Peter Lucas University of Twente, Enschede Radboud University, Nijmegen The Netherlands Email: peterl at cs.ru.nl

AI Research for the Future

Model-based, probabilistic learning and reasoning. Special focus on biomedical applications.

Covid-19

• Covid-19 surveillance made simple
  
• A privacy-preserving Bayesian network model for personalised COVID19 risk assessment and contact tracing

Conferences, Workshops, Special Issues

• 27th European Conference on Artificial Intelligence, 19-24 October, 2024, Santiago de Compostela, Spain
• IEEE 37th International Symposium on Computer Based Medical Systems (CBMS 2024)
• International Conference on Probabilistic Graphical Models 2024 (PGM 2024), Nijmegen, September 11 - 13, 2024
• SmarterCare Workshop: Towards smarter health care: can Artificial Intelligence help? Milan, 29th November, 2021
• Prestigious Applications of Intelligent Systems (PAIS-2012) with ECAI-2012, Montpelier, France, 29-30 August, 2012
• Emerging Smart Technologies for Personalised Healthcare 2012 (SmarTech4Health 2012) at CBMS 2012, Rome, Italy, 20-22 June, 2012
• Foundations of Biomedical Knowledge Representation, Lorentz Center, Leiden, 29th October-2nd November, 2012
• Probabilistic Problem Solving in Biomedicine (ProBioMed-2011) Bled, Slovenia, July 2, 2011
• CIHC 2010: Computational Intelligence in Health Care, Eindhoven, 20-24 September, 2010
• ACAI'09: Advanced Course in Artificial Intelligence '09, Belfast, 23-29 August, 2009
• Lorentz Centre Workshop: Computer-based Clinical Guidelines and Protocols 2008
• ECAI'06: Workshop on AI techniques in healthcare: evidence-based guidelines and protocols
• PGM'04: Probabilistic Graphical Models 2004
• Workshop on Model-based and Qualitative Reasoning in Biomedicine during AIME'03
• 27-29 October, 2002: ESF workshop, Fundamentals of Medical Informatics
• IDAMAP-2002 Workshop during ECAI 2002 (Proceedings now online!)
• Special issue of AIMED on Bayesian Models in Medicine
• Workshop on Bayesian Models in Medicine during AIME'01 (Proceedings now online)
• Workshop on Prognostic Models in Medicine during AIME'99 (Proceedings online)
• Workshop on Intelligent Prognostic Methods in Medical Diagnosis and Treatment Planning during CESA'98

Research Activities

• Self-management, patient empowerment, mHealth:
  • AERIAL and COPD+ project [Website]
  • eMomCare project [Video]
• Disease modelling and multimorbidity: PANDORA project
• Industrial applications of intelligent systems:
  • Octopus project
  • Metis project
• B-Screen project: Bayesian networks and computer-aided detection
• TimeBayes and ProBayes projects: Bayesian networks and machine learning
• Protocure project: using formal methods in guideline design
• Theory of model-based diagnosis
• Bayesian network and decision theory
• Logical foundations of knowledge-based systems
• Biomedical modelling: (Domain-status report now online)
• ICEA project: Modelling bacterial colonisation by means Bayesian networks, and applying decision theory to improve the use of antibiotics in the intensive care unit
• NHL and CRC projects: Optimal treatment of patients with cancer (non-Hodgkin lymphoma of the stomach and colorectal cancer)
• Stroke project: Prediction of outcome of stroke, taking MRI data into account
• Vitatron: Intelligent systems for pacemaker reprogramming

Books

• Foundations of Biomedical Knowledge Representation, Springer, LNAI 9521, 2015
• Computer-based Medical Guidelines and Protocols: A Primer and Current Trends. Studies in Health Technology and Informatics, Vol. 139, A. Ten Teije, S. Miksch and P. Lucas, July 2008, approx. 282 pp, hardcover, ISBN: 978-1-58603-873-1
• Advances in Probabilistic Graphical Models. Series: Studies in Fuzziness and Soft Computing , Vol. 213. Lucas, Peter; Gamez, Jose A.; Salmeron, Antonio (Eds.) 2007, X, 396 p., hardcover, ISBN: 978-3-540-68994-2
• Peter Lucas & Linda van der Gaag, Principles of Expert Systems, Addison-Wesley, Wokingham, 1991 (freely available textbook)

