Connect with us

News

Five winners of global AI cardio-health challenge announced

Published

on

The five winners of a brand new challenge from a collaboration of regulators and healthcare organisations in the UK and US were announced this week.

The challenge saw 25 teams of AI and machine learning developers from across the globe compete against each other to build models that predicted heart failure-related health outcomes for veterans.

The Veterans Cardiac Health and AI Model Predictions (V-CHAMPs) Challenge was a first from the VHA Innovation Ecosystem, the FDA Digital Health Center of Excellence, precisionFDA (part of the FDA’s Office of Digital Transformation) and the UK’s Medicines and Healthcare products Regulatory Agency (MHRA).

Using synthetic datasets based on real US veteran health records, entrants explored a range of potential outcomes following heart failure, including the prediction of cardiovascular outcomes, hospital re-admission rates and mortality, over a two phase, nine-month challenge.

This insight is designed to help health systems both in the UK and US to better understand the cardiovascular risks and specific health outcomes in veterans, as well as increasing understanding of synthetic data and AI/ML models and how they could be used to explore similar topics in the future.

The five winning teams were:

  1. VHeartAI
  2. ZS Associates ADS Team
  3. TeamDSS
  4. CognizantGoodHeartML
  5. Team D&D

“This has been a fantastic opportunity for developers to challenge themselves against other experts across the globe, all while contributing towards a worthy goal.

“This challenge has not only shown how advances in AI methodology can help improve healthcare, by providing forecasts of certain health outcomes in specific patient populations like veterans, it has also demonstrated the potential of synthetic data for the initial training and testing of AI algorithms.

“So, it has been fascinating to see how the best and brightest participants from around the world tested this potential to its limits in this challenge, and the knowledge that our sector has gained from their work will be invaluable.

“I’m so pleased to have been able to work with our US partners, bringing together cutting-edge health data expertise from both sides of the Atlantic, and helping to drive forward our combined understanding for application in future projects.”

News

BioAge expands drug into diabetic macular oedema

Published

on

BioAge Labs is expanding its lead drug candidate into diabetic macular oedema, with plans to start a phase 1b/2a trial in mid-2026.

The clinical-stage biotechnology company will test BGE-102, an oral therapy, in patients with the condition, which is one of the most common causes of vision impairment among people with diabetes.

Diabetic macular oedema occurs when persistently high blood sugar damages the small blood vessels in the retina, the light-sensitive tissue at the back of the eye, leading to fluid leakage and distorted vision.

While the condition is linked to diabetes, its progression is tied to chronic inflammation.

Current treatments focus on managing damage after it has begun. Patients often receive regular injections directly into the eye, sometimes monthly, to control swelling and preserve sight.

These therapies can be effective, but they are invasive, time-intensive and difficult to sustain over years.

Kristen Fortney is chief executive and co-founder of BioAge.

She said: “NLRP3 sits at the apex of this cascade, and BGE-102 offers the potential to deliver broader anti-inflammatory benefit in an oral formulation, which could meaningfully reduce treatment burden for patients with serious, sight-threatening conditions who currently require frequent intravitreal injections.”

BGE-102 is an oral NLRP3 inhibitor, designed to dampen inflammation at its source.

NLRP3 is a protein that drives inflammatory signalling and becomes increasingly active with age and metabolic stress.

When overactivated, it triggers signals that damage tissues throughout the body, including the retina.

What BioAge says makes BGE-102 notable in ophthalmology is its potential to reach the retina via oral dosing, a barrier many drugs struggle to cross.

If successful, this could reduce the treatment burden for patients who currently rely on frequent eye injections.

In early laboratory studies designed to mimic diabetic eye disease, BGE-102 helped keep the retina’s tiny blood vessels intact.

In studies examining ageing in the retina more broadly, blocking NLRP3 reduced the build-up of lipofuscin, a toxic waste material that accumulates in eye cells over time and is linked to degenerative vision loss, by roughly 80 per cent.

In an ongoing phase 1 trial, the drug has been well tolerated and reduced inflammatory signals in the body, including markers linked to cardiovascular and metabolic ageing.

The phase 1b/2a trial will test BGE-102 on its own and alongside existing treatments, aiming to show whether the drug calms the inflammation that damages vision over time.

Researchers will track changes in IL-6, a key inflammatory signal, within the eye, alongside measures of vision and retinal swelling. Results are expected in mid-2027.

The eye study will run alongside BioAge’s ongoing cardiovascular trial.

The company describes BGE-102 as a potential “pipeline in a pill”, targeting NLRP3-driven inflammation across cardiovascular, central nervous system and ocular diseases.

Continue Reading

Research

USC funds AI projects for Alzheimer’s trials

Published

on

The USC Clinical Trial Recruitment Lab will fund four projects testing how AI can strengthen recruitment for Alzheimer’s trials.

The initiative, dedicated to accelerating and improving Alzheimer’s clinical trials, selected the projects from more than 30 applicants to explore digital approaches.

Alzheimer’s clinical trials are more complex, costlier and take longer than those in other therapeutic areas, despite the pressing need for new treatments.

The lab evaluates innovative recruitment strategies to improve access and representation in trials, with the goal of identifying scalable evidence-based recruitment practices.

