Gemelli decision tree Algorithm to Predict the need for home monitoring or hospitalization of confirmed and unconfirmed COVID-19 patients (GAP-Covid19): preliminary results from a retrospective cohort study.

OBJECTIVE: To develop a deep learning-based decision tree for the primary care setting, to stratify adult patients with confirmed and unconfirmed coronavirus disease 2019 (COVID-19), and to predict the need for hospitalization or home monitoring. PATIENTS AND METHODS: We performed a retrospective cohort study on data from patients admitted to a COVID hospital in Rome, Italy, between 5 March 2020 and 5 June 2020. A confirmed case was defined as a patient with a positive nasopharyngeal RT-PCR test result, while an unconfirmed case had negative results on repeated swabs. Patients' medical history and clinical, laboratory and radiological findings were collected, and the dataset was used to train a predictive model for COVID-19 severity. RESULTS: Data of 198 patients were included in the study. Twenty-eight (14.14%) had mild disease, 62 (31.31%) had moderate disease, 64 (32.32%) had severe disease, and 44 (22.22%) had critical disease. The G2 value assessed the contribution of each collected value to decision tree building. On this basis, SpO2 (%) with a cut point at 92 was chosen for the optimal first split. Therefore, the decision tree was built using values maximizing G2 and LogWorth. After the tree was built, the correspondence between inputs and outcomes was validated. CONCLUSIONS: We developed a machine learning-based tool that is easy to understand and apply. It provides good discrimination in stratifying confirmed and unconfirmed COVID-19 patients with different prognoses in every context. Our tool might allow general practitioners visiting patients at home to decide whether the patient needs to be hospitalized.

Hospital reengineering against COVID-19 outbreak: 1-month experience of an Italian tertiary care center.

OBJECTIVE: The recent outbreak of SARS-CoV-2 infection in Italy has resulted in a sudden and massive flow of patients into emergency rooms, and a high number of hospitalizations with the need for respiratory isolation. Massive admission of patients to the Policlinico "Agostino Gemelli" Foundation of Rome, Italy, determined the need for reengineering the entire hospital. MATERIALS AND METHODS: In this article, we consider some of the structural and organizational changes that have been necessary to deal with the emergency, with particular reference to non-intensive medicine wards, and the preventive measures aimed at limiting the spread of SARS-CoV-2 infection among hospital staff and patients themselves. RESULTS: 577 staff members were subjected to molecular tests in 1-month period and 3.8% of the total were positive. 636 patients admitted to the COVID-19 pathway were included and analyzed: 45.4% were identified as SARS-CoV-2 positive. More SARS-CoV-2 negative patients were discharged in comparison to SARS-CoV-2 positive patients (59% vs. 41%, respectively). On the other hand, more SARS-CoV-2 positive patients were transferred to ICUs in comparison to SARS-CoV-2 negative patients (16% vs. 1%, respectively). Occurrence of death was similar between the two groups, 11% vs. 7%, for SARS-CoV-2 negative and positive patients, respectively. 25% of ≥80 years old SARS-CoV-2 positive patients died during the hospitalization, while death rate was lower in other age groups (5% in 70-79 years old patients and 0% in remaining age groups). CONCLUSIONS: Rapid hospital reengineering has probably had an impact on the management of patients with and without SARS-CoV-2 infection, and on in-hospital mortality rates over the reporting period.