The structure and function of dietary proteins, as well as their subcellular prediction, are critical for designing and developing new drug compositions and understanding the pathophysiology of certain diseases. As a remedy, we provide a subcellular localization method based on feature fusion and clustering for dietary proteins. Additionally, an enhanced PseAAC (Pseudo-amino acid composition) method is suggested, which builds upon the conventional PseAAC. The study initially builds a novel model of representing the food protein sequence by integrating autocorrelation, chi density, and improved PseAAC to better convey information about the food protein sequence. After that, the dimensionality of the fused feature vectors is reduced by using principal component analysis. With prediction accuracies of 99.24% in the Gram-positive dataset and 95.33% in the Gram-negative dataset, respectively, the experimental findings demonstrate the practicability and efficacy of the proposed approach. This paper is basically exploring pseudo-amino acid composition of not any clinical aspect but exploring a pharmaceutical aspect for drug repositioning.
Bioinformatics and Healthcare Integration Disease prediction models have been revolutionized by Big Data. These models, which make use of extensive medical data, predict illnesses before symptoms appear. Deep neural networks are well-known for their ability to increase accuracy by extending the network's depth and modifying weights through gradient descent. Traditional approaches, however, are hindered by issues such as gradient instability and delayed training. As a substitute, the Broad Learning (BL) system is introduced, which avoids gradient descent in favor of quick reconstruction by incremental learning. However, BL has trouble extracting complicated features from medical data, which makes it perform poorly in cases involving complex healthcare. We suggest ABL, which combines the effectiveness of BL with the noise reduction of Denoising Auto Encoder (AE), to address this. Robust feature extraction is an area in which the hybrid model shines, especially in intricate medical environments. Accuracy of up to 98.50 % is achieved by remarkable results from validation using a variety of datasets. The ability of ABL to quickly adapt through incremental learning suggests that it may be used to forecast diseases in complicated healthcare contexts with agility and accuracy.
According to experts in neurology, brain tumours pose a serious risk to human health. The clinical identification and treatment of brain tumours rely heavily on accurate segmentation. The varied sizes, forms, and locations of brain tumours make accurate automated segmentation a formidable obstacle in the field of neuroscience. U-Net, with its computational intelligence and concise design, has lately been the go-to model for fixing medical picture segmentation issues. Problems with restricted local receptive fields, lost spatial information, and inadequate contextual information are still plaguing artificial intelligence. A convolutional neural network (CNN) and a Mel-spectrogram are the basis of this cough recognition technique. First, we combine the voice in a variety of intricate settings and improve the audio data. After that, we preprocess the data to make sure its length is consistent and create a Mel-spectrogram out of it. A novel model for brain tumor segmentation (BTS), Intelligence Cascade U-Net (ICU-Net), is proposed to address these issues. It is built on dynamic convolution and uses a non-local attention mechanism. In order to reconstruct more detailed spatial information on brain tumours, the principal design is a two-stage cascade of 3DU-Net. The paper's objective is to identify the best learnable parameters that will maximize the likelihood of the data. After the network's ability to gather long-distance dependencies for AI, Expectation-Maximization is applied to the cascade network's lateral connections, enabling it to leverage contextual data more effectively. Lastly, to enhance the network's ability to capture local characteristics, dynamic convolutions with local adaptive capabilities are used in place of the cascade network's standard convolutions. We compared our results to those of other typical methods and ran extensive testing utilising the publicly available BraTS 2019/2020 datasets. The suggested method performs well on tasks involving BTS, according to the experimental data. The Dice scores for tumor core (TC), complete tumor, and enhanced tumor segmentation BraTS 2019/2020 validation sets are 0.897/0.903, 0.826/0.828, and 0.781/0.786, respectively, indicating high performance in BTS.
In this paper, the new subclass S b , λ , δ , p n ( α ) of a linear differential operator's N λ , δ , p n f ( ζ ) associated with multivalent analytical function has been introduced. Further, the coefficient inequalities, extreme points for the extremal function, sharpness of the growth and distortion bounds, partial sums, starlikeness, and convexity of the subclass is investigated.
