Doug Teany is the Chief Operating Officer of Corindus, a Siemens Healthineers company, a global technology leader in robotic-assisted vascular interventions. The Company’s CorPath® platform is the first FDA-cleared medical device to bring robotic precision to percutaneous coronary and vascular procedures.
What is it that compelled you to dedicate your life to developing lifesaving medical products?
Almost all of us strive to work on something meaningful – something that makes a difference in our communities and broader society. I believe that everyone who works in the medical device industry is motivated by the fact that our work can make a difference in the lives of patients. And for most, it’s not an abstract concept. Those patients are often friends and family members. The possibility of improving or prolonging the life of people we care about is a powerful motivator.
You’ve worked in high-level positions with phenomenal companies such as Boston Scientific Corporation, and Abbott Laboratories. What is it that attracted you to work with Corindus Vascular Robotics?
I feel very fortunate to have worked for world-class companies like Boston Scientific. The scale and resources of large companies allows them to reach hundreds of thousands of patients with life-saving products. However, some of the most innovative products come from small and emerging companies – companies that are actively challenging the current treatment paradigm, and by doing so, moving patient care forward. For me, Corindus falls squarely into this model. It’s sort of a David vs. Goliath story – a small innovative company working to disrupt the current care model for emergent conditions like heart attack and stroke. It’s a bold goal, but sometimes the most difficult challenges are the best things to work on. They have the biggest returns – both for the people working on them and for the patients that will benefit from them.
Vascular Robotics enables robotic assisted vascular interventions. Can you discuss the benefits of robotic-assisted intervention versus manual human intervention?
There are two categories of benefits stemming from robotic-assisted intervention: benefits that we are realizing right now and benefits we have the potential to bring to fruition in the future. Right now, robotic assistance makes procedures such as PCI safer for both the patient and the physician by making them more precise and effective while shielding the physician from harmful radiation exposure.
Moving forward, our goal is to normalize remote robotic intervention, or telerobotics, to treat highly emergent conditions that require specialized care such as acute ischemic strokes and heart attacks. In the U.S. today, 80% of patients that suffer from a heart attack live close enough to a hospital to receive essential care in under an hour. However, we think that number should be closer to 100%. With remote robotics, if we can reach the 20% of patients who live more than an hour away from the hospital, we can do wonderful things for them while taking a lot of costs out of the health care system long term.
One of the benefits of robotic intervention is that the human operator can avoid long-term radiation exposure. How big of a problem is radiation exposure for medical staff, and how does the CorPath System minimize this level of radiation?
Interventional cardiologists experience the highest amount of radiation exposure of any medical professionals, which leads to a significantly increased risk of developing a malignant tumor. 85% of brain tumors reported by physicians occurred on the left side of the head, which is the side closest to the radiation source and a sign that performing these procedures manually contributed to the diagnosis.
To protect our physicians, as well as technicians and patients, the CorPath GRX System is designed to remove the physician from the radiation field, reducing exposure by upwards of 95%. The technologist and patient also receive a markedly lower dose of radiation with robotic-assisted procedures compared to manual procedures, which has tremendous benefits for their long-term health.
Can you discuss the level of precision that CorPath Systems are currently capable of, and how that compares to humans?
One of the primary advantages of robotic assistance in a procedure like PCI is that it brings a level of precision that you simply can’t attain with human hands alone. The robot can move interventional devices one millimeter at a time. It provides physicians the tools to measure patient anatomy to the sub-millimeter. A human just cannot calculate consistent measurements that fine without technology. That precision provides benefit to the patient because the physician can complete cases more effectively with one procedure. Moving wires and catheters within the vasculature and placing stents exactly where they need to be – down to the millimeter – will ensure the patient receives the best possible outcome from the procedure and reduces the likelihood of needing a second stent because the first one was slightly misplaced.
Robotic-assisted intervention also provides the operating physician with a much clearer visualization of the case. They sit at a robotic control station directly in front of a large, high-definition monitor, which gives them a much better view of their work as opposed to the traditional method of standing hunched over the operating table. That visualization component also contributes to accuracy and precision in these delicate procedures.
A study demonstrated that accurate measurement of coronary anatomy, using CorPath, reduced the use of unnecessary additional stents in 8.3% of cases. Can you discuss why this is so important?
Today, physicians have tools to perform visual estimates of lesion length to select stent size. Robotics offers the ability for sub-millimeter lesion measurements and accurate stent positioning, levels of procedural control which are difficult to do manually. Stenting one lesion in the heart with a single stent is better long-term for the patient than requiring a second stent. With reduced devices, robotics can help decrease the likelihood that the patient may need additional interventions or have long-term complications. As our health system works to achieve value-based care initiatives, this technology also makes readmission for a second stent procedure an avoidable expense for the patient and payer.
