Screening the General Population for Non-Alcoholic Fatty Liver Disease: Model Development and Validation.

BACKGROUND: The prevalence of non-alcoholic fatty liver disease (NAFLD) is increasing worldwide. Screening the general population for this may help to select appropriate diagnostic and preventive measures before disease progression. AIMS: We aimed to develop a screening method to identify patients with NAFLD in the general population. METHODS: We analyzed cross-sectional data from a large Japanese study of NAFLD. Principal component analysis was used to analyze the data. Candidate predictors were patients' demographic, clinical, and laboratory characteristics. The resulting model was externally validated using three data sets from different populations. RESULTS: Of 15,464 (54.5% men) included patients, 2,741 (17.7%) had NAFLD as determined by ultrasonography. An index was calculated as the arithmetic mean of the scaled body mass index and serum triglyceride levels for both men and women. The area under the receiver operating characteristic curve, sensitivity, specificity, and false positive rate were 0.875, 0.824, 0.770, and 17.6%, respectively. The mean index values were significantly different between the patients with and without non-alcoholic fatty liver disease (p <0.001). The odds ratio of the index cutoff was 15.6 (95% confidence interval [CI]:14.05, 17.39). The model yielded areas under the curve of 0.828, 0.851, and 0.836 for a Chinese (N = 2,319), an Iranian (N = 2,160), and a Brazilian (N = 45,029) data set, respectively. CONCLUSIONS: The proposed composite index demonstrated high performance and generalizability, suggesting its potential use as a screening tool for NAFLD in the general population.

Prognostic Clinical Phenotypes of Patients with Acute Decompensated Heart Failure.

INTRODUCTION: Acute decompensated heart failure (AHF) is a clinical syndrome with a poor prognosis. AIM: This study was conducted to identify clusters of inpatients with acute decompensated heart failure that shared similarities in their clinical features. METHODS: We analyzed data from a cohort of patients with acute decompensated heart failure hospitalized between February 2013 and January 2017 in a Department of Cardiology. Patients were clustered using factorial analysis of mixed data. The clusters (phenotypes) were then compared using log-rank tests and profiled using a logistic model. In total, 458 patients (255; 55.7% male) with a mean (SD) age of 72.7 (11.1) years were included in the analytic dataset. The demographic, clinical, and laboratory features were included in the cluster analysis. RESULTS: The two clusters were significantly different in terms of time to mortality and re-hospitalization (all P < 0.001). Cluster profiling yielded an accurate discriminating model (AUC = 0.934). Typically, high-risk patients were elderly females with a lower estimated glomerular filtration rate and hemoglobin on admission compared to the low-risk phenotype. Moreover, the high-risk phenotype had a higher likelihood of diabetes type 2, transient ischemic attack/cerebrovascular accident, previous heart failure or ischemic heart disease, and a higher serum potassium concentration on admission. Patients with the high-risk phenotype were of higher New York Heart Association functional classes and more positive in their medication history. CONCLUSIONS: There are two phenotypes among patients with decompensated heart failure, high-risk and low-risk for mortality and re-hospitalization. They can be distinguished by easy-to-measure patients' characteristics.

The importance of predictors for in-hospital COVID-19 mortality changes over one month.

BACKGROUND: Risk stratification enables care providers to make the proper clinical decision for the management of patients with COVID-19 infection. We aimed to explore changes in the importance of predictors for inpatient mortality of COVID-19 over one month. METHODS: This research was a secondary analysis of data from in-hospital patients with COVID-19 infection. Individuals were admitted to four hospitals, New York, USA. Based on the length of hospital stay, 4370 patients were categorized into three mutually exclusive interval groups, day 1, day 2-7, and day 8-28. We measured changes in the importance of twelve confirmed predictors for mortality over one month, using principal component analysis. RESULTS: On the first day of admission, there was a higher risk for organ dysfunction, particularly in elderly patients. On day 1, serum aspartate aminotransferase and sodium were also associated with an increased risk of mortality, while normal troponin opposes in-hospital death. With time, the importance of high aspartate aminotransferase and sodium concentrations decreases, while the variable quality of high troponin levels increases. Our study suggested the importance of maintaining normal blood pressure early in the management of patients. High serum concentrations of creatinine and C-reactive protein remain poor prognostic factors throughout the 28 days. The association of age with mortality increases with the length of hospital stay. CONCLUSION: The importance of some patients' characteristics changes with the length of hospital stay. This should be considered in developing and deploying predictive models and the management of patients with COVID-19 infection.

