Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study.

BACKGROUND AND AIMS: Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F≥ 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD. APPROACH AND RESULTS: Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS ≥ 4;53%), at-risk NASH (NASH with F ≥ 2;35%), significant (F ≥ 2;47%), and advanced fibrosis (F ≥ 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82). CONCLUSIONS: Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.

Biomarkers for staging fibrosis and non-alcoholic steatohepatitis in non-alcoholic fatty liver disease (the LITMUS project): a comparative diagnostic accuracy study.

BACKGROUND: The reference standard for detecting non-alcoholic steatohepatitis (NASH) and staging fibrosis-liver biopsy-is invasive and resource intensive. Non-invasive biomarkers are urgently needed, but few studies have compared these biomarkers in a single cohort. As part of the Liver Investigation: Testing Marker Utility in Steatohepatitis (LITMUS) project, we aimed to evaluate the diagnostic accuracy of 17 biomarkers and multimarker scores in detecting NASH and clinically significant fibrosis in patients with non-alcoholic fatty liver disease (NAFLD) and identify their optimal cutoffs as screening tests in clinical trial recruitment. METHODS: This was a comparative diagnostic accuracy study in people with biopsy-confirmed NAFLD from 13 countries across Europe, recruited between Jan 6, 2010, and Dec 29, 2017, from the LITMUS metacohort of the prospective European NAFLD Registry. Adults (aged ≥18 years) with paired liver biopsy and serum samples were eligible; those with excessive alcohol consumption or evidence of other chronic liver diseases were excluded. The diagnostic accuracy of the biomarkers was expressed as the area under the receiver operating characteristic curve (AUC) with liver histology as the reference standard and compared with the Fibrosis-4 index for liver fibrosis (FIB-4) in the same subgroup. Target conditions were the presence of NASH with clinically significant fibrosis (ie, at-risk NASH; NAFLD Activity Score ≥4 and F≥2) or the presence of advanced fibrosis (F≥3), analysed in all participants with complete data. We identified thres holds for each biomarker for reducing the number of biopsy-based screen failures when recruiting people with both NASH and clinically significant fibrosis for future trials. FINDINGS: Of 1430 participants with NAFLD in the LITMUS metacohort with serum samples, 966 (403 women and 563 men) were included after all exclusion criteria had been applied. 335 (35%) of 966 participants had biopsy-confirmed NASH and clinically significant fibrosis and 271 (28%) had advanced fibrosis. For people with NASH and clinically significant fibrosis, no single biomarker or multimarker score significantly reached the predefined AUC 0·80 acceptability threshold (AUCs ranging from 0·61 [95% CI 0·54-0·67] for FibroScan controlled attenuation parameter to 0·81 [0·75-0·86] for SomaSignal), with accuracy mostly similar to FIB-4. Regarding detection of advanced fibrosis, SomaSignal (AUC 0·90 [95% CI 0·86-0·94]), ADAPT (0·85 [0·81-0·89]), and FibroScan liver stiffness measurement (0·83 [0·80-0·86]) reached acceptable accuracy. With 11 of 17 markers, histological screen failure rates could be reduced to 33% in trials if only people who were marker positive had a biopsy for evaluating eligibility. The best screening performance for NASH and clinically significant fibrosis was observed for SomaSignal (number needed to test [NNT] to find one true positive was four [95% CI 4-5]), then ADAPT (six [5-7]), MACK-3 (seven [6-8]), and PRO-C3 (nine [7-11]). INTERPRETATION: None of the single markers or multimarker scores achieved the predefined acceptable AUC for replacing biopsy in detecting people with both NASH and clinically significant fibrosis. However, several biomarkers could be applied in a prescreening strategy in clinical trial recruitment. The performance of promising markers will be further evaluated in the ongoing prospective LITMUS study cohort. FUNDING: The Innovative Medicines Initiative 2 Joint Undertaking.

NAFLD and NASH biomarker qualification in the LITMUS consortium - Lessons learned.

