Early Prediction Research Articles

Utilizing Attention-Enhanced Deep Neural Networks for Large-Scale Preliminary Diabetes Screening in Population Health Data

Early screening for diabetes can promptly identify potential early stage patients, possibly delaying complications and reducing mortality rates. This paper presents a novel technique for early diabetes screening and prediction, called the Attention-Enhanced Deep Neural Network (AEDNN). The proposed AEDNN model incorporates an Attention-based Feature Weighting Layer combined with deep neural network layers to achieve precise diabetes prediction. In this study, we utilized the Diabetes-NHANES dataset and the Pima Indians Diabetes dataset. To handle significant missing values and outliers, group median imputation was applied. Oversampling techniques were used to balance the diabetes and non-diabetes groups. The data were processed through an Attention-based Feature Weighting Layer for feature extraction, producing a feature matrix. This matrix was subjected to Hadamard product operations with the raw data to obtain weighted data, which were subsequently input into deep neural network layers for training. The parameters were fine-tuned and the L2 regularization and dropout layers were added to enhance the generalization performance of the model. The model’s reliability was thoroughly assessed through various metrics, including the accuracy, precision, recall, F1 score, mean squared error (MSE), and R2 score, as well as the ROC and AUC curves. The proposed model achieved a prediction accuracy of 98.4% in the Pima Indians Diabetes dataset. When the test dataset was expanded to the large-scale Diabetes-NHANES dataset, which contains 52,390 samples, the test precision of the model improved further to 99.82%, with an AUC of 0.9995. A comparative analysis was conducted using multiple models, including logistic regression with L1 regularization, support vector machine (SVM), random forest, K-nearest neighbors (KNNs), AdaBoost, XGBoost, and the latest semi-supervised XGBoost. The feature extraction method using attention mechanisms was compared with the classical feature selection methods, Lasso and Ridge. The experiments were performed on the same dataset, and the conclusion was that the Attention-based Ensemble Deep Neural Network (AEDNN) outperformed all the aforementioned methods. These results indicate that the model not only performs well on smaller datasets but also fully leverages its advantages on larger datasets, demonstrating strong generalization ability and robustness. The proposed model can effectively assist clinicians in the early screening of diabetes patients. This is particularly beneficial for the preliminary screening of high-risk individuals in large-scale, extensive healthcare datasets, followed by detailed examination and diagnosis. Compared to the existing methods, our AEDNN model showed an overall performance improvement of 1.75%.

Contemporary issues of the birth trauma

Background. Birth trauma is a group of diseases caused by mechanical factors during childbirth. Birth trauma is an interdisciplinary problem, affecting various fields of medicine, such as obstetrics, pediatrics, child neurology and other sciences. Birth trauma occupies an important place in the structure of perinatal morbidity and mortality. Birth injuries of newborns during vaginal birth occur in 3.6% of cases, during cesarean section — in 1.2%. However, at present, despite a comprehensive study of the problem, the incidence of birth trauma in newborns remains high. Along with obstetric birth trauma, spontaneous birth trauma also occurs — not associated with any obstetric care.Purpose of review. To summarize and analyze the available data on the causes of birth trauma in newborns depending on the type of birth injury.Materials and methods. The review includes published data over the past 10 years regarding the study of the causes of the main types of birth injuries in newborns. The literature search was conducted in Web of Science, Google Scholar, PubMed, and ELibrary databases.Results. The problem of fetal-pelvic disproportion in the genesis of the development of risk factors for maternal-fetal trauma remains relevant. Fetal macrosomia is one of the most significant factors in birth trauma. The most common skull injury in newborns is cephalohematoma. According to the mechanism of occurrence, birth trauma is divided into spontaneous — occurring during physiological childbirth — and obstetric — associated with any obstetric benefits. The degree of configuration of the fetal head plays a significant role in the pathogenesis of birth trauma. Birth trauma is considered as a systemic reaction on the part of the newborn’s body, which leads to a breakdown of compensatory and adaptive mechanisms and the development of critical damage to the central nervous system and is differentiated from birth damage, which includes only local changes.Conclusion. To search for preventive measures aimed at preventing birth injuries in newborns, it is necessary to systematize the groups of causes that influence the increased risk of birth injury. Timely assessment of the pathological configuration of the fetal head is extremely important when deciding on the advisability of using obstetric aids during vaginal operative delivery, since it is an early predictor of the formation of fetal-pelvic disproportion — a significant factor in birth trauma in the newborn. In recent years, taking into account the active study of molecular genetic mechanisms in the genesis of the formation of various pathological conditions, the search for various genetic and epigenetic factors that influence the risk of developing birth traumatic injuries in a newborn against the background of individual susceptibility to the effects of any physical factors during childbirth.

