AI Diagnoses Illness Based On the Sound of Your Voice

Voices offer lots of information. Turns out, they can even help diagnose an illness — and researchers are working on an app for that. The National Institutes of Health is funding a massive research project to collect voice data and develop an AI that could diagnose people based on their speech. Everything from your vocal cord vibrations to breathing patterns when you speak offers potential information about your health, says laryngologist Dr. Yael Bensoussan, the director of the University of South Florida’s Health Voice Center and a leader on the study.

We asked experts: Well, if you close your eyes when a patient comes in, just by listening to their voice, can you have an idea of the diagnosis they have?” Bensoussan says. “And that’s where we got all our information.”

Someone who speaks low and slowly might have Parkinson’s disease. Slurring is a sign of a stroke. Scientists could even diagnose depression or cancer. The team will start by collecting the voices of people with conditions in five areas: neurological disorders, voice disorders, mood disorders, respiratory disorders and pediatric disorders like autism and speech delays. The project is part of the NIH‘s Bridge to AI program, which launched over a year ago with more than $100 million in funding from the federal government, with the goal of creating large-scale health care databases for precision medicine.

We were really lacking large what we call open source databases,” Bensoussan says. “Every institution kind of has their own database of data. But to create these networks and these infrastructures was really important to then allow researchers from other generations to use this data.” This isn’t the first time researchers have used AI to study human voices, but it’s the first time data will be collected on this level — the project is a collaboration between USF, Cornell and 10 other institutions. “We saw that everybody was kind of doing very similar work but always at a smaller level,” Bensoussan says. “We needed to do something as a team and build a network.”

The ultimate goal is an app that could help bridge access to rural or underserved communities, by helping general practitioners refer patients to specialists. Long term, iPhones or Alexa could detect changes in your voice, such as a cough, and advise you to seek medical attention.


Brain Implants Imminent

It’s inevitable that we’ll see brain implants become a common piece of technology — first for those who suffer from certain neurological disorders like epilepsy, then later on as an enhancement for the average person looking for a cognitive boost. Despite growing research and development in the field of brain-computer interfaces (BCIs), there has been little progress when it comes to the ethics of this technology.

Two new papers have been published by researchers with North Carolina State University addressing the ethical matters around BCI technology, including external devices that aren’t implanted and internal devices that are implanted in the brain. The researchers pay particular focus on implanted BCIs and such technologies intended for cognitive enhancement.

Put simply, BCI devices are designed to take brain signals and translate them into data for a computer to utilize. Perhaps the best example of such technology comes from Elon Musk’s Neuralink, which recently gave a demonstration of a brain implant involving pigs. Musk presented the technology as promising for people suffering from neurological conditions, among other things.

The invasive devices are more efficient, since they can read signals directly from the brain. However, they also raise more ethical concerns. For example, invasive BCI technologies carry more associated risks such as surgery, infection, and glial scarring – and invasive BCI devices would be more difficult to replace as technology improves.” said Veljko Dubljević, a co-author on both of the new papers, pointing out the particularly tricky issue of implants.

Among other things, the papers note that there are two areas, in particular, that should get priority when it comes to exploring ethical considerations: the psychological and physical effects of brain-computer interfaces. Multiple issues are presented, including the potential long-term effects of these devices, whether it is ethical to use animals to test invasive technologies, and what kind of psychological effects may manifest related to various BCI technologies.

The researchers present one example of potential unwanted psychological outcomes, noting a study in which people with epilepsy were given an advanced warning of seizures via an invasive BCI — and some of those patients went on to develop ‘radical psychological distress’ as a result. The researchers also explore the potential future use of BCIs for enhancing cognition, a technological future that would expand beyond the current trend of using ‘smart drugs.’ If someone with an enhancing implant takes a test, are the results ‘authenticas they would be from someone who doesn’t have a BCI?


Algorithms Boost Cell Therapy

Cellular therapy is a powerful strategy to produce patient-specific, personalised cells to treat many diseases, including heart disease and neurological disorders. But a major challenge for cell therapy applications is keeping cells alive and well in the lab.

That may soon change as researchers at Duke-NUS Medical School, Singapore, and Monash University, Australia, have devised an algorithm that can predict what molecules are needed to keep cells healthy in laboratory cultures. They developed a computational approach called EpiMogrify, that can predict the molecules needed to signal stem cells to change into specific tissue cells, which can help accelerate treatments that require growing patient cells in the lab.

Computational biology is rapidly becoming a key enabler in cell therapy, providing a way to short-circuit otherwise expensive and time-consuming discovery approaches with cleverly designed algorithms,” said Assistant Professor Owen Rackham, a computational biologist at Duke-NUS, and a senior and corresponding author of the study, published today in the journal Cell Systems.

In the laboratory, cells are often grown and maintained in cell cultures, formed of a substance, called a medium, which contains nutrients and other molecules. It has been an ongoing challenge to identify the necessary molecules to maintain high-quality cells in culture, as well as finding molecules that can induce stem cells to convert to other cell types.

The research team developed a computer model called EpiMogrify that successfully identified molecules to add to cell culture media to maintain healthy nerve cells, called astrocytes, and heart cells, called cardiomyocytes. They also used their model to successfully predict molecules that trigger stem cells to turn into astrocytes and cardiomyocytes. “Research at Duke-NUS is paving the road for cell therapies and regenerative medicine to enter the clinic in Singapore and worldwide; this study leverages our expertise in computational and systems biology to facilitate the good manufacturing practice (GMP) production of high-quality cells for these much needed therapeutic applications,” said Associate Professor Enrico Petretto, who leads the Systems Genetics group at Duke-NUS, and is a senior and corresponding author of the study.