Development and validation of a clinical model for predicting the severity of carpal tunnel syndrome.

OBJECTIVES: Pain, discomfort, and cost may result in incomplete or inconclusive electrodiagnostic studies to assess the severity of carpal tunnel syndrome. We aimed to develop a clinical instrument for stratifying patients based on easy-to-measure variables to assess carpal tunnel syndrome severity. METHODS: We performed a secondary analysis of data from patients diagnosed with a diagnosis of carpal tunnel syndrome using a factor analysis of mixed data. In total, 1037 patients (405; 39.1% male) with a mean (SD) age of 58.0 (10.8) years were included. For each patient, demographic information, physical examination findings, ultrasonographic findings, and the severity of the syndrome based on electrodiagnostic studies were recorded. RESULTS: We devised a composite index incorporating a pain numeric rating scale (NRS) rated from 0 (no pain at all) to 10 (the worst pain ever possible), presence of thenar muscle weakness or atrophy (TW), cross-sectional area (CSA) of the median nerve (mm2), and occurrence of nocturnal pain (NP). The composite index was calculated as [scale(NRS)+scale(CSA)+NP+TW]/4, where both NP and TW are binary features (0 or 1). The overall accuracy and area under the curve of the index for stratifying the syndrome severity were 0.85 and 0.71, respectively (Cohen's Kappa = 0.51, McNemar's test P = 0.249). The composite index increased pretest probability by 1.6, 1.8, and 3.3 times with positive likelihood ratios of 3.3, 2.5, and 13.5, and false-positive rates of 26.6, 17.6, and 4.8% for mild, moderate, and severe syndrome, respectively. The index thresholds for mild, moderate, and severe carpal tunnel syndrome were <0.8, ≥0.8 to <1.1, and ≥1.1, respectively. CONCLUSION: Using a composite index, patients with carpal tunnel syndrome can be categorized for the severity of the syndrome before carrying out electrodiagnostic studies.

Application of novel artificial bee colony optimized ANN and data preprocessing techniques for monthly streamflow estimation.

Streamflow estimation is important in hydrology, especially in drought and flood-prone areas. Accurate estimation of streamflow values is crucial for the sustainable management of water resources, the development of early warning systems for disasters, and for various applications such as irrigation, hydropower production, dam sizing, and siltation management. This study developed the ANN algorithm by optimizing with an artificial bee colony (ABC). Then, the ABC-ANN hybrid model, which was established, was combined with different signal decomposition techniques to evaluate its performance in streamflow estimation in the East Black Sea Region, Türkiye. For this purpose, the lagged streamflow values were divided into subcomponents using the local mean decomposition (LMD) with the empirical envelope and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) signal decomposition techniques presented to the ABC-ANN algorithm. Thus, the success of the novel hybrid LMD-ABC-ANN and CEEMDAN-ABC-ANN approaches in streamflow prediction was evaluated. The outputs are reliable strategies and resources for water resource planners and policymakers.

The association of stroke risk factors with the future thickness of carotid atherosclerotic plaques.