Pentosidine and Renal Resistance Index Are Potential Early Predictors Of Diabetic Nephropathy In Children With Type 1 Diabetes Mellitus

Pentosidine and Renal Resistance Index Are Potential Early Predictors Of Diabetic Nephropathy In Children With Type 1 Diabetes Mellitus

Soluble B-cell maturation antigen levels for disease monitoring in oligo- and non-secretory relapsed multiple myeloma

Soluble B-cell maturation antigen (sBCMA) is overexpressed on multiple myeloma (MM) cells. We investigated whether sBCMA levels correlated with other myeloma tumor volume indicators and its utility in monitoring oligo-secretory/non-secretory (O-S/Non-S) MM. In 115 patients with newly diagnosed MM, sBCMA was compared with M-protein levels, bone marrow plasma cells (BMPCs), circulating tumor cells (CTCs), and total diffusion volume (tDV; estimated by whole-body diffusion-weighted magnetic resonance imaging) at diagnosis. sBCMA levels increased significantly with International Staging System stage, chromosome 1q21 gain/amplification and CTC levels. sBCMA also correlated strongly with %BMPC (r = 0.65), moderately with tDV (r = 0.55) and paraprotein levels (involved immunoglobulin in IgG and IgA subtypes, r = 0.44 and 0.4; involved free light-chain levels in light-chain-only MM, r = 0.61, all P < 0.05). Longitudinal changes in sBCMA were consistent with disease status in both 17 O-S/Non-S and other secretory MM cases. Furthermore, sBCMA levels increased as early as 6 months pre-relapse in almost all O-S/Non-S relapsed patients. Thus, sBCMA correlates strongly with total tumor volume in MM, as assessed using different modalities. We suggest that sBCMA is useful, not only for monitoring responses in patients with O-S/Non-S MM but also for early relapse detection and prediction.

Development and validation of a risk prediction model for feeding intolerance in neurocritical patients with enteral nutrition.

This study collects and analyzes clinical data on enteral nutrition therapy in neurocritical patients, develops and validates a feeding intolerance (FI) risk prediction model, and provides a theoretical basis for screening patients with high risk of feeding intolerance (FI) and delivering personalized care. A convenience sampling method was employed to select 300 patients who were admitted to a tertiary hospital in China for early enteral nutrition therapy in the neurointensive care unit between April 2022 and December 2022. Independent risk factors for FI were identified using univariate and logistic regression analyses. A prediction model was established, and the goodness of fit and discriminant validity of the model were evaluated. The incidence of FI in neurocritical patients receiving enteral nutrition was 71%. Logistic regression analysis identified age, Glasgow Coma Scale (GCS) scores, Acute Physiology and Chronic Health Evaluation II (APACHE II) scores, mechanical ventilation, feeding via the nasogastric tube route, hyperglycemia, and low serum albumin as independent risk factors for the development of FI (p < 0.05). The predictive formula for FI risk was established as follows: Logit p = -14.737 + 1.184 × mechanical ventilation +2.309 × feeding route +1.650 × age + 1.336 × GCS tertile (6-8 points) + 1.696 × GCS tertile (3-5 points) + 1.753 × APACHE II score + 1.683 × blood glucose value +1.954 × serum albumin concentration. The Hosmer-Lemeshow test showed χ2 = 9.622, p = 0.293, and the area under the ROC curve was 0.941 (95% confidence interval: 0.912-0.970, p < 0.001). The optimal critical value was 0.767, with a sensitivity of 85.9%, a specificity of 90.8%, and a Youden index of 0.715. The early enteral nutrition FI risk prediction model developed in this study demonstrated good predictive ability. This model can serve as a valuable reference for effectively assessing the risk of FI in neurocritical patients, thereby enhancing clinical outcomes.

