Lets face it.We are living in a world surrounded by Artificial intelligence and we probably are using it everyday with applications like Siri, Google Assistant,Alexa etc. Artificial intelligence and machine learning are parts of digital technology that are correlated with each other.
Artificial Intelligence
AI is a bigger concept to create intelligent machines that can simulate human thinking capability and behaviour, whereas, machine learning is an application or subset of AI that allows machines to learn from data without being programmed explicitly.
The Artificial intelligence system does not require to be pre-programmed, instead of that, they use such algorithms which can work with their own intelligence. It involves machine learning algorithms such as Reinforcement learning algorithm and deep learning neural networks. AI is being used in multiple places such as Siri, Google Assistant , AlphaGo, AI in Chess playing, etc.
Based on capabilities, AI can be classified into three types:
- Weak AI or narrow AI(ANI)
- General AI/ Strong AI/Deep AI(GAI)
- Artificial super intelligence (ASI)
ANI systems can attend to a task in real-time, but they pull information from a specific dataset. As a result, these systems don’t perform outside of the single task that they are designed to perform.
AGI can think, understand, and act in a way that is indistinguishable from that of a human in any given situation
ASI is the hypothetical AI that doesn’t just mimic or understand human intelligence and behaviour; ASI is where machines become self-aware and surpass the capacity of human intelligence and ability.
Currently, we are working with weak AI ( Siri, chat bots etc)and general AI( in development). The future of AI is Strong AI for which it is said that it will be intelligent than humans.
Machine Learning (ML)
Machine learning is a subfield of artificial intelligence, which enables machines to learn from past data or experiences without being explicitly programmed.
Machine learning enables a computer system to make predictions or take some decisions using historical data without being explicitly programmed. Machine learning uses a massive amount of structured and semi-structured data so that a machine learning model can generate accurate result or give predictions based on that data.
Machine learning is being used in various places such as for online recommender system, for Google search algorithms, Email spam filter, Facebook Auto friend tagging suggestion, etc.
It can be divided into 2 main types:
1. Supervised
2. Unsupervised/ deep learning(DL)
Supervised learning
Entails labelled data based on a black and white fact or known fact. For example, a database of lateral x- rays has films prelabelled as either “fracture” or “no fracture.” A portion of this data (training dataset) is analysed to build a model that synthesizes the pattern between independent variables (i.e., pixel in an image) and dependent variables (presence or absence of pathology). The remainder of the x-ray films (untrained dataset) are fed to the machine, which is then assessed based on its ability to accurately predict a fracture or otherwise.
Unsupervised learning
Or deep learning on the other hand, involves the analysis of unlabelled datasets. Unsupervised machines (like humans) can appreciate non-linear relationships and do so without presumptions related to the data. Unsupervised learners are particularly adept at identifying clusters of related variables, detecting anomalies, and constructing artificial neural networks. While unsupervised learning is thought to be the standard for the future, most current ML examples in spine surgery and clinical medicine are of the supervised variety.
While basic machine learning models do become progressively better at whatever their function is, they still need some guidance. If an AI algorithm returns an inaccurate prediction, then an engineer has to step in and make adjustments. With a deep learning model, an algorithm can determine on its own if a prediction is accurate or not through its own neural network.
AI in Health Care
Artificial intelligence is proving to be a game-changer in healthcare, improving virtually every aspect of the industry from robot-assisted surgeries to safeguarding private records against cyber criminals.
Healthcare has long suffered from skyrocketing medical costs and inefficient processes. Artificial intelligence is giving the industry a much-needed makeover.
AI-enabled virtual assistants are reducing unnecessary hospital visits and giving nurses 20% of their time back in the process; workflow assistants are helping doctors free up 17% of their schedules; pharmaceutical companies are researching lifesaving medicines in a fraction of the time and cost it traditionally takes; and AI is even being used to help bring healthcare to underdeveloped nations.
In clinical medicine, the rise of machine learning applications represents a new era of solving
healthcare problems. This is particularly true in spine surgery where algorithmic decision support tools, computer assisted navigation, and surgical robots are already being used in the clinic and operation theatres
AI in spine – The Back Ground
Spiralling Cost
Spine care is expensive: annual expenditures in the United States currently average $110 billion in direct costs. By 2025, total health expenditures are expected to average $5.3 trillion, or close to 20% of the gross domestic product of the United States. Furthermore, health care reform has developed into an environment of decreasing reimbursements, increasing payer denials, and profiling hospitals and physicians on the utilization and quality of care.Without innovation, or significant downsizing, the current trajectory of spine surgery expenditures is not sustainable.
