Posted by Kostas Pantremenos in Epilepsy on October 13, 2020
Leonardo Bonilha, M.D. Ph.D., sees his clinical work and his research work as a seamless whole.
“I actually don’t see it as two different things. I think my job as a physician is to help people, but also to better understand diseases so treatments can improve,” said the SmartState endowed chair for brain imaging.
A neurologist, Bonilha splits his research interests between two important problems – epilepsy and aphasia. Epilepsy is one of the world’s oldest recognized conditions, going back to 4000 B.C., notes the World Health Organization. Doctors and researchers are still trying to fully understand the disease. Aphasia is a condition in which a person can’t produce or can’t understand language. It’s caused by damage to the brain, usually because of stroke.
Since joining the MUSC faculty in 2012, Bonilha has built a multidisciplinary lab with a varied group of researchers whose backgrounds include language pathology, neurology, biomedical imaging, biomedical engineering and neuropsychology.
“One of the main themes of the lab is to better understand the complexity of brain networks and how our brain functions emerge from the organization and the dynamics within the networks of neurons,” he said.
Training new researchers is an important part of his job. It’s not just a matter of more hands making lighter work; through the research, they see how these diseases affect people and begin thinking in a cross-disciplinary fashion.
“They form their careers and their thinking in terms of how to be researchers in the field,” he said. “Really, how we make an impact is by having multiple people thinking about these issues – talented and passionate investigators collaborating across disciplines.”
Teamwork across MUSC, and even across the state, is key as well. He works with the Stroke Recovery Research Center, housed in the College of Health Professions, as well as the Center for the Study of Aphasia Recovery (C-STAR), housed at the University of South Carolina (UofSC) led by Julius Fridriksson, Ph.D. Before completing his neurology residency at MUSC, Bonilha was an assistant research professor in the Department of Communication Sciences and Disorders in the Arnold School of Public Health at UofSC, and those professional ties helped to launch the Bonilha lab and have fostered continued collaboration.
“We are a strong group because of our collaborations. In fact, South Carolina is probably one of the best places in the country for aphasia research because of the pioneering work at UofSC and the synergism between our groups,” Bonilha said.
“There are no clear guidelines right now regarding which speech treatments are better for each patient,” said Janina Wilmskoetter, Ph.D., a postdoctoral scholar in Bonilha’s lab.
About 2 million people in the U.S. live with aphasia, according to the National Aphasia Association. Although aphasia can result from brain trauma or brain tumors, most often it is the result of a stroke. There are several subtypes of aphasia, but even within the same subtype, there is enough variability that the most effective treatment isn’t immediately apparent.
Language therapy is a well-established treatment for aphasia, but there are different types and it remains unclear how to best match a person with aphasia with the form of language therapy that would be most beneficial. “The choice of language therapy remains trial and error,” Wilmskoetter explained.
Bonilha’s team is working to provide clarity. He’s currently principal investigator on two aphasia studies funded by the National Institute on Deafness and Other Communication Disorders (NIDCD). The first study uses brain scans to understand the structural brain features common in patients who show improvement and how their brains change as a result of therapy, with the eventual goal of developing guideposts to match the right type of therapy to the right patient.
The second study is testing the results of a little-used type of language therapy called speech entrainment. It’s a therapy that Bonilha, along with collaborators at the University of South Carolina, has studied for several years. Bonilha and his team are expanding their understanding of how well this technique works with a five-year, multi-site study dubbed SpARc, or Speech Entrainment for Aphasia Recovery. Stroke survivors with non-fluent aphasia – meaning they can understand language and know what they want to communicate but have trouble getting out more than a few words at a time – who enroll in the study at MUSC, UofSC or the University of Utah will be divided into four groups: a control group that receives no treatment and groups that receive the therapy for three, four-and-a-half or six weeks.
Anna Doyle, manager of aphasia clinical trials in the Bonilha lab, said participants watch a video of a closeup of a person’s mouth speaking, then attempt to speak the words along with the video while wearing headphones to block out the sound of their own voices. Speech entrainment therapy takes advantage of a natural communication pattern in which people’s speech becomes more similar to each other’s over the course of a conversation, but in the therapy, all stimuli are blocked out except for the video and sound of the speaker’s mouth and voice.
Doyle, who worked as a speech language pathologist before turning to research, said she particularly likes this approach. Speaking can be frustrating for people with non-fluent aphasia because they’re aware of their errors yet can’t fix them. In this method, they simply keep going, mimicking the video speaker as best as they can without focusing on errors.
“The goal is for them to get out as many correct words as they can,” she said.
Participants will be assessed three months after treatment on the number of verbs per minute they can speak while engaging in both procedural and narrative storytelling. In other words, they’ll be asked to explain an everyday task, like how to make scrambled eggs, and to retell a common fairy tale, like the story of Little Red Riding Hood.
