Glu-Ensemble: An ensemble deep learning framework for blood glucose forecasting in type 2 diabetes patients.

Diabetes is a chronic metabolic disorder characterized by elevated blood glucose levels, posing significant health risks such as cardiovascular disease, and nerve, kidney, and eye damage. Effective management of blood glucose is essential for individuals with diabetes to mitigate these risks. This study introduces the Glu-Ensemble, a deep learning framework designed for precise blood glucose forecasting in patients with type 2 diabetes. Unlike other predictive models, Glu-Ensemble addresses challenges related to small sample sizes, data quality issues, reliance on strict statistical assumptions, and the complexity of models. It enhances prediction accuracy and model generalizability by utilizing larger datasets and reduces bias inherent in many predictive models. The framework's unified approach, as opposed to patient-specific models, eliminates the need for initial calibration time, facilitating immediate blood glucose predictions for new patients. The obtained results indicate that Glu-Ensemble surpasses traditional methods in accuracy, as measured by root mean square error, mean absolute error, and error grid analysis. The Glu-Ensemble framework emerges as a promising tool for blood glucose level prediction in type 2 diabetes patients, warranting further investigation in clinical settings for its practical application.

Impartial feature selection using multi-agent reinforcement learning for adverse glycemic event prediction.

We developed an attention model to predict future adverse glycemic events 30 min in advance based on the observation of past glycemic values over a 35 min period. The proposed model effectively encodes insulin administration and meal intake time using Time2Vec (T2V) for glucose prediction. The proposed impartial feature selection algorithm is designed to distribute rewards proportionally according to agent contributions. Agent contributions are calculated by a step-by-step negation of updated agents. Thus, the proposed feature selection algorithm optimizes features from electronic medical records to improve performance. For evaluation, we collected continuous glucose monitoring data from 102 patients with type 2 diabetes admitted to Cheonan Hospital, Soonchunhyang University. Using our proposed model, we achieved F1-scores of 89.0%, 60.6%, and 89.8% for normoglycemia, hypoglycemia, and hyperglycemia, respectively.

WBC YOLO-ViT: 2 Way - 2 stage white blood cell detection and classification with a combination of YOLOv5 and vision transformer.

Accurate detection and classification of white blood cells, otherwise known as leukocytes, play a critical role in diagnosing and monitoring various illnesses. However, conventional methods, such as manual classification by trained professionals, must be revised in terms of accuracy, efficiency, and potential bias. Moreover, applying deep learning techniques to detect and classify white blood cells using microscopic images is challenging owing to limited data, resolution noise, irregular shapes, and varying colors from different sources. This study presents a novel approach integrating object detection and classification for numerous type-white blood cell. We designed a 2-way approach to use two types of images: WBC and nucleus. YOLO (fast object detection) and ViT (powerful image representation capabilities) are effectively integrated into 16 classes. The proposed model demonstrates an exceptional 96.449% accuracy rate in classification.

Glucose Transformer: Forecasting Glucose Level and Events of Hyperglycemia and Hypoglycemia.

To avoid the adverse consequences from abrupt increases in blood glucose, diabetic inpatients should be closely monitored. Using blood glucose data from type 2 diabetes patients, we propose a deep learning model-based framework to forecast blood glucose levels. We used continuous glucose monitoring (CGM) data collected from inpatients with type 2 diabetes for a week. We adopted the Transformer model, commonly used in sequence data, to forecast the blood glucose level over time and detect hyperglycemia and hypoglycemia in advance. We expected the attention mechanism in Transformer to reveal a hint of hyperglycemia and hypoglycemia, and performed a comparative study to determine whether Transformer was effective in the classification and regression of glucose. Hyperglycemia and hypoglycemia rarely occur and this results in an imbalance in the classification. We built a data augmentation model using the generative adversarial network. Our contributions are as follows. First, we developed a deep learning framework utilizing the encoder part of Transformer to perform the regression and classification under a unified framework. Second, we adopted a data augmentation model using the generative adversarial network suitable for time-series data to solve the data imbalance problem and to improve performance. Third, we collected data for type 2 diabetic inpatients for mid-time. Finally, we incorporated transfer learning to improve the performance of regression and classification.

