Abigail Brooks is an assistant editor for 

She joined MJH Life Sciences in August 2023 shortly after graduating from Monmouth University where she earned her BA in Communication with a concentration in Public Relations/Journalism and later an MA in Interactive Digital Media. She enjoys traveling, running, and reading books. She can be reached at abrooks@mjhlifesciences.com.

Abigail Brooks, MA

A novel machine learning model may offer a more accurate tool for forecasting de novo hepatocellular carcinoma (HCC) risk in virologically and biochemically stable patients with chronic 

 after 5 years of potent antiviral therapy.

 years of antiviral therapy” (MAPL-5), addresses the limited accuracy of conventional models for predicting HCC risk in this context by combining logistic regression and random forest based on 36 comprehensive clinical variables.

According to the World Health Organization, in 2022, an estimated 254 million people were living with chronic hepatitis B infection and an estimated 1.1 million deaths occurred due to hepatitis B, mostly from cirrhosis and HCC. Treatment with potent nucleos(t)ide analogs (NAs), such as entecavir (ETV) or tenofovir (TFV), has significantly reduced the risk of complications and mortality from HBV, but concerns remain regarding long-term HCC risk in these patients.

“The overall incidence of HCC is estimated to increase with the longer life expectancy of CHB patients who have achieved virological and biochemical stability,” Han Chu Lee, of the Asan Liver Center at the University of Ulsan College of Medicine in South Korea, and colleagues wrote.

 “Therefore, prediction models are needed for CHB patients who did not develop HCC during the first 5 years of treatment because the risk of hepatocarcinogenesis is relatively low in these patients; however, the absolute risk could gradually increase, considering the patients' prolonged lifespan.”

Investigators sought to develop and validate a machine learning model for predicting HCC in patients with chronic HBV after the first 5 years of ETV or TFV therapy. To do so, they conducted a multicenter retrospective cohort study leveraging data for patients from 2 hospitals who started ETV/TFV therapy between January 2009 and December 2015 and continued treatment for > 5 years.

Those with a diagnosis of HCC or other malignant tumors within the first 5 years of ETV/TFV therapy; decompensated liver cirrhosis at the initiation of ETV/TFV therapy; death or liver transplantation within the first 5 years of ETV/TFV therapy; no regular surveillance for HCC development; and other definite etiologies of chronic liver disease were excluded from the study.

Investigators collected data at the baseline, defined as the first prescription date, and the 5-year mark for ETV/TFV therapy. They used 36 variables, including baseline characteristics and laboratory values, for model development. A total of 5 machine learning algorithms were applied to the training dataset, internally validated using a test dataset, and further externally validated.

A total of 6470 patients were included in the study, of whom 5908 and 562 were included in the derivation and external validation cohorts, respectively. Investigators noted patients in the derivation cohort were significantly older than those in the external validation cohort (mean age, 50 vs 46 years; 

 <.001). There were also greater proportions of male patients (66.1% vs 58.4%; 

 <.001) and patients with liver cirrhosis (60.0% vs 23.5%; 

During a median follow-up duration of 8.6 (95% CI, 8.5–8.7) years, a total of 279 (4.7%) and 25 (4.5%) patients developed HCC in the derivation and external validation cohorts, respectively, in years 5–15.

In the training dataset with 4726 patients, AdaBoost (0.729), logistic regression (0.735), and random forest (0.721) exhibited the highest balanced accuracy. Investigators then combined each model for ensemble learning, ultimately determining the ensemble model combining logistic regression and random forest outperformed the non-ensemble baseline model, with the highest balanced accuracy of 0.754 and AUC of 0.811. Therefore, this was selected as the final prediction model.

Investigators conducted ablation studies in 3 categories to evaluate the contribution of each variable to the entire system in the ensemble model, including the presence of liver cirrhosis at baseline; absolute changes in laboratory values and Child-Pugh score; and relative changes in laboratory values and Child-Pugh scores. The final ensemble model incorporating all 3 categories of the 26 previously selected variables achieved the best performance over the 4 metrics of sensitivity, accuracy, balanced accuracy, and AUC.

In an independent test dataset (n = 1182), the MAPL-5 model combining LR and random forest exhibited the best performance for predicting HCC development with a balanced accuracy of 0.712 and an AUC of 0.784. Investigators noted the similarity between the results of the cross-validation and the test dataset suggested minimal overfitting or underfitting of the model.