• Introductory scientific paper about knowledge-based expert systems, written for UNESCO (UNESCO, 2007)

• Conversion of a Rule-based System to a Belief Network (including design issues) (Medical Informatics, 1993)
• Using Theorem Proving Techniques to build Medical Expert Systems (Medical Artificial Intelligence, 1993)
• Refinement of a Rule-based System (Medical Artificial Intelligence, 1994)
• Logic Engineering in Medicine (Knowledge Engineering Review, 1995)
• Knowledge Acquisition for Decision-theoretic Expert Systems (AISB, 1996)
• A Decision-theoretic Network Approach to Treatment Management and Prognosis (Proceedings of ES'97)
• Decision Support in the Management of non-Hodgkin lymphoma of the Stomach (Methods of Information in Medicine, 1998)
• Prognostic methods in medicine (Artificial Intelligence in Medicine, 1999)
• A diagnostic advice systems based on pathophysiological models of diseases (Proceedings MIE99)
• Improving antibiotic therapy of ventilator associated pneumonia using a probabilistic approach (Proceedings MIE99)
• Probabilistic and decision-theoretic approach to the management of infectious disease in the ICU (Artificial Intelligence in Medicine 2000; 19(3): 251-279)
• Prognostic models in medicine: AI and statistical approaches (Methods of Information in Medicine 2001; 40: 1-5)
• Bayesian networks in medicine: a model-based approach to medical decision making (K-P. Adlassnig (ed.), Proceedings of the EUNITE workshop on Intelligent Systems in patient Care, Vienna, Oct. 2001, pp. 73-97)
• A model-based approach to improved prescription of antibiotics (MONET Newsletter, 2003)
• Quality checking of medical guidelines through logical abduction (Proceedings AI-2003, Springer, London, 2003, pp. 309-321)
• Meta-level verification of the quality of medical guidelines using interactive theorem proving (JELIA-2004, LNAI 3229, Springer, Berlin Heidelberg, 2004, pp. 654-666)
• Verification of medical guidelines using background knowledge in task networks (IEEE Transactions on Knowledge and Data Engineering, vol. 19, no. 6, 2007, pp. 832-846)
• Checking the quality of clinical guidelines using automated reasoning tools (Theory and Practice of Logic Programming, vol. 8, pp. 941-641, 2008)
• A decision support system for breast cancer detection in screening program (Proceedings ECAI 2008, pp. 658-662)
• A dynamic Bayesian network for diagnosing ventilator-associated pneumonia in ICU patients (Expert Systems with Applications, vol. 36, 2009, pp. 1249-1258)
• Improved mammographic CAD performance using multi-view information: a Bayesian network framework (Phys. Med. Biol. 54 (2009) 1131-1147)
• Modelling treatment effects in a clinical Bayesian network using Boolean threshold functions (Artificial Intelligence in Medicine, 2009)
• Using model checking for critiquing based on clinical guidelines (Artificial Intelligence in Medicine, vol. 46 (2009) 19-36)
• Causal probabilistic modelling for two-view mammographic analysis (AI in Medicine, LNAI 5651, 2009, pp. 395-404)
• Managing COPD exacerbations with telemedicine (AI in Medicine, LNAI 6747, 2011, pp. 169-178)
• A probabilistic framework for image information fusion with an application to mammographic analysis (Medical Image Analysis 16 (2012) 865-875)
• On the interplay of machine learning and background knowledge in image interpretation by Bayesian networks (AI in Medicine 57 (2013) 73-86)
• An autonomous mobile system for the management of COPD (Journal of Biomedical Informatics 46 (2013) 458-469)
• Describing disease processes using a probabilistic logic of qualitative time (AI in Medicine 59 (2013) 143-155)
• Learning Bayesian networks for clinical time series analysis (Journal of Biomedical Informatics 48 (2014) 94-105)
• Exploiting causal functional relationships in Bayesian network modelling for personalised healthcare (International Journal of Approximate Reasoning 55 (2014) 59-73)
• Understanding disease processes by partitioned dynamic Bayesian networks (Journal of Biomedical Informatics 61 (2016) 283-297)

