Posts Tagged ‘medicine’

by George Dvorsky

Using brain-scanning technology, artificial intelligence, and speech synthesizers, scientists have converted brain patterns into intelligible verbal speech—an advance that could eventually give voice to those without.

It’s a shame Stephen Hawking isn’t alive to see this, as he may have gotten a real kick out of it. The new speech system, developed by researchers at the ​Neural Acoustic Processing Lab at Columbia University in New York City, is something the late physicist might have benefited from.

Hawking had amyotrophic lateral sclerosis (ALS), a motor neuron disease that took away his verbal speech, but he continued to communicate using a computer and a speech synthesizer. By using a cheek switch affixed to his glasses, Hawking was able to pre-select words on a computer, which were read out by a voice synthesizer. It was a bit tedious, but it allowed Hawking to produce around a dozen words per minute.

But imagine if Hawking didn’t have to manually select and trigger the words. Indeed, some individuals, whether they have ALS, locked-in syndrome, or are recovering from a stroke, may not have the motor skills required to control a computer, even by just a tweak of the cheek. Ideally, an artificial voice system would capture an individual’s thoughts directly to produce speech, eliminating the need to control a computer.

New research published today in Scientific Advances takes us an important step closer to that goal, but instead of capturing an individual’s internal thoughts to reconstruct speech, it uses the brain patterns produced while listening to speech.

To devise such a speech neuroprosthesis, neuroscientist Nima Mesgarani and his colleagues combined recent advances in deep learning with speech synthesis technologies. Their resulting brain-computer interface, though still rudimentary, captured brain patterns directly from the auditory cortex, which were then decoded by an AI-powered vocoder, or speech synthesizer, to produce intelligible speech. The speech was very robotic sounding, but nearly three in four listeners were able to discern the content. It’s an exciting advance—one that could eventually help people who have lost the capacity for speech.

To be clear, Mesgarani’s neuroprosthetic device isn’t translating an individual’s covert speech—that is, the thoughts in our heads, also called imagined speech—directly into words. Unfortunately, we’re not quite there yet in terms of the science. Instead, the system captured an individual’s distinctive cognitive responses as they listened to recordings of people speaking. A deep neural network was then able to decode, or translate, these patterns, allowing the system to reconstruct speech.

“This study continues a recent trend in applying deep learning techniques to decode neural signals,” Andrew Jackson, a professor of neural interfaces at Newcastle University who wasn’t involved in the new study, told Gizmodo. “In this case, the neural signals are recorded from the brain surface of humans during epilepsy surgery. The participants listen to different words and sentences which are read by actors. Neural networks are trained to learn the relationship between brain signals and sounds, and as a result can then reconstruct intelligible reproductions of the words/sentences based only on the brain signals.”

Epilepsy patients were chosen for the study because they often have to undergo brain surgery. Mesgarani, with the help of Ashesh Dinesh Mehta, a neurosurgeon at Northwell Health Physician Partners Neuroscience Institute and a co-author of the new study, recruited five volunteers for the experiment. The team used invasive electrocorticography (ECoG) to measure neural activity as the patients listened to continuous speech sounds. The patients listened, for example, to speakers reciting digits from zero to nine. Their brain patterns were then fed into the AI-enabled vocoder, resulting in the synthesized speech.

The results were very robotic-sounding, but fairly intelligible. In tests, listeners could correctly identify spoken digits around 75 percent of the time. They could even tell if the speaker was male or female. Not bad, and a result that even came as “a surprise” to Mesgaran, as he told Gizmodo in an email.

Recordings of the speech synthesizer can be found here (the researchers tested various techniques, but the best result came from the combination of deep neural networks with the vocoder).

The use of a voice synthesizer in this context, as opposed to a system that can match and recite pre-recorded words, was important to Mesgarani. As he explained to Gizmodo, there’s more to speech than just putting the right words together.

“Since the goal of this work is to restore speech communication in those who have lost the ability to talk, we aimed to learn the direct mapping from the brain signal to the speech sound itself,” he told Gizmodo. “It is possible to also decode phonemes [distinct units of sound] or words, however, speech has a lot more information than just the content—such as the speaker [with their distinct voice and style], intonation, emotional tone, and so on. Therefore, our goal in this particular paper has been to recover the sound itself.”

