Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia.

BACKGROUND: Chest radiograph (CXR) is a basic diagnostic test in community-acquired pneumonia (CAP) with prognostic value. We developed a CXR-based artificial intelligence (AI) model (CAP AI predictive Engine: CAPE) and prospectively evaluated its discrimination for 30-day mortality. METHODS: Deep-learning model using convolutional neural network (CNN) was trained with a retrospective cohort of 2235 CXRs from 1966 unique adult patients admitted for CAP from 1 January 2019 to 31 December 2019. A single-centre prospective cohort between 11 May 2020 and 15 June 2020 was analysed for model performance. CAPE mortality risk score based on CNN analysis of the first CXR performed for CAP was used to determine the area under the receiver operating characteristic curve (AUC) for 30-day mortality. RESULTS: 315 inpatient episodes for CAP occurred, with 30-day mortality of 19.4% (n=61/315). Non-survivors were older than survivors (mean (SD)age, 80.4 (10.3) vs 69.2 (18.7)); more likely to have dementia (n=27/61 vs n=58/254) and malignancies (n=16/61 vs n=18/254); demonstrate higher serum C reactive protein (mean (SD), 109 mg/L (98.6) vs 59.3 mg/L (69.7)) and serum procalcitonin (mean (SD), 11.3 (27.8) µg/L vs 1.4 (5.9) µg/L). The AUC for CAPE mortality risk score for 30-day mortality was 0.79 (95% CI 0.73 to 0.85, p<0.001); Pneumonia Severity Index (PSI) 0.80 (95% CI 0.74 to 0.86, p<0.001); Confusion of new onset, blood Urea nitrogen, Respiratory rate, Blood pressure, 65 (CURB-65) score 0.76 (95% CI 0.70 to 0.81, p<0.001), respectively. CAPE combined with CURB-65 model has an AUC of 0.83 (95% CI 0.77 to 0.88, p<0.001). The best performing model was CAPE incorporated with PSI, with an AUC of 0.84 (95% CI 0.79 to 0.89, p<0.001). CONCLUSION: CXR-based CAPE mortality risk score was comparable to traditional pneumonia severity scores and improved its discrimination when combined.

Outcomes for emergency department patients with suspected and confirmed COVID-19: An analysis of the Australian experience in 2020 (COVED-5).

OBJECTIVE: The aim of the present study was to describe the characteristics and outcomes of patients presenting to Australian EDs with suspected and confirmed COVID-19 during 2020, and to determine the predictors of in-hospital death for SARS-CoV-2 positive patients. METHODS: This analysis from the COVED Project presents data from 12 sites across four Australian states for the period from 1 April to 30 November 2020. All adult patients who met local criteria for suspected COVID-19 and underwent testing for SARS-CoV-2 in the ED were eligible for inclusion. Study outcomes were mechanical ventilation and in-hospital mortality. RESULTS: Among 24 405 eligible ED presentations over the whole study period, 423 tested positive for SARS-CoV-2. During the 'second wave' from 1 July to 30 September 2020, 26 (6%) of 406 SARS-CoV-2 patients received invasive mechanical ventilation, compared to 175 (2%) of the 9024 SARS-CoV-2 negative patients (odds ratio [OR] 3.5; 95% confidence interval [CI] 2.3-5.2, P < 0.001), and 41 (10%) SARS-CoV-2 positive patients died in hospital compared to 312 (3%) SARS-CoV-2 negative patients (OR 3.2; 95% CI 2.2-4.4, P = 0.001). For SARS-CoV-2 positive patients, the strongest independent predictors of hospital death were age (OR 1.1; 95% CI 1.1-1.1, P < 0.001), higher triage category (OR 3.5; 95% CI 1.3-9.4, P = 0.012), obesity (OR 4.2; 95% CI 1.2-14.3, P = 0.024) and receiving immunosuppressive treatment (OR 8.2; 95% CI 1.8-36.7, P = 0.006). CONCLUSIONS: ED patients who tested positive for SARS-CoV-2 had higher odds of mechanical ventilation and death in hospital. The strongest predictors of death were age, a higher triage category, obesity and receiving immunosuppressive treatment.