OBJECTIVES: An advancing atherosclerotic plaque is a risk factor for stroke. We conducted this study to assess the relationship between risk factors of stroke with changing in the thickness of carotid plaques thickness evident on sonography. METHODS: We carried out a secondary analysis of data from a study on carotid bifurcation plaques. Data were collected in the sonography laboratories of two university hospitals. In total, 564 (240; 42.6% men) patients with atherosclerotic plaques in the carotid bifurcation and internal carotid artery with stenosis ≥ 30% evident on duplex sonography were included. We developed machine learning models using an extreme gradient boosting algorithm with Shapley additive explanation method to find important risk factors and their interactions. The outcome was a change in the carotid plaque thickness after 36 months, and the predictors were initial plaque thickness and the risk factors of stroke. RESULTS: Two regression models were developed for left and right carotid arteries. The R-squared values were 0.964 for the left, and 0.993 for the right model. Overall, the three top features were BMI, age, and initial plaque thickness for both left and right plaques. However, the risk factors of stroke showed stronger interaction in predicting plaque thickening of the left carotid more than the right carotid artery. DISCUSSION: The effect of each predictor on plaque thickness is complicated by interactions with other risk factors, particularly for the left carotid artery. The side of carotid artery involvement should be considered for stroke prevention.

The long-term prognostic value provided by Coronary CT angiography.

BACKGROUND: Risk-stratification of patients has a major role in the prevention and treatment of cardiovascular disease. The aim was to find the most informative predictors of cardiovascular events in patients undergoing Coronary CT Angiography. METHODS: We carried out a secondary analysis of a large registry dataset. The included population comprises adults aged 18 or older who underwent Coronary CT Angiography of 64-detector rows or greater. We clustered patients based on their characteristics and compared the risk for poor clinical outcomes between the two clusters. RESULTS: There were two clusters of patients having different risks for all-cause death, myocardial infarction, and late revascularization [hazard ratios (95%CI) = 2.28 (2.02, 2.57), 1.63 (1.40, 1.89), and 2.46 (2.1, 2.88), all P < 0.001]. The severity of stenosis in the left main coronary artery adjusted for age and sex was the most significant predictor of the high-risk cluster [adjusted odds ratio (95%CI) = 3.35 (2.98, 3.77), P < 0.001]. The severity of stenosis in the first obtuse marginal branch of the left circumflex, distal left circumflex, distal left anterior descending, posterior descending, the first diagonal branch of the left anterior descending, and proximal right coronary artery were important as well (all adjusted odds ratios ≥ 2.52). Cluster profiling showed a higher performance for CT Angiography features (sensitivity = 97.4%, specificity = 85.7%, C-statistic = 98.7%) than calcium, Framingham, and Duke scores in identifying high-risk patients (C-statistic = 82.1, 77.0, and 88.2%, respectively). CONCLUSION: Coronary CT Angiography can accurately risk-stratify patients concerning poor clinical outcomes.

Neuropsychological features in children and adults with congenital heart disease: an exploratory data analysis.

We aimed to recognize clinically meaningful patterns among patients with congenital heart disease to support clinical decision-making and better classification in practice. This research was a secondary analysis of data from the Congenital Heart Disease Genetic Network Study conducted from December 2010 to November 2014 in the United States. The analytic dataset included 6002 patients ≥1 year of age with non-syndromic congenital heart disease. For each patient, features included demographic, clinical, maternal and paternal characteristics. We clustered patients to identify subgroups that shared similarities in their clinical features. The performance of the clustering algorithm was evaluated with a random forest. Next, we used the apriori algorithm to generate clinical rules from patients' characteristics. The clustering algorithm identified two discernible groups of patients. The two classes of patients were different in maternal diabetes and in neuropsychological indicators [Accuracy (95% CI) = 97.1% (96.2, 97.8), area under the ROC curve = 96.8%]. Our rule extraction suggested the presence of clinical pictures with high lift values among patients with maternal diabetes or with seizure, depression, attention-deficit hyperactivity disorder, anxiety, developmental delay, learning disability and speech problem. Beyond the age of 1 year, maternal diabetes and neuropsychological characteristics identify two clusters of patients with congenital heart disease. These characteristics have the potential of being incorporated into the current systems for the classification of congenital heart disease.

IHACRES, GR4J and MISD-based multi conceptual-machine learning approach for rainfall-runoff modeling.