Looking ahead, Mesgarani would like to synthesize more complicated words and sentences, and collect brain signals of people who are simply thinking or imagining the act of speaking.

Jackson was impressed with the new study, but he said it’s still not clear if this approach will apply directly to brain-computer interfaces.

“In the paper, the decoded signals reflect actual words heard by the brain. To be useful, a communication device would have to decode words that are imagined by the user,” Jackson told Gizmodo. “Although there is often some overlap between brain areas involved in hearing, speaking, and imagining speech, we don’t yet know exactly how similar the associated brain signals will be.”

William Tatum, a neurologist at the Mayo Clinic who was also not involved in the new study, said the research is important in that it’s the first to use artificial intelligence to reconstruct speech from the brain waves involved in generating known acoustic stimuli. The significance is notable, “because it advances application of deep learning in the next generation of better designed speech-producing systems,” he told Gizmodo. That said, he felt the sample size of participants was too small, and that the use of data extracted directly from the human brain during surgery is not ideal.

Another limitation of the study is that the neural networks, in order for them do more than just reproduce words from zero to nine, would have to be trained on a large number of brain signals from each participant. The system is patient-specific, as we all produce different brain patterns when we listen to speech.

“It will be interesting in future to see how well decoders trained for one person generalize to other individuals,” said Jackson. “It’s a bit like early speech recognition systems that needed to be individually trained by the user, as opposed to today’s technology, such as Siri and Alexa, that can make sense of anyone’s voice, again using neural networks. Only time will tell whether these technologies could one day do the same for brain signals.”

No doubt, there’s still lots of work to do. But the new paper is an encouraging step toward the achievement of implantable speech neuroprosthetics.

https://gizmodo.com/neuroscientists-translate-brain-waves-into-recognizable-1832155006

https://www.nature.com/articles/s41598-018-37359-z

Advertisements

Levels of a protein called neurofilament light chain increase in the blood and spinal fluid of some Alzheimer’s patients 16 years before they develop symptoms, according to a study published January 21 in Nature Medicine.

The results suggest that neurofilament light chain (NfL), which is part of the cytoskeleton of neurons and has previously been tied to brain damage in mice, could serve as a biomarker to noninvasively track the progression of the disease. “This is something that would be easy to incorporate into a screening test in a neurology clinic,” coauthor Brian Gordon, an assistant professor of radiology at Washington University, says in a press release.

Gordon and his colleagues measured NfL in nearly 250 people carrying an Alzheimer’s-risk allele and more than 160 of their relatives who did not carry the variant. They found that those at risk of developing the disease had higher levels of the protein early on, and that NfL levels in both the blood and spinal fluid were on the rise well before the patients began to show signs of neurodegeneration, more than 16 years before disease onset.

Examining a subset of the patients more closely, the team saw that the rate of increase in NfL correlated with the shrinkage of a brain region called the precuneus, and patients whose NfL levels were rising rapidly tested worse on cognitive tests. “It is not necessarily the absolute levels which tell you your neurodegeneration is ongoing, it is the rate of change,” coauthor Mathias Jucker, a professor of cellular neurology at the German Center for Neurodegenerative Diseases in Tübingen, tells The Guardian.

The Alzheimer’s-linked mutation carried by patients examined in this study only affects about 1 percent of people who get the neurodegenerative disease, so the approach must be validated in a broader patient population, James Pickett, the head of research at the Alzheimer’s Society, tells The Guardian.

“We validated it in people with Alzheimer’s disease because we know their brains undergo lots of neurodegeneration, but this marker isn’t specific for Alzheimer’s,” Gordon says in the release. “I could see this being used in the clinic in a few years to identify signs of brain damage in individual patients.”

Meanwhile, a research team at Seoul National University in South Korea described another potential blood test for Alzheimer’s, focusing on the tau and amyloid proteins known to be associated with the disease. According to their study published today in Brain, blood levels of tau and amyloid correlate with how much tau has accumulated in the brain, as well as other markers of neurodegeneration such as hippocampal volume. “These results indicate that combination of plasma tau and amyloid-β1–42 levels might be potential biomarkers for predicting brain tau pathology and neurodegeneration,” the researchers write in their report.

https://www.the-scientist.com/news-opinion/protein-changes-detected-in-blood-years-before-alzheimers-onset-65347


Case Western Reserve researchers cure drug-resistant infections without antibiotics

Biochemists, microbiologists, drug discovery experts and infectious disease doctors have teamed up in a new study that shows antibiotics are not always necessary to cure sepsis in mice. Instead of killing causative bacteria with antibiotics, researchers treated infected mice with molecules that block toxin formation in bacteria. Every treated mouse survived. The breakthrough study, published in Scientific Reports, suggests infections in humans might be cured the same way.