Additionally, external validation performed in an independent cohort (n = 562) confirmed the good performance of the MAPL-5 model, with the highest accuracy metrics in terms of balanced accuracy (0.771) and AUC (0.862).

Investigators acknowledged multiple limitations to these findings, including the potential lack of generalizability to patients of other ethnicities and with different HBV genotypes; the need for additional analyses with a larger group of patients to determine optimal cut-off values for high vs low risk; and the need for validation in a prospective cohort.

“The MAPL-5 model can assist practitioners' clinical decision-making, educate patients, and formulate evidence-based policies regarding HCC surveillance for public health organizations,” investigators concluded.

Ha Y, Lee S, Lim J, et al. A Machine Learning Model to Predict De Novo Hepatocellular Carcinoma Beyond Year 5 of Antiviral Therapy in Patients With Chronic Hepatitis B. 

World Health Organization. Hepatitis B. Newsroom. April 9, 2024. Accessed December 20, 2024. https://www.who.int/news-room/fact-sheets/detail/hepatitis-b

Articles

A novel machine learning model, MAPL-5, has been developed to predict hepatocellular carcinoma (HCC) risk in patients with chronic hepatitis B virus (HBV) after five years of antiviral therapy. This model, combining logistic regression and random forest, addresses the limitations of conventional models by utilizing 36 clinical variables. A multicenter retrospective cohort study validated the model, demonstrating its superior performance in predicting HCC development. Despite its promising results, the model's generalizability and optimal cut-off values require further investigation and validation in diverse patient populations.

The ML model exhibited better predictive performance than previous traditional HCC models in patients with chronic HBV on long-term antiviral therapy.

Machine Learning Model Accurately Predicts Long-Term HCC Risk in Patients with HBV

The phase 2b/3 NAVIGATE trial of Galectin Therapeutics’ belapectin in patients with 

metabolic dysfunction-associated steatohepatitis (MASH)

 cirrhosis and portal hypertension missed its composite primary endpoint for the prevention of varices, according to a press release from the company.

Topline results showed that although belapectin in both 2 mg/kg and 4 mg/kg doses reduced the incidence of varices in the intent-to-treat population, the difference over placebo was not statistically significant. According to a December 20, 2024, release from Galectin, the Company is conducting a full analysis of the NAVIGATE trial data and anticipates having additional data from approximately 50 patients with 36 months of belapectin treatment in early 2025, at which point they will provide clinical updates and determine next steps for its development.

“While we had hoped that the NAVIGATE trial would meet its composite primary endpoint, we are highly encouraged by trends we have seen at only 18 months of treatment in the ITT population and by the statistically significant 48.9% reduction in new varices noted in the per-protocol population with belapectin 2 mg,” Khurram Jamil, MD, chief medical officer at Galectin Therapeutics, said in a press release.

 “All enrolled subjects transitioned into a 36-month treatment period, with approximately 50 subjects completing the full 36 months to date. We are still analyzing the extensive data from the trial and anticipate providing multiple clinical updates from the subjects completing 36-month therapy, as well as additional biomarker data in Q1 2025.”

A global, multicenter, randomized, double-blind, placebo-controlled study conducted in over 130 sites across 15 countries, the NAVIGATE trial included 355 patients who were randomly assigned in a 1:1:1 ratio to receive intravenous belapectin 2mg/kg of lean body mass (LBM; n = 119), belapectin 4 mg/kg/LBM (n = 118), or placebo (n = 118) every other week for 18 months.

The primary endpoint was the prevention of varices, assessed as a composite clinical outcome including subjects with any varices, those with intercurrent events, or those without an endoscopy or intercurrent events at 18 months.

In the intent-to-treat population (n = 355), the incidence of varices was reduced by 43.2% in the belapectin 2 mg/kg dose group compared with placebo, but the composite endpoint did not reach statistical significance. In the per-protocol population (n = 290), which comprised subjects who completed 18 months of therapy with upper endoscopy performed at both baseline and 18 months, the incidence of varices was reduced by 48.9% compared to the targeted 52.5% reduction in the belapectin 2 mg/kg dose group (

 <.05). Of note, these clinical outcomes were supported by noninvasive measures.

Results additionally showed the incidence of adverse events and serious adverse events were comparable across the 3 cohorts. Rates of discontinuation, adverse events, and serious adverse events were similar to placebo, with no drug-related severe adverse events reported in the trial.

