Limits...
Predictive modeling in pediatric traumatic brain injury using machine learning.

Chong SL, Liu N, Barbier S, Ong ME - BMC Med Res Methodol (2015)

Bottom Line: To predict moderate to severe TBI, we built a machine learning (ML) model and a multivariable logistic regression model and compared their performances by means of Receiver Operating Characteristic (ROC) analysis.The following 4 predictors remained statistically significant after multivariable analysis: Involvement in road traffic accident, a history of loss of consciousness, vomiting and signs of base of skull fracture.At the optimal cutoff scores, the ML method improved upon the logistic regression method with respect to the area under the ROC curve (0.98 vs 0.93), sensitivity (94.9% vs 82.1%), specificity (97.4% vs 92.3%), PPV (90.2% vs 72.7%), and NPV (98.7% vs 95.4%).

View Article: PubMed Central - PubMed

Affiliation: Department of Emergency Medicine, KK Women's and Children's Hospital, Singapore, Singapore. chong.shu-ling@kkh.com.sg.

ABSTRACT

Background: Pediatric traumatic brain injury (TBI) constitutes a significant burden and diagnostic challenge in the emergency department (ED). While large North American research networks have derived clinical prediction rules for the head injured child, these may not be generalizable to practices in countries with traditionally low rates of computed tomography (CT). We aim to study predictors for moderate to severe TBI in our ED population aged < 16 years.

Methods: This was a retrospective case-control study based on data from a prospective surveillance head injury database. Cases were included if patients presented from 2006 to 2014, with moderate to severe TBI. Controls were age-matched head injured children from the registry, obtained in a 4 control: 1 case ratio. These children remained well on diagnosis and follow up. Demographics, history, and physical examination findings were analyzed and patients followed up for the clinical course and outcome measures of death and neurosurgical intervention. To predict moderate to severe TBI, we built a machine learning (ML) model and a multivariable logistic regression model and compared their performances by means of Receiver Operating Characteristic (ROC) analysis.

Results: There were 39 cases and 156 age-matched controls. The following 4 predictors remained statistically significant after multivariable analysis: Involvement in road traffic accident, a history of loss of consciousness, vomiting and signs of base of skull fracture. The logistic regression model was created with these 4 variables while the ML model was built with 3 extra variables, namely the presence of seizure, confusion and clinical signs of skull fracture. At the optimal cutoff scores, the ML method improved upon the logistic regression method with respect to the area under the ROC curve (0.98 vs 0.93), sensitivity (94.9% vs 82.1%), specificity (97.4% vs 92.3%), PPV (90.2% vs 72.7%), and NPV (98.7% vs 95.4%).

Conclusions: In this study, we demonstrated the feasibility of using machine learning as a tool to predict moderate to severe TBI. If validated on a large scale, the ML method has the potential not only to guide discretionary use of CT, but also a more careful selection of head injured children who warrant closer monitoring in the hospital.

No MeSH data available.


Related in: MedlinePlus

The architecture of the machine learning (ML) method. Input x is the patient whose risk of abnormal CT scan is being evaluated. Lt is the training set consisting of K samples (xk, yk) where k = 1, 2, …, K and yk is the class label. By using the training data, a total of T individual classifiers φt(x, Lt) are created to form the decision ensemble. Each individual classifier is built based on a subset of the training data. Then the prediction outcomes are combined by means of majority voting scheme to generate a final risk score for patient x.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4374377&req=5

Fig1: The architecture of the machine learning (ML) method. Input x is the patient whose risk of abnormal CT scan is being evaluated. Lt is the training set consisting of K samples (xk, yk) where k = 1, 2, …, K and yk is the class label. By using the training data, a total of T individual classifiers φt(x, Lt) are created to form the decision ensemble. Each individual classifier is built based on a subset of the training data. Then the prediction outcomes are combined by means of majority voting scheme to generate a final risk score for patient x.

Mentions: Due to its flexibility in many application domains, the above ML method is readily adaptable to our study with minor changes. The architecture of the ML method used in this study is illustrated in Figure 1. Each ensemble classifier φt where t = 1, 2, …, T and T is the number of individual classifiers in the decision ensemble. Ensemble learning methods [21,22] usually generate a predictive label rather than a score as the output. The ML method uses a simple and straightforward approach to convert the predictive decision into a risk score. Details are elaborated as follows.Figure 1


Predictive modeling in pediatric traumatic brain injury using machine learning.

