This sponsored article is delivered to you by NYU Tandon School of Engineering.
To deal with at this time’s well being challenges, particularly in our growing old society, we should turn into extra clever in our approaches. Clinicians now have entry to a variety of superior applied sciences designed to help early analysis, consider prognosis, and improve affected person well being outcomes, together with telemedicine, medical robots, powered prosthetics, exoskeletons, and AI-powered good wearables. Nevertheless, many of those applied sciences are nonetheless of their infancy.
The assumption that advancing know-how can enhance human well being is central to analysis associated to medical system applied sciences. This types the center of analysis for Prof. S. Farokh Atashzar who directs the Medical Robotics and Interactive Intelligent Technologies (MERIIT) Lab on the NYU Tandon School of Engineering.
Atashzar is an Assistant Professor of Electrical and Pc Engineering and Mechanical and Aerospace Engineering at NYU Tandon. He’s additionally a member of NYU WIRELESS, a consortium of researchers devoted to the following era of wi-fi know-how, in addition to the Middle for City Science and Progress (CUSP), a middle of researchers devoted to all issues associated to the way forward for fashionable city life.
Atashzar’s work is devoted to creating clever, interactive robotic, and AI-driven assistive machines that may increase human sensorimotor capabilities and permit our healthcare system to transcend pure competences and overcome physiological and pathological limitations.
Stroke detection and rehabilitation
Stroke is the main reason for age-related motor disabilities and is changing into more prevalent in youthful populations as effectively. However whereas there’s a burgeoning marketplace for rehabilitation units that declare to speed up restoration, together with robotic rehabilitation programs, suggestions for a way and when to make use of them are based mostly totally on subjective analysis of the sensorimotor capacities of sufferers in want.
Atashzar is working in collaboration withJohn-Ross Rizzo, affiliate professor of Biomedical Engineering at NYU Tandon and Ilse Melamid Affiliate Professor of rehabilitation drugs on the NYU College of Medication and Dr. Ramin Bighamian from the U.S. Meals and Drug Administration to design a regulatory science instrument (RST) based mostly on knowledge from biomarkers with the intention to enhance the assessment processes for such units and the way greatest to make use of them. The staff is designing and validating a sturdy restoration biomarker enabling a first-ever stroke rehabilitation RST based mostly on exchanges between areas of the central and peripheral nervous programs.
S. Farokh Atashzar is an Assistant Professor of Electrical and Pc Engineering and Mechanical and Aerospace Engineering at New York College Tandon College of Engineering. He’s additionally a member of NYU WIRELESS, a consortium of researchers devoted to the following era of wi-fi know-how, in addition to the Middle for City Science and Progress (CUSP), a middle of researchers devoted to all issues associated to the way forward for fashionable city life, and directs the MERIIT Lab at NYU Tandon.NYU Tandon
As well as, Atashzar is collaborating with Smita Rao, PT, the inaugural Robert S. Salant Endowed Affiliate Professor of Bodily Remedy. Collectively, they intention to establish AI-driven computational biomarkers for motor management and musculoskeletal harm and to decode the hidden advanced synergistic patterns of degraded muscle activation utilizing knowledge collected from floor electromyography (sEMG) and high-density sEMG. Prior to now few years, this collaborative effort has been exploring the fascinating world of “Nonlinear Practical Muscle Networks” — a brand new computational window (rooted in Shannon’s data concept) into human motor management and mobility. This synergistic community orchestrates the “music of mobility,” harmonizing the synchrony between muscle tissues to facilitate fluid motion.
However rehabilitation is barely one of many analysis thrusts at MERIIT lab. When you can forestall strokes from taking place or reoccurring, you may head off the issue earlier than it occurs. For Atashzar, a giant clue might be the place you least anticipate it: in your retina.
Atashzar together with NYU Abu Dhabi Assistant Professor Farah Shamout, are engaged on a undertaking they name “EyeScore,” an AI-powered know-how that makes use of non-invasive scans of the retina to foretell the recurrence of stroke in sufferers. They use optical coherence tomography — a scan of the again of the retina — and monitor adjustments over time utilizing superior deep studying fashions. The retina, connected on to the mind by the optic nerve, can be utilized as a physiological window for adjustments within the mind itself.
