Dr Kaveh Kiani
School of Science, Engineering & Environment
Current positions
Lecturer in Data Science
Biography
Dr Kaveh Kiani is a Lecturer in Data Science at the University of Salford and Programme Leader for MSc Data Science and MSc Internet of Things with Data Science. He holds a PhD in Applied Statistics and a master's degree in Data Science, bringing together a strong statistical foundation with research in contemporary artificial intelligence, machine learning and applied data science.
His research spans several interconnected areas of data science and AI. A major strand of his work focuses on the application of computer vision and deep learning to medical image analysis and computer-aided diagnosis, including research on skin lesion and melanoma classification, respiratory disease detection from chest X-ray images, and lung cancer detection. His research also includes survival modelling, particularly the analysis of censored survival data and models incorporating time-dependent covariates.
A further major area of his research is collaborative and multi-agent AI for cancer diagnosis and care. He leads work on human-centred AI systems that combine medical image analysis, structured reporting and coordinated reasoning while keeping clinicians actively involved in decision-making. This research explores how multiple specialised AI components can work together to support more integrated and reliable clinical decision support, rather than operating as isolated diagnostic tools.
Building on this work, his research also investigates how AI can support the broader cancer care pathway beyond diagnosis, including the organisation and synthesis of clinical evidence, communication of uncertainty, identification of missing information, guideline-informed decision support and case prioritisation. The aim is to improve the efficiency and consistency of multidisciplinary cancer care while preserving clinical accountability, specialist judgement and patient safety.
His fundamental AI research investigates alternative mechanisms for sequence modelling and information exchange in neural architectures. This work focuses on the Hub mechanism, exploring how global context and structured representations can emerge through shared intermediary representations without relying on conventional token-to-token interaction.
A separate strand of his research investigates the internal representational geometry of large language models. This work examines whether learned latent structures can provide reproducible computational proxies for studying recurring patterns in human language, narrative and cultural production.
His wider research interests include big data analytics and applied machine learning. He has more than 15 years of industry experience and has supervised and supported numerous PhD and MSc research projects. He has published across applied statistics, artificial intelligence and medical image analysis in peer-reviewed journals and other scholarly outlets.
He is a Senior Fellow of the Higher Education Academy (SFHEA) and holds a Postgraduate Certificate in Academic Practice (PGCAP).
Areas of Research
Artificial intelligence and machine learning; medical computer vision and AI-assisted diagnosis; collaborative and multi-agent AI for cancer diagnosis and care pathways; neural architectures and sequence modelling; large language model representations, latent geometry and computational analysis of human narrative and cultural patterns; survival modelling; and big data analytics.
Programs: MSc Data Science / MSc Artificial Intelligence / MSc Internet of Things with Data Science.
Modules: Big Data Tools and Techniques / Applied Statistics and Data Visualisation
Qualifications
-
Applied Statistics
-
Data Science
-
Applied Statistics
-
Statistics
-
PGCAP
-
SFHEA - Senior Fellowship of the Higher Education Academy.