المؤلفون: Park, Hyung, Song, Min, Lee, Eun Byul, Seo, Bo Kyung, Choi, Chang Min

المصدر: JMIR Medical Informatics, Vol 9, Iss 5, p e24803 (2021)

مصطلحات موضوعية: Computer applications to medicine. Medical informatics, R858-859.7

الوصف: BackgroundIn the analysis of electronic health records, proper labeling of outcomes is mandatory. To obtain proper information from radiologic reports, several studies were conducted to classify radiologic reports using deep learning. However, the classification of pneumonia in bilingual radiologic reports has not been conducted previously. ObjectiveThe aim of this research was to classify radiologic reports into pneumonia or no pneumonia using a deep learning method. MethodsA data set of radiology reports for chest computed tomography and chest x-rays of surgical patients from January 2008 to January 2018 in the Asan Medical Center in Korea was retrospectively analyzed. The classification performance of our long short-term memory (LSTM)–Attention model was compared with various deep learning and machine learning methods. The area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, sensitivity, specificity, accuracy, and F1 score for the models were compared. ResultsA total of 5450 radiologic reports were included that contained at least one pneumonia-related word. In the test set (n=1090), our proposed model showed 91.01% (992/1090) accuracy (AUROCs for negative, positive, and obscure were 0.98, 0.97, and 0.90, respectively). The top 3 performances of the models were based on FastText or LSTM. The convolutional neural network–based model showed a lower accuracy 73.03% (796/1090) than the other 2 algorithms. The classification of negative results had an F1 score of 0.96, whereas the classification of positive and uncertain results showed a lower performance (positive F1 score 0.83; uncertain F1 score 0.62). In the extra-validation set, our model showed 80.0% (642/803) accuracy (AUROCs for negative, positive, and obscure were 0.92, 0.96, and 0.84, respectively). ConclusionsOur method showed excellent performance in classifying pneumonia in bilingual radiologic reports. The method could enrich the research on pneumonia by obtaining exact outcomes from electronic health data.

وصف الملف: electronic resource

العلاقة: https://medinform.jmir.org/2021/5/e24803Test; https://doaj.org/toc/2291-9694Test

الوصول الحر: https://doaj.org/article/f4c9e6f956ff4c508acec0d0b6241e18Test

المؤلفون: Park, Hyung Jun, Jung, Dae Yon, Ji, Wonjun, Choi, Chang-Min

المصدر: Journal of Medical Internet Research, Vol 22, Iss 8, p e19512 (2020)

مصطلحات موضوعية: Computer applications to medicine. Medical informatics, R858-859.7, Public aspects of medicine, RA1-1270

الوصف: BackgroundDetecting bacteremia among surgical in-patients is more obscure than other patients due to the inflammatory condition caused by the surgery. The previous criteria such as systemic inflammatory response syndrome or Sepsis-3 are not available for use in general wards, and thus, many clinicians usually rely on practical senses to diagnose postoperative infection. ObjectiveThis study aims to evaluate the performance of continuous monitoring with a deep learning model for early detection of bacteremia for surgical in-patients in the general ward and the intensive care unit (ICU). MethodsIn this retrospective cohort study, we included 36,023 consecutive patients who underwent general surgery between October and December 2017 at a tertiary referral hospital in South Korea. The primary outcome was the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC) for detecting bacteremia by the deep learning model, and the secondary outcome was the feature explainability of the model by occlusion analysis. ResultsOut of the 36,023 patients in the data set, 720 cases of bacteremia were included. Our deep learning–based model showed an AUROC of 0.97 (95% CI 0.974-0.981) and an AUPRC of 0.17 (95% CI 0.147-0.203) for detecting bacteremia in surgical in-patients. For predicting bacteremia within the previous 24-hour period, the AUROC and AUPRC values were 0.93 and 0.15, respectively. Occlusion analysis showed that vital signs and laboratory measurements (eg, kidney function test and white blood cell group) were the most important variables for detecting bacteremia. ConclusionsA deep learning model based on time series electronic health records data had a high detective ability for bacteremia for surgical in-patients in the general ward and the ICU. The model may be able to assist clinicians in evaluating infection among in-patients, ordering blood cultures, and prescribing antibiotics with real-time monitoring.

