Biochemical Test Data Research Articles

Multimodal ischemic stroke recurrence prediction model based on the capsule neural network and support vector machine.

Ischemic stroke (IS) has a high recurrence rate. Machine learning (ML) models have been developed based on single-modal biochemical tests, and imaging data have been used to predict stroke recurrence. However, the prediction accuracy of these models is not sufficiently high. Therefore, this study aimed to collect biochemical detection and magnetic resonance imaging (MRI) data to establish a dataset and propose a high-performance heterogeneous multimodal IS recurrence prediction model based on deep learning. This is a retrospective cohort study. Data were retrospectively collected from 634 IS patients in Zhuhai, China, a 12-month follow-up was conducted to determine stroke recurrence. We propose the ischemic stroke multi-group learning (ISGL) model, an integrated model for predicting the recurrence risk of multimodal IS in patients, based on a capsule neural network and a linear support vector machine (SVM). Two capsule neural network prediction models based on T1 and T2 signals in the MRI data and a SVM prediction model based on biochemical test data were established. Finally, a vote was conducted on the final judgment of the integrated model. The ISGL model was compared with 6 classical ML and deep learning models: k-nearest neighbors, SVM, logistic regression, random forest, eXtreme Gradient Boosting, and visual geometry group. The results revealed that the accuracy, specificity, sensitivity and the area under the curve of the ISGL model were 95%, 96%, 94%, and 95%, respectively. Among the comparison models, the visual geometry group method exhibited the best performance, but it much lower than those of the ISGL model. Analysis of the importance of biochemical test data revealed that low-density lipoprotein, smoking, and heart disease history were the positively correlated factors, and total cholesterol, high-density lipoprotein, and diabetes were and the negatively correlated factors. This study proposes the ISGL model can be used simultaneously with MRI and biochemical data to predict IS recurrence. This combination resulted in higher rate of performance than that of the other ML models. Additionally, this study found related risk factors affected recurrence, which can be used to intervene in high-risk patients' recurrence as early as possible and promote the development of secondary prevention of stroke.

Developing predictive precision medicine models by exploiting real-world data using machine learning methods

Computational Medicine encompasses the application of Statistical Machine Learning and Artificial Intelligence methods on several traditional medical approaches, including biochemical testing which is extremely valuable both for early disease prognosis and long-term individual monitoring, as it can provide important information about a person's health status. However, using Statistical Machine Learning and Artificial Intelligence algorithms to analyze biochemical test data from Electronic Health Records requires several preparatory steps, such as data manipulation and standardization. This study presents a novel approach for utilizing Electronic Health Records from large, real-world databases to develop predictive precision medicine models by exploiting Artificial Intelligence. Furthermore, to demonstrate the effectiveness of this approach, we compare the performance of various traditional Statistical Machine Learning and Deep Learning algorithms in predicting individuals' future biochemical test outcomes. Specifically, using data from a large real-world database, we exploit a longitudinal format of the data in order to predict the future values of 15 biochemical tests and identify individuals at high risk. The proposed approach and the extensive model comparison contribute to the personalized approach that modern medicine aims to achieve.

An Evaluation of the Efficacy of Machine Learning in Predicting Thyrotoxicosis and Hypothyroidism: A Comparative Assessment of Biochemical Test Parameters Used in Different Health Checkups.

Objective This study assessed the efficacy of machine learning in predicting thyrotoxicosis and hypothyroidism [thyroid-stimulating hormone >10.0 mIU/L] by leveraging age and sex as variables and integrating biochemical test parameters used by the Japan Society of Health Evaluation and Promotion (JHEP) and the Japan Society of Ningen Dock (JND). Methods Our study included 20,653 untreated patients with Graves' disease, 3,435 untreated patients with painless thyroiditis, 4,266 healthy individuals, and 18,937 untreated patients with Hashimoto's thyroiditis. Machine learning was conducted using Prediction One on three distinct datasets: the Ito dataset (age, sex, and 30 blood tests and biochemical test data), the JHEP dataset (age, sex, and total protein,total bilirubin, aspartate aminotransferase (AST), alanine aminotransferase (ALT), gamma-glutamyl transpeptidase (γGTP), alkaline phosphatase, creatinine (CRE), uric acid (UA), and T-Cho test data), and the JND dataset (age, sex, and AST, ALT, γGTP, CRE, and UA test data). Results The results for distinguishing thyrotoxicosis patients from the healthy control group showed that the JHEP dataset yielded substantial discriminative capacity with an area under the curve (AUC) of 0.966, sensitivity of 92.2%, specificity of 89.1%, and accuracy of 91.7%. The JND dataset displayed similar robustness, with an AUC of 0.948, sensitivity of 92.0%, specificity of 81.3%, and accuracy of 90.4%. Differentiating hypothyroid patients from the healthy control group yielded similarly robust performances, with the JHEP dataset yielding AUC, sensitivity, specificity, and accuracy values of 0.864, 84.2%, 72.1%, and 77.4%, respectively, and the JND dataset yielding values of 0.840, 83.2%, 67.2%, and 74.3%, respectively. Conclusion Machine learning is a potent screening tool for thyrotoxicosis and hypothyroidism.