Verbs per minute was chosen as a measurement because verbs tend to be harder to use, Doyle said. It’s easier to point out an object and give it a name than to say what it does, especially once verb conjugation enters the picture. Verbs add significant meaning to a sentence and are part of what makes speech fluent, so it is a good measure to judge improvements in fluent speech for those with non-fluent aphasia.
This five-year study has just gotten underway with its first subject. Doyle said the COVID-19 pandemic somewhat delayed the study’s start and forced the organizers to get creative in delivering the therapy. Originally designed as an in-person therapy, the study will now be conducted virtually.
“I think it’s really great that we’re able to do it online, because our population is more vulnerable,” she said. “They’re really happy to be able to do it in the comfort of their own homes.”
While the SpARc study gets started, Wilmskoetter is using structural MRI scans to analyze the results of two aphasia studies led by C-STAR with the goal of understanding who is likely to respond to treatment and, ultimately, how to promote recovery in more patients.
One study, now completed, used transcranial direct current stimulation (tDCS), or electric stimulation of the brain, during language therapy to see whether it improved results. The second ongoing study, called Prediction of Outcome of Language Rehabilitation, or POLAR, compares semantic treatment to phonological treatment. In semantic treatment, patients learn to analyze the meaning of words. In phonological treatment, patients learn to analyze the sounds in the words they want to say.
Wilmskoetter isn’t directly analyzing the outcomes of each study to determine effectiveness of a particular treatment. Instead, she is comparing patients’ MRI scans with their results to determine which features in residual brain tissue can predict which patients are more likely to recover. Residual brain tissue is that which is not directly affected by the stroke.
From there, she’s looking at what happens in the brain when someone gets better. Researchers think that for people with lots of healthy white matter connecting language areas that are not affected by the stroke, their brains can recruit more nearby brain areas to take over additional language functions.
With all this information, the lab then wants to make the leap to figuring out how to elicit these positive brain structural changes after stroke to improve recovery.
Overall, the idea behind all of the lab’s work is to find how to match the best treatment to the right patient, she said, so that clinicians can look at a patient and determine that with this type of stroke and this type of brain health, one treatment or the other would be best.
“The idea is to find the best solution early on,” Wilmskoetter said.
The second line of research in the Bonilha lab is epilepsy. Epilepsy is one of the most common neurological disorders, affecting about 50 million people worldwide, according to the World Health Organization. Epilepsy can be caused by head injury or stroke, but in about half of cases, the cause is unknown, the WHO states. According to the Centers for Disease Control and Prevention, more than 53,000 people in South Carolina live with epilepsy.
Medication is often enough to control epilepsy in two thirds of patients. For the other third, surgery may hold the hope for cure.
The problem, said Ezequiel Gleichgerrcht, M.D., Ph.D., an epilepsy fellow who also conducts research in the Bonilha lab, is that doctors still can’t know whether a particular patient will benefit from surgery. About 30% of patients who receive surgery do not become seizure free.
“We still don’t understand why some people are different regarding their treatment response. And so far, none of the studies that use just the standard of care imaging – looking visually at the MRI or looking at the EEG or predicting the pathology they found when they look under the microscope – none of those variables alone or in combination predict accurately who will be seizure-free after the surgery,” he said.
Thus, the Bonilha lab is leading a five-year National Institutes of Health study taking place across five sites to come up with better predictions of who will benefit from epilepsy surgery.
The study builds on previous research conducted in the Bonilha lab. Past studies have been retrospective – meaning they looked back at previous patients’ records – and they were confined to MUSC patients. A single site study is somewhat limited in its findings, Gleichgerrcht said. More recently, a multi-site study with data from six busy academic epilepsy centers, led by MUSC’s Bonilha lab, demonstrated that the single-site findings could be replicated in independent samples using artificial intelligence methods.
This new study will gather data from Hofstra/Northwell in New York, Emory in Atlanta, the University of Pittsburgh and the University of Pennsylvania, and it will be prospective, meaning it will look at the records of current and future patients, once recruited.
“This is one of many outcomes that can be measured – seizure freedom. It’s a very important outcome because it’s the one that defines a lot of the patient’s quality of life. However, there are other contributors to quality of life.”
Ezequiel Gleichgerrcht, M.D., Ph.D.
The study won’t determine the care the patients receive. Their doctors will continue to make their best assessments as to whether the patients are good candidates for surgery and whether they should undergo laser ablation or resection.
“I think that’s what makes it a very attractive study. You’re still doing standard of care. No one gets more or less than if they were not participating,” Gleichgerrcht said.
Epilepsy patients already get MRI scans. For those who agree to participate in the study, their scans will be fed into a machine learning system. The computer has already developed an algorithm for likely success based on scans during previous studies, but as more scans and surgery results are entered, the computer will continually learn and hopefully find common features among those for whom the surgery worked.
