Skip to main content

Artificial Neural Networks Predict 30-Day Mortality After Hip Fracture: Insights From Machine Learning.

Publication ,  Journal Article
DeBaun, MR; Chavez, G; Fithian, A; Oladeji, K; Van Rysselberghe, N; Goodnough, LH; Bishop, JA; Gardner, MJ
Published in: J Am Acad Orthop Surg
November 15, 2021

OBJECTIVES: Accurately stratifying patients in the preoperative period according to mortality risk informs treatment considerations and guides adjustments to bundled reimbursements. We developed and compared three machine learning models to determine which best predicts 30-day mortality after hip fracture. METHODS: The 2016 to 2017 National Surgical Quality Improvement Program for hip fracture (AO/OTA 31-A-B-C) procedure-targeted data were analyzed. Three models-artificial neural network, naive Bayes, and logistic regression-were trained and tested using independent variables selected via backward variable selection. The data were split into 80% training and 20% test sets. Predictive accuracy between models was evaluated using area under the curve receiver operating characteristics. Odds ratios were determined using multivariate logistic regression with P < 0.05 for significance. RESULTS: The study cohort included 19,835 patients (69.3% women). The 30-day mortality rate was 5.3%. In total, 47 independent patient variables were identified to train the testing models. Area under the curve receiver operating characteristics for 30-day mortality was highest for artificial neural network (0.92), followed by the logistic regression (0.87) and naive Bayes models (0.83). DISCUSSION: Machine learning is an emerging approach to develop accurate risk calculators that account for the weighted interactions between variables. In this study, we developed and tested a neural network model that was highly accurate for predicting 30-day mortality after hip fracture. This was superior to the naive Bayes and logistic regression models. The role of machine learning models to predict orthopaedic outcomes merits further development and prospective validation but shows strong promise for positively impacting patient care.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

J Am Acad Orthop Surg

DOI

EISSN

1940-5480

Publication Date

November 15, 2021

Volume

29

Issue

22

Start / End Page

977 / 983

Location

United States

Related Subject Headings

  • Orthopedics
  • Neural Networks, Computer
  • Male
  • Machine Learning
  • Logistic Models
  • Humans
  • Hip Fractures
  • Female
  • Bayes Theorem
  • 3202 Clinical sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
DeBaun, M. R., Chavez, G., Fithian, A., Oladeji, K., Van Rysselberghe, N., Goodnough, L. H., … Gardner, M. J. (2021). Artificial Neural Networks Predict 30-Day Mortality After Hip Fracture: Insights From Machine Learning. J Am Acad Orthop Surg, 29(22), 977–983. https://doi.org/10.5435/JAAOS-D-20-00429
DeBaun, Malcolm R., Gustavo Chavez, Andrew Fithian, Kingsley Oladeji, Noelle Van Rysselberghe, L Henry Goodnough, Julius A. Bishop, and Michael J. Gardner. “Artificial Neural Networks Predict 30-Day Mortality After Hip Fracture: Insights From Machine Learning.J Am Acad Orthop Surg 29, no. 22 (November 15, 2021): 977–83. https://doi.org/10.5435/JAAOS-D-20-00429.
DeBaun MR, Chavez G, Fithian A, Oladeji K, Van Rysselberghe N, Goodnough LH, et al. Artificial Neural Networks Predict 30-Day Mortality After Hip Fracture: Insights From Machine Learning. J Am Acad Orthop Surg. 2021 Nov 15;29(22):977–83.
DeBaun, Malcolm R., et al. “Artificial Neural Networks Predict 30-Day Mortality After Hip Fracture: Insights From Machine Learning.J Am Acad Orthop Surg, vol. 29, no. 22, Nov. 2021, pp. 977–83. Pubmed, doi:10.5435/JAAOS-D-20-00429.
DeBaun MR, Chavez G, Fithian A, Oladeji K, Van Rysselberghe N, Goodnough LH, Bishop JA, Gardner MJ. Artificial Neural Networks Predict 30-Day Mortality After Hip Fracture: Insights From Machine Learning. J Am Acad Orthop Surg. 2021 Nov 15;29(22):977–983.

Published In

J Am Acad Orthop Surg

DOI

EISSN

1940-5480

Publication Date

November 15, 2021

Volume

29

Issue

22

Start / End Page

977 / 983

Location

United States

Related Subject Headings

  • Orthopedics
  • Neural Networks, Computer
  • Male
  • Machine Learning
  • Logistic Models
  • Humans
  • Hip Fractures
  • Female
  • Bayes Theorem
  • 3202 Clinical sciences