Emerging from the convergence of digital twin technology and the metaverse, consumer health (MCH) is witnessing a transformative shift. The amalgamation of bioinformatics with healthcare Big Data has ushered in a new era of disease prediction models that harness comprehensive medical data, enabling the anticipation of illnesses even before the onset of symptoms. In this model, deep neural networks stand out because they improve accuracy remarkably by increasing network depth and making weight changes using gradient descent. Nonetheless, traditional methods face their own set of challenges, including the issues of gradient instability and slow training. In this case, the Broad Learning System (BLS) stands out as a good alternative. It gets around the problems with gradient descent and lets you quickly rebuild a model through incremental learning. One problem with BLS is that it has trouble extracting complex features from complex medical data. This makes it less useful in a wide range of healthcare situations. In response to these challenges, we introduce DAE-BLS, a novel hybrid model that marries Denoising AutoEncoder (DAE) noise reduction with the efficiency of BLS. This hybrid approach excels in robust feature extraction, particularly within the intricate and multifaceted world of medical data. Validation using diverse datasets yields impressive results, with accuracies reaching as high as 98.50%. DAE-BLS's ability to rapidly adapt through incremental learning holds great promise for accurate and agile disease prediction, especially within the complex and dynamic healthcare scenarios of today.
Big Data , Technology , Humans , Computational Biology , Health Facilities , Neural Networks, Computer
BACKGROUND: Many complex factors contribute to suicide in older adults. The suicidal ideation that precedes suicide is an especially direct predictor of suicide. This study aimed to identify the effects between variables affecting suicidal ideation among older adults using the International Classification of Functioning, Disability and Health (ICF) model and understand the causal relationships to systematize complex factors. METHODS: This study used data from 9920 community-dwelling older adults who completed a national survey in 2020 to classify predictors of suicidal ideation (e.g., depression, subjective health status, sociodemographic factors, health factors, social support, instrumental activities of daily living (IADL), and social participation) by using the ICF model. To determine the causal relationship between variables, this study examined significance based on the critical ratio (C.R.) and squared multiple correlation (SMC) by using a path model. RESULTS: Gender, education level, economic level, age, IADL, relationship satisfaction with a child, depression, and the number of chronic diseases significantly affected suicidal ideation, while age, employment status, participation in social groups, formal and informal support, satisfaction with a friend/neighbor relationship, and subjective health status did not significantly influence it. Moreover, depression mediated the relationship between each of these variables and suicidal ideation. CONCLUSIONS: It was found that depression was the most direct and mediating factor in suicidal ideation among many factors affecting the suicidal ideation of community-dwelling older adults. Additional studies should be conducted to develop community-level strategies based on these factors and understand causal relationships.
A simplified mathematical model has been developed for understanding combined effects of surface roughness, viscosity variation and couple stresses on the squeeze film behaviour of a flat and a curved circular plate in the presence of transverse magnetic field. The Stokes (1966) couple stress fluid model is included to account for the couple stresses arising due to the presence of microstructure additives in the lubricant. In the context of Christensen's (1969) stochastic theory for the lubrication of rough surfaces, two types of one-dimensional roughness patterns (radial and azimuthal) are considered. The governing modified stochastic Reynolds type equations are derived for these roughness patterns. Expressions for the mean squeeze film characteristics are obtained. Numerical computations of the results show that the azimuthal roughness pattern on the curved circular and flat plate results in more pressure buildup whereas performance of the squeeze film suffers due to the radial roughness pattern. Further the Lorentz force characterized by the Hartmann number, couple stress parameter and viscosity variation parameter improve the performance of the squeeze film lubrication as compared to the classical case (Non-magnetic, Newtonian case and non-viscous case).
