Future of A.I. in Neurosurgery

Artificial intelligence tutoring outperforms expert instructors in neurosurgical training, what does it mean?

PUBLISHED MON, FEB 28 2022: 6:30 AM EST

A.I is becoming implicated in robotic surgery and even the training of the next generation of Neurosurgeons according to McGill University.

• A new study from the Montreal Neurological Institute found that when it comes to teaching brain surgery, artificial intelligence (AI) performs better than real teachers. - CTV News.

• Machine learning algorithms enhanced technical performance and learning outcomes during simulated brain tumor removal - McGill.

Artificial intelligence tutoring outperforms expert instructors in neurosurgical training. Machine learning algorithms enhanced technical performance and learning outcomes during simulated brain tumor removal.

The Neurosurgical Simulation and Artificial Intelligence Learning Centre at The Neuro (Montreal Neurological Institute-Hospital) recruited seventy medical students to perform virtual brain tumour removals on a neurosurgical simulator. Students were randomly assigned to receive instruction and feedback by either an AI tutor or a remote expert instructor, with a third control group receiving no instruction.

Shockingly, students who received VOA (An AI-powered tutor called the Virtual Operative Assistant) instruction and feedback learned surgical skills 2.6 times faster and achieved 36 per cent better performance compared to those who received instruction and feedback from remote instructors.

White Collar Jobs like Medical Surgeons as AI-Human Hybrid Workforce by 2040

This could be an argument for A.I. in medical training and certain kinds of surgery. A.I could also possibly optimize how surgeons make decisions in crucial moments of interventions.

Neurosurgeons receive extensive and lengthy training to equip themselves with various technical skills, and neurosurgery require a great deal of pre-, intra- and postoperative clinical data collection, decision making, care and recovery.

The last decade has seen a significant increase in the importance of artificial intelligence (AI) in neurosurgery. AI can provide a great promise in neurosurgery by complementing neurosurgeons' skills to provide the best possible interventional and noninterventional care for patients by enhancing diagnostic and prognostic outcomes in clinical treatment and help neurosurgeons with decision making during surgical interventions to improve patient outcomes.

Do you enjoy A.I. articles at the intersection of breaking news, then help me continue to write on the subject. I cannot continue to write without support. Grateful for all tips, patronage and community contributions.

A.I. Based Virtual Operate Assistant Outperformed Human Tutors

At McGill University and their affiliated Hospital, the MUHC, an AI-powered tutor called the Virtual Operative Assistant (VOA) used a machine learning algorithm to teach safe and efficient surgical technique and provided personalized feedback, while a deep learning Intelligent Continuous Expertise Monitoring System (ICEMS) and a panel of experts assessed student performance.

Clearly A.I. has implications potentially in the medical training of our future surgeons. The Montreal Neurological Institute has been considered a world leader for years. Researchers compared students who used virtual reality and AI with those taught by humans, and found that students taught by machines learned twice as fast.

Academics have been writing papers about how A.I. will be introduced into surgery for some years now. The reality is surgeons are well-positioned to help integrate AI into modern practice. Surgeons should partner with data scientists to capture data across phases of care and to provide clinical context, for AI has the potential to revolutionize the way surgery is taught and practiced with the promise of a future optimized for the highest quality patient care, according to a 2018 paper.

Standford itself as a Neurological and A.I. lab specifically for this: https://med.stanford.edu/neurosurgery/research/AILab.html

Traditionally, students learn neurosurgery by observing the operating room, and then slowly start doing small surgical tasks on their own. That should probably be part of the past, and AI-tutorically should be further studied and adopted.

Institutions in Healthcare need to train the medical professionals of tomorrow with the likely partners they will have, that is, Artificial Intelligence. The Neurosurgical Simulation and Artificial Intelligence Learning Centre at The Neuro (Montreal Neurological Institute-Hospital) recruited seventy medical students to perform virtual brain tumour removals on a neurosurgical simulator. It’s pretty pioneering news for the use of A.I. in neurosurgical training.

---

About My Work

Did you know, I also run other related Newsletters? The front page of my Newsletters are small treasure droves of articles now.

• AiSupremacy (Dozens of free articles)

• Datascience Learning Center (Dozens of free articles)

• Quantum Foundry (new Quantum computing based Newsletter).

I’ve also started a recent Newsletter on A.I. bite-size news articles.

To my knowledge, I’m among just a handful of indie media startups developing multiple Newsletters simultaneously.

---

The Intersection of Neuroscience and A.I. is Extremely Important

Clearly from many points of view neuroscience and A.I. will converge to a breathtaking extent in the 21st century, perhaps unlike even we envision today in 2022.

A.I tutors like the one at McGill demonstrates the useful of A.I. in the clinical educational setting. “I think above all it just provides an opportunity for junior learners to get some hands on exposure,” said medical student Ali Fazlollahi.

In the virtual simulation, every action is recorded and analyzed, so the computer can tell students how to best proceed.

Just as prospective airplane pilots in training spend thousands of hours in simulations for training, so the same it should be for our brain surgeons.

“Let’s say you are a trainee and this is a new type of operation that you may not have seen before, we have simulations on the simulator that simulate many different types of operations so you can practice,” the director of the Neurosurgical Simulation Research Centre explained.

