Primary ArthroplastyClinical and Statistical Validation of a Probabilistic Prediction Tool of Total Knee Arthroplasty Outcome
Section snippets
Model Generation
A BBN was developed using a publicly accessible database created and maintained by the National Institutes of Health Osteoarthritis Initiative (OAI) (available at https://data-archive.nimh.nih.gov/oai/). The OAI is a multicenter, longitudinal, prospective observational study of knee OA based in the United States, recruiting from Brown University, Ohio State University, the University of Maryland/Johns Hopkins University joint center, and the University of Pittsburgh in Pennsylvania. Data
Consecutive Case Series Validation
For the consecutive case series cohort, the demographics and difference in pain scores preoperatively between the 2 groups are shown in Table 1, showing no difference between the 2 groups.
The use of the tool’s predictions during consultation did not significantly change the proportion of patients booked for TKA surgery. Without the use of the tool’s predictions, 20 patients (26.7%) were booked for surgery, and with use of the tool, 24 patients (32%) were booked for surgery (P = .44). However, a
Discussion
This study demonstrates validation of a shared decision-making tool in the prediction of outcome by demonstrating a moderately strong correlation between predicted and actual improvements in KOOS. Patients predicted at risk of not improving were found to be 19.3 times more likely to not meet the MCID. This study also validated clinical utility of tool by demonstrating a change in the characteristic preoperative KOOS pain scores of patients booked for surgery before and after introduction of the
Conclusion
In order to be useful clinically, a prediction tool has to provide outputs that are accurate and can be integrated easily with consultation workflows. Indications for TKA are complex, and selecting patients for surgery based on prediction of outcome alone may not be reasonable given the limitations of prediction tools. Instead, prediction tools should aim to communicate information to both patients and surgeons, highlight potentially modifiable risk factors, and enable a shared decision-making
Acknowledgments
The OAI is a public-private partnership comprised of 5 contracts (N01-AR-2-2258; N01-AR-2-2259; N01-AR-2-2260; N01-AR-2-2261; N01-AR-2-2262) funded by the National Institutes of Health, a branch of the Department of Health and Human Services, and conducted by the OAI Study Investigators. Private funding partners include Merck Research Laboratories; Novartis Pharmaceuticals Corporation, GlaxoSmithKline, and Pfizer, Inc Private sector funding for the OAI is managed by the Foundation for the
References (51)
- et al.
Polyethylene in knee arthroplasty: a review
J Clin Orthop Trauma
(2015) - et al.
Computer aided orthopaedic surgery: incremental shift or paradigm change?
Med Image Anal
(2016) - et al.
Acute postoperative pain at rest after hip and knee arthroplasty: severity, sensory qualities and impact on sleep
Orthop Traumatol Surg Res
(2011) - et al.
Psychological determinants of problematic outcomes following total knee arthroplasty
Pain
(2009) - et al.
The role of presurgical expectancies in predicting pain and function one year following total knee arthroplasty
Pain
(2011) - et al.
A new prediction model for patient satisfaction after total knee arthroplasty
J Arthroplasty
(2016) - et al.
DIAVAL, a Bayesian expert system for echocardiography
Artif Intell Med
(1997) - et al.
Exploiting causal functional relationships in Bayesian network modelling for personalised healthcare
Int J Approx Reason
(2014) - et al.
Influence of low back pain on total knee arthroplasty outcome
Knee
(2014) - et al.
Component rotational alignment in unexplained painful primary total knee arthroplasty
Knee
(2014)
A systematic review and meta-analysis of patient-specific instrumentation for improving alignment of the components in total knee replacement
Bone Joint J
Patient satisfaction after total knee arthroplasty: who is satisfied and who is not?
Clin Orthop Relat Res
What proportion of patients report long-term pain after total hip or knee replacement for osteoarthritis? A systematic review of prospective studies in unselected patients
BMJ Open
Effect of patient characteristics on reported outcomes after total knee replacement
Rheumatology
Predicting dissatisfaction following total knee replacement: a prospective study of 1217 patients
J Bone Joint Surg Br
Total knee replacement in patients with concomitant back pain results in a worse functional outcome and a lower rate of satisfaction
Bone Joint J
The role of pain and function in determining patient satisfaction after total knee replacement. Data from the National Joint Registry for England and Wales
J Bone Joint Surg Br
The effect of surgical factors on early patient-reported outcome measures (PROMS) following total knee replacement
J Bone Joint Surg Br
Predictors of outcomes of total knee replacement surgery
Rheumatology
Predicting total knee replacement pain: a prospective, observational study
Clin Orthop Relat Res
The role of preoperative self-efficacy in predicting outcome after total knee replacement
Musculoskelet Care
The John Insall Award: patient expectations affect satisfaction with total knee arthroplasty
Clin Orthop Relat Res
Selecting and optimising patients for total knee arthroplasty
Med J Aust
Development of explicit criteria for total knee replacement
Int J Technol Assess Health Care
Primary hip and knee replacement surgery: Ontario criteria for case selection and surgical priority
Qual Health Care
Cited by (23)
Instruments to assess appropriateness of hip and knee arthroplasty: a systematic review
2023, Osteoarthritis and CartilagePredictive Models for Clinical Outcomes in Total Knee Arthroplasty: A Systematic Analysis
2021, Arthroplasty TodayUsing machine learning to predict clinical outcomes after shoulder arthroplasty with a minimal feature set
2021, Journal of Shoulder and Elbow Surgery
One or more of the authors of this paper have disclosed potential or pertinent conflicts of interest, which may include receipt of payment, either direct or indirect, institutional support, or association with an entity in the biomedical field which may be perceived to have potential conflict of interest with this work. For full disclosure statements refer to https://doi.org/10.1016/j.arth.2019.06.007.