Search

Aims Although overt hyperthyroidism adversely affects a patient’s prognosis, thyroid function tests (TFTs) are not routinely conducted. Furthermore, vague symptoms of hyperthyroidism often lead to hyperthyroidism being overlooked. An electrocardiogram (ECG) is a commonly used screening test, and the association between thyroid function and ECG is well known. However, it is difficult for clinicians to detect hyperthyroidism through subtle ECG changes. For early detection of hyperthyroidism, we aimed to develop and validate an electrocardiographic biomarker based on a deep learning model (DLM) for detecting hyperthyroidism. Methods and results This multicentre retrospective cohort study included patients who underwent ECG and TFTs within 24 h. For model development and internal validation, we obtained 174 331 ECGs from 113 194 patients. We extracted 48 648 ECGs from 33 478 patients from another hospital for external validation. Using 500 Hz raw ECG, we developed a DLM with 12-lead, 6-lead (limb leads, precordial leads), and single-lead (lead I) ECGs to detect overt hyperthyroidism. We calculated the model’s performance on the internal and external validation sets using the area under the receiver operating characteristic curve (AUC). The AUC of the DLM using a 12-lead ECG was 0.926 (0.913–0.94) for internal validation and 0.883(0.855–0.911) for external validation. The AUC of DLMs using six and a single-lead were in the range of 0.889–0.906 for internal validation and 0.847–0.882 for external validation. Conclusion We developed a DLM using ECG for non-invasive screening of overt hyperthyroidism. We expect this model to contribute to the early diagnosis of diseases and improve patient prognosis.

Peripartum cardiomyopathy (PPCM) is a fatal maternal complication, with left ventricular systolic dysfunction (LVSD; Left ventricular ejection fraction 45% or less) occurring at the end of pregnancy or in the months following delivery. The scarcity of screening tools for PPCM leads to a delayed diagnosis and increases its mortality and morbidity. We aim to evaluate an electrocardiogram (ECG)-deep learning model (DLM) for detecting cardiomyopathy in the peripartum period.For the DLM development and internal performance test for detecting LVSD, we obtained a dataset of 122,733 ECG-echocardiography pairs from 58,530 male and female patients from two community hospitals. For the DLM external validation, this study included 271 ECG-echocardiography pairs (157 unique pregnant and postpartum period women) examined in the Ajou University Medical Center (AUMC) between January 2007 and May 2020. All included cases underwent an ECG within two weeks before or after the day of transthoracic echocardiography, which was performed within a month before delivery, or within five months after delivery. Based on the diagnostic criteria of PPCM, we analyzed the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) to evaluate the model effectiveness.The ECG-based DLM detected PPCM with an AUROC of 0.877. Moreover, its sensitivity, specificity, PPV, and NPV for the detection of PPCM were 0.877, 0.833, 0.809, 0.352, and 0.975, respectively.An ECG-based DLM non-invasively and effectively detects cardiomyopathies occurring in the peripartum period and could be an ideal screening tool for PPCM.

In this demo, we present RealGraph Web , a web-based platform that provides various kinds of graph analysis services. RealGraph Web is based on RealGraph, a graph engine that addresses the problem of performance degradation in processing real-world big graphs, achieving great performance improvement up to 44 times over existing state-of-the-art graph engines. RealGraph Web runs on a single machine with a web-based interface, thereby allowing users to easily and conveniently enjoy graph analysis services and perform various graph algorithms anywhere on the web . In this demo, we present how a user can analyze a graph on RealGraph Web in three steps and get the analysis result quickly via a graphical user interface.

Introduction Early detection and intervention of atrial fibrillation (AF) is a cornerstone for effective treatment and prevention of mortality. Diverse deep learning models (DLMs) have been developed, but they could not be applied in clinical practice owing to their lack of interpretability. We developed an explainable DLM to detect AF using ECG and validated its performance using diverse formats of ECG. Methods We conducted a retrospective study. The Sejong ECG dataset comprising 128,399 ECGs was used to develop and internally validated the explainable DLM. DLM was developed with two feature modules, which could describe the reason for DLM decisions. DLM was external validated using data from 21,837, 10,605, and 8528 ECGs from PTB-XL, Chapman, and PhysioNet non-restricted datasets, respectively. The predictor variables were digitally stored ECGs, and the endpoints were AFs. Results During internal and external validation of the DLM, the area under the receiver operating characteristic curves (AUCs) of the DLM using a 12‑lead ECG in detecting AF were 0.997–0.999. The AUCs of the DLM with VAE using a 6‑lead and single‑lead ECG were 0.990–0.999. The AUCs of explainability about features such as rhythm irregularity and absence of P-wave were 0.961–0.993 and 0.983–0.993, respectively. Conclusions Our DLM successfully detected AF using diverse ECGs and described the reason for this decision. The results indicated that an explainable artificial intelligence methodology could be adopted to the DLM using ECG and enhance the transparency of the DLM for its application in clinical practice.

