Artificial intelligence (AI) and machine learning (ML) are rapidly becoming integral components of modern healthcare, offering new avenues for diagnosis, treatment, and outcome prediction. This review explores their current applications and potential future in the field of spinal care. From enhancing imaging techniques to predicting patient outcomes, AI and ML are revolutionizing the way we approach spinal diseases. AI and ML have significantly improved spinal imaging by augmenting detection and classification capabilities, thereby boosting diagnostic accuracy. Predictive models have also been developed to guide treatment plans and foresee patient outcomes, driving a shift towards more personalized care. Looking towards the future, we envision AI and ML further ingraining themselves in spinal care with the development of algorithms capable of deciphering complex spinal pathologies to aid decision making. Despite the promise these technologies hold, their integration into clinical practice is not without challenges. Data quality, integration hurdles, data security, and ethical considerations are some of the key areas that need to be addressed for their successful and responsible implementation. In conclusion, AI and ML represent potent tools for transforming spinal care. Thoughtful and balanced integration of these technologies, guided by ethical considerations, can lead to significant advancements, ushering in an era of more personalized, effective, and efficient healthcare.
Background
Standing whole spinal radiographs are used to evaluate spinal alignment in adult spinal deformity (ASD), yet some studies have reported that pelvic incidence, pelvic tilt, and thoracic kyphosis (TK) intra- and inter-observer reliability is low. This study aimed to evaluate the accuracy of spinopelvic parameters through comparing standing whole spinal radiographs and upright CT images.
Methods
We enrolled 26 patients with ASD. All standing whole spinal posterior/anterior and lateral radiographs and upright whole spinal CT had been obtained in a natural standing position. Two examiners independently measured 13 radiographic parameters. Interclass correlation coefficients (ICCs) were used to analyze measurement intra- and inter-observer reliability. Paired t- and Pearson’s correlation tests were used to analyze validity of the standing whole spinal radiographs.
Results
ICCs of upright CT were excellent in both intra- and inter-observer reliability. However, intra-observer ICCs for TK2–12, TK1–5, TK2–5, and TK5–12 on standing lateral radiographs were relatively low, as were inter-observer ICCs for TK2–12, TK1–5, TK2–5, and TK5–12. Concerning TK values, the difference between the radiographs and CT in TK1–12 and TK2–12 were 4.4 ± 3.1 and 6.6 ± 4.6, respectively, and TK values from T2 showed greater measurement error (p < 0.05).
Conclusions
Upright CT showed excellent intra- and inter-observer reliability in the measurement of spinopelvic parameters. Measurement of TK with T2 on standing whole spinal radiographs resulted in a greater measurement error of up to 6.6°. Surgeons need to consider this when planning surgery and measuring postoperative TK changes in patients with ASD.
The S2 alar-iliac screw (S2AIS) is commonly used for long spinal fusion as a rigid distal foundation in spinal deformity surgeries, and it is also used in percutaneous sacropelvic fixation for providing an in-line connection to the proximal spinal constructs without using offset connectors. Although the pelvic shape is different between males and females, reports on S2AIS trajectories according to gender have been scarce in the literature. In this paper, S2AIS trajectories are compared between males and females using pelvic three-dimensional computed tomography (3D-CT) in a normal Japanese population. After resetting the caudal angulation in CT-imaging plane manipulation, the angulation of S2AIS was more lateral in the axial plane and more horizontal in the coronal plane in females. Mean distances from the midline to starting points of S2AIS tended to be shorter in females, whereas mean distances from the midline to the posterior superior iliac spine was significantly longer in females. We also found that there were positive correlations between the patients’ height and the maximal lengths of S2AISs, and the patients’ height and minimal areas of S2AIS pathways. Our results are useful not only for conventional open spinal surgery, but also for minimally invasive spine surgery.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.