, the mortality rate was relatively high as 25% in 1982 and 16.7% in 1983, and when transannular patch widening of Right Ventricular Outflow Tract was used, the mortality rate was 12.5% in 1982 and 27.3% in 1983. Preoperative angiographic measurements of the pulmonary arterial status for prediction of the ratio between the Left Ventricular and Right Ventricular peak systolic pressure were calculated retrospectively according to the Blackstones formula, and the predicted value of PRV/LV greater than 0.6 carried apparently high complication and mortality rate as 16.6% M.R. in 1982 and 11.1 % in 1983. Among postoperative complications, c-RBBB occurred most frequently about 50% but did not influenced to mortality, Low Cardiac Output Syndrome was developed in about 40%. If we select the patient who should have the staged operation including shunt operation and choose the type of RVOT relief, we expect the improvement of postoperative clinical results.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제45권3호
• /
• pp.152-157
• /
• 2019

Objectives: The number of elderly patients with systemic basal disease requiring invasive dental treatment has increased. Appropriate prediction of surgical invasiveness and combined use of psychosedation are thought to contribute to safe whole-body management. Dexmedetomidine (DEX) exhibits analgesic and anti-anxiolytic properties and causes mild respiratory depression. Studies regarding DEX use in elderly non-intubated patients are scarce. We aimed to use retrospective data to determine an effective dose of DEX to induce adequate sedation in elderly patients undergoing invasive dental surgery under local anesthesia. Materials and Methods: One hundred two patients aged 70 to 96 years were presumably appropriately controlled with sedation. DEX was administered at an initial loading dose of 2.0 to $3.1{\mu}g/kg/hr$ for 10 minutes. We divided the patients into five groups by age and compared their blood pressures and heart rates. Results: In all five groups, blood pressure decreased suddenly at approximately 15 and 20 minutes after DEX administration. A marked decrease in blood pressure was noted in patients aged 75 to 79 years. Conclusion: For elderly patients aged 75 years and above, the initial loading dose of DEX needs to be reduced to lower than half that required for young and middle-age adults.