TY - JOUR
T1 - Machine learning combining CT findings and clinical parameters improves prediction of length of stay and ICU admission in torso trauma
AU - Staziaki, Pedro Vinícius
AU - Wu, Di
AU - Rayan, Jesse C.
AU - Santo, Irene Dixe de Oliveira
AU - Nan, Feng
AU - Maybury, Aaron
AU - Gangasani, Neha
AU - Benador, Ilan
AU - Saligrama, Venkatesh
AU - Scalera, Jonathan
AU - Anderson, Stephan W.
N1 - Publisher Copyright:
© 2021, European Society of Radiology.
PY - 2021/7
Y1 - 2021/7
N2 - Objective: To develop machine learning (ML) models capable of predicting ICU admission and extended length of stay (LOS) after torso (chest, abdomen, or pelvis) trauma, by using clinical and/or imaging data. Materials and methods: This was a retrospective study of 840 adult patients admitted to a level 1 trauma center after injury to the torso over the course of 1 year. Clinical parameters included age, sex, vital signs, clinical scores, and laboratory values. Imaging data consisted of any injury present on CT. The two outcomes of interest were ICU admission and extended LOS, defined as more than the median LOS in the dataset. We developed and tested artificial neural network (ANN) and support vector machine (SVM) models, and predictive performance was evaluated by area under the receiver operating characteristic (ROC) curve (AUC). Results: The AUCs of SVM and ANN models to predict ICU admission were up to 0.87 ± 0.03 and 0.78 ± 0.02, respectively. The AUCs of SVM and ANN models to predict extended LOS were up to 0.80 ± 0.04 and 0.81 ± 0.05, respectively. Predictions based on imaging alone or imaging with clinical parameters were consistently more accurate than those based solely on clinical parameters. Conclusions: The best performing models incorporated imaging findings and outperformed those with clinical findings alone. ML models have the potential to help predict outcomes in trauma by integrating clinical and imaging findings, although further research may be needed to optimize their performance. Key Points: • Artificial neural network and support vector machine–based models were used to predict the intensive care unit admission and extended length of stay after trauma to the torso. • Our input data consisted of clinical parameters and CT imaging findings derived from radiology reports, and we found that combining the two significantly enhanced the prediction of both outcomes with either model. • The highest accuracy (83%) and highest area under the receiver operating characteristic curve (0.87) were obtained for artificial neural networks and support vector machines, respectively, by combining clinical and imaging features in the prediction of intensive care unit admission.
AB - Objective: To develop machine learning (ML) models capable of predicting ICU admission and extended length of stay (LOS) after torso (chest, abdomen, or pelvis) trauma, by using clinical and/or imaging data. Materials and methods: This was a retrospective study of 840 adult patients admitted to a level 1 trauma center after injury to the torso over the course of 1 year. Clinical parameters included age, sex, vital signs, clinical scores, and laboratory values. Imaging data consisted of any injury present on CT. The two outcomes of interest were ICU admission and extended LOS, defined as more than the median LOS in the dataset. We developed and tested artificial neural network (ANN) and support vector machine (SVM) models, and predictive performance was evaluated by area under the receiver operating characteristic (ROC) curve (AUC). Results: The AUCs of SVM and ANN models to predict ICU admission were up to 0.87 ± 0.03 and 0.78 ± 0.02, respectively. The AUCs of SVM and ANN models to predict extended LOS were up to 0.80 ± 0.04 and 0.81 ± 0.05, respectively. Predictions based on imaging alone or imaging with clinical parameters were consistently more accurate than those based solely on clinical parameters. Conclusions: The best performing models incorporated imaging findings and outperformed those with clinical findings alone. ML models have the potential to help predict outcomes in trauma by integrating clinical and imaging findings, although further research may be needed to optimize their performance. Key Points: • Artificial neural network and support vector machine–based models were used to predict the intensive care unit admission and extended length of stay after trauma to the torso. • Our input data consisted of clinical parameters and CT imaging findings derived from radiology reports, and we found that combining the two significantly enhanced the prediction of both outcomes with either model. • The highest accuracy (83%) and highest area under the receiver operating characteristic curve (0.87) were obtained for artificial neural networks and support vector machines, respectively, by combining clinical and imaging features in the prediction of intensive care unit admission.
KW - Accidental injuries, diagnostic imaging
KW - Artificial intelligence
KW - Length of stay
KW - Machine learning
KW - Multidetector computed tomography
UR - http://www.scopus.com/inward/record.url?scp=85099930968&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099930968&partnerID=8YFLogxK
U2 - 10.1007/s00330-020-07534-w
DO - 10.1007/s00330-020-07534-w
M3 - Article
C2 - 33475772
AN - SCOPUS:85099930968
SN - 0938-7994
VL - 31
SP - 5434
EP - 5441
JO - European Radiology
JF - European Radiology
IS - 7
ER -