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.