TY - JOUR
T1 - A Machine Learning Algorithm to Predict the Probability of (Occult) Posterior Malleolar Fractures Associated With Tibial Shaft Fractures to Guide "Malleolus First" Fixation
AU - Hendrickx, Laurent A.M.
AU - Sobol, Garret L.
AU - Langerhuizen, David W.G.
AU - Bulstra, Anne Eva J.
AU - Hreha, Jeremy
AU - Sprague, Sheila
AU - Sirkin, Michael S.
AU - Ring, David
AU - Kerkhoffs, Gino M.M.J.
AU - Jaarsma, Ruurd L.
AU - Doornberg, Job N.
AU - Machine Learning Consortium
PY - 2020/3/1
Y1 - 2020/3/1
N2 - OBJECTIVES: To develop an accurate machine learning (ML) predictive model incorporating patient, fracture, and trauma characteristics to identify individual patients at risk of an (occult) PMF. METHODS: Databases of 2 studies including patients with TSFs from 2 Level 1 trauma centers were combined for analysis. Using ten-fold cross-validation, 4 supervised ML algorithms were trained in recognizing patterns associated with PMFs: (1) Bayes point machine; (2) support vector machine; (3) neural network; and (4) boosted decision tree. Performance of each ML algorithm was evaluated and compared based on (1) C-statistic; (2) calibration slope and intercept; and (3) Brier score. The best-performing ML algorithm was incorporated into an online open-access prediction tool. RESULTS: Total data set included 263 patients, of which 28% had a PMF. Training of the Bayes point machine resulted in the best-performing prediction model reflected by good C-statistic, calibration slope, calibration intercept, and Brier score of 0.89, 1.02, -0.06, and 0.106, respectively. This prediction model was deployed as an open-access online prediction tool. CONCLUSION: A ML-based prediction model accurately predicted the probability of a (occult) PMF in patients with a TSF based on patient- and fracture-specific characteristics. This prediction model can guide surgeons in their diagnostic workup and preoperative planning. Further research is required to externally validate the model before implementation in clinical practice. LEVEL OF EVIDENCE: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.
AB - OBJECTIVES: To develop an accurate machine learning (ML) predictive model incorporating patient, fracture, and trauma characteristics to identify individual patients at risk of an (occult) PMF. METHODS: Databases of 2 studies including patients with TSFs from 2 Level 1 trauma centers were combined for analysis. Using ten-fold cross-validation, 4 supervised ML algorithms were trained in recognizing patterns associated with PMFs: (1) Bayes point machine; (2) support vector machine; (3) neural network; and (4) boosted decision tree. Performance of each ML algorithm was evaluated and compared based on (1) C-statistic; (2) calibration slope and intercept; and (3) Brier score. The best-performing ML algorithm was incorporated into an online open-access prediction tool. RESULTS: Total data set included 263 patients, of which 28% had a PMF. Training of the Bayes point machine resulted in the best-performing prediction model reflected by good C-statistic, calibration slope, calibration intercept, and Brier score of 0.89, 1.02, -0.06, and 0.106, respectively. This prediction model was deployed as an open-access online prediction tool. CONCLUSION: A ML-based prediction model accurately predicted the probability of a (occult) PMF in patients with a TSF based on patient- and fracture-specific characteristics. This prediction model can guide surgeons in their diagnostic workup and preoperative planning. Further research is required to externally validate the model before implementation in clinical practice. LEVEL OF EVIDENCE: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.
KW - posterior malleolar fracture
KW - tibial shaft fracture
KW - machine learning
KW - prediction model
KW - prediction tool
UR - http://www.scopus.com/inward/record.url?scp=85081925449&partnerID=8YFLogxK
U2 - 10.1097/BOT.0000000000001663
DO - 10.1097/BOT.0000000000001663
M3 - Article
C2 - 32108120
AN - SCOPUS:85081925449
SN - 0890-5339
VL - 34
SP - 131
EP - 138
JO - Journal of Orthopaedic Trauma
JF - Journal of Orthopaedic Trauma
IS - 3
ER -