Common risk factors for dental caries and impaired glucose regulation in Guangxi, China.

To assess the prevalence of caries and impaired glucose regulation (IGR) and try to investigate their common risk factors among adult residents in Guangxi province. A cross-sectional study was conducted on a sample of 2993 adults from five different areas of Guangxi province. The sociodemographic data, history of personal habits such as diet and physical activities, physical measurements, oral examination results and biochemical laboratory test data were collected to establish a database and prepare a sound research model. Chi-square test and multiple logistic regression were used to analyse the risk factors for dental caries and IGR. The prevalence rate for caries was 85.9%, and the mean DMFT score was 7.35. In multiple logistic regression, after adjustment, education level, occupation, daily consumption of vegetables, weekly consumption of carbonated beverages and weekly exercise were associated with caries (odds ratio [OR]: 2.10, OR: 1.80, OR: 1.40, OR: 2.45, OR: 2.38). The prevalence of IGR was 33.5%, and after adjustment, results showed that occupation, body mass index, waist circumference, systolic blood pressure, diastolic blood pressure, high-density lipoprotein-C levels and low-density lipoprotein-C levels were significantly associated with IGR (OR: 0.80, OR: 1.70, OR: 1.56, OR: 1.88, OR: 1.60, OR: 1.43, OR: 1.48). The strength of association between caries/IGR and risk factors was a weak association or moderate association. We have not found common risk factors between dental caries and IGR. Therefore, further studies are needed to explore these common risk factors to prevent caries and IGR.

Cognitive status of hospitalized therapeutic elderly patients

Relevance. In connection with the trend toward an increase in life expectancy and aging of the population, the issue of timely detection and treatment of geriatric disorders in elderly and senile patients becomes relevant. The aim of the study is to analyze cognitive impairment in hospitalized elderly and senile patients.Materials and methods. The study involved 93 patients older than 75 years, namely 63 women (80,2±5,0 years) and 30 men (80,2±6,4 years). All patients underwent a brief geriatric examination. The probability of frailty syndrome was assessed using the "Age is not a barrier" questionnaire, the risk of falls was assessed using the Morse scale. Cognitive status was determined using the MINI-COG questionnaire and the Mini-Mental State Examination (MMSE) scale. The data of biochemical blood tests (creatinine, uric acid, glucose, total cholesterol and lipid spectrum, K, Na) were also taken into account.Results. Normal cognitive status was recorded in women 2,5 times more often than in men. Patients with dementia were more likely to be obese than those without dementia (70% versus 35%; χ2=4,46; p=0,035). Cognitive impairment was accompanied by a decrease in physical functioning: the risk of falls on the Morse scale in the group of patients with dementia was 25% (p=0,038) higher, and the score on the "Age is not a barrier" test was 45% (p=0,009) worse than in patients without dementia. Patients with dementia tended to hyperuricemia and hypokalemia. Spearman's correlation analysis revealed inverse relationships between MMSE scores and the presence of arterial hypertension (r=–0,43; p<0,05) and type 2 diabetes (r=–0,33; p<0,05), with physical functioning ("Age is not a barrier": r=–0,49; p<0,05 / Morse: r=–0,41; p<0,05), with uric acid level (r=–0,61; p<0,05) and creatinine (r=–0,37; p<0,05). The presence of arterial hypertension and diabetes mellitus was combined with a more pronounced decrease in cognitive potential.Conclusions. The share of elderly patients reached 80% of all hospitalized persons. Dementia is 25% more common in men than in women. The presence of arterial hypertension, type 2 diabetes, and obesity increased the risk of dementia. The presence of dementia limits the physical functioning of patients by 45% and increases the risk of falls by 25%.

Role of perfusion computed tomography for diagnostic intermediate stages of fibrosis in diffuse liver diseases: prospective study