Biomarkers have the potential to accelerate drug development, as early indicators of improved clinical response, to improve patient safety, and for personalised medicine. However, few have been approved through the biomarker qualification pathways of the regulatory agencies. This paper outlines how biomarkers can accelerate drug development, and reviews the lessons learned by the EU IMI2-funded LITMUS consortium, which has had several interactions with regulatory agencies in both the US and EU regarding biomarker qualification in patients with non-alcoholic fatty liver disease and non-alcoholic steatohepatitis. Sharing knowledge of such interactions with the scientific community is of paramount importance to increase the chances of qualification of relevant biomarkers that may accelerate drug development, and thereby help patients, across disease indications. A qualified biomarker enables a decision to be made that all understand and support in a common framework.

Redefinition of Fatty Liver Disease from NAFLD to MAFLD through the Lens of Drug Development and Regulatory Science.

Metabolic (dysfunction)-associated fatty liver disease (MAFLD) affects a third of the population and is a leading cause of liver-related death. Since no effective treatments exist, novel approaches to drug development are required. Unfortunately, outdated terminology and definitions of the disease are hampering efforts to develop new drugs and treatments. An international consensus panel has put forth an influential proposal for the disease to be renamed from nonalcoholic fatty liver disease (NAFLD) to MAFLD, including a proposal for how the disease should be diagnosed. As allies with the many stakeholders in MAFLD care-including patients, patients' advocates, clinicians, researchers, nurse and allied health groups, regional societies, and others-we are aware of the negative consequences of the NAFLD term and definition. We share the sense of urgency for change and will act in new ways to achieve our goals. Although there is much work to be done to overcome clinical inertia and reverse worrisome recent trends, the MAFLD initiative provides a firm foundation to build on. It provides a roadmap for moving forward toward more efficient care and affordable, sustainable drug and device innovation in MAFLD care. We hope it will bring promising new opportunities for a brighter future for MAFLD care and improve care and outcomes for patients of one of the globe's largest and costliest public health burdens. From this viewpoint, we have revisited this initiative through the perspectives of drug development and regulatory science.

Comparison of ADAPT, FIB-4 and APRI as non-invasive predictors of liver fibrosis and NASH within the CENTAUR screening population.

BACKGROUND & AIMS: The development of accurate non-invasive tests to detect and measure the extent of fibrosis and disease activity in patients with non-alcoholic steatohepatitis (NASH) - the progressive phenotype of non-alcoholic fatty liver disease (NAFLD) - is of great clinical importance. Herein, we aimed to validate the performance of PRO-C3 and ADAPT for the detection of moderate/severe fibrosis within the CENTAUR screening population. METHODS: PRO-C3 was assessed in plasma from the screening population of the phase IIb CENTAUR study (NCT02217475) in adults with NASH and liver fibrosis. The relation between PRO-C3 and histologic features of NASH was evaluated, as well as the demographics of patients with high and low levels of PRO-C3. The diagnostic ability of PRO-C3, as a standalone marker or incorporated into ADAPT, to identify patients with F≥2 and NASH was estimated using receiver-operating characteristic analysis and logistic regression models. RESULTS: A total of 517 individuals with matched biopsy and PRO-C3 measurements were included. Patients with PRO-C3 levels ≥20.2 ng/ml showed increased levels of insulin, HOMA-IR, alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase, and platelet count compared to patients with low PRO-C3 (p <0.05). PRO-C3 increased stepwise with increasing liver fibrosis, lobular inflammation, hepatocyte ballooning, steatosis, and NAFLD activity score (p <0.05), and could distinguish between NAFL and NASH (p <0.0001). PRO-C3 was independently associated with fibrosis and NASH when adjusted for clinical confounders. ADAPT outperformed Fibrosis-4, AST-to-platelet ratio index, and AST/ALT ratio as a predictor of advanced fibrosis and NASH (p <0.001). CONCLUSION: PRO-C3 was associated with NAFLD activity score and fibrosis. ADAPT outperformed other non-invasive scores for detecting NASH. These data support the use of PRO-C3 and ADAPT as diagnostic tools to identify patients with NASH eligible for inclusion in clinical trials. CLINICAL TRIAL NUMBER: NCT02217475 LAY SUMMARY: PRO-C3 is a serological biomarker associated with liver disease activity and fibrosis. Its performance for the detection of disease activity and fibrosis is improved when it is incorporated into the ADAPT score. Herein, we showed that ADAPT was better at selecting patients with non-alcoholic steatohepatitis for inclusion in clinical trials than other non-invasive scores.

The European NAFLD Registry: A real-world longitudinal cohort study of nonalcoholic fatty liver disease.

