AI Watson and other nanorobots to help ‘detective doctors’ solve medical mysteries

Originally posted on MIMS.

In Arthur Conan Doyle’s The Adventures of Sherlock Holmes, Dr. John H. Watson serves as the friend and assistant for the famous detective, Sherlock Holmes, who has an intellectual fetish for solving the most puzzling of crimes. But in the real world, doctors often play the role of a detective in the practice of medicine – to correctly diagnose their patients – a crucial challenge to ensure they can receive appropriate medical care.

In January last year, a female patient in her 60s was admitted to a hospital in Japan – for acute myeloid leukemia. She underwent chemotherapy and it was successful. Or so the doctors thought.

Her recovery was unusually slow, her doctors observed. This left to them suspecting a different type of leukemia, though conventional tests failed to show any sign of it.

Artificial Intelligence (AI) Watson diagnoses leukemia in 10 minutes

It seemed like a dead end for the medical Sherlocks – and the patient – until Arinobu Tojo, professor of molecular therapy at a hospital affiliated to the University of Tokyo’s Institute of Medical Science, sought IBM’s Watson for help. Watson, a cloud-based AI-powered computer system, has ingested tens of millions of oncology papers and vast volumes of leukemia data made available by international research institutes.

“This patient had mutations in more than 1,000 genes, but many of them were not related to her disease and they were just hereditary characteristics she had inherited from her parents,” Tojo said. “While it would have taken about two weeks for human scientists to check which of the 1,000 changes were diagnostically important or not, Watson did it in 10 minutes.”

To elucidate the cause of her illness, the researchers fed Watson the patient’s genetic data, and after cross-checking the database, the machine had detected gene mutations that are unique to a particular type of leukemia.

Watson’s quick work helped the researchers to conclude that the patient had a rare secondary leukemia caused by myelodysplastic syndromes, a group of diseases in which the bone marrow makes too few healthy blood cells.

Whilst Watson is a software that is capable of machine learning to help its users answer tough questions, Tojo remarks that Watson can often make errors as well. However, he notes that in 10 years or so, Watson’s quality will improve to such a degree that it will be common for doctors to use genetic tests in cancer treatment.

Nanorobotics allow for “Goldilocks reach” for cancer drugs

So on one hand, we have technology like Watson that can help doctors to diagnose illnesses that seem elusive. On the other, we have nanorobotics agents capable of navigating through a crowded stream of blood cells in the bloodstream and to administer a cancer-targeting drug.

This breakthrough in cancer research, made by researchers from Polytechnique Montréal, Université de Montréal and McGill University, is able to inject medicine for the optimal targeting of cancer and avoid causing damage to the surrounding organs and tissue. As a result, a drug’s dosage for a patient can be significantly reduced if it is highly toxic for them.

The research, published in Nature Nanotechnology, was conducted on mice, which were successfully administered nanorobotic agents into colorectal tumours.

“These legions of nanorobotic agents were actually composed of more than 100 million flagellated bacteria – and therefore self-propelled – and loaded with drugs that moved by taking the most direct path between the drug’s injection point and the area of the body to cure,” explains Professor Sylvain Martel, holder of the Canada Research Chair in Medical Nanorobotics and Director of the Polytechnique Montréal Nanorobotics Laboratory. “The drug’s propelling force was enough to travel efficiently and enter deep inside the tumours.”

When the nanorobotic agents enter a tumour, it is as if they know what to look for. The nanorobots would scour inside the tumour and upon encountering oxygen-depleted tumour areas, known as hypoxic zones, the nanorobots deliver the drugs here. Hypoxic zones, known to be resistant to most therapies such as radiotherapy, are created by the substantial consumption of oxygen by rapidly proliferative tumour cells. Delivering the drugs to these areas might effectively impede the growth of aggressive tumours.

“This innovative use of nanotransporters will have an impact not only on creating more advanced engineering concepts and original intervention methods, but it also throws the door wide open to the synthesis of new vehicles for therapeutic, imaging and diagnostic agents,” Professor Martel adds. “Chemotherapy, which is so toxic for the entire human body, could make use of these natural nanorobots to move drugs directly to the targeted area, eliminating the harmful side effects while also boosting its therapeutic effectiveness.”


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s