Data Science Investment Counter —Funding raised by UK data science companies in 2018.
£ 5.640 Million

Using artificial intelligence to adjust chemotherapy dosages

Adrien Coulet, lecturer at the Université de Lorraine and researchers from Stanford University have created an algorithm to predict the need to prescribe a reduced dose of medication for a patient rather than a standard dose.

The research, which was published on the scientific journal Nature, is based on an existing automatic learning method called “Random Forest Classifier“, which combines the results of decision trees based on slightly different subsets of data.

The project’s uniqueness lies in the fact that, in order to feed the system, the scientists who worked on it compiled information from very different sources (analysis results, notes, prescriptions, etc.) on groups of patients who needed to have their dosage of drugs changed or not.

Stanford University Hospitals computerised anonymous patients’ data for research purposes for years so the algorithm had consistent information on the highly variable responses of patients to their treatments. This allowed the program to learn and then predict whether patients who had never taken specific drugs at the time would hypothetically need a lower dosage.

Finding the right dose of medication by trial and error can be a painful experience for patients who are already suffering because of their disease. Adrien Coulet’s new algorithm and its artificial intelligence capabilities can greatly accelerate this process, potentially making patients’ lives better.

Image via Pixabay.


Co-working space and blog dedicated to all things data science.

Subscribe to our newsletter