Combining Diagnostics and Artificial Intelligence enabling Precision Medicine, Risk Prediction and Prognosis to Guide Therapy.
Presumed NASH fibrosis as per noninvasive screening blood biomarker LIVERFASt-GP+ is predictive for Covid-19 short-term severe outcome
Poster Presented June 2022
To demonstrate that LIVERFASt-GP+ through presumed liver fibrosis severity identification provides prognostication for the short-term risk of developing COVID-19 severe outcomes (SO).
Repeated noninvasive liver biopsy surrogate LIVERFASt correlates with BMI and liver enzymes improvements
Poster Presented June 2022
To assess liver fibrosis regression rate (LFR) USING repeated LIVERFASt AND CORRELATIONS with IMPROVEMENTS IN clinical endpoints, body mass index
BMI ≥ 10% and liver enzymes
ALT ≥ 50%from baseline.
Comparative assessment of noninvasive methods (NIMs) - LIVERFASt, liver stiffness measurement (LSM) with transient elastography (TE, Fibroscan), ELF and FiB-4 - in a prospective cohort with chronic liver diseases (CLD) from a tertiary liver center
Poster Presented June 2022
In a prospective tertiary cohort with CLD, to assess clinical performance against liver biopsy of different NIMs :
- For advanced and bridging fibrosis: LIVERFASt Fibrosis test, Enhanced liver fibrosis score (ELF), FIB-4 and LSM using vibration controlled transient elastography (VCTE).
- For steatosis (mild, moderate and marked): LIVERFASt Steatosis test and CAP (Fibroscan) in NAFLD patients, including a control group with CLD without steatosis (S0)].
Noninvasive LIVERFASt transition rate to liver fibrosis is similar to that estimated with liver biopsy in NAFLD patients
Poster Presented Nov 2021
Aim of the study is to demonstrate that LIVERFASt is an alternative to LB for the estimation of the transition rate to fibrosis [transition to stage F1 or more (TRF)] in T2D and noT2D, comparatively to other NITs [FIB- 4, liver stiffness measurement (LSM) by Fibroscan].
Long-term prognosis of MAFLD patients according to non-invasive methods
Poster Presented Nov 2021
Recently, a new terminology “metabolic(dysfunction)-associated fatty liver disease”(MAFLD) has been suggested by a group of experts to more accurately reflect the pathogenesis of fatty liver diseases. Non-invasive assessment of fibrosis has been shown to predict global and specific mortality and morbidity in NAFLD and AFLD, but this has not yet been demonstrated in MAFLD
Comparison analysis of FIB-4, LIVERFASt(LF) and Liver Stiffness Measurement (LSM) with Transient Elastography (TE) in sequential and combinatory pathways for Non-Alcoholic Fatty Liver Disease (NAFLD)
Poster Presented Nov 2021
The identification of NAFLD bridging liver fibrosis (F3F4) remains challenging. Using non-invasive liver fibrosis tools (NITs) may permit earlier detection of F3F4 for liver specialist review.
Our study suggested that NITs such as Transient Elastography and LIVERFASt when used in combination:
- outperform sequential approaches, including those integrating FIB4
- could palliate for the non-applicable TE results If both TE and LF agree on the presence of F3F4, the detection of severe NAFLD is improved.
Comparative performances of LIVERFASt, Fibroscan and other noninvasive tests for severe fibrosis in NAFLD patients.
Poster Presented September 2020
The study aimed to assess comparatively the diagnostic values of AI neural network constructed blood marker Liverfast (LF), transient elastography liver stiffness measurements (TE M/XL probes), Hepascore (HS), Fibrosure (FS), FIB4, APRI and Forns index for cirrhosis (F4 stage) and severe fibrosis (F3F4 stage), taking liver biopsy (LB) as reference in NAFLD patients.
Simulating clinical confidence intervals for black-box algorithmic predictions of liver steatosis.
Paper Presented September 2020
Clinicians have begun using blood-serum biomarkers with artificial intelligence algorithms (AIAs) to assess the degree of liver steatosis without taking a liver biopsy. However, intra-patient and intra-lab variability could affect the inputs, and with >5 biomarkers used by an AIA, noise is compounded. Interpretable measures of an AIA’s confidence are absent in the clinical workflow. We aim to resolve this gap in interpretability of non-invasive AIA with a stochastic noise injection method and interactive data visualization—allowing clinicians to a) observe steatosis predictions under simulated noise conditions and b) interactively simulate expected regression of steatosis with respect to changes in biomarkers through course of treatment.
Poster Presented September 2020
Despite the high efficacy of current direct acting agents (DAA), in Thailand CHC is still a leading cause of liver-related morbidity and mortality and staging of liver fibrosis is critical for the management of outcomes in patients even after viral cure. LIVERFAStTM (LF, Fibronostics, US) is a proprietary technology based in serum biomarkers to assess quantitatively liver fibrosis (LF-Fib), necroinflammatory (NAI) activity (LF-Act) and steatosis (LF-Ste).
