• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.6
• /
• pp.402-409
• /
• 2019

Patients with dementia or elderly patients who can not move at all by themselves are at a high risk of falls and bedsore due to lack of caregivers. In this paper, to solve this problem, we propose an algorithm to determine the patient's lying postures by discriminating the main body parts such as head, shoulders, and hips based on the pressure intensity sensed at regular intervals. A smart mat with a lattice structure in which a pressure sensor is arranged so that the body part can be discriminated irrespective of the physical characteristics has been implemented. It consists of two modules of $7{\times}7$ array size. Each module consists of 49 FSR-406 sensors and independently senses pressure. For each module, the body part corresponding to the upper body or the lower body is sequentially discriminated by using a pressure distribution such as a cumulative pressure sum using a filter. The proposed algorithm can identify five lying positions by examining the inclusion relationship between body parts belonging to layer-1 such as head, shoulder, and hip area.

• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.24-34
• /
• 2019

In this research, a practical deep learning framework to differentiate the lesions and nodules in breast acquired with ultrasound imaging has been proposed. 7408 ultrasound breast images of 5151 patient cases were collected. All cases were biopsy proven and lesions were semi-automatically segmented. To compensate for the shift caused in the segmentation, the boundaries of each lesion were drawn using Fully Convolutional Networks(FCN) segmentation method based on the radiologist's specified point. The data set consists of 4254 benign and 3154 malignant lesions. In 7408 ultrasound breast images, the number of training images is 6579, and the number of test images is 829. The margin between the boundary of each lesion and the boundary of the image itself varied for training image augmentation. The training images were augmented by varying the margin between the boundary of each lesion and the boundary of the image itself. The images were processed through histogram equalization, image cropping, and margin augmentation. The networks trained on the data with augmentation and the data without augmentation all had AUC over 0.95. The network exhibited about 90% accuracy, 0.86 sensitivity and 0.95 specificity. Although the proposed framework still requires to point to the location of the target ROI with the help of radiologists, the result of the suggested framework showed promising results. It supports human radiologist to give successful performance and helps to create a fluent diagnostic workflow that meets the fundamental purpose of CADx.

• Journal of Society of Preventive Korean Medicine
• /
• v.23 no.2
• /
• pp.1-10
• /
• 2019

Backgrounds : In 2017, National Health Insurance implemented the pilot coverage program for Chuna manual therapy(CMT). 65 Korean Medicine(KM) hospitals and clinics were selected in the program to monitor the effectiveness and patients' satisfaction of insured CMT. Objectives : This study aimed to evaluate patients' satisfaction of CMT in the pilot coverage program of National Health Insurance. Methods : Survey participants were recruited among the patients who used CMT at the designated organizations. On-line questionnaire link was sent to the smart phones of patients who agreed to participate in the survey and provide personal contact information. The questionnaire consisted of the basic charactersitics of respondents, imformation on using CMT satisfaction with CMT and willingness to recommend CMT to others. The answers that were automatically coded and saved were statistically analyzed. Results : Of 386 participants who completed the questionnaire, 92.8% satisfied or strongly satisfied with the CMT. Most frequent reason of satisfaction was 'Good effectiveness', and there was no difference in satisfaction between patients of hospital and those of clinics. Patients with the highest and the lowest level of pain satisfied more than those with other pain levels(p=0.003), but the level of copayment and reasons of CMT use did not affect the satisfaction results(p=0.405). The proportions of respondents who had willingness to recommend CMT to others and to revisit for CMT use were 97.8% and 98.8%, respectively. Conclusions : Most patients were satisfied with CMT in the pilot coverage program, and it can provide the rationale for expanding the insurance coverage of CMT to all KM hospitals and clinics.

