Purpose
To develop a machine learning algorithm to predict total charges after ambulatory
hip arthroscopy and create a risk-adjusted payment model based on patient comorbidities.
Methods
A retrospective review of the New York State Ambulatory Surgery and Services database
was performed to identify patients who underwent elective hip arthroscopy between
2015 and 2016. Features included in initial models consisted of patient characteristics,
medical comorbidities, and procedure-specific variables. Models were generated to
predict total charges using 5 algorithms. Model performance was assessed by the root-mean-square
error, root-mean-square logarithmic error, and coefficient of determination. Global
variable importance and partial dependence curves were constructed to show the impact
of each input feature on total charges. For performance benchmarking, the best candidate
model was compared with a multivariate linear regression using the same input features.
Results
A total of 5,121 patients were included. The median cost after hip arthroscopy was
$19,720 (interquartile range, $12,399-$26,439). The gradient-boosted ensemble model
showed the best performance (root-mean-square error, $3,800 [95% confidence interval,
$3,700-$3,900]; logarithmic root-mean-square error, 0.249 [95% confidence interval,
0.24-0.26]; R2 = 0.73). Major cost drivers included total hours in facility less than 12 or more
than 15, longer procedure time, performance of a labral repair, age younger than 30
years, Elixhauser Comorbidity Index (ECI) of 1 or greater, African American race,
residence in extreme urban and rural areas, and higher household and neighborhood
income.
Conclusions
The gradient-boosted ensemble model effectively predicted total charges after hip
arthroscopy. Few modifiable variables were identified other than anesthesia type;
nonmodifiable drivers of total charges included duration of care less than 12 hours
or more than 15 hours, operating room time more than 100 minutes, age younger than
30 years, performance of a labral repair, and ECI greater than 0. Stratification of
patients based on the ECI highlighted the increased financial risk borne by physicians
via flat reimbursement schedules given variable degrees of comorbidities.
Level of Evidence
Level III, retrospective cohort study.
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to ArthroscopyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Effects of arthroscopy for femoroacetabular impingement syndrome on quality of life and economic outcomes.Am J Sports Med. 2018; 46: 1205-1213
- Does primary hip arthroscopy result in improved clinical outcomes?: 2-Year clinical follow-up on a mixed group of 738 consecutive primary hip arthroscopies performed at a high-volume referral center.Am J Sports Med. 2016; 44: 74-82
- Crossing the quality chasm: A new health system for the 21st century.National Academies Press, Washington, DC2001
- Value-based healthcare: The politics of value-based care and its impact on orthopaedic surgery.Clin Orthop Relat Res. 2021; 479: 674-678
- Construct validation of machine learning in the prediction of short-term postoperative complications following total shoulder arthroplasty.J Shoulder Elbow Surg. 2019; 28: e410-e421
- Machine learning algorithms predict functional improvement after hip arthroscopy for femoroacetabular impingement syndrome in athletes.J Bone Joint Surg Am. 2021; 103: 1055-1062
- Machine learning modeling for predicting hospital readmission following lumbar laminectomy.J Neurosurg Spine. 2018; 30: 344-352
- Machine learning ensemble models predict total charges and drivers of cost for transsphenoidal surgery for pituitary tumor.J Neurosurg. 2018; 131: 507-516
- The value of artificial neural networks for predicting length of stay, discharge disposition, and inpatient costs after anatomic and reverse shoulder arthroplasty.J Shoulder Elbow Surg. 2020; 29: 2385-2394
- Guidelines for developing and reporting machine learning predictive models in biomedical research: A multidisciplinary view.J Med Internet Res. 2016; 18: e323
- Transparent reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): The TRIPOD Statement.Br J Surg. 2015; 102: 148-158
- The primary cost drivers of arthroscopic rotator cuff repair surgery: A cost-minimization analysis of 40,618 cases.J Shoulder Elbow Surg. 2019; 28: 1977-1982
- Cost drivers associated with anterior shoulder stabilization surgery.Orthop J Sports Med. 2020; 8 (2325967120926465)
- What are the primary cost drivers of anterior cruciate ligament reconstruction in the United States? A cost-minimization analysis of 14,713 patients.Arthroscopy. 2019; 35: 1576-1581
- Consumer Price Index archived news releases. 2020. US Bureau of Labor Statistics, Washington, DC2021
- A modification of the Elixhauser comorbidity measures into a point system for hospital death using administrative data.Med Care. 2009; 47: 626-633
- Infection rates in arthroscopic versus open rotator cuff repair.Orthop J Sports Med. 2017; 5 (2325967117715416)
- MissForest—Non-parametric missing value imputation for mixed-type data.Bioinformatics (Oxford, England). 2012; 28: 112-118
- Missing the missing values: The ugly duckling of fairness in machine learning.Int J Intell Syst. 2021; 36: 3217-3258
- Bias arising from missing data in predictive models.J Clin Epidemiol. 2006; 59: 1115-1123
- Missing data in prediction research: A five-step approach for multiple imputation, illustrated in the CENTER-TBI study.J Neurotrauma. 2021; 38: 1842-1857
- Application of machine learning for predicting clinically meaningful outcome after arthroscopic femoroacetabular impingement surgery.Am J Sports Med. 2020; 48: 415-423
- Using recursive feature elimination in random forest to account for correlated variables in high dimensional data.BMC Genet. 2018; 19: 65
