Prognostic Utility of Left Atrial Strain From MRI Feature Tracking in Ischemic and Nonischemic Dilated Cardiomyopathy: A Multicenter Study.

BACKGROUND. MRI-based prognostic evaluation in patients with dilated cardiomyopathy (DCM) has historically used markers of late gadolinium enhancement (LGE) and feature tracking (FT)-derived left ventricular global longitudinal strain (LVGLS). Early data indicate that FT-derived left atrial strain (LAS) parameters, including reservoir, conduit, and booster, may also have prognostic roles in such patients. OBJECTIVE. The purpose of our study was to evaluate the prognostic utility of LAS parameters, derived from MRI FT, in patients with ischemic or nonischemic DCM, including in comparison with the traditional parameters of LGE and LVGLS. METHODS. This retrospective study included 811 patients with ischemic or nonischemic DCM (median age, 60 years; 640 men, 171 women) who underwent cardiac MRI at any of five centers. FT-derived LAS parameters and LVGLS were measured using two- and four-chamber cine images. LGE percentage was quantified. Patients were assessed for a composite outcome of all-cause mortality or heart failure hospitalization. Multivariable Cox regression analyses including demographic characteristics, cardiovascular risk factors, medications used, and a wide range of cardiac MRI parameters were performed. Kaplan-Meier analyses with log-rank tests were also performed. RESULTS. A total of 419 patients experienced the composite outcome. Patients who did, versus those who did not, experience the composite outcome had larger LVGLS (-6.7% vs -8.3%, respectively; p < .001) as well as a smaller LAS reservoir (13.3% vs 19.3%, p < .001), LAS conduit (4.7% vs 8.0%, p < .001), and LAS booster (8.1% vs 10.3%, p < .001) but no significant difference in LGE (10.1% vs 11.3%, p = .51). In multivariable Cox regression analyses, significant independent predictors of the composite outcome included LAS reservoir (HR = 0.96, p < .001) and LAS conduit (HR = 0.91, p < .001). LAS booster and LGE were not significant independent predictors in the models. LVGLS was a significant independent predictor only in a model that initially included LAS booster but not the other LAS parameters. In Kaplan-Meier analysis, all three LAS parameters were significantly associated with the composite outcome (p < .001). CONCLUSION. In this multicenter study, LAS reservoir and LAS conduit were significant independent prognostic markers in patients with ischemic or nonischemic DCM, showing greater prognostic utility than the currently applied markers of LVGLS and LGE. CLINICAL IMPACT. FT-derived LAS analysis provides incremental prognostic information in patients with DCM.

Prognostic Utility of Cardiac MRI Myocardial Strain Parameters in Patients With Ischemic and Nonischemic Dilated Cardiomyopathy: A Multicenter Study.

BACKGROUND. Prior small single-center studies have yielded conflicting results regarding the prognostic significance of myocardial strain parameters derived from feature tracking (FT) on cardiac MRI in patients with dilated cardiomyopathy (DCM). OBJECTIVE. The purpose of this study was to evaluate the prognostic utility of FT parameters on cardiac MRI in patients with ischemic and nonischemic DCM and to determine the optimal strain parameter for outcome prediction. METHODS. This retrospective study included 471 patients (median age, 61 years; 365 men, 106 women) with ischemic (n = 233) or nonischemic (n = 238) DCM and left ventricular (LV) ejection fraction (EF) less than 50% who underwent cardiac MRI at any of four centers from January 2011 to December 2019. Cardiac MRI parameters were determined by manual contouring. In addition, software-based FT was used to calculate six myocardial strain parameters (LV and right ventricular [RV] global radial strain, global circumferential strain, and global longitudinal strain [GLS]). Late gadolinium enhancement (LGE) was also evaluated. Patients were assessed for a composite outcome of all-cause mortality and/or heart-failure hospitalization. Cox regression models were used to determine associations between strain parameters and the composite outcome. RESULTS. Mean LV EF was 27.5% and mean LV GLS was -6.9%. The median follow-up period was 1328 days. The composite outcome occurred in 220 patients (125 deaths, 95 heart-failure hospitalizations). All six myocardial strain parameters were significant independent predictors of the composite outcome (hazard ratio [HR] = 0.92-1.16; all p < .05). In multivariable models that included age, corrected LV and RV end-diastolic volume, LV and RV EF, and presence of LGE, the only strain parameter that was a significant independent predictor of the composite outcome was LV GLS (HR = 1.13, p = .006); LV EF and presence of LGE were not independent predictors of the composite outcome in the models (p > .05). A LV GLS threshold of -6.8% had sensitivity of 62.6% and specificity of 62.6% in predicting the composite outcome rate at 4.0 years. CONCLUSION. LV GLS, derived from FT on cardiac MRI, is a significant independent predictor of adverse outcomes in patients with DCM. CLINICAL IMPACT. This study strengthens the body of evidence supporting the clinical implementation of FT when performing cardiac MRI in patients with DCM.

Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph.

Triaging and prioritising patients for RT-PCR test had been essential in the management of COVID-19 in resource-scarce countries. In this study, we applied machine learning (ML) to the task of detection of SARS-CoV-2 infection using basic laboratory markers. We performed the statistical analysis and trained an ML model on a retrospective cohort of 5148 patients from 24 hospitals in Hong Kong to classify COVID-19 and other aetiology of pneumonia. We validated the model on three temporal validation sets from different waves of infection in Hong Kong. For predicting SARS-CoV-2 infection, the ML model achieved high AUCs and specificity but low sensitivity in all three validation sets (AUC: 89.9-95.8%; Sensitivity: 55.5-77.8%; Specificity: 91.5-98.3%). When used in adjunction with radiologist interpretations of chest radiographs, the sensitivity was over 90% while keeping moderate specificity. Our study showed that machine learning model based on readily available laboratory markers could achieve high accuracy in predicting SARS-CoV-2 infection.

Long-Term Prognosis of Patients With Coronary Microvascular Disease Using Stress Perfusion Cardiac Magnetic Resonance.

OBJECTIVES: This study investigated the prognosis of coronary microvascular disease (CMD) as determined by stress perfusion cardiac magnetic resonance (CMR) in patients with ischemic symptoms but without significant coronary artery disease (CAD). BACKGROUND: Patients with CMD have poorer prognosis with various cardiac diseases. The myocardial perfusion reserve index (MPRI) derived from noninvasive stress perfusion CMR has been established to diagnose microvascular angina with a threshold MPRI <1.4. The prognosis of CMD as determined by MPRI is unknown. METHODS: Chest pain patients without epicardial CAD or myocardial disease from January 2009 to December 2017 were retrospectively included from 3 imaging centers in Hong Kong (HK). Stress perfusion CMR examinations were performed using either adenosine or adenosine triphosphate. Adequate stress was assessed by achieving splenic switch-off sign. Measurement of MPRI was performed in all stress perfusion CMR scans. Patients were followed for major adverse cardiovascular events defined as all-cause death, acute coronary syndrome (ACS), epicardial CAD development, heart failure hospitalization and non-fatal stroke. RESULTS: A total of 218 patients were studied (mean age 59 ± 12 years; 49.5% male) and the average MPRI of that cohort was 1.56 ± 0.33. Females and a history of hyperlipidemia were predictors of lower MPRI. Major adverse cardiovascular events (MACE) occurred in 15.6% of patients during a median follow-up of 5.5 years (interquartile range: 4.6 to 6.8 years). The optimal cutoff value of MPRI in predicting MACE was found with a threshold MPRI ≤1.47. Patients with MPRI ≤1.47 had three-fold increased risk of MACE compared with those with MPRI >1.47 (hazard ratio [HR]: 3.14; 95% confidence interval [CI]: 1.58 to 6.25; p = 0.001). Multivariate Cox regression after adjusting for age and hypertension demonstrated that MPRI was an independent predictor of MACE (HR: 0.10; 95% CI: 0.03 to 0.34; p < 0.001). CONCLUSIONS: Stress perfusion CMR-derived MPRI is an independent imaging marker that predicts MACE in patients with ischemic symptom and no overt CAD over the medium term.