INTRODUCTION: Despite the wide availability of the use of ultrasonic elastography to assess fibrosis in patients with diffuse liver diseases, this method didn’t have a high specificity for diagnosing intermediate stages of fibrosis.OBJECTIVE: To evaluate the diagnostic effectiveness of perfusion computed tomography (PCT) for detecting intermediate stages of fibrosis in patients with diffuse liver diseases.MATERIALS AND METHODS: PCT of the liver was performed in 73 patients (37 men, 36 women, mean age 47.2±4.4 years). All patients underwent a biochemical blood test, ultrasound elastography, PCT, based on the obtained biochemical blood test and instrumental data, the examined patients were divided into three groups depending on diffuse liver disease: hepatitis (n=25), cirrhosis (n=26), non-alcoholic inflammatory liver disease (n=22). Statistics: The results were processed using the Statistica 10.0 for Windows software package. Identification of the relationship between two quantitative variables that do not obey the normal distribution law was carried out using the Spearman rank correlation coefficient. To assess the diagnostic efficiency of perfusion parameters in patients with DLD, an ROC-analysis (Receiver Operating Characteristic Analysis) was performed. In all statistical analysis procedures, changes were considered statistically significant at a significance level of p<0.05. RESULTS: BV correlated in all three groups of diseases with the elastography in patients with viral hepatitis — (r=–0.5; p><0.04), in patients with alcoholic cirrhosis (r=0.66; p><0.02), in patients with non-alcoholic inflammatory liver disease (r=–0.55; p><0.02). In patients with alcoholic hepatitis — correlation between HAF and elastography index (r=0.98; p><0.001), with viral hepatitis — HAF and elastography index (r=0.66; p><0.01). MTT was statistically correlated with elastography index in patients in the alcoholic cirrhosis group (r=0.78; p><0.006). The BF had the highest diagnostic effectiveness for differentiating F1 and F2 fibrosis in patients with diffuse liver diseases (p><0.0001). DISCUSSION: PCT is able to differentiate between minimal and intermediate fibrosis, which accompany not only hepatitis, but also non-alcoholic fatty liver disease, whose diagnosis is very relevant, and the use of ultrasound elastography is limited. CONCLUSION: The BF promotes to the differentiation of intermediate stages of fibrosis, and in combination with ultrasonic elastography can provide a promising direction for the dynamic monitoring of the parenchyma in patients with diffuse liver diseases.> p<0.05.RESULTS: BV correlated in all three groups of diseases with the elastography in patients with viral hepatitis — (r=–0.5; p<0.04), in patients with alcoholic cirrhosis (r=0.66; p><0.02), in patients with non-alcoholic inflammatory liver disease (r=–0.55; p<0.02). ><0.02). In patients with alcoholic hepatitis — correlation between HAF and elastography index (r=0.98; p<0.001), with viral hepatitis — HAF and elastography index (r=0.66; p><0.01). MTT was statistically correlated with elastography index in patients in the alcoholic cirrhosis group (r=0.78; p<0.006). The BF had the highest diagnostic effectiveness for differentiating F1 and F2 fibrosis in patients with diffuse liver diseases (p><0.0001). >p<0.006). The BF had the highest diagnostic effectiveness for differentiating F1 and F2 fibrosis in patients with diffuse liver diseases (p<0.0001). ><0.0001).DISCUSSION: PCT is able to differentiate between minimal and intermediate fibrosis, which accompany not only hepatitis, but also non-alcoholic fatty liver disease, whose diagnosis is very relevant, and the use of ultrasound elastography is limited.CONCLUSION: The BF promotes to the differentiation of intermediate stages of fibrosis, and in combination with ultrasonic elastography can provide a promising direction for the dynamic monitoring of the parenchyma in patients with diffuse liver diseases.

Assessing efficacy and safety of iron (III) hydroxide oligoisomaltosate in reproductive-age women with iron deficiency anemia

Aim: to demonstrate efficacy and safety of iron (III) hydroxide oligoisomaltosate in patients with iron deficiency. Materials and Methods. An observational cohort study was conducted: 31 patients were examined – 10 puerpera patients, 13 pregnant women, 8 gynecological patients suffering from iron deficiency anemia, stage 1–3. After further examination (biochemical blood test – ferritin, iron, latent iron binding capacity, total calcium, inorganic phosphorus, transferrin, C-reactive protein), therapy with "Monofer" (iron (III) hydroxide oligoisomaltosate) was performed. Four weeks after the final drug administration, the efficacy and patient satisfaction were monitored. Results. During the examination, significant changes in the following parameters were found: erythrocyte count increased after therapy by 1.3-fold, hemoglobin – by 26.5 g/L, hematocrit – by 0.58 % (p = 0.00). Biochemical blood test data also showed positive dynamics: ferritin was higher by 216.21 ng/ml, latent iron binding capacity – lower by 30.73 µmol/l, transferrin – lower by 1.17 g/L, iron level – higher by 6.87 µmol/l, modestly increased total calcium – by 0.14 mmol/l, and inorganic phosphorus – by 0.1 mmol/l. Patients surveyed according to the Likert scale showed a high degree of satisfaction with treatment. No adverse effects (AE) and Serious Adverse Effects (SAE) occurred during the study. Conclusion. A significant increase in the parameters of the qualitative and quantitative composition of blood cell count and biochemical parameters has been achieved. Posttransfusion hypophosphatemia and hypocalcemia were not observed in the studied patients. High satisfaction with the treatment and drug safety in patients were noted.