Clinical predictive value of PD-1/PD-L1-induced electrocardiogram changes for cardiotoxicity

Objective: To observe the electrocardiogram (ECG) changes of programmed death receptor 1 (PD-1)/programmed death receptor-ligand 1 (PD-L1) immune checkpoint inhibitors before and after immunotherapy of patients during clinical antitumor process, and to explore the occurrence and influencing factors of cardiotoxicity of immune checkpoint inhibitors. Methods: A total of 93 patients with locally advanced or metastatic solid tumors confirmed by pathological diagnosis in Cancer Hospital of Chinese Academy of Medical Sciences from October 1, 2019 to September 30, 2020 were selected and treated with PD-1/PD-L1 inhibitor monotherapy. Groups were divided according to immunotherapy regimen: Group A (drug code: 609A), 16 patients were given 1 mg/kg of the drug for 21 days; Group B (drug code: HX008), 23 patients were treated with 200mg for 21 days; Group C (drug code: GB226), 28 patients were treated with 3mg/kg for 14 days; Group D (drug code: LP002), 26 patients were treated with 900mg for 14 days. The patients were monitored and followed up for 10 cycles. The ECG results of each group were recorded, and the correlation between ECG abnormality and cardiotoxicity was analyzed. Results: A total of 75 patients showed abnormal ECG that met the diagnostic criteria. There was no significant difference in abnormal ECG rate after immunotherapy in group A (P＞0.05), while the incidence of adverse cardiac events increased after immunotherapy in group B (P＜0.05), and the abnormal ECG rate increased significantly after chemotherapy in group C and group D. There was statistical difference before and after immunotherapy (P＜0.001). The number of abnormal cases in group A (8 cases, 50.0%, 8/16) was significantly lower than that of group B (20 cases, 87.0%, 20/23). The number of abnormal cases in group C and group D was 24 (85.7%) and 23 (88.4%), respectively, without statistical difference (P＞0.05), but their abnormal rates of ECG were higher than that in group A. The incidence of electrical adverse events in immunotherapy center of patients with underlying diseases was 1.93 times higher than that of patients without underlying diseases. The incidence of central electrical adverse events during immunotherapy in group B, C and D was 6.667, 6.000 and 7.667 times higher than that in group A, respectively. Conclusions: The high sensitivity of early ECG changes induced by immune checkpoint inhibitors enables early prediction of related cardiotoxicity. The presence or absence of comorbid underlying disease and drug dosage are correlated with the occurrence of adverse cardiac events, and these early changes provide a evidence for clinical treatment and prevention.

Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection

Background: Lung cancer, also known as lung carcinoma, has a high mortality rate; however, an early prediction helps to reduce the risk. In the current literature, various approaches have been developed for the prediction of lung carcinoma (at an early stage), but these still have various issues, such as low accuracy, high noise, low contrast, poor recognition rates, and a high false-positive rate, etc. Thus, in this research effort, we have proposed an advanced algorithm and combined two different types of deep neural networks to make it easier to spot lung melanoma in the early phases. Methods: We have used WDSI (weakly supervised dense instance-level lung segmentation) for laborious pixel-level annotations. In addition, we suggested an SS-CL (deep continuous learning-based deep neural network) that can be applied to the labeled and unlabeled data to improve efficiency. This work intends to evaluate potential lightweight, low-memory deep neural net (DNN) designs for image processing. Results: Our experimental results show that, by combining WDSI and LSO segmentation, we can achieve super-sensitive, specific, and accurate early detection of lung cancer. For experiments, we used the lung nodule (LUNA16) dataset, which consists of the patients’ 3D CT scan images. We confirmed that our proposed model is lightweight because it uses less memory. We have compared them with state-of-the-art models named PSNR and SSIM. The efficiency is 32.8% and 0.97, respectively. The proposed lightweight deep neural network (DNN) model archives a high accuracy of 98.2% and also removes noise more effectively. Conclusions: Our proposed approach has a lot of potential to help medical image analysis to help improve the accuracy of test results, and it may also prove helpful in saving patients’ lives.

Improving Clinical Preparedness: Community Health Nurses and Early Hypoglycemia Prediction in Type 2 Diabetes Using Hybrid Machine Learning Techniques.

