TY - JOUR
T1 - Can unsupervised cluster analysis identify patterns of complex adult spinal deformity with distinct perioperative outcomes?
AU - On behalf of The International Spine Study Group
AU - Lafage, Renaud
AU - Fourman, Mitchell S.
AU - Smith, Justin S.
AU - Bess, Shay
AU - Shaffrey, Christopher I.
AU - Kim, Han Jo
AU - Kebaish, Khaled M.
AU - Burton, Douglas C.
AU - Hostin, Richard
AU - Passias, Peter G.
AU - Protopsaltis, Themistocles S.
AU - Daniels, Alan H.
AU - Klineberg, Eric O.
AU - Gupta, Munish C.
AU - Kelly, Michael P.
AU - Lenke, Lawrence G.
AU - Schwab, Frank J.
AU - Lafage, Virginie
N1 - Funding Information:
as reimbursement for airfare/hotel; receiving reimbursement for airfare/hotel and grant support (monies to the institution) from the SRS; receiving grant support from the Setting Scoliosis Straight Foundation (monies to the institution); receiving a donation from the Evans Family as philanthropic research funding from a grateful patient/family; receiving a donation from the Fox Family Foundation as philanthropic research funding from a grateful patient; receiving reimbursement for airfare/hotel, grant support (monies to institution), and fellowship support (to institution) from AO Spine; being a paid consultant for and receiving royalties from Acuity Surgical; being a paid consultant to Abryx (monies donated to a charitable foundation); and receiving grant support from EOS Technology (monies to institution). Dr. Schwab reported being an executive committee member of the ISSG; being an uncompensated shareholder of VFT Solutions and SeaSpine; being a consultant for Medtronic, Zimmer Biomet, and Mainstay Medical; and receiving royalties from Medtronic, Zimmer Biomet, and Stryker. Dr. V. Lafage reported receiving grants from ISSG during the conduct of the study, and personal fees from Alphatec, Globus Medical, NuVasive, Johnson & Johnson, and Stryker outside the submitted work.
Funding Information:
Dr. Smith reported grants from DePuy Synthes/International Spine Study Group Foundation (ISSGF) during the conduct of the study; personal fees from Cerapedics, Carlsmed, ZimVie, NuVasive, and SeaSpine; grants from AO Spine, DePuy Synthes/
Funding Information:
ISSGF; and having stock ownership in NuVasive and Alphatec outside the submitted work. Dr. Bess reported grants from DePuy Synthes, NuVasive, K2M, and ISSGF during the conduct of the study; and grants from Medtronic, Globus, DePuy Synthes, K2M Stryker, Carlsmed, SI Bone, SeaSpine, Alphatec, ISSGF, and NuVasive outside the submitted work. Dr. Shaffrey reported grants from the ISSGF during the conduct of the study; and personal fees from NuVasive, Medtronic, SI Bone, and Proprio outside the submitted work. Dr. Burton reported grants from ISSGF outside the submitted work; DePuy research support; consulting fees from Globus and Blue Ocean Spine; and stock ownership in Progenerative Medical. Dr. Protopsaltis reported personal fees from Globus, NuVasive, Medtronic, and Altus; grants from Medtronic; and stock ownership in OnePoint Surgical outside the submitted work. Dr. Daniels reported grants from Medtronic and Orthofix, and personal fees from Stryker and Spineart outside the submitted work. Dr. Klineberg reported personal fees from DePuy Synthes, Stryker, AO Spine, SI Bone, Medtronic, and Agnovos; grants from AO Spine; and being the Fellowship Chair (Chair Elect) for AO Spine outside the submitted work. Dr. Gupta reported personal fees and nonfinancial support from DePuy; personal fees and nonfinancial support from Globus; personal fees from Medtronic, AO Spine, LSU Grand Rounds, and Wright State Grand Rounds; travel paid for training from Zimmer; stock ownership in Johnson & Johnson; and nonfinancial support from the SRS Board of Directors outside the submitted work. Dr. Kelly reported personal fees from Wolters Kluwer and nonfinancial support from AO Spine outside the submitted work. Dr. Lenke reported being a paid consultant to Medtronic (monies donated to a charitable foundation); receiving royalties from Broadwater
Funding Information:
The International Spine Study Group (ISSG) is funded through research grants from DePuy Synthes (current), NuVasive (current), K2M (current), Innovasis (past), Biomet (past), and individual donations.
Publisher Copyright:
©AANS 2023, except where prohibited by US copyright law.