How many hospitals are currently using CorPath Systems?
Corindus has seen a significant amount of growth over the last couple of years. There are approximately 70 facilities worldwide that have developed robotic programs for interventional procedures.
In November 2019, Corindus Completed the first transcontinental Simulated Telerobotic Percutaneous Coronary Intervention Procedures Over 5G, Fiber, and Public Internet Networks. Can you discuss why this is so important.
When telerobotic procedures become more widely adopted to treat patients remotely, the first and most common scenario will involve a physician at one hospital directly connected to a robotic system at a second hospital through a secure fiber optics network. We refer to this as a “hub-and-spoke” model, where a physician at a larger “hub” location can operate a robot at the smaller “spoke” location where the patient presented because it was closer to them. Long-term hub-and-spoke will evolve into something that looks more like a connected mesh, or a connected network. Any of those spokes could reach out to each other, or a spoke could reach back to the hub, creating a very dynamic model where a physician at any location could treat a patient at any location, and it’s the best infrastructure to provide quick access to timely care.
The emergence of 5G offers an opportunity to broaden the hub-and-spoke model. 5G is the first generation of wireless connectivity with the speed and bandwidth to support a remote robotic procedure without any perceptible latency, as Dr. Madder demonstrated in the test procedures you referenced. Theoretically, we could install a robot at a treatment facility in a remote area and connect it via 5G to a capable healthcare system to treat patients. Instead of the hub-and-spoke including hospitals in a connected network, we can extend our reach to include treatment facilities in extremely remote areas. In this scenario, 5G could play a key role in bridging the gap of where the fiber network ends and where patients need specialty care.
How big of a market and how important do you believe long-distance, multi-location remote procedures will become?
For certain procedures, such as heart attack and stroke, time is of the essence. When treating stroke, time is brain. Any delay in treatment can have a negative impact on outcomes for patients. However, due to the lack of skilled specialists and facilities that can perform the gold standard of treatment, less than 10% of eligible patients receive this treatment and rates of death and disability are staggeringly high. If we can bring the physician to the patient through telerobotics, we believe there would be an increase in the number of patients treated in a shorter time window. Not only does this improve patient outcomes, it also may reduce long-term care costs to society.
Is there anything else that you would like to share about Corindus Vascular Robotics?
We’re really excited about what we’re developing with procedural automation at Corindus. In the future, when we incorporate technology like artificial intelligence, the robotic system will be able to learn from experience and adjust to new inputs, allowing it to perform the same movements that some of the best physicians in the world perform to overcome challenges when treating patients. This will allow physicians to focus their attention on case strategy and respond to problems as they arise. Automation will standardize the way procedures are done to a very high level of quality, which gets to the overarching goal of robotic automation – making cases safer, faster and more effective while reducing trauma on the patient. In pursuing this goal, our objective is to achieve levels of “high automation.” While large portions of the case can be automated, we believe there should always be a physician present to monitor progression of the case and intervene at any time to ensure the highest levels of safety and patient care.
Thank you for the great interview. It’s exciting to learn about the future of telerobotic procedures, and how Corindus is leading us towards that future.
AI Algorithms Can Enhance the Creation of Bioscaffold Materials and Help Heal Wounds
Artificial intelligence and machine learning could help heal injuries by boosting the development speed of 3D printed bioscaffolds. Bioscaffolds are materials that allow organic objects, like skin and organs, to grow on them. Recent work done by researchers at Rice University applied AI algorithms to the development of bioscaffold materials, with the goal of predicting the quality of printed materials. The researchers found that controlling the speed of the printing is crucial to the development of useful bioscaffold implants.
As reported by ScienceDaily, team of researchers from Rice University collaborated to use machine learning to identify possible improvements to bioscaffold materials. Computer scientist Lydia Kavraki, from the Brown School of Engineering at Rice, lead a research team that applied machine learning algorithms to predict scaffold material quality. The study was co-authored by Rice bioengineer Antonios Mikos, who works on bone-like bioscaffolds that serve as tissue replacements, intended to support the growth of blood vessels and cells and enable wounded tissue to heal more quickly. The bioscaffolds Mikos works on are intended to heal musculoskeletal and craniofacial wounds. The bioscaffolds are produced with the assistance of 3D printing techniques that produce scaffolds that fit the perimeter of a given wound.
The process of 3D printing bioscaffold material requires a lot of trial and error to get the printed batch just right. Various parameters like material composition, structure, and spacing must be taken into account. The application of machine learning techniques can reduce much of this trial and error, giving the engineers useful guidelines that reduce the need to fiddle around with parameters. Kavraki and other researchers were able to give the bioengineering team feedback on which parameters were most important, those most likely to impact the quality of the printed material.