Development and validation of risk prediction models for COVID-19 positivity in a hospital setting.

OBJECTIVES: To develop: (1) two validated risk prediction models for coronavirus disease-2019 (COVID-19) positivity using readily available parameters in a general hospital setting; (2) nomograms and probabilities to allow clinical utilisation. METHODS: Patients with and without COVID-19 were included from 4 Hong Kong hospitals. The database was randomly split into 2:1: for model development database (n = 895) and validation database (n = 435). Multivariable logistic regression was utilised for model creation and validated with the Hosmer-Lemeshow (H-L) test and calibration plot. Nomograms and probabilities set at 0.1, 0.2, 0.4 and 0.6 were calculated to determine sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). RESULTS: A total of 1330 patients (mean age 58.2 ± 24.5 years; 50.7% males; 296 COVID-19 positive) were recruited. The first prediction model developed had age, total white blood cell count, chest x-ray appearances and contact history as significant predictors (AUC = 0.911 [CI = 0.880-0.941]). The second model developed has the same variables except contact history (AUC = 0.880 [CI = 0.844-0.916]). Both were externally validated on the H-L test (p = 0.781 and 0.155, respectively) and calibration plot. Models were converted to nomograms. Lower probabilities give higher sensitivity and NPV; higher probabilities give higher specificity and PPV. CONCLUSION: Two simple-to-use validated nomograms were developed with excellent AUCs based on readily available parameters and can be considered for clinical utilisation.

Detection of COVID-19 Using Deep Learning Algorithms on Chest Radiographs.

PURPOSE: To evaluate the performance of a deep learning (DL) algorithm for the detection of COVID-19 on chest radiographs (CXR). MATERIALS AND METHODS: In this retrospective study, a DL model was trained on 112,120 CXR images with 14 labeled classifiers (ChestX-ray14) and fine-tuned using initial CXR on hospital admission of 509 patients, who had undergone COVID-19 reverse transcriptase-polymerase chain reaction (RT-PCR). The test set consisted of a CXR on presentation of 248 individuals suspected of COVID-19 pneumonia between February 16 and March 3, 2020 from 4 centers (72 RT-PCR positives and 176 RT-PCR negatives). The CXR were independently reviewed by 3 radiologists and using the DL algorithm. Diagnostic performance was compared with radiologists' performance and was assessed by area under the receiver operating characteristics (AUC). RESULTS: The median age of the subjects in the test set was 61 (interquartile range: 39 to 79) years (51% male). The DL algorithm achieved an AUC of 0.81, sensitivity of 0.85, and specificity of 0.72 in detecting COVID-19 using RT-PCR as the reference standard. On subgroup analyses, the model achieved an AUC of 0.79, sensitivity of 0.80, and specificity of 0.74 in detecting COVID-19 in patients presented with fever or respiratory systems and an AUC of 0.87, sensitivity of 0.85, and specificity of 0.81 in distinguishing COVID-19 from other forms of pneumonia. The algorithm significantly outperforms human readers (P<0.001 using DeLong test) with higher sensitivity (P=0.01 using McNemar test). CONCLUSIONS: A DL algorithm (COV19NET) for the detection of COVID-19 on chest radiographs can potentially be an effective tool in triaging patients, particularly in resource-stretched health-care systems.

Discrimination of pulmonary ground-glass opacity changes in COVID-19 and non-COVID-19 patients using CT radiomics analysis.