Intraoperative Hypotension Prediction Model Based on Systematic Feature Engineering and Machine Learning.

Arterial hypotension is associated with incidence of postoperative complications, such as myocardial infarction or acute kidney injury. Little research has been conducted for the real-time prediction of hypotension, even though many studies have been performed to investigate the factors which affect hypotension events. This forecasting problem is quite challenging compared to diagnosis that detects high-risk patients at current. The forecasting problem that specifies when events occur is more challenging than the forecasting problem that does not specify the event time. In this work, we challenge the forecasting problem in 5 min advance. For that, we aim to build a systematic feature engineering method that is applicable regardless of vital sign species, as well as a machine learning model based on these features for real-time predictions 5 min before hypotension. The proposed feature extraction model includes statistical analysis, peak analysis, change analysis, and frequency analysis. After applying feature engineering on invasive blood pressure (IBP), we build a random forest model to differentiate a hypotension event from other normal samples. Our model yields an accuracy of 0.974, a precision of 0.904, and a recall of 0.511 for predicting hypotensive events.

Transiently Observed Trace Albuminuria on Urine Dipstick Test Is Associated With All-Cause Death, Cardiovascular Death, and Incident Chronic Kidney Disease: A National Health Insurance Service-National Sample Cohort in Korea.

Introduction: Albuminuria is a well-known risk factor for end-stage kidney disease, all-cause mortality, and cardiovascular mortality, even when the albumin-to-creatinine ratio is <30 mg/g. However, the association between transiently observed trace albuminuria and these major adverse outcomes has not yet been reported. This study aimed to examine the effect of transient albuminuria on these major adverse outcomes using the National Health Insurance Service data in Korea. Methods and Results: The National Health Insurance Service-National Sample Cohort from Korea, followed from 2002 to 2015, consisted of 1,025,340 individuals, accounting for 2.2% of the total Korean population. We analyzed the effect of transient albuminuria on all-cause death, cardiovascular death, and incident chronic kidney disease (CKD) and compared it with the group without albuminuria. Among 1,025,340 individuals, 121,876 and 2,815 had transient albuminuria and no albuminuria, respectively. Adjusted hazard ratios of the transient albuminuria group for cardiovascular death and incident CKD were 1.76 (1.01-3.08) and 1.28 (1.15-1.43), respectively. There were significant differences in all-cause death, cardiovascular death, and incident CKD between the two groups after propensity score matching (p = 0.0037, p = 0.015, and p < 0.0001, respectively). Propensity score matching with bootstrapping showed that the hazard ratios of the transient albuminuria group for all-cause death and cardiovascular death were 1.39 (1.01-1.92) and 2.18 (1.08-5.98), respectively. Conclusions: In this nationwide, large-scale, retrospective cohort study, transient albuminuria was associated with all-cause death, cardiovascular death, and incident CKD, suggesting that transient albuminuria could be a risk marker for adverse outcomes in the future, and that its own subclinical phenotype could play an important role during the course of CKD.

Antimalarial Drug Predictions Using Molecular Descriptors and Machine Learning against Plasmodium Falciparum.

