RESUMEN
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.
RESUMEN
Aim: to build, a predictive model for severe COVID-19 prediction in young adults using deep learning methods. Materials and methods: 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. Results: 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 СOVID-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. © 2022 Interregional public organization Association of infectious disease specialists of Saint-Petersburg and Leningrad region (IPO AIDSSPbR). All rights reserved.
RESUMEN
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.
RESUMEN
AIM: To evaluate clinical efficacy of nucleoside analogues in therapy of moderate COVID-19 in in-patients. MATERIALS AND METHODS: Retrospective processing of 108 completed clinical cases with moderate novel coronavirus disease was carried out for the period 2020-2021. The duration of the disease at the time of admission did not exceed three days. Experimental group consisted of 53 patients who, in addition to standard therapy, were prescribed "off-label" riamilovir at a daily dosage of 1250 mg for 5 days by the decision of the medical commission. Comparison group included 55 patients who received a combination of umifenovir and ribavirin as antiviral therapy for 5 days. The duration of the main clinical manifestations of the disease, the indicators of clinical and biochemical blood tests, results of the SARS-CoV-2 virus RNA study using the nucleic acid amplification method (NAAT diagnostics). RESULTS: Significantly faster achievement of clinical improvement in the group of patients treated with riamilovir was shown, as well as faster sanitation from SARS-CoV-2 virus based on the results of etiological testing. CONCLUSION: The use of riamilovir for the treatment of patients with moderate novel coronavirus infection (COVID-19) resulted in a significant reduction of general infectious syndromes and respiratory symptoms. Patients from the experimental group significantly faster achieved clinical recovery and sanitation from the pathogen according to the results of NAAT diagnostics.
Asunto(s)
Tratamiento Farmacológico de COVID-19 , Humanos , SARS-CoV-2 , Nucleósidos , Estudios Retrospectivos , Antivirales , Inhibidores de la Síntesis del Ácido NucleicoRESUMEN
Aim. The study evaluates clinical effectiveness and safety of etiotropic antiviral medications with a direct mechanism of action (Riamiiovir, Ribavirin, Umifenovir) for the treatment of moderate SARS-CoV-2 infection in adults. Materials and methods. The study used the data from 59 health records of patients with moderate PCR-confirmed SARS-CoV-2 infection. Control group included 29 patients treated with 1250 mg Riamiiovir off-label per day for 5 days (250 mg 5 times a day), comparison group consisted of 30 patients, who received 800 mg Ribavirin and Umifenovir per day for 5 days. The effectiveness of the medications was assessed by the duration and severity of general infectious and respiratory syndromes, anosmia and ageusia, as well as the oxygen content in the blood, the timing of SARS-COV-2 virus elimination from the body according to the results of control studies of nasopharyngeal swabs using the PCR method and dynamics of blood tests results. Results. A statistically significant decrease in the duration of fever, cough, and anosmia and a more rapid elimination of the virus from the body were noted in the group of patients receiving Riamiiovir. Decreased levels of non-specific inflammatory markers in blood serum, as well as normal values of liver enzymes were observed in control group during therapy, as opposed to the comparison group. No serious adverse events were noted when using the medication. Conclusion. Nucleoside analogue medication Riamiiovir showed good effectiveness and safety profile in adult patients with moderate SARS-CoV-2 infection.
RESUMEN
AIM: In this study we evaluated the effects of Riamilovir on SARS-CoV-2 viral shedding and on admission duration in patients with moderate COVID-19. MATERIALS AND METHODS: We have used data from 69 health records of patients with moderate severe PCR confirmed SARS-CoV-2 infection. Control group included 34 patients treated with off-label riamilovir 1250 mg per day for 5 days (250 mg 5 times a day), comparison groups 35 patients, who received ribavirin and umifenovir 800 mg a day for 5 days. The antiviral therapy was administered within 72 hours from the onset of the disease. The primary endpoints were elimination of virus in oropharyngeal and nasopharyngeal swabs on 7 day of admission and discharge from the hospital by 14 day. RESULTS: Patients assigned to riamilovir had significantly shorter time to clinical improvement as well as increased PCR negative rate by day 7. CONCLUSION: Yearly administration of riamilovir as opposed to the umifenovir and ribavirin in therapy of moderate SARS-CoV-2 infection was associated with significant shorter time to clinical improvement by 14 day of hospitalization. PCR negative rate by 7 days of hospitalization is significantly more likely in riamilovir group.
RESUMEN
Aim. In this study we evaluated clinical effectiveness and safety of nebulized prostacyclin in patients with Novel Coronavirus Disease (SARS-CoV-2). Materials and methods: We have included 44 male patients with moderate PCR confirmed SARS-CoV-2 infection in this study. Control group consisted of 23 patients treated with nebulized prostacyclin (PGI2). besides standard therapy. We compared intensiveness and duration of infectious intoxication syndrome, duration of fever, cough as well as SpO2 level, complete blood count and chemokine status values. Results: Statistically significant difference in duration of fever, cough, intensiveness and duration of infectious intoxication syndrome were observed. Lymphocyte and platelet counts were significantly higher in control group We have also noticed significantly lower level of proinflammatory mediators and C4-complement component in control group. Only 1 adverse effect associated with inhaled prostacyclin was reported. Conclusion. Nebulized prostacyclin showed therapeutic efficacy and good safety profile in adults with moderate CO-VID-19.