Johnson, Sarah E.

Study design. Retrospective observational study of consecutive patients. Objective. The purpose of the study is to determine if a surgeon’s qualitative assessment of bone intraoperatively correlates with radiologic parameters of bone strength. Summary of Background Data. Preoperative radiologic assessment of bone can include modalities such as computed tomography (CT) Hounsfield units (HUs), dual-energy x-ray absorptiometry (DXA) bone mineral density with trabecular bone score (TBS) and magnetic resonance imaging vertebral bone quality (VBQ). Quantitative analysis of bone with screw insertional torque and pull-out strength measurement has been performed in cadaveric models and has been correlated to these radiologic parameters. However, these quantitative measurements are not routinely available for use in surgery. Surgeons anecdotally judge bone strength, but the fidelity of the intraoperative judgment has not been investigated. Methods. All adult patients undergoing instrumented posterior thoracolumbar spine fusion by one of seven surgeons at a single center over a 3-month period were included. Surgeons evaluated the strength of bone based on intraoperative feedback and graded each patient’s bone on a 5-point Likert scale. Two independent reviewers measured preoperative CT HUs and magnetic resonance imaging VBQ. Bone mineral density, lowest T-score, and TBS were extracted from DXA within 2 years of surgery. Results. Eighty-nine patients were enrolled and 16, 28, 31, 13, and 1 patients had Likert grade 1 (strongest bone), 2, 3, 4, and 5 (weakest bone), respectively. The surgeon assessment of bone correlated with VBQ (τ=0.15, P=0.07), CT HU (τ=−0.31, P<0.01), lowest DXA T-score (τ=−0.47, P<0.01), and TBS (τ=−0.23, P=0.06). Conclusion. Spine surgeons’ qualitative intraoperative assessment of bone correlates with preoperative radiologic parameters, particularly in posterior thoracolumbar surgeries. This information is valuable to surgeons as this supports the idea that decisions based on feel in surgery have a statistical foundation.

Spinal cord tumors constitute a diverse group of rare neoplasms associated with significant mortality and morbidity that pose unique clinical and surgical challenges. Diagnostic accuracy and outcome prediction are critical for informed decision making and can promote personalized medicine and facilitate optimal patient management. Machine learning has the ability to analyze and combine vast amounts of data, allowing the identification of patterns and the establishment of clinical associations, which can ultimately enhance patient care. Although artificial intelligence techniques have been explored in other areas of spine surgery, such as spinal deformity surgery, precise machine learning models for spinal tumors are lagging behind. Current applications of machine learning in spinal cord tumors include algorithms that improve diagnostic precision by predicting genetic, molecular, and histopathological profiles. Furthermore, artificial intelligence-based systems can assist surgeons with preoperative planning and surgical resection, potentially reducing the risk of recurrence and consequently improving clinical outcomes. Machine learning algorithms promote personalized medicine by enabling prognostication and risk stratification based on accurate predictions of treatment response, survival, and postoperative complications. Despite their promising potential, machine learning models require extensive validation processes and quality assessments to ensure safe and effective translation to clinical practice.