وصف الملف: electronic resource

العلاقة: https://www.jmir.org/2020/8/e19512Test; https://doaj.org/toc/1438-8871Test

الوصول الحر: https://doaj.org/article/068ca4cdc3c1401496dcb3a2e92a4e09Test

المؤلفون: Song, Wongeun, Jung, Se Young, Baek, Hyunyoung, Choi, Chang Won, Jung, Young Hwa, Yoo, Sooyoung

المصدر: JMIR Medical Informatics, Vol 8, Iss 7, p e15965 (2020)

مصطلحات موضوعية: Computer applications to medicine. Medical informatics, R858-859.7

الوصف: BackgroundNeonatal sepsis is associated with most cases of mortalities and morbidities in the neonatal intensive care unit (NICU). Many studies have developed prediction models for the early diagnosis of bloodstream infections in newborns, but there are limitations to data collection and management because these models are based on high-resolution waveform data. ObjectiveThe aim of this study was to examine the feasibility of a prediction model by using noninvasive vital sign data and machine learning technology. MethodsWe used electronic medical record data in intensive care units published in the Medical Information Mart for Intensive Care III clinical database. The late-onset neonatal sepsis (LONS) prediction algorithm using our proposed forward feature selection technique was based on NICU inpatient data and was designed to detect clinical sepsis 48 hours before occurrence. The performance of this prediction model was evaluated using various feature selection algorithms and machine learning models. ResultsThe performance of the LONS prediction model was found to be comparable to that of the prediction models that use invasive data such as high-resolution vital sign data, blood gas estimations, blood cell counts, and pH levels. The area under the receiver operating characteristic curve of the 48-hour prediction model was 0.861 and that of the onset detection model was 0.868. The main features that could be vital candidate markers for clinical neonatal sepsis were blood pressure, oxygen saturation, and body temperature. Feature generation using kurtosis and skewness of the features showed the highest performance. ConclusionsThe findings of our study confirmed that the LONS prediction model based on machine learning can be developed using vital sign data that are regularly measured in clinical settings. Future studies should conduct external validation by using different types of data sets and actual clinical verification of the developed model.

وصف الملف: electronic resource

العلاقة: http://medinform.jmir.org/2020/7/e15965Test/; https://doaj.org/toc/2291-9694Test

الوصول الحر: https://doaj.org/article/f7f599f2f3524731801dfa30e4908ff9Test

المؤلفون: Kim, Sangwook, Lee, Jimin, Kim, Jungye, Kim, Bitbyeol, Choi, Chang Heon, Jung, Seongmoon

مصطلحات موضوعية: Physics - Medical Physics, Computer Science - Computer Vision and Pattern Recognition

الوصف: Objectives: We propose a deep learning (DL) multi-task learning framework using convolutional neural network (CNN) for a direct conversion of single-energy CT (SECT) to three different parametric maps of dual-energy CT (DECT): Virtual-monochromatic image (VMI), effective atomic number (EAN), and relative electron density (RED). Methods: We propose VMI-Net for conversion of SECT to 70, 120, and 200 keV VMIs. In addition, EAN-Net and RED-Net were also developed to convert SECT to EAN and RED. We trained and validated our model using 67 patients collected between 2019 and 2020. SECT images with 120 kVp acquired by the DECT (IQon spectral CT, Philips) were used as input, while the VMIs, EAN, and RED acquired by the same device were used as target. The performance of the DL framework was evaluated by absolute difference (AD) and relative difference (RD). Results: The VMI-Net converted 120 kVp SECT to the VMIs with AD of 9.02 Hounsfield Unit, and RD of 0.41% compared to the ground truth VMIs. The ADs of the converted EAN and RED were 0.29 and 0.96, respectively, while the RDs were 1.99% and 0.50% for the converted EAN and RED, respectively. Conclusions: SECT images were directly converted to the three parametric maps of DECT (i.e., VMIs, EAN, and RED). By using this model, one can generate the parametric information from SECT images without DECT device. Our model can help investigate the parametric information from SECT retrospectively. Advances in knowledge: Deep learning framework enables converting SECT to various high-quality parametric maps of DECT.
Comment: 29 pages, 17 figures

الوصول الحر: http://arxiv.org/abs/2309.15314Test

المؤلفون: Ji, Wonjun, Kwon, Hee, Lee, Sungin, Kim, Seulgi, Hong, Jeong Sook, Park, Yu Rang, Kim, Hyeong Ryul, Lee, Jae Cheol, Jung, Eun Ji, Kim, Donghyun, Choi, Chang-Min

المصدر: JMIR mHealth and uHealth, Vol 7, Iss 6, p e12645 (2019)

مصطلحات موضوعية: Information technology, T58.5-58.64, Public aspects of medicine, RA1-1270