PURPOSE: The coronavirus disease 2019 (COVID-19) has evolved into a worldwide pandemic. CT although sensitive in detecting changes suffers from poor specificity in discrimination from other causes of ground glass opacities (GGOs). We aimed to develop and validate a CT-based radiomics model to differentiate COVID-19 from other causes of pulmonary GGOs. METHODS: We retrospectively included COVID-19 patients between 24/01/2020 and 31/03/2020 as case group and patients with pulmonary GGOs between 04/02/2012 and 31/03/2020 as a control group. Radiomics features were extracted from contoured GGOs by PyRadiomics. The least absolute shrinkage and selection operator method was used to establish the radiomics model. We assessed the performance using the area under the curve of the receiver operating characteristic curve (AUC). RESULTS: A total of 301 patients (age mean ±â€¯SD: 64 ±â€¯15 years; male: 52.8 %) from three hospitals were enrolled, including 33 COVID-19 patients in the case group and 268 patients with malignancies or pneumonia in the control group. Thirteen radiomics features out of 474 were selected to build the model. This model achieved an AUC of 0.905, accuracy of 89.5 %, sensitivity of 83.3 %, specificity of 90.0 % in the testing set. CONCLUSION: We developed a noninvasive radiomics model based on CT imaging for the diagnosis of COVID-19 based on GGO lesions, which could be a promising supplementary tool for improving specificity for COVID-19 in a population confounded by ground glass opacity changes from other etiologies.

Frequency and Distribution of Chest Radiographic Findings in Patients Positive for COVID-19.

Background Current coronavirus disease 2019 (COVID-19) radiologic literature is dominated by CT, and a detailed description of chest radiography appearances in relation to the disease time course is lacking. Purpose To describe the time course and severity of findings of COVID-19 at chest radiography and correlate these with real-time reverse transcription polymerase chain reaction (RT-PCR) testing for severe acute respiratory syndrome coronavirus 2, or SARS-CoV-2, nucleic acid. Materials and Methods This is a retrospective study of patients with COVID-19 confirmed by using RT-PCR and chest radiographic examinations who were admitted across four hospitals and evaluated between January and March 2020. Baseline and serial chest radiographs (n = 255) were reviewed with RT-PCR. Correlation with concurrent CT examinations (n = 28) was performed when available. Two radiologists scored each chest radiograph in consensus for consolidation, ground-glass opacity, location, and pleural fluid. A severity index was determined for each lung. The lung scores were summed to produce the final severity score. Results The study was composed of 64 patients (26 men; mean age, 56 years ± 19 [standard deviation]). Of these, 58 patients had initial positive findings with RT-PCR (91%; 95% confidence interval: 81%, 96%), 44 patients had abnormal findings at baseline chest radiography (69%; 95% confidence interval: 56%, 80%), and 38 patients had initial positive findings with RT-PCR testing and abnormal findings at baseline chest radiography (59%; 95% confidence interval: 46%, 71%). Six patients (9%) showed abnormalities at chest radiography before eventually testing positive for COVID-19 with RT-PCR. Sensitivity of initial RT-PCR (91%; 95% confidence interval: 83%, 97%) was higher than that of baseline chest radiography (69%; 95% confidence interval: 56%, 80%) (P = .009). Radiographic recovery (mean, 6 days ± 5) and virologic recovery (mean, 8 days ± 6) were not significantly different (P = .33). Consolidation was the most common finding (30 of 64; 47%) followed by ground-glass opacities (21 of 64; 33%). Abnormalities at chest radiography had a peripheral distribution (26 of 64; 41%) and lower zone distribution (32 of 64; 50%) with bilateral involvement (32 of 64; 50%). Pleural effusion was uncommon (two of 64; 3%). The severity of findings at chest radiography peaked at 10-12 days from the date of symptom onset. Conclusion Findings at chest radiography in patients with coronavirus disease 2019 frequently showed bilateral lower zone consolidation, which peaked at 10-12 days from symptom onset. © RSNA, 2020.