Robot allows 'remote presence' in programming brain and spine stimulators

Jan. 16, 2013 — With the rapidly expanding use of brain and spinal cord stimulation therapy (neuromodulation), new "remote presence" technologies may help to meet the demand for experts to perform stimulator programming, reports a study in the January issue of Neurosurgery.

The preliminary study by Dr. Ivar Mendez of Queen Elizabeth II Health Sciences Centre in Halifax, Nova Scotia, Canada, supports the feasibility and safety of using a remote presence robot -- called the "RP-7" -- to increase access to specialists qualified to program the brain and spine stimulators used in neuromodulation.

Robot Lets Experts Guide Nurses in Programming Stimulators Dr. Mendez and his group developed the RP-7 as a way of allowing experts to "telementor" nonexpert nurses in programming stimulator devices. Already widely used for Parkinson's disease and severe chronic pain, neuromodulation is being explored for use in other conditions, such as epilepsy, severe depression, and obsessive-compulsive disorder.

In this form of therapy, a small electrode is surgically placed in a precise location in the brain or spine. A mild electrical current is delivered to stimulate that area, with the goal of interrupting abnormal activity. As more patients undergo brain and spine stimulation therapy, there's a growing demand for experts to program the stimulators that generate the electrical current.

The RP-7 is a mobile, battery-powered robot that can be controlled using a laptop computer. It is equipped with digital cameras and microphones, allowing the expert, nurse, and patient to communicate. The robot's "head" consists of a flat-screen monitor that displays the face of the expert operator.

The RP-7 also has an "arm" equipped with a touch-screen programmer, which the nurse can use to program the stimulator. The expert can "telestrate" to indicate to the nurse the correct buttons to push on the programming device.

Access to Specialists in the Next Room -- or Miles Away In the preliminary study, patients with neuromodulation devices were randomly assigned to conventional programming, with the expert in the room; or remote programming, with the expert using the RP-7 to guide a nurse in programming the stimulator. For the study, the expert operators were simply in another room of the same building. However, since the RP-7 operates over a conventional wireless connection, the expert can be anyplace that has Internet access.

On analysis of 20 patients (10 in each group), there was no significant difference in the accuracy or clinical outcomes of remote-presence versus conventional programming. No adverse events occurred with either type of session.

The remote-presence sessions took a little more time: 33 versus 26 minutes, on average. Patients, experts, and nonexpert nurses all gave high satisfaction scores for the programming experience.

"This study demonstrated that remote presence can be used for point-of-care programming of neuromodulation devices," Dr. Mendez and coauthors write. The study provides "proof of principle" that the RP-7 or similar devices can help to meet the need for experts needed to serve the rapidly expanding number of patients with neuromodulation therapies.

The researchers have also started a pilot study using a new mobile device, called the RP-Xpress. About the size of a small suitcase, the RP-Xpress is being used to perform long-distance home visits for patients living hundreds of miles away, using existing local cell phone networks. Dr. Mendez and colleagues conclude, "We envision a time, in the near future, when patients with implanted neuromodulation devices will have real-time access to an expert clinician from the comfort of their own home."

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by Wolters Kluwer Health: Lippincott Williams & Wilkins, via Newswise.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Journal Reference:

Ivar Mendez, Michael Song, Paula Chiasson, Luis Bustamante. Point-of-Care Programming for Neuromodulation. Neurosurgery, 2013; 72 (1): 99 DOI: 10.1227/NEU.0b013e318276b5b2

Note: If no author is given, the source is cited instead.

Disclaimer: This article is not intended to provide medical advice, diagnosis or treatment. Views expressed here do not necessarily reflect those of ScienceDaily or its staff.

View the original article here

Training computers to understand the human brain

ScienceDaily (Oct. 5, 2012) — Tokyo Institute of Technology researchers use fMRI datasets to train a computer to predict the semantic category of an image originally viewed by five different people.

Understanding how the human brain categorizes information through signs and language is a key part of developing computers that can 'think' and 'see' in the same way as humans. Hiroyuki Akama at the Graduate School of Decision Science and Technology, Tokyo Institute of Technology, together with co-workers in Yokohama, the USA, Italy and the UK, have completed a study using fMRI datasets to train a computer to predict the semantic category of an image originally viewed by five different people.