Aims Paroxysmal supraventricular tachycardia (PSVT) is not detected owing to its paroxysmal nature, but it is associated with the risk of cardiovascular disease and worsens the patient quality of life. A deep learning model (DLM) was developed and validated to identify patients with PSVT during normal sinus rhythm in this multicentre retrospective study. Methods and results This study included 12 955 patients with normal sinus rhythm, confirmed by a cardiologist. A DLM was developed using 31 147 electrocardiograms (ECGs) of 9069 patients from one hospital. We conducted an accuracy test with 13 753 ECGs of 3886 patients from another hospital. The DLM was developed based on residual neural network. Digitally stored ECG were used as predictor variables and the outcome of the study was ability of the DLM to identify patients with PSVT using an ECG during sinus rhythm. We employed a sensitivity map method to identify an ECG region that had a significant effect on developing PSVT. During accuracy test, the area under the receiver operating characteristic curve of a DLM using a 12-lead ECG for identifying PSVT patients during sinus rhythm was 0.966 (0.948–0.984). The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of DLM were 0.970, 0.868, 0.972, 0.255, and 0.998, respectively. The DLM showed delta wave and QT interval were important to identify the PSVT. Conclusion The proposed DLM demonstrated a high performance in identifying PSVT during normal sinus rhythm. Thus, it can be used as a rapid, inexpensive, point-of-care means of identifying PSVT in patients.

Image compression is used in several clinical organizations to help address the overhead associated with medical imaging. These methods reduce file size by using a compact representation of the original image. This study aimed to analyze the impact of image compression on the performance of deep learning-based models in classifying mammograms as “malignant”—cases that lead to a cancer diagnosis and treatment—or “normal” and “benign,” non-malignant cases that do not require immediate medical intervention. In this retrospective study, 9111 unique mammograms–5672 normal, 1686 benign, and 1754 malignant cases were collected from the National Cancer Center in the Republic of Korea. Image compression was applied to mammograms with compression ratios (CRs) ranging from 15 to 11 K. Convolutional neural networks (CNNs) with three convolutional layers and three fully-connected layers were trained using these images to classify a mammogram as malignant or not malignant across a range of CRs using five-fold cross-validation. Models trained on images with maximum CRs of 5 K had an average area under the receiver operating characteristic curve (AUROC) of 0.87 and area under the precision-recall curve (AUPRC) of 0.75 across the five folds and compression ratios. For images compressed with CRs of 10 K and 11 K, model performance decreased (average 0.79 in AUROC and 0.49 in AUPRC). Upon generating saliency maps that visualize the areas each model views as significant for prediction, models trained on less compressed (CR

Introduction The detection and monitoring of electrolyte imbalance is essential for appropriate management of many metabolic diseases; however, there is no tool that detects such imbalances reliably and noninvasively. In this study, we developed a deep learning model (DLM) using electrocardiography (ECG) for detecting electrolyte imbalance and validated its performance in a multicenter study. Methods and Results This retrospective cohort study included two hospitals: 92,140 patients who underwent a laboratory electrolyte examination and an ECG within 30 min were included in this study. A DLM was developed using 83,449 ECGs of 48,356 patients; the internal validation included 12,091 ECGs of 12,091 patients. We conducted an external validation with 31,693 ECGs of 31,693 patients from another hospital, and the result was electrolyte imbalance detection. During internal, the area under the receiving operating characteristic curve (AUC) of a DLM using a 12‐lead ECG for detecting hyperkalemia, hypokalemia, hypernatremia, hyponatremia, hypercalcemia, and hypocalcemia were 0.945, 0.866, 0.944, 0.885, 0.905, and 0.901, respectively. The values during external validation of the AUC of hyperkalemia, hypokalemia, hypernatremia, hyponatremia, hypercalcemia, and hypocalcemia were 0.873, 0.857, 0.839, 0.856, 0.831, and 0.813 respectively. The DLM helped to visualize the important ECG region for detecting each electrolyte imbalance, and it showed how the P wave, QRS complex, or T wave differs in importance in detecting each electrolyte imbalance. Conclusion The proposed DLM demonstrated high performance in detecting electrolyte imbalance. These results suggest that a DLM can be used for detecting and monitoring electrolyte imbalance using ECG on a daily basis.