Distribution of water sectors in patients in chronic critical illness: Early rehabilitation stage

BACKGROUND: Fluid therapy in the intensive care unit is not only one of the most common components of therapy but also one of the most controversial and widely discussed. The choice of volume and type of infusion is a multifactorial issue. Currently, the search continues for a convenient non-invasive method that can be used to assess the water composition of the patients body.
 AIM: To analyze the distribution of fluid sectors in patients with chronic critical illness using bioimpedance with standard fluid therapy.
 MATERIALS AND METHODS: The study included 63 patients with chronic critical illness (CCI) after brain damage (men, n=28; women, n=35; average age, 5419 years). According to nosology, 22 patients had ischemic stroke; 17, traumatic brain injury; 14, hemorrhagic stroke; 7, condition after brain surgery; and 2, post-hypoxic conditions. The study was conducted in the morning before breakfast using the analyzer of bioimpedance metabolic processes and body composition ABC-02 Medass. A total of 140 measurements were conducted.
 RESULTS: In most cases, the volume of the total body water (TBW) in patients was within the age and sex norm (78.6%); however, the volume of extracellular water (ECW) reached normal values only in 45.7%. Moreover, both indicators were simultaneously within the normal range only in 44.3%. In addition, TBW and ECW did not coincide at 35.7%. The most common option was an increase in ECW while maintaining a normal TBW (24.3%). When conducting a correlation analysis of TBW and ECW indicators with biochemical blood test data (a decrease in the total protein level and albumin level), the strength of the relationship between the correlation coefficients of the samples on the Chaddock scale turned out to be very weak for all options considered.
 CONCLUSIONS: In patients in CCI after brain damage, there may be an accumulation of water in the extracellular space without visible edema in 50% of the patients, whereas the TBW indicator is within the age and sex norm in 24.3%. This indicator does not depend on either the level of hypoproteinemia and hypoalbuminemia.

Lactobacillus delbrueckii subsp. bulgaricus strain TCI904 reduces body weight gain, modulates immune response, improves metabolism and anxiety in high fat diet-induced obese mice

The multiple probiotic characteristics of strain TCI904 isolated in this study from natural fermented milk were investigated using a mouse model. TCI904 was identified as Lactobacillus delbrueckii subsp. bulgaricu (LDB), a well-known lactic acid starter bacterium found in yogurt. TCI904 exhibited an outstanding pancreatic lipase inhibition activity among several strains of lactic acid bacteria in vitro. Its in vivo effects were further studied. In a comparison of mice fed a high-fat diet (HFD) and those fed a HFD combined with TCI904 for 9 weeks, differences were observed in various aspects of health, and the adverse effects of a HFD were prevented in the latter group. TCI904 effectively prevented fat and body weight accumulation without reducing food intake; it also modulated innate immunity and increased the level of IgA in feces, reversing the increased blood sugar and insulin levels and attenuated the hyperlipidemia caused by a HFD. Based on biochemical test data, compared with the HFD group, a HFD combined with TCI904 induced significant lowering of insulin resistance indicator, homeostasis model assessment-insulin resistance (HOMA-IR) and atherogenic indices of plasma (AIP), the atherogenic coefficient (AC) and cardiac risk ratio (CRR) and increased the cardioprotective index (CPI). In addition, the administration of TCI904 alleviated mood disorders caused by a HFD. Taking the recommended human dose of TCI904 did not affect the liver or kidney function, indicating that TCI904 has sufficient in vivo safety. Taken together, the results of the present study contributed towards validation of the probiotic benefits of lactic acid starter microflora. Orally taken TCI904 exhibited positive immune- and metabolic-modulating, and anxiolytic properties, especially in HFD-induced obesity.

Morphological and biochemical changes in blood parameters in cats with infectious peritonitis

Feline infectious peritonitis is a feline disease, the causative agent of which is a mutant coronavirus, which leads to the death of young animals. Presently, this pathology is considered incurable, and therefore it requires a detailed study. The purpose of this study was to establish the features of clinical manifestation and haematological parameters in cats with infectious peritonitis. This paper presents the results of a clinical and laboratory study of 12 cats aged from 6 months to 3 years who were diagnosed with effusive and dry infectious peritonitis. Clinical, laboratory, and visual research methods were used. Laboratory analysis included a study of morphological and biochemical parameters of blood, cytological examination of effusion from the abdominal and pleural cavities, and a Rivalta test. As a result of cytological examination of effusion from these cavities, a high concentration of cells, macrophage accumulation, neutrophil phagocytosis, and red blood cells were detected in the entire field of view. It was found that the predictive value of the Rivalta test for feline infectious peritonitis is 62.5%. According to haematological examination, all sick animals were diagnosed with anaemia, lymphopenia, hypoalbuminemia, hyperglobulinemia, hyperbilirubinemia, increased activity of relative liver- specific enzymes (aspartate aminotransferase, alkaline phosphatase). Trobmocytopenia was observed in two animals, and an increase in blood markers of the functional state of the kidneys (creatinine, urea) was found in one cat. The serum albumin/globulin ratio should also be considered an important diagnostic indicator. Thus, with feline infectious peritonitis, this indicator should be < 0.4. In 11 sick cats, this ratio was characterized by values below 0.4, and in one animal this indicator was 0.46. In general, the obtained data of morphological and biochemical blood tests are not specific for feline infectious peritonitis, and therefore the authors of this paper recommend their comprehensive investigation for diagnostic purposes. An objective assessment of the available methods of laboratory diagnostics will contribute to the creation of a diagnostic protocol for feline infectious peritonitis