Malaria remains by far one of the most threatening and dangerous illnesses caused by the plasmodium falciparum parasite. Chloroquine (CQ) and first-line artemisinin-based combination treatment (ACT) have long been the drug of choice for the treatment and controlling of malaria; however, the emergence of CQ-resistant and artemisinin resistance parasites is now present in most areas where malaria is endemic. In this work, we developed five machine learning models to predict antimalarial bioactivities of a drug against plasmodium falciparum from the features (i.e., molecular descriptors values) obtained from PaDEL software from SMILES of compounds and compare the machine learning models by experiments with our collected data of 4794 instances. As a consequence, we found that three models amongst the five, namely artificial neural network (ANN), extreme gradient boost (XGB), and random forest (RF), outperform the others in terms of accuracy while observing that, using roughly a quarter of the promising descriptors picked by the feature selection algorithm, the five models achieved equivalent and comparable performance. Nevertheless, the contribution of all molecular descriptors in the models was investigated through the comparison of their rank values by the feature selection algorithm and found that the most potent and relevant descriptors which come from the 'Autocorrelation' module contributed more while the 'Atom type electrotopological state' contributed the least to the model.

Prediction of Postoperative Complications for Patients of End Stage Renal Disease.

End stage renal disease (ESRD) is the last stage of chronic kidney disease that requires dialysis or a kidney transplant to survive. Many studies reported a higher risk of mortality in ESRD patients compared with patients without ESRD. In this paper, we develop a model to predict postoperative complications, major cardiac event, for patients who underwent any type of surgery. We compare several widely-used machine learning models through experiments with our collected data yellow of size 3220, and achieved F1 score of 0.797 with the random forest model. Based on experimental results, we found that features related to operation (e.g., anesthesia time, operation time, crystal, and colloid) have the biggest impact on model performance, and also found the best combination of features. We believe that this study will allow physicians to provide more appropriate therapy to the ESRD patients by providing information on potential postoperative complications.

Developing an Individual Glucose Prediction Model Using Recurrent Neural Network.

In this study, we propose a personalized glucose prediction model using deep learning for hospitalized patients who experience Type-2 diabetes. We aim for our model to assist the medical personnel who check the blood glucose and control the amount of insulin doses. Herein, we employed a deep learning algorithm, especially a recurrent neural network (RNN), that consists of a sequence processing layer and a classification layer for the glucose prediction. We tested a simple RNN, gated recurrent unit (GRU), and long-short term memory (LSTM) and varied the architectures to determine the one with the best performance. For that, we collected data for a week using a continuous glucose monitoring device. Type-2 inpatients are usually experiencing bad health conditions and have a high variability of glucose level. However, there are few studies on the Type-2 glucose prediction model while many studies performed on Type-1 glucose prediction. This work has a contribution in that the proposed model exhibits a comparative performance to previous works on Type-1 patients. For 20 in-hospital patients, we achieved an average root mean squared error (RMSE) of 21.5 and an Mean absolute percentage error (MAPE) of 11.1%. The GRU with a single RNN layer and two dense layers was found to be sufficient to predict the glucose level. Moreover, to build a personalized model, at most, 50% of data are required for training.

Malware Detection of Hangul Word Processor Files Using Spatial Pyramid Average Pooling.

Malware detection of non-executables has recently been drawing much attention because ordinary users are vulnerable to such malware. Hangul Word Processor (HWP) is software for editing non-executable text files and is widely used in South Korea. New malware for HWP files continues to appear because of the circumstances between South Korea and North Korea. There have been various studies to solve this problem, but most of them are limited because they require a large amount of effort to define features based on expert knowledge. In this study, we designed a convolutional neural network to detect malware within HWP files. Our proposed model takes a raw byte stream as input and predicts whether it contains malicious actions or not. To incorporate highly variable lengths of HWP byte streams, we propose a new padding method and a spatial pyramid average pooling layer. We experimentally demonstrate that our model is not only effective, but also efficient.

Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension.