As a complex hydrological problem, rainfall-runoff (RR) modeling is of importance in runoff studies, water supply, irrigation issues, and environmental management. Among the variety of approaches for RR modeling, conceptual approaches use physical concepts and are appropriate methods for representation of the physics of the problem while may fail in competition with their advanced alternatives. Contrarily, machine learning approaches for RR modeling provide high computation ability however, they are based on the data characteristics and the physics of the problem cannot be completely understood. For the sake of overcoming the aforementioned deficiencies, this study coupled conceptual and machine learning approaches to establish a robust and more reliable RR model. To this end, three hydrological process-based models namely: IHACRES, GR4J, and MISD are applied for runoff simulating in a snow-covered basin in Switzerland and then, conceptual models' outcomes together with more hydro-meteorological variables were incorporated into the model structure to construct multilayer perceptron (MLP) and support vector machine (SVM) models. At the final stage of the modeling procedure, the data fusion machine learning approach was implemented through using the outcomes of MLP and SVM models to develop two evolutionary models of fusion MLP and hybrid MLP-whale optimization algorithm (MLP-WOA). As a result of conceptual models, the IHACRES-based model better simulated the RR process in comparison to the GR4J, and MISD models. The effect of incorporating meteorological variables into the coupled hydrological process-based and machine learning models was also investigated where precipitation, wind speed, relative humidity, temperature and snow depth were added separately to each hydrological model. It is found that incorporating meteorological variables into the hydrological models increased the accuracy of the models in runoff simulation. Three different learning phases were successfully applied in the current study for improving runoff peak simulation accuracy. This study proved that phase one (only hydrological model) has a big error while phase three (coupling hydrological model by machine learning model) gave a minimum error in runoff estimation in a snow-covered catchment. The IHACRES-based MLP-WOA model with RMSE of 8.49 m3/s improved the performance of the ordinary IHACRES model by a factor of almost 27%. It can be considered as a satisfactory achievement in this study for runoff estimation through applying coupled conceptual-ML hydrological models. Recommended methodology in this study for RR modeling may motivate its application in alternative hydrological problems.

Improving generalisation capability of artificial intelligence-based solar radiation estimator models using a bio-inspired optimisation algorithm and multi-model approach.

One way of reducing environmental pollution is to reduce our dependence on fossil fuels by replacing them with solar radiation (Rs), which is one of the main sources of clean and renewable energy. In this study, daily Rs values at seven meteorological stations in Iran (Ahvaz, Isfahan, Kermanshah, Mashhad, Bandar Abbas, Kerman and Tabriz) over 2010-2019 were estimated using empirical models, support vector machine (SVM), SVM coupled with cuckoo search algorithm (SVM-CSA) and multi-model approach in the form of two structures. In structure 1, data from each station were divided into training and testing sets. In structure 2, data from the former four stations were used for model training, and those from the latter three stations were used to test the models. The results showed that using meteorological parameters improved estimation accuracy compared with the use of geographical parameters for both SVM and SVM-CSA models. Coupling the CSA to SVM did improve the accuracy of radiation estimates, reducing RMSE by up to 38% (Kermanshah station) and 36% (Tabriz station) for the first structure and about 42.4% (Tabriz station) for the second. Performance analysis of the models over three intervals including, the first, middle and last third of measured radiation values at each station showed that for both structures (except at Tabriz station), the best model performance in under- and over-estimation sets of radiation values was obtained, respectively, in the first third interval (first structure, Mashhad station, RMSE = 28.39 J.cm-2.day-1) and the last third interval (first structure, Bandar Abbas station, RMSE = 12.23 J.cm-2.day-1). Determining the effects of climate change on Rs estimation and using remotely sensed data as inputs of the models could be considered as future works.

Improving streamflow simulation by combining hydrological process-driven and artificial intelligence-based models.

