Using the ELF test, FIB-4 and NAFLD fibrosis score to screen the population for liver disease.

BACKGROUND & AIMS: There is a need for accurate biomarkers of fibrosis for population screening of alcohol-related and non-alcoholic fatty liver disease (ALD, NAFLD). We compared the performance of the enhanced liver fibrosis (ELF) test to the fibrosis-4 index (FIB-4) and NAFLD fibrosis score (NFS), using transient elastography as the reference standard. METHODS: We prospectively included participants from the general population, and people at risk of ALD or NAFLD. Screening positive participants (TE ≥8 kPa) were offered a liver biopsy. We measured concomitant ELF, FIB-4, and NFS using validated cut-offs: ≥9.8, ≥1.3, ≥-1.45, respectively. RESULTS: We included 3,378 participants (1,973 general population, 953 at risk of ALD, 452 at risk of NAFLD), with a median age of 57 years (IQR: 51-63). Two hundred-and-forty-two were screening positive (3.4% in the general population, 12%/14% who were at-risk of ALD/NAFLD, respectively). Most participants with TE <8 kPa also had ELF <9.8 (88%) despite a poor overall correlation between ELF and TE (Spearman´s rho = 0.207). ELF was associated with significantly fewer false positives (11%) than FIB-4 and NFS (35% and 45%), while retaining a low rate of false negatives (<8%). A screening strategy of FIB-4 followed by ELF in indeterminate cases resulted in false positives in 8%, false negatives in 4% and the correct classification in 88% of cases. We performed a liver biopsy in 155/242 (64%) patients who screened positive, of whom 54 (35%) had advanced fibrosis (≥F3). ELF diagnosed advanced fibrosis with significantly better diagnostic accuracy than FIB-4 and NFS: AUROC 0.85 (95% CI 0.79-0.92) vs. 0.73 (0.64-0.81) and 0.66 (0.57-0.76), respectively. CONCLUSION: The ELF test alone or combined with FIB-4 for liver fibrosis screening in the general population and at-risk groups reduces the number of futile referrals compared to FIB-4 and NFS, without overlooking true cases. IMPACT AND IMPLICATIONS: We need referral pathways that are efficient at detecting advanced fibrosis from alcohol-related and non-alcoholic fatty liver disease in the population, but without causing futile referrals or excessive use of resources. This study indicates that a sequential test strategy of FIB-4 followed by the ELF test in indeterminate cases leads to few patients referred for confirmatory liver stiffness measurement, while retaining a high rate of detected cases, and at low direct costs. This two-step referral pathway could be used by primary care for mass, targeted, or opportunistic screening for liver fibrosis in the population. CLINICAL TRIAL NUMBER: Clinicaltrials.gov number NCT03308916.

An AI-based patient-specific clinical decision support system for OA patients choosing surgery or not: study protocol for a single-centre, parallel-group, non-inferiority randomised controlled trial.

BACKGROUND: Osteoarthritis (OA) affects 20% of the adult Danish population, and the financial burden to society amounts to DKK 4.6 billion annually. Research suggests that up to 75% of surgical patients could have postponed an operation and managed with physical training. ERVIN.2 is an artificial intelligence (AI)-based clinical support system that addresses this problem by enhancing patient involvement in decisions concerning surgical knee and hip replacement. However, the clinical outcomes and cost-effectiveness of using such a system are scantily documented. OBJECTIVE: The primary objective is to investigate whether the usual care is non-inferior to ERVIN.2 supported care. The second objective is to determine if ERVIN.2 enhances clinical decision support and whether ERVIN.2 supported care is cost-effective. METHODS: This study used a single-centre, non-inferiority, randomised controlled in a two-arm parallel-group design. The study will be reported in compliance with CONSORT guidelines. The control group receives the usual care. As an add-on, the intervention group have access to baseline scores and predicted Oxford hip/knee scores and HRQoL for both the surgical and the non-surgical trajectory. A cost-utility analysis will be conducted alongside the trial using a hospital perspective, a 1-year time horizon and effects estimated using EQ-5D-3L. Results will be presented as cost per QALY gain. DISCUSSION: This study will bring knowledge about whether ERVIN.2 enhances clinical decision support, clinical effects, and cost-effectiveness of the AI system. The study design will not allow for the blinding of surgeons. TRIAL REGISTRATION: ClinicalTrials.gov NCT04332055 . Registered on 2 April 2020.