Health related quality of life, physical function, and cognitive performance in mechanically ventilated COVID-19 patients: A long term follow-up study.

BACKGROUND: Survivors of severe COVID-19 related respiratory failure may experience durable functional impairments. We aimed at investigating health-related quality of life (HR-QoL), physical functioning, fatigue, and cognitive outcomes in COVID-19 patients who received invasive mechanical ventilation (IMV). METHODS: Case-series, prospective, observational cohort study at 18 months from hospital discharge. Patients referring to the Intensive Care Unit (ICU) of Humanitas Research Hospital (Milan, Italy) were recruited if they needed IMV due to COVID-19 related respiratory failure. After 18 months, these patients underwent the 6-min walking test (6MWT), the Italian version of the 5-level EQ-5D questionnaire (EQ-5D-5L), the Functional Assessment of Chronic Illness Therapy - Fatigue questionnaire (FACIT-F), the Trail Making Test-B (TMT-B) and the Montreal Cognitive Assessment-BLIND test (MoCA-BLIND). RESULTS: 105 patients were studied. The population's age was 60 ± 10 years on average, with a median Frailty Scale of 2 (Hodgson et al., 2017; Carenzo et al., 2021a [2,3]). EQ-VAS was 80 [70-90] out of 100, walked distance was 406 [331-465] meters, corresponding to about 74 ± 19,1% of the predicted value. FACIT-F score was 43 [36-49] out of 52, and MoCa-BLIND score was 19 (DeSalvo et al., 2006; von Elm et al., 2008; Herdman et al., 2011; Scalone et al., 2015 [16-20]) out of 22. The median TMT-B time was 90 [62-120] seconds. We found a possible age and gender specific effect on HR-QoL and fatigue. CONCLUSIONS: After 18 months from ICU discharge, survivors of severe COVID-19 respiratory failure experience a moderate reduction in HR-QoL, and a severe reduction in physical functioning. Fatigue prevalence is higher in younger patients and in females. Finally, cognitive impairment was present at a low frequency.

AirMLP: A Multilayer Perceptron Neural Network for Temporal Correction of PM2.5 Values in Turin.

In recent times, pollution has emerged as a significant global concern, with European regulations stipulating limits on PM 2.5 particle levels. Addressing this challenge necessitates innovative approaches. Smart low-cost sensors suffer from imprecision, and can not replace legal stations in terms of accuracy, however, their potential to amplify the capillarity of air quality evaluation on the territory is not under discussion. In this paper, we propose an AI system to correct PM 2.5 levels in low-cost sensor data. Our research focuses on data from Turin, Italy, emphasizing the impact of humidity on low-cost sensor accuracy. In this study, different Neural Network architectures that vary the number of neurons per layer, consecutive records and batch sizes were used and compared to gain a deeper understanding of the network's performance under various conditions. The AirMLP7-1500 model, with an impressive R-squared score of 0.932, stands out for its ability to correct PM 2.5 measurements. While our approach is tailored to the city of Turin, it offers a systematic methodology for the definition of those models and holds the promise to significantly improve the accuracy of air quality data collected from low-cost sensors, increasing the awareness of citizens and municipalities about this critical environmental information.