Objective: The Eastern Cooperative Oncology Group performance status (ECOG PS) is a widely recognized measure used to assess the functional abilities of cancer patients and predict their prognosis. It plays a crucial role in guiding treatment decisions made by physicians. This study aimed to build a stacking ensemble-based prognosis predictor model for predicting the ECOG PS of a liver cancer patient undergoing treatment. Methods: We used Light Gradient Boosting Machine (LightGBM) as the meta-model, and five base models, including Random Forest (RF), Extra Trees (ET), AdaBoost (Ada), Gradient Boosting Machine (GBM), and Extreme Gradient Boosting (XGBoost). After preprocessing the data and applying feature selection method, the stacking ensemble model was trained using 1622 liver cancer patients' data and 46 variables. We also integrated the stacking ensemble model with a LIME-based explainable model to obtain model prediction explainability. Results: According to the research, the best combination of the stacking ensemble model is ET + XGBoost + RF + GBM + Ada + LightGBM and achieved a ROC AUC of 0.9826 on the training set and 0.9675 on the test set. Conclusions: This explainable stacking ensemble model can become a helpful tool for objectively predicting ECOG PS in liver cancer patients and aiding healthcare practitioners to adapt their treatment approach more effectively.
Objective: This study identified major risk factors for depression in community diabetic patients using machine learning techniques and developed predictive models for predicting the high-risk group for depression in diabetic patients based on multiple risk factors. Methods: This study analyzed 26,829 adults living in the community who were diagnosed with diabetes by a doctor. The prevalence of a depressive disorder was the dependent variable in this study. This study developed a model for predicting diabetic depression using multiple logistic regression, which corrected all confounding factors in order to identify the relationship (influence) of predictive factors for diabetic depression by entering the top nine variables with high importance, which were identified in CatBoost. Results: The prevalence of depression was 22.4% (n = 6,001). This study calculated the importance of factors related to depression in diabetic patients living in South Korean community using CatBoost to find that the top nine variables with high importance were gender, smoking status, changes in drinking before and after the COVID-19 pandemic, changes in smoking before and after the COVID-19 pandemic, subjective health, concern about economic loss due to the COVID-19 pandemic, changes in sleeping hours due to the COVID-19 pandemic, economic activity, and the number of people you can ask for help in a disaster situation such as COVID-19 infection. Conclusion: It is necessary to identify the high-risk group for diabetes and depression at an early stage, while considering multiple risk factors, and to seek a personalized psychological support system at the primary medical level, which can improve their mental health.
COVID-19 , Diabetes Mellitus , Adult , Humans , Nomograms , COVID-19/epidemiology , Depression/epidemiology , Pandemics , Diabetes Mellitus/epidemiology , Machine Learning
Background: We systematically reviewed (evaluated methodological quality) meta-analysis studies on the suicidal ideation of South Koreans using a measurement tool to assess systematic reviews version 2 (AMSTAR-2) to present the ways for improving the quality of follow-up meta-analysis studies and suggest the direction of future studies. Methods: We analyzed 11 meta-analysis studies based on AMSTAR-2 criteria by collecting documents related to suicidal thoughts using seven electronic databases (DBPia, Scholar, KISS, KCI, RISS, KoreaEmbase, and National Assembly Electronic Library) from Jan 1, 2000 to Dec 3, 2022. Results: Among the 142 papers searched, we analyzed the final 11 selected studies. Not all analyzed meta-analysis studies conducted quality assessment and these studies omitted the list of excluded references and the adequacy of the literature search. Moreover, 54.5% of the analyzed studies (six out of eleven studies) did not present the effect of publication bias. Consequently, SOMETHING was critically low due to omissions in critical domains. Conclusion: In all 11 studies analyzed, 2 or more of 7 critical domains were omitted, and the quality level was confirmed to be critically low. Therefore, future meta-analysis studies on suicidal ideation will have to include quality assessment and improve the quality of meta-analysis, such as testing bias effects.