Purpose Although renal failure is a major healthcare burden globally and the cornerstone for preventing its irreversible progression is an early diagnosis, an adequate and noninvasive tool to screen renal impairment (RI) reliably and economically does not exist. We developed an interpretable deep learning model (DLM) using electrocardiography (ECG) and validated its performance. Methods This retrospective cohort study included two hospitals. We included 115,361 patients who had at least one ECG taken with an estimated glomerular filtration rate measurement within 30 min of the index ECG. A DLM was developed using 96,549 ECGs of 55,222 patients. The internal validation included 22,949 ECGs of 22,949 patients. Furthermore, we conducted an external validation with 37,190 ECGs of 37,190 patients from another hospital. The endpoint was to detect a moderate to severe RI (estimated glomerular filtration rate 2). Results The area under the receiver operating characteristic curve (AUC) of a DLM using a 12-lead ECG for detecting RI during the internal and external validation was 0.858 (95% confidence interval 0.851–0.866) and 0.906 (0.900–0.912), respectively. In the initial evaluation of 25,536 individuals without RI patients whose DLM was defined as having a higher risk had a significantly higher chance of developing RI than those in the low-risk group (17.2% vs. 2.4%, p Conclusion The DLM demonstrated high performance for RI detection and prediction using 12-, 6-, single-lead ECGs.

Background Sepsis is a life-threatening organ dysfunction and a major healthcare burden worldwide. Although sepsis is a medical emergency that requires immediate management, screening for the occurrence of sepsis is difficult. Herein, we propose a deep learning-based model (DLM) for screening sepsis using electrocardiography (ECG). Methods This retrospective cohort study included 46,017 patients who were admitted to two hospitals. A total of 1,548 and 639 patients had sepsis and septic shock, respectively. The DLM was developed using 73,727 ECGs from 18,142 patients, and internal validation was conducted using 7774 ECGs from 7,774 patients. Furthermore, we conducted an external validation with 20,101 ECGs from 20,101 patients from another hospital to verify the applicability of the DLM across centers. Results During the internal and external validations, the area under the receiver operating characteristic curve (AUC) of the DLM using 12-lead ECG was 0.901 (95% confidence interval, 0.882–0.920) and 0.863 (0.846–0.879), respectively, for screening sepsis and 0.906 (95% confidence interval (CI), 0.877–0.936) and 0.899 (95% CI, 0.872–0.925), respectively, for detecting septic shock. The AUC of the DLM for detecting sepsis using 6-lead and single-lead ECGs was 0.845–0.882. A sensitivity map revealed that the QRS complex and T waves were associated with sepsis. Subgroup analysis was conducted using ECGs from 4,609 patients who were admitted with an infectious disease, and the AUC of the DLM for predicting in-hospital mortality was 0.817 (0.793–0.840). There was a significant difference in the prediction score of DLM using ECG according to the presence of infection in the validation dataset (0.277 vs. 0.574, p p = 0.018). Conclusions The DLM delivered reasonable performance for sepsis screening using 12-, 6-, and single-lead ECGs. The results suggest that sepsis can be screened using not only conventional ECG devices but also diverse life-type ECG machines employing the DLM, thereby preventing irreversible disease progression and mortality.