Non-Alcoholic Fatty Liver Disease (NAFLD), a progressive liver disease that is closely associated with obesity, type 2 diabetes, hypertension and dyslipidaemia, represents an increasing global public health challenge. There is significant variability in the disease course: the majority exhibit only fat accumulation in the liver but a significant minority develop a necroinflammatory form of the disease (non-alcoholic steatohepatitis, NASH) that may progress to cirrhosis and hepatocellular carcinoma. At present our understanding of pathogenesis, disease natural history and long-term outcomes remain incomplete. There is a need for large, well characterised patient cohorts that may be used to address these knowledge gaps and to support the development of better biomarkers and novel therapies. The European NAFLD Registry is an international, prospectively recruited observational cohort study that aims to establish a large, highly-phenotyped patient cohort and linked bioresource. Here we describe the infrastructure, data management and monitoring plans, and the standard operating procedures implemented to ensure the timely and systematic collection of high-quality data and samples. Already recruiting subjects at secondary/tertiary care centres across Europe, the Registry is supporting the European Union IMI2-funded LITMUS 'Liver Investigation: Testing Marker Utility in Steatohepatitis' consortium, which is a major international effort to robustly validate biomarkers that diagnose, risk stratify and/or monitor NAFLD progression and liver fibrosis stage. The European NAFLD Registry has the demonstrable capacity to support research and biomarker development at scale and pace.

Defining Improvement in Nonalcoholic Steatohepatitis for Treatment Trial Endpoints: Recommendations From the Liver Forum.

Identifying effective therapies for nonalcoholic steatohepatitis (NASH) with fibrosis is a pressing challenge, with 1%-2% of the population in developed nations at risk of developing NASH cirrhosis and its complications. The design of NASH clinical therapeutic trials is hampered by the long period of minimally symptomatic disease that typically precedes the development of decompensated cirrhosis and the accompanying uncertainties regarding the best precirrhotic trial endpoints that reliably reflect a subsequent reduction in liver-related morbidity and mortality. The Liver Forum is a multistakeholder organization comprised of academic, industry, and regulatory experts working from a regulatory science perspective to identify barriers, prioritize research, and identify solutions to accelerate therapeutic development for NASH. Past work of The Liver Forum has focused on recommendations for disease definitions and baseline parameters to be implemented in clinical trials that are designed to assess disease status and prevent progression to cirrhosis, liver transplantation, hepatocellular carcinoma, and death. The purpose of this summary is to review currently available clinical data to identify parameters that change in parallel with liver histology and are likely to reflect clinically meaningful reductions in the risk of developing cirrhosis and its complications. We review available data on exploratory histological, blood-based, and imaging pharmacodynamic biomarkers that may reflect meaningful treatment responses and provide recommendations regarding measurements to be considered in phase 2 and 3 trials as well as during postmarketing monitoring trials.

Validation studies on the 5-hydroxy-L-[beta-11C]-tryptophan/PET method for probing the decarboxylase step in serotonin synthesis.

The two-tissue compartment model, including irreversible trapping in the second compartment (2TCM) is used to describe the kinetics of 5-Hydroxy-L-[beta-(11)C]-tryptophan ([(11)C]HTP), a radioligand used in positron emission tomography (PET) for probing the second enzymatic step in the biosynthesis of serotonin. In this study, we examined the capacity of the model to track pharmacological changes in this biological process. We also investigated the potential loss of [(11)C]HTP-derived radioactivity during a PET study, since loss should be negligible not to alter quantification. Six rhesus monkeys were investigated using bolus [(11)C]HTP/PET methodology before and after pharmacological intervention. The second enzymatic step in serotonin synthesis was inhibited using the aromatic L-amino acid decarboxylase inhibitor NSD1015 (10 mg/kg). The extent of [(11)C]-derived radioactivity loss from the brain was studied by inhibition of the enzyme responsible for formation of the tissue metabolite, monoamine oxidase A, using clorgyline (2 mg/kg). After NSD1015, the uptake of [(11)C]HTP-derived radioactivity was increased in all the investigated brain regions, while the parameter used to reflect decarboxylase activity, the net accumulation rate constant (K(acc)), was decreased by 37% in the striatum, compared with baseline. Pretreatment with clorgyline did not change the brain uptake of [(11)C]HTP-derived radioactivity or K(acc). This study demonstrates that the 2TCM for [(11)C]HTP/PET is able to detect changes occurring during alteration of the biological process (i.e., the conversion of HTP to serotonin). Elimination of the radiotracer metabolite [(11)C]HIAA from the brain may be considered negligible if the PET study is limited to 60 min.

