Selection of forecasting models for infectious diseases in large warships.

As important combat platforms, large warships have the characteristics of compact internal space and dense personnel. Once infectious diseases occur, they are very easy to spread. Therefore, it is very important to select suitable forecasting models for infectious diseases in this environment. This paper introduces 4 classic dynamics models of infectious diseases, summarizes various kinds of compartmental models and their key characteristics, and discusses several common practical simulation requirements, helping relevant health personnel to cope with the challenges in health and epidemic prevention such as the prevention and control of coronavirus disease 2019.Copyright © 2022, Second Military Medical University Press. All rights reserved.

Vaccine Rate Coverage Forecast in Brazil: Is It Possible to Keep Polio Eradicated?

Objectives: Brazil's annual vaccination coverage rate (AVCR) for Polio has risen to alarming levels in recent years. Given the imminent possibility of the return of the disease eradicated 32 years ago in Brazil, the objective was to assess the historical data of AVCR and foresee the Brazilian performance in the next five years. Method(s): We apply a classic linear forecasting model Holt Winter (HW), composed of a forecasting equation and three corresponding smoothing equations alpha, beta, and gamma. The Polio AVCR between 1994 and 2022 was collected from the National Immunization Program and was evaluated in two stages using the R software involving (i) analysis of data, (ii) application of the HW using least squares adjustment. Result(s): The AVCR showed a growing trend between 1994 (38%) and 1999 (86%). From 2000 to 2015, the average AVCR was 78.72%, with the best coverage in 2015 (95.07%). Between 2016 and 2022, the AVCR was 66.75%, with a tendency to reduce over time. Between 2020 and 2022, AVCR had its lower result (64.44%), which can be explained by the postponement of Polio vaccination due to the COVID-19 pandemic. The best adjustment of smoothing alpha, beta and gamma was achieved (0.67, 0, 0) by HW. The forecast showed positive results in the average AVCR, with a growth of 16.71% in the next five years and with an AVCR projection of just 75.89%, in the case of no public health action is endowed by the country. To reach the best AVCR achieved in 2015, it is necessary to expand it by 48.5%. Conclusion(s): Forecasts using HW are recommended for public health monitoring, helping managers make decisions with limited resources. The results indicate that it is necessary to develop a strategic plan to expand AVCR to keep Polio eradicated from Brazil, mainly due to both disease gravity and treatment unavailability.Copyright © 2023

Application of Machine Learning Techniques to Predict Visitors to the Tourist Attractions of the Moche Route in Peru

Due to the COVID-19 pandemic, the tourism sector has been one of the most affected sectors and requires management entities to develop urgent measures to reactivate and achieve digital transformation using emerging disruptive technologies. The objective of this research is to apply machine learning techniques to predict visitors to tourist attractions on the Moche Route in northern Peru, for which a methodology based on four main stages was applied: (1) data collection, (2) model analysis, (3) model development, and (4) model evaluation. Public data from official sources and internet data (TripAdvisor and Google Trends) during the period from January 2011 to May 2022 are used. Four algorithms are evaluated: linear regression, KNN regression, decision tree, and random forest. In conclusion, for both the prediction of national and foreign tourists, the best algorithm is linear regression, and the results allow for taking the necessary actions to achieve the digital transformation to promote the Moche Route and, thus, reactivate tourism and the economy in the north of Peru.

Selection of forecasting models for infectious diseases in large warships

As important combat platforms, large warships have the characteristics of compact internal space and dense personnel. Once infectious diseases occur, they are very easy to spread. Therefore, it is very important to select suitable forecasting models for infectious diseases in this environment. This paper introduces 4 classic dynamics models of infectious diseases, summarizes various kinds of compartmental models and their key characteristics, and discusses several common practical simulation requirements, helping relevant health personnel to cope with the challenges in health and epidemic prevention such as the prevention and control of coronavirus disease 2019.Copyright © 2022, Second Military Medical University Press. All rights reserved.