Design and Multicenter Clinical Validation of a 3-Dimensionally Printed Nasopharyngeal Swab for SARS-CoV-2 Testing.

Importance: Three-dimensionally printed nasopharyngeal swabs (3DP swabs) have been used to mitigate swab shortages during the coronavirus disease 2019 (COVID-19) pandemic. Clinical validation for diagnostic accuracy and consistency, as well as patient acceptability, is crucial to evaluate the swab's performance. Objective: To determine the accuracy and acceptability of the 3DP swab for identifying severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Design, Setting, and Participants: A diagnostic study was conducted from May to July 2020 at 2 tertiary care centers in Singapore with different reference swabs (FLOQSwab [COPAN Diagnostics] or Dacron swab [Deltalab]) and swab processing techniques (wet or dry) to evaluate the performance of the 3DP swab compared with traditional, standard-of-care nasopharyngeal swabs used in health care institutions. The participants were patients with COVID-19 in the first 2 weeks of illness and controls with acute respiratory illness with negative test results for SARS-CoV-2. Paired nasopharyngeal swabs were obtained from the same nostril and tested for SARS-CoV-2 by reverse-transcriptase polymerase chain reaction. The sequence of swabs was randomized based on odd and even participant numbers. Main Outcomes and Measures: Primary outcome measures were overall agreement (OA), positive percentage agreement (PPA), and negative percentage agreement of the 3DP swab compared with reference swabs. Secondary outcome measures were the correlation of cycle threshold (Ct) values of both swabs. Results: The mean (SD) age of participants was 45.4 (13.1) years, and most participants were men (87 of 89 [97.8%]), in keeping with the epidemiology of the COVID-19 pandemic in Singapore. A total of 79 patients with COVID-19 and 10 controls were recruited. Among the patients with COVID-19, the overall agreement and PPA of the 3DP swab was 91.1% and 93.5%, respectively, compared with reference swabs. The PPA was 100% for patients with COVID-19 who were tested within the first week of illness. All controls tested negative. The reverse-transcriptase polymerase chain reaction Ct values for the ORF1ab and E-gene targets showed a strong correlation (intraclass correlations coefficient, 0.869-0.920) between the 3DP and reference swab on independent testing at each institution despite differences in sample processing. Discordant results for both gene targets were observed only at high Ct values. Conclusions and Relevance: In this diagnostic study of 79 patients with COVID-19 and 10 controls, the 3DP swab performed accurately and consistently across health care institutions and could help mitigate strained resources in the escalating COVID-19 pandemic.

Clinical Diagnostic Study of a Novel Injection Molded Swab for SARS-Cov-2 Testing.

INTRODUCTION: The gold standard for COVID-19 diagnosis is currently a real-time reverse transcriptase polymerase chain reaction (RT-PCR) to detect SARS-CoV-2. This is most commonly performed on respiratory secretions obtained via a nasopharyngeal swab. Due to supply chain limitations and high demand worldwide because of the COVID-19 pandemic, access to commercial nasopharyngeal swabs has not been assured. 3D printing methods have been used to meet the shortfall. For longer-term considerations, 3D printing may not compare well with injection molding as a production method due to the challenging scalability and greater production costs of 3D printing. METHODS: To secure sufficient nasopharyngeal swab availability for our national healthcare system, we designed a novel injection molded nasopharyngeal swab (the IM2 swab). We performed a clinical diagnostic study comparing the IM2 swab to the Copan FLOQSwab. Forty patients with a known diagnosis of COVID-19 and 10 healthy controls were recruited. Paired nasopharyngeal swabs were obtained from the same nostril of each participant and tested for SARS-CoV-2 by RT-PCR. RESULTS: When compared to the Copan FLOQswab, results from the IM2 swab displayed excellent overall agreement and positive percent agreement of 96.0% and 94.9%, respectively. There was no significant difference in mean RT-PCR cycle threshold values for the ORF1ab (28.05 vs. 28.03, p = 0.97) and E-gene (29.72 vs. 29.37, p = 0.64) targets, respectively. We did not observe any significant adverse events and there was no significant difference in patient-reported pain. CONCLUSION: In summary, the IM2 nasopharyngeal swab is a clinically safe, highly accurate option to commercial nasopharyngeal swabs.