The intention of this work is to study a mathematical model for fractal-fractional tuberculosis and COVID-19 co-infection under the Atangana-Baleanu fractal-fractional operator. Firstly, we formulate the tuberculosis and COVID-19 co-infection model by considering the tuberculosis recovery individuals, the COVID-19 recovery individuals, and both disease recovery compartment in the proposed model. The fixed point approach is utilized to explore the existence and uniqueness of the solution in the suggested model. The stability analysis related to solve the Ulam-Hyers stability is also investigated. This paper is based on Lagrange's interpolation polynomial in the numerical scheme, which is validated through a specific case with a comparative numerical analysis for different values of the fractional and fractal orders.
COVID-19 , Coinfection , Humans , Fractals , Intention
Since the emergence of the Coronavirus disease (COVID-19) pandemic, the disease has affected more than 675 million people worldwide, including more than 6.87 million deaths. To mitigate the effects of this pandemic, many countries established control measures to contain its spread. Their riposte was based on a combination of pharmaceutical (vaccination) and non-pharmaceutical (such as facemask wearing, social distancing, and quarantine) measures. In this way, cross-sectional research was conducted in Algeria from 23 December 2021 to 12 March 2022 to investigate the effectiveness of preventative interventions in lowering COVID-19 infection and severity. More specifically, we investigated the link between mask-wearing and infection on one side, and the relationship between vaccination and the risk of hospitalization on the other. For this purpose, we used binary logistic regression modeling that allows learning the role of mask-wearing and vaccination in a heterogeneous society with respect to compliance with barrier measures. This study determined that wearing a mask is equally important for people of all ages. Further, findings revealed that the risk of infection was 0.79 times lower among those who were using masks (odds ratio (OR) = 0.79; confidence interval (CI) 95% = 0.668-0.936; p-value = 0.006). At the same time, vaccination is a necessary preventive measure as the risk of hospitalization increases with age. Compared with those who did not get vaccinated, those who got vaccinated were 0.429 times less likely to end up in the hospital (OR = 0.429; CI95% = 0.273-0.676; p < 0.0001). The model performance demonstrates significant relationships between the dependent and independent variables, with the absence of over-dispersion in both studied models, such as the Akaike Information Criterion (AIC) scores. These findings emphasize the significance of preventative measures and immunization in the battle against the COVID-19 pandemic.
This study aimed to test a predictive model for depression in older adults in the community after the COVID-19 pandemic and identify influencing factors using the International Classification of Functioning, Disability, and Health (ICF). The subjects of this study were 9920 older adults in South Korean local communities. The analysis results of path analysis and bootstrapping analysis revealed that subjective health status, instrumental activities of daily living (IADL), number of chronic diseases, social support satisfaction, household economic level, informal support, and participation in social groups were factors directly influencing depression, while formal support, age, gender, education level, employment status, and participation in social groups were factors indirectly affecting it. It will be needed to prepare measures to prevent depression in older adults during an infectious disease pandemic, such as the COVID-19 pandemic, based on the results of this study.
Objective: This study identified factors related to adolescent obesity during the COVID-19 pandemic by using machine learning techniques and developed a model for predicting high-risk obesity groups among South Korean adolescents based on the result. Materials and methods: This study analyzed 50,858 subjects (male: 26,535 subjects, and female: 24,323 subjects) between 12 and 18 years old. Outcome variables were classified into two classes (normal or obesity) based on body mass index (BMI). The explanatory variables included demographic factors, mental health factors, life habit factors, exercise factors, and academic factors. This study developed a model for predicting adolescent obesity by using multiple logistic regressions that corrected all confounding factors to understand the relationship between predictors for South Korean adolescent obesity by inputting the seven variables with the highest Shapley values found in categorical boosting (CatBoost). Results: In this study, the top seven variables with a high impact on model output (based on SHAP values in CatBoost) were gender, mean sitting hours per day, the number of days of conducting strength training in the past seven days, academic performance, the number of days of drinking soda in the past seven days, the number of days of conducting the moderate-intensity physical activity for 60 min or more per day in the past seven days, and subjective stress perception level. Conclusion: To prevent obesity in adolescents, it is required to detect adolescents vulnerable to obesity early and conduct monitoring continuously to manage their physical health.