Development and validation of a RASS-related nomogram to predict the in-hospital mortality of neurocritical patients: a retrospective analysis based on the MIMIC-IV clinical database

Background: Richmond agitation-sedation scale (RASS) is a simple and widely used tool for evaluating sedation and agitation in adult ICU patients. Early deep sedation has been shown to be an important independent predictor of death, however, studies on the role of RASS in the prognostic assessment of neurocritical patients are lacking. The purpose of this study was to investigate the relationship between RASS and in-hospital mortality in neurocritical patients, and to develop and validate an effective predictive model based on this. Methods: This was a retrospective study of neurocritical patients from a large clinical database. A total of 2651 patients were collected, including general demographic characteristics, past medical history, biochemical test data and physical examination within 24 hours of admission, and related medical records. Univariate and multivariate logistic regression analyses were used to screen out significant variables. Finally, 11 significant predictors were included into the logistic regression to establish the nomogram. Results: The area under the curve (AUC) of the nomogram was 0.9087(0.8950-0.9224) and the corrected c index was 0.9043, which gave the model better discriminatory ability compared with critical care related scales, such as SOFA and SAPSII scores. Besides, tools including calibration curve, decision curve analysis (DCA), and clinical impact curve (CIC) were used to verify that the model had good discrimination, calibration, and clinical applicability. Conclusions: RASS score was an independent prognostic predictor of in-hospital death in neurocritical patients, and patients who are deeply sedated have a worse prognosis. RASS-related nomogram could be applied to predict the prognosis of neurocritical patients and to take effective intervention measures in early stage.

Association between Selenium Status and Chronic Kidney Disease in Middle-Aged and Older Chinese Based on CHNS Data.

Background: The association between selenium and chronic kidney disease (CKD) remains controversial. Population studies with large samples facilitate the reliability of conclusions. Objective: In this study, we aimed to describe the prevalence of a CKD association with selenium intake in middle-aged and older Chinese. Methods: Data for this study were obtained from the China Health and Nutrition Survey (CHNS). A total of 5381 participants (aged ≥ 45) with biochemical test data were included in the study. Logistic regression models were used to examine the association between diet selenium intake (quartile) and the prevalence of CKD. Results: A total of 942 (17.01%) participants had CKD. The prevalence of CKD was 23.33%, 20.32%, 14.98%, and 9.25% among participants with average selenium intakes of 21.5 ± 4.82, 33.1 ± 2.79, 43.8 ± 3.70, and 67.0 ± 13.97 µg/day, respectively. In the fully adjusted model (Model 3), across the quartiles of selenium intake, the ORs for the prevalence of CKD were 1.00, 1.09 (95% CI 0.69–1.73), 0.82 (95% CI 0.49–1.38), and 0.43 (95% CI 0.22–0.85). The protein intake had a certain diagnostic significance for the selenium intake. Conclusions: An adequate selenium intake may have a positive effect on CKD. The influence of individual weight and location on the effect of selenium on CKD needs to be further explored.

Identification of Prognostic Factors in Patients With Streptococcus Bloodstream Infection.

AimThe purpose of this study was to explore prognostic factors of bloodstream infections (BSIs), a common severe infection and a major cause of mortality worldwide, so as to construct a prognosis model of patients with BSI.Materials and MethodsClinical and biochemical test data were obtained retrospectively from the medical records of 562 patients with BSI who had been treated at a single center; the end point was 60 days of all-cause death. The chi-square test was used to compare the mortality of patients grouped by the types of antibiotic treatment. The logistic regression analysis was adopted to identify prognostic factors; the Kaplan–Meier survival curve and log-rank test were conducted to compare the survival rate of patients with different prognostic factors; the receiver operating characteristic (ROC) curve was used to estimate the predictive value of different prognostic factors.ResultsOf the 562 patients, 455 survived (80.96%), and 107 died (19.04%). The mortality rate of patients treated with a combination of antibiotics (25.40%) was higher than that treated with a single antibiotic (15.82%). Univariate analysis identified 19 prognostic factors for patients with BSI, including gender, age, diabetes, malignant tumor (non-blood system), total hospitalization time, alanine aminotransferase, aspartate aminotransferase, total protein, albumin, total bilirubin, direct bilirubin, creatinine, ratio of granulocytes, fibrinogen, D-dimer, platelet, C-reactive protein, shock, and respiratory failure (P < 0.05). Multivariate analysis indicated that albumin (odds ratio [OR] = 0.94, 95% confidence interval [CI]: 0.89–0.99), fibrinogen (OR = 0.61, 95%CI: 0.46–0.82), shock (OR = 16.61, 95%CI: 7.00–39.41), and respiratory failure (OR = 47.53, 95%CI: 19.93–133.64) were independent factors. The combination of four indicators demonstrated a favorable predictive value for the 60-day outcome of patients with BSI, with an area under the ROC of 0.96 (95%CI: 0.94–0.99), sensitivity of 90.65%, specificity of 94.95%, and accuracy of 94.13%.ConclusionsShock, respiratory failure, albumin, and fibrinogen are potential independent prognostic factors for 60-day mortality.

