Development of machine learning models to predict RT-PCR results for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in patients with influenza-like symptoms using only basic clinical data.

BACKGROUND: Reverse Transcription-Polymerase Chain Reaction (RT-PCR) for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) diagnosis currently requires quite a long time span. A quicker and more efficient diagnostic tool in emergency departments could improve management during this global crisis. Our main goal was assessing the accuracy of artificial intelligence in predicting the results of RT-PCR for SARS-COV-2, using basic information at hand in all emergency departments. METHODS: This is a retrospective study carried out between February 22, 2020 and March 16, 2020 in one of the main hospitals in Milan, Italy. We screened for eligibility all patients admitted with influenza-like symptoms tested for SARS-COV-2. Patients under 12 years old and patients in whom the leukocyte formula was not performed in the ED were excluded. Input data through artificial intelligence were made up of a combination of clinical, radiological and routine laboratory data upon hospital admission. Different Machine Learning algorithms available on WEKA data mining software and on Semeion Research Centre depository were trained using both the Training and Testing and the K-fold cross-validation protocol. RESULTS: Among 199 patients subject to study (median [interquartile range] age 65 [46-78] years; 127 [63.8%] men), 124 [62.3%] resulted positive to SARS-COV-2. The best Machine Learning System reached an accuracy of 91.4% with 94.1% sensitivity and 88.7% specificity. CONCLUSION: Our study suggests that properly trained artificial intelligence algorithms may be able to predict correct results in RT-PCR for SARS-COV-2, using basic clinical data. If confirmed, on a larger-scale study, this approach could have important clinical and organizational implications.

Dysfunctional eating in type 2 diabetes mellitus: A multicenter Italian study of socio-demographic and clinical associations.

BACKGROUND AND AIMS: Dysfunctional eating might impact on the management and metabolic control of type 2 diabetes (T2DM), modifying adherence to healthy diet and food choices. METHODS AND RESULTS: In a multicenter study, we assessed the prevalence of dysfunctional eating in 895 adult outpatients with T2DM (51% males, median age 67, median BMI 30.3 kg/m2). Socio-demographic and clinical characteristics were recorded; dysfunctional eating was tested by validated questionnaires (Eating Attitude Test-EAT-26, Binge Eating Scale-BES; Night Eating Questionnaire-NEQ); food intake and adherence to Mediterranean diet were also measured (in-house developed questionnaire and Mediterranean Diet Score-MDS). Obesity was present in 52% of cases (10% obesity class III), with higher rates in women; 22% had HbA1c ≥ 8%. The EAT-26 was positive in 19.6% of women vs. 10.2% of men; BES scores outside the normal range were recorded in 9.4% of women and 4.4% of men, with 3.0% and 1.5% suggestive of binge eating disorder, respectively. Night eating (NEQ) was only present in 3.2% of women and 0.4% of men. Critical EAT and BES values were associated with higher BMI, and all NEQ + ve cases, but one, were clustered among BES + ve individuals. Calorie intake increased with BES, NEQ, and BMI, and decreased with age and with higher adherence to Mediterranean diet. In multivariable logistic regression analysis, female sex, and younger age were associated with increase risk of dysfunctional eating. CONCLUSION: Dysfunctional eating is present across the whole spectrum of T2DM and significantly impacts on adherence to dietary restriction and food choices.