The hope is that one day, an automated algorithm could offer a prediction, on an individual patient basis, about whether surgery would likely be successful, Gleichgerrcht said. There’s a long way to go before that point, he said, but this study is an important step forward.
And although this study doesn’t cover other beneficial outcomes, it’s possible that eventually other benefits could be predicted as well.
“This is one of many outcomes that can be measured – seizure freedom. It’s a very important outcome because it’s the one that defines a lot of the patient’s quality of life. However, there are other contributors to quality of life,” he said, listing among them memory and the ability to hold down a job.
Bonilha said Wilmskoetter, Doyle and Gleichgerrcht are great examples of the next generation of researchers who will become leaders in the field and generate medical discoveries to help people who suffer from these diseases.
“Being a clinician scientist is part of the commitment to medical discovery, which ultimately means improving treatment and improving outcomes.”/Uni Release. The material in this public release comes from the originating organization and may be of a point-in-time nature, edited for clarity, style and length. View in full here.
Posted by Kostas Pantremenos in Artificial intelligence, Gait Rehabilitation - Foot Drop, REHABILITATION on September 15, 2020
September 14, 2020 By Annette Boyle
B-Temia Inc.’s Keeogo mobility device is on the move in the U.S. now that it has received 510(k) clearance from the U.S. FDA. Unlike currently available exoskeletons that move for patients, the Keeogo (keep on going) Dermoskeleton system amplifies signals from patients who can initiate movement but need additional assistance.
“This U.S. market clearance is the biggest milestone of our global regulatory expansion, as the USA is the largest medical device market. It also gives us great confidence for the other regulatory approvals we are currently completing for additional territories,” said B-Temia’s president and CEO Stéphane Bédard.
The U.S. action specifically covers use of the device for stroke patients in rehabilitation settings. “Stroke is just the entry door,” Bédard told BioWorld. “We want to extend U.S. authorization for other indications in the future. We’ve done very well for stroke patients and want to do the same for those with multiple sclerosis, osteoarthritis of the knee, Parkinson’s disease, and partial spinal cord injuries.”
The company also hopes to gain clearance for patients to use the device on a day-to-day basis, not just during rehab sessions. “Keeogo has as its main purpose providing the person the ability to regain their activity on a daily basis walking, shopping, out in the yard. That’s why we invented it,” Bédard added. “We will reach that level in the U.S., but with the FDA, you have to go step-by-step for each indication.”
Keeogo already has much broader authorization in Europe where it received CE mark authorization in December 2019. In the 28 European countries covered by the CE mark, Quebec-based B-Temia can market the system to provide additional strength and stability to users with musculoskeletal weakness or lower limb instability both at home and in clinics. The system has been approved by Health Canada since 2015 for a range of indications as well.
The technology
Keeogo is a lightweight motorized walking assistive device that boosts leg power. Its dermoskeleton technology employs artificial intelligence (AI) to help individuals with impaired mobility walk, run, sit, and climb. Underpinned by a model of human biomechanics and the basics elements of gait, the AI uses additional mathematical equations to intervene properly in the movement.
The AI, housed on a belt worn at the waist, interprets information transmitted by sensors strapped to the leg to understand the user’s intent and then provides the compensation needed so they can achieve their goal. It is unique in that it does not replace an individual’s motion, only augments it. “If you don’t walk, it won’t move,” said Bédard. “It will add its response to your own characteristic speed and cadence and is fully customizable to the specifics of a disease and person. We’re only able to achieve this level of sophistication with AI.”
By augmenting the user’s motions, Keeogo works to help them regain or retain their autonomy and mobility. “When you go in the lab with Keeogo, you extend your range of motion, augment stride length, and increase the biomechanical ability to walk,” explained Bédard. “When you repeat recursive exercises, you build your capacity. You extend what you’ve done in the past– the body has a memory of that – and Keeogo synchronizes the motions, extends the gait, so that day after day you regain capacity.” In Parkinson’s and other degenerative diseases, the system helps patients hold onto their independence and not fall into a pattern of doing less and less as the disease progresses and movement becomes more challenging.
Notably, the system is not tied to an idealized motion. “We’re not trying to perfect the individual’s gait, just to improve it. We want to keep the individual’s natural gait. They will improve themselves as they use the system,” Bédard said.
Aside from its clinical applications, B-Temia also continues to develop its military version of Keeogo, the Onyx exoskeleton, for the U.S. Army. It has worked with Lockheed Martin since 2017 to support soldiers tasked with carrying loads of more than 100 pounds. Under that weight, people naturally change their gait. In addition, the weight puts such pressure on the joints that it often leads to both acute and chronic musculoskeletal injuries.
Future plans
“The approval also confers additional credibility for the corporation that will open a lot of doors in terms of investors, financing, and partnerships,” Bédard said.
He plans to spend the next several weeks determining how to execute properly on commercialization in the U.S. and elsewhere so that the device can be easily acquired by individuals who could benefit. “Our next challenge is to establish a good strategy. There are many options on the table and we want to make sure we choose the right structure, partners and channels.
