A Multicenter Radiographic Evaluation of the Rates of Preoperative and Postoperative Malalignment in Degenerative Spinal Fusions.

By London Spine

A Multicenter Radiographic Evaluation of the Rates of Preoperative and Postoperative Malalignment in Degenerative Spinal Fusions.

Spine (Phila Pa 1976). 2017 Nov 20;:

Authors: Leveque JA, Segebarth B, Schroerlucke SR, Khanna N, Pollina J, Youssef JA, Tohmeh AG, Uribe JS

Abstract
STUDY DESIGN: Multicenter, retrospective, IRB-approved study at 18 institutions in the United States with 24 treating investigators.
OBJECTIVE: This study was designed to retrospectively assess the prevalence of spinopelvic malalignment in patients who underwent one- or two-level lumbar fusions for degenerative (non-deformity) indications and to assess the incidence of malalignment following fusion surgery as well as the rate of alignment preservation and/or correction in this population.
SUMMARY OF BACKGROUND DATA: Spinopelvic malalignment following lumbar fusion has been associated with lower postoperative health-related quality of life and elevated risk of adjacent segment failure. The prevalence of spinopelvic malalignment in short-segment degenerative lumbar fusion procedures from a large sample of patients is heretofore unreported and may lead to an under-appreciation of these factors in surgical planning and ultimate preservation or correction of alignment.
METHODS: Lateral preoperative and postoperative lumbar radiographs were retrospectively acquired from 578 one- or two-level lumbar fusion patients and newly measured for LL, PI, and pelvic tilt (PT). Patients were categorized at pre-op and post-op time points as aligned if PI-LL < 10° or malaligned if PI-LL≥10°. Patients were grouped into categories based on their alignment progression from pre- to postoperative, with preserved (aligned to aligned), restored (malaligned to aligned), not corrected (malaligned to malaligned), and worsened (aligned to malaligned) designations.
RESULTS: Preoperatively, 173 (30%) patients exhibited malalignment. Postoperatively, 161 (28%) of patients were malaligned. Alignment was preserved in 63%, restored in 9%, not corrected in 21%, and worsened in 7% of patients.
CONCLUSION: This is the first multicenter study to evaluate the preoperative prevalence and postoperative incidence of spinopelvic malalignment in a large series of short-segment degenerative lumbar fusions, finding over 25% of patients out of alignment at both time points, suggesting that alignment preservation/restoration considerations should be incorporated into the decision-making of even degenerative lumbar spinal fusions.
LEVEL OF EVIDENCE: 3.

PMID: 29189645 [PubMed – as supplied by publisher]

Examining the Ability of Artificial Neural Networks Machine Learning Models to Accurately Predict Complications Following Posterior Lumbar Spine Fusion.

By London Spine
Related Articles

Examining the Ability of Artificial Neural Networks Machine Learning Models to Accurately Predict Complications Following Posterior Lumbar Spine Fusion.

Spine (Phila Pa 1976). 2017 Oct 09;:

Authors: Kim JS, Merrill RK, Arvind V, Kaji D, Pasik SD, Nwachukwu CC, Vargas L, Osman NS, Oermann EK, Caridi JM, Cho SK

Abstract
STUDY DESIGN: Cross-sectional database study.
OBJECTIVE: To train and validate machine learning models to identify risk factors for complications following posterior lumbar spine fusion.
SUMMARY OF BACKGROUND DATA: Machine learning models such as artificial neural networks (ANNs) are valuable tools for analyzing and interpreting large and complex datasets. ANNs have yet to be used for risk factor analysis in orthopedic surgery.
METHODS: The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database was queried for patients who underwent posterior lumbar spine fusion. This query returned 22,629 patients, 70% of whom were used to train our models, and 30% were used to evaluate the models. The predictive variables used included sex, age, ethnicity, diabetes, smoking, steroid use, coagulopathy, functional status, American society for anesthesiology (ASA) class ≥ 3, body mass index (BMI), pulmonary comorbidities, and cardiac comorbidities. The models were used to predict cardiac complications, wound complications, venous thromboembolism (VTE), and mortality. Using ASA class as a benchmark for prediction, area under receiver operating curves (AUC) was used to determine the accuracy of our machine learning models.
RESULTS: Based on AUC values, ANN and LR both outperformed ASA class for predicting all four types of complications. ANN was the most accurate for predicting cardiac complications, and LR was most accurate for predicting wound complications, VTE, and mortality, though ANN and LR had comparable AUC values for predicting all types of complications. ANN had greater sensitivity than LR for detecting wound complications and mortality.
CONCLUSIONS: Machine learning in the form of logistic regression and artificial neural networks were more accurate than benchmark ASA scores for identifying risk factors of developing complications following posterior lumbar spine fusion, suggesting they are potentially great tools for risk factor analysis in spine surgery.
LEVEL OF EVIDENCE: 3.

PMID: 29016439 [PubMed – as supplied by publisher]