Variability
A 2014 survey of neurosurgical and orthopaedic spine surgeons in the United States demonstrated disagreement on the surgical treatment of a recurrent lumbar disc herniations in 69% of the surgeons.
In 2016, another survey demonstrated a 75% rate of disagreement among spine surgeons on various treatments for chronic low back pain patients. This heterogeneity of care leads to variability in treatment and costly in care delivery and research. In addition variability was also note n patient related outcome scores .
With these factors in mind, there exist numerous areas where AI algorithms (e.g., machine learning [ML], deep learning) can be used to improve care and develop consensus among surgeons. While there has also been controversy surrounding AI, if implemented appropriately, it has the potential to revolutionize the standard of care in spine surgery, reduce cost and waste, and improve the efficiency and patient care. In addition, AI could enhance individualized care to patients and reduce heterogeneity in both clinical practice and research.
Lets go thru various applications of AI and ML in spine surgery
Pre op care/ Planning
Imagine a patient with l4/l5 grade 2 listhesis with spinal stenosis requiring surgery. For The current generation of spine surgeons, options are many. They make these decisions based on the available literature and patient and surgeon factors that are known. Imagine if we can add other 50 odd variables to it and the machine gives you the optimal plan including the various costs involved and a treatment plan tailored for that particular patient!! That is the future of AI in preop care and surgical planning.
- identifying optimal surgical candidates
- advise the surgeon on operative approaches
- predict the likelihood of success
- cost, and/or payments of various treatment pathways
While these innovative approaches to ML in spine surgery have not yet been scaled to encompass the whole field, models that help surgeons determine the probability of an adverse event like infection following spine surgery have emerged in recent years1.
ML models that help surgeons predict complications like infection, bleeding etc. preoperatively will inevitably improve with the availability of more data, hopefully to the point of effective clinical implementation.
Research
As ML applications improve, this may ultimately lead to a paradigm shift in the way evidence-based guidelines are used and interpreted.
The evidence used to create the guidelines that ultimately dictate the standard practice of spine surgery is mostly derived through large, multicentre, retrospective data- base studies. The results produced from these studies are wholly dependent on the data that is utilized to generate these hypotheses.
AI-based research enables clinical data to speak for itself. Rather than utilizing a data mining approach, which drives much spine research, AI has the ability to revolutionize the field by analysing tons of data in a short span of time. Several key areas of spine research that have benefited from AI and ML, namely, diagnostic imaging, outcome prediction, clinical decision support, and biomechanics1.
Spinal Imaging
AI is already being used in spinal imaging in the last few years like synthetic mri.
Synthetic MRI is a technique that generates contrast weighted images based on measurements of tissue properties from a single acquisition.
The technique enables the reconstruction of multiple sequences from one single scan and thus reduces the scanning time. This property is especially useful in paediatrics, for uncollaborative patients and also interesting for patients with multiple follow ups.
In contrast to subjective visual analysis of signal intensity differences in a conventional MR image, synthetic MRI produces objective numeric values that can be used with or without production of actual images.
The classification of degenerative discs via feature-extraction from MRI (magnetic resonance imaging) imaging exemplifies the critical contributions that AI has already made to the field of spine surgery.
Applications for spine surgery could include preoperative assessment of osteoporosis, and postoperative assessment of changes in disc composition, marrow composition, or spinal cord or nerve root tissue characterization.
In the future, quantitative data acquisition with AI analysis will allow direct transfer of information, with characterization and interpretation of patient pathology, from imaging equipment to the surgeon, without the need for radiology interpretation and reports.
The adoption of AI tools by other members of the larger health care team will also affect surgical evaluation and workflow.
Algorithms that provide image augmentation with deep learning have recently been cleared by the Federal Drug Administration (FDA).
This technology facilitates MR image acquisition in a fraction of the normal study time, by collecting less data and using the algorithm to interpolate the missing information based on training from large, high-quality data sets. These time savings benefit the surgeon and patient: exams are substantially shorter, reducing motion artifact and enhancing image quality; patient satisfaction is improved with less time in the MR scanner; and the time from initial order to delivered report is substantially decreased.