Tetrahydrobiopterin in the treatment of children with autistic disorder: a double-blind placebo-controlled crossover study.

Twelve children, all boys, aged 4 to 7 years, with a diagnosis of autistic disorder and low concentrations of spinal 6R-l-erythro-5,6,7,8-tetrahydrobiopterin (tetrahydrobiopterin) were selected to participate in a double-blind, randomized, placebo-controlled, crossover study. The children received a daily dose of 3 mg tetrahydrobiopterin per kilogram during 6 months alternating with placebo. Treatment-induced effects were assessed with the Childhood Autism Rating Scale every third month. The results showed small nonsignificant changes in the total scores of Childhood Autism Rating Scale after 3- and 6-month treatment. Post hoc analysis looking at the 3 core symptoms of autism, that is, social interaction, communication, and stereotyped behaviors, revealed a significant improvement of the social interaction score after 6 months of active treatment. In addition, a high positive correlation was found between response of the social interaction score and IQ. The results indicate a possible effect of tetrahydrobiopterin treatment.

Kinetic compartment modeling of [11C]-5-hydroxy-L-tryptophan for positron emission tomography assessment of serotonin synthesis in human brain.

The substrate for the second enzymatic step in serotonin synthesis, 5-hydroxy-L-tryptophan, labeled in the beta-position ([11C]-HTP), was used for positron emission tomography (PET) measurements in six healthy human participants, examined on two occasions. One- and two-tissue kinetic compartment modeling of time-radioactivity curves was performed, using arterial, metabolite-corrected [11C]-HTP values as input function. The availability of unchanged tracer in arterial blood plasma was > or = 80% up to 60 minutes after injection, while [11C]-hydroxyindole acetic acid and [11C]-serotonin accounted for the remaining radioactivity, amounting to < or = 16% and < or = 4%, respectively. Compartment modeling was performed for brain stem, putamen, caudate nucleus, anterior cingulate, white matter, and superior occipital, occipitotemporal, and temporal cortices. The average biologic half-life for plasma-to-tissue equilibrium was 7 to 12 minutes, and the volume of distribution was 0.2 to 0.5 microL.mL(-1). In all regions except white matter, the kinetic compartment model that included irreversible [11C]-HTP trapping showed significantly improved model fits with respect to a one-tissue compartment model. The [11C]-HTP trapping rate constant depended on the estimated tissue availability of the serotonin precursor tryptophan, known to reflect serotonin synthesis in healthy individuals, and correlated with serotonin tissue concentration and synthesis rates reported previously in literature. These findings suggest the use of [11C]-HTP PET measurements to investigate serotonin synthesis.

Interaction of a muscarinic cholinergic agonist on acetylcholine and dopamine receptors in the monkey brain studied with positron emission tomography.

The effects on the binding to cholinergic and dopaminergic receptors in the brain during continuous intravenous infusion of the muscarinic cholinergic receptor agonist milameline (CI-979) were studied in the rhesus monkey by means of positron emission tomography. Binding to milameline cholinergic receptors was quantified using the muscarinic receptor antagonist [(11)C]-N-methyl-4-piperidinylbenzilate ([(11)C]NMP), and the effects on nicotine receptor binding were measured with (S)-[(11)C-methyl]nicotine. Changes in the binding of the D(2) dopamine receptor antagonist [(11)C]raclopride were measured as well. The binding of [(11)C]NMP increased in most brain regions with the infusion of increasing doses of milameline from 0.5 to 10 microg/kg/h. (S)-[(11)C-methyl]nicotine binding was unchanged or increased somewhat. Binding of [(11)C]raclopride to the D(2) dopaminergic receptors in the striatum of the brain increased by 10 +/- 4% following 2 microg/kg/h of milameline. The results suggest a possible action of milameline both on presynaptic muscarinic receptor subtypes as well as dopamine levels dependent on the receptor reserve of the muscarinic receptor subtypes.