Posted by Kostas Pantremenos in Epilepsy on September 9, 2020
September 8th, 2020
University spinout company Neuronostics has received funding to develop its BioEP platform, an AI-based system for faster, more accurate diagnosis of epilepsy and to monitor response to treatment with anti-epileptic drugs (AEDs).
BioEP works by creating mathematical models of the brain using short segments of electroencephalogram (EEG) recordings. Computer simulations rapidly reveal the ease with which seizures can emerge and form the basis of the BioEP seizure risk score.
Neuronostics is developing BioEP in partnership with the University of Birmingham, where mathematician Professor John Terry, co-founder of the company, is Director of Centre for Systems Modelling & Quantitative Biomedicine.
Professor Terry’s research aims to improve diagnosis and treatment for people with epilepsy. He explains: “We build personalised models of the brain using EEG that is routinely collected when seeking to diagnose epilepsy. From these models the risk of epilepsy can be quickly determined. In contrast, multiple EEG recordings are often required to reach a clinical diagnosis at present. This is expensive, time-consuming, and exposes people with suspected epilepsy to risk.”
The funding, from the National Institute for Health Research (NIHR), will enable the research partnership to progress a prototype clinical platform that can provide a risk score showing the individual’s susceptibility to seizures. This measurement can be used in diagnosis, and as an objective assessment of response to treatment with AEDs, resulting in faster seizure control for people with epilepsy.
The clinical utility of the BioEP seizure risk score has already been demonstrated in a cohort of people with idiopathic generalized epilepsy.1 Using just 20 seconds of an EEG recording that would be considered inconclusive in the current clinical pathway, BioEP achieved 72% diagnostic accuracy. This matches the accuracy achieved in the current diagnostic pathway, which typically takes a year, and involves multiple follow-ups.2
The company is interested to hear from commercial partners in EEG hardware manufacturing, digital EEG analysis, and companion diagnostics or prognostics, and research and clinical partners with interests in epilepsy, traumatic brain injury and dementia. For collaboration enquiries please email: info@neuronostics.com.
The NIHR funding was delivered through the AI in Health and Care Award, part of the NHS AI Lab, which was launched by the UK Government earlier this year to accelerate the adoption of Artificial Intelligence in health and care.
More information:
References
1. H Schmidt et al. A computational biomarker of idiopathic generalized epilepsy from resting state EEG Epilepsia 57: e200-e204 (2016).
2. S Smith. EEG in the diagnosis, classification, and management of patients with epilepsy Journal of Neurology, Neurosurgery & Psychiatry 76: ii2-ii7 (2005).
For further media information please contact: Ruth Ashton, Reputation & Communications Development Manager, University of Birmingham Enterprise, email: r.c.ashton@bham.ac.uk.
About Neuronostics
Neuronostics was established in 2018 and is focussed on developing clinical decision support tools and at home monitoring devices for people with suspected neurological conditions. Neuronostics is currently Medilink SW Start up of the Year and has been supported by grant funding in excess of £1M. Neuronostics’ first product—BioEP—is a revolutionary, patented, biomarker of the susceptibility to seizures in the human brain, informed by clinical EEG recordings.
About the University of Birmingham
The University of Birmingham is ranked amongst the world’s top 100 institutions. Its work brings people from across the world to Birmingham, including researchers, teachers and more than 6,500 international students from over 150 countries.
About NIHR
The National Institute for Health Research (NIHR) is the nation’s largest funder of health and care research. The NIHR:
● Funds, supports and delivers high quality research that benefits the NHS, public health and social care
● Engages and involves patients, carers and the public in order to improve the reach, quality and impact of research
● Attracts, trains and supports the best researchers to tackle the complex health and care challenges of the future
● Invests in world-class infrastructure and a skilled delivery workforce to translate discoveries into improved treatments and services
● Partners with other public funders, charities and industry to maximise the value of research to patients and the economy
The NIHR was established in 2006 to improve the health and wealth of the nation through research, and is funded by the Department of Health and Social Care. In addition to its national role, the NIHR supports applied health research for the direct and primary benefit of people in low- and middle-income countries, using UK aid from the UK government.
Provided by University of Birmingham
Source: https://sciencex.com/wire-news/361008258/funding-boost-for-ai-based-epilepsy-monitoring.html
Posted by Kostas Pantremenos in REHABILITATION on August 18, 2020
Objective: To understand the relatively complete cerebral stroke rehabilitation systems in some foreign countries and relevant AI-based technical supports, and to find out and improve the defects in the interactive system of cerebral stroke rehabilitation system in China.
Method: Analyze and compare the differences between domestic and overseas cerebral stroke rehabilitation systems, and related AI-based technologies mainly through literature research and desk research method, so as to summarize the interactive modes and development trends of the interactive system of cerebral stroke rehabilitation system.
