PROTEUS Study: A Prospective Randomized Controlled Trial Evaluating the Use of Artificial Intelligence in Stress Echocardiography.

BACKGROUND: Stress echocardiography (SE) is one of the most commonly used diagnostic imaging tests for coronary artery disease (CAD) but requires clinicians to visually assess scans to identify patients who may benefit from invasive investigation and treatment. EchoGo Pro provides an automated interpretation of SE based on artificial intelligence (AI) image analysis. In reader studies, use of EchoGo Pro when making clinical decisions improves diagnostic accuracy and confidence. Prospective evaluation in real world practice is now important to understand the impact of EchoGo Pro on the patient pathway and outcome. METHODS: PROTEUS is a randomized, multicenter, 2-armed, noninferiority study aiming to recruit 2,500 participants from National Health Service (NHS) hospitals in the UK referred to SE clinics for investigation of suspected CAD. All participants will undergo a stress echocardiogram protocol as per local hospital policy. Participants will be randomized 1:1 to a control group, representing current practice, or an intervention group, in which clinicians will receive an AI image analysis report (EchoGo Pro, Ultromics Ltd, Oxford, UK) to use during image interpretation, indicating the likelihood of severe CAD. The primary outcome will be appropriateness of clinician decision to refer for coronary angiography. Secondary outcomes will assess other health impacts including appropriate use of other clinical management approaches, impact on variability in decision making, patient and clinician qualitative experience and a health economic analysis. DISCUSSION: This will be the first study to assess the impact of introducing an AI medical diagnostic aid into the standard care pathway of patients with suspected CAD being investigated with SE. TRIAL REGISTRATION: Clinicaltrials.gov registration number NCT05028179, registered on 31 August 2021; ISRCTN: ISRCTN15113915; IRAS ref: 293515; REC ref: 21/NW/0199.

Quantitative multiparametric magnetic resonance imaging can aid non-alcoholic steatohepatitis diagnosis in a Japanese cohort.

BACKGROUND: Non-invasive assessment of non-alcoholic steatohepatitis (NASH) is increasing in desirability due to the invasive nature and costs associated with the current form of assessment; liver biopsy. Quantitative multiparametric magnetic resonance imaging (mpMRI) to measure liver fat (proton density fat fraction) and fibroinflammatory disease [iron-corrected T1 (cT1)], as well as elastography techniques [vibration-controlled transient elastography (VCTE) liver stiffness measure], magnetic resonance elastography (MRE) and 2D Shear-Wave elastography (SWE) to measure stiffness and fat (controlled attenuated parameter, CAP) are emerging alternatives which could be utilised as safe surrogates to liver biopsy. AIM: To evaluate the agreement of non-invasive imaging modalities with liver biopsy, and their subsequent diagnostic accuracy for identifying NASH patients. METHODS: From January 2019 to February 2020, Japanese patients suspected of NASH were recruited onto a prospective, observational study and were screened using non-invasive imaging techniques; mpMRI with LiverMultiScan ®, VCTE, MRE and 2D-SWE. Patients were subsequently biopsied, and samples were scored by three independent pathologists. The diagnostic performances of the non-invasive imaging modalities were assessed using area under receiver operating characteristic curve (AUC) with the median of the histology scores as the gold standard diagnoses. Concordance between all three independent pathologists was further explored using Krippendorff's alpha (a) from weighted kappa statistics. RESULTS: N = 145 patients with mean age of 60 (SD: 13 years.), 39% females, and 40% with body mass index ≥ 30 kg/m2 were included in the analysis. For identifying patients with NASH, MR liver fat and cT1 were the strongest performing individual measures (AUC: 0.80 and 0.75 respectively), and the mpMRI metrics combined (cT1 and MR liver fat) were the overall best non-invasive test (AUC: 0.83). For identifying fibrosis ≥ 1, MRE performed best (AUC: 0.97), compared to VCTE-liver stiffness measure (AUC: 0.94) and 2D-SWE (AUC: 0.94). For assessment of steatosis ≥ 1, MR liver fat was the best performing non-invasive test (AUC: 0.92), compared to controlled attenuated parameter (AUC: 0.75). Assessment of the agreement between pathologists showed that concordance was best for steatosis (a = 0.58), moderate for ballooning (a = 0.40) and fibrosis (a = 0.40), and worst for lobular inflammation (a = 0.11). CONCLUSION: Quantitative mpMRI is an effective alternative to liver biopsy for diagnosing NASH and non-alcoholic fatty liver, and thus may offer clinical utility in patient management.

The Effect of Multi-Parametric Magnetic Resonance Imaging in Standard of Care for Nonalcoholic Fatty Liver Disease: Protocol for a Randomized Control Trial.

BACKGROUND: The rising prevalence of nonalcoholic fatty liver disease (NAFLD) and the more aggressive subtype, nonalcoholic steatohepatitis (NASH), is a global public health concern. Left untreated, NAFLD/NASH can lead to cirrhosis, liver failure, and death. The current standard for diagnosing and staging liver disease is a liver biopsy, which is costly, invasive, and carries risk for the patient. Therefore, there is a growing need for a reliable, feasible, and cost-effective, noninvasive diagnostic tool for these conditions. LiverMultiScan is one such promising tool that uses multi-parametric magnetic resonance imaging (mpMRI) to characterize liver tissue and to aid in the diagnosis and monitoring of liver diseases of various etiologies. OBJECTIVE: The primary objective of this trial (RADIcAL1) is to evaluate the cost-effectiveness of the introduction of LiverMultiScan as a standardized diagnostic test for liver disease in comparison to standard care for NAFLD, in different EU territories. METHODS: RADIcAL1 is a multi-center randomized control trial with 2 arms conducted in 4 European territories (13 sites, from across Germany, Netherlands, Portugal, and the United Kingdom). In total, 1072 adult patients with suspected fatty liver disease will be randomized to be treated according to the result of the mpMRI in the intervention arm, so that further diagnostic evaluation is recommended only when values for metrics of liver fat or fibro-inflammation are elevated. Patients in the control arm will be treated as per center guidelines for standard of care. The primary outcome for this trial is to compare the difference in the proportion of patients with suspected NAFLD incurring liver-related hospital consultations or liver biopsies between the study arms, from the date of randomization to the end of the study follow-up. Secondary outcomes include patient feedback from a patient satisfaction questionnaire, at baseline and all follow-up visits to the end of the study, and time, from randomization to diagnosis by the physician, as recorded at the final follow-up visit. RESULTS: This trial is currently open for recruitment. The anticipated completion date for the study is December 2020. CONCLUSIONS: This randomized controlled trial will provide the evidence to accelerate decision making regarding the inclusion of mpMRI-based tools in existing NAFLD/NASH clinical care. RADIcAL1 is among the first and largest European health economic studies of imaging technologies for fatty liver disease. Strengths of the trial include a high-quality research design and an in-depth assessment of the implementation of the cost-effectiveness of the mpMRI diagnostic. If effective, the trial may highlight the health economic burden on tertiary-referral hepatology clinics imposed by unnecessary consultations and invasive diagnostic investigations, and demonstrate that including LiverMultiScan as a NAFLD diagnostic test may be cost-effective compared to liver-related hospital consultations or liver biopsies. TRIAL REGISTRATION: ClinicalTrials.gov NCT03289897 https://clinicaltrials.gov/ct2/show/NCT03289897. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/19189.