The participants were asked to look at pictures of animals and hand tools together with an auditory or written (orthographic) description. They were asked to silently 'label' each pictured object with certain properties, whilst undergoing an fMRI brain scan. The resulting scans were analysed using algorithms that identified patterns relating to the two separate semantic groups (animal or tool).

After 'training' the algorithms in this way using some of the auditory session data, the computer correctly identified the remaining scans 80-90% of the time. Similar results were obtained with the orthographic session data. A cross-modal approach, namely training the computer using auditory data but testing it using orthographic, reduced performance to 65-75%. Continued research in this area could lead to systems that allow people to speak through a computer simply by thinking about what they want to say.

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by Tokyo Institute of Technology, via ResearchSEA.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Journal Reference:

Hiroyuki Akama, Brian Murphy, Li Na, Yumiko Shimizu, Massimo Poesio. Decoding semantics across fMRI sessions with different stimulus modalities: a practical MVPA study. Frontiers in Neuroinformatics, 2012; 6 DOI: 10.3389/fninf.2012.00024

Note: If no author is given, the source is cited instead.

Disclaimer: This article is not intended to provide medical advice, diagnosis or treatment. Views expressed here do not necessarily reflect those of ScienceDaily or its staff.

View the original article here

Scientists create chemical 'brain': Giant network links all known compounds and reactions

ScienceDaily (Aug. 22, 2012) — Northwestern University scientists have connected 250 years of organic chemical knowledge into one giant computer network -- a chemical Google on steroids. This "immortal chemist" will never retire and take away its knowledge but instead will continue to learn, grow and share.

A decade in the making, the software optimizes syntheses of drug molecules and other important compounds, combines long (and expensive) syntheses of compounds into shorter and more economical routes and identifies suspicious chemical recipes that could lead to chemical weapons.

"I realized that if we could link all the known chemical compounds and reactions between them into one giant network, we could create not only a new repository of chemical methods but an entirely new knowledge platform where each chemical reaction ever performed and each compound ever made would give rise to a collective 'chemical brain,'" said Bartosz A. Grzybowski, who led the work. "The brain then could be searched and analyzed with algorithms akin to those used in Google or telecom networks."

Called Chematica, the network comprises some seven million chemicals connected by a similar number of reactions. A family of algorithms that searches and analyzes the network allows the chemist at his or her computer to easily tap into this vast compendium of chemical knowledge. And the system learns from experience, as more data and algorithms are added to its knowledge base.

Details and demonstrations of the system are published in three back-to-back papers in the Aug. 6 issue of the journal Angewandte Chemie.

Grzybowski is the senior author of all three papers. He is the Kenneth Burgess Professor of Physical Chemistry and Chemical Systems Engineering in the Weinberg College of Arts and Sciences and the McCormick School of Engineering and Applied Science.

In the Angewandte paper titled "Parallel Optimization of Synthetic Pathways Within the Network of Organic Chemistry," the researchers have demonstrated algorithms that find optimal syntheses leading to drug molecules and other industrially important chemicals.

"The way we coded our algorithms allows us to search within a fraction of a second billions of chemical syntheses leading to a desired molecule," Grzybowski said. "This is very important since within even a few synthetic steps from a desired target the number of possible syntheses is astronomical and clearly beyond the search capabilities of any human chemist."

Chematica can test and evaluate every possible synthesis that exists, not only the few a particular chemist might have an interest in. In this way, the algorithms find truly optimal ways of making desired chemicals.

The software already has been used in industrial settings, Grzybowski said, to design more economical syntheses of companies' products. Synthesis can be optimized with various constraints, such as avoiding reactions involving environmentally dangerous compounds. Using the Chematica software, such green chemistry optimizations are just one click away.

Another important area of application is the shortening of synthetic pathways into the so-called "one-pot" reactions. One of the holy grails of organic chemistry has been to design methods in which all the starting materials could be combined at the very beginning and then the process would proceed in one pot -- much like cooking a stew -- all the way to the final product.

The Northwestern researchers detail how this can be done in the Angewandte paper titled "Rewiring Chemistry: Algorithmic Discovery and Experimental Validation of One-Pot Reactions in the Network of Organic Chemistry."