The aim of the study was to analyze the data of diabetic patients regarding warning signs of hypoglycemia to predict it at an early stage using various novel machine learning (ML) algorithms. Individual interviews with diabetic patients were conducted over 6 months to acquire information regarding their experience with hypoglycemic episodes. This information included warning signs of hypoglycemia, such as incoherent speech, exhaustion, weakness, and other clinically relevant cases of low blood sugar. Researchers used supervised, unsupervised, and hybrid techniques. In supervised techniques, researchers applied regression, while in hybrid classification ML techniques were used. In a 5-fold cross-validation approach, the prediction performance of seven models was examined using the area under the receiver operating characteristic curve (AUROC). We analyzed the data of 290 diabetic patients with low blood sugar episodes. Our investigation discovered that gradient boosting and neural networks performed better in regression, with accuracies of 0.416 and 0.417, respectively. In classification models, gradient boosting, AdaBoost, and random forest performed better overall, with AUC scores of 0.821, 0.814, and 0.821, individually. Precision values were 0.779, 0.775, and 0.776 for gradient boosting, AdaBoost, and random forest, respectively. AdaBoost and Gradient Boosting models, in particular, outperformed all others in predicting the probability of clinically severe hypoglycemia. These techniques enable community health nurses to predict hypoglycemia at an early stage and provide the necessary therapies to patients to prevent complications resulting from hypoglycemia.

Application of Artificial Intelligence in the Diagnosis, Follow-Up and Prediction of Treatment of Ophthalmic Diseases.

To describe the application of artificial intelligence (AI) in ophthalmic diseases and its possible future directions. A retrospective review of the literature from PubMed, Web of Science, and Embase databases (2019-2024). AI assists in cataract diagnosis, classification, preoperative lens calculation, surgical risk, postoperative vision prediction, and follow-up. For glaucoma, AI enhances early diagnosis, progression prediction, and surgical risk assessment. It detects diabetic retinopathy early and predicts treatment effects for diabetic macular edema. AI analyzes fundus images for age-related macular degeneration (AMD) diagnosis and risk prediction. Additionally, AI quantifies and grades vitreous opacities in uveitis. For retinopathy of prematurity, AI facilitates disease classification, predicting disease occurrence and severity. Recently, AI also predicts systemic diseases by analyzing fundus vascular changes. AI has been extensively used in diagnosing, following up, and predicting treatment outcomes for common blinding eye diseases. In addition, it also has a unique role in the prediction of systemic diseases.

Progression of aortic calcification among Japanese in Japan and white and Japanese Americans: a prospective cohort study.

Continued low mortality from coronary heart disease in Japan, despite deleterious changes in traditional risk factors, remains unexplained. Since aortic calcification (AC) was an early predictor of cardiovascular mortality, we compared the progression and incidence of AC between Japanese in Japan, white Americans, and third-generation Japanese Americans in the ERA JUMP cohort. We examined whether higher blood levels of marine-derived n-3 fatty acids (FAs) in Japanese than in Americans accounted for the difference. Men (n=700) aged 40-49 years (252 Japanese in Japan, 238 white, and 210 Japanese Americans) were examined at baseline and 4-7 years later. AC was evaluated from the aortic arch to the iliac bifurcation with computed tomography and quantified by the Agatston method. Robust linear regression and linear mixed models were used to compare the progression of AC. Multivariable logistic regression models were fitted to compare the incidence of AC (AC≥50 at follow-up) among those with baseline AC<50. Japanese in Japan had a significantly slower progression of AC than white and Japanese Americans after adjusting for age, baseline AC, follow-up time, and traditional risk factors. White Americans had a significantly higher incidence of AC than Japanese in Japan (OR=4.61 [95%CI, 1.27-16.82]). Additional adjustment for blood levels of n-3 FAs accounted for the difference in AC incidence but not progression. Japanese in Japan had a significantly slower progression and lower incidence of AC than white Americans. High levels of marine-derived n-3 FAs in Japanese in Japan partly accounted for the difference in incidence.

Increased inter-atrial and intra-atrial conduction times in pediatric patients with non-alcoholic fatty liver disease.

