Innovations and New Technology in Spine Surgery

121.3K
views
93
authors
16
articles
Cover image for research topic "Innovations and New Technology in Spine Surgery"
Editors
3
Impact
Loading...
27,590 views
36 citations
Review
21 August 2020
The Role of Machine Learning in Spine Surgery: The Future Is Now
Michael Chang
3 more and 
Alexander R. Vaccaro

The recent influx of machine learning centered investigations in the spine surgery literature has led to increased enthusiasm as to the prospect of using artificial intelligence to create clinical decision support tools, optimize postoperative outcomes, and improve technologies used in the operating room. However, the methodology underlying machine learning in spine research is often overlooked as the subject matter is quite novel and may be foreign to practicing spine surgeons. Improper application of machine learning is a significant bioethics challenge, given the potential consequences of over- or underestimating the results of such studies for clinical decision-making processes. Proper peer review of these publications requires a baseline familiarity of the language associated with machine learning, and how it differs from classical statistical analyses. This narrative review first introduces the overall field of machine learning and its role in artificial intelligence, and defines basic terminology. In addition, common modalities for applying machine learning, including classification and regression decision trees, support vector machines, and artificial neural networks are examined in the context of examples gathered from the spine literature. Lastly, the ethical challenges associated with adapting machine learning for research related to patient care, as well as future perspectives on the potential use of machine learning in spine surgery, are discussed specifically.

17,665 views
87 citations

Introduction: Demineralized bone matrix (DBM) is a widely used bone graft in spinal fusion. Most commercial DBMs are composed of demineralized bone particles (~125–800 microns) suspended in a carrier that provides improved handling but dilutes the osteoinductive component. DBM fibers (DBF) provide improved osteoconductivity and do not require a carrier. It has been suggested that 100% DBF may offer improved performance over particulate-based DBMs with carrier.

Study Design: Seven commercially available DBM products were tested in an athymic rat posterolateral fusion model. There were four 100% DBFs, two DBFs containing a carrier, and one particulate-based DBM containing carrier.

Objective: The study objectives were to evaluate the in vivo performance: (1) compare fusion rate and fusion maturity of six commercially available DBFs and one particulate-based DBM, and (2) assess the effect of carrier on fusion outcomes for DBFs in a posterolateral fusion model.

Methods: The DBF/DBM products evaluated were: StrandTM Family, Propel® DBM Fibers, Vesuvius® Demineralized Fibers, Optium® DBM Putty, Grafton® DBF, Grafton Flex, and DBX® Putty. Single-level posterolateral fusion was performed in 69 athymic rats. Fusion was assessed bilaterally after 4 weeks by manual palpation, radiograph and CT for bridging bone. Fusion mass maturity was assessed with a CT maturity grading scale and by histology. Statistical analysis was performed using Fishers Exact Test for categorical data and Kruskal-Wallis Test for non-parametric data.

Results: Strand Family achieved 100% fusion (18/18) by manual palpation, radiographic and CT evaluation, significantly higher than Propel Fibers, Vesuvius Fibers, Optium Putty, and DBX Putty, and not statistically higher than Grafton DBF and Grafton Flex. Strand Family provided the highest fusion maturity, with CT maturity grade of 2.3/3.0 and 89% mature fusion rate. Fusion results suggest a detrimental effect of carrier on fusion performance.

Conclusions: There were large variations in fusion performance for seven commercially available DBM products in an established preclinical fusion model. There were even significant differences between different 100% DBF products, suggesting that composition alone does not guarantee in vivo performance. In the absence of definitive clinical evidence, surgeons should carefully consider available data in valid animal models when selecting demineralized allograft options.

14,258 views
24 citations
Recommended Research Topics