A Computational Approach in the Diagnostic Process of COVID-19: The Missing Link between the Laboratory and Emergency Department.

BACKGROUND: The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is responsible for the COVID-19 pandemic and so it is crucial the right evaluation of viral infection. According to the Centers for Disease Control and Prevention (CDC), the Real-Time Reverse Transcription PCR (RT-PCR) in respiratory samples is the gold standard for confirming the disease. However, it has practical limitations as time-consuming procedures and a high rate of false-negative results. We aim to assess the accuracy of COVID-19 classifiers based on Arificial Intelligence (AI) and statistical classification methods adapted on blood tests and other information routinely collected at the Emergency Departments (EDs). METHODS: Patients admitted to the ED of Careggi Hospital from April 7th-30th 2020 with pre-specified features of suspected COVID-19 were enrolled. Physicians prospectively dichotomized them as COVID-19 likely/unlikely case, based on clinical features and bedside imaging support. Considering the limits of each method to identify a case of COVID-19, further evaluation was performed after an independent clinical review of 30-day follow-up data. Using this as a gold standard, several classifiers were implemented: Logistic Regression (LR), Quadratic Discriminant Analysis (QDA), Random Forest (RF), Support Vector Machine (SVM), Neural Networks (NN), K-nearest neighbor (K-NN), Naive Bayes (NB). RESULTS: Most of the classifiers show a ROC >0.80 on both internal and external validation samples but the best results are obtained applying RF, LR and NN. The performance from the external validation sustains the proof of concept to use such mathematical models fast, robust and efficient for a first identification of COVID-19 positive patients. These tools may constitute both a bedside support while waiting for RT-PCR results, and a tool to point to a deeper investigation, by identifying which patients are more likely to develop into positive cases within 7 days. CONCLUSIONS: Considering the obtained results and with a rapidly changing virus, we believe that data processing automated procedures may provide a valid support to the physicians facing the decision to classify a patient as a COVID-19 case or not.

A 4C mortality score based dichotomic rule supports Emergency Department discharge of COVID-19 patients.

BACKGROUND: For COVID-19 patients evaluated in the Emergency Department (ED), decision on hospital admission vs home discharge is challenging. The 4C mortality score (4CMS) is a prognostication tool integrating key demographic/clinical/biochemical data validated for COVID-19 inpatients. We sought to derive and validate a dichotomic rule based on 4CMS identifying patients with mild outcomes, suitable for safe ED discharge. METHODS: Derivation was performed in a prospective cohort of ED patients with suspected COVID-19 from two centers (April 2020). Validation was pursued in a prospective multicenter cohort of ED patients with confirmed COVID-19 from 6 centers (October 2020 to January 2021). Chest x-ray (CXR) images were independently scored. The primary composite outcome was all-cause 30-day mortality or hospital admission. Secondary outcomes were ED re-visit, oxygen therapy and ventilation. RESULTS: In a derivation cohort of 838 ED patients with suspected COVID-19, 4CMS ≤8 was associated with low outpatient mortality (0.4%) and was thus selected as a feasible discharge rule. In a validation cohort of 521 COVID-19 outpatients, the mean age was 51±17 years; 97 (18.6%) patients had ≥1 CXR infiltrate. The 4CMS had an AUC of 0.82 for the primary outcome and 0.93 for mortality, outperforming other scores (CURB-65, qCSI, qSOFA, NEWS) and CXR. In 474 (91%) patients with 4CMS≤8, the mortality rate was 0.2% and the hospital admission rate was 6.8%, versus 12.8% and 36.2% for 4CMS≥9 (P<0.001). CXR did not provide additional discrimination. CONCLUSIONS: COVID-19 outpatients with 4CMS≤8 have mild outcomes and can be safely discharged from the ED. [NCT0462918].

Lung Ultrasound Improves Outcome Prediction over Clinical Judgment in COVID-19 Patients Evaluated in the Emergency Department.