Hypotensive events in the initial stage of anesthesia can cause serious complications in the patients after surgery, which could be fatal. In this study, we intended to predict hypotension after tracheal intubation using machine learning and deep learning techniques after intubation one minute in advance. Meta learning models, such as random forest, extreme gradient boosting (Xgboost), and deep learning models, especially the convolutional neural network (CNN) model and the deep neural network (DNN), were trained to predict hypotension occurring between tracheal intubation and incision, using data from four minutes to one minute before tracheal intubation. Vital records and electronic health records (EHR) for 282 of 319 patients who underwent laparoscopic cholecystectomy from October 2018 to July 2019 were collected. Among the 282 patients, 151 developed post-induction hypotension. Our experiments had two scenarios: using raw vital records and feature engineering on vital records. The experiments on raw data showed that CNN had the best accuracy of 72.63%, followed by random forest (70.32%) and Xgboost (64.6%). The experiments on feature engineering showed that random forest combined with feature selection had the best accuracy of 74.89%, while CNN had a lower accuracy of 68.95% than that of the experiment on raw data. Our study is an extension of previous studies to detect hypotension before intubation with a one-minute advance. To improve accuracy, we built a model using state-of-art algorithms. We found that CNN had a good performance, but that random forest had a better performance when combined with feature selection. In addition, we found that the examination period (data period) is also important.

Development of a prediction model for hypotension after induction of anesthesia using machine learning.

Arterial hypotension during the early phase of anesthesia can lead to adverse outcomes such as a prolonged postoperative stay or even death. Predicting hypotension during anesthesia induction is complicated by its diverse causes. We investigated the feasibility of developing a machine-learning model to predict postinduction hypotension. Naïve Bayes, logistic regression, random forest, and artificial neural network models were trained to predict postinduction hypotension, occurring between tracheal intubation and incision, using data for the period from between the start of anesthesia induction and immediately before tracheal intubation obtained from an anesthesia monitor, a drug administration infusion pump, an anesthesia machine, and from patients' demographics, together with preexisting disease information from electronic health records. Among 222 patients, 126 developed postinduction hypotension. The random-forest model showed the best performance, with an area under the receiver operating characteristic curve of 0.842 (95% confidence interval [CI]: 0.736-0.948). This was higher than that for the Naïve Bayes (0.778; 95% CI: 0.65-0.898), logistic regression (0.756; 95% CI: 0.630-0.881), and artificial-neural-network (0.760; 95% CI: 0.640-0.880) models. The most important features affecting the accuracy of machine-learning prediction were a patient's lowest systolic blood pressure, lowest mean blood pressure, and mean systolic blood pressure before tracheal intubation. We found that machine-learning models using data obtained from various anesthesia machines between the start of anesthesia induction and immediately before tracheal intubation can predict hypotension occurring during the period between tracheal intubation and incision.

The Whole-Genome and Transcriptome of the Manila Clam (Ruditapes philippinarum).

The manila clam, Ruditapes philippinarum, is an important bivalve species in worldwide aquaculture including Korea. The aquaculture production of R. philippinarum is under threat from diverse environmental factors including viruses, microorganisms, parasites, and water conditions with subsequently declining production. In spite of its importance as a marine resource, the reference genome of R. philippinarum for comprehensive genetic studies is largely unexplored. Here, we report the de novo whole-genome and transcriptome assembly of R. philippinarum across three different tissues (foot, gill, and adductor muscle), and provide the basic data for advanced studies in selective breeding and disease control in order to obtain successful aquaculture systems. An approximately 2.56 Gb high quality whole-genome was assembled with various library construction methods. A total of 108,034 protein coding gene models were predicted and repetitive elements including simple sequence repeats and noncoding RNAs were identified to further understanding of the genetic background of R. philippinarum for genomics-assisted breeding. Comparative analysis with the bivalve marine invertebrates uncover that the gene family related to complement C1q was enriched. Furthermore, we performed transcriptome analysis with three different tissues in order to support genome annotation and then identified 41,275 transcripts which were annotated. The R. philippinarum genome resource will markedly advance a wide range of potential genetic studies, a reference genome for comparative analysis of bivalve species and unraveling mechanisms of biological processes in molluscs. We believe that the R. philippinarum genome will serve as an initial platform for breeding better-quality clams using a genomic approach.

Detecting and classifying method based on similarity matching of Android malware behavior with profile.