The global incidence of pediatric non-alcoholic fatty liver disease (NAFLD) is rising, and it is linked to various potentially dangerous complications such as cardiovascular complications, particularly atrial fibrillation (AF). Atrial electromechanical conduction delay (EMD) has been reported as an early predictor for AF development. This study aimed to explore the link between NAFLD and the increased risk of AF development. This cross-sectional study was performed on 100 newly diagnosed NAFLD children (aged 14-18 years) as the patient group and 100 healthy individuals as a control group. Transthoracic echocardiography and simultaneous electrocardiography (ECG) recording were employed to estimate atrial electromechanical properties. EMD values were calculated for the inter-atrial, left intra-atrial, and right intra-atrial. Our results showed that pediatric patients with NAFLD exhibited significantly prolonged EMD values in the left and right intra-atrial as well as in inter-atrial regions compared to the control group (P = 0.03, P < 0.001, P < 0.01, respectively). Conclusion: Children with NAFLD show atrial electromechanical alterations that may presage AF in adulthood.

Evaluation of antibodies to oxidized low-density lipoprotein in children with obesity of different degrees

Introduction. The interest in the study of anti-oxidized low-density lipoproteins (anti-oxLDL) is due to their association with the development and progression of atherosclerosis and metabolic syndrome. Purpose of the study. To study the level of antibodies of oxidized low-density lipoproteins (anti-oxLDL) in serum in obese children. Materials and Methods. 76 children aged 5 to 17 years participated in the study. A standard objective and laboratory examination was performed, including physical and sexual development, lipidogram and anti-oxLDL levels. To assess anthropometric data, the standard deviation coefficient was calculated using the Auxology application. The parameters of fat metabolism were determined according to the data of blood biochemical analysis. The content of anti-oxLDL was determined by immuno-enzymatic analysis using test kits “Biomedica”. Results. According to the results of the examination the patients were divided into three groups: group 1 included 36 children with constitutional-exogenous obesity and increased level of anti-oxLDL, group 2-30 patients with constitutional-exogenous obesity and normal level of anti-oxLDL, group 3-10 healthy children. The level of antibodies to oxidized low density lipoproteins (oxLDL) in obese children is 11.6 times higher compared to healthy children. The antibody titer in prepubertal children is 2206 [1809;2603] IU/mL, and in adolescents it is 1505.5 [1109;1902] IU/mL. The highest values of anti-oxLDL levels were observed in patients with 1st degree obesity 2623 [2245;3001] IU/mL and 3rd degree obesity 2914.5 [2678;3151] IU/mL. Conclusion. High of anti-oxLDL levels were found in pre-pubertal children with obesity, especially in 1st and 3rd degree obesity. In obese children, the level of anti-oxLDL has a direct correlation with the duration of the underlying disease and the increase in low-density lipoprotein (LDL) levels. Further studies are needed on the role of anti-OCOLDL as an early predictor of atherosclerosis in clidren with obesity.

A predictive score for early in-patient tuberculosis mortality: A case-control study

IntroductionIn-hospital mortality rates for tuberculosis (TB) patients are high within the first seven days of admission. This study sought to identify predictors of early inpatient mortality and assess the performance of a predictive score for early mortality in a Ugandan tertiary hospital. Materials and methodsA case-control study was conducted at Kiruddu National Referral Hospital in Kampala, Uganda. Cases included patients admitted with TB who died within seven days of admission, while controls survived beyond this period. Logistic regression was utilized to identify early mortality predictors. The performance of an adapted predictive score (PROS score) was evaluated, assigning scores based on the following criteria: Pulse rate >100 beats/min (1 point), Respiratory rate >20 breaths/min (2 points), Oxygen saturation <92 % (4 points), and Systolic blood pressure <90 mmHg (2 points). ResultsOf 602 hospitalized TB patients, 187 (31.0 %) died during admission. Among these, 78 (41.7 %) died within seven days. Wasting (adjusted odds ratio [aOR] = 5.76, 95 % confidence interval [CI] 2.12–15.63, p = 0.001) and respiratory rate >20 breaths/min (aOR = 2.89, 95 % CI 1.19–7.00, p = 0.019) predicted early mortality. PROS score of ≥1 demonstrated a sensitivity of 87.8 % and negative predictive value of 90.0 %. The ultimate TB treatment success rate of all hospitalized patients (n = 599) was 47.4 % with 275 (45.9 %) dying during TB treatment. ConclusionEarly and long term mortality rates among hospitalized TB patients are high. Wasting and tachypnea predict early inpatient mortality. The PROS score could be useful in ruling out low-risk patients in low-resource settings.