PY - 2023/5
Y1 - 2023/5
N2 - OBJECTIVE The objective of this study was to use an unsupervised cluster approach to identify patterns of operative adult spinal deformity (ASD) and compare the perioperative outcomes of these groups. METHODS A multicenter data set included patients with complex surgical ASD, including those with severe deformities, significant surgical complexity, or advanced age who underwent a multilevel fusion. An unsupervised cluster analysis allowing for 10% outliers was used to identify different deformity patterns. The perioperative outcomes of these clusters were then compared using ANOVA, Kruskal-Wallis, and chi-square tests, with p values < 0.05 considered significant. RESULTS Two hundred eighty-six patients were classified into four clusters of deformity patterns: hyper-thoracic kyphosis (hyper-TK), severe coronal, severe sagittal, and moderate sagittal. Hyper-TK patients had the lowest disability (mean Oswestry Disability Index [ODI] 32.9 ± 17.1) and pain scores (median numeric rating scale [NRS] back score 6, leg score 1). The severe coronal cluster had moderate functional impairment (mean physical component score 34.4 ± 12.3) and pain (median NRS back score 7, leg score 4) scores. The severe sagittal cluster had the highest levels of disability (mean ODI 49.3 ± 15.6) and low appearance scores (mean 2.3 ± 0.7). The moderate cluster (mean 68.8 ± 7.8 years) had the highest pain interference subscores on the Patient-Reported Outcomes Measurement Information System (mean 65.2 ± 5.8). Overall 30-day adverse events were equivalent among the four groups. Fusion to the pelvis was most common in the moderate sagittal (89.4%) and severe sagittal (97.5%) clusters. The severe coronal cluster had more osteotomies per case (median 11, IQR 6.5-14) and a higher rate of 30-day implant-related complications (5.5%). The severe sagittal and hyper-TK clusters had more three-column osteotomies (43% and 32.3%, respectively). Hyper-TK patients had shorter hospital stays. CONCLUSIONS This cohort of patients with complex ASD surgeries contained four natural clusters of deformity, each with distinct perioperative outcomes.
AB - OBJECTIVE The objective of this study was to use an unsupervised cluster approach to identify patterns of operative adult spinal deformity (ASD) and compare the perioperative outcomes of these groups. METHODS A multicenter data set included patients with complex surgical ASD, including those with severe deformities, significant surgical complexity, or advanced age who underwent a multilevel fusion. An unsupervised cluster analysis allowing for 10% outliers was used to identify different deformity patterns. The perioperative outcomes of these clusters were then compared using ANOVA, Kruskal-Wallis, and chi-square tests, with p values < 0.05 considered significant. RESULTS Two hundred eighty-six patients were classified into four clusters of deformity patterns: hyper-thoracic kyphosis (hyper-TK), severe coronal, severe sagittal, and moderate sagittal. Hyper-TK patients had the lowest disability (mean Oswestry Disability Index [ODI] 32.9 ± 17.1) and pain scores (median numeric rating scale [NRS] back score 6, leg score 1). The severe coronal cluster had moderate functional impairment (mean physical component score 34.4 ± 12.3) and pain (median NRS back score 7, leg score 4) scores. The severe sagittal cluster had the highest levels of disability (mean ODI 49.3 ± 15.6) and low appearance scores (mean 2.3 ± 0.7). The moderate cluster (mean 68.8 ± 7.8 years) had the highest pain interference subscores on the Patient-Reported Outcomes Measurement Information System (mean 65.2 ± 5.8). Overall 30-day adverse events were equivalent among the four groups. Fusion to the pelvis was most common in the moderate sagittal (89.4%) and severe sagittal (97.5%) clusters. The severe coronal cluster had more osteotomies per case (median 11, IQR 6.5-14) and a higher rate of 30-day implant-related complications (5.5%). The severe sagittal and hyper-TK clusters had more three-column osteotomies (43% and 32.3%, respectively). Hyper-TK patients had shorter hospital stays. CONCLUSIONS This cohort of patients with complex ASD surgeries contained four natural clusters of deformity, each with distinct perioperative outcomes.
KW - adult spine deformity
KW - artificial intelligence
KW - cluster analysis
KW - multicenter database
KW - perioperative outcomes
UR - http://www.scopus.com/inward/record.url?scp=85158894813&partnerID=8YFLogxK
U2 - 10.3171/2023.1.SPINE221095
DO - 10.3171/2023.1.SPINE221095
M3 - Article
C2 - 36806173
AN - SCOPUS:85158894813
SN - 1547-5654
VL - 38
SP - 547
EP - 557
JO - Journal of Neurosurgery: Spine
JF - Journal of Neurosurgery: Spine
IS - 5
ER -