Accurate and timely monitoring of streamflow and its variation is crucial for water resources management in watersheds. This study aimed at evaluating the performance of two process-driven conceptual rainfall-runoff models (HBV: Hydrologiska Byråns Vattenbalansavdelning, and NRECA: Non Recorded Catchment Areas) and seven hybrid models based on three artificial intelligence (AI) methods (adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM), and group method of data handling (GMDH)) in simulating streamflow in four river basins in Indonesia. HBV and NRECA were developed based on precipitation data. Various combinations of 1-month lagged precipitation data together with outputs of HBV and NRECA were used for developing ANFIS and SVM models, and the best results of ANFIS and SVM formed the inputs to GMDH. Results showed that AI-based hybrid models have generally led to more accurate streamflow estimates compared with HBV and NRECA, and the GMDH model had the best performance at Cipero, Kedungdowo, Notog, and Sukowati stations, with RMSEs of 12.21, 6.07, 20.35, and 24.2 m3 s-1, respectively. More accurate estimation of peak values in training set at Cipero and Sukowati stations, and in both training and testing sets at Kedungdowo station was another advantage of GMDH. Hybrid models based on AI methods can be suitable alternatives to hydrological models, particularly in watersheds where there is a lack of measured data (e.g. climatic parameters, land cover-plant growth data, soil data, stream conditions, and properties of groundwater aquifers), provided that appropriate inputs are used.

Machine learning algorithm-based risk assessment of riparian wetlands in Padma River Basin of Northwest Bangladesh.

Wetland risk assessment is a global concern especially in developing countries like Bangladesh. The present study explored the spatiotemporal dynamics of wetlands, prediction of wetland risk assessment. The wetland risk assessment was predicted based on ten selected parameters, such as fragmentation probability, distance to road, and settlement. We used M5P, random forest (RF), reduced error pruning tree (REPTree), and support vector machine (SVM) machine learning techniques for wetland risk assessment. The results showed that wetland areas at present are declining less than one-third of those in 1988 due to the construction of the dam at Farakka, which is situated at the upstream of the Padma River. The distance to the river and built-up area are the two most contributing drivers influencing the wetland risk assessment based on information gain ratio (InGR). The prediction results of machine learning models showed 64.48% of area by M5P, 61.75% of area by RF, 62.18% of area by REPTree, and 55.74% of area by SVM have been predicted as the high and very high-risk zones. The results of accuracy assessment showed that the RF outperformed than other models (area under curve: 0.83), followed by the SVM, M5P, and REPTree. Degradation of wetlands explored in this study demonstrated the negative effects on biodiversity. Therefore, to conserve and protect the wetlands, continuous monitoring of wetlands using high resolution satellite images, feeding with the ecological flow, confining built up area and agricultural expansion towards wetlands, and new wetland creation is essential for wetland management.

A new hybrid model based on relevance vector machine with flower pollination algorithm for phycocyanin pigment concentration estimation.

Precise monitoring of cyanobacteria concentration in water resources is a daunting task. The development of reliable tools to monitor this contamination is an important research topic in water resources management. Indirect methods such as chlorophyll-a determination, cell counting, and toxin measurement of the cyanobacteria are tedious, cumbersome, and often lead to inaccurate results. The quantity of phycocyanin (PC) pigment is considered more appropriate for cyanobacteria monitoring. Traditional approaches for PC estimation are time-consuming, expensive, and require high expertise. Recently, some studies have proposed the application of artificial intelligence (AI) techniques to predict the amount of PC concentration. Nonetheless, most of these researches are limited to standalone modeling schemas such as artificial neural network (ANN), multilayer perceptron (MLP), and support vector machine (SVM). The independent schema provides imprecise results when faced with highly nonlinear systems and data uncertainties resulting from environmental disturbances. To alleviate the limitations of the existing models, this study proposes the first application of a hybrid AI model that integrates the potentials of relevance vector machine (RVM) and flower pollination algorithm (RVM-FPA) to predict the PC concentration in water resources. The performance of the hybrid model is compared with the standalone RVM model. The prediction performance of the proposed models was evaluated at two stations (stations 508 and 478) using different statistical and graphical performance evaluation methods. The results showed that the hybrid models exhibited higher performance at both stations compared to the standalone RVM model. The proposed hybrid RVM-FPA can therefore serve as a reliable predictive tool for PC concentration in water resources.

Letter to the editor "comparing artificial intelligence techniques for chlorophyll-a prediction in US lakes".