The molecules cling to a toxin-making protein found across Gram-positive bacterial species, called AgrA, rendering it ineffective. Treating mice with the therapeutic molecules effectively cured infections caused by methicillin-resistant Staphylococcus aureus (MRSA). S. aureus is notorious for its ability to overcome even the most potent antibiotics. Its resistance arsenal is broad, limiting therapeutic options to treat infections.

In a mouse model of S. aureus sepsis, treatment with small molecules alone resulted in 100 percent survival, while 70 percent of untreated animals died. The small molecules were as effective in promoting survival as antibiotics currently used to treat S. aureus infections. The molecules also appear to give antibiotics a boost. Septic mice treated with a combination of the small molecules and antibiotics had 10x fewer bacteria in their bloodstream than mice treated with antibiotic alone.

“For relatively healthy patients, such as athletes suffering from a MRSA infection, these molecules may be enough to clear an infection,” said Menachem Shoham, associate professor of biochemistry at Case Western Reserve University School of Medicine and senior author on the study. “For immunocompromised patients, combination therapy with the molecules and a low-dose antibiotic may be in order. The antibiotic in the combination could be one to which the bacteria are resistant in monotherapy, because our small molecules enhance the activity of conventional antibiotics, such as penicillin.”

With support from the small molecules, previously obsolete antibiotics could reenter the clinic.

Said Shoham: “This could provide a partial solution to the looming, global threat of antibiotic resistance.”

If available, antibiotics kill most bacteria, but a small number of bacteria with natural resistance survive. Over time, antibiotic-resistant bacteria multiply and spread. By Centers for Disease Control and Prevention estimates, at least two million Americans get an antibiotic-resistant infection annually. For some infections, effective antibiotics are no longer available. Disarming bacteria of disease-causing toxins represents a promising alternative to dwindling antibiotics.

Eliminating toxins frees up the immune system to eliminate bacterial pathogens instead of antibiotics, said Shoham, who also is affiliated with Q2 Pharma, Ltd., Haifa, Israel. “Without the toxins the bacteria become harmless. And since they don’t need the toxins to survive, there is less pressure to develop resistance.”

The small molecules work against multiple bacterial species. The new study included preliminary experiments showing the molecules prevent three other bacterial species from killing immune cells.

“These results indicate broad-spectrum efficacy against Gram-positive pathogens,” wrote the authors.

Added Shoham: “We have proven efficacy not only against MRSA but also against Staphylococcus epidermidis, which is notorious for clogging catheters, Streptococcus pyogenes that causes strep throat, Streptococcus pneumoniae, and other pathogens.”

Shoham led the study in collaboration with colleagues from the departments of biochemistry and dermatology and the Center for RNA and Therapeutics at Case Western Reserve University. The researchers developed two small molecules, F12 and F19, both of which potentiate antibiotic efficacy in the mouse models. The researchers are now working to commercialize both potential drugs. Case Western Reserve University has issued a license to Q2Pharma, Ltd., a biopharmaceutical startup company in Israel, to perform additional preclinical studies and develop F12 and F19 for clinical trials. Their initial trials will focus on patients suffering from systemic multi-drug resistant infections.

This research was supported by a Transformational Award to Menachem Shoham by the Dr. Ralph and Marian Falk Medical Research Trust Bank of America, N.A., Trustee. Some in vitro studies were supported by NIH/NIAID Preclinical Services under contract numbers HHSN272201100012I and HHSN27200007.

Greenberg, M, et al. “Small-molecule AgrA inhibitors F12 and F19 act as antivirulence agents against Gram-positive pathogens.” Scientific Reports. 2018 Oct 1;8(1):14578. doi: 10.1038/s41598-018-32829-w. PMID: 30275455.

By Sara G. Miller

Gluten has been implicated in a number of symptoms related to celiac disease that go beyond the digestive system, including rashes, anemia and headaches. But according to a recent case report, the wheat protein played a role in one woman’s severe psychosis.

