Murat Seçkin Ayhan

Murat Seçkin Ayhan

Assistant Professor
Computing and Software Systems

Research

Vision and interests

Progress in artificial intelligence (AI) continues to accelerate at a dizzying pace. While instances of AI are expected to stimulate digital innovation and have transformative impacts in our lives through diverse applications, an extensive adoption of AI also calls for scrutiny in order to ensure the safety of these systems and the distribution of their benefits to all, especially in high-stakes fields like medicine. Thanks to my educational background and proven research experience in diverse teams of clinicians, neuroscientists as well as other data and computer scientists, I am well-equipped to address modern challenges regarding not only the development of AI-based solutions with tangible impact but also their thorough inspection prior to deployment in safety critical settings. My overarching goal is to facilitate the transformation of healthcare in the digital era through efficient use of AI at scale.

Algoritmic peers in medicine

AI promises to transform healthcare by not only improving clinical workflows and patient outcomes but also equitably distributing the benefits to everyone, everywhere. To live up to these promises, AI implementations must be informed by the needs of clinicians, patients, healthcare providers as well as legal policies, and thoroughly validated with a clinical mindset. Only then, the state-of-the-art AI models can be conceived as peers (or co-pilots) that train differently and make algorithmic decisions based on sophisticated analyses of data.

Human-AI collaboration for discovery of novel biomarkers

Beyond assisting clinicians in diagnosis, one hope for AI in medical imaging is to identify novel biomarkers that are not easily found by humans. With the learnings from my work in clinically-minded AI, I will focus on diseases of the nervous and cardiovascular systems. I aspire to discover biomarkers and validate them through clinical trials that are also improved via the interaction of experts and models, or even agentic systems for greater sense of human-AI collaboration.