Nomogram for Predicting Viral Shedding Time of SARS-CoV-2 Delta Variant in Patients with COVID-19: A Retrospective Study

Background The coronavirus disease 2019 (COVID-19) cases continue to rise, and the demand for medical treatment and resources in healthcare systems surges. Assessing the viral shedding time (VST) of patients with COVID-19 can facilitate clinical decision making. Although some studies have been conducted on the factors affecting the VST of severe acute respiratory syndrome coronavirus 2 (SARS-COV-2), few prediction models are currently available. Methods This retrospective study included the consecutive patients with COVID-19 admitted to Xi'an Chest Hospital in Shaanxi, China, for treatment between December 19, 2021 and February 5, 2022. The clinical data of the patients were extracted from their electronic medical records. Combining significant factors affecting the VST, a nomogram was developed to predict the VST of the SARS-CoV-2 Delta variant in patients with COVID-19. Results We included 332 patients in this study. The average VST was 21 d. VST was significantly prolonged in patients with severe clinical symptoms, sore throat, old age, long time from onset to diagnosis, and an abnormal white blood cell count. Consequently, we developed a nomogram prediction model using these 5 variables. The concordance index (C-index) of this nomogram was 0.762, and after internal validation using bootstrapping (1000 resamples), the adjusted C-index was 0.762. The area under the nomogram's receiver operator characteristic curve showed good discriminative ability (0.965). The calibration curve showed high consistency. The VST was prolonged in the group with lower model fitting scores according to the Kaplan-Meier curve (χ2=286, log-rank P < 0.001). Conclusions We developed a nomogram for predicting VST based on 5 easily accessible factors. It can effectively estimate the appropriate isolation period, control viral transmission, and optimize clinical strategies. © Wolters Kluwer Health, Inc. All rights reserved.

An observational cohort study to examine SPUR, a patient-reported outcome measure of medication adherence, as a predictor of admission and early readmission in patients living with Type 2 Diabetes

Introduction: Conservative estimates suggest that the cost of poor medication adherence (MA) to healthcare systems in the UK is close to 800Mn annually, however figures may be as high as 920Mn to 224Bn across larger parts of Europe and the US.(1) This may be attributed to the relationship between poor MA and an increased risk of hospital admission.(2) Often, cases are preventable and hence present an opportunity for avoidable costs if appropriately identified and managed, such as in the case of early readmissions (admissions occurring within 30 days of discharge). However, despite the association between MA and admissions, to date no predictive model has been developed that integrates a holistic Patient-Reported Outcome Measure (PROM) of MA. This study evaluated one such PROM, known as SPUR, as a predictor of general admission and early readmission in patients living with Type 2 Diabetes (T2D). Aim(s): This study sought to develop a predictive model of early readmission and general admission risk using the SPUR tool as a PROM of MA in patients living with T2D. Method(s): Using an observational study design, 6-month retrospective and prospective patient monitoring were conducted to assess the number of admissions and early readmissions during the observational period. Outcomes were reported as binary and count variables. Patients were previously recruited from a large London NHS Trust as part of a cross-sectional study to validate SPUR. Covariates of interest included: age, ethnicity, gender, education level, income, the number of medicines and medical conditions, and Covid-19 diagnoses. A Poisson or negative binomial model was employed for count outcomes, with the exponentiated coefficient indicating incident ratios (IR) [95% CI]. For binary outcomes (Coefficient, [95% CI]), a logistic regression model was developed. Result(s): Data were available for 200 patients. The modal age range was 70-79 years (n=74/200, 37.0%). Most participants were GCSE educated (42.5%), white (76.0%), and over a third female (36.0%) identified as female. For general admission risk as a count variable, a higher SPUR score (increased adherence) was significantly associated with a lower number of admissions (IR = 0.98, [0.96, 1.00]). Other factors associated with an increased risk of admission included: age >=80 years (IR = 5.18, [1.01, 26.55]), GCSE education (IR = 2.11, [1.15 - 3.87]), number of medical conditions (IR = 1.07, [1.01, 1.13]), and a positive Covid- 19 diagnosis during follow-up (IR = 1.83, [1.11, 3.02]). SPUR remained significant when modelled as a binary variable (-0.048, [-0.094, -0.003]). For early readmission, only the SPUR score was significantly predictive of the outcome as a binary variable (-0.051, [-0.094, -0.007]), indicating that those with a higher SPUR score were at less risk of an early readmission. Conclusion(s): The study successfully developed a predictive model for both general admission and early readmissions in patients living with T2D using the SPUR tool and several covariates of clinical relevance. However, a small sample size is noted as a limitation. Future work may look to integrate SPUR as a holistic PROM of MA to support the development of tailored interventions to reduce patients' risk of admission.