الوصف: BackgroundLung cancer patients experience various symptoms during treatment. Although pulmonary rehabilitation is an effective way to improve these symptoms, a medical environment of limited availability makes it difficult to provide seamless and adequate rehabilitation for lung cancer patients. ObjectiveThis study aimed to investigate the effects of a personalized pulmonary rehabilitation program using real-time mobile patient health data for patients with non–small cell lung cancer. MethodsWe conducted a prospective clinical trial in 64 patients with non–small cell lung cancer aged between 20 and 80 years at a large tertiary hospital in Seoul, South Korea. A 12-week personalized pulmonary rehabilitation program, called efil breath, was administered to determine the effectiveness of the newly developed rehabilitation app. Participants were randomly allocated to the fixed exercise or fixed-interactive exercise group (which received the personalized program). We measured changes in 6-minute walk distance (6MWD) and dyspnea (modified Medical Research Council [mMRC] score) at 6 weeks; and quality of life and service satisfaction at 12 weeks. We used the paired t test to analyze the variables. ResultsPatients used the newly developed mobile health pulmonary rehabilitation app and a real-time patient monitoring website. In all participants, significant changes were observed in 6MWD at 12 weeks from a mean of 433.43m (SD 65.60) to 471.25m (SD 75.69; P=.001), and mMRC from a mean score of 0.94 (0.66) to 0.61 (SD 0.82; P=.02). The intervention significantly improved their quality of life (EuroQol-visual analog scale [EQ-VAS]) compared with baseline (mean score 76.05, SD 12.37 vs 82.09, SD 13.67, respectively; P=.002). ConclusionsA personalized mobile health–based pulmonary rehabilitation app for recording and monitoring real-time health data of patients with non–small cell lung cancer can supplement traditional health care center–based rehabilitation programs. This technology can encourage improvement of physical activity, dyspnea, and quality of life.

وصف الملف: electronic resource

العلاقة: http://mhealth.jmir.org/2019/6/e12645Test/; https://doaj.org/toc/2291-5222Test

الوصول الحر: https://doaj.org/article/f5cd87f153df4a2e889274d10b4fcb41Test

المؤلفون: Park, Sojung, Kim, Ji Youn, Lee, Jae Cheol, Kim, Hyeong Ryul, Song, Seungjae, Kwon, Hee, Ji, Wonjun, Choi, Chang Min

المصدر: JMIR mHealth and uHealth, Vol 7, Iss 2, p e11094 (2019)

مصطلحات موضوعية: Information technology, T58.5-58.64, Public aspects of medicine, RA1-1270

الوصف: BackgroundAdvanced lung cancer patients often have chronic lung disease with reduced exercise capacities and various symptoms leading to altered quality of life (QoL). No studies have assessed pulmonary rehabilitation (PR) employing a mobile app and an Internet of Things device in advanced lung cancer patients undergoing chemotherapy. ObjectiveThis study aimed to determine the feasibility and efficacy of smartphone app–based PR on exercise capacity, symptom management, and QoL in patients with advanced lung cancer undergoing chemotherapy. MethodsA total of 100 patients were recruited in a prospective, single-arm intervention study using a smartphone app–based PR program for 12 weeks. Exercise capacity (6-min walking distance, 6MWD), QoL, symptom scale scores, and distress indexes were investigated. ResultsA total of 90 patients completed the PR program. The most common cause of drop out was hospitalization because of cancer progression. After PR, there was significant improvement in the 6MWD; 380.1 m (SD 74.1) at baseline, 429.1 m (SD 58.6) at 6 weeks (P

وصف الملف: electronic resource

العلاقة: http://mhealth.jmir.org/2019/2/e11094Test/; https://doaj.org/toc/2291-5222Test

الوصول الحر: https://doaj.org/article/b8e4fe45acdc4094b418eb3110b6bd27Test

المؤلفون: Lee, Jang Ho, Park, Yu Rang, Kweon, Solbi, Kim, Seulgi, Ji, Wonjun, Choi, Chang-Min

المصدر: JMIR mHealth and uHealth, Vol 6, Iss 12, p e12864 (2018)

مصطلحات موضوعية: Information technology, T58.5-58.64, Public aspects of medicine, RA1-1270

وصف الملف: electronic resource

العلاقة: http://mhealth.jmir.org/2018/12/e12864Test/; https://doaj.org/toc/2291-5222Test

الوصول الحر: https://doaj.org/article/8449bd3318444c8ebb008e8399245d5fTest

المؤلفون: Lee, Jang Ho, Park, Yu Rang, Kweon, Solbi, Kim, Seulgi, Ji, Wonjun, Choi, Chang-Min

المصدر: JMIR mHealth and uHealth, Vol 6, Iss 11, p e12048 (2018)