Atashzar and Shamout are presently formulating their hybrid AI mannequin, pinpointing the precise adjustments that may predict a stroke and recurrence of strokes. The end result will be capable to analyze these pictures and flag doubtlessly troublesome developments. And for the reason that scans are already in use in optometrist workplaces, this life-saving know-how might be within the palms of medical professionals ahead of anticipated.
Atashzar is using AI algorithms for makes use of past stroke. Like many researchers, his gaze was drawn to the biggest medical occasion in current historical past: COVID-19. Within the throes of the COVID-19 pandemic, the very bedrock of worldwide healthcare supply was shaken. COVID-19 sufferers, vulnerable to swift and extreme deterioration, introduced a significant issue for caregivers.
Particularly within the pandemic’s early days, when our grasp of the virus was tenuous at greatest, predicting affected person outcomes posed a formidable problem. The merest tweaks in admission protocols held the ability to dramatically shift affected person fates, underscoring the necessity for vigilant monitoring. As healthcare programs groaned below the pandemic’s weight and contagion fears loomed, outpatient and nursing heart residents had been steered towards distant symptom monitoring through telemedicine. This cautious strategy sought to spare them pointless hospital publicity, permitting in-person visits just for these within the throes of grave signs.
However whereas a lot of the pandemic’s analysis highlight fell on diagnosing COVID-19, this examine took a distinct avenue: predicting affected person deterioration sooner or later. Current research usually juggled an array of information inputs, from advanced imaging to lab outcomes, however did not harness knowledge’s temporal features. Enter this analysis, which prioritized simplicity and scalability, leaning on knowledge simply gathered not solely inside medical partitions but in addition within the consolation of sufferers’ properties with the usage of easy wearables.
S. Farokh Atashzar and colleagues at NYU Tandon are utilizing deep neural community fashions to evaluate COVID knowledge and attempt to predict affected person deterioration sooner or later.
Atashzar, alongside together with his Co-PI of the undertaking Yao Wang, Professor of Biomedical Engineering and Electrical and Pc Engineering at NYU Tandon, used a novel deep neural community mannequin to evaluate COVID knowledge, leveraging time sequence knowledge on simply three important indicators to foresee COVID-19 affected person deterioration for some 37,000 sufferers. The last word prize? A streamlined predictive mannequin able to aiding scientific decision-making for a large spectrum of sufferers. Oxygen ranges, heartbeats, and temperatures shaped the trio of important indicators below scrutiny, a selection propelled by the ubiquity of wearable tech like smartwatches. A calculated exclusion of sure indicators, like blood stress, adopted, as a consequence of their incompatibility with these wearables.
The researchers utilized real-world knowledge from NYU Langone Well being’s archives spanning January 2020 to September 2022 lent authenticity. Predicting deterioration inside timeframes of three to 24 hours, the mannequin analyzed important signal knowledge from the previous 24 hours. This crystal ball aimed to forecast outcomes starting from in-hospital mortality to intensive care unit admissions or intubations.
“In a scenario the place a hospital is overloaded, getting a CT scan for each single affected person can be very troublesome or unimaginable, particularly in distant areas when the healthcare system is overstretched,” says Atashzar. “So we’re minimizing the necessity for knowledge, whereas on the similar time, maximizing the accuracy for prediction. And that may assist with creating higher healthcare entry in distant areas and in areas with restricted healthcare.”
Along with addressing the pandemic on the micro stage (people), Atashzar and his staff are additionally engaged on algorithmic options that may help the healthcare system on the meso and macro stage. In one other effort associated to COVID-19, Atashzar and his staff are creating novel probabilistic fashions that may higher predict the unfold of illness when taking into consideration the consequences of vaccination and mutation of the virus. Their efforts transcend the basic small-scale fashions that had been beforehand used for small epidemics. They’re engaged on these large-scale advanced fashions with the intention to assist governments higher put together for pandemics and mitigate fast illness unfold. Atashzar is drawing inspiration from his lively work with management algorithms utilized in advanced networks of robotic programs. His staff is now using comparable strategies to develop new algorithmic instruments for controlling unfold within the networked dynamic fashions of human society.