COVID-19 HOSPITALIZATION RISK AFTER SARS-CoV-2 VACCINATION AND OUTPATIENT TREATMENT

Background: Given effectiveness of SARS-CoV-2 vaccines and outpatient antiviral and monoclonal antibody therapy for reducing progression to severe COVID-19, we sought to estimate the impact of these interventions on risk of hospitalization following SARS-CoV-2 infection in a large US healthcare system. Method(s): All patients >=18 of age in the UNC Health system, with first positive SARS-CoV-2 RT-PCR test or U07.1 ICD-10-CM (diagnosis date) during 07/01/2021- 05/31/2022, were included. The outcome was first hospitalization with U07.1 ICD-10-CM primary diagnosis <=14 days after SARS-CoV-2 diagnosis date. SARS-CoV-2 vaccinations were included if received >=14 days prior to diagnosis. Outpatient therapies were included if administered after diagnosis date and before hospital admission. Age, gender, race, ethnicity, and comorbidities associated with COVID-19 (using ICD-10-CM, if documented >=14 days prior to diagnosis date) were also evaluated. Risk ratios for hospitalization were estimated using generalized linear models, and predictors identified using extreme gradient boosting using feature influence with Shapley additive explanations algorithm. Result(s): The study population included 54,886 patients, 41% men and 27% >=60 years of age. One-third of SARS-CoV-2 diagnoses occurred July-December 2021 and 67% December-May 2022 (predominantly Delta and Omicron variants, respectively). Overall 7.0% of patients were hospitalized for COVID-19, with median hospitalization stay of 5 days (IQR: 3-9). 32% and 12% of patients received >=1 SARS-CoV-2 vaccine dose and outpatient therapy, respectively. Unadjusted and age-adjusted hospitalization risk decreased with vaccination and outpatient therapy (TABLE). Comparing patients who received 3 vaccine doses versus none we observed a 66% relative reduction in risk, with stronger association for more recent vaccination. For patients who received nirmatrelvir/ ritonavir versus no therapy we observed a 99% relative reduction in risk. In predictive models, older age was the most influential predictor of being hospitalized with COVID-19, while vaccination and outpatient therapy were the most influential factors predicting non-hospitalization. Conclusion(s): The impact of recent SARS-CoV-2 vaccination and outpatient antiviral and monoclonal antibody therapy on reducing COVID-19 hospitalization risk was striking in this large healthcare system covering Delta and Omicron variant timeframes. SARS-CoV-2 vaccinations and outpatient therapeutics are critical for preventing severe COVID-19. Unadjusted and age-adjusted risk ratios for hospitalization among patients with SARS-CoV-2.

Vaccine rate forecast for COVID-19 in Africa using hybrid forecasting models

Background: The public health sectors can use the forecasting applications to determine vaccine stock requirements to avoid excess or shortage stock. This prediction will ensure that immunization protection for COVID-19 is well-distributed among African citizens. Objective(s): The aim of this study is to forecast vaccination rate for COVID-19 in Africa Methods: The method used to estimate predictions is the hybrid forecasting models which predicts the COVID-19 vaccination rate (CVR). HARIMA is a hybrid of ARIMA and the Linear Regression model and HGRNN is a hybrid of Generalized Regression Neural Network (GRNN) and the Gaussian Process Regression (GPR) model which are used to improve predictive accuracy. Result(s): In this study, standard and hybrid forecasting models are used to evaluate new COVID-19 vaccine cases daily in May and June 2021. To evaluate the effectiveness of the models, the COVID-19 vaccine dataset for Africa was used, which included new vaccine cases daily from 13 January 2021 to 16 May 2021. Root Mean Squared Error (RMSE) and Error Percentage (EP) are used as evaluation measures in this process. The results obtained showed that the hybrid GRNN model performed better than the hybrid ARIMA model. Conclusion(s): HGRNN model provides accurate daily vaccinated case forecast, which helps to maintain optimal vaccine stock to avoid vaccine wastage and save many lives.Copyright © 2023 Dhamodharavadhani S et al.