Predictive value of non-invasive methods LIVERFASt, acoustic radiation force impulse (ARFI), FIB-4 and APRI to identify the natural phases of chronic hepatitis b (CHB) infection from the National University Hospital (NUH) CHB study cohort of Singapore.
Poster Presented September 2020
In order to determine the outcomes and progression to significant liver fibrosis (SLF) as per ARFI, we set up a prospective NUH HBV cohort with chronic HBV infection (Ch.Inf) expected to have no/minimal liver disease vs moderate/severe in chronic hepatitis (Ch.Hep) patients (pts).(JHepatol2017) LIVERFASt (LF, Fibronostics, US), is a patented technology to assess liver fibrosis(LF-F) and activity(LF-A).
Evaluating serum biomarkers LIVERFASt surrogates of liver fibrosis and steatosis could identify risks in a clinical population experiencing sars-cov2 infection (covid19).
Paper Presented September 2020
Coronavirus disease-2019 (COVID-19) is a life-threatening infection caused by the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) virus. Age, diabetes and metabolic factors has rapidly emerged as a major comorbidity for COVID-19 severity. However, the phenotypic characteristics of patients (pts) in COVID-19 are unknown. For clinicians, it’s imperative to predict the outcome of a given patient following a positive test for SARS-CoV2—it is known that prior health history and demographics are informative towards describing the wide range of prognostic outcomes for COVID19 pts.
Comparative performances of LIVERFASt, VTCE (Fibroscan) and other serum non-invasive tests (NITS) for the diagnosis of advanced chronic liver disease in non-alcoholic fatty liver disease (NAFLD) patients from a cohort with liver biopsy.
Paper Presented September 2020
There is a call for action in the management of patients (pts) with type 2 diabetes mellitus (T2DM) and steatohepatitis (NASH) LIVERFASt (LF) is a serum-based proprietary panel for assessing fibrosis (LF-Fib), steatosis (LF-Ste) and activity (LF-Act) in NAFLD pts.
Monitoring fatty liver disease during pre/post-bariatric surgery with non-invasive LIVERFASt
Paper Presented June 2020
According to the American Society for Metabolic and Bariatric Surgery (ASMBS)1, non-alcoholic fatty liver disease (NAFLD) is one of the obesity-related co-morbidities that qualifies a patient to undergo a bariatric surgery if BMI> 35. By 2030, it is predicted that nearly half of adults in the USA will have obesity2. Over 80% of the patients with obesity submitted to bariatric surgery suffer from (NAFLD), with 25% – 55% resulting in steatohepatitis (NASH) and 2% – 12% liver fibrosis and cirrhosis3.
Introducing LIVERFASt in your clinic: simplifying liver assessment in medicine
Paper Presented May 2020
Dr. Sam Pappas uses the capabilities of Artificial Intelligence (AI) algorithm LIVERFASt blood-based test for evaluation of liver disease, fatty liver disease and NASH (Non-Alcoholic Steatohepatitis) to provide excellent care for his patients.
Assessment of fatty liver disease using a biomarker-based non-invasive algorithm LIVERFASt test in South-East Asia
Poster Presented January 2020
Scientific poster presented at the NASH-TAG conference, January 2020 for “Assessment of fatty liver disease using a biomarker-based non-invasive algorithm LIVERFASt test in South-East Asia”.
At NASH-TAG international conference, clinicians and researchers share the latest advances and challenges in the diagnosis and therapy of NASH and liver fibrosis.
Machine learning technology for evaluation of liver fibrosis, inflammation activity and steatosis (LIVERFASt)
Paper Presented November 2019
Use of non-invasive liver tests in extended populations is evaluated in 13068 patients who underwent the LIVERFASt test for fatty liver disease assessment. Data evaluation revealed 11% of the patients exhibited significant fibrosis, approximately 7% of the population had severe hepatic inflammation, and steatosis was observed in most patients, 63%, whereas severe steatosis S3 was observed in 20%. Using modified SAF (Steatosis, Activity and Fibrosis) scores obtained using the LIVERFASt algorithm, NAFLD was detected in 13.41% of the patients.
Non-invasive assessment of liver fibrosis, inflammation and steatosis
Poster Presented November 2019
The LIVERFASt machine learning-based algorithm uses a combination of anthropometric and serum biomarkers that are individually used to provide fatty liver disease staging. It is a reliable, and reproducible tool which provides grading or staging of the three liver lesions: fibrosis, inflammation activity and steatosis.
Non-invasive testing for Fatty Liver disease for primary care providers
Poster Presented November 2018
High sensitivity and specificity indicating “Elevated” or “Low” risk for NAFLD can be achieved using a simple algorithm based on minimal information from patients seeking routine check-ups from Primary Care Physicians or PCPs. The algorithmic result is significantly more precise than current reliance on identification of outlier values for standard individual liver function biomarkers. Furthermore, most patients at elevated risk can be evaluated for quantitative SAF score prediction using additional biomarkers – without undergoing expensive or invasive procedures of elastography, imaging or biopsy.