A state-of-the-art human-machine interface module with wearable controller is certainly one of many multi-modal applied sciences examined in S. Farokh Atashzar’s MERIIT Lab at NYU Tandon.NYU Tandon
The place minds meet machines
These tasks signify solely a fraction of Atashzar’s work. Within the MERIIT lab, he and his college students construct cyber-physical programs that increase the performance of the next-generation medical robotic programs. They delve into haptics and robotics for a variety of medical functions. Examples embrace telesurgery and telerobotic rehabilitation, that are constructed upon the capabilities of next-generation telecommunications. The staff is particularly within the software of 5G-based tactile web in medical robotics.
Just lately, he acquired a donation from the Intuitive Basis: a Da Vinci analysis equipment. This state-of-the-art surgical system will permit his staff to discover methods for a surgeon in a single location to function on a affected person in one other—whether or not they’re in a distinct metropolis, area, and even continent. Whereas a number of researchers have investigated this imaginative and prescient previously decade, Atashzar is particularly concentrating on connecting the ability of the surgeon’s thoughts with the autonomy of surgical robots – selling discussions on methods to share the surgical autonomy between the intelligence of machines and the thoughts of surgeons. This strategy goals to scale back psychological fatigue and cognitive load on surgeons whereas reintroducing the sense of haptics misplaced in conventional surgical robotic programs.
Atashzar poses with NYU Tandon’s Da Vinci analysis equipment. This state-of-the-art surgical system will permit his staff to discover methods for a surgeon in a single location to function on a affected person in one other—whether or not they’re in a distinct metropolis, area, and even continent.NYU Tandon
In a associated line of analysis, the MERIIT lab can be specializing in cutting-edge human-machine interface applied sciences that allow neuro-to-device capabilities. These applied sciences have direct functions in exoskeletal units, next-generation prosthetics, rehabilitation robots, and presumably the upcoming wave of augmented actuality programs in our good and linked society. One frequent important problem of such programs which is targeted by the staff is predicting the meant actions of the human customers by processing alerts generated by practical habits of motor neurons.
By fixing this problem utilizing superior AI modules in real-time, the staff can decode a consumer’s motor intentions and predict the meant gestures for controlling robots and digital actuality programs in an agile and sturdy method. Some sensible challenges embrace making certain the generalizability, scalability, and robustness of those AI-driven options, given the variability of human neurophysiology and heavy reliance of basic fashions on knowledge. Powered by such predictive fashions, the staff is advancing the advanced management of human-centric machines and robots. They’re additionally crafting algorithms that take note of human physiology and biomechanics. This requires conducting transdisciplinary options bridging AI and nonlinear management theories.
Atashzar’s work dovetails completely with the work of different researchers at NYU Tandon, which prizes interdisciplinary work with out the silos of conventional departments.
“Dr. Atashzar shines brightly within the realm of haptics for telerobotic medical procedures, positioning him as a rising star in his analysis neighborhood,” says Katsuo Kurabayashi, the brand new chair of the Mechanical and Aerospace Engineering division at NYU Tandon. “His pioneering analysis carries the thrilling potential to revolutionize rehabilitation remedy, facilitate the analysis of neuromuscular illnesses, and elevate the sector of surgical procedure. This holds the important thing to ushering in a brand new period of subtle distant human-machine interactions and leveraging machine learning-driven sensor sign interpretations.”
This dedication to human well being, by the embrace of recent advances in biosignals, robotics, and rehabilitation, is on the coronary heart of Atashzar’s enduring work, and his unconventional approaches to age-old downside make him an ideal instance of the strategy to engineering embraced at NYU Tandon.
From Your Web site Articles
Associated Articles Across the Net