Cancer patients could have treatment chosen by computer rather than a doctor

A computer model of lung cancer was found to be consistently better at predicting the future symptoms of patients following a course of radiotherapy or chemotherapy than the doctors responsible for their care. Each model is fed with the personal medical details and the treatment history of each patient, researchers explained. Dr Cary Oberije, of Maastricht University Medical Hospital in the Netherlands, said: “If models based on a patient, tumour and treatment characteristics already outperform the doctors, then it is unethical to make treatment decisions based solely on the doctors’ opinion. “We believe models should be implemented in clinical practice to guide decisions.” Dr Oberije and his team used computer models to determine how many lung cancer sufferers in a group of 21 would survive for two years, how many would experience difficulties with breathing and how many would find it hard to swallow. As more and more data is collected on patients, such as information about their genetic make-up, computer models are set to become increasingly important in deciding how to respond to certain diseases. Scientists have recently shown that cancer tumours can vary between patients and different types of treatment may be needed according to a patient’s genes. Computer models could prove effective at calculating this complex mathematical analysis. Dr Oberije said the research proved that “individualised treatment can only succeed it prediction models are used in clinical practice”. He added: “We know that there are many factors that play a role in the prognosis of patients and prediction models can combine them all.” Professor Alan Ashworth, chief executive of the Institute of Cancer Research in London, said computer models were become increasingly important as doctors collect more and more information on genetics and cancer diagnostics.