According to researchers from Google and the New York Stem Cell Foundation, a robotic system armed with AI-powered cameras can grow and image skin cells from test tubes to diagnose Parkinson’s disease with minimal human assistance.
It is estimated that Parkinson’s disease affects 2-3% of the population over the age of 65. Nerve cells deep in the basal ganglia region of the brain die slowly over time, impacting movement. Patients find it difficult to control their movements; their limbs may shake or feel stiff. Scientists don’t know what causes the disease, and it is currently incurable.
“Traditional drug discovery doesn’t work very well, especially for complex diseases like Parkinson’s disease,” said NYSCF CEO Susan Solomon. Explain in a report. “The robotic technology that NYSCF has built allows us to generate large amounts of data from large patient populations and discover new disease signatures as an entirely new basis for discovering drugs that actually work.”
The non-profit research institute has developed a robotic system capable of performing laboratory experiments in a controlled environment. Known as the Global Stem Cell Array, the robotic system is made up of a series of machines with robotic arms capable of manipulating test tube samples for cell culture.
Fibroblast cells are extracted and grown from skin cells – the process takes about four weeks. Google Research engineers took the system one step further by installing AI software trained to diagnose Parkinson’s disease from skin cells with 79% accuracy, according to a research paper. published on Friday at Nature Communication.
Skin samples are not currently used in the diagnosis of Parkinson’s disease, said Daniel Paull, senior vice president of discovery and platform development at NYSCF. The register.
“This was a new line of research where we wanted to see if we could identify a signature in patient fibroblasts using artificial intelligence,” he explained. “Other groups have already described alterations in the behavior of fibroblasts from patients with Parkinson’s disease, in particular dysfunction of mitochondria and other organelles, although these are largely small studies. “
First, cells obtained from patient skin biopsies are cultured in test tubes. Then these samples are stained and placed under a fluorescence microscope. The cameras take images of the cells and feed them into a convolutional neural network to study them. The model is trained to focus on individual cells and determine whether or not they belong to a patient with Parkinson’s disease and the robots can operate 24/7 without human assistance.
Skin cell biopsies obtained from 91 participants were used to train and test the system. The AI-powered Global Stem Cell Array was able to diagnose the disease with 79% accuracy. He was able to trace cells from individual patients, even when new samples collected years after the first biopsy were analyzed.
An image of NYSCF’s Global Stem Cell Array robot. Image credit: Samwan Rob, The New York Stem Cell Foundation… Click to enlarge
Solomon said the project was a proof of concept that showed Parkinson’s disease could be diagnosed by examining skin samples from patients. The technology – using a robotic system armed with AI software to grow cells – could also potentially help scientists in drug discovery. “You can apply drugs to diseased cells and, using AI, see if you can find drugs that make diseased cells look like cells from healthy individuals,” she told us.
It is difficult to distinguish a diseased skin cell from a healthy one, which humans cannot do with their own eyes. The machine learning algorithm needed to analyze over 1,200 features. “Our analysis indicates that the detection [Parkinson’s disease-specific] the morphological signatures are extremely complex, as is its clinical manifestation, and comprehensive perturbation studies will be needed to delineate the underlying molecular mechanisms,” the paper explains.
Combining the robotic lab worker with AI algorithms will allow researchers to study a wider range of diseases in greater depth, Paull said. “This is the first tool to successfully identify disease characteristics with such precision and sensitivity. Its power to identify patient subgroups has important implications for precision medicine and drug development in many life-threatening diseases.
Solomon said the NYSCF plans to continue to develop the technology so it can be used in therapeutic or diagnostic applications in clinical settings. “We continue to improve our abilities to accurately stratify diseased patients from controls. We are now advancing this approach in other areas of disease, from very common diseases like aging to extremely rare conditions,” a- she declared. The Reg. ®