Search

The aim of this work is to investigate possible relationships between air quality and the spread of the pandemic. We evaluate the performance of machine learning techniques in predicting new cases. Specifically, we describe a cross-correlation analysis on daily COVID-19 cases and environmental factors, such as temperature, relative humidity, and atmospheric pollutants. Our analysis confirms a significant association of some environmental parameters with the spread of the virus. This suggests that machine learning models trained using environmental parameters might provide accurate predictions about the number of infected cases. Our empirical evaluation shows that temperature and ozone are negatively correlated with confirmed cases (therefore, the higher the values of these parameters, the lower the number of infected cases), whereas atmospheric particulate matter and nitrogen dioxide are positively correlated. We developed and compared three different predictive models to test whether these technologies can be useful to estimate the evolution of the pandemic. [ABSTRACT FROM AUTHOR]

Objective: We report performance indicators and costs of the first round of a cervical cancer screening programme based on the human papillomavirus (HPV)-DNA test., Methods: We implemented a demonstration study using HPV as the primary test in Guidonia, Italy (90,000 inhabitants). All women aged 25-64 were invited to undergo a Hybrid Capture II high-risk HPV test. Two cervical samplings, smear and liquid, were taken. The smear was dyed and interpreted only for HPV-positive (HPV+) women. Women with a non-negative Pap smear were referred for colposcopy, women HPV+/cytology negative were referred to one-year follow-up with HPV. A cost-analysis indicated the price at which the HPV-based and cytological screening would cost the same per screened woman and per lesion found., Results: Of 24,000 women invited, 7639 accepted and 427 (5.6%) were HPV+; 141 (34%) of these had a non-negative Pap test, and 20 cervical intraepithelial neoplasia (CIN) 2 or higher were found (positive predictive value 15%). Compliance to one-year follow-up was 58% (166/286); 90 (54%) were HPV-positive and five additional lesions were found (positive predictive value 9%; overall detection rate 3.4/1000). The cost analysis showed that at a price of 8.3 euros per HPV-DNA test, the strategy using HPV as primary test followed by cytological triage would cost the same per screened woman, while at a price of 12.7 euros it would have the same cost per CIN2+ found., Conclusion: The workload for management of positive women was similar to cytological screening. Low compliance to one-year follow-up was the main barrier to effectiveness. The price of HPV test should be about 9 euros to maintain the same screening budget, and can go as high as 13 euros per lesion found.