Diagnosis of coronavirus disease 2019 and the potential role of deep learning: insights from the experience of Cairo University Hospitals.

OBJECTIVES: Early detection of coronavirus disease 2019 (COVID-19) is crucial for patients and public health to ensure pandemic control. We aimed to correlate clinical and laboratory data of patients with COVID-19 and their polymerase chain reaction (PCR) results and to assess the accuracy of a deep learning model in diagnosing COVID-19. METHODS: This was a retrospective study using an anonymized dataset of patients with suspected COVID-19. Only patients with a complete dataset were included (n = 440). A deep analytics framework and dual-modal approach for PCR-based classification was used, integrating symptoms and laboratory-based modalities. RESULTS: Participants with loss of smell or taste were two times more likely to have positive PCR results (odds ratio [OR] 1.86). Participants with neutropenia, high serum ferritin, or monocytosis were three, four, and five times more likely to have positive PCR results (OR 2.69, 4.18, 5.42, respectively). The rate of accuracy achieved using the deep learning framework was 78%, with sensitivity of 83.9% and specificity of 71.4%. CONCLUSION: Loss of smell or taste, neutropenia, monocytosis, and high serum ferritin should be routinely assessed with suspected COVID-19 infection. The use of deep learning for diagnosis is a promising tool that can be implemented in the primary care setting.

Accuracy of the Traditional COVID-19 Phone Triaging System and Phone Triage-Driven Deep Learning Model.

OBJECTIVES: During the COVID-19 pandemic, a quick and reliable phone-triage system is critical for early care and efficient distribution of hospital resources. The study aimed to assess the accuracy of the traditional phone-triage system and phone triage-driven deep learning model in the prediction of positive COVID-19 patients. SETTING: This is a retrospective study conducted at the family medicine department, Cairo University. METHODS: The study included a dataset of 943 suspected COVID-19 patients from the phone triage during the first wave of the pandemic. The accuracy of the phone triaging system was assessed. PCR-dependent and phone triage-driven deep learning model for automated classifications of natural human responses was conducted. RESULTS: Based on the RT-PCR results, we found that myalgia, fever, and contact with a case with respiratory symptoms had the highest sensitivity among the symptoms/ risk factors that were asked during the phone calls (86.3%, 77.5%, and 75.1%, respectively). While immunodeficiency, smoking, and loss of smell or taste had the highest specificity (96.9%, 83.6%, and 74.0%, respectively). The positive predictive value (PPV) of phone triage was 48.4%. The classification accuracy achieved by the deep learning model was 66%, while the PPV was 70.5%. CONCLUSION: Phone triage and deep learning models are feasible and convenient tools for screening COVID-19 patients. Using the deep learning models for symptoms screening will help to provide the proper medical care as early as possible for those at a higher risk of developing severe illness paving the way for a more efficient allocation of the scanty health resources.

Molecular characterization of carbapenem-resistant Acinetobacter baumannii clinical isolates from Egyptian patients.

Acinetobacter baumannii (A. baumannii) represents a global threat owing to its ability to resist most of the currently available antimicrobial agents. Moreover, emergence of carbapenem resistant A. baumannii (CR-AB) isolates limits the available treatment options. Enzymatic degradation by variety of ß-lactamases, have been identified as the most common mechanism of carbapenem resistance in A. baumannii. The alarming increase in the prevalence of CR-AB necessitates continuous screening and molecular characterization to appreciate the problem. The present study was performed to assess the prevalence and characterize carbapenemases among 206 CR-AB isolated from various clinical specimens collected from different intensive care units at Kasr Al-Aini Hospital. All isolates were confirmed to be A. baumannii by detection of the blaOXA-51-like gene. Molecular screening of 13 common Ambler class bla carbapenemases genes in addition to insertion sequence (IS-1) upstream OXA-23 were performed by using four sets of multiplex PCR, followed by identification using gene sequencing technology. Among the investigated genes, the prevalence of blaOXA-23, and blaOXA-58 were 77.7%, and 1.9%, respectively. The ISAba1 was detected in 10% of the blaOXA-23 positive isolates. The prevalence of metallo-ß-lactamases (MBLs) studied; blaNDM-1, blaSPM, blaVIM, blaSIM-1 were 11.7%, 6.3%, 0.5%, and 0.5% respectively. One of class A; bla KPC was detected in 10.7% of the investigated isolates. blaOXA-24/40, blaIMP, blaGES, blaVEB and blaGIM were not detected in any of the studied isolates. Moreover, 18.4% of the isolates have shown to harbor two or more of the screened bla genes. We concluded that the most prevalent type of ß-lactamases genes among CR-AB isolates collected from Egyptian patients were blaOXA-23 followed by blaNDM-1 and blaKPC.