Objective: This epidemiological study (1) identified factors associated with impaired fasting glucose using 3,019 subjects (≥30 years old and <60 years old) without diabetes mellitus from national survey data and (2) developed a nomogram that could predict groups vulnerable to impaired fasting glucose by using machine learning. Methods: This study analyzed 3,019 adults between 30 and 65 years old who completed blood tests, physical measurements, blood pressure measurements, and health surveys. Impaired fasting glucose, a dependent variable, was classified into normal blood glucose (glycated hemoglobin<5.7% and fasting blood glucose ≤ 100mg/dl) and impaired fasting glucose (glycated hemoglobin is 5.7-6.4% and fasting blood glucose is 100-125mg/dl). Explanatory variables included socio-demographic factors, health habit factors, anthropometric factors, dietary habit factors, and cardiovascular disease risk factors. This study developed a model for predicting impaired fasting glucose by using logistic nomogram and categorical boosting (CatBoost). Results: In this study, the top eight variables with a high impact on CatBoost model output were age, high cholesterol, WHtR, BMI, drinking more than one shot per month for the past year, marital status, hypertension, and smoking. Conclusion: It is necessary to improve lifestyle and continuously monitor subjects at the primary medical care level so that we can detect non-diabetics vulnerable to impaired fasting glucose living in the community at an early stage and manage their blood glucose.
Blood Glucose , Prediabetic State , Adult , Aged , Cholesterol , Fasting , Glycated Hemoglobin , Humans , Middle Aged , Prediabetic State/epidemiology , Prediabetic State/etiology , Republic of Korea/epidemiology , Risk Factors
Although the full vaccination rate of South Korea compared to other countries, concerns about the effectiveness of the vaccine are growing as new COVID variants such as Alpha, Beta, Gamma, Delta, and Omicron appear over time. In this study, we collected Twitter data in South Korea that contained keywords like vaccines after the outbreak of the Omicron variant from 27 November 2021 to 14 February 2022. First, we analyzed the relationship between potential keywords associated with vaccination after the appearance of the Omicron variant in Twitter using network analysis. Second, we developed an efficient model for predicting the emotion of speech regarding vaccination after the COVID-19 Omicron variant pandemic by using deep learning algorithms. We constructed sentiment analysis models regarding vaccination after the COVID-19 Omicron pandemic by using five algorithms [i.e., support vector machine (SVM), recurrent neural networks (RNNs), long short-term memory models (LSTMs), bidirectional encoder representations from transformers (BERT), and Korean BERT (KoBERT)]. The results confirmed that KoBERT showed the best performance (71%) in all predictive performance indicators (accuracy, precision, and F1 score). It is necessary to prepare measures to alleviate the negative factorss of the public about vaccination in the long-term pandemic situation and help the public recognize the efficacy and safety of vaccination by using big data based on the results of this study.
BACKGROUND: Although South Korea has developed and carried out evidence-based interventions and prevention programs to prevent depressive disorder in adolescents, the number of adolescents with depressive disorder has increased every year for the past 10 years. AIM: To develop a nomogram based on a naïve Bayesian algorithm by using epidemiological data on adolescents in South Korea and present baseline data for screening depressive disorder in adolescents. METHODS: Epidemiological data from 2438 subjects who completed a brief symptom inventory questionnaire were used to develop a model based on a Bayesian nomogram for predicting depressive disorder in adolescents. RESULTS: Physical symptoms, aggression, social withdrawal, attention, satisfaction with school life, mean sleeping hours, and conversation time with parents were influential factors on depressive disorder in adolescents. Among them, physical symptoms were the most influential. CONCLUSION: Active intervention by periodically checking the emotional state of adolescents and offering individual counseling and in-depth psychological examinations when necessary are required to mitigate depressive disorder in adolescents.
