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.

Acute uncomplicated diverticulitis: key points for early management. A single-centre retrospective study.

OBJECTIVE: Acute uncomplicated diverticulitis is an important clinical condition usually managed in clinical practice with antibiotic therapies and hospitalization in ward. In this setting, recent papers and guidelines suggest to limit the use of antibiotics in selected cases and encourage an early discharge in low-risk patients. The purpose of this retrospective study is to identify serological inflammatory markers and CT findings of acute uncomplicated diverticulitis (AUD) at the onset of the disease and the correlation with the need for in-patient or out-patient management. PATIENTS AND METHODS: It was used a database drawn from the collection of the patients admitted to our Emergency Room from January 2016 to 2019 and undergoing urgent abdominal CT-scan for suspicious of acute diverticulitis. For each patient we considered biochemical and radiological parameters at the onset of the disease and if patients were managed as in-patients (hospitalization in ward) or as out-patient (early discharged or after observation in Short Stay Unit). RESULTS: Among patients with early diagnosis of AUD, 108 (65%) were hospitalized in ward with mean time of in-stay of 6.94 days, while only 58 (35%) patients with same diagnosis were managed as out-patient and early discharged from emergency room or after observation in short stay unit with a mean time of in-stay significantly shorter (3.39 days, p-value 0.0007). Higher levels of C reactive protein and the length of colon involved considered as percentage (%) in comparison with the entire colon were significantly related to the need for hospitalization (p-value 0.03). CONCLUSIONS: Biochemical parameters and a more advanced radiological evaluation, as the length (%) of colon involved, could allow a stratification of patients with diagnosis of AUD at the admission and help physicians in the early management.

Knowledge, attitudes and behaviors of the Italian population towards Neisseria meningitidis, Streptococcus pneumoniae and HPV diseases and vaccinations: A cross-sectional multicentre study.

OBJECTIVES: This study addressed knowledge of Streptococcus pneumoniae, Neisseria meningitidis and human papillomavirus (HPV), and attitudes and behaviours towards vaccines against them. STUDY DESIGN: This is a cross-sectional, multicentre study. METHODS: Data were collected through a questionnaire administered to 530 adults who accessed four Departments of Prevention of the Italian National Health Service in 2013. RESULTS: Less than 50% of people gave the right answer to all the questions concerning the three diseases, but 96.2%, 94% and 92.7% agreed with the importance of vaccination against N. meningitidis, S. pneumoniae and HPV, respectively, and 58.4% expressed own willingness to have their children vaccinated with N. meningitidis B vaccine. The attitude towards vaccination was more positive in women for N. meningitidis and in people having children for HPV. Furthermore, individuals giving correct answers to all knowledge items were more in favour of both HPV and S. pneumoniae vaccination. A total of 68.8%, 82.6% and 84.5% of respondents vaccinated their own children against N. meningitidis C, S. pneumoniae and HPV, respectively. About 50% of the respondents reported paediatricians' or other health professionals' recommendations as the main reason for vaccination. CONCLUSIONS: Vaccinations may be promoted through actions aimed at increasing citizens' knowledge. Health professionals should be educated to actively provide information on vaccinations in a clear, comprehensive and effective way.