- Doctors could soon be using computer models to help them decide how best to treat cancer patients
- Models are more successful at predicting how patients will respond to treatment than doctors
- They can analyse all of the factors that affect prognosis and come up with the best treatment option
06:00 EST, 23 April 2013
06:00 EST, 23 April 2013
Computers could soon be used to revolutionise the way that a cancer patientâ€™s treatment is planned.
Doctors may start using computer models to help them decide how to treat patients because scientists have discovered that mathematical formulas are more successful at predicting how patients will respond to treatment.
Researchers found that a computer model was better able to predict the way in which lung cancer patients would respond to radiotherapy and chemotherapy than health experts were.
Doctors may start using computer models to help them decide how to treat cancer patients
According to The Independent, the scientists inputted each patientâ€™s medical history into the model which then gave more accurate predictions of how the patient would fare over the next two years than experienced oncologists did.
The researchers, at Maastricht University Medical Hospital in The Netherlands, used the computer model to predict the futures of 121 lung cancer patients.
The model analysed the patientsâ€™ chances of surviving for two years and predicted which ones would suffer from swallowing and breathing difficulties.
In all three predictions, the computer proved significantly more accurate than the patientsâ€™ doctors were.
Dr Cary Oberije told the newspaper: â€˜We have shown that current models already outperform doctors.
â€˜Therefore, this study can be used as a strong argument in favour of using prediction models and changing currently clinical practice.â€™
Researchers found that a computer model was better able to predict the way in which lung cancer patients would respond to radiotherapy and chemotherapy than health experts were
She added: â€˜We know that there are many factors that play a role in the prognoses of patients and prediction models can combine them allâ€¦Our study shows that it is very unlikely that a doctor can outperform a model.â€™
Dr Oberije and her team believe that computer models will become more and more important in cancer treatment as increasing amounts of data is collected about each sufferer.
This theory is compounded by the discovery that tumours differ between patients so require different treatment depending on the patientâ€™s genes â€“ establishing the best form of treatment based on genetics, and the stage and type of a tumour, is so complicated that it requires mathematical analysis.
The comments below have not been moderated.
All you want now is a computer to feed, water and wash you during your stay in hospital, to make life that bit more bearable. Hospitals have still not mastered the basics.
IBMâ€™s Watson computer has read several thousand cancer research papers and now teaches doctors.
4 in 10 children would perform better than doctors given a sample size of 3.
Irvine, United States,
Actually often chat rooms on proper illness sites are also more helpful for finding out whatâ€™s wrong with you.
Buckinghamshire, United Kingdom,
Iâ€™m reading about all the promising work in the area of fighting cancer however Iâ€™ve yet to see anything applied. Just lost a sibling to lung cancer which ran rampant once it hit the liver. I am constantly seeing all the things that could have been applied with her especially since she could no longer take chemo. Very possible she would have been spared death at this time.
I find it quite disgusting that a cure for cancer has already been found and we are still investing in â€˜curesâ€™. Of course though, curing diseases doesnâ€™t make any money does it?
Devon, United Kingdom,
Your comments:This is news? They were in the early stages of using this technology when I had breast cancer 7 years ago.
Fife, United Kingdom,
The views expressed in the contents above are those of our users and do not necessarily reflect the views of MailOnline.