“I am encouraged by the results demonstrating an approximately 49% reduction in the development of varices in patients with MASH cirrhosis with the previously studied belapectin dose of 2 mg in such a large, global trial,” Naim Alkhouri, MD, chief medical officer and director of the Steatotic Liver Program at Arizona Liver Health, said in a press release.

 “I believe the results warrant further clinical development as belapectin could become a pivotal therapeutic option for these patients that currently do not have any treatment options.”

According to the release from Galectin, based on results from previous clinical and preliminary nonclinical studies as well as preliminary data from the NAVIGATE trial, the lack of increased efficacy at the 4 mg dose of belapectin is likely attributable to saturable binding dynamics and interactions with Galectin-3 proteins. Specifically, the 2 mg dose may provide optimal therapeutic effects, while doses ≥ 4 mg may not lead to greater binding and an increase in pharmacodynamic effects, leading to saturable drug disposition and the appearance of reduced efficacy.

Galectin is performing further analysis of the pharmacodynamic data from the NAVIGATE trial and is conducting a full analysis of the NAVIGATE data, with additional data from approximately 50 patients that have completed 36 months of treatment with belapectin anticipated in early 2025.

“I have been involved with the belapectin development program in MASH cirrhosis since the beginning and am very pleased to see that prevention of esophageal varices in patients with MASH cirrhosis in this large NAVIGATE clinical trial confirmed the results that were seen in the previous trial conducted by Galectin in the 2 mg/kg cohort,” Naga Chalasani, MD, David W. Crabb Professor of Gastroenterology and Hepatology and adjunct professor of anatomy, cell biology, and physiology at Indiana University School of Medicine, said.

 “Belapectin clearly is offering a reproducible benefit and should be continued in clinical development as there is a significant unmet need for patients with MASH cirrhosis.”

Galectin Therapeutics. Galectin Therapeutics Announces Top-Line Results of NAVIGATE Clinical Trial Evaluating Belapectin in Patients with Cirrhotic Portal Hypertension Caused by MASH. December 20, 2024. Accessed December 20, 2024. https://investor.galectintherapeutics.com/news-releases/news-release-details/galectin-therapeutics-announces-top-line-results-navigate

Galectin Therapeutics. Belapectin: Targeting Galectin-3. Accessed December 20, 2024. https://galectintherapeutics.com/about-belapectin/

The NAVIGATE trial evaluated belapectin in patients with MASH cirrhosis and portal hypertension but did not achieve its primary endpoint of preventing varices. Although belapectin reduced varices incidence, the difference from placebo was not statistically significant. The trial involved 355 patients across 15 countries, with belapectin doses of 2 mg/kg and 4 mg/kg. The 2 mg/kg dose showed a 48.9% reduction in varices in the per-protocol population. No severe drug-related adverse events were reported. Further analysis and updates are expected in early 2025.

The phase 2b/3 NAVIGATE trial missed its primary endpoint for the prevention of varices in patients with MASH cirrhosis and portal hypertension.

Belapectin Misses Primary Endpoint in Phase 3 MASH Cirrhosis, Portal Hypertension Trial

Retransplantation in patients originally transplanted due to 

 offers good graft and patient survival and yields similar or better outcomes compared with patients transplanted for other liver diseases, according to findings from a recent study.

Leveraging data from the Nordic Liver Transplant Registry (NLTR) for transplants completed between 1982 and 2022, the study found liver retransplantation in patients with PSC and recurrent PSC does not represent a futile use of liver grafts and should therefore be encouraged in national and international liver transplant programs.

A chronic liver disease in which the bile ducts inside and outside the liver become inflamed and scarred, there is currently no cure for PSC. Treatment seeks to address narrowed or blocked bile ducts and relieve associated symptoms and complications of PSC, but liver transplantation may be necessary for cases leading to liver failure. However, PSC can recur after liver transplantation, potentially leading to graft failure and requiring retransplantation.

“A liver retransplant can be technically demanding and raises questions related to both health economics and ethical aspects in organ allocation policies. Given the challenges with recurrent PSC, it is important to establish whether the outcomes following retransplantation in patients originally transplanted for PSC are acceptable and comparable to retransplantation for other etiologies,” Espen Melum, MD, PhD, a professor of medicine at the University of Oslo and a senior consultant at Oslo University Hospital, and colleagues wrote.

 “Outcomes of retransplantation in patients with PSC have not been well documented, and recent findings are not consistent between cohorts and may be affected by study size and selection of the appropriate comparison groups.”