Mass-market mobile security threats have increased recently due to the growth of mobile technologies and the popularity of mobile devices. Accordingly, techniques have been introduced for identifying, classifying, and defending against mobile threats utilizing static, dynamic, on-device, and off-device techniques. Static techniques are easy to evade, while dynamic techniques are expensive. On-device techniques are evasion, while off-device techniques need being always online. To address some of those shortcomings, we introduce Andro-profiler, a hybrid behavior based analysis and classification system for mobile malware. Andro-profiler main goals are efficiency, scalability, and accuracy. For that, Andro-profiler classifies malware by exploiting the behavior profiling extracted from the integrated system logs including system calls. Andro-profiler executes a malicious application on an emulator in order to generate the integrated system logs, and creates human-readable behavior profiles by analyzing the integrated system logs. By comparing the behavior profile of malicious application with representative behavior profile for each malware family using a weighted similarity matching technique, Andro-profiler detects and classifies it into malware families. The experiment results demonstrate that Andro-profiler is scalable, performs well in detecting and classifying malware with accuracy greater than 98 %, outperforms the existing state-of-the-art work, and is capable of identifying 0-day mobile malware samples.

Epidemic model for information diffusion in web forums: experiments in marketing exchange and political dialog.

As social media has become more prevalent, its influence on business, politics, and society has become significant. Due to easy access and interaction between large numbers of users, information diffuses in an epidemic style on the web. Understanding the mechanisms of information diffusion through these new publication methods is important for political and marketing purposes. Among social media, web forums, where people in online communities disseminate and receive information, provide a good environment for examining information diffusion. In this paper, we model topic diffusion in web forums using the epidemiology model, the susceptible-infected-recovered (SIR) model, frequently used in previous research to analyze both disease outbreaks and knowledge diffusion. The model was evaluated on a large longitudinal dataset from the web forum of a major retail company and from a general political discussion forum. The fitting results showed that the SIR model is a plausible model to describe the diffusion process of a topic. This research shows that epidemic models can expand their application areas to topic discussion on the web, particularly social media such as web forums.

Complete mitochondrial genome of the Pacific cod, Gadus macrocephalus (Gadiformes, Gadidae).

The Pacific cod Gadus macrocephalus is a commercially important species belonging to the family Gadidae. In this study, we performed the first sequencing and assembly of the complete mitochondrial genome of G. macrocephalus. The complete mitochondrial genome is 16,567 bp long, consisting of 13 protein-coding genes, 22 tRNA genes, 2 rRNA genes, and a control region. It has the typical vertebrate mitochondrial gene arrangement. Phylogenetic analysis using the mitochondrial genomes of 15 species showed that G. macrocephalus clusters with G. ogac. This mitochondrial genome provides potentially important resources for performing population genetic analysis and addressing phylogenetic issues.

The complete mitochondrial genome of Gymnogobius heptacanthus (Perciformes, gobiidae).

Gymnogobius heptacanthus is a small intertidal species belonging to the family Gobiidae. Herein, we report the first sequencing and assembly of the complete mitochondrial genome of G. heptacanthus. The complete mitochondrial genome is 16,529 bp long and has the typical vertebrate mitochondrial gene arrangement, consisting of 13 protein-coding genes, 22 tRNA genes, 2 rRNA genes, and a control region. Phylogenetic analysis using mitochondrial genomes of 12 species showed that G. heptacanthus is clustered with G. urotaenia and G. petschiliensis and rooted with other Gobiidae species. This mitochondrial genome provides potentially important resources for addressing taxonomic issues and studying molecular evolution.

Reliability of the percent density in digital mammography with a semi-automated thresholding method.