The 37-year-old woman, whose case was described in the report, was studying for her Ph.D. when she started having delusions. Her symptoms began with a belief that people were talking about her as part of a conspiracy in which friends, family members and strangers were acting out scenes for her in a “game,” the doctors who treated the woman wrote in their report, published May 12 in The New England Journal of Medicine.

After making threats against her family, the patient was admitted to a psychiatric hospital and was diagnosed with a psychotic disorder, the doctors wrote. She was prescribed anti-psychotic medications to help control her symptoms, but they did not work very well, according to the report.

During the woman’s stay at the psychiatric hospital and at follow-up appointments after she was released, doctors noticed that she had several vitamin and mineral deficiencies, had lost a lot of weight and also had thyroid problems, according to the report.

These symptoms led doctors to suspect that the woman had celiac disease, said Dr. Alessio Fasano, director of the Center for Celiac Research and Treatment at Massachusetts General Hospital in Boston and one of the doctors who treated the woman. It was at that point that the doctors who wrote the case report got involved, he said.

The doctors at Massachusetts General Hospital confirmed that the woman had celiac disease, according to the report. However, her delusions led her to believe that the doctors were being “deceitful,” and she refused to follow a gluten-free diet, they wrote.

The woman lost her job, became homeless and attempted suicide, the doctors wrote. Eventually, she was rehospitalized at a psychiatric facility, where she was successfully placed on a gluten-free diet, they wrote.

When the woman was on a gluten-free diet, her symptoms improved, Fasano said. She was once again functional and aware of what gluten was doing to her, he said. She knew that being exposed to gluten caused her to lose control of her life, and she wanted people to understand that the gluten was causing this bizarre behavior, he added.

The differences between how the woman behaved on a gluten-free diet and after being exposed to gluten was like “Dr. Jekyll and Mr. Hyde,” Fasano said. “This was a bright young lady on her way to [getting] a Ph.D., and all of sudden,” something changed and she would do things that were harmful to herself and people around her, he said.

During the time the doctors were working with the woman, she inadvertently consumed gluten on several occasions, Fasano said. When this would happen, she would become completely lost, he said. But when she was gluten-free, she was well aware that she needed to avoid gluten because “she [didn’t] want to go to ‘that place,'” Fasano said.

When Fasano last saw the woman, around January 2016, he reported that she was doing very well. She was completely avoiding gluten, and her symptoms had gone away, he said. In fact, the woman was planning to participate in an experiment with her doctors so that they could study what happened to her when she consumed gluten, he said.

The plan was to do the experiment in a very controlled environment so that the patient would not do anything harmful, he said. The experiment would give the doctors the opportunity to study the inflammatory process that potentially caused these symptoms. They also planned to do some brain scans, he said.

But before the doctors could do the experiment, the woman accidentally ate some gluten, Fasano said. Her delusions returned, and she was put in jail after trying to kill her parents, he said.

https://www.livescience.com/55166-celiac-disease-gluten-psychosis.html

i-b-2-01

by SUKANYA CHARUCHANDRA

It wasn’t until the latter half of the 13th century that human dissections became acceptable in Italy. Previously, both the Roman Empire and Islamic law had prevented the dissection of humans and its depiction. While the Greek surgeon Galen’s anatomical drawings from the second century had been preserved and studied until the Renaissance, they were largely based on dissections of animals, such as apes.

In the mid-16th century, however, famed Flemish anatomist Andreas Vesalius dissected the bodies of executed criminals—not an uncommon practice in that period—while studying in Paris. He realized that Galen had been “misled” by apes, whose anatomy was not exactly like that of humans.

“The challenge of anatomy is rendering the 3-D experience of opening bodies onto a 2-D page,” writes Hannah Marcus, a science historian at Harvard University, in an email to The Scientist. Lack of refrigeration also presented a challenge. In overcoming those hurdles to produce the first realistic depictions of internal human biology, Vesalius’s De Humani Corporis Fabrica, published in Basel, Switzerland, in 1543, galvanized the study of anatomy.

Meanwhile, Spanish-born Juan Valverde de Amusco was learning anatomy under the guidance of Roman surgeon Realdo Colombo, and possibly of Vesalius himself, at the University of Padua in Italy. Valverde observed and participated in many dissections under Colombo’s guidance, and pored over old books on the subject. He later moved to Rome and was welcomed into the home of Spanish Cardinal Juan Álvarez de Toledo.