Data Mining Techniques for Iraqi Biochemical Dataset Analysis

This research aims to analyze and simulate biochemical real test data for uncovering the relationships among the tests, and how each of them impacts others. The data were acquired from Iraqi private biochemical laboratory. However, these data have many dimensions with a high rate of null values, and big patient numbers. Then, several experiments have been applied on these data beginning with unsupervised techniques such as hierarchical clustering, and k-means, but the results were not clear. Then the preprocessing step performed, to make the dataset analyzable by supervised techniques such as Linear Discriminant Analysis (LDA), Classification And Regression Tree (CART), Logistic Regression (LR), K-Nearest Neighbor (K-NN), Naïve Bays (NB), and Support Vector Machine (SVM) techniques. CART gives clear results with high accuracy between the six supervised algorithms. It is worth noting that the preprocessing steps take remarkable efforts to handle this type of data, since its pure data set has so many null values of a ratio 94.8%, then it becomes 0% after achieving the preprocessing steps. Then, in order to apply CART algorithm, several determined tests were assumed as classes. The decision to select the tests which had been assumed as classes were depending on their acquired accuracy. Consequently, enabling the physicians to trace and connect the tests result with each other, which extends its impact on patients’ health.

DIAGNOSTIC ROLE OF DIFFUSION-WEIGHTED IMAGE OF THE LIVER WITH MAGNETIC RESONANCE IMAGING IN PREDICTING ABSTINENCE DISORDERS IN PATIENTS WITH ALCOHOLIC LIVER DISEASE

Objective. To assess the diagnostic role of diffusion-weighted images of the liver with magnetic resonance imaging in predicting abstinence disorders in patients with alcoholic liver disease.&#x0D; Methods. A total of 122 patients with ALD aged 48±5.4 years were examined. The survey algorithm we used included: performing liver DWI with MRI (n=122) with b-value values of 100/600/1000, ultrasound of abdominal organs with clinical elastography – 97 (80%) patients. Trepan liver biopsy was chosen as a reference method (n=64).&#x0D; Results. The patients were monitored for 2.5 years. The terms of follow-up were selected individually, depending on the results of clinical and laboratory research methods. A high correlation was established (r=0.879), when comparing clinical elastography and quantitative indicators of DWI of the liver, at admission and during dynamic observation of patients, also at the middle level, the data obtained correlated with the results of trephine biopsy of the liver (r=0.721). After 3 months, 6 (15%) of 40 patients showed normalization of biochemical blood test parameters with no diffusion restriction according to the results of DWI of the liver. Based on the results obtained, a high correlation was noted between changes in the biochemical blood test and MRI data in the DWI mode. After 9 months of follow-up, according to DWI data, 34 patients showed persistence of cytolysis syndrome and limited diffusion on DWI of the liver. After collecting an additional history and clarifying the details of the lifestyle of the patients' relatives, it was found that these patients continued to consume alcoholic beverages against the background of the received treatment, which was manifested by the presence of diffusion restriction on MRI in the DWI mode, which was a magnetic resonance sign of the presence of inflammatory processes in the structure of the parenchyma liver. After 12 months, positive dynamics – the absence of diffusion restriction according to the results of DWI of the liver was noted in 34 patients, which indicates the effectiveness of using the qualitative characteristics of DWI of the liver to assess the violation of the abstinence regimen (AUROC=0.906 (95% CI 0.872-0.916)). But in 16 (13%) patients from this group, changes in the biochemical blood test were noted, but no diffusion limitation was noted according to the DWI of the liver. Patients (n=16) underwent a correction of the received treatment – after 1 month there was a positive trend. There was a correlation of quantitative parameters of DWI of the liver with clinical forms of ALD, regardless of the presence or absence of diffusion restriction (r=0.936). Next, we assessed the prognostic and diagnostic significance of the developed criteria for DWI of the liver for patients with ALD on admission. The results of the study indicated the effectiveness of using the diagnostic and prognostic model of MRI in the DWI mode for patients with ALD on admission and in dynamic observation.&#x0D; Conclusions. 1. A high correlation was found between the quantitative parameters of DWI of the liver and clinical elastography (r=0.879) at admission and follow-up. Average correlation relationship of DWI of the liver with the results of trephine biopsy of the liver in patients with ALD on admission and follow-up (r=0.721).&#x0D; &#x0D; There was a high correlation between the results of DWI of the liver on MRI with the data of clinical and laboratory parameters in dynamic observation of patients with ALD: no diffusion limitation – positive (r=0.887); yes – negative (r=0.887).&#x0D; The high prognostic and diagnostic value of DWI of the liver in assessing the violation of the abstinence regimen in patients with ALD was established (AUROC=0.906 (95% CI 0.872-0.916)).&#x0D; Prognostic and diagnostic criteria for liver DWI on MRI in patients with ALD at admission: qualitative characteristic – AUROC=0.846 (95% CI 0.811-0.862), quantitative characteristic – AUROC=0.909 (95% CI 0.879-0.912); with dynamic observation: qualitative characteristic – AUROC=0.949 (95% CI 0.907-0.965), quantitative characteristic – AUROC=0.917 (95% CI 0.876-0.932).&#x0D;

