VSI Research Provides Great Promise for Patients: Novel Artificial Intelligence Algorithm Can Accurately and Independently Measure Spinopelvic Parameters

As presented at the annual conference of the International Society for the Advancements of Spine Surgery (ISASS) we are proud to report these powerful findings with regards to artificial intelligence and the algorithm that can improve physician workflow efficiency and reduce inter-rater and intra-rater measurement errors. This research was presented at the ISASS annual conference where it was nominated for “Best Paper” recognition.

Introduction: Preoperative and postoperative sagittal plane assessment is crucial in both spinal deformity and degenerative pathologies. Sagittal malalignment is a well-established cause of poor patient-reported outcomes. The currently available spine measurement software programs require users to identify several landmarks prior to calculating parameters, making them time-consuming and more reliant upon user experience. There is a growing need for an automated analysis tool that measures pelvic parameters with speed, precision, and reproducibility without relying on user-identified landmarks. A new AI algorithm has been developed to measure important radiographic parameters independently.

Aims/Objectives: Aim 1.) To evaluate and demonstrate that an algorithm based on artificial intelligence (AI) can independently determine spinopelvic parameters.

Hypothesis: The novel, fully automatic method will have a high agreement with human measurements for lumbar lordosis (LL), pelvic incidence (PI), pelvic tilt (PT), and sacral slope (SS).

Methods: From a total of 200 lateral lumbar radiographs (preoperative and postoperative images from 100 patients undergoing fusion) five independent observers (4 spinal surgeons, 1 senior researcher) digitally measured LL, PI, PT, and SS. Their parameters were compared with AI algorithm-generated parameters. Mean error (95% confidence interval, standard deviation) and inter-rater reliability were assessed using two-way mixed, single-measure intraclass correlation (ICC). ICC values larger than 0.75 were considered excellent (Ciccetti, Psychol. Assess. 1994).

Results: The novel algorithm’s spinopelvic parameter ICC values were excellent in 98% of preoperative and in 95% of postoperative radiographs (PreOp range: 0.85–0.92, PostOp range: 0.81–0.87). Exemplarily, mean errors are smallest for the PI (PreOp: -0.5° (95%-CI: -1.5°–0.6°; Fig. 1); PostOp: 0.0° (-1.1°–1.2°)) and largest for LL (1.3° (0.3°–2.4°); 3.8° (2.5°–5.0°)).

Conclusion: Novel AI algorithm automated spinopelvic parameter measurements from spine radiographs have a high degree of accuracy comparable to digital measurements by experts. This algorithm can improve physician workflow efficiency and reduce inter-rater and intra-rater measurement errors.

 Research Team:

Colin Haines, MD – Virginia Spine Institute
Lindsay Orosz, MS, PA-C – The National Spine Health Foundation
Alexandra E. Thomson, MD, MPH – Virginia Spine Institute
Thomas C. Schuler, MD – Virginia Spine Institute
Christopher R. Good, MD – Virginia Spine Institute
Priyanka Grover, MS – RAYLYTIC GmbH
Marcel Dreischarf, PhD –  RAYLYTIC GmbH
Rita Roy, MD – The National Spine Health Foundation
Ehsan Jazini, MD – Virginia Spine Institute