- Prognosis Research Strategy (PROGRESS) 3: Prognostic model research.PLoS Med. 2013; 10e1001381
- Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation.Water Resour Res. 1999; 35: 233-241
- Improving classification performance with discretization on biomedical datasets.AMIA Annu Symp Proc. 2008; 2008: 445-449
- Study of discretization methods in classification.in: 2017 9th International Conference on Knowledge and Smart Technology (KST). IEEE, Piscataway, NJ2017: 50-55
- Hospital physicians' views on discharge and readmission processes: A qualitative study from Norway.BMJ Open. 2019; 9e031297
- Trends in hip arthroscopic labral repair: An American Board of Orthopaedic Surgery database study.Arthroscopy. 2019; 35: 1413-1419
- A shift in hip arthroscopy use by patient age and surgeon volume: A New York State-based population analysis 2004 to 2016.Arthroscopy. 2019; 35: 2847-2854.e2841
- The economic implications of a multimodal analgesic regimen for patients undergoing major orthopedic surgery: A comparative study of direct costs.Reg Anesth Pain Med. 2009; 34: 301-307
- Examining the role of perioperative nerve blocks in hip arthroscopy: A systematic review.Arthroscopy. 2016; 32: 704-715.e701
- Orthopaedic shoulder surgery in the ambulatory surgical center: Safety and outcomes.Arthroscopy. 2019; 35: 2545-2550.e2541
- Decline in racial disparities for United States hospital admissions after anterior cruciate ligament reconstruction from 2007 to 2015.Orthop J Sports Med. 2020; 8 (2325967120964473)
- National utilization and inpatient safety measures of lumbar spinal fusion methods by race/ethnicity.Spine J. 2021; 21: 785-794
- Worsening racial disparities in patients undergoing anatomic and reverse total shoulder arthroplasty in the United States.J Shoulder Elbow Surg. 2021; 30: 1844-1850
- The "July effect" in total shoulder arthroplasty.J Shoulder Elbow Surg. 2017; 26: e59-e64
- Resident involvement in arthroscopic knee surgery is not associated with increased short-term risk to patients.Orthop J Sports Med. 2020; 8 (2325967120967460)
- The July effect for total joint arthroplasty procedures.Orthopedics. 2020; 43: e543-e548
- Comparison of hospital charge prediction models for gastric cancer patients: Neural network vs. decision tree models.BMC Health Serv Res. 2009; 9: 161
- Machine learning and artificial intelligence: Definitions, applications, and future directions.Curr Rev Musculoskelet Med. 2020; 13: 69-76
Seamless integration. Vol 2021. PCMag Encyclopedia https://www.pcmag.com/encyclopedia/term/seamless-integration. Accessed May 20, 2022.
- Integration of automated predictive analytics into electronic health records: Can spine surgery applications lead the way using SMART on FHIR and CDS Hooks?.Semin Spine Surg. 2021; 33: 100870
- A comparison of multiple imputation methods for missing data in longitudinal studies.BMC Med Res Methodol. 2018; 18 (168-168)
- Multiple imputation for missing data in epidemiological and clinical research: Potential and pitfalls.BMJ. 2009; 338: b2393
- Using the outcome for imputation of missing predictor values was preferred.J Clin Epidemiol. 2006; 59: 1092-1101
- Missing data and multiple imputation in clinical epidemiological research.Clin Epidemiol. 2017; 9: 157-166
- Machine learning for prediction of sustained opioid prescription after anterior cervical discectomy and fusion.Spine J. 2019; 19: 976-983
- Model evaluation, model selection, and algorithm selection in machine learning [arXiv preprint].(Available at) (Accessed May 20, 2022)
- Ensemble methods in machine learning.in: International workshop on multiple classifier systems. Springer, New York2000: 1-15
- Model checking in multiple imputation: An overview and case study.Emerg Themes Epidemiol. 2017; 14: 8
- Applied predictive modeling.Springer, New York2013
Article info
Publication history
Published online: December 15, 2021
Accepted:
December 4,
2021
Received:
June 8,
2021
Footnotes
See commentary on page 2217
The authors report the following potential conflicts of interest or sources of funding: Support was provided by the Foderaro-Quattrone Musculoskeletal-Orthopaedic Surgery Research Innovation Fund. A.P. receives hospitality payments from Stryker, outside the submitted work. B.F. receives research support from Arthrex, Smith & Nephew, and Stryker; receives publishing royalties and financial or material support from Elsevier; owns stock or stock options in Jace Medical; is a paid consultant for Stryker; receives education support from Medwest Associates; and receives food and beverage support from DePuy Synthes Sales, outside the submitted work. B.A.L. receives intellectual property royalties from Arthrex; is a paid consultant for Arthrex and Smith & Nephew; owns stock or stock options in COVR Medical; and is on the editorial or governing board of Journal of Knee Surgery, Knee Surgery, Sports Traumatology, Arthroscopy, and Orthopedics Today, outside the submitted work A.J.K. receives research support from Aesculap/B. Braun, Arthritis Foundation, Ceterix, Histogenics, Exactech, and Gemini Medical; is on the editorial or governing board of American Journal of Sports Medicine; is a paid consultant for Arthrex, Musculoskeletal Transplant Foundation, Vericel, DePuy, JRF, and Responsive Arthroscopy; receives travel/lodging support from Arthrex and Musculoskeletal Transplant Foundation; is a paid speaker for Arthrex and Musculoskeletal Transplant Foundation; and is a board or committee member of International Cartilage Repair Society, International Society of Arthroscopy, Knee Surgery and Orthopaedic Sports Medicine, Minnesota Orthopaedic Society, and Musculoskeletal Transplant Foundation, outside the submitted work. Full ICMJE author disclosure forms are available for this article online, as supplementary material.
Identification
Copyright
© 2022 Published by Elsevier on behalf of the Arthroscopy Association of North America
