Self-learning computers for surgical planning and prediction of postoperative alignment
In past decades, the role of sagittal alignment has been widely demonstrated in the setting of spinal conditions. As several parameters can be affected, identifying the driver of the deformity is the cornerstone of a successful treatment approach. Despite the importance of restoring sagittal alignment for optimizing outcome, this task remains challenging. Self-learning computers and optimized algorithms are of great interest in spine surgery as in that they facilitate better planning and prediction of postoperative alignment. Nowadays, computer-assisted tools are part of surgeons’ daily practice; however, the use of such tools remains to be time-consuming.
Methods: Narrative review and results
Computer-assisted methods for the prediction of postoperative alignment consist of a three step analysis: identification of anatomical landmark, definition of alignment objectives, and simulation of surgery. Recently, complex rules for the prediction of alignment have been proposed. Even though this kind of work leads to more personalized objectives, the number of parameters involved renders it difficult for clinical use, stressing the importance of developing computer-assisted tools. The evolution of our current technology, including machine learning and other types of advanced algorithms, will provide powerful tools that could be useful in improving surgical outcomes and alignment prediction. These tools can combine different types of advanced technologies, such as image recognition and shape modeling, and using this technique, computer-assisted methods are able to predict spinal shape. The development of powerful computer-assisted methods involves the integration of several sources of information such as radiographic parameters (X-rays, MRI, CT scan, etc.), demographic information, and unusual non-osseous parameters (muscle quality, proprioception, gait analysis data). In using a larger set of data, these methods will aim to mimic what is actually done by spine surgeons, leading to real tailor-made solutions.
Integrating newer technology can change the current way of planning/simulating surgery. The use of powerful computer-assisted tools that are able to integrate several parameters and learn from experience can change the traditional way of selecting treatment pathways and counseling patients. However, there is still much work to be done to reach a desired level as noted in other orthopedic fields, such as hip surgery. Many of these tools already exist in non-medical fields and their adaptation to spine surgery is of considerable interest.
KeywordsSelf-learning computers Machine learning Surgical planning Sagittal alignment Spine surgery
Compliance with ethical standards
Conflict of interest
None of the authors has any potential conflict of interest.
- 1.Glassman SD, Bridwell K, Dimar JR, Horton W, Berven S, Schwab F (2005) The impact of positive sagittal balance in adult spinal deformity. Spine (Phila Pa 1976) 30(18):2024–2029. https://doi.org/10.1097/01.brs.0000179086.30449.96
- 8.Camargo FP, Cordeiro EN, Napoli MM (1986) Corrective osteotomy of the spine in ankylosing spondylitis. Experience with 66 cases. Clin Orthop Relat Res 208:157–167Google Scholar
- 11.Gupta M, Henry JK, Schwab F et al (2016) Dedicated spine measurement software quantifies key spino-pelvic parameters more reliably than traditional picture archiving and communication systems tools. Spine (Phila Pa 1976) 41(1):E22–E37. https://doi.org/10.1097/brs.0000000000001216 CrossRefGoogle Scholar
- 15.Smith JS, Bess S, Shaffrey CI et al (2012) Dynamic changes of the pelvis and spine are key to predicting postoperative sagittal alignment after pedicle subtraction osteotomy: a critical analysis of preoperative planning techniques. Spine (Phila Pa 1976) 37(10):845–853. https://doi.org/10.1097/brs.0b013e31823b0892 CrossRefGoogle Scholar
- 21.Yilgor C, Sogunmez N, Boissiere L et al (2017) Global alignment and proportion (GAP) score: development and validation of a new method of analyzing spinopelvic alignment to predict mechanical complications after adult spinal deformity surgery. J Bone Joint Surg Am 99:1661–1672. https://doi.org/10.2106/JBJS.16.01594 CrossRefPubMedGoogle Scholar