Improvement in internal rotation (IR) after anatomic (aTSA) and reverse (rTSA) total
shoulder arthroplasty is difficult to predict, with rTSA patients experiencing greater
variability and more limited IR improvements than aTSA patients. The purpose of this
study is to quantify and compare the IR score for aTSA and rTSA patients and create
supervised machine learning that predicts IR after aTSA and rTSA at multiple postoperative
Clinical data from 2,270 aTSA and 4,198 rTSA patients were analyzed using 3 supervised
machine learning techniques to create predictive models for internal rotation as measured
by the IR score at 6 postoperative timepoints. Predictions were performed using the
full input feature set and 2 minimal input feature sets. The mean absolute error (MAE)
quantified the difference between actual and predicted IR scores for each model at
each timepoint. The predictive accuracy of the XGBoost algorithm was also quantified
by its ability to distinguish which patients would achieve clinical improvement greater
than the minimal clinically important difference (MCID) and substantial clinical benefit
(SCB) patient satisfaction thresholds for IR score at 2-3 years after surgery.
RTSA patients had significantly lower mean IR scores and significantly less mean IR
score improvement than aTSA patients at each postoperative timepoint. Both aTSA and
rTSA patients experienced significant improvements in their ability to perform ADLs;
however, aTSA patients were significantly more likely to perform these ADLs. Using
a minimal feature set of preoperative inputs, our machine learning algorithms had
equivalent accuracy when predicting IR score for both aTSA (0.92-1.18 MAE) and rTSA
(1.03-1.25 MAE) from 3 months to >5 years after surgery. Furthermore, these predictive
algorithms identified with 90% accuracy for aTSA and 85% accuracy for rTSA which patients
will achieve MCID IR score improvement and predicted with 85% accuracy for aTSA patients
and 77% accuracy for rTSA which patients will achieve SCB IR score improvement at
2-3 years after surgery.
Our machine learning study demonstrates that active internal rotation can be accurately
predicted after aTSA and rTSA at multiple postoperative timepoints using a minimal
feature set of preoperative inputs. These predictive algorithms accurately identified
which patients will, and will not achieve clinical improvement in IR score that exceeds
the MCID and SCB patient satisfaction thresholds.
Received in revised form:
Publication stageIn Press Accepted Manuscript
Funding: Data collection was funded by Exactech, Inc. (Gainesville, FL, USA).
Conflicts of Interest: Vikas Kumar, Christine Allen, and Steven Overman are employed by Ken Sci, Inc.
Ankur Teredesai is employed by the University of Washington
Bradley Schoch, William Aibinder, Moby Parsons, Jonathan Watling, Jiawei Kevin Ko, Bruno Gobbato, Thomas Throckmorton, and Howard Routman are consultants for Exactech, Inc.
Christopher Roche is employed by Exactech, Inc.
All data was acquired in an IRB approved study and was carried out in accordance with
relevant regulations of the US Health Insurance Portability and Accountability Act
Level of Evidence: Level III; Retrospective Cohort Comparison; Prognosis Study
© 2021 Published by Elsevier Inc. on behalf of Journal of Shoulder and Elbow Surgery Board of Trustees.