Class prediction of the prevalent transmission mode of COVID-19 within a geographic area

This research developed a multinomial classification model that predicts the prevalent mode of transmission of the coronavirus from person to person within a geographic area, using data from the World Health Organization (WHO). The WHO defines four transmission modes of the coronavirus disease 2019 (COVID-19);namely, community transmission, pending (unknown), sporadic cases, and clusters of cases. The logistic regression was deployed on the COVID-19 dataset to construct a multinomial model that can predict the prevalent transmission mode of coronavirus within a geographic area. The k-fold cross validation was employed to test predictive accuracy of the model, which yielded 73% accuracy. This model can be adopted by local authorities such as regional, state, local government, and cities, to predict the prevalent transmission mode of the virus within their territories. The outcome of the prediction will determine the appropriate strategies to put in place or re-enforced to curtail further transmission.Copyright © 2023 Inderscience Enterprises Ltd.

Host Genetic Factors, Comorbidities and the Risk of Severe COVID-19.

BACKGROUND: Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), was varied in disease symptoms. We aim to explore the effect of host genetic factors and comorbidities on severe COVID-19 risk. METHODS: A total of 20,320 COVID-19 patients in the UK Biobank cohort were included. Genome-wide association analysis (GWAS) was used to identify host genetic factors in the progression of COVID-19 and a polygenic risk score (PRS) consisted of 86 SNPs was constructed to summarize genetic susceptibility. Colocalization analysis and Logistic regression model were used to assess the association of host genetic factors and comorbidities with COVID-19 severity. All cases were randomly split into training and validation set (1:1). Four algorithms were used to develop predictive models and predict COVID-19 severity. Demographic characteristics, comorbidities and PRS were included in the model to predict the risk of severe COVID-19. The area under the receiver operating characteristic curve (AUROC) was applied to assess the models' performance. RESULTS: We detected an association with rs73064425 at locus 3p21.31 reached the genome-wide level in GWAS (odds ratio: 1.55, 95% confidence interval: 1.36-1.78). Colocalization analysis found that two genes (SLC6A20 and LZTFL1) may affect the progression of COVID-19. In the predictive model, logistic regression models were selected due to simplicity and high performance. Predictive model consisting of demographic characteristics, comorbidities and genetic factors could precisely predict the patient's progression (AUROC = 82.1%, 95% CI 80.6-83.7%). Nearly 20% of severe COVID-19 events could be attributed to genetic risk. CONCLUSION: In this study, we identified two 3p21.31 genes as genetic susceptibility loci in patients with severe COVID-19. The predictive model includes demographic characteristics, comorbidities and genetic factors is useful to identify individuals who are predisposed to develop subsequent critical conditions among COVID-19 patients.

KIR2DL2/C1: A potential predictive immunogenetic marker to COVID-19 severity in Spanish patients

COVID-19 has aspects on its pathogenesis that still need elucidating and an analysis of clinical and immunogenetic factors in each cohort of patients is paramount to understanding how genetic variability can explain the multiple clinical spectra seen in patients infected with SARS-CoV-2. The aim of this study was to correlate the KIR polymorphism/HLA class I ligand interactions from patients and healthy subjects with either the susceptibility or severity to COVID-19. Genotyping of HLA-A, -B, -C and KIR genes were carried out from 459 symptomatic as well as 667 non-infected Spanish Caucasian individuals using Lifecodes HLA-SSO and KIR-SSO kits (ImmucorTM, USA) and analyzed in the Luminex in this uni-centre case-control study performed at the University Hospital of Salamanca, Spain. Comparative KIR gene analysis showed that KIR2DS4 was significantly more representative in healthy versus infected individuals. When comparing subgroups of infected patients, KIR2DS3 had a higher frequency in those who progressed to a more severity disease and yet with higher mortality rate. Three functional combinations were significant on univariate analysis: KIR2DL2/C1, KIR2DS2/C1, and KIR2DS3/C1. However, in the multivariate analysis, only the KIR2DL2/C1 interaction remained significant (OR = 15.2 (95% CI 1.5-147), p = 0.0189). Compared with the solo-clinical characteristics predictive model, that included well-known comorbidity variables such as hypertension, age, sex, diabetes, C-reactive protein, dyslipidemia, smoking, ferritin, and fibrinogen, the clinical-and-KIR-based model showed a better ability to discriminate between severe and nonsevere patients with higher sensitivity and specificity. Our results support a fundamental role of KIR/ligand interaction in the clinical course of COVID-19. Since the KIR2DL2 gene has a high frequency in Spain (60%), the analysis of the KIR2DL2/C1 in symptomatic patients who require hospitalization could be helpful to better determine their prognosis.