• Journal of the Korea Convergence Society
• /
• v.12 no.4
• /
• pp.125-133
• /
• 2021

With the advent of experience era, the user experience has attracted much attention in all walks of life. And the importance of user experience emphasize began to be emphasized. It analyzed the interfering factors of user experience of smart phone medical APP, and evaluated their relative importance. Then it made suggestions on the priority of medical APP development and provided reference for medical APP design optimization and service quality improvement. First of all, based on the related research about user experience theory, smartphone APP user experience and mobile medical APP, it summarized the user experience elements of smartphone medical APP. Secondly, 200 subjects in the 20-40 age group who chose smartphone download experience and used medical APP were surveyed to rate the effect of 18 factors. The results show that the factors such as product resources, medical advertising recommendations, doctor-patient interaction, emotional pleasure, easy to learn, and other factors have a significant impact on users' good experience when using app.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.36 no.4
• /
• pp.203-210
• /
• 2020

By facing the era of the 4th industrial revolution, personalized medical services for patients are expanding with the development of information and communications technology. With these changes, digital medical devices have begun to be used to support diagnosis, patient monitoring, and decision-making of diseases, and recently software medical devices for the purpose of preventing, managing, or treating disorders or diseases have become popular. The aim of this article is to understand the current concept and status of Software as a Medical Device (SaMD), which are actively being carried out in the United States, and to find out what fields can be applied in the future. In addition, it intends to find out the Korean domestic policy trends related to smart healthcare and find out the application of digital software as a medical devices that can be used in dental clinic to keep pace with the upcoming changes in the medical field.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.7
• /
• pp.3235-3242
• /
• 2016

Background: Complementary alternative medicine (CAM) use in children with cancer is widespread. Health-care providers (HCP) need to acknowledge and address this need. This study explored and compared perspectives on CAM of HCP and parents of young patients with cancer in Indonesia. Materials and Methods: We conducted a cross-sectional study using semi-structured questionnaires in HCP and parents of childhood cancer patients at an Indonesian academic hospital. Results: A total of 351 respondents participated: 175 HCP (response rate 80%) and 176 parents (response rate 80%). Parents were more likely than HCP to think that chemotherapy can cure cancer (80% compared to 69%, P=0.013). Nearly half of all parents (46%) and HCP (45%) doubted whether CAM can cure cancer. Parents were more likely than HCP to think that CAM can be helpful in childhood cancer treatment (54% compared to 35%, P=0.003). The most recommended CAM by HCP was self-prayer (93%). Reasons for recommending CAM were: hope for improvement of the child's condition (48%), patient wants to stop treatment (42%). Most discouraged CAM by HCP was by old-smart people (70%), the reasons being: lack of evidence for usefulness (77%), lack of CAM knowledge (75%). The proportion thinking that patients were unlikely to raise the CAM topic if they perceived that doctors were skeptical was higher in parents than in HCP (52% versus 1%) (P<0.001). Most HCP (71%) and parents (77%) acknowledged that their knowledge about safety and efficacy of CAM was inadequate (P=ns). The proportion that wanted to learn or read more about CAM was higher among parents than HCP (48% compared to 31%, P=0.002). Conclusions: HCP and parents have different perspectives on CAM use in children with cancer. HCP should enhance their CAM knowledge and encourage open communication about CAM with parents. If doctors' skepticism is perceived, parents are unlikely to raise CAM as a topic.

• Journal of Internet Computing and Services
• /
• v.17 no.2
• /
• pp.59-65
• /
• 2016

The result of analyzing the cognitive reaction due to the color environment has been applied to various filed especially in medical field. Moreover, the study about the identification of patient's condition and examination the brain activity by collecting the bio-signal based on the color environment is being actively conducted. Even though, there were a variety of experiments by convention the color environment using a light or LED color, it still has a problem that affects the psychological information. Therefore, our proposed system using a HMD (Head Mounting display) to provide a completed color environment condition. This system uses the BMS(Biomedical System) to collect the biometric information which responds to the specific color condition and the human body response information can be measured by the development the Memory and Attention test on Mobile phone. The collection of Biometric information includes electro cardiogram(ECG), respiration, oxygen saturation (Sp02), Bio-impedance, blood pressure will store in the database. In addition, we can verify the result of the human body reaction in the color environment by Memory and Attention application. By utilizing the reaction of the human body information that is collected thought the proposed system, we can analyze the correlation between the physiological information and the color environment. And we also expect that this system can apply to the medical diagnosis and treatment. For future work, we will expand the system for prediction and treatment of Alzheimer disease by analyzing the visualization data through the proposed system. We will also do evaluation on the effectiveness of the system for using in the rehabilitation program.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.397-403
• /
• 2017