In 1555, Valverde served as a doctor at the foremost contemporaneous Roman hospital, Santo Spirito, where many luminaries of anatomy worked during that period, including Bartolomeo Eustachi, under whom Valverde studied for a time. The following year, Valverde crafted the Spanish-language anatomical text Historia de la Composicion del Cuerpo Humano, or Account of the Composition of the Human Body. In seven parts, the book covered topics such as “bone and cartilage,” “ligaments and bandaging,” and “instruments of sensation and external motion.” Largely copied from the 1543 and 1555 editions of Vesalius’s tome, it included 15 new illustrations in four copper plates. Valverde’s book also included more than 60 corrections to Vesalius’s text, which enhanced the contemporary understanding of the intracranial passage of carotid arteries, the extraocular muscles, the stapes bone of the middle ear, and how blood moves through the septum. Historians attribute the few original illustrations to Spanish-born Gaspar Becerra.

“Vesalius was angry about Amusco’s work and accused him of plagiarism,” Marcus writes. In 1564, Vesalius wrote in his book Anatomicarum Gabrielis Fallopii Observationum Examen that “Valverde who never put his hand to a dissection and is ignorant of medicine as well as of the primary disciplines, undertook to expound our art in the Spanish language only for the sake of shameful profit.” Valverde conceded his borrowing, explaining that Vesalius’s drawings were so thorough that “it would look like envy or malignity not to take advantage of them.”

Valverde simplified Vesalius’s Latin text considerably, however, as he considered it difficult to understand. His more concise (and thus cheaper) text had more than a dozen editions published in Italian, Latin, Dutch, and Greek, in addition to Spanish, and facilitated the spread of scientific ideas and Vesalius’s modern anatomy throughout Europe and the Spanish Americas.

https://www.the-scientist.com/foundations/homo-sapiens-exposed–1556-64679

microbial-activity-in-the-mouth-may-help-identify-autism-in-children

Weight gain trajectories in early childhood are related to the composition of oral bacteria of two-year-old children, suggesting that this understudied aspect of a child’s microbiota — the collection of microorganisms, including beneficial bacteria, residing in the mouth — could serve as an early indicator for childhood obesity. A study describing the results appears September 19 in the journal Scientific Reports.

“One in three children in the United States is overweight or obese,” said Kateryna Makova, Pentz Professor of Biology and senior author of the paper. “If we can find early indicators of obesity in young children, we can help parents and physicians take preventive measures.”

The study is part of a larger project with researchers and clinicians at the Penn State Milton S. Hershey Medical Center called INSIGHT, led by Ian Paul, professor of pediatrics at the Medical Center, and Leann Birch, professor of foods and nutrition at the University of Georgia. The INSIGHT trial includes nearly 300 children and tests whether a responsive parenting intervention during a child’s early life can prevent the development of obesity. It is also designed to identify biological and social risk factors for obesity.

“In this study, we show that a child’s oral microbiota at two years of age is related to their weight gain over their first two years after birth,” said Makova.

The human digestive tract is filled with a diverse array of microorganisms, including beneficial bacteria, that help ensure proper digestion and support the immune system. This “microbiota” shifts as a person’s diet changes and can vary greatly among individuals. Variation in gut microbiota has been linked to obesity in some adults and adolescents, but the potential relationship between oral microbiota and weight gain in children had not been explored prior to this study.

“The oral microbiota is usually studied in relation to periodontal disease, and periodontal disease has in some cases been linked to obesity,” said Sarah Craig, a postdoctoral scholar in biology at Penn State and first author of the paper. “Here, we explored any potential direct associations between the oral microbiota and child weight gain. Rather than simply noting whether a child was overweight at the age of two, we used growth curves from their first two years after birth, which provides a more complete picture of how the child is growing. This approach is highly innovative for a study of this kind, and gives greater statistical power to detect relationships.”

Among 226 children from central Pennsylvania, the oral microbiota of those with rapid infant weight gain — a strong risk factor for childhood obesity — was less diverse, meaning it contained fewer groups of bacteria. These children also had a higher ratio of Firmicutes to Bacteroidetes, two of the most common bacteria groups found in the human microbiota.