Prediction model of intention to use digital fitness services for health promotion during the COVID-19 pandemic: a gender-based multi-group analysis

As the number of people infected with COVID-19 in Korea is increasing, several measures have been implemented to gradually restrict outdoor activities and indoor gatherings while promoting a non-face-to-face social culture. In this study, we performed a gender-based multi-group analysis using a technology acceptance model (TAM) as an external variable for COVID-19 risk perception to verify the model's predictive ability to increase participation behavior toward digital fitness services. We analyzed the data of 433 Koreans using an online survey consisting of 23 items. A structural equation model was used to verify the perceived ease of use (PEOU), perceived usefulness (PU), intention to use and exercise participation behavior of the TAM with COVID-19 risk perception as an external variable. First, our results showed that COVID-19 risk perception had a statistically higher significant and positive effect on PEOU (beta = 0.170, t = 3.296, p < 0.001) than on PU (beta = 0.130, t = 2.848, p = 0.004) of digital fitness services. Second, the PEOU of the digital fitness service was found to have a statistically higher significant positive effect on PU (beta = 0.512, t = 9.728, p < 0.001) than on intention to use (beta = 0.130, t = -2.774, p = 0.006). Third, the PU of digital fitness services was found to have a statistically significant positive effect on the intention to use (beta = 0.684, t = 12.909, p < 0.001). Fourth, the intention to use the digital fitness service was found to have a statistically significant positive effect on exercise participation behavior (beta = 0.796, t = 16.248, p < 0.001). Lastly, we observed a significant difference between men and women in COVID-19 risk perception and PEOU among the six paths established. Digital environments that encourage participation in exercises could promote health during a pandemic. This study highlighted the need to consider digital environments that encourage exercise participation in creating physical exercise contents as there was no significant difference in the intention to use digital fitness services between men and women.Copyright © 2023 The Author(s).

Predictive analysis, diagnosis of COVID-19 through computational screening and validation with spectro photometrical approach

Objective: To develop Favipiravir, based predictive models of coronavirus disease 2019 (COVID-19) from small molecule databases such as PubChem, Drug Bank, Zinc Database, and literature. Method(s): High Throughput Virtual Screening (HTVS) using different computational screening methods is used to identify the target and lead molecules. CoMFA (Comparative Molecular Field Analysis) is a 3D-QSAR procedure depending on information from known dynamic atoms and eventually permits one to plan and anticipate exercises of particles. These two analysis is used to train predictive models. Result(s): The predictive model achieved the highest accuracy score with a relatively small dataset size can be a subject of overfitting. Datasets with over 500 samples demonstrate an accuracy of about 85-95%, that can be considered as very good. Conclusion(s): From the result it is observed that Increasing level of potassium, sodium and nitrogen will lead to burst lipid bilayer membrane of virus which cause RNA replication rapidly. However, low level of sodium, potassium and nitrogen will help in the DNA polymerase inhibition and replication can be stopped. The best developed QSAR model in terms of the druggability and activity relation has been selected over the parent Favipiravir molecule for designing COVID-19 drugs may lead towards pharmaceutical development in future.Copyright © 2023, The Author(s), under exclusive licence to Korean Society of Environmental Risk Assessment and Health Science.