Chong SL, Liu N, Barbier S, Ong ME - BMC Med Res Methodol (2015)

The architecture of the machine learning (ML) method. Input x is the patient whose risk of abnormal CT scan is being evaluated. Lt is the training set consisting of K samples (xk, yk) where k = 1, 2, …, K and yk is the class label. By using the training data, a total of T individual classifiers φt(x, Lt) are created to form the decision ensemble. Each individual classifier is built based on a subset of the training data. Then the prediction outcomes are combined by means of majority voting scheme to generate a final risk score for patient x.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4374377&req=5

Fig1: The architecture of the machine learning (ML) method. Input x is the patient whose risk of abnormal CT scan is being evaluated. Lt is the training set consisting of K samples (xk, yk) where k = 1, 2, …, K and yk is the class label. By using the training data, a total of T individual classifiers φt(x, Lt) are created to form the decision ensemble. Each individual classifier is built based on a subset of the training data. Then the prediction outcomes are combined by means of majority voting scheme to generate a final risk score for patient x.
Mentions: Due to its flexibility in many application domains, the above ML method is readily adaptable to our study with minor changes. The architecture of the ML method used in this study is illustrated in Figure 1. Each ensemble classifier φt where t = 1, 2, …, T and T is the number of individual classifiers in the decision ensemble. Ensemble learning methods [21,22] usually generate a predictive label rather than a score as the output. The ML method uses a simple and straightforward approach to convert the predictive decision into a risk score. Details are elaborated as follows.Figure 1

Bottom Line: To predict moderate to severe TBI, we built a machine learning (ML) model and a multivariable logistic regression model and compared their performances by means of Receiver Operating Characteristic (ROC) analysis.The following 4 predictors remained statistically significant after multivariable analysis: Involvement in road traffic accident, a history of loss of consciousness, vomiting and signs of base of skull fracture.At the optimal cutoff scores, the ML method improved upon the logistic regression method with respect to the area under the ROC curve (0.98 vs 0.93), sensitivity (94.9% vs 82.1%), specificity (97.4% vs 92.3%), PPV (90.2% vs 72.7%), and NPV (98.7% vs 95.4%).

View Article: PubMed Central - PubMed

Affiliation: Department of Emergency Medicine, KK Women's and Children's Hospital, Singapore, Singapore. chong.shu-ling@kkh.com.sg.

ABSTRACT

Background: Pediatric traumatic brain injury (TBI) constitutes a significant burden and diagnostic challenge in the emergency department (ED). While large North American research networks have derived clinical prediction rules for the head injured child, these may not be generalizable to practices in countries with traditionally low rates of computed tomography (CT). We aim to study predictors for moderate to severe TBI in our ED population aged < 16 years.

Methods: This was a retrospective case-control study based on data from a prospective surveillance head injury database. Cases were included if patients presented from 2006 to 2014, with moderate to severe TBI. Controls were age-matched head injured children from the registry, obtained in a 4 control: 1 case ratio. These children remained well on diagnosis and follow up. Demographics, history, and physical examination findings were analyzed and patients followed up for the clinical course and outcome measures of death and neurosurgical intervention. To predict moderate to severe TBI, we built a machine learning (ML) model and a multivariable logistic regression model and compared their performances by means of Receiver Operating Characteristic (ROC) analysis.

Results: There were 39 cases and 156 age-matched controls. The following 4 predictors remained statistically significant after multivariable analysis: Involvement in road traffic accident, a history of loss of consciousness, vomiting and signs of base of skull fracture. The logistic regression model was created with these 4 variables while the ML model was built with 3 extra variables, namely the presence of seizure, confusion and clinical signs of skull fracture. At the optimal cutoff scores, the ML method improved upon the logistic regression method with respect to the area under the ROC curve (0.98 vs 0.93), sensitivity (94.9% vs 82.1%), specificity (97.4% vs 92.3%), PPV (90.2% vs 72.7%), and NPV (98.7% vs 95.4%).

Conclusions: In this study, we demonstrated the feasibility of using machine learning as a tool to predict moderate to severe TBI. If validated on a large scale, the ML method has the potential not only to guide discretionary use of CT, but also a more careful selection of head injured children who warrant closer monitoring in the hospital.

No MeSH data available.


Related in: MedlinePlus