Saturday February 16, 2019

Researchers Develop AI That Can Help Make Cancer Treatment Less Toxic

The new "self-learning" machine-learning technique could make the dosing regimen less toxic but still effective

0
//
Cancer
Cancer Ribbon. Pixabay

MIT researchers, including one of Indian-origin, have developed novel machine-learning techniques to improve the quality of life for patients by reducing toxic chemotherapy and radiotherapy dosing for an aggressive form of brain cancer.

Glioblastoma is a malignant tumour that appears in the brain or spinal cord, and the prognosis for adults is no more than five years.

Patients are generally administered maximum safe drug doses to shrink the tumour as much as possible, but they still remain at risk of debilitating side effects.

The new “self-learning” machine-learning technique could make the dosing regimen less toxic but still effective.

It looks at the treatment regimen currently in use, and finds an optimal treatment plan, with the lowest possible potency and frequency of doses that should still reduce tumour sizes to a degree comparable to that of traditional regimen, the researchers said.

“We kept the goal where we have to help patients by reducing tumour sizes but, at the same time, we want to make sure the quality of life — the dosing toxicity — doesn’t lead to overwhelming sickness and harmful side effects,” said Pratik Shah, principal investigator from the Massachusetts Institute of Technology (MIT) in Boston, US.

Cancer
Representational image. Pixabay

The findings will be presented at the 2018 Machine Learning for Healthcare conference at Stanford University in California, US.

In simulated trials of 50 patients, the model comprising of artificially intelligent “agents”, designed treatment cycles that reduced the potency to a quarter or half of nearly all the doses while maintaining the same tumour-shrinking potential.

Many times, it skipped doses altogether, scheduling administrations only twice a year instead of monthly.

You May Also Like to Read About The Relation of Cancer Cells With Immune System- Decoded: How Cancer Cells Cripple Immune System

However, the researchers also had to make sure the model does not just dish out a maximum number and potency of doses. Whenever the model chooses to administer all full doses, it gets penalized, so instead it chooses fewer, smaller doses.

“If all we want to do is reduce the mean tumour diameter, and let it take whatever actions it wants, it will administer drugs irresponsibly,” Shah said.

“Instead, we need to reduce the harmful actions it takes to get to that outcome.” (IANS)

Next Story

With Ovarian Cancer Deaths Set to Spike by 67%, AI to Rescue: Study

However, the scans cannot give clinicians detailed insight into patients’ likely overall outcomes or on the likely effect of a therapeutic intervention

0
Cancer
Cancer Ribbon. Pixabay

With the incidence of ovarian cancer likely to increase by 55 per cent in another 15 years or so, researchers have created an artificial intelligence (AI) software to help best treat ovarian cancer that will pave the way for personalised medicine and expedite relief, a new study says.

The mathematical software tool — TEXLab — can also predict what treatment might be most effective for patients with the World Ovarian Cancer Coalition predicting that deaths will likely increase by 67 per cent by 2035 due to this particular cancer.

The technology can be used to identify patients who are unlikely to respond to standard treatments and offer alternatives as ovarian cancer is the sixth most common cancer in women in the UK that usually strikes after menopause or those with a family history of the disease.

Early detection of the disease could improve survival rates, the study noted.

“Long-term survival rate for patients with advanced ovarian cancer is poor despite advancements in treatments. There is an urgent need for new ways,” said lead author Eric Aboagye, Professor at Imperial College London.

For the study, researchers used the software to identify the aggressiveness of tumours in CT scans and tissue samples from 364 women with ovarian cancer.

The patients were then given a score known as Radiomic Prognostic Vector (RPV) which indicates how severe the disease is, ranging from mild to severe.

Cancer patient
Cancer patient.

The findings, published in Nature Communications, showed that the software was up to four times more accurate for predicting deaths from ovarian cancer than standard methods.

In addition, five per cent of patients with high RPV scores had a survival rate of less than two years, results showed.

High RPV was also associated with chemotherapy resistance and poor surgical outcomes, suggesting that RPV can be used as a potential bio-marker to predict how patients would respond to treatments.

“Our technology is able to give clinicians more detailed and accurate information on how the patients are likely to respond to different treatments, which could enable them to make better and more targeted treatment decisions,” said Aboagye.

Also Read- AI Can Help Improve Understanding of Earth Science

Doctors as of now diagnose ovarian cancer in a number of ways, including a blood test followed by a CT scan that uses X-rays and a computer to create detailed pictures of the ovarian tumour.

This helps clinicians know how far the disease has spread and determines the type of treatment patients receive, such as surgery and chemotherapy.

However, the scans cannot give clinicians detailed insight into patients’ likely overall outcomes or on the likely effect of a therapeutic intervention. (IANS)