Association of HPA Antigens with Immune Thrombocytopenia: A Case-Control Study by PCR-SSP Method

Background: Human platelet antigens (HPAs) play a clinically significant role in alloimmunization and the development of immune-mediated disorders such as immune thrombocytopenia (ITP), fetal and neonatal alloimmune thrombocytopenia (FNAIT), and post-transfusion purpura (PTP). Understanding the genetic profiles of HPAs is critical for preventing and treating these conditions. Given the limitations of serological methods in determining HPA genotypes, this study aims to investigate the association between the genotypes of HPA1, HPA2, HPA3, HPA4, and HPA15 antigens and autoimmune thrombocytopenia in Lorestan Province, utilizing the PCR-SSP method. Materials and Methods: This case-control study involved 80 individuals diagnosed with ITP and 120 healthy controls. DNA samples were extracted using a commercial DNA extraction kit, with concentrations quantified via a Nanodrop spectrophotometer. Genotyping was performed using the PCR-SSP method with specific primers for each HPA gene. The genotype data were verified using previously established sample sets. The frequencies of each HPA genotype were recorded, and a comparative analysis was conducted between the patient and control groups to evaluate the study hypothesis. Results: The results revealed that individuals carrying the HPA2b allele had a 5.31-fold increased risk of developing ITP, a statistically significant finding (P &lt; 0.05, OR = 5.31). Similarly, the presence of the HPA15b allele was associated with a 6.54-fold increased risk (P &lt; 0.05, OR = 6.54). Conclusion: These findings, in conjunction with previous studies, suggest the need for larger-scale investigations across different populations. Such research could aid in the early diagnosis and prediction of thrombocytopenia severity, inform treatment strategies, and facilitate the removal of pathogenic antibodies from circulation.

State monitoring and fault prediction of centrifugal compressors based on long short–term memory and principal component analysis (LSTM-PCA)

Centrifugal compressors are widely used in the petroleum and natural gas industry for gas compression, reinjection, and transportation. Early fault identification and fault evolution prediction for centrifugal compressors can improve equipment safety and reduce maintenance and operating costs. This article proposes a dynamic process monitoring method for centrifugal compressors based on long short-term memory (LSTM) and principal component analysis (PCA). This method constructs a sliding window for monitoring at each sampling point, which contains 100 data from the past and current time points, and uses LSTM to predict 30 future data points. At the same time, this method is also combined with the PCA threshold process monitoring method to construct a new LSTM-PCA monitoring algorithm. And the method was validated using centrifugal compressor process data. The results show that this method can effectively detect process anomalies, The improvements significantly reduced the false positive rate of detected anomalies, and can make multi-step advance predictions of system behavior after faults occur.

Machine learning algorithm approach to complete blood count can be used as early predictor of COVID-19 outcome.

Although the SARS-CoV-2 infection has established risk groups, identifying biomarkers for disease outcomes is still crucial to stratify patient risk and enhance clinical management. Optimal efficacy of COVID-19 antiviral medications relies on early administration within the initial five days of symptoms, assisting high-risk patients in avoiding hospitalization and improving survival chances. The complete blood count can be an efficient and affordable option to find biomarkers that predict the COVID-19 prognosis due to infection-induced alterations in various blood parameters. This study aimed to associate hematological parameters with different COVID-19 clinical forms and utilize them as disease outcome predictors. We performed a complete blood count in blood samples from 297 individuals with COVID-19 from Belo Horizonte, Brazil. Statistical analysis, as well as ROC Curves and machine learning Decision Tree algorithms were used to identify correlations, and their accuracy, between blood parameters and disease severity. In the initial four days of infection, traditional hematological COVID-19 alterations, such as lymphopenia, were not yet apparent. However, the monocyte percentage and granulocyte-to-lymphocyte ratio proved to be reliable predictors for hospitalization, even in cases where patients exhibited mild symptoms that later progressed to hospitalization. Thus, our findings demonstrate that COVID-19 patients with monocyte percentages lower than 7.7% and a granulocyte-to-lymphocyte ratio higher than 8.75 are assigned to the hospitalized group with a precision of 86%. This suggests that these variables can serve as important biomarkers in predicting disease outcomes and could be used to differentiate patients at hospital admission for managing therapeutic interventions, including early antiviral administration. Moreover, they are simple parameters that can be useful in minimally equipped health care units.