In the Emergency Department (ED), the decision to hospitalize or discharge COVID-19 patients is challenging. We assessed the utility of lung ultrasound (LUS), alone or in association with a clinical rule/score. This was a multicenter observational prospective study involving six EDs (NCT046291831). From October 2020 to January 2021, COVID-19 outpatients discharged from the ED based on clinical judgment were subjected to LUS and followed-up at 30 days. The primary clinical outcome was a composite of hospitalization or death. Within 393 COVID-19 patients, 35 (8.9%) reached the primary outcome. For outcome prognostication, LUS had a C-index of 0.76 (95%CI 0.68-0.84) and showed good performance and calibration. LUS-based classification provided significant differences in Kaplan-Meier curves, with a positive LUS leading to a hazard ratio of 4.33 (95%CI 1.95-9.61) for the primary outcome. The sensitivity and specificity of LUS for primary outcome occurrence were 74.3% (95%CI 59.8-88.8) and 74% (95%CI 69.5-78.6), respectively. The integration of LUS with a clinical score further increased sensitivity. In patients with a negative LUS, the primary outcome occurred in nine (3.3%) patients (p < 0.001 vs. unselected). The efficiency for rule-out was 69.7%. In unvaccinated ED patients with COVID-19, LUS improves prognostic stratification over clinical judgment alone and may support standardized disposition decisions.

The presentations/physician ratio predicts door-to-physician time but not global length of stay in the emergency department: an Italian multicenter study during the SARS-CoV-2 pandemic.

To investigate the effects of the dramatic reduction in presentations to Italian Emergency Departments (EDs) on the main indicators of ED performance during the SARS-CoV-2 pandemic. From February to June 2020 we retrospectively measured the number of daily presentations normalized for the number of emergency physicians on duty (presentations/physician ratio), door-to-physician and door-to-final disposition (length-of-stay) times of seven EDs in the central area of Tuscany. Using the multivariate regression analysis we investigated the relationship between the aforesaid variables and patient-level (triage codes, age, admissions) or hospital-level factors (number of physician on duty, working surface area, academic vs. community hospital). We analyzed data from 105,271 patients. Over ten consecutive 14-day periods, the number of presentations dropped from 18,239 to 6132 (- 67%) and the proportion of patients visited in less than 60 min rose from 56 to 86%. The proportion of patients with a length-of-stay under 4 h decreased from 59 to 52%. The presentations/physician ratio was inversely related to the proportion of patients with a door-to-physician time under 60 min (slope - 2.91, 95% CI - 4.23 to - 1.59, R2 = 0.39). The proportion of patients with high-priority codes but not the presentations/physician ratio, was inversely related to the proportion of patients with a length-of-stay under 4 h (slope - 0.40, 95% CI - 0.24 to - 0.27, R2 = 0.36). The variability of door-to-physician time and global length-of-stay are predicted by different factors. For appropriate benchmarking among EDs, the use of performance indicators should consider specific, hospital-level and patient-level factors.

Laryngotracheal aspiration test reduce the false negative rate in patients with suspected SARS-COV-2 pneumonia despite a negative nasopharyngeal swab.

BACKGROUND: In the emergency department (ED) definitive diagnosis of SARS-COV-2 pneumonia is challenging as nasopharyngeal swab (NPS) can give false negative results. Strategies to reduce false negative rate of NPS have limitations. Serial NPSs (24-48 h from one another) are time-consuming, sputum can not be collected in the majority of patients, and bronchoalveolar lavage (BAL), the most sensitive test, requires specific expertise. Laryngotracheal aspiration (LTA) is easy to perform and showed a similar accuracy to BAL for diagnosis of other pulmonary diseases, however it was not studied to diagnose SARS-COV-2 pneumonia. OBJECTIVE: An observational cross-sectional study was performed to evaluate the negative predictive value of LTA in patients with suspected SARS-COV-2 pneumonia despite a negative NPS. METHODS: In the EDs of two university hospitals, consecutive patients with suspected SARS-COV-2 pneumonia despite a negative NPS underwent LTA performed with a nasotracheal tube connected to a vacuum system. Final diagnosis based on all respiratory specimen tests (NPS, LTA and BAL) and hospital data was established by two reviewers and in case of discordance by a third reviewer. RESULTS: 117 patients were enrolled. LTA was feasible in all patients and no patients experienced adverse events. Fifteen (12.7%) patients were diagnosed with community-acquired SARS-COV-2 pneumonia: 13 LTA positive and only 2 (1.7%) LTA negative. The negative predictive value of NPS and LTA was 87.3% (79.9% - 92.7%) and 98.1% (93.3%99.8%) respectively. CONCLUSIONS: LTA resulted feasible, safe and reduced false negative rate in patients with suspected SARS-COV-2 pneumonia despite a negative NPS.