Background: Albumin has a pivotal role in the homeostasis of osmotic pressure and is associated with cardiovascular, nephrotic, hepatic, and nutritional diseases. The detection of hypoalbuminemia is a cornerstone for diagnosis of hidden diseases and patient deterioration. We developed and validated a deep-learning-based model (DLM) for detection of hypoalbuminemia using electrocardiography (ECG). Methods: This historical cohort study included data from consecutive patients from two hospitals. The patient data in one hospital were divided into development (82,499 ECGs from 54,248 patients) and internal validation (20,664 ECGs from 20,664 patients) datasets, whereas the patient data in the other hospital were included in only an external validation (37,421 ECGs from 37,421 patients) dataset. An DLM was developed using a 12-lead ECG signal, age, and sex from the development dataset. The endpoint was hypoalbuminemia, defined by serum albumin concentration below 3.5 g/dL. Results: During the internal and external validations, the areas under the receiver operating characteristic curve of the DLM for the detection of hypoalbuminemia were 0.887 (0.877–0.897) and 0.888 (0.880–0.896), respectively. Among the 27,400 individuals without hypoalbuminemia at the initial laboratory exam, those identified by the DLM as higher-risk patients had a significantly larger change in developing hypoalbuminemia than those in the low-risk group (7.09% vs. 1.01%, p < 0.001) during 24 months. The sensitivity map showed that the DLM focused on the T wave and QRS complex for the detection of hypoalbuminemia. Conclusions: The DLM exhibited a high accuracy for hypoalbuminemia detection and prediction using 12-, 6-, and single-lead ECGs.

Background Early detection and intervention is the cornerstone for appropriate treatment of arrhythmia and prevention of complications and mortality. Although diverse deep learning models have been developed to detect arrhythmia, they have been criticized due to their unexplainable nature. In this study, we developed an explainable deep learning model (XDM) to classify arrhythmia, and validated its performance using diverse external validation data. Methods In this retrospective study, the Sejong dataset comprising 86,802 electrocardiograms (ECGs) was used to develop and internally variate the XDM. The XDM based on a neural network-backed ensemble tree was developed with six feature modules that are able to explain the reasons for its decisions. The model was externally validated using data from 36,961 ECGs from four non-restricted datasets. Results During internal and external validation of the XDM, the average area under the receiver operating characteristic curves (AUCs) using a 12‑lead ECG for arrhythmia classification were 0.976 and 0.966, respectively. The XDM outperformed a previous simple multi-classification deep learning model that used the same method. During internal and external validation, the AUCs of explainability were 0.925–0.991. Conclusion Our XDM successfully classified arrhythmia using diverse formats of ECGs and could effectively describe the reason for the decisions. Therefore, an explainable deep learning methodology could improve accuracy compared to conventional deep learning methods, and that the transparency of XDM can be enhanced for its application in clinical practice.

BACKGROUND Postoperative length of stay is a key indicator in the management of medical resources and an indirect predictor of the incidence of surgical complications and the degree of recovery of the patient after cancer surgery. Recently, machine learning has been used to predict complex medical outcomes, such as prolonged length of hospital stay, using extensive medical information. OBJECTIVE The objective of this study was to develop a prediction model for prolonged length of stay after cancer surgery using a machine learning approach. METHODS In our retrospective study, electronic health records (EHRs) from 42,751 patients who underwent primary surgery for 17 types of cancer between January 1, 2000, and December 31, 2017, were sourced from a single cancer center. The EHRs included numerous variables such as surgical factors, cancer factors, underlying diseases, functional laboratory assessments, general assessments, medications, and social factors. To predict prolonged length of stay after cancer surgery, we employed extreme gradient boosting classifier, multilayer perceptron, and logistic regression models. Prolonged postoperative length of stay for cancer was defined as bed-days of the group of patients who accounted for the top 50% of the distribution of bed-days by cancer type. RESULTS In the prediction of prolonged length of stay after cancer surgery, extreme gradient boosting classifier models demonstrated excellent performance for kidney and bladder cancer surgeries (area under the receiver operating characteristic curve [AUC] >0.85). A moderate performance (AUC 0.70-0.85) was observed for stomach, breast, colon, thyroid, prostate, cervix uteri, corpus uteri, and oral cancers. For stomach, breast, colon, thyroid, and lung cancers, with more than 4000 cases each, the extreme gradient boosting classifier model showed slightly better performance than the logistic regression model, although the logistic regression model also performed adequately. We identified risk variables for the prediction of prolonged postoperative length of stay for each type of cancer, and the importance of the variables differed depending on the cancer type. After we added operative time to the models trained on preoperative factors, the models generally outperformed the corresponding models using only preoperative variables. CONCLUSIONS A machine learning approach using EHRs may improve the prediction of prolonged length of hospital stay after primary cancer surgery. This algorithm may help to provide a more effective allocation of medical resources in cancer surgery.