A business retrieval model using scenario planning and analytics for life during and after the pandemic crisis

The COVID-19 pandemic crisis has fundamentally changed the way we live and work forever. The business sector is forecasting and formulating different scenarios associated with the impact of the pandemic on its employees, customers, and suppliers. Various business retrieval models are under construction to cope with life after the COVID-19 Pandemic Crisis. However, the proposed plans and scenarios are static and cannot address the dynamic pandemic changes worldwide. They also have not considered the peripheral in-between scenarios to propel the shifting paradigm of businesses from the existing condition to the new one. Furthermore, the scenario drivers in the current studies are generally centered on the economic aspects of the pandemic with little attention to the social facets. This study aims to fill this gap by proposing scenario planning and analytics to study the impact of the Coronavirus pandemic on large-scale information technology-led Companies. The primary and peripheral scenarios are constructed based on a balanced set of business continuity and employee health drivers. Practical action plans are formulated for each scenario to devise plausible responses. Finally, a damage management framework is developed to cope with the mental disorders of the employees amid the disease.Copyright © 2021 The Author(s)

Study of corona epidemic: Predictive mathematical model

The outbreak of SARS-CoV-2 (Covid-19) is one of the most unprecedented and devastating events that the world has witnessed so far. It was manifested in Wuhan, China in December 2019 and has spread worldwide. The rapidity at which Covid-19 is transmitted has become one of the major concerns regarding the safety of mankind. The similarity of symptoms between Covid-19 and normal flu, like cough, body ache and headache, makes it difficult to ascertain a case to be of normal flu or of Covid. Consequently, many Covid cases are unreported which further increases the risk of spread of infection. In the present chapter, by using three mathematical models, we aim to give an outline of the spread of Covid-19 in West Bengal and how lockdown has helped to reduce the number of Covid cases. The first model is an exponential model;the second model is based on Geometric Progression which shows spread of coronavirus using a tree chart. The third model, named as Model for Stay at Home, shows that due to lockdown, the number of cases is gradually attaining a constant level instead of growing exponentially;thus urging each citizen to stay at home during lockdown unless an unavoidable situation arises. © 2022 Scrivener Publishing LLC.

SARS-CoV-2 severity prediction in young adults using artificial intelligence.

Aim: to build, a predictive model for severe COVID-19 prediction in young adults using deep learning methods. Material(s) and Method(s): data from 906 medical records of patients aged. 18 to 44 years with laboratory-confirmed SARS- CoV-2 infection during 2020-2021 period, was analyzed. Evaluation of laboratory and. instrumental data was carried out using the Mann-Whitney U-test. The level of statistical significance was p<0,05. The neural network was trained, using the Pytorch. framework. Result(s): in patients with mild to moderate SARS-CoV-2 infection, peripheral oxygen saturation, erythrocytes, hemoglobin, total protein, albumin, hematocrit, serum, iron, transferrin, and. absolute peripheral blood, eosinophil and. lymphocyte counts were significantly higher than in patients with severe SOVID-19 (p< 0,001). The values of the absolute number of neutrophils, ESR, glucose, ALT, AST, CPK, urea, LDH, ferritin, CRP, fibrinogen, D-dimer, respiration rate, heart rate, blood, pressure in the group of patients with mild and. moderate severity were statistically significantly lower than in the group of severe patients (p < 0.001). Eleven indicators were identified as predictors of severe COVID-19 (peripheral oxygen level, peripheral blood erythrocyte count, hemoglobin level, absolute eosinophil count, absolute lymphocyte count, absolute neutrophil count, LDH, ferritin, C-reactive protein, D-dimer levels) and. their threshold, values. A model intended, to predict COVID-19 severity in young adults was built. Conclusion. The values of laboratory and instrumental indicators obtained in patients with SARS-CoV-2 infection upon admission significantly differ. Among them, eleven indicators were significantly associated with the development of a severe COVID-19. A predictive model based, on artificial intelligence method, with high, accuracy predicts the likelihood, of severe SARS-CoV-2 course development in young adults.Copyright © 2022 Interregional public organization Association of infectious disease specialists of Saint-Petersburg and Leningrad region (IPO AIDSSPbR). All rights reserved.

SARS-CoV-2 severity prediction in young adults using artificial intelligence.