Lung ultrasound for the early diagnosis of COVID-19 pneumonia: an international multicenter study.

PURPOSE: To analyze the application of a lung ultrasound (LUS)-based diagnostic approach to patients suspected of COVID-19, combining the LUS likelihood of COVID-19 pneumonia with patient's symptoms and clinical history. METHODS: This is an international multicenter observational study in 20 US and European hospitals. Patients suspected of COVID-19 were tested with reverse transcription-polymerase chain reaction (RT-PCR) swab test and had an LUS examination. We identified three clinical phenotypes based on pre-existing chronic diseases (mixed phenotype), and on the presence (severe phenotype) or absence (mild phenotype) of signs and/or symptoms of respiratory failure at presentation. We defined the LUS likelihood of COVID-19 pneumonia according to four different patterns: high (HighLUS), intermediate (IntLUS), alternative (AltLUS), and low (LowLUS) probability. The combination of patterns and phenotypes with RT-PCR results was described and analyzed. RESULTS: We studied 1462 patients, classified in mild (n = 400), severe (n = 727), and mixed (n = 335) phenotypes. HighLUS and IntLUS showed an overall sensitivity of 90.2% (95% CI 88.23-91.97%) in identifying patients with positive RT-PCR, with higher values in the mixed (94.7%) and severe phenotype (97.1%), and even higher in those patients with objective respiratory failure (99.3%). The HighLUS showed a specificity of 88.8% (CI 85.55-91.65%) that was higher in the mild phenotype (94.4%; CI 90.0-97.0%). At multivariate analysis, the HighLUS was a strong independent predictor of RT-PCR positivity (odds ratio 4.2, confidence interval 2.6-6.7, p < 0.0001). CONCLUSION: Combining LUS patterns of probability with clinical phenotypes at presentation can rapidly identify those patients with or without COVID-19 pneumonia at bedside. This approach could support and expedite patients' management during a pandemic surge.

Diagnostic accuracy of physician's gestalt in suspected COVID-19: Prospective bicentric study.

OBJECTIVES: Physicians' gestalt is central in the diagnostic pipeline of suspected COVID-19, due to the absence of a single tool allowing conclusive rule in or rule out. The aim of this study was to estimate the diagnostic test characteristics of physician's gestalt for COVID-19 in the emergency department (ED), based on clinical findings or on a combination of clinical findings and bedside imaging results. METHODS: From April 1 to April 30, 2020, patients with suspected COVID-19 were prospectively enrolled in two EDs. Physicians prospectively dichotomized patients in COVID-19 likely or unlikely twice: after medical evaluation of clinical features (clinical gestalt [CG]) and after evaluation of clinical features and results of lung ultrasound or chest x-ray (clinical and bedside imaging-integrated gestalt [CBIIG]). The final diagnosis was adjudicated after independent review of 30-day follow-up data. RESULTS: Among 838 ED enrolled patients, 193 (23%) were finally diagnosed with COVID-19. The area under the curve (AUC), sensitivity, and specificity of CG and CBIIG for COVID-19 were 80.8% and 91.6% (p < 0.01), 82.9% and 91.4% (p = 0.01), and 78.6% and 91.8% (p < 0.01), respectively. CBIIG had similar AUC and sensitivity to reverse transcription-polymerase chain reaction (RT-PCR) for SARS-CoV-2 on the first nasopharyngeal swab per se (93.5%, p = 0.24; and 87%, p = 0.17, respectively). CBIIG plus RT-PCR had a sensitivity of 98.4% for COVID-19 (p < 0.01 vs. RT-PCR alone) compared to 95.9% for CG plus RT-PCR (p = 0.05). CONCLUSIONS: In suspected COVID-19, CG and CBIIG have fair diagnostic accuracy, in line with physicians' gestalt for other acute conditions. Negative RT-PCR plus low probability based on CBIIG can rule out COVID-19 with a relatively low number of false-negative cases.

A simple lung ultrasound protocol for the screening of COVID-19 pneumonia in the emergency department.