The clinical value of serum creatinine to bilirubin ratio in predicting the severity and prognosis of acute pancreatitis.

Bilirubin (BIL) and creatinine (Cr) have been used as potential early predictors of the severity of many diseases. A recent study found that the Cr to BIL ratio (CTR) was more sensitive and specific than either serum Cr or BIL alone. Our research focused on the clinical significance of CTR in evaluating the severity and prognosticating outcomes of acute pancreatitis (AP) in patients. Patients diagnosed with AP at the First Affiliated Hospital of Guangdong Pharmaceutical University between July 1, 2016, and December 31, 2020 were included. The analysis then focused on examining the relationship between CTR levels and the severity of the illness, the occurrence of complications, and the prognosticating outcomes for individuals diagnosed with AP. A total of 286 AP patients were enrolled. Multivariate regression analyses showed that patients with AP with increased CTR levels had a poorer disease (easier to develop severe AP); higher Ranson, and Acute Physiology and Chronic Health Evaluation (APACHE-II) scores; higher incidence of organ failure (acute heart failure, acute kidney injury and acute myocardial infarction ); and leading to a worse prognosis characterized more by frequent use of vasoactive and diuretic agents. When CTR &gt;14.05, AP patients had increased occurrence of AHF and AKI, higher 30-day all-cause mortality rates, more frequently using vasoactive agent and diuretic agent. Besides, the disease severity scores and hospital stays were markedly increased. Patients with AP who exhibit higher CTR levels tend to experience escalating disease severity, more complications, and a poorer outcome compared with those with lower CTR levels.

Assessment of the quality of life of GPs in situations of high epidemic risk

The purpose is to assess the characteristics of the decrease in the quality of life of GPs working in a specialized COVID-19 hospital, a multidisciplinary hospital, and a poly clinic during the pandemic of the novel coronavirus infection COVID-19, as well as early diagnosis, prediction, and prevention of a decrease in the quality of life in this category of medical workers. Material and research methods. The study was carried out on the basis of the Department of Occupational Diseases and Clinical Pharmacology named after honored scientist of the Russian Federation professor V. V. Kosarev, FSBEI HE Samara State Medical University of the Ministry of Health of the Russian Federation, and the Department of Occupational Pathology, Regional Center for Occupational Pathology of the Samara City Hospital No. 5. The study was carried out within the framework of a complex theme «Systematic ap proach to early diagnosis, prevention, and prediction of the impact of low-intensity pro duction factors on workers’ health» of the Department of Occupational Diseases and Clinical Pharmacology named after honored scientist of the Russian Federation profes sor V. V. Kosarev, FSBEI HE Samara State Medical University (state registration number AAAA-A18‑118122190069‑6, registration date — December 21, 2018). The study was approved by the local ethics committee of the FSBEI HE Samara State Medical University of the Ministry of Health of the Russian Federation on November 23, 2021. The study included the following groups of examined medical workers: group 1 consisted of physicians of internal medicine working in a COVID hospital (in the «red zone») (n = 111); group 2 included GPs working in a multidisciplinary hospital (n = 106); group 3 consisted of GPs working in a polyclinic (n = 102); group 4 was the control group (n = 190) comprising employees of engineering, technical, and economic specialties not relat ed to work in medical organizations (healthy). To assess the psychophysiological state and quality of life of medical workers during the pandemic of the novel coronavirus infection COVID-19, the SF-36 questionnaire [J. E. Ware, 1993], designed to study all components of the quality of life, was used. The obtained data were processed using the Statistica package from StatSoft (USA). Results. The professional activities of GPs providing medical care in the «red zone», mul  tidisciplinary hospitals, and clinics are associated with the exposure of physicians to a number of risk factors in the working environment and the labor process, related to the provision of regular or occasional care to infected COVID-19 patients, which, under con ditions of exposure to an increased level of occupational stress, leads to a decrease in the quality of life in these categories of health workers. The decrease in the quality of life among medical workers in medical institutions of various profiles during the pandemic of the novel coronavirus infection COVID-19 is due to the fact that health workers faced many additional difficulties during this period: sleep deprivation, stress, strain, and chronic fa tigue. Chronic fatigue can affect behavior, communication, learning, and decision-making, which overall leads to a decrease in the qualit y of life of medical workers. Conclusion. Thus, the obtained data indicate that when identifying risk factors for a de crease in the quality of life in medical workers working in situations of high epidemic risk, there is the need to use specialized rehabilitation measures with relaxation techniques, art therapy, as well as professional adaptation programs, physiotherapeutic techniques, such as electrosleep and reflexology, and, if possible, resort treatment in health care centers, local sanatoriums, etc. with visits to psychotherapy offices, as well as psychopharmaco logical medications.