The USC Clinical Trial Recruitment Lab is a collaboration between the USC Schaeffer Center for Health Policy and Economics and the USC Epstein Family Alzheimer’s Therapeutic Research Institute.

The four projects will explore the following strategies.

  • Miriam Ashford at University of California, San Francisco will develop and test a generative AI voice agent to support remote informed consent and assess patient capacity for Alzheimer’s clinical trials.
  • Erika Cottrell at OCHIN, a national network of community health centres, and Vijaya Kolachalama at Cognimark will integrate an AI-enabled diagnostic platform into primary care electronic health record workflows to support earlier identification and referral of patients.
  • Andrew Kiselica at University of Georgia will establish a digitally enabled, trial-ready cohort of rural older adults to improve recruitment, participant selection and engagement.
  • Raeanne Moore at University of California, San Diego will leverage electronic health record portals and digital cognitive assessments to accelerate prescreening and better match potential participants.

An estimated 5.6 million Americans are living with Alzheimer’s and related dementias, a number expected to increase dramatically in the coming decades as the population ages.

An extensive therapeutic development pipeline and new early-detection approaches, such as diagnostic blood tests and advanced digital tools, have the potential to reduce the burden of the disease.

However, fewer than one per cent of eligible individuals participate in Alzheimer’s therapeutic trials due to barriers that include limited patient awareness, health system resource constraints and lack of access to diagnostics, according to research from USC Schaeffer.

Certain populations at higher risk for the disease, including Black and Hispanic patients, remain underrepresented.

“We can only innovate as quickly as we can test new therapies,” said Dana Goldman, founding director of the USC Schaeffer Institute.

“That’s why it’s crucial we keep expanding the toolkit of evidence-based recruitment strategies for running faster, better trials.”

The lab previously funded six pilots, some of which have already yielded insights.

For example, one found remote blood collection could help identify potential participants, while another showed that offering a small gift card significantly increased enrolment in an online memory concerns registry.

“Faster and more effective recruitment is essential, and we’re excited to incorporate these solutions in an integrated way as part of our clinical trials,” said Paul Aisen, founding director of the USC Epstein Family Alzheimer’s Therapeutic Research Institute.

“As studies move earlier into pre-symptomatic disease, this opens the door to new recruitment paradigms, and continuing to push forward the science of recruitment will be critical to what comes next in Alzheimer’s research.”

Continue Reading

News

Insilico in US$66m deal for Parkinson’s drug

Published

on

Insilico Medicine has agreed a US$66m deal with a Chinese biotech for half of the rights to a brain-penetrant Parkinson’s drug.

Under the agreement, the artificial intelligence-powered drug developer will take the lead on bringing the preclinical asset, dubbed ISM8969, into a phase 1 trial.

Hygtia Therapeutics will then take over for further studies and onward toward regulators and commercialisation.

Ren Feng is co-chief executive and chief scientific officer at Insilico.

Feng said: “Targeting neuroinflammation via NLRP3 represents a scientifically sound and high-potential approach to treating neurodegenerative and age-related diseases.

“However, developing a safe molecule with good blood-brain barrier penetration remains a formidable obstacle for drug developers.

“Through our generative AI platform, we have designed a molecule specifically engineered to overcome this barrier.

“We are pleased to partner with Hygtia Therapeutics.

“We believe that through our combined efforts, we can accelerate its clinical progress to address significant unmet medical needs.”

ISM8969 is an NLRP3 inhibitor.

NLRP3 is a protein involved in inflammation, and blocking it is being explored as a way to address a range of neuroinflammatory and cardiometabolic diseases. Interest in NLRP3 inhibition has increased in the past year.

Earlier this month, Eli Lilly paid US$1.2bn to acquire Ventyx Biosciences in the wake of a phase 2 study tying Ventyx’s lead NLRP3 inhibitor to improvements in Parkinson’s symptoms.

That same NLRP3 inhibitor had also been shown to cut levels of a biomarker for stroke and other serious risks by almost 80 per cent within a week in a separate mid-stage study.

Preclinical data for ISM8969 have “demonstrated the molecule’s robust efficacy, favourable safety profile and marked anti-inflammatory activity in various disease models,” said Insilico, which also noted the therapy’s “desirable blood-brain barrier penetration.”

The blood-brain barrier is the protective barrier around the brain that many drugs struggle to cross.

Insilico, which went public on the Hong Kong Stock Exchange last month, said it had discovered ISM8969 via its generative chemistry engine Chemistry42.

As well as an upfront fee of US$10m, Insilico is in line for up to US$56m in milestone payments from Hygtia.

Insilico has attracted interest from pharmaceutical companies for its AI-enabled drug discovery technology, including Sanofi, Pfizer, Menarini Group and Boehringer Ingelheim.

Most recently, Lilly agreed a deal worth more than US$100m in November.

Hygtia, which was founded last August after being incubated by Fosun Pharma, said the agreement with Insilico “marks a pivotal step in our global strategy.

This partnership aligns with our strategy to expand our innovative neuroscience pipeline through high-quality assets.”

Continue Reading

Trending

Agetech World