Sparse matrix multiplication (spGEMM) is widely used to analyze the sparse network data, and extract important information based on matrix representation. As it contains a high degree of data parallelism, many efficient implementations using data-parallel programming platforms such as CUDA and OpenCL have been introduced on graphic processing units (GPUs). Several well-known spGEMM techniques, such as cuS- PARSE and CUSP, often do not utilize the GPU resources fully, owing to the load imbalance between threads in the expansion process and high memory contention in the merge process. Furthermore, even though several outer-product-based spGEMM techniques are proposed to solve the load balancing problem on expansion, they still do not utilize the GPU resources fully, because severe computation load variations exist among the multiple thread blocks.To solve these challenges, this paper proposes a new optimization pass called Block Reorganizer, which balances the total computations of each computing unit on target GPUs, based on the outer-product-based expansion process, and reduces the memory pressure during the merge process. For expansion, it first identifies the actual computation amount for each block, and then performs two thread block transformation processes based on their characteristics: 1) B-Splitting to transform a heavy-computation blocks into multiple small blocks and 2) B- Gathering to aggregate multiple small-computation blocks to a larger block. While merging, it improves the overall performance by performing B-Limiting to limit the number of blocks on each computing unit. Experimental results show that it improves the total performance of kernel execution by 1.43x, on an average, when compared to the row-product-based spGEMM, for NVIDIA Titan Xp GPUs on real-world datasets.

The wide use of recommendation systems includes more users and items in system operations, leading to a significant increase in the size of related datasets. However, recommendation algorithms on existing single-machine-based graph engines have been developed without considering the important characteristics of recommendation datasets, i.e., huge size and power-law degree distribution. In this paper, we address how to realize efficient graph- and matrix-factorization-based recommendation algorithms, handling recommendation datasets on RealGraph, a state-of-the-art single-machine-based graph engine. Through extensive experiments, we demonstrate that our recommendation algorithms on RealGraph universally and consistently outperform the algorithms on other graph engines over all datasets up to 34 times.

An intuitive way to process the big data efficiently is to reduce the volume of data transferred over the storage interface to a host system. This is the reason that the notion of intelligent SSD (iSSD) was proposed to give processing power to SSD. There is rich literature on iSSD, however, its real implementation has not been provided to the public yet. Most prior work aims to quantify the benefits of iSSD with analytical modeling. In this paper, we first develop on iSSD simulator and present the potential of iSSD in data mining through the iSSD simulator. Our iSSD simulator performs on top of the gem 5 simulator and fully simulates all the processes of data mining algorithms running in iSSD with cycle-level accuracy. Then, we further addresse how to exploit all the computing resources for efficient processing of data mining algorithms. These days, CPU, GPU, and SSD are recently equipped together in most computing environment. If SSD is replaced with iSSD later on, we have a new computing environment where the three computing resources collaborate one another to process big data quite effectively. For this, scheduling is required to decide which computing resource is going to run for which function at which time. In our heterogeneous scheduling, types of computing resources, memory sizes in computing resources, and inter-processor communication times including IO time in SSD are considered. Our scheduling results show that processing in the collaborative environment outperforms that in the traditional one by up to about 10 times.

As the size of real-world graphs has drastically increased in recent years, a wide variety of graph engines have been developed to deal with such big graphs efficiently. However, the majority of graph engines have been designed without considering the power-law degree distribution of real-world graphs seriously. Two problems have been observed when existing graph engines process real-world graphs: inefficient scanning of the sparse indicator and the delay in iteration progress due to uneven workload distribution. In this paper, we propose RealGraph, a single-machine based graph engine equipped with the hierarchical indicator and the block-based workload allocation. Experimental results on real-world datasets show that RealGraph significantly outperforms existing graph engines in terms of both speed and scalability.

This research was supported by (1) Semiconductor Industry Collaborative Project between Hanyang University and Samsung Electronics Co. Ltd., (2) the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2014R1A2A1A10054151), (3) the ICT R&D program of MSIP/IITP (B0101-15-0266, Development of High Performance Visual Big-Data Discovery Platform for Large-Scale Realtime Data Analysis), and (4) the National Research Foundation of Korea (NRF) Grant funded by the Korean Government (MSIP) (No. 2015R1A5A7037751).