The most relevant manifestation of coronavirus disease 2019 (COVID-19) is interstitial pneumonia. Several lung ultrasound (US) protocols for pneumonia diagnosis are used in clinical practice, but none has been proposed for COVID-19 patients' screening in the emergency department. We adopted a simplified 6-scan lung US protocol for COVID-19 pneumonia diagnosis (LUSCOP) and compared its sensitivity with high resolution computed tomography (HRCT) in patients suspected for COVID-19, presenting to one Emergency Department from February 21st to March 15th, 2020, during the outbreak burst in northern Italy. Patients were retrospectively enrolled if both LUSCOP protocol and HRCT were performed in the Emergency Department. The sensitivity of LUSCOP protocol and HRCT were compared. COVID-19 pneumonia's final diagnosis was based on real-time reverse-transcription polymerase chain reaction from nasal-pharyngeal swab and on clinical data. Out of 150 suspected COVID-19 patients, 131 were included in the study, and 130 had a final diagnosis of COVID-19 pneumonia. The most frequent lung ultrasonographic features were: bilateral B-pattern in 101 patients (77%), B-pattern with subpleural consolidations in 26 (19.8%) and lung consolidations in 2 (1.5%). LUSCOP Protocol was consistent with HRCT in correctly screening 130 out of the 131 COVID-19 pneumonia cases (99.2%). In one case COVID-19 pneumonia was excluded by both HRCT and lung US. LUSCOP protocol showed optimal sensitivity and can be proposed as a simple screening tool for COVID-19 pneumonia diagnosis in the context of outbreak burst areas where prompt isolation of suspected patients is crucial for patients' and operators' safety.

Chest X-ray in the emergency department during COVID-19 pandemic descending phase in Italy: correlation with patients' outcome.

PURPOSE: The aims of our study are: (1) to estimate admission chest X-ray (CXR) accuracy during the descending phase of pandemic; (2) to identify specific CXR findings strictly associated with COVID-19 infection; and (3) to correlate lung involvement of admission CXR with patients' outcome. MATERIALS AND METHODS: We prospectively evaluated the admission CXR of 327 patients accessed to our institute during the Italian pandemic descending phase (April 2020). For each CXR were searched ground glass opacification (GGO), consolidation (CO), reticular-nodular opacities (RNO), nodules, excavations, pneumothorax, pleural effusion, vascular congestion and cardiac enlargement. For lung alterations was defined the predominance (upper or basal, focal or diffuse, central or peripheric, etc.). Then radiologists assessed whether CXRs were suggestive or not for COVID-19 infection. For COVID-19 patients, a prognostic score was applied and correlated with the patients' outcome. RESULTS: CXR showed 83% of specificity and 60% of sensitivity. GGO, CO, RNO and a peripheric, diffuse and basal prevalence showed good correlation with COVID-19 diagnosis. A logistic regression analysis pointed out GGO and a basal or diffuse distribution as independent predictors of COVID-19 diagnosis. The prognostic score showed good correlation with the patients' outcome. CONCLUSION: In our study, admission CXR showed a fair specificity and a good correlation with patients' outcome. GGO and others CXR findings showed a good correlation with COVID-19 diagnosis; besides GGO a diffuse or bibasal distribution resulted in independent variables highly suggestive for COVID-19 infection thus enabling radiologists to signal to clinicians radiologically suspect patients during the pandemic descending phase.

Multi-organ point-of-care ultrasound for COVID-19 (PoCUS4COVID): international expert consensus.

COVID-19 has caused great devastation in the past year. Multi-organ point-of-care ultrasound (PoCUS) including lung ultrasound (LUS) and focused cardiac ultrasound (FoCUS) as a clinical adjunct has played a significant role in triaging, diagnosis and medical management of COVID-19 patients. The expert panel from 27 countries and 6 continents with considerable experience of direct application of PoCUS on COVID-19 patients presents evidence-based consensus using GRADE methodology for the quality of evidence and an expedited, modified-Delphi process for the strength of expert consensus. The use of ultrasound is suggested in many clinical situations related to respiratory, cardiovascular and thromboembolic aspects of COVID-19, comparing well with other imaging modalities. The limitations due to insufficient data are highlighted as opportunities for future research.