@inproceedings{56477,
  abstract     = {{We describe a prototype of a Clinical Decision Support System (CDSS) that provides (counterfactual) explanations to support accurate medical diagnosis. The prototype is based on an inherently interpretable Bayesian network (BN). Our research aims to investigate which explanations are most useful for medical experts and whether co-constructing explanations can foster trust and acceptance of CDSS.}},
  author       = {{Liedeker, Felix and Cimiano, Philipp}},
  keywords     = {{Explainable AI, Clinical decision support, Bayesian network, Counterfactual explanations}},
  location     = {{Lissabon}},
  title        = {{{A Prototype of an Interactive Clinical Decision Support System with Counterfactual Explanations}}},
  year         = {{2023}},
}

@inproceedings{51343,
  abstract     = {{This paper presents preliminary work on the formalization of three prominent cognitive biases in the diagnostic reasoning process over epileptic seizures, psychogenic seizures and syncopes. Diagnostic reasoning is understood as iterative exploration of medical evidence. This exploration is represented as a partially observable Markov decision process where the state (i.e., the correct diagnosis) is uncertain. Observation likelihoods and belief updates are computed using a Bayesian network which defines the interrelation between medical risk factors, diagnoses and potential findings. The decision problem is solved via partially observable upper confidence bounds for trees in Monte-Carlo planning. We compute a biased diagnostic exploration policy by altering the generated state transition, observation and reward during look ahead simulations. The resulting diagnostic policies reproduce reasoning errors which have only been described informally in the medical literature. We plan to use this formal representation in the future to inversely detect and classify biased reasoning in actual diagnostic trajectories obtained from physicians.}},
  author       = {{Battefeld, Dominik and Kopp, Stefan}},
  booktitle    = {{Proceedings of the 8th Workshop on Formal and Cognitive Reasoning}},
  keywords     = {{Diagnostic reasoning, Cognitive bias, Cognitive model, POMDP, Bayesian network, Epilepsy, CDSS}},
  location     = {{Trier}},
  title        = {{{Formalizing cognitive biases in medical diagnostic reasoning}}},
  year         = {{2022}},
}

@article{9976,
  abstract     = {{State-of-the-art mechatronic systems offer inherent intelligence that enables them to autonomously adapt their behavior to current environmental conditions and to their own system state. This autonomous behavior adaptation is made possible by software in combination with complex sensor and actuator systems and by sophisticated information processing, all of which make these systems increasingly complex. This increasing complexity makes the design process a challenging task and brings new complex possibilities for operation and maintenance. However, with the risk of increased system complexity also comes the chance to adapt system behavior based on current reliability, which in turn increases reliability. The development of such an adaption strategy requires appropriate methods to evaluate reliability based on currently selected system behavior. A common approach to implement such adaptivity is to base system behavior on different working points that are obtained using multiobjective optimization. During operation, selection among these allows a changed operating strategy. To allow for multiobjective optimization, an accurate system model including system reliability is required. This model is repeatedly evaluated by the optimization algorithm. At present, modeling of system reliability and synchronization of the models of behavior and reliability is a laborious manual task and thus very error-prone. Since system behavior is crucial for system reliability, an integrated model is introduced that integrates system behavior and system reliability. The proposed approach is used to formulate reliability-related objective functions for a clutch test rig that are used to compute feasible working points using multiobjective optimization.}},
  author       = {{Kaul, Thorben and Meyer, Tobias and Sextro, Walter}},
  journal      = {{SAGE Journals}},
  keywords     = {{Integrated model, reliability, system behavior, Bayesian network, multiobjective optimization}},
  pages        = {{390 -- 399}},
  title        = {{{Formulation of reliability-related objective functions for design of intelligent mechatronic systems}}},
  doi          = {{10.1177/1748006X17709376}},
  volume       = {{Vol. 231(4)}},
  year         = {{2017}},
}