Automated calculation of the right ventricle to left ventricle ratio on CT for the risk stratification of patients with acute pulmonary embolism.

OBJECTIVES: To assess the feasibility and reliability of the use of artificial intelligence post-processing to calculate the RV:LV diameter ratio on computed tomography pulmonary angiography (CTPA) and to investigate its prognostic value in patients with acute PE. METHODS: Single-centre, retrospective study of 101 consecutive patients with CTPA-proven acute PE. RV and LV volumes were segmented on 1-mm contrast-enhanced axial slices and maximal ventricular diameters were derived for RV:LV ratio using automated post-processing software (IMBIO LLC, USA) and compared to manual analysis in two observers, via intraclass coefficient correlation analysis. Each CTPA report was analysed for mention of the RV:LV ratio and compared to the automated RV:LV ratio. Thirty-day all-cause mortality post-CTPA was recorded. RESULTS: Automated RV:LV analysis was feasible in 87% (n = 88). RV:LV ratios ranged from 0.67 to 2.43, with 64% (n = 65) > 1.0. There was very strong agreement between manual and automated RV:LV ratios (ICC = 0.83, 0.77-0.88). The use of automated analysis led to a change in risk stratification in 45% of patients (n = 40). The AUC of the automated measurement for the prediction of all-cause 30-day mortality was 0.77 (95% CI: 0.62-0.99). CONCLUSION: The RV:LV ratio on CTPA can be reliably measured automatically in the majority of real-world cases of acute PE, with perfect reproducibility. The routine use of this automated analysis in clinical practice would add important prognostic information in patients with acute PE. KEY POINTS: • Automated calculation of the right ventricle to left ventricle ratio was feasible in the majority of patients and demonstrated perfect intraobserver variability. • Automated analysis would have added important prognostic information and altered risk stratification in the majority of patients. • The optimal cut-off value for the automated right ventricle to left ventricle ratio was 1.18, with a sensitivity of 100% and specificity of 54% for the prediction of 30-day mortality.

Uncertainty quantification in computed tomography pulmonary angiography.

Computed tomography (CT) imaging of the thorax is widely used for the detection and monitoring of pulmonary embolism (PE). However, CT images can contain artifacts due to the acquisition or the processes involved in image reconstruction. Radiologists often have to distinguish between such artifacts and actual PEs. We provide a proof of concept in the form of a scalable hypothesis testing method for CT, to enable quantifying uncertainty of possible PEs. In particular, we introduce a Bayesian Framework to quantify the uncertainty of an observed compact structure that can be identified as a PE. We assess the ability of the method to operate under high-noise environments and with insufficient data.

Screening success: A virtual MDT can reduce the number of patients requiring respiratory follow-up post-COVID-19 pneumonia in line with British Thoracic Society guidance.

Introduction and objectivesThe ongoing respiratory sequelae of COVID-19 pneumonia remain unclear, and the ideal follow-up of these patients is still a work in progress. We describe our experience of using a pre-follow-up multidisciplinary team (MDT) to decide the follow-up stream in patients hospitalised for COVID-19 pneumonia. METHODS: We reviewed all patients with a clinico-radiological diagnosis of COVID-19 admitted to hospital during a 3-month period and assigned a follow-up stream based on British Thoracic Society guidance. RESULTS: We changed the follow-up pathway in 71% (277/392) and refined the pathway in 67% (261/392) of indeterminate cases. We also created an automated process for the general practitioner to book follow-up imaging and will use this process going forward. CONCLUSION: These findings highlight the importance of the MDT review of cases with suspected COVID-19 pneumonia prior to clinic attendance to ensure appropriate patients are followed up and to optimise utilisation of outpatient imaging and clinics.

IMproving PULmonary hypertension Screening by Echocardiography: IMPULSE.

BACKGROUND: The world symposium on pulmonary hypertension (PH) has proposed that PH be defined as a mean pulmonary artery pressure (mPAP) > 20 mmHg as assessed by right heart catheterisation (RHC). Transthoracic echocardiography (TTE) is an established screening tool used for suspected PH. International guidelines recommend a multi-parameter assessment of the TTE PH probability although effectiveness has not been established using real world data. STUDY AIMS: To determine accuracy of the European Society of Cardiology (ESC) and British Society of Echocardiography (BSE) TTE probability algorithm in detecting PH in patients attending a UK PH centre. To identify echocardiographic markers and revised algorithms to improve the detection of PH in those with low/intermediate BSE/ESC TTE PH probability. METHODS: TTE followed by RHC (within 4 months after) was undertaken in patients for suspected but previously unconfirmed PH. BSE/ESC PH TTE probabilities were calculated alongside additional markers of right ventricular (RV) longitudinal and radial function, and RV diastolic function. A refined IMPULSE algorithm was devised and evaluated in patients with low and/or intermediate ESC/BSE TTE PH probability. RESULTS: Of 310 patients assessed, 236 (76%) had RHC-confirmed PH (average mPAP 42.8 ± 11.7). Sensitivity and specificity for detecting PH using the BSE/ESC recommendations was 89% and 68%, respectively. 36% of those with low BSE/ESC TTE probability had RHC-confirmed PH and BSE/ESC PH probability parameters did not differ amongst those with and without PH in the low probability group. Conversely, RV free wall longitudinal strain (RVFWLS) was lower in patients with vs. without PH in low BSE/ESC probability group (- 20.6 ± 4.1% vs - 23.8 ± 3.9%) (P < 0.02). Incorporating RVFWLS and TTE features of RV radial and diastolic function (RVFAC and IVRT) within the IMPULSE algorithm reduced false negatives in patients with low BSE/ESC PH probability by 29%. The IMPULSE algorithm had excellent specificity and positive predictive value in those with low (93%/80%, respectively) or intermediate (82%/86%, respectively) PH probability. CONCLUSION: Existing TTE PH probability guidelines lack sensitivity to detect patients with milder haemodynamic forms of PH. Combining additional TTE makers assessing RV radial, longitudinal and diastolic function enhance identification of milder forms of PH, particularly in those who have a low BSE/ESC TTE PH probability.

Multiple dimensions of excessive daytime sleepiness.

BACKGROUND: In this study we investigated subjective measures of sleepiness and related our findings to dimensions of affect, fatigue, emotion, mood and quality of life based on a hypothetical multidimensional model of sleepiness. METHODS: Patients referred to a sleep clinic were assessed regarding their excessive daytime sleepiness (EDS), sleep complaints, routine and symptoms. Age, gender and body mass index (BMI), the Epworth Sleepiness Scale (ESS), the Stanford Sleepiness Scale (SSS), the Samn-Perelli fatigue Scale (SPS), the Global Vigor and Affect Scale (GVS and GAS, respectively), the Hospital Anxiety and Depression Scale (HADS-A and HADS-D, respectively), and the Positive and Negative Affect Schedule (PAS and NAS, respectively) scores were recorded. RESULTS: Fifty patients [25 male, 45.2 (18.7) years] completed the questionnaires. The ESS scores were positively correlated with SSS, SPS, HADS-A, HADS-D and NAS scores and negatively with GVS and GAS scores (P<0.05). The SPS (P<0.001) and HADS-A scores (P=0.002) were independently associated with the ESS scores (R2=0.532, adjusted R2 =0.4794, P<0.001). CONCLUSIONS: A model of sleepiness that assesses dimensions of fatigue and anxiety could explain the symptom of subjective sleepiness better than the isolated use of the ESS.