Search

We assessed whether the insurance type reflects a patient's quality of care after an anterior discectomy and fusion (ACDF) procedure by comparing differences in the postoperative complications, readmission rates, reoperation rates, lengths of hospital stay, and cost of treatment between patients with Medicare versus private insurance. Propensity score matching was used to match patient cohorts insured by Medicare and private insurance in the MarketScan Commercial Claims and Encounters Database (2007–2016). Age, sex, year of operation, geographic region, comorbidities, and operative factors were used to match cohorts of patients who had undergone an ACDF procedure. A total of 110,911 patients met the inclusion criteria. Of these patients, 97,543 patients (87.9%) were privately insured and 13,368 patients (12.1%) were insured by Medicare. The propensity score matching algorithm matched 7026 privately insured patients to 7026 Medicare patients. After matching, no significant differences were found in the 90-day postoperative complication rates, lengths of stay, or reoperation rates between the Medicare and privately insured cohorts. The Medicare group had had lower postoperative readmission rates for all time points: 30 days (1.8% vs. 4.6%; P < 0.001), 60 days (2.5% vs. 6.3%; P < 0.001), and 90 days (4.2% vs. 7.7%; P < 0.001). The median payment to physicians was significantly lower for the Medicare group ($3885 vs. $5601; P < 0.001). In the present study, propensity score matched patients covered by Medicare and private insurance who had undergone an ACDF procedure had had similar treatment outcomes. [ABSTRACT FROM AUTHOR]

Study Design: Retrospective cohort.Objective: Due to anterior cervical discectomy and fusion (ACDF) popularity, it is important to predict postoperative complications, unfavorable 90-day readmissions, and two-year reoperations to improve surgical decision-making, prognostication, and planning.Summary Of Background Data: Machine learning has been applied to predict postoperative complications for ACDF; however, studies were limited by sample size and model type. These studies achieved ≤0.70 area under the curve (AUC). Further approaches, not limited to ACDF, focused on specific complication types and resulted in AUC between 0.70 and 0.76.Materials and Methods: The IBM MarketScan Commercial Claims and Encounters Database and Medicare Supplement were queried from 2007 to 2016 to identify adult patients who underwent an ACDF procedure (N=176,816). Traditional machine learning algorithms, logistic regression, and support vector machines, were compared with deep neural networks to predict: 90-day postoperative complications, 90-day readmission, and two-year reoperation. We further generated random deep learning model architectures and trained them on the 90-day complication task to approximate an upper bound. Last, using deep learning, we investigated the importance of each input variable for the prediction of 90-day postoperative complications in ACDF.Results: For the prediction of 90-day complication, 90-day readmission, and two-year reoperation, the deep neural network-based models achieved AUC of 0.832, 0.713, and 0.671. Logistic regression achieved AUCs of 0.820, 0.712, and 0.671. Support vector machine approaches were significantly lower. The upper bound of deep learning performance was approximated as 0.832. Myelopathy, age, human immunodeficiency virus, previous myocardial infarctions, obesity, and documentary weakness were found to be the strongest variable to predict 90-day postoperative complications.Conclusions: The deep neural network may be used to predict complications for clinical applications after multicenter validation. The results suggest limited added knowledge exists in interactions between the input variables used for this task. Future work should identify novel variables to increase predictive power. [ABSTRACT FROM AUTHOR]