In the modern society, psychological diseases and impulsive crimes due to stress are occurring. In order to reduce the stress, the existing treatment methods consisted of continuous visit counseling to determine the psychological state and prescribe medication or psychotherapy. Although this face-to-face counseling method is effective, it takes much time to determine the state of the patient, and there is a problem of treatment efficiency that is difficult to be continuously managed depending on the individual situation. In this paper, we propose an artificial intelligence emotion management system that emotions of user monitor in real time and induced to a table state. The system measures multiple bio-signals based on the PPG and the GSR sensors, preprocesses the data into appropriate data types, and classifies four typical emotional states such as pleasure, relax, sadness, and horror through the SVM algorithm. We verify that the emotion of the user is guided to a stable state by providing a real-time emotion management service when the classification result is judged to be a negative state such as sadness or fear through experiments.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.89-103
• /
• 2023

Obstructive sleep apnea (OSA) is one of the most prevalent sleep disorders that can lead to serious consequences, including hypertension and/or cardiovascular diseases, if not treated promptly. Continuous positive airway pressure (CPAP) is widely recognized as the most effective treatment for OSA, which needs the proper titration of airway pressure to achieve the most effective treatment results. However, the process of CPAP titration can be time-consuming and cumbersome. There is a growing importance in predicting personalized CPAP pressure before CPAP treatment. The primary objective of this study was to optimize the CPAP titration process for obstructive sleep apnea patients through EEG feature engineering with machine learning techniques. We aimed to identify and utilize the most critical EEG features to forecast key OSA predictive indicators, ultimately facilitating more precise and personalized CPAP treatment strategies. Here, we analyzed 126 OSA patients' PSG datasets before and after the CPAP treatment. We extracted 29 EEG features to predict the features that have high importance on the OSA prediction index which are AHI and SpO2 by applying the Shapley Additive exPlanation (SHAP) method. Through extracted EEG features, we confirmed the six EEG features that had high importance in predicting AHI and SpO2 using XGBoost, Support Vector Machine regression, and Random Forest Regression. By utilizing the predictive capabilities of EEG-derived features for AHI and SpO2, we can better understand and evaluate the condition of patients undergoing CPAP treatment. The ability to predict these key indicators accurately provides more immediate insight into the patient's sleep quality and potential disturbances. This not only ensures the efficiency of the diagnostic process but also provides more tailored and effective treatment approach. Consequently, the integration of EEG analysis into the sleep study protocol has the potential to revolutionize sleep diagnostics, offering a time-saving, and ultimately more effective evaluation for patients with sleep-related disorders.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.731-736
• /
• 2023

Recently, the medical field has been applying mandatory Electronic Medical Records (EMRs) and Electronic Health Records (EHRs) systems that computerize and manage medical records, and distributing them throughout the entire medical industry to utilize patients' past medical records for additional medical procedures. However, the conversations between medical professionals and patients that occur during general medical consultations and counseling sessions are not separately recorded or stored, so additional important patient information cannot be efficiently utilized. Therefore, we propose an electronic medical record system that uses speech recognition and natural language processing deep learning to store conversations between medical professionals and patients in text form, automatically extracts and summarizes important medical consultation information, and generates electronic medical records. The system acquires text information through the recognition process of medical professionals and patients' medical consultation content. The acquired text is then divided into multiple sentences, and the importance of multiple keywords included in the generated sentences is calculated. Based on the calculated importance, the system ranks multiple sentences and summarizes them to create the final electronic medical record data. The proposed system's performance is verified to be excellent through quantitative analysis.