If we had the performance information of every application on every SSD, it would be very beneficial to both SSD users and SSD manufacturers. For SSD users, they can buy the SSD that is fastest for the most frequently using applications; for SSD manufacturers, they can figure out the strength and weakness of their SSD for every application. Toward this end, this article proposes a framework named ${\sf FORESEE}$ FORESEE that estimates accurately the execution time of a given IO trace (i.e., query IO trace ) of a given application on a target SSD without its actual execution . ${\sf FORESEE}$ FORESEE is developed based on the observation that if two IO traces are similar to each other in their IO behavior, their execution times tend to be similar when they are executed on the same SSD . In ${\sf FORESEE}$ FORESEE , the execution time of a query IO trace is estimated by using the execution times of the IO traces in a database similar to the query IO trace. Our technical contributions in ${\sf FORESEE}$ FORESEE are as follows: (1) we propose a goodness function that efficiently evaluates the quality of sets of features that are used to measure the similarity of IO traces; (2) we propose a DB structure and a searching method for efficiently searching for similar IO traces to a query IO trace; (3) we propose an aggregation method that aggregates the execution times of similar IO traces to a query IO trace for accurately estimating the execution time of the query IO trace; and (4) we verify the effectiveness of ${\sf FORESEE}$ FORESEE via extensive experiments by using real-world application IO traces. According to the results, the Pearson correlation coefficient (PCC) of the actual execution time and the estimated execution time by ${\sf FORESEE}$ FORESEE is found to be 0.87, indicating ${\sf FORESEE}$ FORESEE estimates the execution time accurately.

Alternating least squares (ALS) is one of the algorithms widely used in recommendation systems. In this paper, we propose a method to perform ALS on a graph engine on a single machine. We employ our graph engine, RealGraph, to handle big graphs and develop ALS efficiently performed on top of it. Real-world graphs in performing ALS follow the power-law degree distribution, specifying that a few nodes have a lot of edges while a lot of nodes do only a few edges. Prior graph engines do not consider this important characteristic, which slows down their performance. According to our extensive performance evaluation, our ALS running on RealGraph significantly outperforms those on other engines up to 2.5 times.

Graphs are very widely used to represent datasets in various real-world applications. Many algorithms dealing with graphs represent them in the form of sparse matrices and process them through sparse matrix operations. Recently, as the size of a graph increases rapidly, a single-machine-based graph engine has emerged as a general framework for effectively performing large-scale sparse matrix operations. Sparse matrices multiplication (SpGEMM) is a core building block for developing a variety of graph algorithms such as all source shortest paths, betweenness centrality, breadth first search from multiple sources, subgraph indexing, and graph construction. This paper addresses how to perform two sparse matrices multiplication (SpGEMM) efficiently on a single-machine-based graph engine. To effectively perform the large-scale SpGEMM, we have two issues: (1) selecting an appropriate type of matrix products (i.e., inner products, outer products, and row-row products), and (2) allocating memory space to matrices according to different types of matrix products. We first formulate the cost models for the three matrix product types by reflecting their characteristics. We observed the commonality in the processes of the matrix multiplication and the join in a relational database. Based on this observation, we propose memory allocation schemes for three matrix products by borrowing the idea of memory allocation employed in join. Finally, we show the effectiveness of our approach via extensive experiments with real-life datasets.

The size of graphs has dramatically increased. Graph engines for a single machine have been emerged to process these graphs efficiently. However, existing engines have overlooked a data locality which is an imperative factor to improve the performance of these engines in the previous literature. In this paper, we show the importance of data locality with graph algorithms by running on graph engines based on a single machine.

Due to an explosive growth of Internet applications, the amount of data has increased enormously. In order to store and process this big data more efficiently, a solid-state device (SSD) has replaced a hard disk drive (HDD) as a primary storage media. In spite of high internal bandwidth, SSD has its performance bottleneck on the host interface whose bandwidth is relatively low. To overcome the problem of performance bottleneck in big data processing, the notion of intelligent SSD (iSSD) was proposed to give computing power to SSD. However, its real implementation has not been provided to the public yet. In this paper, we are going to verify the potential of iSSD in handling data-intensive algorithms. To the end, we first develop an iSSD simulator and then evaluate the performance of data mining algorithms inside iSSD on the top of it in comparison with that by the host CPU. The results reveal that data mining with iSSD outperforms that with host CPUs up to around 300%.

