Search

Study Design: Retrospective review of prospectively-collected, multicenter adult spinal deformity (ASD) databases.Objective: To apply artificial intelligence (AI)-based hierarchical clustering as a step toward a classification scheme that optimizes overall quality, value, and safety for ASD surgery.Summary Of Background Data: Prior ASD classifications have focused on radiographic parameters associated with patient reported outcomes. Recent work suggests there are many other impactful preoperative data points. However, the ability to segregate patient patterns manually based on hundreds of data points is beyond practical application for surgeons. Unsupervised machine-based clustering of patient types alongside surgical options may simplify analysis of ASD patient types, procedures, and outcomes.Methods: Two prospective cohorts were queried for surgical ASD patients with baseline, 1-year, and 2-year SRS-22/Oswestry Disability Index/SF-36v2 data. Two dendrograms were fitted, one with surgical features and one with patient characteristics. Both were built with Ward distances and optimized with the gap method. For each possible n patient cluster by m surgery, normalized 2-year improvement and major complication rates were computed.Results: Five hundred-seventy patients were included. Three optimal patient types were identified: young with coronal plane deformity (YC, n = 195), older with prior spine surgeries (ORev, n = 157), and older without prior spine surgeries (OPrim, n = 218). Osteotomy type, instrumentation and interbody fusion were combined to define four surgical clusters. The intersection of patient-based and surgery-based clusters yielded 12 subgroups, with major complication rates ranging from 0% to 51.8% and 2-year normalized improvement ranging from -0.1% for SF36v2 MCS in cluster [1,3] to 100.2% for SRS self-image score in cluster [2,1].Conclusion: Unsupervised hierarchical clustering can identify data patterns that may augment preoperative decision-making through construction of a 2-year risk-benefit grid. In addition to creating a novel AI-based ASD classification, pattern identification may facilitate treatment optimization by educating surgeons on which treatment patterns yield optimal improvement with lowest risk.Level Of Evidence: 4. [ABSTRACT FROM AUTHOR]

Evidence suggests that increasing age raises the risk for higher complications with traditional open deformity surgery. The decreased exposure related morbidity associated with minimally invasive surgery (MIS) has the potential to lower the complication profile in older surgical patients. To evaluate the impact of age on complications and reoperations. Prospective outcomes registry. A total of 142 patients. Complications and reoperations. Inclusion criteria included age ≥ 18 years, and at least one of the following criteria: coronal curve (CC) ≥ 20°, sagittal vertical axis (SVA) > 5 cm, pelvic tilt (PT) > 25°, or thoracic kyphosis (TK) > 60°. Complications (major/minor) and reoperations were collected. A total of 142 patients who underwent circumferential MIS surgery were divided into younger (≤65 yrs, N=45) and older (>65 yrs, N=97) groups. Chi-square and t-test analyses were performed. Mean age was 57 years (SD±10) in the younger and 73.7yrs (SD±4.8) in the older groups (p<0.001). There were no significant differences in gender (F:76% vs F:66%), BMI (28.2 vs 29.0), frailty (3.7 vs 3.3), interbody levels fused (3.0 vs 3.3), posterior levels fused (4.8 vs 5.6) between younger and older groups, respectively. CCI was significantly lower in the younger (1.64) vs older (2.4) group (p=0.014). Total complications did not differ between younger (48.9%, N=22) and older (47.4%, N=46) patients (p=0.8). Major complications occurred in 11.1% of younger and 7.2% of older patients (p=0.317). Minor complications occurred in 17.8% of younger and 18.6% of older patients (p=0.555). Both major and minor complications occurred in 11.1% of younger and 6.2% of older patients (p=0.242). Reoperations were significantly less in the younger (4.4%, N=2) compared to the older (16.5%, N=16) (p=0.035). Follow-up was 12.8 months in the younger and 12.5 months in the older group. Despite significantly more comorbidities, total complications were not higher in elderly patients undergoing MIS surgery. However, elderly patients were found to have a higher reoperation rate, with PJK and instrumentation failure/mal-positioning being the most frequent reasons. This abstract does not discuss or include any applicable devices or drugs. [ABSTRACT FROM AUTHOR]