PMID- 34813889
OWN - NLM
STAT- MEDLINE
DCOM- 20220425
LR  - 20220425
IS  - 1532-6500 (Electronic)
IS  - 1058-2746 (Linking)
VI  - 31
IP  - 5
DP  - 2022 May
TI  - Using machine learning to predict internal rotation after anatomic and reverse 
      total shoulder arthroplasty.
PG  - e234-e245
LID - S1058-2746(21)00811-9 [pii]
LID - 10.1016/j.jse.2021.10.032 [doi]
AB  - BACKGROUND: 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 time points. METHODS: Clinical 
      data from 2270 aTSA and 4198 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 time points. 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 time point. 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. RESULTS: rTSA 
      patients had significantly lower mean IR scores and significantly less mean IR 
      score improvement than aTSA patients at each postoperative time point. Both aTSA 
      and rTSA patients experienced significant improvements in their ability to 
      perform activities of daily living (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. DISCUSSION: Our machine learning study 
      demonstrates that active internal rotation can be accurately predicted after aTSA 
      and rTSA at multiple postoperative time points 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.
CI  - Copyright (c) 2021 Journal of Shoulder and Elbow Surgery Board of Trustees. 
      Published by Elsevier Inc. All rights reserved.
FAU - Kumar, Vikas
AU  - Kumar V
AD  - KenSci, Seattle, WA, USA.
FAU - Schoch, Bradley S
AU  - Schoch BS
AD  - Department of Orthopedic Surgery, Mayo Clinic, Jacksonville, FL, USA.
FAU - Allen, Christine
AU  - Allen C
AD  - KenSci, Seattle, WA, USA.
FAU - Overman, Steve
AU  - Overman S
AD  - KenSci, Seattle, WA, USA; University of Washington School of Medicine, Seattle, 
      WA, USA.
FAU - Teredesai, Ankur
AU  - Teredesai A
AD  - University of Washington School of Medicine, Seattle, WA, USA.
FAU - Aibinder, William
AU  - Aibinder W
AD  - Department of Orthopaedic Surgery and Rehabilitation Medicine, Downstate Health 
      Sciences University, Brooklyn, NY, USA.
FAU - Parsons, Moby
AU  - Parsons M
AD  - The Knee Hip and Shoulder Center, Portsmouth, NH, USA.
FAU - Watling, Jonathan
AU  - Watling J
AD  - Maine Health, Portland, ME, USA.
FAU - Ko, Jiawei Kevin
AU  - Ko JK
AD  - Orthopedic Physician Associates, Swedish Orthopedic Institute, Seattle, WA, USA.
FAU - Gobbato, Bruno
AU  - Gobbato B
AD  - IDOMED, Jaragua do Sul, Brazil.
FAU - Throckmorton, Thomas
AU  - Throckmorton T
AD  - Department of Orthopaedic Surgery, University of Tennessee-Campbell Clinic, 
      Memphis, TN, USA.
FAU - Routman, Howard
AU  - Routman H
AD  - Atlantis Orthopedics, Palm Beach Gardens, FL, USA.
FAU - Roche, Christopher
AU  - Roche C
AD  - Exactech Inc., Gainesville, FL, USA. Electronic address: Chris.Roche@exac.com.
LA  - eng
PT  - Journal Article
DEP - 20211120
PL  - United States
TA  - J Shoulder Elbow Surg
JT  - Journal of shoulder and elbow surgery
JID - 9206499
SB  - IM
MH  - Activities of Daily Living
MH  - *Arthroplasty, Replacement, Shoulder/methods
MH  - Humans
MH  - Machine Learning
MH  - Range of Motion, Articular
MH  - Retrospective Studies
MH  - *Shoulder Joint/surgery
MH  - Treatment Outcome
OTO - NOTNLM
OT  - aTSA
OT  - clinical outcomes
OT  - internal rotation
OT  - machine learning
OT  - prediction models
OT  - rTSA
EDAT- 2021/11/24 06:00
MHDA- 2022/04/26 06:00
CRDT- 2021/11/23 20:14
PHST- 2021/08/20 00:00 [received]
PHST- 2021/10/21 00:00 [revised]
PHST- 2021/10/23 00:00 [accepted]
PHST- 2021/11/24 06:00 [pubmed]
PHST- 2022/04/26 06:00 [medline]
PHST- 2021/11/23 20:14 [entrez]
AID - S1058-2746(21)00811-9 [pii]
AID - 10.1016/j.jse.2021.10.032 [doi]
PST - ppublish
SO  - J Shoulder Elbow Surg. 2022 May;31(5):e234-e245. doi: 10.1016/j.jse.2021.10.032. 
      Epub 2021 Nov 20.