The chemists have taught their network some 86,000 chemical rules that check -- again, in a fraction of a second -- whether a sequence of individual reactions can be combined into a one-pot procedure. Thirty predictions of one-pot syntheses were tested and fully validated. Each synthesis proceeded as predicted and had excellent yields.

In one striking example, Grzybowski and his team synthesized an anti-asthma drug using the one-pot method. The drug typically would take four consecutive synthesis and purification steps.

"Our algorithms told us this sequence could be combined into just one step, and we were naturally curious to check it out in a flask," Grzybowski said. "We performed the one-pot reaction and obtained the drug in excellent yield and at a fraction of the cost the individual steps otherwise would have accrued."

The third area of application is the use of the Chematica network approach for predicting and monitoring syntheses leading to chemical weapons. This is reported in the Angewandte paper titled "Chemical Network Algorithms for the Risk Assessment and Management of Chemical Threats."

"Since we now have this unique ability to scrutinize all possible synthetic strategies, we also can identify the ones that a potential terrorist might use to make a nerve gas, an explosive or another toxic agent," Grzybowski said.

Algorithms known from game theory first are applied to identify the strategies that are hardest to detect by the federal government -- the use of substances, for example, such as kitchen salt, clarifiers, grain alcohol and a fertilizer, all freely available from a local convenience store. Characteristic combinations of seemingly innocuous chemicals, such as this example, are red flags.

This strategy is very different from the government's current approach of monitoring and regulating individual substances, Grzybowski said. Chematica can be used to monitor patterns of chemicals that together become suspicious, instead of monitoring individual compounds. Grzybowski is working with the federal government to implement the software.

Chematica now is being commercialized. "We chose this name," Grzybowski said, "because networks will do to chemistry what Mathematica did to scientific computing. Our approach will accelerate synthetic design and discovery and will optimize synthetic practice at large."

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by Northwestern University. The original article was written by Megan Fellman.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Journal References:

Mikolaj Kowalik, Chris M. Gothard, Aaron M. Drews, Nosheen A. Gothard, Alex Weckiewicz, Patrick E. Fuller, Bartosz A. Grzybowski, Kyle J. M. Bishop. Parallel Optimization of Synthetic Pathways within the Network of Organic Chemistry. Angewandte Chemie International Edition, 2012; 51 (32): 7928 DOI: 10.1002/anie.201202209Chris M. Gothard, Siowling Soh, Nosheen A. Gothard, Bartlomiej Kowalczyk, Yanhu Wei, Bilge Baytekin, Bartosz A. Grzybowski. Rewiring Chemistry: Algorithmic Discovery and Experimental Validation of One-Pot Reactions in the Network of Organic Chemistry. Angewandte Chemie International Edition, 2012; 51 (32): 7922 DOI: 10.1002/anie.201202155Patrick E. Fuller, Chris M. Gothard, Nosheen A. Gothard, Alex Weckiewicz, Bartosz A. Grzybowski. Chemical Network Algorithms for the Risk Assessment and Management of Chemical Threats. Angewandte Chemie International Edition, 2012; 51 (32): 7933 DOI: 10.1002/anie.201202210

Note: If no author is given, the source is cited instead.

Disclaimer: Views expressed in this article do not necessarily reflect those of ScienceDaily or its staff.

View the original article here

Crucial advances in 'brain reading' demonstrated

ScienceDaily (Dec. 21, 2011) — At UCLA's Laboratory of Integrative Neuroimaging Technology, researchers use functional MRI brain scans to observe brain signal changes that take place during mental activity. They then employ computerized machine learning (ML) methods to study these patterns and identify the cognitive state -- or sometimes the thought process -- of human subjects. The technique is called "brain reading" or "brain decoding."

In a new study, the UCLA research team describes several crucial advances in this field, using fMRI and machine learning methods to perform "brain reading" on smokers experiencing nicotine cravings.

The research, presented last week at the Neural Information Processing Systems' Machine Learning and Interpretation in Neuroimaging workshop in Spain, was funded by the National Institute on Drug Abuse, which is interested in using these method to help people control drug cravings.