The effect of a Forest Biomass Supplement on Morphophysiological Parameters of Calves

Breeding, preserving, and successfully rearing young animals resistant to various environmental influences is one of the main parameters of effective livestock management. The study aimed to study the indicators of natural resistance and the growth rate of calves under the influence of dietary supplements. The studies were carried out on four groups of black-and-white calves, 10 heads each, at the age of 2-5 months. The dairy calves of the control group were fed according to the ration adopted on the farm (basic ration, including cereal-legume hay, whole milk, milk replacer, concentrates, chalk, salt). In addition to the main diet, the animals of the experimental groups were given a dietary supplement. At 2-3, 3-4, and 4-5, months of age, calves were given 12-23, 19-38, and 23-47 g.head-1 of dietary supplement per day, respectively. The article deals with the effect of a forest biomass supplement on the morphophysiological parameters of calves. Biochemical blood analysis and the features of metabolic processes in the bodies of animals are studied. The results indicated that the use of a dietary supplement at a dosage of 30 g/head of cattle per day contributes to the highest increase (9.9%) in live weight gain of experimental animals and an improvement in natural resistance parameters (bactericidal activity of blood serum, phagocytic activity of neutrophils). Based on the data of biochemical and haematological blood tests, the authors conclude that the inclusion of a dietary supplement in the diet of calves has a positive effect on the indices of natural resistance and the course of nitrogen metabolism.

Clinical assessment of nutritional status using the modified quantified subjective global assessment and anthropometric and biochemical parameters in patients undergoing hemodialysis in Macao

ObjectiveMalnutrition is widespread among patients undergoing hemodialysis and is linked to high morbidity and mortality rates. We evaluated the nutritional status and malnutrition markers in patients undergoing hemodialysis in Macao.MethodsWe performed a cross-sectional analysis of 360 patients in a hemodialysis center. The modified quantitative subjective global assessment (MQSGA), anthropometric indices and related biochemical test data were used to evaluate nutritional status.ResultsThe sample's mean age was 63.47 ± 13.95 years. There were 210 well-nourished (58.3%), 139 mild-to-moderately malnourished (38.6%) and 11 severely malnourished (3.1%) patients. Older patients had a higher incidence of severe malnutrition, but there were no significant differences between diabetic and non-diabetic patients. Mid-arm circumference (MAC); mid-arm muscle circumference; body mass index; triceps skin fold thickness; serum albumin, creatinine and urea; and hemoglobin were all valid for assessing nutritional status. MAC and the serum albumin and creatinine concentrations significantly negatively correlated with MQSGA.ConclusionsMalnutrition is commonplace in patients undergoing hemodialysis in Macao, but their nutritional status is not affected by diabetes. Serum creatinine, serum albumin and MAC, and especially pre-dialysis creatinine concentration, represent effective, readily available, and easily remembered screening measures of nutritional status for patients undergoing maintenance dialysis.

Predicting Malnutrition Risk with Data from Routinely Measured Clinical Biochemical Diagnostic Tests in Free-Living Older Populations.

Malnutrition (undernutrition) in older adults is often not diagnosed before its adverse consequences have occurred, despite the existence of established screening tools. As a potential method of early detection, we examined whether readily available and routinely measured clinical biochemical diagnostic test data could predict poor nutritional status. We combined 2008–2017 data of 1518 free-living individuals ≥50 years from the United Kingdom National Diet and Nutrition Survey (NDNS) and used logistic regression to determine associations between routine biochemical diagnostic test data, micronutrient deficiency biomarkers, and established malnutrition indicators (components of screening tools) in a three-step validation process. A prediction model was created to determine how effectively routine biochemical diagnostic tests and established malnutrition indicators predicted poor nutritional status (defined by ≥1 micronutrient deficiency in blood of vitamins B6, B12 and C; selenium; or zinc). Significant predictors of poor nutritional status were low concentrations of total cholesterol, haemoglobin, HbA1c, ferritin and vitamin D status, and high concentrations of C-reactive protein; except for HbA1c, these were also associated with established malnutrition indicators. Additional validation was provided by the significant association of established malnutrition indicators (low protein, fruit/vegetable and fluid intake) with biochemically defined poor nutritional status. The prediction model (including biochemical tests, established malnutrition indicators and covariates) showed an AUC of 0.79 (95% CI: 0.76–0.81), sensitivity of 66.0% and specificity of 78.1%. Clinical routine biochemical diagnostic test data have the potential to facilitate early detection of malnutrition risk in free-living older populations. However, further validation in different settings and against established malnutrition screening tools is warranted.

