Evaluating Listening Performance for COVID-19 Detection by Clinicians and Machine Learning: Comparative Study.

BACKGROUND: To date, performance comparisons between men and machines have been carried out in many health domains. Yet machine learning (ML) models and human performance comparisons in audio-based respiratory diagnosis remain largely unexplored. OBJECTIVE: The primary objective of this study was to compare human clinicians and an ML model in predicting COVID-19 from respiratory sound recordings. METHODS: In this study, we compared human clinicians and an ML model in predicting COVID-19 from respiratory sound recordings. Prediction performance on 24 audio samples (12 tested positive) made by 36 clinicians with experience in treating COVID-19 or other respiratory illnesses was compared with predictions made by an ML model trained on 1162 samples. Each sample consisted of voice, cough, and breathing sound recordings from 1 subject, and the length of each sample was around 20 seconds. We also investigated whether combining the predictions of the model and human experts could further enhance the performance in terms of both accuracy and confidence. RESULTS: The ML model outperformed the clinicians, yielding a sensitivity of 0.75 and a specificity of 0.83, whereas the best performance achieved by the clinicians was 0.67 in terms of sensitivity and 0.75 in terms of specificity. Integrating the clinicians' and the model's predictions, however, could enhance performance further, achieving a sensitivity of 0.83 and a specificity of 0.92. CONCLUSIONS: Our findings suggest that the clinicians and the ML model could make better clinical decisions via a cooperative approach and achieve higher confidence in audio-based respiratory diagnosis.

AI-SCoRE (artificial intelligence-SARS CoV2 risk evaluation): a fast, objective and fully automated platform to predict the outcome in COVID-19 patients.

PURPOSE: To develop and validate an effective and user-friendly AI platform based on a few unbiased clinical variables integrated with advanced CT automatic analysis for COVID-19 patients' risk stratification. MATERIAL AND METHODS: In total, 1575 consecutive COVID-19 adults admitted to 16 hospitals during wave 1 (February 16-April 29, 2020), submitted to chest CT within 72 h from admission, were retrospectively enrolled. In total, 107 variables were initially collected; 64 extracted from CT. The outcome was survival. A rigorous AI model selection framework was adopted for models selection and automatic CT data extraction. Model performances were compared in terms of AUC. A web-mobile interface was developed using Microsoft PowerApps environment. The platform was externally validated on 213 COVID-19 adults prospectively enrolled during wave 2 (October 14-December 31, 2020). RESULTS: The final cohort included 1125 patients (292 non-survivors, 26%) and 24 variables. Logistic showed the best performance on the complete set of variables (AUC = 0.839 ± 0.009) as in models including a limited set of 13 and 5 variables (AUC = 0.840 ± 0.0093 and AUC = 0.834 ± 0.007). For non-inferior performance, the 5 variables model (age, sex, saturation, well-aerated lung parenchyma and cardiothoracic vascular calcium) was selected as the final model and the extraction of CT-derived parameters was fully automatized. The fully automatic model showed AUC = 0.842 (95% CI: 0.816-0.867) on wave 1 and was used to build a 0-100 scale risk score (AI-SCoRE). The predictive performance was confirmed on wave 2 (AUC 0.808; 95% CI: 0.7402-0.8766). CONCLUSIONS: AI-SCoRE is an effective and reliable platform for automatic risk stratification of COVID-19 patients based on a few unbiased clinical data and CT automatic analysis.

A Pilot Study of the Efficacy and Economical Sustainability of Acute Coronavirus Disease 2019 Patient Management in an Outpatient Setting.

Objective: To report a preliminary experience of outpatient management of patients with Coronavirus disease 2019 (COVID-19) through an innovative approach of healthcare delivery. Patients and Methods: Patients evaluated at the Mild-to-Moderate COVID-19 Outpatient clinics (MMCOs) of San Raffaele University Hospital and Luigi Sacco University Hospital in Milan, Italy, from 1 October 2020 to 31 October 2021 were included. Patients were referred by general practitioners (GPs), Emergency Department (ED) physicians or hospital specialists (HS) in case of moderate COVID-19. A classification and regression tree (CART) model predicting ED referral by MMCO physicians was developed to aid GPs identify those deserving immediate ED admission. Cost-effectiveness analysis was also performed. Results: A total of 660 patients were included. The majority (70%) was referred by GPs, 21% by the ED and 9% by HS. Patients referred by GPs had more severe disease as assessed by peripheral oxygen saturation (SpO2), ratio of arterial oxygen partial pressure to fractional inspired oxygen (PaO2/FiO2), C-reactive protein (CRP) levels and interstitial involvement at lung ultrasound. Among them, 18% were addressed to the ED following MMCO assessment. CART analysis identified three independent predictors, namely home-measured SpO2, age and body mass index (BMI), that robustly divide patients into risk groups of COVID-19 severity. Home-measured SpO2 < 95% and BMI ≥ 33 Kg/m2 defined the high-risk group. The model yielded an accuracy (95% CI) of 83 (77-88)%. Outpatient management of COVID-19 patients allowed the national healthcare system to spare 1,490,422.05 € when compared with inpatient care. Conclusion: Mild-to-moderate COVID-19 outpatient clinics were effective and sustainable in managing COVID-19 patients and allowed to alleviate pressure on EDs and hospital wards, favoring effort redirection toward non-COVID-19 patients.