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

• Published in: Journal of primary care & community health Vol. 13; p. 21501319221113544
• Main Authors: Ahmed, Marwa M., Sayed, Amal M., Khafagy, Ghada M., El Sayed, Inas T., Elkholy, Yasmine S., Fares, Ahmed H., Hasan, Marwa D., El Nahas, Heba G., Sarhan, Mai D., Raslan, Eman I., Elsayed, Radwa M., Sayed, Asmaa A., Elmeshmeshy, Eman I., Yassen, Rehab M., Tawfik, Nadia M., Hussein, Hala A., Gaber, Dalia M., Shehata, Mervat M., Fares, Samar
• Format: Journal Article
• Language: English
• Published: Los Angeles, CA SAGE Publications 01.07.2022; SAGE PUBLICATIONS, INC; SAGE Publishing
• Subjects: Accuracy; Classification; Coronaviruses; COVID-19; Deep learning; Health care; Learning; Medical screening; Original Research; Pandemics; Risk factors; Severe acute respiratory syndrome coronavirus 2; Smoking; Symptoms; Triage; COVID-19; deep learning; SARS-CoV-2; family medicine; neural network; phone triage
• ISSN: 2150-1319; 2150-1327
• DOI: 10.1177/21501319221113544

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.