Predicting response in cancer patients using machine learning models

Current clinical decision making for colorectal cancer (CRC) patients is based on a relatively small number of clinical and pathological hallmarks. Developments in the cost effectiveness and robustness of genome-wide molecular phenotyping greatly expand the number of features that can feed into decision making. The Computational Biology and Integrative Genomics Lab and associated researchers in the Bioinformatics Hub, use machine learning to develop and validate clinical classifiers, based on multi-omic data, which can predict treatment response for cancer patients. If successful, this would allow treatment to be individually tailored, meaning that patients receive the most effective treatment in the first instance.

Recently, Dr. Sanjay Rathee, postdoctoral working under the direction of Prof. Francesca Buffa, developed a model to predict treatment response for CRC patients undergoing chemotherapy, radiotherapy, and oxaliplatin treatment using data from the S:CORT consortium led by Prof. Tim Maughan. Looking at concordant predictions between different methods, this approach addresses the challenge of discovering decision-making genes with minimum noise, ensuring models are general and reliable.

In the first analysis of S:CORT samples (131 rectal cancer samples) from patients treated with radiotherapy and capecitabine, the model gives an accuracy of 90%. Whilst initial accuracy is quite high on retrospective cohorts, the results needs to be validated in external, independent cohorts. If validated, the model could predict response for a new patient based on a pre-treatment biopsy. Finding out whether a treatment is likely to be effective could greatly minimise the number of unnecessary interventions and associated side effects (and cost) whilst also increasing the chance of the chosen intervention being an effective treatment strategy.

Find out more about our research below

T-cell landscape mapping identifies new targets for pancreatic cancer immunotherapy

Through analysis of T-cell populations, Oxford pancreatic researchers identify novel therapeutic opportunities in pancreatic cancer patients
An animation showing a dial with green, amber and red risk levels for myeloma

New clinical prediction tools for myeloma

Dr Constantinos Koshiaris has developed clinical prediction models for use in primary care with the aim of accelerating myeloma diagnoses.

Oxford at the American Association for Cancer Research Annual Meeting

Oxford researchers are out in force at next week’s AACR Annual Meeting, check out what they’ll be talking about

Early Detection Award for research into the clinical application of single cell genomics

Dr Onima Chowdhury will investigate the clinical application of single cell sequencing for early diagnosis and response prediction in myelodysplastic syndromes.
Doctor looking at skin

Higher testosterone levels in men linked to greater melanoma risk

New research from Dr Eleanor Watts at the Nuffield Department of Population Health has found this association for the first time

New funding for early diagnosis research using platelets

Dr Bethan Psaila and her team will investigate the potential of circulating blood platelets for early detection of a range of cancer types.

Novel imaging device enters first round of development funding programme

Anna Vella is designing CAPULET: a device to increase the accuracy in delivering particle beam radiotherapy in cancer treatment

Oxford spin out influencing patient care world wide

Oxford cancer research spin our Optellum has received FDA clearance for the world’s first AI-powered clinical decision support for early lung cancer diagnosis

Funding to improve childhood, teenage and young adult cancer detection

Dr Defne Saatci and Professor Julia Hippisley-Cox will develop risk prediction tools using the QResearch database to support the earlier detection of childhood, teenage and young adult cancer