Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- CT angiography (1)
- NT‐proBNP (1)
- acute decompensated heart failure (1)
- aneurysmal subarachnoid hemorrhage (1)
- aneurysms (1)
- congestion (1)
- convolutional neural networks (1)
- deep learning (1)
- inferior vena cava (1)
- ultrasound (1)
Aims
Treating patients with acute decompensated heart failure (ADHF) presenting with volume overload is a common task. However, optimal guidance of decongesting therapy and treatment targets are not well defined. The inferior vena cava (IVC) diameter and its collapsibility can be used to estimate right atrial pressure, which is a measure of right‐sided haemodynamic congestion. The CAVA‐ADHF‐DZHK10 trial is designed to test the hypothesis that ultrasound assessment of the IVC in addition to clinical assessment improves decongestion as compared with clinical assessment alone.
Methods and results
CAVA‐ADHF‐DZHK10 is a randomized, controlled, patient‐blinded, multicentre, parallel‐group trial randomly assigning 388 patients with ADHF to either decongesting therapy guided by ultrasound assessment of the IVC in addition to clinical assessment or clinical assessment alone. IVC ultrasound will be performed daily between baseline and hospital discharge in all patients. However, ultrasound results will only be reported to treating physicians in the intervention group. Treatment target is relief of congestion‐related signs and symptoms in both groups with the additional goal to reduce the IVC diameter ≤21 mm and increase IVC collapsibility >50% in the intervention group. The primary endpoint is change in N‐terminal pro‐brain natriuretic peptide from baseline to hospital discharge. Secondary endpoints evaluate feasibility, efficacy of decongestion on other scales, and the impact of the intervention on clinical endpoints.
Conclusions
CAVA‐ADHF‐DZHK10 will investigate whether IVC ultrasound supplementing clinical assessment improves decongestion in patients admitted for ADHF.
Purpose
To evaluate whether a deep learning model (DLM) could increase the detection sensitivity of radiologists for intracranial aneurysms on CT angiography (CTA) in aneurysmal subarachnoid hemorrhage (aSAH).
Methods
Three different DLMs were trained on CTA datasets of 68 aSAH patients with 79 aneurysms with their outputs being combined applying ensemble learning (DLM-Ens). The DLM-Ens was evaluated on an independent test set of 104 aSAH patients with 126 aneuryms (mean volume 129.2 ± 185.4 mm3, 13.0% at the posterior circulation), which were determined by two radiologists and one neurosurgeon in consensus using CTA and digital subtraction angiography scans. CTA scans of the test set were then presented to three blinded radiologists (reader 1: 13, reader 2: 4, and reader 3: 3 years of experience in diagnostic neuroradiology), who assessed them individually for aneurysms. Detection sensitivities for aneurysms of the readers with and without the assistance of the DLM were compared.
Results
In the test set, the detection sensitivity of the DLM-Ens (85.7%) was comparable to the radiologists (reader 1: 91.2%, reader 2: 86.5%, and reader 3: 86.5%; Fleiss κ of 0.502). DLM-assistance significantly increased the detection sensitivity (reader 1: 97.6%, reader 2: 97.6%,and reader 3: 96.0%; overall P=.024; Fleiss κ of 0.878), especially for secondary aneurysms (88.2% of the additional aneurysms provided by the DLM).
Conclusion
Deep learning significantly improved the detection sensitivity of radiologists for aneurysms in aSAH, especially for secondary aneurysms. It therefore represents a valuable adjunct for physicians to establish an accurate diagnosis in order to optimize patient treatment.