Algorithms that automate evaluation of spinal hardware location and integrity on routine longitudinal radiographic follow-up are currently being developed. These AI tools can analyse multiple prior studies in a fraction of the time and cost of a human interpretation.1
Result Prediction
Predictive models using ML techniques such as decision tree and random forest enable surgeons to anticipate everything from the best course of care—surgical intervention versus conservative to operative complications, such as those following spinal deformity surgery.
The implementation of sophisticated machine learning algorithms for spine surgery has the potential to revolutionize how surgeons approach preoperative clinic visits with patients and guide clinical decisions based on predictive models.
More recently, Ames and the International Spine Study Group utilized AI to perform unsupervised learning via hierarchical clustering to identify unique patient types with distinct risk-benefit profiles for adult spinal deformity (ASD) and are currently trialling the prospective use of risk calculators built from predictive models prognosticating postoperative complications .
By catering outcomes analysis to a specific patient, surgeons have the power to supplement years of clinical experience and knowledge with robust mathematical estimates, augmenting their ability to counsel patients and focus more closely on the individual needs of patients.1
Surgical virtual reality-enabled robotics for surgery
Over the past several years, technical advancements in surgical simulation, augmented reality, and robotic-assisted spine surgery have led to fundamental changes in spine surgery practice.
Since image processing is a key strength of AI programs, neuronavigation stands to particularly benefit from evolving AI techniques. Furthermore, AI can facilitate the individualization of management and surgical planning to each patient.
By accounting for anatomical variations among patients, the image processing prowess of AI allows exact reconstruction of relevant spinal anatomy during surgical planning.
The advent of advanced navigation technologies allows surgeons construct a 3-dimensional rendering of the spine that provides real-time positional feedback during the operation, thereby allowing visualization of deeper structures. Thus intraoperatively, the operating team can also use AI-powered image guidance to direct anatomical positioning of constructs and avoid iatrogenic injury.1
One of the biggest challenges in spine surgery is maintaining precision and accuracy of motion during lengthy operations. It is not only human to error, but also human to fatigue, and even the best trained spine surgeon is not an exception to this human attribute. Robotics address these drawbacks by providing a precision and indefatigability impossible to consistently reproduce in a surgeon.
AI Robot-Assisted Surgery
Robots equipped with cameras, mechanical arms and surgical instruments augment the experience, skill and knowledge of doctors to create a new kind of surgery. Surgeons control the mechanical arms while seated at a computer console while the robot gives the doctor a three dimensional, magnified view of the surgical site that surgeons could not get from relying on their eyes alone. The surgeon then leads other team members who work closely with the robot through the entire operation.
The SpineAssist robot and the ROSA robot are various examples of robotic systems used in spine currently.
It is important to note that while surgical robotics are clearly advancing spine surgery, they do not supplement the surgeon. Even in the most technically challenging cases, which would benefit from the increased precision of robotics, it is still the surgeon that makes operative decisions and guides the robots in their function. Like any instrument, surgical robots are tools in the spine surgeon’s armamentarium. Furthermore, there is a large cost burden to overcome with surgical robotic devices, which may prove to be a barrier to widespread implementation of these devices in the future1.
Artificial intelligence has enormous potential in revolutionizing comprehensive spine care. AI’s evidence-based, predictive analytics can help surgeons improve preoperative patient selection and a tailored plan can be designed for implementation. This execution of plan in the operation theatre with high precision navigational systems in turn improves individualized postoperative care. In the realm of research, AI computing capacity can be used to collect, process, and analyse huge volumes of patient information to extract valuable clinical information for studies. Robotic-assisted surgery, while still new and improving, has potential to help reduce surgeon fatigue and improve technical precision. One thig is for certain.
The boundaries of spine surgery is being pushed at a pace that we have never seen before. In the future with advances in AI in spine surgery at every level from preoperative care to operating theatre precision and rehabilitation, we will see the rise of the machines and safety and accuracy will be at the pinnacle of every health care system. But Empathy will still be our forte !!
See you soon with some more spine tips in My Spine World. Remember, we got your back!
1.Rasouli JJ, Shao J, Neifert S, Gibbs WN, Habboub G, Steinmetz MP, Benzel E, Mroz TE. Artificial Intelligence and Robotics in Spine Surgery.