skip to content

Cambridge Mathematics of Information in Healthcare

 
Read more at: Recent methodological advances in federated learning for healthcare

Recent methodological advances in federated learning for healthcare

24 June 2024

Federated learning (FL) promises to solve the challenges of applying machine learning methods within healthcare, such as isolated datasets, ethical, privacy, and logistical concerns with data sharing, and the lack of diversity in single-center datasets. By connecting multiple sites and keeping data at their source, FL can...


Read more at: The curious case of the test set AUROC

The curious case of the test set AUROC

4 April 2024

The area under the receiver operating characteristic curve (AUROC) is a staple within machine learning for reporting model performance and assessing model generalisability. However, CMIH researchers demonstrate that reporting the AUROC alone for a test set masks not only domain shift between validation and test data but...


Read more at: The impact of imputation quality on machine learning classifiers for datasets with missing values

The impact of imputation quality on machine learning classifiers for datasets with missing values

6 October 2023

Classifying samples in incomplete datasets is a common aim for machine learning practitioners, but is non-trivial. Missing data is found in most real-world datasets and these missing values are typically imputed using established methods, followed by classification of the now complete samples. The focus of the machine...


Read more at: Integrating Artificial Intelligence Tools in the Clinical Research Setting: The Ovarian Cancer Use Case

Integrating Artificial Intelligence Tools in the Clinical Research Setting: The Ovarian Cancer Use Case

25 September 2023

Artificial intelligence (AI) methods applied to healthcare problems have shown enormous potential to alleviate the burden of health services worldwide and to improve the accuracy and reproducibility of predictions. In particular, developments in computer vision are creating a paradigm shift in the analysis of radiological...


Read more at: Career intentions of medical students in the UK: a national, cross-sectional study (AIMS study)

Career intentions of medical students in the UK: a national, cross-sectional study (AIMS study)

15 September 2023

CMIH Hub investigator Prof. Richard Samworth and his AIMS study colleagues recently published the largest survey of it's kind exploring the career intentions of UK medical students within two years of graduating. The survey found that almost a third of the respondants intended to change career or leave the UK to practice...


Read more at: Navigating the development challenges in creating complex data systems

Navigating the development challenges in creating complex data systems

1 June 2023

Machine learning is in a reproducibility crisis. Many codebases simply do not run when tested outside of the development environment and, even when they do run, many algorithms do not generalise outside of the dataset on which they are trained. In this paper, researchers from the CMIH Hub and AIX-CO VNET teams argue that...


Read more at: Multi-modal learning for predicting the genotype of glioma

Multi-modal learning for predicting the genotype of glioma

23 May 2023

Glioma is the most common malignant brain tumour in adults. These tumours often vary between people resulting in very different outcomes.One of the most significant markers for the diagnosis and prognonsis of glioma is a mutation of the isocitrate dehydogenase (IDH) gene. Studies have shown that MRI can predict the...


Read more at: Summer Internships with the Cambridge Mathematics Placement Programme

Summer Internships with the Cambridge Mathematics Placement Programme

13 February 2023

One of the aims of the CMIH Hub is to encourage the mathematicians of the future. We're pleased to work with the Cambridge Mathematics Placements (CMP) programme, part of the Faculty of Mathematics within the University of Cambridge , to enable students to learn skills outside of the standard academic curriculum and to...


Read more at: Mutual Contrastive Low-rank Learning to Disentangle Whole Slide Image Representations for Glioma Grading

Mutual Contrastive Low-rank Learning to Disentangle Whole Slide Image Representations for Glioma Grading

22 December 2022

Histology images of cancer tissue provide valuable information for the malignancy grading of cancers. AI shows promise to automatically determine cancer malignancy based on histology images, providing rapid support for cancer diagnostics. Currently, the most widely used histology images include the images of formalin-fixed...


Read more at: Using artificial intelligence to interrogate multi-national imaging datasets to determine the mechanism of COVID-19 pneumothorax

Using artificial intelligence to interrogate multi-national imaging datasets to determine the mechanism of COVID-19 pneumothorax

5 December 2022

A collapsed lung, known as a pneumothorax, is more common in COVID-19 patients in hospital than in patients admitted for other diseases. It was initially thought that this was a complication of high pressures used in ventilation of those with severe disease, but this cannot explain all cases and the reasons why COVID-19...


Funded by