To address this gap in knowledge, investigators assessed data from the NLTR for adult liver transplant recipients in Denmark, Estonia, Finland, Iceland, Norway, and Sweden between 1982 and 2022. They compared data for patients listed with PSC as the primary transplant indication to patients transplanted due to nonviral, non-malignant, and non-acute liver diseases.

Between 1982 and 2022, 8486 patients recorded in NLTR received a first liver transplant and 866 (10.2%) also underwent retransplantation. Of these patients, 185 had PSC and 208 had other liver disease etiologies, including alcoholic (22%), autoimmune (17%), metabolic-cryptogenic (23%), and other cholestatic liver diseases (25%).

Investigators observed an increased rate of retransplantation in the PSC group versus the comparison group (18.9% vs 10.1%, respectively; 

 = .011). Additionally, the PSC group had longer graft survival following the first liver transplant than the comparison group (log-rank 

 <.001), with a median survival of 4.1 years versus 0.4 years. Urgent retransplantation after the primary transplant was also less frequent in the PSC group (10% vs 34%; 

Patients undergoing retransplantation in the PSC group had better graft survival than the comparison group. The graft survival at 1, 5, 10, 15, and 20 years post retransplantation in the PSC group were 85%, 73%, 61%, 41%, and 36%, respectively, while the numbers in the comparison group were 66%, 54%, 44%, 33%, and 17% (log-rank 

Investigators called attention to a significant difference between PSC and the comparison group for patient survival (log-rank 

 <.001). In multivariate analysis, donor age was a significant predictor of graft survival, while blood group mismatch and transplant year were significant predictors of patient survival.

Of note, retransplantation for recurrence of PSC had similar and better outcomes for graft and patient survival compared to other etiologies. Specifically, patients in the recurrent PSC group had survival rates of 87%, 79%, 59%, and 43% at 1, 5, 10, and 15 years post retransplantation versus 69%, 60%, 56%, and 47% in the comparison group (log-rank 

 = .09). Additionally, patients with PSC recurrence had statistically significantly improved survival compared with the comparison group (log-rank 

Investigators also pointed out the mortality rates following retransplantation in the PSC group were 5% at 90 days and 33% at 5 years while the corresponding rates in the comparison group were 10% and 52% (

 <.001). The 90-day mortality was similar in the recurrent PSC group and the comparison group (

 = .35), while the 5-year mortality in the recurrent PSC group was significantly lower (

“Our data suggest that retransplantation in PSC has a good performance in terms of graft and patient survival compared to other etiologies and does not represent futile use of liver grafts,” investigators concluded.

 “While we seek new and effective treatment strategies for PSC and rPSC, retransplantation in patients originally transplanted for PSC should be performed when needed and encouraged in the national and international liver transplant programs.”

Molinaro A, Engesæter LK, Jorns C, et al. Outcome of Liver Retransplantation in Patients With Primary Sclerosing Cholangitis. 

National Institutes of Health. Primary Sclerosing Cholangitis. February 2022. Accessed December 19, 2024. https://www.niddk.nih.gov/health-information/liver-disease/primary-sclerosing-cholangitis

Retransplantation in patients with primary sclerosing cholangitis (PSC) demonstrates favorable graft and patient survival rates, comparable or superior to those with other liver diseases. Analysis of data from the Nordic Liver Transplant Registry (1982-2022) indicates that PSC retransplantation is not a futile use of liver grafts. The study highlights better graft survival and lower mortality rates in PSC patients compared to other etiologies. Factors such as donor age and blood group mismatch influence outcomes. The findings support encouraging PSC retransplantation in liver transplant programs globally.

Retransplantation outcomes were similar or better in patients with PSC compared with patients with other liver disease etiologies.

New Data Supports Liver Retransplantation for Patients with PSC Recurrence

The US Food and Drug Administration (FDA) has issued a Complete Response Letter (CRL) to Zealand Pharma’s glepaglutide for the treatment of adult patients with 

Announced on December 19, 2024, the CRL ​​states the New Drug Application (NDA) did not meet the full requirements for substantial evidence to establish the efficacy and safety of the to-be-marketed dose of glepaglutide. As a result, the FDA recommends Zealand Pharma conduct an additional clinical trial to provide further evidence to confirm the efficacy and safety of glepaglutide at the to-be-marketed dose.