The research team started by analyzing data on printing scaffolds from a 2016 study on biodegradable polypropylene fumarate. Beyond this data, the researchers came up with a set of variables that would help them design a machine learning classifier. Once all the necessary data was collected, the researchers were able to design models, test them, and get the results published in just over half a year.
In terms of the machine learning models used by the research team, the team experimented with two different approaches. Both machine learning approaches were based on random forest algorithms, which aggregate decision trees to achieve a more robust and accurate model. One of the models that the team tested was a binary classification method that predicted if a particular set of parameters would result in a low or high-quality product. Meanwhile, the second classification method utilized a regression-method that estimated which parameter values would give a high-quality result.
According to the results of the research, the most important parameters for high-quality bioscaffolds were spacing, layering, pressure, material composition, and print speed. Print speed was the most important variable overall, followed by material composition. Its hoped that the results of the study will lead to better, faster printing of bioscaffolds, thereby enhancing the reliability of 3D printing body parts like cartilage, kneecaps, and jawbones.
According to Kavraki, the methods used by the research team have the potential to be used at other labs. As Kavraki was quoted by ScienceDaily:
“In the long run, labs should be able to understand which of their materials can give them different kinds of printed scaffolds, and in the very long run, even predict results for materials they have not tried. We don’t have enough data to do that right now, but at some point we think we should be able to generate such models.”
Cognoa Seeks FDA Clearance for Digital Autism Diagnostic Device After Successful Study
Cognoa, the leading pediatric behavioral health company developing diagnostic and therapeutic solutions for children living with autism and other behavioral health conditions, announced today that after surpassing all FDA targets in the pivotal study, the company will be submitting its autism spectrum disorder (ASD) diagnostic to the FDA for clearance. Cognoa’s diagnostic was previously granted Breakthrough Device Designation by the FDA in October 2018.
Cognoa seeks to introduce a new, efficient and accurate approach to diagnosing ASD in the primary care setting, using artificial intelligence (AI) to provide a new paradigm of care that empowers pediatricians. Currently, pediatricians refer most children with suspected developmental delay to specialists to diagnose and prescribe treatment. This often results in children and families facing an arduous process, forcing families to wait months or even years before their child receives an initial diagnosis of ASD and can start life-changing therapy. Cognoa’s solution is positioned to fundamentally change this standard of care by reducing wait times to diagnosis, thereby allowing early intervention to begin during critical neurodevelopmental windows. Early intervention has shown to improve lifelong outcomes for children and their families living with autism.
“The data from our pivotal study was strong, and we are incredibly excited to submit a de novo request for FDA clearance of Cognoa’s ASD Diagnostic,” said David Happel, CEO of Cognoa. “The accuracy of our autism diagnostic solution is unparalleled, exceeding all pre-specified endpoints, and we are looking forward to a priority review. Cognoa’s mission is to improve the lives of children and families living with autism and helping pediatricians diagnose autism within the primary care setting is a vital first step.”
If cleared by the FDA, Cognoa’s ASD Diagnostic will be crucial in helping the approximately 64,000 general pediatricians across the U.S. rule-out or diagnose autism – enabling early intervention and supporting improved life-long outcomes for children, in line with the American Academy of Pediatrics (AAP) updated ASD guidelines as of January 2020. This will streamline the autism care journey for children and families, as specialists will now be able to focus on children with more complex diagnoses.
“There is a significant unmet need for early ASD diagnosis in the pediatric primary care setting,” said Dr. Colleen Kraft, former AAP President and Senior Medical Director of Clinical Adoption at Cognoa. “A clinically validated, FDA-cleared digital assessment platform would empower pediatricians to take definitive action on parental concerns. They would be able to diagnose ASD much more efficiently, with actionable information to drive the clinical management of the 1 in every 54 children with ASD and ensure that these children receive access to the appropriate care and treatment.”
The Pivotal Study
Cognoa’s ASD Diagnostic surpassed its targeted benchmarks in a trial involving 425 participants – aged between 18 to 72 months – whose caregivers or pediatricians had expressed concern about their development but who were never formally evaluated or diagnosed with autism.
The pivotal study ran from July 2019 through May 2020 and was a multi-site, prospective, double-blinded, active comparator, cohort study conducted at 14 sites across the U.S. The study evaluated the ability of Cognoa’s ASD Diagnostic device to aid in the diagnosis of ASD by comparing its diagnostic output with the clinical reference standard, consisting of a diagnosis made by a specialist clinician, based on DSM-5 criteria and validated by one or more reviewing specialist clinicians. This approach was taken to effectively evaluate the accuracy of Cognoa’s investigational device as measured by how often in the study population it correctly identifies a patient with ASD, and how frequently it correctly determines that a patient does not have ASD.
