At FutureNeuro, we place patients at the heart of all of our research. With our integrated clinical network and an engaged patient community, we serve as a testbed for developing and testing AI-powered solutions that improve neurological care while prioritising patient safety and privacy. 

Our partnerships with industry leaders, healthcare providers, and patient organisations enable us to deliver cutting-edge diagnostics, treatments, and digital health solutions. Within digital health, we adopt a holistic approach to individual health and well-being, leveraging AI and diverse datasets to generate new insights that can be directly translated into clinical practice. Our aim? To change the way we treat and manage brain diseases, making healthcare more personalised, accessible, and proactive. 

A Socio-Technical Approach to AI 

Digital health, the so-called “fourth wave” of healthcare, places the patient at the core of healthcare delivery. However, the integration of AI into clinical practice has faced challenges, such as safety concerns, privacy issues, evolving regulations, ethical challenges, and difficulties in interpreting AI models.  

At FutureNeuro, we recognize that AI isn’t just about technology—it’s about people and processes. That’s why we embrace a socio-technical, team-based approach, aligning AI development with the needs of patients, clinicians, and healthcare systems. From the outset, our researchers collaborate with healthcare professionals, ethicists, and patients to co-design practical, innovative solutions. Our strong focus on Public and Patient Involvement (PPI) ensures that research is done with patients, not just for them. This co-creation process ensures that the AI solutions we develop are grounded in real-world needs, improving both the delivery of care and patient outcomes.  

Building Trust in AI 

One of the biggest challenges facing AI in healthcare is trust. AI can often seem like a “black box,” producing decisions that are difficult to interpret. We are tackling this by conducting research that explores attitudes toward AI from various perspectives. Through interviews and focus groups with patients, caregivers, clinicians, and academics, we are gaining crucial insights into what is needed to build trust in AI-driven healthcare systems. 

AI-Enabled Projects: Epilepsy, Mental Health, and Multiple Sclerosis 

At the heart of our AI strategy is the ability to harness large, rich datasets to improve patient care. For instance, the Irish National Epilepsy Electronic Patient Record (EPR), one of the world’s most comprehensive epilepsy datasets, spans over 50,000 years of cumulative patient data. Our multidisciplinary teams use machine learning to uncover patterns that would otherwise go unnoticed, such as predicting disease progression or identifying optimal treatment plans based on data-driven trends. 

In mental health, we are using AI to help individuals to better understand and manage psychotic experiences, which exist along a continuum in the population. Our researchers are developing app-based tools and psychoeducational resources that integrate data from digital devices and gamified cognitive tests. These tools help detect early warning signs, enabling timely interventions through predictive models. 

In multiple sclerosis (MS), we are exploring new digital biomarkers that can alert clinicians to early signs of deterioration. By tracking gait and subtle eye movements using digital devices, we can analyse this data alongside clinical records to detect early changes in a patient’s condition, allowing for proactive interventions. 

Nurturing a Culture of Data Literacy 

We are deeply committed to improving data literacy among our researchers. This means equipping our teams to collect and manage high-quality, representative data that reflects real-world patient conditions. It’s not just about the volume of data but about its accuracy, completeness, and relevance to the population. By adhering to emerging regulations like the AI Act and the European Data Governance Act, and following global standards like the FAIR data principles, we ensure that our AI research is ethical, transparent, and impactful.