In simulations A.I tutors can follow a student’s progress and help them along to learn better. An AI-powered tutor called the Virtual Operative Assistant (VOA) used a machine learning algorithm to teach safe and efficient surgical technique and provided personalized feedback, while a deep learning Intelligent Continuous Expertise Monitoring System (ICEMS) and a panel of experts assessed student performance. So in reality, it’s a team of different AIs augmenting the student’s ability to learn the correct techniques.

Applications of AI to clinical data for diagnostic purposes have already begun to demonstrate capability approximating that of specialist physicians. Eventually this will lead to A.I. surgical robots who will be able to do the surgeries themselves better than human surgeons.

The International Organization for Standardization (ISO 8373:2012) defines autonomy as “an ability to perform intended tasks based on current state and sensing without human intervention.” It’s not clear by what year A.I. robotic surgeons will truly be fully autonomous and what degree of more complex surgeries they will be able to handle.

Back in 2019, examples of robotic surgical devices of variable autonomy include the DaVinci (Intuitive Surgical, Sunnyvale, CA) a “master-slave” robot completely dependent upon human control; the TSolution-One (previously ROBODOC; THINK Surgical, Fremont, CA) orthopedic robot; and the Mazor X (Mazor Robotics, Caesarea, Israel) spinal robot. The latter 2 offer reduced levels of human input for a limited range of surgical tasks. Clearly robot-surgeons need years and perhaps decades more experience to be refined enough to reach autonomous levels.

The MUHC/McGill study does show a lot of promise for A.I. augmenting the training process for the surgeons of tomorrow. Likely in their careers they will be working increasingly with various forms of artificial intelligence and semi-autonomous robotic surgical instruments.

• The researchers found that students who received VOA instruction and feedback learned surgical skills 2.6 times faster and achieved 36 per cent better performance compared to those who received instruction and feedback from remote instructors.

• And while researchers expected students instructed by VOA to experience greater stress and negative emotion, they found no significant difference between the two groups.

The Medical Tutors of Tomorrow - A.I. Simulations

Just as consumers often tend to prefer to relate to A.I over other retail sales people, the same might occur in very specialized fields of education over time.

The A.I. will also be able to measure your performance and data points that no human tutor or teacher could possibly evaluate.

“When you’re doing a simulated procedure, we can measure 6,000 things that your hands are doing at the same time. There’s no human that can deal with that amount of data. When you add artificial intelligence, you are able to deconstruct the complications and understand what makes an expert an expert.”

Check out Rolando’s page for more insights on his work. Rolando Fausto Del Maestro’s work has focused on on surgical simulation using the NeuroTouch platform working in cooperation with the National Research Council of Canada and multiple national and international research groups.

“Artificially intelligent tutors like the VOA may become a valuable tool in the training of the next generation of neurosurgeons,” says Dr. Rolando Del Maestro, the study’s senior author. “The VOA significantly improved expertise while fostering an excellent learning environment. Ongoing studies are assessing how in-person instructors and AI-powered intelligent tutors can most effectively be used together to improve the mastery of neurosurgical skills.”

I like this story because it illustrates A.I. from education, to training to clinical practice in healthcare setting. We know healthcare of the future will require A.I.’s increasing interventions to reduce healthcare costs, improve patient-centric care and improve our medical data to augment the quality of that care.

Surgical skill plays an important role in patient outcomes both during and after brain surgery. VOA may be an effective way to increase neurosurgeon performance, improving patient safety while reducing the burden on human instructors. If various A.I. solutions can improve surgical skill, more people can be saved.

This study, published in the Journal of the American Medical Association (JAMA Network Open) on Feb. 22, 2022, was funded by the Franco Di Giovanni Foundation, the Royal College of Physicians and Surgeons of Canada, and the Brain Tumour Foundation of Canada Tumour Research Grant along with The Neuro. Cognitive assessment was led by Dr. Jason Harley at McGill University’s Department of Surgery.

About the MNI, MUHC and McGill University

The Montreal Neurological Institute is a McGill University research and teaching institute. The Montreal Neurological Hospital is part of the Neuroscience Mission of the McGill University Health Centre (MUHC). The Neuro has grown to be the largest specialized neuroscience research and clinical center in Canada, and one of the largest in the world.

I’m impressed by the speed and R&D now going into the future of healthcare from the perspective if artificial intelligence. The institutions of law, healthcare and education remain the most entrenched in the past (think paper not digital and in-person not virtual) and take among the longest to adopt new technologies and artificial intelligence, but once they are ready, new companies will form around them that will change the world forever.

VOA adoption is likely to occur due to papers like these. To better understand the emerging role of artificial intelligence (AI) in surgical training, efficacy of AI tutoring systems, such as the Virtual Operative Assistant (VOA), must be tested and compared with conventional approaches that is now already well underway.

---

NOTE FROM THE AUTHOR

I cannot continue to write without tips, patronage and community support from you, my readers and audience. I want to keep my articles free for the majority of my readers.

So by subscribing you are essentially helping fund a network of Newsletters whose aim is to inspire and inform. This is my only job and stream of income.

AiSupremacy is the fastest Substack Newsletter in AI at the intersection of breaking news. It’s ranked #1 in Machine Learning as of January 22nd, 2022.

Thanks for reading!