Result: This paper puts forward the concept of interactive system of cerebral stroke rehabilitation system regarding the “hospital – family – hospital” structure, which complies with the domestic situation, in order to provide reference for the subsequent development, but it still needs further improvement in realizing its intelligence and universality.
Conclusion: With the rapid development of AI and the continuous increase of cerebral stroke patients, the traditional cerebral stroke rehabilitation system can no longer meet the actual situation in China, so it is of great necessity to integrate AI into it to create a more convenient interactive system and rehabilitation training for both patients and doctors.
Source: https://link.springer.com/chapter/10.1007/978-3-030-53980-1_48
Posted by Kostas Pantremenos in Paretic Hand, Tele/Home Rehabilitation on June 6, 2020
Background:
Human activity recognition (HAR) technology has been advanced with the development of wearable devices and the machine learning (ML) algorithm. Although previous researches have shown the feasibility of HAR technology for home rehabilitation, there has not been enough evidence based on clinical trial.
Objective:
We intended to achieve two goals: (1) To develop a home-based rehabilitation (HBR) system, which can figure out the home rehabilitation exercise of patient based on ML algorithm and smartwatch; (2) To evaluate clinical outcomes for patients with chronic stroke using the HBR system.
Methods:
We used off-the-shelf smartwatch and the convolution neural network (CNN) of ML algorithm for developing our HBR system. It was designed to be able to share the time data of home exercise of individual patient with physical therapist. To figure out the most accurate way for detecting exercise of chronic stroke patients, we compared accuracy results with dataset of personal/total data and accelerometer only/gyroscope/accelerometer combined with gyroscope data. Using the system, we conducted a preliminary study with two groups of stroke survivors (22 participants in HBR group and 10 participants in a control group). The exercise compliance was periodically checked by phone calls in both groups. To measure clinical outcomes, we assessed the Wolf motor function test (WMFT), Fugl-meyer assessment of upper extremity (FMA-UE), grip power test, Beck’s depression index and range of motion (ROM) of the shoulder joint at 0 (baseline), 6 (mid-term), 12 weeks (final) and 18 weeks(6 weeks after the final assessment without HBR system).
Results:
The ML model created by personal data(99.9%) showed greater accuracy than total data(95.8%). The movement detection accuracy was the highest in accelerometer combined with gyroscope data (99.9%) compared to gyroscope(96.0%) or accelerometer alone(98.1%). With regards to clinical outcomes, drop-out rates of control and experimental group were 4/10 (40%) and 5/22 (22%) at 12 weeks and 10/10 (100%) and 10/22 (45%) at 18 weeks, respectively. The experimental group (N=17) showed a significant improvement in WMFT score (P=.02) and ROM (P<.01). The control group (N=6) showed a significant change only in shoulder internal rotation (P=.03).
Conclusions:
This research found that the homecare system using the commercial smartwatch and ML model can facilitate the participation of home training and improve the functional score of WMFT and shoulder ROM of flexion and internal rotation for the treatment of patients with chronic stroke. We recommend our HBR system strategy as an innovative and cost-effective homecare treatment modality. Clinical Trial: Preliminary study (Phase I)
Posted by Kostas Pantremenos in Paretic Hand, REHABILITATION, Tele/Home Rehabilitation, Video Games/Exergames, Virtual reality rehabilitation on March 7, 2020
Posted by Kostas Pantremenos in Depression, Pharmacological, REHABILITATION on February 20, 2020
Researchers used electroencephalography and an algorithm to identify a brain-wave signature in individuals with depression who will most likely respond to a medication.
Andrea Danti/Shutterstock.comA new method of interpreting brain activity could potentially be used in clinics to help determine the best treatment options for depression, according to a study led by researchers at the Stanford School of Medicine.
Stanford researchers and their collaborators used electroencephalography, a tool for monitoring electrical activity in the brain, and an algorithm to identify a brain-wave signature in individuals with depression who will most likely respond to sertraline, an antidepressant marketed as Zoloft.
A paper describing the work was published today in Nature Biotechnology.
The study emerged from a decades-long effort funded by the National Institute of Mental Health to create biologically based approaches, such as blood tests and brain imaging, to help personalize the treatment of depression and other mental disorders. Currently, there are no such tests to objectively diagnose depression or guide its treatment.
“This study takes previous research showing that we can predict who benefits from an antidepressant and actually brings it to the point of practical utility,” said Amit Etkin, MD, PhD, professor of psychiatry and behavioral sciences at Stanford. “I will be surprised if this isn’t used by clinicians within the next five years.”
Instead of functional magnetic resonance imaging, an expensive technology often used in studies to image brain activity, the scientists turned to electroencephalography, or EEG, a much less costly technology.
Etkin shares senior authorship of the paper with Madhukar Trivedi, MD, professor of psychiatry at the University of Texas-Southwestern. Wei Wu, PhD, an instructor of psychiatry at Stanford, is the lead author.
