System Bits: June 26

I’m enjoying a very busy Design Automation Conference this week in San Francisco, and on the lookout for interesting research topics here. In the meantime, enjoy a few interesting items from around the globe.

AI platform diagnoses Zika and other pathogens
University of Campinas (UNICAMP) researchers in Brazil have developed an AI platform that can diagnose several diseases with a high degree of precision using metabolic markers found in patients’ blood.

Method created in Brazil combines mass spectrometry analysis of blood serum with an algorithm that recognizes patterns associated with viral diseases as well as diseases of bacterial, fungal and even genetic origin.
Source: UNICAMP

The team explained the method combines mass spectrometry, which can identify tens of thousands of molecules present in blood serum, with an artificial intelligence algorithm capable of finding patterns associated with diseases of viral, bacterial, fungal and even genetic origin.

The research was conducted as part of Carlos Fernando Odir Rodrigues Melo’s PhD. “We used infection by Zika virus as a model to develop the platform and showed that in this case, diagnostic accuracy exceeded 95%. One of the main advantages is that the method doesn’t lose sensitivity even if the virus mutates,” said Melo’s supervisor Rodrigo Ramos Catharino, principal investigator for the project, and a professor at UNICAMP’s School of Pharmaceutical Sciences (FCF) and head of its Innovare Biomarker Laboratory.

Another strength of the platform, he said, is the capacity to identify positive cases of Zika even in blood serum analyzed 30 days after the start of infection, when the acute phase of the disease is over.

“None of the currently available diagnostic kits has the sensitivity to detect infection by Zika after the end of the acute phase. The method we developed could be useful to analyze transfusion blood bags, for example,” Catharino said.

All the data obtained in a spectrometry analysis of both a group that tested positive for Zika and a control group were then fed into a computer program running a random-forest machine learning algorithm. This type of artificial intelligence tool is capable of analyzing a large amount of data by specific statistical methods in search of patterns that can be used as a basis for classification, prediction, decision making, modeling and so on.

“The algorithm separates samples randomly, determines which one will be the training group and the blind group, and then carries out testing and validation. At the end, it tells us whether with that number of samples it was possible to obtain a set of metabolic markers capable of identifying patients infected by Zika,” Catharino explained.

Each new set of patient data fed into the program enhances its learning capacity and makes it more sensitive, he went on. In the case of Zika, a panel of 42 biomarkers was established as a specific key to identifying the virus. Twelve of these were found by the algorithm to be highly prevalent in the blood of patients who tested positive for the disease.

“In this platform, it isn’t important to know a lot individually about each of the molecules that serve as markers of the infection. It’s the set that matters and that will tell us with a high level of accuracy whether we’re looking at Zika. Moreover, even if the virus mutates, the program adapts and changes too. It’s not a static methodology,” Catharino said.

The UNICAMP group is currently performing tests to evaluate the platform’s capacity to diagnose systemic diseases caused by fungi. They also plan to test how well it detects bacterial and genetic diseases. Anderson de Rezende Rocha, a professor at the same university’s Institute of Computing (IC-UNICAMP), is collaborating on the research.

Interestingly, the researchers said any laboratory equipped with a mass spectrometer could use the new diagnostic platform developed at UNICAMP. Mass spectrometers are routinely used in procedures such as measuring vitamin D and screening blood spots from newborns to detect metabolic diseases via the heel prick test.

“Our proposal is to make the platform available in the cloud, so that it can be downloaded to any mass spectrometer anywhere in the world. Data analysis can be performed online. Whether it would be free or paid is yet to be defined,” Catharino added.

Smart, stretchable electronic skin
An electrically-conductive metal carbide within a hydrogel composite has been developed by KAUST researchers that senses, stretches and heals like human skin for use in wound healing, soft robotics and biosensing.

Signals from the electrically conductive hydrogel can clearly distinguish between different facial expressions.
Source: KAUST

Husam Alshareef, professor of materials science and engineering at KAUST believes the material outperforms all previously reported hydrogels and introduces new functionalities.

Indeed, smart materials that flex, sense and stretch like skin have many applications in which they interact with the human body including biodegradable patches that help wounds heal, wearable electronics, and touch-sensitive robotic devices.

The material is a composite of the water-containing hydrogel and a metal-carbide compound known as MXene, the team said. As well as being able to stretch by more than 3400%, the material can quickly return to its original form and will adhere to many surfaces, including skin. When cut into pieces, it can quickly mend itself upon reattachment.

This differing sensitivity to stretching and compression is what adds a new dimension to the sensing capability of hydrogels, the researchers noted.

These capabilities could be crucial in applications that sense changes in the skin and convert them into electronic signals. A thin slab of the material attached to a user’s forehead, for example, can distinguish between different facial expressions, such as a smile or a frown. This ability could allow patients with extreme paralysis to control electronic equipment and communicate.

Strips of the material attached to the throat have impressive abilities to convert speech into electronic signals. This might allow people with speech difficulties to be clearly heard.

“There is real potential for our material in various biosensing and biomedical applications,” says co-author Kanghyuck Lee.

More straightforward and extremely useful medical possibilities include flexible wound coverings that can release drugs to promote healing. These could be applied internally, on diseased organs, in addition to adhering externally to skin. The team also envisions developing a smart material that could monitor the volume and shape of an organ and vary drug release according to signals produced.

An ideal potential would be to combine both medical sensing and therapy. Other exciting possibilities lie in robotics, where the material could serve in touch-sensitive finger-like extensions for machinery, for example.

There are also anticounterfeiting possibilities, with slabs of the material and integrated electronics proving highly sensitive at detecting signatures as they are written.