Aim: to build, a predictive model for severe COVID-19 prediction in young adults using deep learning methods. Material(s) and Method(s): data from 906 medical records of patients aged. 18 to 44 years with laboratory-confirmed SARS- CoV-2 infection during 2020-2021 period, was analyzed. Evaluation of laboratory and. instrumental data was carried out using the Mann-Whitney U-test. The level of statistical significance was p<0,05. The neural network was trained, using the Pytorch. framework. Result(s): in patients with mild to moderate SARS-CoV-2 infection, peripheral oxygen saturation, erythrocytes, hemoglobin, total protein, albumin, hematocrit, serum, iron, transferrin, and. absolute peripheral blood, eosinophil and. lymphocyte counts were significantly higher than in patients with severe SOVID-19 (p< 0,001). The values of the absolute number of neutrophils, ESR, glucose, ALT, AST, CPK, urea, LDH, ferritin, CRP, fibrinogen, D-dimer, respiration rate, heart rate, blood, pressure in the group of patients with mild and. moderate severity were statistically significantly lower than in the group of severe patients (p < 0.001). Eleven indicators were identified as predictors of severe COVID-19 (peripheral oxygen level, peripheral blood erythrocyte count, hemoglobin level, absolute eosinophil count, absolute lymphocyte count, absolute neutrophil count, LDH, ferritin, C-reactive protein, D-dimer levels) and. their threshold, values. A model intended, to predict COVID-19 severity in young adults was built. Conclusion. The values of laboratory and instrumental indicators obtained in patients with SARS-CoV-2 infection upon admission significantly differ. Among them, eleven indicators were significantly associated with the development of a severe COVID-19. A predictive model based, on artificial intelligence method, with high, accuracy predicts the likelihood, of severe SARS-CoV-2 course development in young adults.Copyright © 2022 Interregional public organization Association of infectious disease specialists of Saint-Petersburg and Leningrad region (IPO AIDSSPbR). All rights reserved.

An Early Detection Of NIPAH Infectious Disease Based On Integrated Medical Features For Human Using Ensemble RBM Techniques

Background: The importance of early diagnosis of a hazardous illness cannot be overstated. The transmission rate is extremely high, especially in the current pandemic condition. The ability to predict epidemics will aid public health in reducing mortality and morbidity. Machine Learning (ML) approaches are used in the construction of an effective disease prognosis model. Furthermore, only if the model learns good associated features from the data is it possible to generate a speedy outcome. As a result, selecting features is also necessary before beginning the forecasting process. Objective(s): However, because of the virus's dynamic structure, it's difficult to predict Nipah disease and/or zoonotic infection. Furthermore, there is no clinical treatment for Nipah. The major goal of this research is to develop a prognostic model for early diagnosis of Nipah disease using a combination of several clinical factors such as symptoms, disease incubation information, and routine blood test results confirmed by a lab technician.Proposed System: The healthcare application and data are more complex to handle than other ML applications since various clinical features are assessed throughout disease manifestation. As a result, selecting the most relevant variables is critical when designing a prognosis model for any viral disease. To deal with clinical features from a vast number of features, we proposed a Restricted Boltzmann Machine (RBM) method in this research. Additionally, we employed a hybrid ensemble learning method to predict if the patient was infected with NiV after choosing features using the RBM. Data Collection: The proposed system is being implemented using the NiV infection dataset that erupted in Kozhikode, Kerala in 2018 and 2019. Result(s): The developed stacking-based ensemble Meta classifier was successfully implemented using the python programming language, and its performance was evaluated using a variety of metrics includingaccuracy, precision, recall, f1-score, log loss, AUROC and MCC. Our proposed Stacking Ensemble Meta Classifier (SEMC) model achieved an accuracy rate of 88.3% with a log loss of 0.36. Model precision, recall, f1-score, AUROC, and MCC value were 92.5%, 89.2%, 90.9%, 92.1%, and 0.74 respectively. In addition, we calculated the gravitational pull of each feature using the SHAP approach and discovered that altered sensorium, fever, headache, and cough were the most critical clinical indicators that distinguished NiVD infection from our dataset. Therefore, this classification may assist the pathologist in diagnosing NiVD with symptoms before performing the RT-PCR medical test. Conclusion(s): Using our proposed SEMC technique, we developed a prognostic model for the diagnosis of Nipah in humans. The proposed technique's discriminatory efficiency exhibited good NiVD diagnosis efficacy. We anticipate that this model will aid medics in determining a prognosis more quickly during future epidemics. However, to achieve maximum accuracy, the model requires more unique samples.Copyright © 2022 Wolters Kluwer Medknow Publications. All rights reserved.