A solid state device (SSD), which has the characteristics such as high IO bandwidth and low access latency, is drawing attention as a next-generation storage device. Even though SSD provides a high internal bandwidth, the performance bottleneck exists on the host interface of relatively low bandwidth in spite of the increased internal bandwidth of SSD. To overcome the performance bottleneck, the notion of intelligent SSD (iSSD) has been proposed. In iSSD, there are still problems in processing the algorithms of high complexity. In this paper, we address an effective collaboration of iSSD and host CPU in order to maximize the performance of data-intensive algorithms. Extensive experimental results show that our approach performs faster up to 2.43 times than a previous approach.

Recently, a draftee’s shooting spree in the inter-Korean border town of Goseong, Gangwon-do resulted in killing five and injuring seven soldiers. The 119 state emergency agency and military were criticized for flawed communication, causing delay in dispatching an emergency helicopter to the frontline unit where the shooting took place [1]. The autopsy results showed that some of the victims died from heavy blood loss rather than directly from their wounds [2]. At this point, several questions are raised. Are military emergency medical technicians well trained? Do they have enough experience? What kind of education is needed to perform their role? What do they need to increase their professional competencies? The aim of this study is to determine what is needed to increase the professional competencies of the Republic of Korea Air Force (ROKAF) emergency medical technicians (EMTs). During three weeks in June 2014, all 78 ROKAF medical technicians were contacted by email. Questionnaire item topics are presented in Table 1. Items can be grouped as follows. Items 1 to 3 address educational activities to colleagues; items 4 and 5 cover patient management experience; items 6 to 11 review educational needs; and items 12 and 13 address professional competence. Not all questions were answered by every respondent; therefore, answers are described by number and percentage of responses to specific questions. The replies were collected and analyzed. Out of total 78 subjects, 67 (86.0%) responded. Results were as follows. (1) Educational activity to teach other soldiers about cardiopulmonary resuscitation (2013): Among the 62 respondents, 40 (64.5%) taught cardiopulmonary resuscitation to other soldiers at least once, while 22 (35.5%) had not. Number of sessions varied (once to 80 times); 16 (40%) of them were five or fewer. Most of them (36, 90%) were 20 or fewer. (2) Educational activity to teach other soldiers about trauma management (TM; 2013): Among the 64 respondents, 37 EMTs (57.8%) taught TM to other soldiers at least once, while 27 (42.2%) had not. Number of sessions varied (once to over 30 times); 27 (73.0%) of them were within five sessions. (3) Experience of cardiac arrest patient management during the last 12 months: Among the 67 respondents, only three EMTs (4.5%) experienced cardiac arrest patient management during the last 12 months. The remainder (64, 95.5%) had not. Two of them had one opportunity each; one had two opportunities. (4) Experience of fracture patient management during last 12 months: Among the 67 respondents, only nine EMTs (13.4%) experienced fracture patient management during the last 12 months. The remainder (58, 86.6%) had not. Two of them had one opportunity each, four had two opportunities, two had three opportunities, and one had five opportunities. (5) Experience of trauma patient management during the last 12 months: Among the 67 respondents, only 10 EMTs (14.9%) experienced trauma patient management during the last 12 months. The remainder (57, 85.1%) had not. Six of them had one opportunity each, three had two opportunities, and one had three opportunities. (6) Attendance at conferences (2013): Among the 67 respondents, only four EMTs (6.0%) attended conferences for emergency medicine in 2013. The remainder (63, 94.0%) had not. Three of them attended once each; one had attended six times. (7) Inclination to attend emergency medical technique conferences: Among the 67 respondents, 58 EMTs (86.6%) were inclined to attend EMT conferences, while the remainder (9, 13.4%) did not. (8) Inclination to attend military emergency medical technique training courses: Among the 67 respondents, 49 EMTs (73.1%) intended to attend military EMT training courses, while the remainder (18, 26.9%) did not. (9) Dispatch to 119 Rescue Center for field experience: Among the 67 respondents, 53 EMTs (79.1%) wanted to gain field experience through 119 Rescue Center dispatch, while the remainder (14, 20.9%) did not. (10) Desirable duration of dispatch to 119 Rescue Center: Among the 50 respondents, 40 EMTs (80.0%) thought the desirable duration