A Taxonomy of Explainable Bayesian Networks

Derks, Iena Petronella; Waal, Alta de

doi:10.1007/978-3-030-66151-9_14

Cited by 15 publications

(19 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Explanation of Bayesian networks has been a topic of interest ever since their introduction [15,19]. Four categories of explanation method are distinguished, depending on the focus of explanation: 1) explanation of evidence; 2) explanation of reasoning; 3) explanation of the model itself, and 4) explanation of decisions [5,11]. The last category is a recent addition to cover methods that address the question of whether or not the user can make an informed enough decision.…”

Section: Introductionmentioning

confidence: 99%

Persuasive Contrastive Explanations for Bayesian Networks

Koopman

Renooij

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Explanation in Artificial Intelligence is often focused on providing reasons for why a model under consideration and its outcome are correct. Recently, research in explainable machine learning has initiated a shift in focus on including so-called counterfactual explanations. In this paper we propose to combine both types of explanation in the context of explaining Bayesian networks. To this end we introduce persuasive contrastive explanations that aim to provide an answer to the question Why outcome t instead of t ? posed by a user. In addition, we propose an algorithm for computing persuasive contrastive explanations. Both our definition of persuasive contrastive explanation and the proposed algorithm can be employed beyond the current scope of Bayesian networks.

show abstract

Section: Introductionmentioning

confidence: 99%

Persuasive Contrastive Explanations for Bayesian Networks

Koopman

Renooij

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…We randomly split the data into equally balanced thirds to train, recalibrate, and validate the model. Missing data among the training data set were imputed during model development using the structural expectation maximization algorithm 16,18 . We applied the Augmented Markov Blanket supervised learning algorithm to define the machine-driven direct and indirect causal relationships between the need for neurosurgical intervention and the selected variables 17 .…”

Section: Methodsmentioning

confidence: 99%

“…A Bayesian network estimates the probability of a dependent variable using the joint probability distribution of observed or unobserved predictor variables. 16,17 We used the software package BayesiaLab (Franklin, TN) to train a Bayesian network to predict the probability of neurosurgical intervention following arrival to the hospital among injured children and adolescents using immediately available emergency department features. We assigned this approach the acronym NINJA: Neurosurgery after INJury in pediAtrics.…”

Section: Bayesian Model Developmentmentioning

confidence: 99%

“…Missing data among the training data set were imputed during model development using the structural expectation maximization algorithm. 16,18 We applied the Augmented Markov Blanket supervised learning algorithm to define the machine-driven direct and indirect causal relationships between the need for neurosurgical intervention and the selected variables. 17 Because the strength of these relationships is not equivalent, a uniform structural coefficient threshold may overfit or underfit the machine-driven model.…”

Section: Bayesian Model Developmentmentioning

confidence: 99%

See 1 more Smart Citation

Development and validation of a Bayesian network predicting neurosurgical intervention after injury in children and adolescents

Sullivan

Sippel

Matison

et al. 2023

J Trauma Acute Care Surg

View full text Add to dashboard Cite

BACKGROUND:Timely surgical decompression improves functional outcomes and survival among children with traumatic brain injury and increased intracranial pressure. Previous scoring systems for identifying the need for surgical decompression after traumatic brain injury in children and adults have had several barriers to use. These barriers include the inability to generate a score with missing data, a requirement for radiographic imaging that may not be immediately available, and limited accuracy. To address these limitations, we developed a Bayesian network to predict the probability of neurosurgical intervention among injured children and adolescents (aged 1-18 years) using physical examination findings and injury characteristics observable at hospital arrival. METHODS:We obtained patient, injury, transportation, resuscitation, and procedure characteristics from the 2017 to 2019 Trauma Quality Improvement Project database. We trained and validated a Bayesian network to predict the probability of a neurosurgical intervention, defined as undergoing a craniotomy, craniectomy, or intracranial pressure monitor placement. We evaluated model performance using the area under the receiver operating characteristic and calibration curves. We evaluated the percentage of contribution of each input for predicting neurosurgical intervention using relative mutual information (RMI). RESULTS:The final model included four predictor variables, including the Glasgow Coma Scale score (RMI, 31.9%), pupillary response (RMI, 11.6%), mechanism of injury (RMI, 5.8%), and presence of prehospital cardiopulmonary resuscitation (RMI, 0.8%).The model achieved an area under the receiver operating characteristic curve of 0.90 (95% confidence interval [CI], 0.89-0.91) and had a calibration slope of 0.77 (95% CI, 0.29-1.26) with a y intercept of 0.05 (95% CI, −0.14 to 0.25). CONCLUSION:We developed a Bayesian network that predicts neurosurgical intervention for all injured children using four factors immediately available on arrival. Compared with a binary threshold model, this probabilistic model may allow clinicians to stratify management strategies based on risk.

show abstract

“…16 This modeling approach allows the estimation of the probability of a dependent variable using observed or unobserved values of each independent variable. 16,17 We used the software package BayesiaLab (Franklin, TN) to train a Bayesian belief network to predict if a patient receives a packed red blood cell transfusion within 4 hours after arrival to the hospital. We assigned this approach the acronym TRAIN: Transfusion pRobability After INjury.…”

Section: Bayesian Network Developmentmentioning

confidence: 99%

Development and validation of a Bayesian belief network predicting the probability of blood transfusion after pediatric injury

Sullivan

Milestone

Tempel

et al. 2022

J Trauma Acute Care Surg

View full text Add to dashboard Cite

BACKGROUND:Early recognition and intervention of hemorrhage are associated with decreased morbidity in children. Triage models have been developed to aid in the recognition of hemorrhagic shock after injury but require complete data and have limited accuracy. To address these limitations, we developed a Bayesian belief network, a machine learning model that represents the joint probability distribution for a set of observed or unobserved independent variables, to predict blood transfusion after injury in children and adolescents. METHODS:We abstracted patient, injury, and resuscitation characteristics of injured children and adolescents (age 1 to 18 years) from the 2017 to 2019 Trauma Quality Improvement Project database. We trained a Bayesian belief network to predict blood transfusion within 4 hours after arrival to the hospital following injury using data from 2017 and recalibrated the model using data from 2018. We validated our model on a subset of patients from the 2019 Trauma Quality Improvement Project. We evaluated model performance using the area under the receiver operating characteristic curve and calibration curves and compared performance with pediatric age-adjusted shock index (SIPA) and reverse shock index with Glasgow Coma Scale (rSIG) using sensitivity, specificity, accuracy, and Matthew's correlation coefficient (MCC). RESULTS:The final model included 14 predictor variables and had excellent discrimination and calibration. The model achieved an area under the receiver operating characteristic curve of 0.92 using emergency department data. When used as a binary predictor at an optimal threshold probability, the model had similar sensitivity, specificity, accuracy, and MCC compared with SIPA when only age, systolic blood pressure, and heart rate were observed. With the addition of the Glasgow Coma Scale score, the model has a higher accuracy and MCC than SIPA and rSIG. CONCLUSION:A Bayesian belief network predicted blood transfusion after injury in children and adolescents better than SIPA and rSIG. This probabilistic model may allow clinicians to stratify hemorrhagic control interventions based upon risk.

show abstract

A Taxonomy of Explainable Bayesian Networks

Cited by 15 publications

References 25 publications

Persuasive Contrastive Explanations for Bayesian Networks

Persuasive Contrastive Explanations for Bayesian Networks

Development and validation of a Bayesian network predicting neurosurgical intervention after injury in children and adolescents

Development and validation of a Bayesian belief network predicting the probability of blood transfusion after pediatric injury

Contact Info

Product

Resources

About