“A healthy person usually has a lot of different bacteria within their gut microbiota,” said Craig. “This high diversity helps protect against inflammation or harmful bacteria and is important for the stability of digestion in the face of changes to diet or environment. There’s also a certain balance of these two common bacteria groups, Firmicutes and Bacteroidetes, that tends to work best under normal healthy conditions, and disruptions to that balance could lead to dysregulation in digestion.”

Lower diversity and higher Firmicutes to Bacteroidetes (F:B) ratio in gut microbiota are sometimes observed as a characteristic of adults and adolescents with obesity. However, the researchers did not see a relationship of weight gain with either of these measures in gut microbiota of two-year-olds, suggesting that the gut microbiota may not be completely established at two years of age and may still be undergoing many changes.

“There are usually dramatic changes to an individual’s microbiota as they develop during early childhood,” said Makova. “Our results suggest that signatures of obesity may be established earlier in oral microbiota than in gut microbiota. If we can confirm this in other groups of children outside of Pennsylvania, we may be able to develop a test of oral microbiota that could be used in clinical care to identify children who are at risk for developing obesity. This is particularly exciting because oral samples are easier to obtain than those from the gut, which require fecal samples.”

Interestingly, weight gain in children was also related to diversity of their mother’s oral microbiota. This could reflect a genetic predisposition of the mother and child to having a similar microbiota, or the mother and child having a similar diet and environment.

“It could be a simple explanation like a shared diet or genetics, but it might also be related to obesity,” said Makova. “We don’t know for sure yet, but if there is an oral microbiome signature linked to the dynamics of weight gain in early childhood, there is a particular urgency to understand it. Now we are using additional techniques to look at specific species of bacteria–rather than larger taxonomic groups of bacteria–in both the mothers and children to see whether specific bacteria species influence weight gain and the risk of obesity.”

In addition to Makova, Craig, Paul, and Birch, the research team includes Jennifer Savage, Michele Marini, Jennifer Stokes, Anton Nekrutenko, Matthew Reimherr, and Francesca Chiaromonte from Penn State, Daniel Blankenberg from the Cleveland Clinic, and Alice Carla Luisa Parodi from Politecnico di Milano. INSIGHT (Intervention Nurses Start Infants Growing on Healthy Trajectories) is coordinated through the Penn State Milton S. Hershey Medical Center.

This work is supported by the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK); the Penn State Eberly College of Science; the Penn State Institute for Cyberscience; the National Center for Research Resources and the National Center for Advancing Translational Sciences of the National Institutes of Health (NIH); and the Pennsylvania Department of Health using Tobacco CURE funds.

http://science.psu.edu/news-and-events/2018-news/Makova9-2018

35472460 - digital illustration of human lungs in colour background

Artificial intelligence (AI) can be an invaluable aid to help lung doctors interpret respiratory symptoms accurately and make a correct diagnosis, according to new research presented yesterday (Wednesday) at the European Respiratory Society International Congress.

Dr Marko Topalovic (PhD), a postdoctoral researcher at the Laboratory for Respiratory Diseases, Catholic University of Leuven (KU Leuven), Belgium, told the meeting that after training an AI computer algorithm using good quality data, it proved to be more consistent and accurate in interpreting respiratory test results and suggesting diagnoses than lung specialists.

“Pulmonary function tests provide an extensive series of numerical outputs and their patterns can be hard for the human eye to perceive and recognise; however, it is easy for computers to manage large quantities of data like these and so we thought AI could be useful for pulmonologists. We explored if this was true with 120 pulmonologists from 16 hospitals. We found that diagnosis by AI was more accurate in twice as many cases as diagnosis by pulmonologists. These results show how AI can serve as a second opinion for pulmonologists when they are assessing and diagnosing their patients,” he said.

Pulmonary function tests (PFT) include: spirometry, which involves the patient breathing through a mouthpiece to measure the amount of air inhaled and exhaled; a body box or plethysmography test, which enables doctors to assess lung volume by measuring the pressure in a booth in which the patient is sitting and breathing through a mouthpiece; and a diffusion capacity test, which tests how well a patient’s lungs are able to transfer oxygen and carbon dioxide to and from the bloodstream by testing the efficiency of the alveoli (small air sacks in the lungs). Results from these tests give doctors important information about the functioning of the lungs, but do not tell them what is wrong with the patient. This requires interpretation of the results in order to reach a diagnosis.

