Abstract
Objectives:To develop and validate a prediction model for a deep surgical site infection (SSI) after fixation of a tibial plateau or pilon fracture.Design:Pooled data from 2 randomized trials (VANCO and OXYGEN).Setting:Fifty-two US trauma centers.Patients:In total, 1847 adult patients with operatively treated tibial plateau or pilon fractures who met criteria for a high risk of infection.Intervention:We considered 13 baseline patient characteristics and developed and externally validated prediction models using 3 approaches (logistic regression, stepwise elimination, and machine learning).Main Outcomes and Measures:The primary prediction model outcome was a deep SSI requiring operative debridement within 182 days of definitive fixation. Our primary prognostic performance metric for evaluating the models was area under the receiver operating characteristic curve (AUC) with clinical utility set at 0.7.Results:Deep SSI occurred in 75 VANCO patients (8%) and in 56 OXYGEN patients (6%). The machine learning model for VANCO (AUC = 0.65) and stepwise elimination model for OXYGEN (AUC = 0.62) had the highest internal validation AUCs. However, none of the external validation AUCs exceeded 0.64 (range, 0.58 to 0.64).Conclusions:The predictive models did not reach the prespecified clinical utility threshold. Our models' inability to distinguish high-risk from low-risk patients is likely due to strict eligibility criteria and, therefore, homogeneous patient populations.
Original language | English |
---|---|
Article number | e348 |
Journal | OTA international : the open access journal of orthopaedic trauma |
Volume | 7 |
Issue number | 4 |
DOIs | |
State | Published - 25 Nov 2024 |
Keywords
- fracture related infection
- infection
- machine learning
- pilon fracture
- prediction model
- surgical site infection
- tibial plateau fracture
Access to Document
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver
}
In: OTA international : the open access journal of orthopaedic trauma, Vol. 7, No. 4, e348, 25.11.2024.
Research output: Contribution to journal › Article › peer-review
TY - JOUR
T1 - Predicting deep infection in pilon and tibial plateau fractures
T2 - A secondary analysis of the VANCO and OXYGEN trials
AU - Overmann, Archie L.
AU - Carlini, Anthony R.
AU - O'Toole, Robert V.
AU - Castillo, Renan C.
AU - O'Hara, Nathan N.
AU - Carroll, Eben A.
AU - Goodman, James Brett
AU - Holden, Martha B.
AU - Miller, Anna N.
AU - Spraggs-Hughes, Amanda
AU - Brennan, Michael L.
AU - Tornetta, Paul
AU - Osborn, Patrick M.
AU - Rivera, Jessica C.
AU - Murray, Clinton K.
AU - Kimmel, Joseph E.
AU - Bosse, Michael J.
AU - Hsu, Joseph R.
AU - Karunakar, Madhav A.
AU - Kempton, Laurence B.
AU - Seymour, Rachel B.
AU - Sims, Stephen H.
AU - Churchill, Christine
AU - Sietsema, Debra L.
AU - Gitajn, Ida Leah
AU - Reilly, Rachel M.
AU - Zura, Robert D.
AU - Howes, Cameron
AU - Mir, Hassan
AU - Weaver, Michael J.
AU - Heng, Marilyn
AU - Ly, Thuan V.
AU - Wagstrom, Emily A.
AU - Westberg, Jerald R.
AU - Mullis, Brian H.
AU - Anglen, Jeffrey O.
AU - Mullis, Leilani S.
AU - Shively, Karl D.
AU - McKinley, Todd O.
AU - Natoli, Roman M.
AU - Sorkin, Anthony
AU - Hill, Lauren C.
AU - Hymes, Robert A.
AU - Gaski, Greg E.
AU - Malekzadeh, A. Stephen
AU - Ramsey, Lolita
AU - Schulman, Jeff E.
AU - Schwartzbach, Cary C.
AU - Sikorski, Robert A.
AU - Lee, Olivia C.
AU - Krause, Peter C.
AU - Gary, Joshua L.
AU - Achor, Timothy S.
AU - Choo, Andrew
AU - Munz, John W.
AU - Boutte, Sterling J.
AU - Galpin, Matthew C.
AU - Frisch, H. Michael
AU - Kaufman, Adam M.
AU - Lecroy, C. Michael
AU - Smith, Christopher S.
AU - Stall, Alec C.
AU - Horne, Andrea
AU - O'Toole, Robert V.
AU - Joshi, Manjari
AU - Nascone, Jason W.
AU - O'Hara, Nathan N.
AU - Sciadini, Marcus F.
AU - Slobogean, Gerard P.
AU - Howe, Andrea L.
AU - Hayda, Roman
AU - Evans, Andrew R.
AU - Stawicki, Stanislaw P.
AU - Wojda, Thomas R.
AU - Gardner, Michael J.
AU - Bishop, Julius A.
AU - Rehman, Saqib
AU - Caroom, Cyrus
AU - Sheridan, Elizabeth
AU - Miclau, Theodore
AU - Morshed, Saam
AU - Higgins, Thomas F.
