Rapid Assessment of COVID-19 Mortality Risk with GASS Classifiers.

Risk prediction models are fundamental to effectively triage incoming COVID-19 patients. However, current triaging methods often have poor predictive performance, are based on variables that are expensive to measure, and often lead to hard-to-interpret decisions. We introduce two new classification methods that can predict COVID-19 mortality risk from the automatic analysis of routine clinical variables with high accuracy and interpretability. SVM22-GASS and Clinical-GASS classifiers leverage machine learning methods and clinical expertise, respectively. Both were developed using a derivation cohort of 499 patients from the first wave of the pandemic and were validated with an independent validation cohort of 250 patients from the second pandemic phase. The Clinical-GASS classifier is a threshold-based classifier that leverages the General Assessment of SARS-CoV-2 Severity (GASS) score, a COVID-19-specific clinical score that recently showed its effectiveness in predicting the COVID-19 mortality risk. The SVM22-GASS model is a binary classifier that non-linearly processes clinical data using a Support Vector Machine (SVM). In this study, we show that SMV22-GASS was able to predict the mortality risk of the validation cohort with an AUC of 0.87 and an accuracy of 0.88, better than most scores previously developed. Similarly, the Clinical-GASS classifier predicted the mortality risk of the validation cohort with an AUC of 0.77 and an accuracy of 0.78, on par with other established and emerging machine-learning-based methods. Our results demonstrate the feasibility of accurate COVID-19 mortality risk prediction using only routine clinical variables, readily collected in the early stages of hospital admission.

Is venous thromboembolism a predictable marker in older patients with COVID-19 infection? A single-center observational study.

Venous thromboembolism (VTE) represents an important clinical complication of patients with SARS-CoV-2 infection, and high plasma D-dimer levels could suggest a higher risk of hypercoagulability. We aimed to analyse if laboratory exams, risk assessment scores, comorbidity scores were useful in predicting the VTE in SARS-CoV-2 patients admitted in internal medicine (IM). We evaluated 49 older adults with suspected VTE analysing history and blood chemistry, besides we calculated the Padua Prediction Score, the modified early warning scoring (MEWS) and the modified Elixhauser index (mEI). All patients underwent venous color-doppler ultrasounds of the lower limbs. Out of the 49 patients enrolled (mean age 79.3±14 years), 10 (20.4%) had deep vein thrombosis (DVT), and they were more frequently female (80% vs 20%, p = 0.04). We could not find any association with the Padua Prediction Score, the MEWS, and the mEI. D-dimer plasma levels were also not associated with DVT. In elderly people hospitalized with SARS-CoV-2 infection hospitalized in IM, our data, although limited by the sample size, suggest that prediction and diagnosis of VTE is difficult, due to lack of precise biomarkers and scores.

Don't stop walking: the in-home rehabilitation program for peripheral artery disease patients during the COVID-19 pandemic.

We studied the outcomes of peripheral artery disease (PAD) patients enrolled in a structured in-home walking program right before the lockdown due to the SARS-CoV-2 epidemic emergency, to determine whether this intervention ensured the maintenance of mobility even in the case of movement restrictions.We selectively studied 83 patients (age 72 ± 11, males n = 65) enrolled in the program within 9-month before the lockdown. The usual intervention was based on two daily 8-min sessions of slow intermittent in-home walking prescribed in circa-monthly hospital visits. During the lockdown, the program was updated by phone. Six-minute (6MWD) and pain-free walking distance (PFWD) were measured pre- and post-lockdown as well as body weight (BW), blood pressure (BP), and ankle-brachial index (ABI). Sixty-six patients were measured 117 ± 23 days after their previous visit. A safe, pain-free execution of the prescribed sessions was reported (median distance: 74 km). Overall, the 6MWD was stable, while PFWD improved (p < 0.001). The improvement was not related to age/gender, comorbidities, type of home but to the time of enrollment before lockdown. The new-entry subjects (≤ 3 months; n = 35) obtained significant improvements post-lockdown for 6MWD and PFWD, while those previously enrolled (> 3 months; n = 31) were stable. Decreased BW with stable BP and ABI values were also recorded, with better outcomes for new-entry subjects. In PAD patients, a structured walking program performed inside home and purposely guided by phone was adhered to by patients and favored mobility and risk factor control during the COVID-19 pandemic, regardless of walking ability, type of home and external conditions.