• International Journal of Computer Science & Network Security
• /
• v.24 no.3
• /
• pp.43-52
• /
• 2024

Health Monitoring System is a sophisticating technology and another way to the normal/regular management of the health of the patient. This Health Monitoring Mobile Application is a contribution from our side to the public and to the overall health industry in Pakistan. With the help of Health mobile application, the users will be able to store their medical records, prescriptions and retrieve them later. The users can store and keep track of their vital readings (heart rate, blood pressure, fasting glucose, random glucose). The mobile application also shows hospitals that are nearby in case the user wants to avail of any medical help. An important feature of the application is the symptoms-based disease prediction, the user selects the symptoms which he has and then the application will name certain diseases that match those symptoms based on relevant algorithms. The major advances and issues have been discussed, and as well as potential tasks to health monitoring will be identified and evaluated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• 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.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.50 no.4
• /
• pp.216-221
• /
• 2024

Objectives: This study aimed to develop and validate a model to predict the need for intensive care unit (ICU) admission in patients with dental infections using an automated machine learning (ML) program called H2O-AutoML. Materials and Methods: Two models were created using only the information available at the initial examination. Model 1 was parameterized with only clinical symptoms and blood tests, excluding contrast-enhanced multi-detector computed tomography (MDCT) images available at the initial visit, whereas model 2 was created with the addition of the MDCT information to the model 1 parameters. Although model 2 was expected to be superior to model 1, we wanted to independently determine this conclusion. A total of 210 patients who visited the Department of Oral and Maxillofacial Surgery at the Dankook University Dental Hospital from March 2013 to August 2023 was included in this study. The patients' demographic characteristics (sex, age, and place of residence), systemic factors (hypertension, diabetes mellitus [DM], kidney disease, liver disease, heart disease, anticoagulation therapy, and osteoporosis), local factors (smoking status, site of infection, postoperative wound infection, dysphagia, odynophagia, and trismus), and factors known from initial blood tests were obtained from their medical charts and retrospectively reviewed. Results: The generalized linear model algorithm provided the best diagnostic accuracy, with an area under the receiver operating characteristic values of 0.8289 in model 1 and 0.8415 in model 2. In both models, the C-reactive protein level was the most important variable, followed by DM. Conclusion: This study provides unprecedented data on the use of ML for successful prediction of ICU admission based on initial examination results. These findings will considerably contribute to the development of the field of dentistry, especially oral and maxillofacial surgery.

• Journal of the Korean Society of Radiology
• /
• v.5 no.1
• /
• pp.19-25
• /
• 2011

Photoplethysmogram(PPG) is the method to obtain the biomedical signal using the linear relationships between the blood volume for changing the cardiac contraction and relaxation and the amount of light for absorbing the hemoglobin in the blood. In this paper, we proposed the analyzed results which show the heart rate variability and the distribution of heart rate for before and after using PPG. Moreover, this paper designed and implemented the system based on personal computer to predict cardiovascular disease in advance using the analyzed results for the autonomic balance from taking the spectral analysis of heart rate and the state of the blood vessel for analyzing APG(acceleration plethysmogram).

• Korean Circulation Journal
• /
• v.53 no.5
• /
• 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
• /
• v.48 no.12
• /
• 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
• /
• v.22 no.2
• /
• 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.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.15 no.2
• /
• 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
• /
• v.6 no.1
• /
• 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
• /
• v.52 no.1
• /
• pp.129-132
• /
• 2009

We describe here our experience with a neonate presenting with cyanosis, grunting, and cardiomegaly, who was diagnosed with isolated left ventricular noncompaction (IVNC) by echocardiography. The patient had high levels of N-terminal pro-B-type natriuretic peptide (NT pro-BNP) and symptoms of heart failure including poor feeding and tachypnea. During the period in which NT pro-BNP levels steadily increased, the patient suffered sudden cardiac arrest despite heart failure management. Following cardiopulmonary resuscitation, cardiac arrest was resolved, NT pro-BNP levels decreased, and all symptoms showed improvement. We consider that assessment of NT pro-BNP with cardiac functional analysis using echocardiography could help in the prediction of disease progress in IVNC.