The discussers wish to thank the authors of the original paper for investigating the comparing accuracy of artificial intelligence techniques trained to predict chlorophyll-a in US lakes. In the original paper (Luo et al., Environ Sci Pollut Res 26: 30524-30532, 2019), four data-driven models were established to estimate the chlorophyll-a (CHLA) values in natural and man-made lakes. Three of these models are adaptive neuro-fuzzy inference system (ANFIS)-based, while one is (artificial neural network) ANN-based. The authors used total phosphorus (TP), total nitrogen (TN), turbidity (TB), and the Secchi depth (SD) as independent variables in order to predict CHLA. They stated that ANFIS with subtractive clustering method (ANFIS_SC) models and multilayer perceptron neural network (MLPNN) models gives higher accuracy in the prediction of CHLA values for natural lakes and man-made lakes, respectively. In this letter, some of the missing points in the original publication, which is important for the estimation and comparison of CHLA values in two different lake sets that differ according to the type of formation, are highlighted. In addition, several points are mentioned in order to make these points more clarified for potential readers.

Application of hybrid ANN-whale optimization model in evaluation of the field capacity and the permanent wilting point of the soils.

Field capacity (FC) and permanent wilting point (PWP) are two important properties of the soil when the soil moisture is concerned. Since the determination of these parameters is expensive and time-consuming, this study aims to develop and evaluate a new hybrid of artificial neural network model coupled with a whale optimization algorithm (ANN-WOA) as a meta-heuristic optimization tool in defining the FC and the PWP at the basin scale. The simulated results were also compared with other core optimization models of ANN and multilinear regression (MLR). For this aim, a set of 217 soil samples were taken from different regions located across the West and East Azerbaijan provinces in Iran, partially covering four important basins of Lake Urmia, Caspian Sea, Persian Gulf-Oman Sea, and Central-Basin of Iran. Taken samples included portion of clay, sand, and silt together with organic matter, which were used as independent variables to define the FC and the PWP. A 80-20 portion of the randomly selected independent and dependent variable sets were used in calibration and validation of the predefined models. The most accurate predictions for the FC and PWP at the selected stations were obtained by the hybrid ANN-WOA models, and evaluation criteria at the validation phases were obtained as 2.87%, 0.92, and 2.11% respectively for RMSE, R2, and RRMSE for the FC, and 1.78%, 0.92, and 10.02% respectively for RMSE, R2, and RRMSE for the PWP. It is concluded that the organic matter is the most important variable in prediction of FC and PWP, while the proposed ANN-WOA model is an efficient approach in defining the FC and the PWP at the basin scale.

Smart article: application of intelligent platforms in next generation biomedical publications.

Production of scientific data has been accelerated exponentially though ease of access to the required knowledge is still challenging. Hence, the emergence of new frameworks to allow more efficient storage of information would be beneficial. Attaining intelligent platforms enable the smart article to serve as a forum for exchanging idea among experts of academic disciplines for a rapid and efficient scientific discourse.

Immunity to Diphtheria and Tetanus in Army Personnel and Adult Civilians in Mashhad, Iran.

This study aimed to investigate serologic immunity to diphtheria and tetanus in army personnel and a sample population of adult civilians in Mashhad, Iran. Army personnel (n = 180) and civilians (n = 83) who presented at Mashhad army hospital participated in this study. Diphtheria and tetanus antitoxin levels were determined by enzyme-linked immunosorbent assay. Approximately 77% and 94% of army personnel aged 18-34 years had at least basic protection against diphtheria (antitoxin level ≥0.1 IU/mL) and tetanus (antitoxin level >0.1 IU/mL), respectively. For civilians in this age group, the proportions were 76% for both diseases. Antitoxin levels waned with age. Thus, participants older than 50 years had lower immunity; this decrease in immunity was more pronounced for tetanus than for diphtheria in both army personnel and civilians. For both diseases, geometric mean antitoxin titers and the proportion of participants with at least basic protection were higher in subjects with a history of vaccination in the last 10 years (P < 0.001), higher in men than women, and in army personnel than civilians in each age group. Young army personnel and civilians (18-34 years old) had adequate immunity to diphtheria and tetanus. However, the large number of susceptible older adults (>50 years old) calls for improved booster vaccination protocols.