The paper is one of several based on data from a federally funded depression study launched in 2011 — the largest randomized, placebo-controlled clinical trial on antidepressants ever conducted with brain imaging — which tested the use of sertraline in 309 medication-free patients. The multicenter trial was called Establishing Moderators and Biosignatures of Antidepressant Response for Clinical Care, or EMBARC. Led by Trivedi, it was designed to advance the goal of improving the trial-and-error method of treating depression that is still in use today.
“It often takes many steps for a patient with depression to get better,” Trivedi said. “We went into this thinking, ‘Wouldn’t it be better to identify at the beginning of treatment which treatments would be best for which patients?’”
Major depression is the most common mental disorder in the United States, affecting about 7% of adults in 2017, according to the National Institute of Mental Health. Among those, about half never get diagnosed. For those who do, finding the right treatment can take years, Trivedi said. He pointed to one of his past studies that showed only about 30% of depressed patients saw any remission of symptoms after their first treatment with an antidepressant.
Amit Etkin
Current methods for diagnosing depression are simply too subjective and imprecise to guide clinicians in quickly identifying the right treatment, Etkin said. In addition to a variety of antidepressants, there are several other types of treatments for depression, including psychotherapy and brain stimulation, but figuring out which treatment will work for which patients is based on educated guessing.
To diagnose depression, clinicians rely on a patient reporting at least 5 of 9 common symptoms of the disease. The list includes symptoms such as feelings of sadness or hopelessness, self-doubt, sleep disturbances — ranging from insomnia to sleeping too much — low energy, unexplained body aches, fatigue, and changes in appetite, ranging from overeating to undereating. Patients often vary in both the severity and types of symptoms they experience, Etkin said.
“As a psychiatrist, I know these patients differ a lot,” Etkin said. “But we put them all under the same umbrella, and we treat them all the same way.” Treating people with depression often begins with prescribing them an antidepressant. If one doesn’t work, a second antidepressant is prescribed. Each of these “trials” often takes at least eight weeks to assess whether the drug worked and symptoms are alleviated. If an antidepressant doesn’t work, other treatments, such as psychotherapy or occasionally transcranial magnetic stimulation, may also be tried. Often, multiple treatments are combined, Etkin said, but figuring out which combination works can take a while.
“People often feel a lot of dejection each time a treatment doesn’t work, creating more self-doubt for those whose primary symptom is most often self-doubt,” Trivedi said.
The EMBARC trial enrolled 309 people with depression who were randomized to receive either sertraline or a placebo.
For their study, Etkin and his colleagues set out to find a brain-wave pattern to help predict which depressed participants would respond to sertraline. First, the researchers collected EEG data on the participants before they received any drug treatment. The goal was to obtain a baseline measure of brain-wave patterns.
Next, using insights from neuroscience and bioengineering, the investigators analyzed the EEG using a novel artificial intelligence technique they developed and identified signatures in the data that predicted which participants would respond to treatment based on their individual EEG scans. The researchers found that this technique reliably predicted which of the patients did, in fact, respond to sertraline and which responded to placebo. The results were replicated at four different clinical sites.
Further research suggested that participants who were predicted to show little improvement with sertraline were more likely to respond to treatment involving transcranial magnetic stimulation, or TMS, in combination with psychotherapy.
“Using this method, we can characterize something about an individual person’s brain,” Etkin said. “It’s a method that can work across different types of EEG equipment, and thus more apt to reach the clinic.”
Etkin is on leave from Stanford, working as the founder and CEO of the startup Alto Neuroscience, a company based in Los Altos, California, that aims to build on these findings and develop a new generation of biologically based diagnostic tests to personalize mental health treatments with a high degree of clinical utility. “Part of getting these study results used in clinical care is, I think, that society has to demand it,” Trivedi said. “That is the way things get put into practice. I don’t see a downside to putting this into clinical use soon.”
When EMBARC was launched, it was part of a broader effort by the NIMH to push for improvements in mental health care by using advances in fields such as genetics, neuroscience and biotechnology, said Thomas Insel, MD, who served as director of that institute from 2002 to 2015.
“We went into EMBARC saying anything is possible,” Insel said. “Let’s see if we can come up with clinically actionable techniques.” He didn’t think it would take this long, but he remains optimistic.
“I think this study is a particularly interesting application of EMBARC,” he said. “It leverages the power of modern data science to predict at the individual level who is likely to respond to an antidepressant.”
In addition to improving care, the researchers said they see a possible side benefit to the use of biologically based approaches: It could reduce the stigma associated with depression and other mental health disorders that prevents many people from seeking appropriate medical care.
“I’d love to think scientific evidence will help to counteract this stigma, but it hasn’t so far,” said Insel. “It’s been over 160 years since Abraham Lincoln said that melancholy ‘is a misfortune, not a fault.’ We still have a long way to go before most people will understand that depression is not someone’s fault.” (President Lincoln suffered bouts of depression.)
