Early detection of COVID-19 outbreaks using textual analysis of electronic medical records.

PURPOSE: Our objective was to develop a tool promoting early detection of COVID-19 cases by focusing epidemiological investigations and PCR examinations during a period of limited testing capabilities. METHODS: We developed an algorithm for analyzing medical records recorded by healthcare providers in the Israeli Defense Forces. The algorithm utilized textual analysis to detect patients presenting with suspicious symptoms and was tested among 92 randomly selected units. Detection of a potential cluster of patients in a unit prompted a focused epidemiological investigation aided by data provided by the algorithm. RESULTS: During a month of follow up, the algorithm has flagged 17 of the units for investigation. The subsequent epidemiological investigations led to the testing of 78 persons and the detection of eight cases in four clusters that were previously gone unnoticed. The resulting positive test rate of 10.25% was five time higher than the IDF average at the time of the study. No cases of COVID-19 in the examined units were missed by the algorithm. CONCLUSIONS: This study depicts the successful development and large scale deployment of a textual analysis based algorithm for early detection of COVID-19 cases, demonstrating the potential of natural language processing of medical text as a tool for promoting public health.

Measures to Limit COVID-19 Outbreak Effects Among Military Personnel: Preliminary Data.

INTRODUCTION: The COVID-19 outbreak posed a threat to the readiness of military forces as well as their ability to fulfill missions. Seeing that military forces have been encountering similar challenges, we found it eminent to share the Israeli Defense Force (IDF) Northern Command's (NC) preliminary experience. MATERIALS AND METHODS: We retrospectively summarized the actions that were taken by our team, focusing on 18 battalions at the Israeli NC. These actions included promoting a series of organizational changes in terms of social distancing and medical regulations as well as working to strengthen medical leadership through designated video meetings with medical commanders across our organization. Meetings included relevant clinical education, updates, and leadership building. These actions and others were aimed to increase our influence on the decision-making processes. While we conducted real-time reverse transcriptase polymerase chain reaction SARS-CoV-2 laboratory tests for soldiers who were suspected to have COVID-19 (those presenting with compatible signs and symptoms after having been exposed to a confirmed COVID-19 patient), we were not able to screen healthy populations, nor did we have serum antibody serologic tests available during the study period. We reviewed the COVID-19 outbreak national data, obtained from Ministry of Health publishings and the IDF databases. Data were included from February 26th, 2020 (day 0, first COVID-19 patient in Israel) to April 19th, 2020 (day 53, about 1 month after most of the COVID-19 regulation were issued in the NC). RESULTS: The mean age of the battalion soldiers was 21.29 ± 4.06 (range 18-50), 81.34% male. Most restrictions were issued on day 18. On day 53, 98.85% of the personnel in the battalions were kept active and asymptomatic in their units. CONCLUSIONS: Despite the limited availability of laboratory testing for COVID-19 our actions enabled us to lead a strict risk-management policy while maintaining most of the available workforce.