Artificial intelligence and machine learning in spine research

Abstract

Artificial intelligence (AI) and machine learning (ML) techniques are revolutionizing several industrial and research fields like computer vision, autonomous driving, natural language processing, and speech recognition. These novel tools are already having a major impact in radiology, diagnostics, and many other fields in which the availability of automated solution may benefit the accuracy and repeatability of the execution of critical tasks. In this narrative review, we first present a brief description of the various techniques that are being developed nowadays, with special focus on those used in spine research. Then, we describe the applications of AI and ML to problems related to the spine which have been published so far, including the localization of vertebrae and discs in radiological images, image segmentation, computer‐aided diagnosis, prediction of clinical outcomes and complications, decision support systems, content‐based image retrieval, biomechanics, and motion analysis. Finally, we briefly discuss major ethical issues related to the use of AI in healthcare, namely, accountability, risk of biased decisions as well as data privacy and security, which are nowadays being debated in the scientific community and by regulatory agencies.

Computer‐assisted pedicle screw trajectory planning using CT‐inferred bone density: A demonstration against surgical outcomes

“…The plans were generated by the proposed computer-assisted tool based on parametric modeling of the vertebral and pedicle shape, maximization of the screw fastening strength, and taking into account two important surgical considerations: (a) pedicle screw placement to simulate the straight-forward surgical insertion technique and (b) pedicle screw entry points to follow the spinal curvature. Although the emerging technologies based on state-of-the-art machine learning approaches [43][44][45][46] may represent an alternative for future modeling of the vertebral bodies, pedicles, and pedicle screw size and trajectories, our approach does not require any training but is based on parametric modeling augmented with morphological, structural, and procedural knowledge of vertebral structures and pedicle screw placement. The pedicle screw placement plans, obtained by different versions of the computer-assisted tool from preoperative CT images, were graded to assess their quality.…”

Applications of Machine Learning Using Electronic Medical Records in Spine Surgery

“…As CT and MRI scans became available in bulk, they became strong datasets for ML training, yielding stronger ML models. 26 With regards to spinal visualization and segmentation, many groups have applied sophisticated automated analysis of CT and MRI to both normal and pathological spines. One University of Cincinnati group used a "guess-and-revise" ML algorithm on sagittal MRI scans of whole spines.…”

Delivering high‐tech, AI‐based health care at Apollo Hospitals

“…The paradigm shift in health care made possible by these technologies has been widely discussed (Galbusera, Casaroli, & Bassani, ). Because AI, machine learning, and big data can identify the occurrence of a disease at an early stage—sometimes even before any observable symptoms—they enable a shift from treatment to predictive health‐care models that reduce the chances of a patient developing chronic health problems, and allow timely clinical treatment to be offered.…”

“…When an AI system provided by an international vendor has been trained using data that is very different from a particular country's local conditions, this could produce false results and lead to unanticipated errors. For example, inappropriate training data may cause unforeseen biases when diagnosing illnesses, prescribing drugs, or suggesting treatment plans (Galbusera et al, ).…”

“…Even if everything is in place, the issue of accountability and responsibility for decisions remains (Galbusera et al, ). It is useful to think of the role of AI on a continuum, ranging from situations where humans and machines work together to perform tasks that humans already do—augmented intelligence—to situations where AI enables humans to do more than they can do currently—assisted intelligence—and to situations where AI performs tasks without human intervention—autonomous intelligence.…”