Other Stanford co-authors of the paper are postdoctoral scholars Yu Zhang, PhD, and Jing Jiang, PhD; former postdoctoral scholar Gregory Fonzo, PhD; neuroscience graduate students Molly Lucas and Camarin Rolle; research assistants Carena Cornelssen and Kamron Sarhadi; clinical research coordinator Trevor Caudle; former clinical research coordinators Rachael Wright, Karen Monuszko and Hersh Trivedi; and former neuroscience graduate student Russell Toll. All Stanford authors, including Etkin, are affiliated with Veterans Affairs Palo Alto Healthcare System and the Sierra Pacific Mental Illness, Research, Education and Clinical Center in Palo Alto.
Etkin is a member of the Wu Tsai Neurosciences Institute at Stanford.
Researchers at South China University of Technology, the Netherlands Research Institute, Harvard Medical School, the New York State Psychiatric Institute, Columbia University and the Netherlands neuroCare Group also contributed to the work.
Insel is an investor in Alto Neuroscience.
The EMBARC study data are publicly available through the NIMH Data Archive.
The study was funded by the National Institutes of Health (U01MH092221, U01MH092250, R01MH103324, DP1 MH116506), the Stanford Neurosciences Institute, the Hersh Foundation, the National Key Research and Development Plan of China, and the National Natural Science Foundation of China.
Stanford Medicine integrates research, medical education and health care at its three institutions – Stanford University School of Medicine, Stanford Health Care (formerly Stanford Hospital & Clinics), and Lucile Packard Children’s Hospital Stanford. For more information, please visit the Office of Communication & Public Affairs site at http://mednews.stanford.edu.
Posted by Kostas Pantremenos in Depression on February 17, 2020
The UT Southwestern researchers hope that this tool could eventually play a critical role in deciding which course of treatment would be best for patients with depression, as well as being part of a new generation of “biology-based, objective strategies” which make use of technologies such as AI to treat psychiatric disorders.
The US-wide trial was initiated in 2011 with the intention of better understanding mood disorders such as major depression and seasonal affective disorder (Sad). The trial has reaped many studies, the latest of which demonstrates that doctors could use computational tools to guide treatment choices for depression. The study was published in Nature Biotechnology.
“These studies have been a bigger success than anyone on our team could have imagined,” said Dr. Madhukar Trivedi, the UT Southwestern psychiatrist who oversaw the trial. “We provided abundant data to show we can move past the guessing game of choosing depression treatments and alter the mindset of how the disease should be diagnosed and treated.”
This 16-week trial involved more than 300 participants with depression, who either received a placebo or SSRI (selective serotonin reuptake inhibitor), the most common type of antidepressant. Despite the widespread prescription of SSRIs, they have been criticised for their side effects and for inefficacy in many patients.
Trivedi had previously established in another study that up to two-thirds of patients do not adequately respond to their first antidepressant, motivating him to find a way of identifying much earlier which treatment path is most likely to help the patient before they begin and potentially suffer further through ineffectual treatment.
Trivedi and his collaborators used an electroencephalogram (EEG) to measure electrical activity in the participants’ cortex before they began the treatment. This data was used to develop a machine learning algorithm to predict which patients would benefit from the medication within two months.
The researchers found that the AI accurately predicted outcomes, with patients less certain to respond to an antidepressant more likely to improve with other interventions, such as brain stimulation or therapeutic approaches. Their findings were replicated across three additional patient groups.
“It can be devastating for a patient when an antidepressant doesn’t work,” Trivedi said. “Our research is showing that they no longer have to endure the painful process of trial and error.”
Dr Amit Etkin, a Stanford University professor of psychiatry who also worked on the algorithm, added: “This study takes previous research, showing that we can predict who benefits from an antidepressant, and actually brings it to the point of practical utility.”
Next, they hope to develop an interface for the algorithm to be used alongside EEGs – and perhaps also with other means of measuring brain activity like functional magnetic resonance imaging (functional MRI, aka fMRI) or MEG – and have the system approved by the US Food and Drug Administration.
via AI could play ‘critical’ role in identifying appropriate treatment for depression | E&T Magazine
Posted by Kostas Pantremenos in Educational, TBI on January 21, 2020
A brain tumor is a mass of abnormal cells that grow in the brain. In 2016 alone, there were 330,000 incident cases of brain cancer and 227,000 related-deaths worldwide. Early detection is crucial to improve patient prognosis, and thanks to a team of researchers, they developed a new imaging technique and artificial intelligence algorithm that can help doctors accurately identify brain tumors.
Image Credit: create jobs 51 / Shutterstock.com
Published in the journal Nature Medicine, the study reveals a new method that combines modern optical imaging and an artificial intelligence algorithm. The researchers at New York University studied the accuracy of machine learning in producing precise and real-time intraoperative diagnosis of brain tumors.
