Artificial intelligence in spine care is “here to stay”

4110
Jonathan Rasouli

Artificial intelligence (AI) has “tremendous potential” to revolutionise comprehensive spine care across areas including patient selection, outcome prediction, research, pre-operative workup and peri-operative assistance, the authors of a large systematic review on the topic have found.

Published in the Global Spine Journal, the review, led by Jonathan J Rasouli (Cleveland Clinic, Cleveland, USA) looks at the current trends and applications of AI and machine learning in conventional and robotic-assisted spine surgery.

According to Rasouli and colleagues, there has been increasing attention and interest in the system-based benefits of AI and its applications to spine surgery. This includes helping clinicians and hospital centres define the quality and cost of care, improve outcomes and mitigate downrange financial exposures to both institutions and payers.

“While there has also been controversy surrounding AI, if implemented appropriately, it has the potential to revolutionise the standard of care in spine surgery, reduce cost and waste, and improve the efficiency and patient care. In addition, AI could enhance individualised care to patients to reduce heterogeneity in both clinical practice and research,” the study team writes.

The first potential area for the employment of AI singled out by Rasouli and colleagues is in preoperative patient care and outcome prediction. The investigators write that while there is evidence to support certain surgical treatments over others, a surgeon’s choice in treatment is often dictated by training, experience and personal performance. They add that there are many patient specific variables that influence cost and outcomes such as body mass index, the presence and severity of comorbidities, tobacco use, and psychosocial factors, to name a few. “It is difficult, if not impossible, for the clinician to reconcile and weight all of the discrete data points and his/her personal performance when indicating such a patient for surgery. AI can assist with such decision making. While most published literature are level III evidence or expert-based guidelines, most cannot guide decision making for complex spine surgery, or when there is clinical equipoise.”

The team add, “AI could assist surgeons in identifying optimal surgical candidates, advise the surgeon on operative approaches, and predict the likelihood of success cost, and/or payments of various treatment pathways.”

Rasouli and colleagues cite a study carried out by Zoher Ghogawala (Lahey Health, Burlington, USA) examining this AI-driven approach in the setting of degenerative lumbar spondylolisthesis, utilising expert-reviewed imaging data to create a supervised machine learning model. “These innovative approaches could allow for a stronger guarantee of optimised patient outcomes in certified surgical candidates through ensuring proper surgical selection,” Rasouli and colleagues note.

The reviewers further cite a study by Christopher Ames  (UCSF, San Francisco, USA) and colleagues, which examined preoperative decision making in the largest spinal deformity patient cohort to date. Ames et al established a model predicting two-year outcomes by constructing a visual risk-benefit grid, which also provides the surgeon insight into which surgical intervention would yield the highest probability of success. Rasouli and colleagues note, “In essence, these models successfully converted surgeons’ gestalt about a patient’s probability of surgical success into an accurate, reproducible, and homogenous clinical decision-making tool in a population of patients at high risk of poor outcome. Ideally, these tools will be developed for a variety of patient populations in the future.”

However, Rasouli and colleagues acknowledge that AI at its core, “is fundamentally a research tool that could be powerful and disruptive to the current body of a spine surgery literature.” As machine learning applications improve, this may ultimately lead to a paradigm shift in the way evidence-based guidelines are used and interpreted, they add. “AI-based research enables clinical data to speak for itself. Rather than utilising a data mining approach, which drives much spine research, AI has the ability to revolutionise the field,” the reviewers reiterate. They highlight a recent review by Fabio Galbusera (Istituto Ortopedico Galeazzi, Milan, Italy) identifying several key areas that have benefited from AI and machine learning in spine care, including diagnostic imaging, outcome prediction and clinical decision support.

Rasouli and colleagues also propose that advances in technology are facilitating the transformation of image analysis; from qualitative, subjective assessment to the acquisition of quantitative, reproducible data. They cite findings from the Galbusera, noting that AI has already made “critical contributions” to the field of spine surgery. The study described an AI-based algorithm used in the classification of degenerative discs.  Utilising a convolutional neural network, the algorithm extracted salient features of discs, including their shape and intensity. The AI-based algorithm was able to achieve a 70.1% concordance with human observations, “which is extremely comparable to the documented rate of agreement between individual expert radiologists” the study team concluded.

“Integration of AI into biomechanical investigations represents yet another frontier of spine surgery research,” Rasouli and colleagues write, adding that while the usage of AI in this field is still in its infancy, AI has promising applications.. Analysis of gait and motion patterns, along with identification of abnormal gait in spinal disorders, represents one area that can benefit from AI usage, they find.

Analysing their findings, Rasouli and colleagues speculate: “AI’s evidence-based, predictive analytics can help surgeons improve preoperative patient selection, surgical indications, and improve individualised postoperative care. In the realm of research, AI computing capacity can be used to collect, process, and analyse volumes of patient information to extract valuable clinical information for studies,” the team writes. Ultimately, the study concludes: “In the ever-evolving landscape of spine surgery, one thing is certain: artificial intelligence technologies have arrived—and they are here to stay.”


LEAVE A REPLY

Please enter your comment!
Please enter your name here