As part of the study, caregivers provided information about their child’s behavior by completing a questionnaire and uploading two short videos using Cognoa’s mobile app. In addition, participating children and their caregiver completed two doctor’s appointments (one with a primary care physician and one with a pediatric specialist). A number of the primary care appointments were completed via telemedicine, with the study finding that the investigational device performed equally well when administered remotely. The trial also showed that Cognoa’s diagnostic device is highly accurate across males and females as well as ethnic and racial backgrounds, thus addressing a longstanding issue of disparities in autism diagnoses.
The pivotal study results are being prepared for publication in a peer-reviewed journal.
AI Used To Identify Gene Activation Sequences and Find Disease-Causing Genes
Artificial intelligence is playing a larger role in the science of genomics every day. Recently, a team of researchers from UC San Diego utilized AI to discover a DNA code that could pave the way for controlling gene activation. In addition, researchers from Australia’s national science organization, CSIRO, employed AI algorithms to analyze over one trillion genetic data points, advancing our understanding of the human genome and through localization of specific disease-causing genes.
The human genome, and all DNA, comprises four different chemical bases: adenine, guanine, thymine, and cytosine, abbreviated as A, G, T, and C respectively. These four bases are joined together in various combinations that code for different genes. Around one-quarter of all human genes are coded by genetic sequences that are roughly TATAAA, with slight variations. These TATAAA derivatives comprise the “TATA Box”, non-coding DNA sequences that play a role in the initialization of transcription for genes comprised of TATA.. It’s unknown how the other approximately 75% of the human genome is activated, however, thanks to the overwhelming number of possible base sequence combinations.
As reported by ScienceDaily, researchers from UCSD have managed to identify a DNA activation code that is employed as often as the TATA box activations, thanks to their use of artificial intelligence. The researchers refer to the DNA activation code as the “downstream core promoter region” (DPR). According to the senior author of the paper detailing the findings, UCSD Biological Sciences professor James Kagonaga, the discovery of the DPR reveals how somewhere between one quarter to one-third of our genes are activated.
Kadonaga initially discovered a gene activation sequence corresponding to portions of DPR when working with fruit flies in 1996. Since that time, Kadonaga and colleagues have been working on determining which DNA sequences were correlated with DPR activity. The research team began by creating half a million different DNA sequences and determining which sequences displayed DPR activity. Around 200,000 DNA sequences were used to train an AI model that could predict whether or not DPR activity would be witnessed within chunks of human DNA. The model was reportedly highly accurate. Kadonaga described the model’s performance as “absurdly good” and its predictive power “incredible”. The process used to create the model proved so reliable that the researchers ended up creating a similar AI focused on discovering new TATA box occurrences.
In the future, artificial intelligence could be leveraged to analyze DNA sequence patterns and give researchers more insight into how gene activation happens in human cells. Kadonaga believes that, much like how AI was able to help his team of researchers identify the DPR, AI will also assist other scientists in discovering important DNA sequences and structures.
In another use of AI to explore the human genome, as MedicalExpress reports, researchers from Australia’s CSIRO national science agency have used an AI platformed called VariantSpark in order to analyze over 1 trillion points of genomic data. It’s hoped that the AI-based research will help scientists determine the location of certain disease-related genes.
Traditional methods of analyzing genetic traits can take years to complete, but as CSIRO Bioinformatics leader Dr. Denis Bauser explained, AI has the potential to dramatically accelerate this process. VarianSpark is an AI platform that can analyze traits such as susceptibility to certain diseases and determine which genes may influence them. Bauer and other researchers made use of VariantSpark to analyze a synthetic dataset of around 100,000 individuals in just 15 hours. VariantSpark analyzed over ten million variants of one trillion genomic data points, a task that would take even the fastest competitors using traditional methods thousands of years to complete.
As Dr. David Hansin, CEO of CSIRO Australian E-Health Research Center explained via MedicalExpress:
“Despite recent technology breakthroughs with whole-genome sequencing studies, the molecular and genetic origins of complex diseases are still poorly understood which makes prediction, application of appropriate preventive measures and personalized treatment difficult.”
Bauer believes that VariantSpark can be scaled up to population-level datasets and help determine the role genes play in the development cardiovascular disease and neuron diseases. Such work could lead to early intervention, personalized treatments, and better health outcomes generally.
- Researchers Develop New Theory on Animal Sensing Which Could be Used in Robotics
- AI Algorithms Can Enhance the Creation of Bioscaffold Materials and Help Heal Wounds
- Zayd Enam, Co-founder and CEO of Cresta
- Cognoa Seeks FDA Clearance for Digital Autism Diagnostic Device After Successful Study
- IoT Enhanced Processors Increase Performance, AI, & Security