In this study on addiction and cravings, the team classified data taken from cigarette smokers who were scanned while watching videos meant to induce nicotine cravings. The aim was to understand in detail which regions of the brain and which neural networks are responsible for resisting nicotine addiction specifically, and cravings in general, said Dr. Ariana Anderson, a postdoctoral fellow in the Integrative Neuroimaging Technology lab and the study's lead author.

"We are interested in exploring the relationships between structure and function in the human brain, particularly as related to higher-level cognition, such as mental imagery," Anderson said. "The lab is engaged in the active exploration of modern data-analysis approaches, such as machine learning, with special attention to methods that reveal systems-level neural organization."

For the study, smokers sometimes watched videos meant to induce cravings, sometimes watched "neutral" videos and at sometimes watched no video at all. They were instructed to attempt to fight nicotine cravings when they arose.

The data from fMRI scans taken of the study participants was then analyzed. Traditional machine learning methods were augmented by Markov processes, which use past history to predict future states. By measuring the brain networks active over time during the scans, the resulting machine learning algorithms were able to anticipate changes in subjects' underlying neurocognitive structure, predicting with a high degree of accuracy (90 percent for some of the models tested) what they were watching and, as far as cravings were concerned, how they were reacting to what they viewed.

"We detected whether people were watching and resisting cravings, indulging in them, or watching videos that were unrelated to smoking or cravings," said Anderson, who completed her Ph.D. in statistics at UCLA. "Essentially, we were predicting and detecting what kind of videos people were watching and whether they were resisting their cravings."

In essence, the algorithm was able to complete or "predict" the subjects' mental states and thought processes in much the same way that Internet search engines or texting programs on cell phones anticipate and complete a sentence or request before the user is finished typing. And this machine learning method based on Markov processes demonstrated a large improvement in accuracy over traditional approaches, the researchers said.

Machine learning methods, in general, create a "decision layer" -- essentially a boundary separating the different classes one needs to distinguish. For example, values on one side of the boundary might indicate that a subject believes various test statements and, on the other, that a subject disbelieves these statements. Researchers have found they can detect these believe-disbelieve differences with high accuracy, in effect creating a lie detector. An innovation described in the new study is a means of making these boundaries interpretable by neuroscientists, rather than an often obscure boundary created by more traditional methods, like support vector machine learning.

"In our study, these boundaries are designed to reflect the contributed activity of a variety of brain sub-systems or networks whose functions are identifiable -- for example, a visual network, an emotional-regulation network or a conflict-monitoring network," said study co-author Mark S. Cohen, a professor of neurology, psychiatry and biobehavioral sciences at UCLA's Staglin Center for Cognitive Neuroscience and a researcher at the California NanoSystems Institute at UCLA.

"By projecting our problem of isolating specific networks associated with cravings into the domain of neurology, the technique does more than classify brain states -- it actually helps us to better understand the way the brain resists cravings," added Cohen, who also directs UCLA's Neuroengineering Training Program.

Remarkably, by placing this problem into neurological terms, the decoding process becomes significantly more reliable and accurate, the researchers said. This is especially significant, they said, because it is unusual to use prior outcomes and states in order to inform the machine learning algorithms, and it is particularly challenging in the brain because so much is unknown about how the brain works.

Machine learning typically involves two steps: a "training phase" in which the computer evaluates a set of known outcomes -- say, a bunch of trials in which a subject indicated belief or disbelief -- and a second, "prediction" phase in which the computer builds a boundary based on that knowledge.

In future research, the neuroscientists said, they will be using these machine learning methods in a biofeedback context, showing subjects real-time brain readouts to let them know when they are experiencing cravings and how intense those cravings are, in the hopes of training them to control and suppress those cravings.

But since this clearly changes the process and cognitive state for the subject, the researchers said, they may face special challenges in trying to decode a "moving target" and in separating the "training" phase from the "prediction" phase.

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by University of California - Los Angeles. The original article was written by Jennifer Marcus.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Note: If no author is given, the source is cited instead.

Disclaimer: This article is not intended to provide medical advice, diagnosis or treatment. Views expressed here do not necessarily reflect those of ScienceDaily or its staff.

View the original article here