Search

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.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.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.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.

Kisspeptin, neuropeptide involved in puberty beginning and regulation of pituitary-gonadal axis, has been shown to stimulate antioxidant defenses in murine models. Its levels are greater in females than males and also in obese prepubertal girls. Therefore, our aim was to evaluate sex-related differences in prepubertal obese patients and the relationships of Kisspeptin with metabolic/hormonal parameters.We studied Kisspeptin concentrations in 54 children (22 males and 32 females, Tanner stage 1), 5-12 ys, classified according to Cole's criteria into 17 overweight and 37 obese; 25 normal-weight children, aged 6-12 years, were studied as controls. We evaluated metabolic (glucose and insulin levels after oral glucose load, total- LDL- HDL-cholesterol, triglycerides, uric acid) and hormonal (fT3, fT4, TSH, IGF-1, leptin) parameters. Moreover, total antioxidant capacity (TAC) was evaluated by spectrophotometric method, using the system H202-metmyoglobin-ABTS. Kisspeptin levels were measured by RIA.We did not find significant differences between obese and normal-weight children, but obese males presented significantly lower levels than females. Kisspeptin did not correlate with BMI, HOMA-IR, Insulin peak levels and TAC; a significant correlation was found between Kisspeptin and fT3 (r2=0.25; p=0.003) in the obese group; leptin levels, significantly greater in obese vs. overweight and control children, significantly correlated with TAC (r2=0.39; p=0.03).These data suggest that both hormones could modulate antioxidants, Kisspeptin indirectly via influence on thyroid hormones, and Leptin by a direct effect. This mechanism seems to be sex-related, not attributable to peripheral steroid levels. Further studies can clarify the complex interrelationship between central and peripheral Kisspeptin secretion and oxidative stress in children obesity.