In the past, the only way to diagnose brain tumors is through hematoxylin and eosin staining of processed tissue in time. Plus, interpretation of the findings relies on pathologists who examine the specimen. The researchers hope the new method will provide a better and more accurate diagnosis, which can help initiate effective treatments right away.
In cancer treatment, the earlier cancer has been diagnosed, the earlier the oncologists can start the treatment. In most cases, early detection improves health outcomes. The researchers have found that their novel method of detection yielded a 94.6 percent accuracy, compared to 93.9 percent for pathology-based interpretation.
The researchers used a new imaging technique called stimulated Raman histology (SRH), which can reveal tumor infiltration in human tissue. The technique collects scattered laser light and emphasizes features that are not usually seen in many body tissue images.
With the new images, the scientists processed and studied using an artificial intelligence algorithm. Within just two minutes and thirty seconds, the researchers came up with a brain tumor diagnosis. The fast detection of brain cancer can help not only in diagnosing the disease early but also in implementing a fast and effective treatment plan. With cancer caught early, treatments may be more effective in killing cancer cells.
The team also utilized the same technology to accurately identify and remove undetectable tumors that cannot be detected by conventional methods.
“As surgeons, we’re limited to acting on what we can see; this technology allows us to see what would otherwise be invisible, to improve speed and accuracy in the OR, and reduce the risk of misdiagnosis. With this imaging technology, cancer operations are safer and more effective than ever before,” Dr. Daniel A. Orringer, associate professor of Neurosurgery at NYU Grossman School of Medicine, said.
The study is a walkthrough of various ideas and efforts by the research team. First off, they built the artificial intelligence algorithm by training a deep convolutional neural network (CNN), containing more than 2.5 million samples from 415 patients. The method helped them group and classify tissue samples into 13 categories, representing the most common types of brain tumors, such as meningioma, metastatic tumors, malignant glioma, and lymphoma.
For validation, the researchers recruited 278 patients who are having brain tumor resection or epilepsy surgery at three university medical centers. The tumor samples from the brain were examined and biopsied. The researchers grouped the samples into two groups – control and experimental.
The team assigned the control group to be processed traditionally in a pathology laboratory. The process spans 20 to 30 minutes. On the other hand, the experimental group had been tested and studied intraoperatively, from getting images and processing the examination through CNN.
There were noted errors in both the experimental and control groups but were unique from each other. The new tool can help centers detect and diagnose brain tumors, particularly those without expert neuropathologists.
“SRH will revolutionize the field of neuropathology by improving decision-making during surgery and providing expert-level assessment in the hospitals where trained neuropathologists are not available,” Dr. Matija Snuderl, associate professor in the Department of Pathology at NYU Grossman School of Medicine, explained.
Patel, A., Fisher, J, Nichols, E., et al. (2019). Global, regional, and national burden of brain and other CNS cancer, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016. The Lancet Neurology. https://www.thelancet.com/journals/laneur/article/PIIS1474-4422(18)30468-X/fulltext#%20
Hollon, T., Pandian, B, Orringer, D. (2019). Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks. Nature Medicine. https://www.nature.com/articles/s41591-019-0715-9
via Novel artificial intelligence algorithm helps detect brain tumor
Posted by Kostas Pantremenos in REHABILITATION, Rehabilitation robotics, Virtual reality rehabilitation on October 17, 2019
An engineering researcher from New Zealand’s University of Auckland has been awarded a Rutherford Discovery Fellowship.
The Associate Professor, who is developing a virtual therapy technology for personal rehabilitation, is one of eleven Fellows for 2019. The Fellowship provides NZ$ 800,000 in funding over five years.
According to a recent press release, his research combines leading-edge data techniques with wearable robotics, artificial intelligence (AI) and machine learning.
The aim is to create devices that are capable of personalising rehabilitation and recovery plans, which are cheaper and more efficient than humans.
In other news, the University was the site of a unique digital treasure hunt recently to mark Stress Less Week.
Stress Less week was held 7 to 11 October as thousands of students prepare to head into study break and exam period.
A student start-up developed the technology used in the app-based game, which challenged the students to unlock and solve riddles on the City Campus to find secret locations and discover rewards.
The start-up’s Founder explained that fun is the ultimate antidote to stress.
They provided an experience that facilitated getting out and connecting with peers, before it gets too close to exams and after the mid-semester wave of assignments.
They are passionate about using new technologies to turn cities into playgrounds, developing a portfolio of technologies in the process.
These technologies include holograms, face-recognition software and transparent glass screens, which they draw on to design interactive games.
Using the campus for a big treasure hunt is a great way to test the waters before thousands of dollars are put into more commercial ventures, and scale-up the app to use in different situations.
via Personal Rehab and Recovery Through Virtual Therapy
TBI Rehabilitation 