In this study, the researchers used historical data from 1430 patients from 33 Belgian hospitals. The data were assessed by an expert panel of pulmonologists and interpretations were measured against gold standard guidelines from the European Respiratory Society and the American Thoracic Society. The expert panel considered patients’ medical histories, results of all PFTs and any additional tests, before agreeing on the correct interpretation and diagnosis for each patient.

“When training the AI algorithm, the use of good quality data is of utmost importance,” explained Dr Topalovic. “An expert panel examined all the results from the pulmonary function tests, and the other tests and medical information as well. They used these to reach agreement on final diagnoses that the experts were confident were correct. These were then used to develop an algorithm to train the AI, before validating it by incorporating it into real clinical practice at the University Hospital Leuven. The challenging part was making sure the algorithm recognised patterns of up to nine different diseases.”

Then, 120 pulmonologists from 16 European hospitals (from Belgium, France, The Netherlands, Germany and Luxembourg) made 6000 interpretations of PFT data from 50 randomly selected patients. The AI also examined the same data. The results from both were measured against the gold standard guidelines in the same way as during development of the algorithm.

The researchers found that the interpretation of the PFTs by the pulmonologists matched the guidelines in 74% of cases (with a range of 56-88%), but the AI-based software interpretations perfectly matched the guidelines (100%). The doctors were able to correctly diagnose the primary disease in 45% of cases (with a range of 24-62%), while the AI gave a correct diagnosis in 82% of cases.

Dr Topalovic said: “We found that the interpretation of pulmonary function tests and the diagnosis of respiratory disease by pulmonologists is not an easy task. It takes more information and further tests to reach a satisfactory level of accuracy. On the other hand, the AI-based software has superior performance and therefore can provide a powerful decision support tool to improve current clinical practice. Feedback from doctors is very positive, particularly as it helps them to identify difficult patterns of rare diseases.”

Two large Belgian hospitals are already using the AI-based software to improve interpretations and diagnoses. “We firmly believe that we can empower doctors to make their interpretations and diagnoses easier, faster and better. AI will not replace doctors, that is certain, because doctors are able to see a broader perspective than that presented by pulmonary function tests alone. This enables them to make decisions based on a combination of many different factors. However, it is evident that AI will augment our abilities to accomplish more and decrease chances for errors and redundant work. The AI-based software has superior performance and therefore may provide a powerful decision support tool to improve current clinical practice.

“Nowadays, we trust computers to fly our planes, to drive our cars and to survey our security. We can also have confidence in computers to label medical conditions based on specific data. The beauty is that, independent of location or medical coverage, AI can provide the highest standards of PFT interpretation and patients can have the best and affordable diagnostic experience. Whether it will be widely used in future clinical applications is just a matter of time, but will be driven by the acceptance of the medical community,” said Dr Topalovic.

He said the next step would be to get more hospitals to use this technology and investigate transferring the AI technology to primary care, where the data would be captured by general practitioners (GPs) to help them make correct diagnoses and referrals.

Professor Mina Gaga is President of the European Respiratory Society, and Medical Director and Head of the Respiratory Department of Athens Chest Hospital, Greece, and was not involved in the study. She said: “This work shows the exciting possibilities that artificial intelligence offers to doctors to help them provide a better, quicker service to their patients. Over the past 20 to 30 years, the evolution in technology has led to better diagnosis and treatments: a revolution in imaging techniques, in molecular testing and in targeted treatments have make medicine easier and more effective. AI is the new addition! I think it will be invaluable in helping doctors and patients and will be an important aid to their decision-making.”

[1] Abstract no: PA5290, “Artificial intelligence improves experts in reading pulmonary function tests”, by M. Topalovic et al; Poster Discussion “The importance of the pulmonary function test in different clinical settings”, 08.30-10.30 hrs CEST, Wednesday 19 September, Room 7.2D.

The research was funded by Vlaams Agentschap Innoveren & Ondernemen – VLAIO (Belgian government body: Agency for Innovation and Entrepreneurship – VLAIO)

http://www.europeanlung.org/en/news-and-events/media-centre/press-releases/artificial-intelligence-improves-doctors%E2%80%99-ability-to-correctly-interpret-tests-and-diagnose-lung-disease