Assessing the utility of a sliding-windows deep neural network approach for risk prediction of trauma patients
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Assessing the utility of a sliding-windows deep neural network approach for risk prediction of trauma patients. / Bonde, Alexander; Bonde, Mikkel; Troelsen, Anders; Sillesen, Martin.
In: Scientific Reports, Vol. 13, 5176, 2023.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Assessing the utility of a sliding-windows deep neural network approach for risk prediction of trauma patients
AU - Bonde, Alexander
AU - Bonde, Mikkel
AU - Troelsen, Anders
AU - Sillesen, Martin
N1 - Publisher Copyright: © 2023, The Author(s).
PY - 2023
Y1 - 2023
N2 - The risks of post trauma complications are regulated by the injury, comorbidities, and the clinical trajectories, yet prediction models are often limited to single time-point data. We hypothesize that deep learning prediction models can be used for risk prediction using additive data after trauma using a sliding windows approach. Using the American College of Surgeons Trauma Quality Improvement Program (ACS TQIP) database, we developed three deep neural network models, for sliding-windows risk prediction. Output variables included early- and late mortality and any of 17 complications. As patients moved through the treatment trajectories, performance metrics increased. Models predicted early- and late mortality with ROC AUCs ranging from 0.980 to 0.994 and 0.910 to 0.972, respectively. For the remaining 17 complications, the mean performance ranged from 0.829 to 0.912. In summary, the deep neural networks achieved excellent performance in the sliding windows risk stratification of trauma patients.
AB - The risks of post trauma complications are regulated by the injury, comorbidities, and the clinical trajectories, yet prediction models are often limited to single time-point data. We hypothesize that deep learning prediction models can be used for risk prediction using additive data after trauma using a sliding windows approach. Using the American College of Surgeons Trauma Quality Improvement Program (ACS TQIP) database, we developed three deep neural network models, for sliding-windows risk prediction. Output variables included early- and late mortality and any of 17 complications. As patients moved through the treatment trajectories, performance metrics increased. Models predicted early- and late mortality with ROC AUCs ranging from 0.980 to 0.994 and 0.910 to 0.972, respectively. For the remaining 17 complications, the mean performance ranged from 0.829 to 0.912. In summary, the deep neural networks achieved excellent performance in the sliding windows risk stratification of trauma patients.
U2 - 10.1038/s41598-023-32453-3
DO - 10.1038/s41598-023-32453-3
M3 - Journal article
C2 - 36997598
AN - SCOPUS:85151316197
VL - 13
JO - Scientific Reports
JF - Scientific Reports
SN - 2045-2322
M1 - 5176
ER -
ID: 344447655