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.

Composite Criteria for Non-Operative Management of Acute Non-Complicated Appendicitis Result in Low Failure Rates.

BACKGROUND: The aim of this study is to investigate the outcomes of conservative management of non-complicated acute appendicitis (AA) using our unique institutional protocol, and to compare between these and the outcomes of operative management. METHODS: Patients admitted to our institution between March 2016 and October 2019 with non-complicated AA were grouped according to their initial management: non-operative versus surgical. Our unique protocol for non-operative management includes: pain < 3 days; afebrile upon admission; non-gravid; WBC <15,000 (× 109/L); CRP < 5 mg/dl; appendix diameter < 1 cm; no appendicolith on imaging; no prior episode of AA; no history of Inflammatory Bowel Disease; no evidence of peritonitis on physical examination. The primary outcome measured was failure of non-surgical management during the index admission. Secondary outcomes included recurrence rate, readmissions, complications, length of antibiotic treatment and length of stay (LOS). RESULTS: A total of 695 patients were included, 436 in the operative group and 259 in the non-surgical treatment group. The mean follow-up time was 1004.9 ± 205.7 days. Patients initially treated conservatively rarely required surgery during their index admission (6.9%). Recurrence rate was 19.1% after a mean follow up of 33.4 months. The overall failure rate of conservative management was documented in 20.8% of the patients. The complication rate was higher in those treated with upfront surgery (1.6% vs. 0.4%, p < 0.001). The overall LOS was not statistically different between the groups. CONCLUSIONS: Our composite protocol for non-surgical management of non-complicated AA results in a low failure rate. A well calculated patient treatment allocation in non-complicated AA can advocate for wide-spread use of the conservative approach.

The Decreasing Incidence of Acute Appendicitis During COVID-19: A Retrospective Multi-centre Study.

BACKGROUND: As the novel coronavirus disease 19 (COVID-19) spreads, a decrease in the number of patients with acute appendicitis (AA) has been noted in our institutions. The aim of this study was to compare the incidence and severity of AA before and during the COVID-19 pandemic. METHODS: A retrospective cohort analysis was performed between December 2019 and April 2020 in the four high-volume centres that provide health care to the municipality of Jerusalem, Israel. Two groups were created. Group A consisted of patients who presented in the 7 weeks prior to COVID-19 first being diagnosed, whilst those in the 7 weeks after were allocated to Group B. A comparison was performed between the clinicopathological features of the patients in each group as was the changing incidence of AA. RESULTS: A total of 378 patients were identified, 237 in Group A and 141 in Group B (62.7% vs. 37.3%). Following the onset of COVID-19, the weekly incidence of AA decreased by 40.7% (p = 0.02). There was no significant difference between the groups in terms of the length of preoperative symptoms or surgery, need for postoperative peritoneal drainage or the distribution of complicated versus uncomplicated appendicitis. CONCLUSIONS: The significant decrease in the number of patients admitted with AA during the onset of COVID-19 possibly represents successful resolution of mild appendicitis treated symptomatically by patients at home. Further research is needed to corroborate this assumption and identify those patients who may benefit from this treatment pathway.