АВТОМАТИЧЕСКИЙ ПЛАЗМАФЕРЕЗ У ПАЦИЕНТОВ С COVID-19-АССОЦИИРОВАННОЙ ПНЕВМОНИЕЙ. ПЕРВЫЙ ОПЫТ ПРИМЕНЕНИЯ

Objective. To determine the possibility of using automatic plasmapheresis in patients with COVID-19- associated bilateral polysegmental pneumonia. Methods. The treatment of three patients with COVID-19-associated pneumonia with application of the Autopheresis-C™ automatic plasmapheresis machine (the USA) has been analyzed. The patients’ age was 47. 49 and 55 years. The patients’ case histories included factors aggravating the course of pneumonia (diabetes mellitus, chronic cardiovascular pathology with heart failure, obesity). The condition of all patients was severe. The effectiveness estimation of the given technique was carried out 6 hours after the manipulation and included a general clinical blood test, a biochemical blood test, hemodynamic parameters, and objective data. Results. After the first application of automatic plasmapheresis, all patients occurred a decrease in temperature and the level of respiratory failure, which was accompanied by an increase in hemoglobin saturation; a decrease in the severity of dyspnea was also reported, which was the reason for the changing patient position from prone to supine. All patients had a blood pressure reduction. Positive changes in the hemodynamic situation were the basis for reducing the dosage of antihypertensive drugs. Along with this, in the course of manipulation, a gradual decrease in the severity of tachycardia was noted in all patients: a reduction of heart rate was recorded. On the second day after the manipulation, the main blood parameters (leukocytosis, c-reactive protein) decreased. The observed positive effects contributed to the early transfer (by 10-15 days) of patients from the intensive care unit to the general somatic departments. Conclusion. The early inclusion of automatic plasmapheresis in the complex therapy of patients with COVID-19- associated bilateral polysegmental pneumonia leads to the stabilization of hemodynamic parameters, decline of the severity of respiratory failure, which made it possible to avoid the mechanical ventilation. What this paper adds For the first time, the clinical effectiveness of the method of automatic plasmapheresis in the framework of the complex therapy of COVID-19- associated polysegmental pneumonia is shown, which is expressed in a decrease in the manifestations of functional and metabolic disorders of vital systems for maintaining homeostasis. It was found that the inclusion of this technology in the complex therapy contributed to the stabilization of respiratory and hemodynamic parameters, which made it possible to avoid the mechanical ventilation.

Diabetes in Patients With Pancreatic Neuroendocrine Neoplasms.

ObjectiveDiabetes mellitus (DM) is probably a risk factor for pancreatic neuroendocrine neoplasms (PNENs). However, the prevalence of DM in PNEN patients remains inconclusive. In the present study we observed the prevalence of DM and possible risk factors in PNEN patients.MethodsAfter excluding those with insulinoma, a total of 197 patients with PNENs were included. The demographic data, pathological characteristics, and data of blood biochemical tests were recorded. DM was considered if there was evidence of a fasting plasma glucose level of ≥7.0 mmol/L or a 2-h plasma glucose level of ≥11.1 mmol/L, or a history of DM at the time of PNEN diagnosis. Impaired fasting glucose was considered if fasting plasma glucose level was between 6.1 and 7.0 mmol/L.ResultsThe prevalence of DM, new-onset DM, and impaired fasting glucose were 17.26, 9.14, and 7.1%, respectively. The prevalence of DM was 26.0% in patients ≥60 years old (19/73) and 12.1% in patients <60 years old. Multivariable logistic regression analysis demonstrated that age, tumor size, and nerve invasion were independent risk factors for DM and impaired fasting glucose + DM (p < 0.05). Age, organs and nerve invasion were independent risk factors for impaired fasting glucose. Low high-density lipoprotein (HDL) was also a risk factor for incident of DM (OR = 0.15, 95%CI: 0.03–0.66). G2/G3 was an independent risk factor for DM in women.ConclusionOur data shows that the prevalence of DM is 17.26% in patients with PNENs and is 26.0% in patients ≥60 years of age after excluding insulinoma. Age, nerve invasion, tumor size, and HDL are risk factors for DM in PNEN patients.