Skip to main content
Digital Environment Research Institute (DERI)
  1. Digital Environment Research Institute (DERI)
  2. DERI People
  3. DERI Staff
  4. Profile

Professor Venet Osmani

Venet

Professor of Clinical AI and Machine Learning

Email: v.osmani@qmul.ac.uk

Profile

I am Professor of Clinical AI and Machine Learning at Queen Mary University of London, where I lead the Osmani Lab within Digital Environment Research Institute (DERI).

My interdisciplinary research focuses on analysis of large-scale, longitudinal health records, including biomarkers, imaging, multi-omics, and routine care data to optimise treatment strategies, improve patient care and mitigate health inequities. Apart from clinical data, I also work on incorporating human behaviour data, such as those generated from wearable devices and smartphones, with a particular focus on mental health.

Methodological aspects of my research include generative architectures, such as GANs VAEs, and Diffusion Models, for synthetic (artificial) patient data, explainable AI methods and sample complexity.

The overarching objective of my research is to integrate predictive modelling at the bedside and bring the acquired evidence back, in a continuously improving feedback loop, consequently establishing a learning digital health system.

My research is funded by UKRI’s Medical Research Council (MRC), Engineering and Physical Sciences Research Council (EPSRC), National Institute for Health and Care Research (NIHR), British Heart Foundation (BHF), and the European Commission (from FP7 to Horizon Europe). I have established collaborations with the leading clinical and research institutions worldwide to translate research into clinical practice.

More information can be found in https://venetosmani.com

Research

Publications

  • Poretto V, Endrizzi W, Betti M et al. (2025). Machine Learning Analysis Applied to Prediction of Early Progression Independent of Relapse Activity in Multiple Sclerosis Patients. nameOfConference


  • Nafis N, Esnaola I, Martinez-Perez A et al. (2025). Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review. nameOfConference


    QMRO: qmroHref
  • Suvon MNI, Zhou S, Tripathi PC et al. (2025). Multimodal Latent Fusion of ECG Leads for Early Assessment of Pulmonary Hypertension. nameOfConference


    QMRO: qmroHref
  • Velichkovska B, Gjoreski H, Denkovski D et al. (2025). Bias in vital signs? Machine learning models can learn patients’ race or ethnicity from the values of vital signs alone. nameOfConference


  • Malaguti MC, Longo C, Moroni M et al. (2025). Reply to Comments on the Article “Machine Learning Predicts Risk of Falls in Parkinson's Disease Patients in a Multicenter Observational Study”. nameOfConference


  • Riello M, Moroni M, Bovo S et al. (publicationYear). Neuropsychological and clinical variables associated with cognitive trajectories in patients with Alzheimer's disease. nameOfConference


  • Marchesi R, Micheletti N, Kuo NI-H et al. (publicationYear). Generative AI mitigates representation bias and improves model fairness through synthetic health data. nameOfConference


  • Malaguti MC, Longo C, Moroni M et al. (2025). Machine Learning Predicts Risk of Falls in Parkison's Disease Patients in a Multicenter Observational Study. nameOfConference


  • Fan W, Suvon MNI, Zhou S et al. (2025). MeDSLIP: Medical Dual-Stream Language-Image Pre-training with Pathology-Anatomy Semantic Alignment. nameOfConference


    QMRO: qmroHref
  • Pukowski P, Osmani V (2025). Identifying Key Challenges of Hardness-Based Resampling. nameOfConference


    QMRO: qmroHref
View profile publication page
Back to top