of dispatch to 119 Rescue Center would be under two weeks. Ten preferred longer periods (20.0%). (11) Inclination to have experience in 119 Rescue Center after hours: Among the 67 respondents, 24 EMTs (35.8%) were willing to gain field experience in 119 Rescue Center after hours (after 5 pm or weekends), while the remainder (43, 64.2%) did not. (12) What is needed for the role performance of military emergency medical technicians? Among the 67 respondents, 29 EMTs (43.3%) answered dispatch to 119 Rescue Center was necessary for the role performance of EMTs. Fixing the duty assignment as an EMT (27, 40.3%) followed. (13) What is needed for the capacity building of ROKAF EMTs? Among the 67 respondents, 50 EMTs (74.6%) answered dispatch to 119 Rescue Center was necessary to increase their professional competencies. Dispatch to emergency centers of civilian hospitals followed (13, 19.4%). Table 1. Thirteen questionnaire items dispatched via email to ROKAF emergency medical technicians surveyed in June 2014 In the Korean Armed Forces, several studies have been conducted on the efficient use of military EMTs [3]. Kim and Jang [4] said that the EMTs’ perceived job satisfaction was low (35.8%) and only 9.5% respondents answered that they knew their role and duty well. Park et al. [5] analyzed the structured questionnaire collected from military EMTs of Korean Army units and insisted it was urgent to provide medical equipment and supply them to guarantee emergency relief work. Recently, the Royal Centre for Defence Medicine in the United Kingdom quantified doctors’ contributions to the Medical Emergency Response Team-Enhanced. Surprisingly, the median time from take-off to arrival was 44 minutes. A doctor flew on the helicopter in 88% of missions. A doctor’s presence was not clinically beneficial in 77% of missions [6]. Comparing the mean arrival time of the United Kingdom team (44 minutes) and the South Korean team to the shooting rampage in the 22nd Division (over 3 hours), the Korean Armed Forces should improve delivery systems and attend to the education of the military EMTs. The Swedish Armed Forces examined how medics perceived their learning outcomes following military pre-hospital training and found that they learned medical care through interaction, action, and reflection. Interaction during the education period is important for learning. Action, being able to act in the field, is based on a drill in which the subject progresses from simple to complex procedures. Reflection, learning to help others, is important for confidence, which in turn creates preparedness, thereby making the knowledge meaningful [7]. Like the Swedish Armed Forces, military EMTs in Korea could act based on a drill. They want to be drilled in practical training by the civilian 119 rescue team. In Sudan, 37 military medics were trained as civilian pre-hospital care providers and the participants successfully completed an intensive 40-hour course consisting of didactic teaching sessions, small-group discussions, and practical skill stations. This improved their knowledge of subjects related to wound care, hemorrhage, and head trauma [8]. In our present study, more than half of the respondents answered that they taught their skills to colleagues in the last year; however, very few got a chance to manage real cases in the last 12 months. Although only a few attended conferences for emergency medicine in the last 12 months, their perceived educational needs were great. Most of them did want to gain field experience through 119 Rescue Center dispatch, even in their off duty time. Without clinical experience, they cannot play their role in emergencies. They should be dispatched to 119 Rescue Center or emergency centers of civilian hospitals for appropriate professional competence.

Solid state drives (SSDs) have higher bandwidth and lower access latency than hard disk drives (HDDs). Therefore, SSDs have been rapidly replacing HDDs. Many SSD manufactures produce their own SSDs. However, they do not open their SSD architecture and control firmware. As a result it is necessary to compare and analyze the performance of different kind of SSDs. A benchmark is used to analyze the storage device's performance. However, most benchmarks are targeted at HDDs. In this paper, we exploit the uFLIP benchmark which reflects flash device characteristics to analyze the SSD performance. Through this process, we have identified common SSD characteristics. Also, we have confirmed that a particular SSD shows strength at some situations.

In this paper, we first analyze how the characteristics of the GPU affect the performance of link-based similarity measures. Based on the analysis, we describe our strategies to improve the performance of link-based similarity measures on the GPU in detail. Finally, through extensive experiments, we evaluate the effectiveness of our strategies.