AU - Haller, Justin M.
AU - Spitler, Clay A.
AU - Morandi, Massimo Max
AU - Matuszewski, Paul Edward
AU - Aneja, Arun
AU - Bergin, Patrick F.
AU - Bhanat, Eldrin
AU - Graves, Matt L.
AU - Morellato, John
AU - Teague, David
AU - Ertl, William
AU - Ahn, Jaimo
AU - Moloney, Gele B.
AU - Weinlein, John C.
AU - Zelle, Boris A.
AU - Agarwal, Animesh
AU - Karia, Ravi A.
AU - Sathy, Ashoke
AU - Sanders, Drew
AU - Weiss, David B.
AU - Yarboro, Seth R.
AU - Lester-Ballard, Veronica
AU - McVey, Eric D.
AU - Firoozabadi, Reza
AU - Dagal, Arman
AU - Kleweno, Conor P.
AU - Agel, Julie
AU - Whiting, Paul S.
AU - Simske, Natasha M.
AU - Siy, Alexander B.
AU - Obremskey, William T.
AU - Attum, Basem
AU - Burgos, Eduardo J.
AU - Gajari, Vamshi
AU - Jahangir, A. Alex
AU - Rodriguez-Buitrago, Andres
AU - Sethi, Manish
AU - Stinner, Daniel J.
AU - Tummuru, Rajesh R.
AU - Trochez, Karen M.
AU - D'Alleyrand, Jean Claude G.
AU - Allen, Lauren E.
AU - Carlini, Anthony R.
AU - Collins, Susan C.
AU - Huang, Yanjie
AU - Taylor, Tara J.
N1 - Publisher Copyright: © 2024 Overmann et al. OTA International.
PY - 2024/11/25
Y1 - 2024/11/25
N2 - Objectives:To develop and validate a prediction model for a deep surgical site infection (SSI) after fixation of a tibial plateau or pilon fracture.Design:Pooled data from 2 randomized trials (VANCO and OXYGEN).Setting:Fifty-two US trauma centers.Patients:In total, 1847 adult patients with operatively treated tibial plateau or pilon fractures who met criteria for a high risk of infection.Intervention:We considered 13 baseline patient characteristics and developed and externally validated prediction models using 3 approaches (logistic regression, stepwise elimination, and machine learning).Main Outcomes and Measures:The primary prediction model outcome was a deep SSI requiring operative debridement within 182 days of definitive fixation. Our primary prognostic performance metric for evaluating the models was area under the receiver operating characteristic curve (AUC) with clinical utility set at 0.7.Results:Deep SSI occurred in 75 VANCO patients (8%) and in 56 OXYGEN patients (6%). The machine learning model for VANCO (AUC = 0.65) and stepwise elimination model for OXYGEN (AUC = 0.62) had the highest internal validation AUCs. However, none of the external validation AUCs exceeded 0.64 (range, 0.58 to 0.64).Conclusions:The predictive models did not reach the prespecified clinical utility threshold. Our models' inability to distinguish high-risk from low-risk patients is likely due to strict eligibility criteria and, therefore, homogeneous patient populations.
AB - Objectives:To develop and validate a prediction model for a deep surgical site infection (SSI) after fixation of a tibial plateau or pilon fracture.Design:Pooled data from 2 randomized trials (VANCO and OXYGEN).Setting:Fifty-two US trauma centers.Patients:In total, 1847 adult patients with operatively treated tibial plateau or pilon fractures who met criteria for a high risk of infection.Intervention:We considered 13 baseline patient characteristics and developed and externally validated prediction models using 3 approaches (logistic regression, stepwise elimination, and machine learning).Main Outcomes and Measures:The primary prediction model outcome was a deep SSI requiring operative debridement within 182 days of definitive fixation. Our primary prognostic performance metric for evaluating the models was area under the receiver operating characteristic curve (AUC) with clinical utility set at 0.7.Results:Deep SSI occurred in 75 VANCO patients (8%) and in 56 OXYGEN patients (6%). The machine learning model for VANCO (AUC = 0.65) and stepwise elimination model for OXYGEN (AUC = 0.62) had the highest internal validation AUCs. However, none of the external validation AUCs exceeded 0.64 (range, 0.58 to 0.64).Conclusions:The predictive models did not reach the prespecified clinical utility threshold. Our models' inability to distinguish high-risk from low-risk patients is likely due to strict eligibility criteria and, therefore, homogeneous patient populations.
KW - fracture related infection
KW - infection
KW - machine learning
KW - pilon fracture
KW - prediction model
KW - surgical site infection
KW - tibial plateau fracture
UR - http://www.scopus.com/inward/record.url?scp=85210949775&partnerID=8YFLogxK
U2 - 10.1097/OI9.0000000000000348
DO - 10.1097/OI9.0000000000000348
M3 - Article
AN - SCOPUS:85210949775
SN - 2574-2167
VL - 7
JO - OTA international : the open access journal of orthopaedic trauma
JF - OTA international : the open access journal of orthopaedic trauma
IS - 4
M1 - e348
ER -