BACKGROUND: Efficiently detecting Parkinson's disease (PD) with dementia (PDD) as soon as possible is an important issue in geriatric medicine. AIM: To develop a model for predicting PDD based on various neuropsychological tests using data from a nationwide survey conducted by the Korean Centers for Disease Control and Prevention and to present baseline data for the early detection of PDD. METHODS: This study comprised 289 patients who were 60 years or older with PD [110 with PDD and 179 Parkinson's Disease-Mild Cognitive Impairment (PD-MCI)]. Regre-ssion with optimal scaling (ROS) was used to identify independent relationships between the neuropsychological test results and PDD. RESULTS: In the ROS analysis, Korean version of mini mental state ex-amination (MMSE) (KOREAN version of MMSE) (b = -0.52, SE = 0.16) and Hoehn and Yahr staging (b = 0.44, SE = 0.19) were significantly effective models for distinguishing PDD from PD-MCI (P < 0.05), even after adjusting for all of the Parkinson's motor symptom and neuropsychological test results. The optimal number of categories (scaling factors) for KOREAN version of MMSE and Hoehn and Yahr Scale was 10 and 7, respectively. CONCLUSION: The results of this study suggest that among the various neuropsychological tests conducted, the optimal classification scores for KOREAN version of MMSE and Hoehn and Yahr Scale could be utilized as an effective screening test for the early discrimination of PDD from PD-MCI.
Objective: This study developed a model to predict groups vulnerable to suicidal ideation after the declaration of the COVID-19 pandemic based on nomogram techniques targeting 54,948 adolescents who participated in a national survey in South Korea. Methods: This study developed a model to predict suicidal ideation by using logistic regression analysis. The model aimed to understand the relationship between predictors associated with the suicidal ideation of South Korean adolescents by using the top seven variables with the highest feature importance confirmed in XGBoost (extreme gradient boosting). The regression model was developed using a nomogram so that medical workers could easily interpret the probability of suicidal ideation and identify groups vulnerable to suicidal ideation. Results: This epidemiological study predicted that eighth graders who experienced depression in the past 12 months, had a lot of subjective stress, frequently felt lonely in the last 12 months, experienced much-worsened household economic status during the COVID-19 pandemic, and had poor academic performance were vulnerable to suicidal ideation. The results of 10-fold cross-validation revealed that the area under the curve (AUC) of the adolescent suicidal ideation prediction nomogram was 0.86, general accuracy was 0.89, precision was 0.87, recall was 0.89, and the F1-score was 0.88. Conclusion: It is required to recognize the seriousness of adolescent suicide and mental health after the onset of the COVID-19 pandemic and prepare a customized support system that considers the characteristics of persons at risk of suicide at the school or community level.
Objective: There are still not enough studies on the prediction of non-utilization of a complication test or a glycated hemoglobin test for preventing diabetes complications by using large-scale community-based big data. This study identified the ratio of not taking a diabetes complication test (fundus examination and microprotein urination test) among adult diabetic patients over 19 years using a national survey conducted in South Korea and developed a model for predicting the probability of not taking a diabetes complication test based on it. Methods: This study analyzed 25,811 subjects who responded that they had been diagnosed with diabetes by a doctor in the 2020 Community Health Survey. Outcome variables were defined as the utilization of the microprotein urination test and the fundus examination during the past year. This study developed a model for predicting the utilization of a diabetes complication test using logistic regression analysis and nomogram to understand the relationship of predictive factors on the utilization of a diabetes complication test. Results: The results of this study confirmed that age, education level, the recognition of own blood glucose level, current diabetes treatment, diabetes management education, not conducting the glycated hemoglobin test in the past year, smoking, single-person household, subjectively good health, and living in the rural area were independently related to the non-utilization of diabetes complication test after the COVID-19 pandemic. Conclusion: Additional longitudinal studies are required to confirm the causality of the non-utilization of diabetes complication screening tests.
COVID-19 , Diabetes Complications , Diabetes Mellitus , Adult , COVID-19/complications , COVID-19/epidemiology , Diabetes Complications/diagnosis , Diabetes Complications/epidemiology , Diabetes Mellitus/diagnosis , Diabetes Mellitus/epidemiology , Glycated Hemoglobin/analysis , Humans , Machine Learning , Pandemics
