arXiv subjects

Mohamad Zeina

Publications and source records attributed to Mohamad Zeina.

3 recordsLinked to original sources

arXiv2026

Quantifying the impact of clinical-academic collaborations

Academic collaboration is of self-evident value but requires a quantitative representation to be optimally guided by policy. No established methodological approach to such representation exists. Here we introduce a general framework of graphical and bibliometric analysis of open data for the task of quantifying the impact of academic networks, with NIHR Biomedical Research Centre (BRC) clinical-academic partnerships in England as the prototype. We define publication-level identities for the 20 English BRCs based on the conjunction of authors from each BRC's partner institutions. Drawing on bibliometric and administrative records, we characterise the graphical properties of each network, estimate what the university adds to the hospital's papers, what the partnership adds to the papers of relatively infrastructure-poor collaborating institutions, and how that gain depends on existing infrastructure. We apply our framework to the NIHR UCLH/UCL BRC as an exemplar. UCLH/UCL authored 20,985 network papers from April 2007, in collaboration with 9,868 distinct external partners over the whole record, forming the most central node of the graph of networks across England. University co-authored papers exhibited 1.6 times the field-weighted citation impact (FWCI) of hospital-only papers, and were 2.1 times as likely to be cited by a patent. Across 60 of the exemplar's most partnered with UK healthcare organisations, the benefit rose from 1.8 times where local NIHR infrastructure activity was densest to 3.4 times where it was sparsest, while impact without the exemplar varied little. Academic networks can be robustly identified from open data, enabling comparative analysis of collaborative impact. Applied to NIHR BRCs, the approach enables quantification of the impact across networks and reveals that benefit is most pronounced where infrastructure is least developed.

cs.DL↗

arXiv2026

Fairboard: a quantitative framework for equity assessment of healthcare models

Despite there now being more than 1,000 FDA-authorised AI medical devices, formal equity assessments -- whether model performance is uniform across patient subgroups -- are rare. Here, we evaluate the equity of 18 open-source brain tumour segmentation models across 648 glioma patients from two independent datasets (n = 11,664 model inferences) along distinct univariate, Bayesian multivariate, spatial, and representational dimensions. We find that patient identity consistently explains more performance variance than model choice, with clinical factors, including molecular diagnosis, tumour grade, and extent of resection, predicting segmentation accuracy more strongly than model architecture. A voxel-wise spatial meta-analysis identifies neuroanatomically localised biases that are compartment-specific yet often consistent across models. Within a high-dimensional latent space of lesion masks and clinic-demographic features, model performance clusters significantly, indicating that the patient feature space contains axes of algorithmic vulnerability. Although newer models tend toward greater equity, none provide a formal fairness guarantee. Lastly, we release Fairboard, an open-source, no-code dashboard that lowers barriers to equitable model monitoring in medical imaging.

cs.LG↗

arXiv2024

Deep Generative Classification of Blood Cell Morphology

Accurate classification of haematological cells is critical for diagnosing blood disorders, but presents significant challenges for machine automation owing to the complexity of cell morphology, heterogeneities of biological, pathological, and imaging characteristics, and the imbalance of cell type frequencies. We introduce CytoDiffusion, a diffusion-based classifier that effectively models blood cell morphology, combining accurate classification with robust anomaly detection, resistance to distributional shifts, interpretability, data efficiency, and superhuman uncertainty quantification. Our approach outperforms state-of-the-art discriminative models in anomaly detection (AUC 0.990 vs. 0.918), resistance to domain shifts (85.85% vs. 74.38% balanced accuracy), and performance in low-data regimes (95.88% vs. 94.95% balanced accuracy). Notably, our model generates synthetic blood cell images that are nearly indistinguishable from real images, as demonstrated by an authenticity test in which expert haematologists achieved only 52.3% accuracy (95% CI: [50.5%, 54.2%]) in distinguishing real from generated images. Furthermore, we enhance model explainability through the generation of directly interpretable counterfactual heatmaps. Our comprehensive evaluation framework, encompassing these multiple performance dimensions, establishes a new benchmark for medical image analysis in haematology, ultimately enabling improved diagnostic accuracy in clinical settings. Our code is available at https://github.com/CambridgeCIA/CytoDiffusion.

cs.CV↗