PMID- 29191094 OWN - NLM STAT- MEDLINE DCOM- 20180803 LR - 20180803 IS - 1092-0684 (Electronic) IS - 1092-0684 (Linking) VI - 43 IP - 6 DP - 2017 Dec TI - Potential of predictive computer models for preoperative patient selection to enhance overall quality-adjusted life years gained at 2-year follow-up: a simulation in 234 patients with adult spinal deformity. PG - E2 LID - 10.3171/2017.9.FOCUS17494 [doi] AB - OBJECTIVE Patients with adult spinal deformity (ASD) experience significant quality of life improvements after surgery. Treatment, however, is expensive and complication rates are high. Predictive analytics has the potential to use many variables to make accurate predictions in large data sets. A validated minimum clinically important difference (MCID) model has the potential to assist in patient selection, thereby improving outcomes and, potentially, cost-effectiveness. METHODS The present study was a retrospective analysis of a multiinstitutional database of patients with ASD. Inclusion criteria were as follows: age >/= 18 years, radiographic evidence of ASD, 2-year follow-up, and preoperative Oswestry Disability Index (ODI) > 15. Forty-six variables were used for model training: demographic data, radiographic parameters, surgical variables, and results on the health-related quality of life questionnaire. Patients were grouped as reaching a 2-year ODI MCID (+MCID) or not (-MCID). An ensemble of 5 different bootstrapped decision trees was constructed using the C5.0 algorithm. Internal validation was performed via 70:30 data split for training/testing. Model accuracy and area under the curve (AUC) were calculated. The mean quality-adjusted life years (QALYs) and QALYs gained at 2 years were calculated and discounted at 3.5% per year. The QALYs were compared between patients in the +MCID and -MCID groups. RESULTS A total of 234 patients met inclusion criteria (+MCID 129, -MCID 105). Sixty-nine patients (29.5%) were included for model testing. Predicted versus actual results were 50 versus 40 for +MCID and 19 versus 29 for -MCID (i.e., 10 patients were misclassified). Model accuracy was 85.5%, with 0.96 AUC. Predicted results showed that patients in the +MCID group had significantly greater 2-year mean QALYs (p = 0.0057) and QALYs gained (p = 0.0002). CONCLUSIONS A successful model with 85.5% accuracy and 0.96 AUC was constructed to predict which patients would reach ODI MCID. The patients in the +MCID group had significantly higher mean 2-year QALYs and QALYs gained. This study provides proof of concept for using predictive modeling techniques to optimize patient selection in complex spine surgery. FAU - Oh, Taemin AU - Oh T AD - Department of Neurological Surgery, University of California, San Francisco, California. FAU - Scheer, Justin K AU - Scheer JK AD - Department of Neurosurgery, University of Illinois at Chicago, Illinois. FAU - Smith, Justin S AU - Smith JS AD - Department of Neurosurgery, University of Virginia Health System, Charlottesville, Virginia. FAU - Hostin, Richard AU - Hostin R AD - Department of Orthopaedic Surgery, Baylor Scoliosis Center, Plano. FAU - Robinson, Chessie AU - Robinson C AD - Baylor Scott & White Health, Center for Clinical Effectiveness, Dallas, Texas. FAU - Gum, Jeffrey L AU - Gum JL AD - Norton Leatherman Spine Center, Louisville, Kentucky. FAU - Schwab, Frank AU - Schwab F AD - Department of Orthopaedic Surgery, New York University Hospital for Joint Diseases, New York, New York. FAU - Hart, Robert A AU - Hart RA AD - Department of Orthopaedic Surgery, Oregon Health & Science University, Portland, Oregon. FAU - Lafage, Virginie AU - Lafage V AD - Department of Orthopaedic Surgery, New York University Hospital for Joint Diseases, New York, New York. FAU - Burton, Douglas C AU - Burton DC AD - Department of Orthopaedic Surgery, University of Kansas Medical Center, Kansas City, Kansas. FAU - Bess, Shay AU - Bess S AD - Rocky Mountain Hospital for Children, Denver, Colorado; and. FAU - Protopsaltis, Themistocles AU - Protopsaltis T AD - Department of Orthopaedic Surgery, New York University Hospital for Joint Diseases, New York, New York. FAU - Klineberg, Eric O AU - Klineberg EO AD - Department of Orthopaedic Surgery, University of California, Davis, California. FAU - Shaffrey, Christopher I AU - Shaffrey CI AD - Department of Neurosurgery, University of Virginia Health System, Charlottesville, Virginia. FAU - Ames, Christopher P AU - Ames CP AD - Department of Neurological Surgery, University of California, San Francisco, California. CN - International Spine Study Group LA - eng PT - Journal Article PL - United States TA - Neurosurg Focus JT - Neurosurgical focus JID - 100896471 SB - IM MH - Adult MH - Aged MH - *Computer Simulation MH - Congenital Abnormalities/*surgery MH - Disability Evaluation MH - Female MH - Follow-Up Studies MH - Humans MH - Male MH - Middle Aged MH - Patient Selection MH - Quality of Life MH - *Quality-Adjusted Life Years MH - Retrospective Studies MH - Scoliosis/diagnosis/*surgery MH - Spinal Fusion/methods MH - Treatment Outcome OTO - NOTNLM OT - ASD = adult spinal deformity OT - AUC = area under the curve OT - BMI = body mass index OT - HRQOL = health-related QOL OT - IBF = interbody fusion OT - LIV = lowermost instrumented vertebra OT - MCID = minimum clinically important difference OT - NRS = numerical rating scale OT - ODI = Oswestry Disability Index OT - Oswestry Disability Index OT - QALY = quality-adjusted life year OT - QOL = quality of life OT - SF-36 = 36-Item Short-Form Health Survey OT - SPO = Smith-Petersen osteotomy OT - SRS = Scoliosis Research Society OT - UIV = uppermost instrumented vertebra OT - minimum clinically important difference OT - predictive modeling OT - quality-adjusted life year EDAT- 2017/12/02 06:00 MHDA- 2018/08/04 06:00 CRDT- 2017/12/02 06:00 PHST- 2017/12/02 06:00 [entrez] PHST- 2017/12/02 06:00 [pubmed] PHST- 2018/08/04 06:00 [medline] AID - 10.3171/2017.9.FOCUS17494 [doi] PST - ppublish SO - Neurosurg Focus. 2017 Dec;43(6):E2. doi: 10.3171/2017.9.FOCUS17494.