“While we are certainly disappointed in the FDA’s decision, we remain confident that the data showed robust and compelling evidence of both efficacy and safety for glepaglutide treatment. We remain firm in our belief that glepaglutide provides a significant advance in GLP-2-based therapies for the potential treatment of SBS patients who are dependent on parenteral support,” David Kendall, MD, chief medical officer of Zealand Pharma, said in a press release.

According to a press release from Zealand, the company expects to initiate a single phase 3 trial in 2025 that is anticipated to support marketing authorizations for glepaglutide in geographies outside the US and the EU and provide further confirmatory evidence for a regulatory resubmission in the US.

A long-acting GLP-2 analog, glepaglutide received orphan drug designation from the FDA on October 24, 2017, based on phase 2 data demonstrating its impact on fecal wet weight output as well as energy, fluid, and electrolyte absorption.

Its NDA was supported by data from the phase 3 EASE program, including 4 clinical trials: EASE-1, EASE-2, EASE-3, and EASE-4.

EASE-1 was a randomized, double-blind phase 3 trial that evaluated the safety and efficacy of once- and twice-weekly subcutaneous administration of glepaglutide 10 mg compared with placebo in 106 patients with SBS and intestinal failure who were dependent on PS ≥ 3 days per week. Results showed twice-weekly glepaglutide significantly reduced the total weekly volume of PS at 24 weeks as compared with placebo (

= .0039). While once-weekly glepaglutide also resulted in a numeric reduction in weekly PS, it did not reach statistical significance.

At 24 weeks, the average reduction in PS from baseline was 5.13 liters/week for patients treated with glepaglutide twice weekly and 3.13 liters/week for patients treated with glepaglutide once weekly, versus 2.85 liters/week for patients treated with placebo. Among the study participants who were treated with glepaglutide, 9 were completely weaned off PS, while no placebo-treated patients were able to discontinue PS.

An extension trial of EASE-1, EASE-2 is a randomized, double-blind trial in which SBS patients continued their randomly assigned treatment from EASE-1 with glepaglutide 10 mg once or twice weekly. Patients who received placebo in EASE-1 were re-randomized to treatment with glepaglutide in EASE-2. Results from an interim analysis conducted when all patients had completed ≥ 6 months of treatment showed clinical response to glepaglutide across the key efficacy endpoints was generally maintained or showed continued improvement, including additional patients on both doses weaning off PS.

Additionally, EASE-3 is evaluating glepaglutide administered once weekly using an auto-injector. Findings from an interim analysisconducted in the first 43 patients rolled over from EASE-2 showed that the reduction in prescribed PS was generally maintained.

EASE-4 is a phase 3b trial to assess mechanistic effects of glepaglutide on intestinal fluid and energy uptake.

“We are committed to working with the agency to align on the path toward a regulatory approval, so that we can bring glepaglutide to patients in the U.S. In parallel, we expect to proceed with our current plans for a European Marketing Authorization Application submission in 2025,” Kendall said.

Global News Wire. U.S. Food and Drug Administration issues Complete Response Letter for the glepaglutide New Drug Application for the treatment of short bowel syndrome. December 19, 2024. Accessed December 19, 2024. https://www.globenewswire.com/news-release/2024/12/19/3000220/0/en/U-S-Food-and-Drug-Administration-issues-Complete-Response-Letter-for-the-glepaglutide-New-Drug-Application-for-the-treatment-of-short-bowel-syndrome.html

Biospace. Zealand Pharma submits New Drug Application to the US FDA for glepaglutide in short bowel syndrome. December 22, 2023. Accessed December 19, 2024. https://www.biospace.com/zealand-pharma-submits-new-drug-application-to-the-us-fda-for-glepaglutide-in-short-bowel-syndrome

Biospace. U.S. FDA Grants Orphan Drug Designation To Zealand Pharma’s Glepaglutide for the Treatment of Short Bowel Syndrome. October 24, 2017. Accessed December 19, 2024. https://www.biospace.com/u-s-fda-grants-orphan-drug-designation-to-zealand-pharma-s-glepaglutide-for-the-treatment-of-short-bowel-syndrome

The FDA issued a Complete Response Letter to Zealand Pharma for glepaglutide, a GLP-2 analog for short bowel syndrome, indicating the need for additional clinical trials to confirm its efficacy and safety. Despite the setback, Zealand Pharma remains confident in glepaglutide's potential, citing robust phase 3 trial data. The company plans a new phase 3 trial in 2025 to support global marketing authorizations and a US regulatory resubmission. Glepaglutide has shown promise in reducing parenteral support dependency, with some patients completely weaned off.