PURPOSE: The reliability of the quantitative measurement of breast density with a semi-automated thresholding method (Cumulus™) has mainly been investigated with film mammograms. This study aimed to evaluate the intrarater reproducibility of percent density (PD) by Cumulus™ with digital mammograms. METHODS: This study included 1,496 craniocaudal digital mammograms from the unaffected breast of breast cancer patients. One rater reviewed each mammogram and estimated the PD using the Cumulus™ method. All images were reassessed by the same rater 1 month later without reference to the previously assigned values. The repeatability of the PD was evaluated by an intraclass correlation coefficient (ICC). All patients were grouped based on their body mass index (BMI), age, family history of breast cancer, breastfeeding history and breast area (calculated with Cumulus™), and subgroup analysis for the ICC of each group was performed. All patients were categorized by their Breast Imaging Reporting and Data System (BI-RADS) density pattern, and the mean and standard deviation of the PD by each BI-RADS categories were compared. RESULTS: The ICC for the PD was 0.94, indicating excellent repeatability. The discrepancy between the paired PD values ranged from 0 to 23.93, with an average of 3.90 (standard deviation=3.39). The subgroup ICCs for the PD ranged from 0.88 to 0.96, indicating excellent reliability in all subgroups regardless of patient variables. The ICCs of the PD for the high-risk (BI-RADS 3 and 4) and low-risk (BI-RADS 1 and 2) groups were 0.90 and 0.88, respectively. CONCLUSION: This study suggests that PD calculated with digital mammograms has an acceptable reliability regardless of patient age, BMI, family history of breast cancer, breastfeeding history, breast size, and BI-RADS density pattern.

Chitosan-hydroxycinnamic acid conjugates: preparation, antioxidant and antimicrobial activity.

In this study, the antioxidant and antimicrobial activities of chitosan-caffeic acid, chitosan-ferulic acid, and chitosan-sinapic acid conjugates with different grafting ratios were investigated. The synthesized chitosan-hydroxycinnamic acid conjugates were verified by performing (1)H NMR and differential scanning calorimetry analysis. The antioxidant activities of the conjugates were increased compared to the unmodified chitosan, by 1.79-fold to 5.05-fold (2,2-diphenyl-1-picrylhydrazyl scavenging assay), 2.44-fold to 4.12-fold (hydrogen peroxide scavenging assay), 1.34-fold to 3.35-fold (ABTS(+) radical scavenging assay), and also exhibited an increased reducing power. The conjugates also showed excellent lipid peroxidation inhibition abilities in a linoleic acid emulsion system. The conjugates exhibited antimicrobial activity against 15 clinical isolates, two standard methicillin-resistant Staphylococcus aureus (MRSA) and three standard methicillin-susceptible S. aureus strains, as well as eight foodborne pathogens. Additionally, the conjugates showed no cytotoxic activity towards human Chang liver and mouse macrophage RAW264.7 cells.

Genetic association of the gene encoding RPGRIP1L with susceptibility to vascular dementia.

A previous genome-wide association study (GWAS) failed to discover any nucleotide sequence variant associated with susceptibility to vascular dementia (VaD) and remained a problem of false negatives produced by a low statistical power. The current study was conducted to identify such potential false negatives and to provide comprehensive evidence for the most plausible predisposing genetic factor using large-scale Korean cohorts. We identified the gene encoding retinitis pigmentosa GTPase regulator-interacting protein 1-like (RPGRIP1L) with multiple nucleotide variants associated with susceptibility to VaD by a modest significant threshold (P<10(-4)). Genetic associations were intensively examined with its sequence variants using 207 VaD patients and 207 age- and gender-matched control subjects. Genetic association analysis with dense variants in the region associated with VaD revealed 3 variants (P<0.0017) in strong linkage. Further analysis with VaD-related phenotypes using Korean Association REsource (KARE) cohort data showed that the region of the gene was associated with alanine aminotransferase (ALT), aspartate aminotransferase (AST), and blood pressure (BP) (P<7.6×10(-4)). The current study provided the first evidence of the association between RPGRIP1L gene and susceptibility of VaD. Functional studies are needed to understand underlying biological mechanism of the genetic association.