Role of Machine Learning in Management of Degenerative Spondylolisthesis

A Systematic Review

Sherif El-Daw, MD; Ahmad El-Tantawy, MD; Tarek Aly, MD; Mohamed Ramadan, MD


Curr Orthop Pract. 2021;32(3):302-308. 

In This Article

Materials and Methods

Ethical Review and Study Design

Instiutional review board approval was not required of this systematic review of previously published literature. Structured key questions were formulated as modified from the scheme developed at McMaster University:[21]

  1. Are machine learning tools helpful in diagnosing of the type of spondylolisthesis?

  2. Is conservative or surgical treatment more successful in patients with spondylolisthesis?

  3. Is decompression alone or with fusion with or without instrumentation better for treating spondylolisthesis?

  4. Is adding reduction of displaced vertebra to instrumentation with fusion more successful than instrumentation without reduction in patients with spondylolisthesis?

Data Collection

The following databases were searched to identify all relevant studies: PubMed, Medline (1966 to January 2020), Cinahl (1982 to January 2020), Allied and Complementary Medical Database (AMED) (1985 to January 2020), Cochrane Register of Controlled trials (1st quarter 2020), Embase, Elsevier clinical key, and Scopus. All possible studies were screened by title and abstract using a single or a combination of terms. Assessments of the references of published articles were also performed.

The criteria for inclusion in this study were studies that they were randomized, quasi-randomized, or controlled clinical trials, included patients with a confirmed diagnosis of degenerative spondylolisthesis that was based on radiographs and CT scans, and noted the use of artificial intelligence or machine learning and its applicable algorithms in the management of the condition. Articles with duplicate reports or articles of which full text could not be obtained were excluded.

The following terms were used for screening: "[(spondylolysis* OR spondylolysis*) AND spondylolisthesis*] AND [(machine learning) OR "artificial intelligence" (Mesh)] AND (spinal fusion* AND decompression) OR ["spinal fusion" (Mesh) OR "management" (Mesh)] AND "conservative" (Mesh)." All articles that were included were analyzed using the PRISMA checklist for evaluation.[22]