Christopher P Ames1, Justin S Smith2, Ferran Pellisé3, Michael Kelly4, Ahmet Alanay5, Emre Acaroğlu6, Francisco Javier Sánchez Pérez-Grueso7, Frank Kleinstück8, Ibrahim Obeid9, Alba Vila-Casademunt10, Christopher I Shaffrey2, Douglas Burton11, Virginie Lafage12, Frank Schwab12, Christopher I Shaffrey2, Shay Bess13, Miquel Serra-Burriel14. 1. Department of Neurosurgery, University of California San Francisco, San Francisco, California. 2. Department of Neurosurgery, University of Virginia Medical Center, Charlottesville, Virginia. 3. Spine Surgery Unit, Hospital Vall d'Hebron, Barcelona, Spain. 4. Department of Orthopaedic Surgery, Washington University, St Louis, Missouri. 5. Department of Orthopedics and Traumatology, Acibadem University, Istanbul, Turkey. 6. Ankara Spine Center, Ankara, Turkey. 7. Spine Surgery Unit, Hospital Universitario La Paz, Madrid, Spain. 8. Spine Center Division, Department of Orthopedics and Neurosurgery, Schulthess Klinik, Zurich, Switzerland. 9. Spine Surgery Unit, Bordeaux University Hospital, Bordeaux, France. 10. Vall d'Hebron Institute of Research, Barcelona, Spain. 11. Department of Orthopaedic Surgery, University of Kansas Medical Center, Kansas City, Kansas. 12. Department of Orthopaedic Surgery, Hospital for Special Surgery, New York, New York. 13. Denver International Spine Center, Presbyterian St. Luke's/Rocky Mountain Hospital for Children, Denver, Colorado. 14. Center for Research in Health and Economics, Universitat Pompeu Fabra, Barcelona, Spain.
Abstract
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.
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 ASDpatient types, procedures, and outcomes. METHODS: Two prospective cohorts were queried for surgical ASDpatients 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.
Authors: André Wirries; Florian Geiger; Ahmed Hammad; Martin Bäumlein; Julia Nadine Schmeller; Ingmar Blümcke; Samir Jabari Journal: Biomedicines Date: 2022-06-04
Authors: Ferran Pellisé; Alba Vila-Casademunt; Susana Núñez-Pereira; Sleiman Haddad; Justin S Smith; Michael P Kelly; Ahmet Alanay; Christopher Shaffrey; Javier Pizones; Çaglar Yilgor; Ibrahim Obeid; Douglas Burton; Frank Kleinstück; Tamas Fekete; Shay Bess; Munish Gupta; Markus Loibl; Eric O Klineberg; Francisco J Sánchez Pérez-Grueso; Miquel Serra-Burriel; Christopher P Ames Journal: Eur Spine J Date: 2022-03-28 Impact factor: 2.721
Authors: Alexander L Hornung; Christopher M Hornung; G Michael Mallow; J Nicolás Barajas; Augustus Rush; Arash J Sayari; Fabio Galbusera; Hans-Joachim Wilke; Matthew Colman; Frank M Phillips; Howard S An; Dino Samartzis Journal: Eur Spine J Date: 2022-03-27 Impact factor: 2.721
Authors: Jonathan J Rasouli; Jianning Shao; Sean Neifert; Wende N Gibbs; Ghaith Habboub; Michael P Steinmetz; Edward Benzel; Thomas E Mroz Journal: Global Spine J Date: 2020-04-01
Authors: Rushikesh S Joshi; Darryl Lau; Justin K Scheer; Miquel Serra-Burriel; Alba Vila-Casademunt; Shay Bess; Justin S Smith; Ferran Pellise; Christopher P Ames Journal: Spine Deform Date: 2021-05-18
Authors: Jamie R F Wilson; Jetan H Badhiwala; Fan Jiang; Jefferson R Wilson; Branko Kopjar; Alexander R Vaccaro; Michael G Fehlings Journal: J Clin Med Date: 2019-10-17 Impact factor: 4.241