PMID- 37868215
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20231030
IS  - 2325-9671 (Print)
IS  - 2325-9671 (Electronic)
IS  - 2325-9671 (Linking)
VI  - 11
IP  - 10
DP  - 2023 Oct
TI  - Using Machine Learning to Predict Nonachievement of Clinically Significant 
      Outcomes After Rotator Cuff Repair.
PG  - 23259671231206180
LID - 10.1177/23259671231206180 [doi]
LID - 23259671231206180
AB  - BACKGROUND: Although some evidence suggests that machine learning algorithms may 
      outperform classical statistical methods in prognosis prediction for several 
      orthopaedic surgeries, to our knowledge, no study has yet used machine learning 
      to predict patient-reported outcome measures after rotator cuff repair. PURPOSE: 
      To determine whether machine learning algorithms using preoperative data can 
      predict the nonachievement of the minimal clinically important difference (MCID) 
      of disability at 2 years after rotator cuff surgical repair with a similar 
      performance to that of other machine learning studies in the orthopaedic surgery 
      literature. STUDY DESIGN: Case-control study; Level of evidence, 3. METHODS: We 
      evaluated 474 patients (n = 500 shoulders) with rotator cuff tears who underwent 
      arthroscopic rotator cuff repair between January 2013 and April 2019. The study 
      outcome was the difference between the preoperative and 24-month postoperative 
      American Shoulder and Elbow Surgeons (ASES) score. A cutoff score was calculated 
      based on the established MCID of 15.2 points to separate success (higher than the 
      cutoff) from failure (lower than the cutoff). Routinely collected imaging, 
      clinical, and demographic data were used to train 8 machine learning algorithms 
      (random forest classifier; light gradient boosting machine [LightGBM]; decision 
      tree classifier; extra trees classifier; logistic regression; extreme gradient 
      boosting [XGBoost]; k-nearest neighbors [KNN] classifier; and CatBoost 
      classifier). We used a random sample of 70% of patients to train the algorithms, 
      and 30% were left for performance assessment, simulating new data. The 
      performance of the models was evaluated with the area under the receiver 
      operating characteristic curve (AUC). RESULTS: The AUCs for all algorithms ranged 
      from 0.58 to 0.68. The random forest classifier and LightGBM presented the 
      highest AUC values (0.68 [95% CI, 0.48-0.79] and 0.67 [95% CI, 0.43-0.75], 
      respectively) of the 8 machine learning algorithms. Most of the machine learning 
      algorithms outperformed logistic regression (AUC, 0.59 [95% CI, 0.48-0.81]); 
      nonetheless, their performance was lower than that of other machine learning 
      studies in the orthopaedic surgery literature. CONCLUSION: Machine learning 
      algorithms demonstrated some ability to predict the nonachievement of the MCID on 
      the ASES 2 years after rotator cuff repair surgery.
CI  - (c) The Author(s) 2023.
FAU - Alaiti, Rafael Krasic
AU  - Alaiti RK
AD  - Research, Technology, and Data Science Office, Grupo Superador, Sao Paulo, 
      Brazil.
AD  - Universidade de Sao Paulo, Sao Paulo, Brazil.
FAU - Vallio, Caio Sain
AU  - Vallio CS
AD  - Health Innovation, Data Science, and MLOps, Semantix, Sao Paulo, Brazil.
FAU - Assuncao, Jorge Henrique
AU  - Assuncao JH
AD  - Faculdade de Medicina, Hospital das Clinicas FMUSP, Universidade de Sao Paulo, 
      Sao Paulo, Brazil.
AD  - DASA, Hospital 9 de Julho, Sao Paulo, Sao Paulo, Brazil.
FAU - de Andrade E Silva, Fernando Brandao
AU  - de Andrade E Silva FB
AD  - Faculdade de Medicina, Hospital das Clinicas FMUSP, Universidade de Sao Paulo, 
      Sao Paulo, Brazil.
FAU - Gracitelli, Mauro Emilio Conforto
AU  - Gracitelli MEC
AD  - Faculdade de Medicina, Hospital das Clinicas FMUSP, Universidade de Sao Paulo, 
      Sao Paulo, Brazil.
FAU - Neto, Arnaldo Amado Ferreira
AU  - Neto AAF
AD  - Faculdade de Medicina, Hospital das Clinicas FMUSP, Universidade de Sao Paulo, 
      Sao Paulo, Brazil.
FAU - Malavolta, Eduardo Angeli
AU  - Malavolta EA
AD  - Faculdade de Medicina, Hospital das Clinicas FMUSP, Universidade de Sao Paulo, 
      Sao Paulo, Brazil.
AD  - Hospital do Coracao, Sao Paulo, Brazil.
LA  - eng
PT  - Journal Article
DEP - 20231019
PL  - United States
TA  - Orthop J Sports Med
JT  - Orthopaedic journal of sports medicine
JID - 101620522
PMC - PMC10588422
OTO - NOTNLM
OT  - artificial intelligence
OT  - machine learning
OT  - rotator cuff repair
OT  - rotator cuff tears
OT  - shoulder pain
COIS- The authors have declared that there are no conflicts of interest in the 
      authorship and publication of this contribution. AOSSM checks author disclosures 
      against the Open Payments Database (OPD). AOSSM has not conducted an independent 
      investigation on the OPD and disclaims any liability or responsibility relating 
      thereto. Ethical approval for this study was obtained from the Clinical Hospital 
      of the Medical School of the University of Sao Paulo, Sao Paulo, Brazil (protocol 
      No. 2.778.930).
EDAT- 2023/10/23 06:49
MHDA- 2023/10/23 06:50
PMCR- 2023/10/19
CRDT- 2023/10/23 04:34
PHST- 2023/05/17 00:00 [received]
PHST- 2023/05/30 00:00 [accepted]
PHST- 2023/10/23 06:50 [medline]
PHST- 2023/10/23 06:49 [pubmed]
PHST- 2023/10/23 04:34 [entrez]
PHST- 2023/10/19 00:00 [pmc-release]
AID - 10.1177_23259671231206180 [pii]
AID - 10.1177/23259671231206180 [doi]
PST - epublish
SO  - Orthop J Sports Med. 2023 Oct 19;11(10):23259671231206180. doi: 
      10.1177/23259671231206180. eCollection 2023 Oct.