مصطلحات موضوعية: Information technology, T58.5-58.64, Public aspects of medicine, RA1-1270

الوصف: BackgroundDuring intrahospital transport, adverse events are inevitable. Real-time monitoring can be helpful for preventing these events during intrahospital transport. ObjectiveWe attempted to determine the viability of risk signal detection using wearable devices and mobile apps during intrahospital transport. An alarm was sent to clinicians in the event of oxygen saturation below 90%, heart rate above 140 or below 60 beats per minute (bpm), and network errors. We validated the reliability of the risk signal transmitted over the network. MethodsWe used two wearable devices to monitor oxygen saturation and heart rate for 23 patients during intrahospital transport for diagnostic workup or rehabilitation. To determine the agreement between the devices, records collected every 4 seconds were matched and imputation was performed if no records were collected at the same time by both devices. We used intraclass correlation coefficients (ICC) to evaluate the relationships between the two devices. ResultsData for 21 patients were delivered to the cloud over LTE, and data for two patients were delivered over Wi-Fi. Monitoring devices were used for 20 patients during intrahospital transport for diagnostic work up and for three patients during rehabilitation. Three patients using supplemental oxygen before the study were included. In our study, the ICC for the heart rate between the two devices was 0.940 (95% CI 0.939-0.942) and that of oxygen saturation was 0.719 (95% CI 0.711-0.727). Systemic error analyzed with Bland-Altman analysis was 0.428 for heart rate and –1.404 for oxygen saturation. During the study, 14 patients had 20 risk signals: nine signals for eight patients with less than 90% oxygen saturation, four for four patients with a heart rate of 60 bpm or less, and seven for five patients due to network error. ConclusionsWe developed a system that notifies the health care provider of the risk level of a patient during transportation using a wearable device and a mobile app. Although there were some problems such as missing values and network errors, this paper is meaningful in that the previously mentioned risk detection system was validated with actual patients.

وصف الملف: electronic resource

العلاقة: http://mhealth.jmir.org/2018/11/e12048Test/; https://doaj.org/toc/2291-5222Test

الوصول الحر: https://doaj.org/article/8e68c012ee5d4e9bb126b484eccc96d8Test

المؤلفون: Aslan, Hacı İsmail, Choi, Chang, Ko, Hoon

المصدر: Math. Biosci. Eng. 19 (2022), no. 12, 12146-12159

مصطلحات موضوعية: Computer Science - Social and Information Networks, Computer Science - Machine Learning

الوصف: Due to the advent of the expressions of data other than tabular formats, the topological compositions which make samples interrelated came into prominence. Analogically, those networks can be interpreted as social connections, dataflow maps, citation influence graphs, protein bindings, etc. However, in the case of social networks, it is highly crucial to evaluate the labels of discrete communities. The reason underneath for such a study is the non-negligible importance of analyzing graph networks to partition the vertices by using the topological features of network graphs, solely. For each of these interaction-based entities, a social graph, a mailing dataset, and two citation sets are selected as the testbench repositories. This paper, it was not only assessed the most valuable method but also determined how graph neural networks work and the need to improve against non-neural network approaches which are faster and computationally cost-effective. Also, this paper showed a limit to be excesses by prospective graph neural network variations by using the topological features of networks trialed.
Comment: This is a paper whose final and definite form is published open access by 'Mathematical Biosciences and Engineering' (ISSN: 1551-0018)

الوصول الحر: http://arxiv.org/abs/2301.11288Test

المؤلفون: Choi, Chang-Sik, Baccelli, François

مصطلحات موضوعية: Electrical Engineering and Systems Science - Signal Processing, Computer Science - Information Theory, Mathematics - Probability

الوصف: To model existing or future low Earth orbit (LEO) satellite networks leveraging multiple constellations, we propose a simple analytical approach to represent the clustering of satellites on orbits. More precisely, we develop a variable-altitude Poisson orbit process that effectively captures the geometric fact that satellites are always positioned on orbits, and these orbits may vary in altitude. Conditionally on the orbit process, satellites situated on these orbits are modeled as linear Poisson point processes, thereby forming a Cox point process. For this model, we derive useful statistics, including the distribution of the distance from the typical user to its nearest visible satellite, the outage probability, the Laplace functional of the proposed Cox satellite point process, and the Laplace transform of the interference power from the Cox-distributed satellites under general fading. The derived statistics enable the evaluation of the performance of such LEO satellite communication systems as functions of network parameters.
Comment: accepted to IEEE Trans. Veh. Technol

الوصول الحر: http://arxiv.org/abs/2301.02469Test