Interleukin-17 Gene Expression and Serum Levels in AsthmaDegenerative Model.

Asthma is one of the most common chronic respiratory diseases. It is associated with significant morbidity and shows an increasing prevalence over time. Accumulating evidence suggests that interleukin (IL)-17 has a key role in severe asthma. The aim of the study was to determine quantitatively gene expression of IL-17 in peripheral blood mononuclear cells (PBMN) & the level of IL-17 in the serum of asthmatic patients, to correlate the level of IL-17 with the severity of asthma and to compare between gene expression of IL-17 and its serum level. Forty (40) asthmatic patients were enrolled and subdivided into 2 subgroups; controlled & uncontrolled asthma according to GINA, 2014. In addition, twenty (20) healthy control subjects were included. Blood samples were subjected to real time PCR assays for IL-17 mRNA gene expression and serum was tested by ELISA for estimation of IL-17 serum levels. Significant higher serum IL-17 levels were found in patients with uncontrolled asthma compared to patients with controlled asthma and healthy control group. Mean serum IL-17 value was 87.24 pg/ml in uncontrolled asthma, 75.9 pg/ml in controlled asthma and 47.0 pg/ml in healthy group (P= 0.00). IL-17 mRNA gene expression levels (ΔΔ Ct) were also significantly elevated in uncontrolled asthma compared to patients with controlled asthma and healthy control group. Mean IL-17 mRNA gene expression levels were 33.7 units in uncontrolled asthma, 7.0 in controlled asthma and 0.30 in healthy group (P=0.00).

Diagnostic Role of CD64 on Different Immune Cells in Early Diagnosis of Neonatal Sepsis.

Neonatal sepsis is an important cause of morbidity and mortality among neonates. Early diagnosis leads to better prognosis. CD64 can be used as an early marker to detect neonatal sepsis with promising results. Advances in flow cytometry have made it possible to assess its level on different white blood cells rapidly, precisely and with minimal blood. The aim of the present work was to assess the role of CD64 expressed on neutrophils, monocytes and lymphocytes in establishing diagnosis of neonatal sepsis as well as to compare its diagnostic value with CRP in diagnosis of neonatal sepsis. This study was performed on 80 neonates divided into 60 cases of neonatal sepsis (48 case of clinical sepsis & 12 cases of lab confirmed sepsis) and 20 healthy control neonates. Cases and controls were subjected to history taking, clinical examination and lab investigations in the form of CBC, CRP, CD64 expression on neutrophils, monocytes & lymphocytes and Blood culture (for cases only). Our study showed that CD64 expression on WBCs increases significantly in neonates with neonatal sepsis (P < 0.05) in comparison to controls. Results also showed that neutrophils CD 64 is the most sensitive indicator for detection of sepsis (sensitivity=95%, NPV=78.57%) at a cut off value of 0.18%, whereas CRP has shown the best specificity at a cut off value 3mg/Ml (specificity= 85%). In conclusion, neutrophil CD64 is superior to monocyte and lymphocyte CD64 and serum CRP in diagnosis of neonatal sepsis.