Models for Prediction, Explanation and Control: Recursive Bayesian Networks

Casini, Lorenzo; Illari, Phyllis; Russo, Federico; Williamson, Jon

doi:10.1387/theoria.784

Cited by 42 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The generalisation of formal models through Bayesian networks [71], have become popular for modelling medical prediction problems [72][73][74][75][76], representing conditional dependencies between variables in the form of a graph, so that evidence can be propagated through the network to update the diagnostic or prognostic states of a patient [77]. This reasoning process can be easily visualised in a straightforward manner.…”

Section: Interpretable Machine Learning Modelsmentioning

confidence: 99%

A Scoping Review on the Progress, Applicability, and Future of Explainable Artificial Intelligence in Medicine

González-Alday,

García-Cuesta,

Kulikowski

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Due to the success of artificial intelligence (AI) applications in the medical field over the past decade, concerns about the explainability of these systems have increased. The reliability requirements of black-box algorithms for making decisions affecting patients pose a challenge even beyond their accuracy. Recent advances in AI increasingly emphasize the necessity of integrating explainability into these systems. While most traditional AI methods and expert systems are inherently interpretable, the recent literature has focused primarily on explainability techniques for more complex models such as deep learning. This scoping review critically analyzes the existing literature regarding the explainability and interpretability of AI methods within the clinical domain. It offers a comprehensive overview of past and current research trends with the objective of identifying limitations that hinder the advancement of Explainable Artificial Intelligence (XAI) in the field of medicine. Such constraints encompass the diverse requirements of key stakeholders, including clinicians, patients, and developers, as well as cognitive barriers to knowledge acquisition, the absence of standardised evaluation criteria, the potential for mistaking explanations for causal relationships, and the apparent trade-off between model accuracy and interpretability. Furthermore, this review discusses possible research directions aimed at surmounting these challenges. These include alternative approaches to leveraging medical expertise to enhance interpretability within clinical settings, such as data fusion techniques and interdisciplinary assessments throughout the development process, emphasizing the relevance of taking into account the needs of final users to design trustable explainability methods.

show abstract

Section: Interpretable Machine Learning Modelsmentioning

confidence: 99%

A Scoping Review on the Progress, Applicability, and Future of Explainable Artificial Intelligence in Medicine

González-Alday,

García-Cuesta,

Kulikowski

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…It is thus not surprising that recursion is also present in many modern probabilistic programming languages (PPL) such as WebPPL [GS14] or Church [SG12]. In fact, there have been numerous approaches to extend Bayesian networks with recursion even before PPL became popular [PK00,Jae01,CIRW11]. Randomized algorithms such as Hoare's quicksort (see, e.g., [Kar91]) with random pivot selection can be readily implemented using recursion.…”

Section: Introductionmentioning

confidence: 99%

Model Checking Temporal Properties of Recursive Probabilistic Programs

Winkler,

Gehnen,

Katoen

2023

Logical Methods in Computer Science

View full text Add to dashboard Cite

Probabilistic pushdown automata (pPDA) are a standard operational model for programming languages involving discrete random choices and recursive procedures. Temporal properties are useful for specifying the chronological order of events during program execution. Existing approaches for model checking pPDA against temporal properties have focused mostly on $\omega$-regular and LTL properties. In this paper, we give decidability and complexity results for the model checking problem of pPDA against $\omega$-visibly pushdown languages that can be described by specification logics such as CaRet. These logical formulae allow specifying properties that explicitly take the structured computations arising from procedural programs into account. For example, CaRet is able to match procedure calls with their corresponding future returns, and thus allows to express fundamental program properties such as total and partial correctness.

show abstract

References

2022

Agent‐based Models and Causal Inference

View full text Add to dashboard Cite

Models for Prediction, Explanation and Control: Recursive Bayesian Networks

Cited by 42 publications

References 38 publications

A Scoping Review on the Progress, Applicability, and Future of Explainable Artificial Intelligence in Medicine

A Scoping Review on the Progress, Applicability, and Future of Explainable Artificial Intelligence in Medicine

Model Checking Temporal Properties of Recursive Probabilistic Programs

References

Contact Info

Product

Resources

About