Epidemiology and outcome of medical emergency team calls within 48 hours of intensive care unit discharge.

Some patients experience early (within 48 h) clinical deterioration and medical emergency team (MET) review following intensive care unit (ICU) discharge. Few studies have explored early MET review, despite it being a recognised quality and safety indicator. To evaluate the (i) proportion of patients discharged from ICU receiving MET review and timing of reviews; (ii) characteristics of patients who received early MET review and (iii) predictors of early MET review and associations with clinical outcomes. This is a retrospective observational study of ICU discharges over 2 years in a tertiary hospital and involves descriptive and inferential statistics, including logistic regression analysis. Of 3712 patients, 312 (8.4%) had an early MET review. Patients with cardiothoracic, cardiovascular, gastrointestinal and general surgical diagnoses, higher illness severity or who received invasive ventilation had a higher risk of early MET review. On multivariable analysis, early MET review was associated with an increased risk of ICU re-admission (odds ratio (OR) 6.76, 95% confidence interval (CI) 5.01-9.13, P < 0.001), in-hospital mortality (OR 3.62, 95% CI 2.19-5.99, P < 0.001) and discharge to a nursing home (OR 2.49, 95% CI 1.25-4.97, P = 0.01). Length of stay was longer in patients requiring early post-ICU MET review compared to those who did not (median 16 days vs. 10 days, P < 0.001). One in 12 patients received post-ICU early MET review. This was more likely in patients who were invasively ventilated, had higher illness severity and had certain admission diagnoses. Such patients were at risk for worse outcomes. There is a need to identify reversible factors contributing to such increased risk.

Perfusion index as an early predictor of hypotension during advanced oncothoracic operations (pilot study)

Introduction. Current standards of intraoperative monitoring significantly reduce the response time to a decrease in blood pressure, but do not include methods for predicting changes in hemodynamics to avoid the effects of systemic hypoperfusion.The objective was to evaluate the usefulness of determining the perfusion index for predicting the development of hypotension and its earlier correction during advanced oncothoracic operations.Materials and methods. A prospective open-label observational study was conducted, which included 100 patients who underwent elective oncothoracic surgery. Standard monitoring was established, as well as continuous monitoring of the perfusion index. The perfusion index value was recorded immediately before induction. The patients were divided into 2 groups: in the 1st group (n = 37), patients experienced a decrease in blood pressure, requiring vasopressor support; in the 2nd group (n = 63), no vasopressor support was required.Results. A moderate linear relationship was revealed with a correlation coefficient (r) equal to (–0.68), p &lt; 0.001, and a strong non-linear relationship with a coefficient (ρ) equal to (–0.95), p &lt; 0.001. To identify the relationship model, polynomial regression analysis was performed. A prognostic formula for the use of vasopressors was calculated depending on the preoperative level of perfusion index. At the next stage, a classification tree for analyzing the data array was used. The entire d data array (n = 100) is randomly divided into training (n = 70) and test samples (n = 30). It was revealed that hypotension requiring vasopressor support occurred in patients whose initial perfusion index was ≤ 2.85. ROC analysis determined an AUC of 0.952 (95% CI: 0.888–1.016).Conclusion. A low PI value before induction of anesthesia during advanced oncothoracic operations can be used to monitor the functional activity of the autonomic nervous system and predict intraoperative hypotension. Patients with a baseline PI ≤ 2.85 have a higher risk of developing hypotension during advanced oncothoracic surgery compared with those with a baseline PI ≥ 2.85. The effectiveness of the method in patients with concomitant pathologies has not been tested.