PMID- 34245310
OWN - NLM
STAT- MEDLINE
DCOM- 20220726
LR  - 20220726
IS  - 1433-7347 (Electronic)
IS  - 0942-2056 (Linking)
VI  - 30
IP  - 8
DP  - 2022 Aug
TI  - Machine learning algorithms do not outperform preoperative thresholds in 
      predicting clinically meaningful improvements after total knee arthroplasty.
PG  - 2624-2630
LID - 10.1007/s00167-021-06642-4 [doi]
AB  - PURPOSE: Patient-reported outcome measures (PROMs) are important measures of 
      success after total knee arthroplasty (TKA) and being able to predict their 
      improvements could enhance preoperative decision-making. Our study aims to 
      compare the predictive performance of machine learning (ML) algorithms and 
      preoperative PROM thresholds in predicting minimal clinically important 
      difference (MCID) attainment at 2 years after TKA. METHODS: Prospectively 
      collected data of 2840 primary TKA performed between 2008 and 2018 was extracted 
      from our joint replacement registry and split into a training set (80%) and test 
      set (20%). Using the training set, ML algorithms were developed using patient 
      demographics, comorbidities and preoperative PROMs, whereas the optimal 
      preoperative threshold was determined using ROC analysis. Both methods were used 
      to predict MCID attainment for the SF-36 PCS, MCS and WOMAC at 2 years 
      postoperatively, with predictive performance evaluated on the independent test 
      set. RESULTS: ML algorithms and preoperative PROM models performed similarly in 
      predicting MCID for the SF-36 PCS (AUC: 0.77 vs 0.74), MCS (AUC: 0.95 vs 0.95) 
      and WOMAC (AUC: 0.89 vs 0.88). For each outcome, the most important predictor of 
      MCID attainment was the patient's preoperative PROM score. ROC analysis also 
      identified optimal preoperative threshold values of 33.6, 54.1 and 72.7 for the 
      SF-36 PCS, MCS and WOMAC, respectively. CONCLUSION: ML algorithms did not perform 
      significantly better than preoperative PROM thresholds in predicting MCID 
      attainment after TKA. Future research should routinely compare the predictive 
      ability of ML algorithms with existing methods and determine the type of clinical 
      problems which may benefit the most from it. LEVEL OF EVIDENCE: II.
CI  - (c) 2021. European Society of Sports Traumatology, Knee Surgery, Arthroscopy 
      (ESSKA).
FAU - Zhang, Siyuan
AU  - Zhang S
AUID- ORCID: 0000-0002-7622-3388
AD  - Yong Loo Lin School of Medicine, National University of Singapore, 10 Medical 
      Drive, Singapore, 117597, Singapore.
FAU - Lau, Bernard Puang Huh
AU  - Lau BPH
AD  - Department of Orthopaedic Surgery, National University Hospital, Level 11, NUHS 
      Tower Block. 1E Kent Ridge Road, Singapore, 119228, Singapore.
FAU - Ng, Yau Hong
AU  - Ng YH
AD  - Department of Orthopaedic Surgery, National University Hospital, Level 11, NUHS 
      Tower Block. 1E Kent Ridge Road, Singapore, 119228, Singapore.
FAU - Wang, Xinyu
AU  - Wang X
AD  - Department of Orthopaedic Surgery, National University Hospital, Level 11, NUHS 
      Tower Block. 1E Kent Ridge Road, Singapore, 119228, Singapore.
FAU - Chua, Weiliang
AU  - Chua W
AD  - Department of Orthopaedic Surgery, National University Hospital, Level 11, NUHS 
      Tower Block. 1E Kent Ridge Road, Singapore, 119228, Singapore. 
      wei_liang_chua@nuhs.edu.sg.
LA  - eng
PT  - Journal Article
DEP - 20210710
PL  - Germany
TA  - Knee Surg Sports Traumatol Arthrosc
JT  - Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA
JID - 9314730
SB  - IM
MH  - *Arthroplasty, Replacement, Knee
MH  - Humans
MH  - Machine Learning
MH  - Minimal Clinically Important Difference
MH  - Patient Reported Outcome Measures
MH  - Registries
MH  - Treatment Outcome
OTO - NOTNLM
OT  - Artificial intelligence
OT  - MCID
OT  - Machine learning
OT  - Patient reported outcome measures
OT  - Total knee arthroplasty
EDAT- 2021/07/11 06:00
MHDA- 2022/07/27 06:00
CRDT- 2021/07/10 12:08
PHST- 2021/04/25 00:00 [received]
PHST- 2021/06/12 00:00 [accepted]
PHST- 2021/07/11 06:00 [pubmed]
PHST- 2022/07/27 06:00 [medline]
PHST- 2021/07/10 12:08 [entrez]
AID - 10.1007/s00167-021-06642-4 [pii]
AID - 10.1007/s00167-021-06642-4 [doi]
PST - ppublish
SO  - Knee Surg Sports Traumatol Arthrosc. 2022 Aug;30(8):2624-2630. doi: 
      10.1007/s00167-021-06642-4. Epub 2021 Jul 10.