Model-based Reasoning, Probabilistic Logics and Bayesian Networks

• Symbolic Diagnosis and its Formalisation (Knowledge Engineering Review, 1997)
• Modeling Interactions in Diagnosis (Proceedings of Proceedings of CESA'96 IMACS Multiconference, Symposium on Modelling, Analysis and Simulation, 1996)
• Diagnosis as Hypothesis Refinement (Proceedings of NAIC'97, 1997)
• Analysis of notions of diagnosis (Artificial Intelligence, vol. 105, 1998)
• A model-based system for pacemaker reprogramming (Artificial Intelligence in Medicine 1999; 17: 249-269)
• Certainty-factor-like structures in Bayesian networks (Technical Report, 2000; the Knowledge-based Systems journal 2001; 14: 327-335)
• Bayesian model-based diagnosis (International Journal of Approximate Reasoning 2001; 27(2): 99-119)
• Comparison of rule-based and Bayesian network approaches in medical diagnostic systems (In: S. Quaglini, P. Barahona, S. Andreassen (eds.). Artificial Intelligence in Medicine (AIME2001), LNAI2101, Springer, Berlin, 2001, pp. 283-292)
• Decision network semantics of branching constraint satisfaction problems (Proceedings ECSQARU 2003, LNAI2711. Springer, Berlin, 2003, pp. 230-242)
• Bayesian network modelling by qualitative patterns (ECAI 2002, 690-694)
• A system for pacemaker treatment advice (ECAI 2004, pp. 735-739)
• Bayesian networks in biomedicine and health-care (Artificial Intelligence in Medicine 30 (2004) 201-214)
• Bayesian network modelling through qualitative patterns (Artificial Intelligence 2005; 163: 233-263)
• Exploiting causal independence in large Bayesian networks (Knowledge-based Systems, 18 (2005) 153-162)
• Conflict-based diagnosis: adding uncertainty to model-based diagnosis (IJCAI 2007, pp. 380-388)
• A generic qualitative characterization of independence of causal influence Journal of Approximate Reasoning, 48 (2008) 214-236
• Explaining clinical decisions by extracting regularity patterns (Decision Support Systems, 44 (2008) 397-408)
• A Bayesian decision-support system for diagnosing ventilator-associated pneumonia (Intensive Care Medicine, 2008)
• Standardizing Research Methods for Prognostics (International Conference on Prognostics and Health Management 2008)
• The Probabilistic Interpretation of Model-based Diagnosis (ECSQARU 2009, LNAI 5590, pp. 204-215)
• Using Bayesian networks in an industrial setting: making printing systems adaptive (Proceedings of ECAI-2010, H. Coelho, et al., IOS Press, Amsterdam, pp. 401-406)
• Modelling the interactions between discrete and continuous causal factors in Bayesian networks (Proceedings of the Fifth European Workshop on Probabilistic Graphical Models (PGM-2010), Petri Myllymki, Teemu Roos and Tommi Jaakkola (Eds), HIIT Publications 2010, pp. 185-193)
• Generalising the interaction rules in probabilistic logic (IJCAI 2011, pp. 912-917)
• Inference for a New Probabilistic Constraint Logic (IJCAI 2013)
• Multilevel Bayesian networks for the analysis of hierarchical health care data (AI in Medicine 2013, vol. 57, 171-183)
• Modeling the interaction between discrete and continuous causal factors in Bayesian Networks (International Journal of Intelligent Systems, 30 (2015) 209-235)
• Approximate probabilistic inference with bounded error for hybrid probabilistic logic programming (Proc IJCAI 2016, NY)
• Weighted positive binary decision diagrams for exact probabilistic inference (International Journal of Approximate Reasoning 90 (2017) 411-432)
• A compositional approach to probabilistic knowledge compilation (International Journal of Approximate Reasoning 138 (2021) 38-66)

• Enhancement of learning by declarative expert-based models (IDAMAP, 2000)
• Expert knowledge and its role in learning Bayesian networks in medicine (extended version) (In: S. Quaglini, P. Barahona, S. Andreassen (eds.). Artificial Intelligence in Medicine (AIME2001), LNAI2101, Springer, Berlin, 2001, pp. 156-166)
• Learning Bayesian-network topologies in realistic medical domains (IDAMAP, 2001)
• Restricted Bayesian network structure learning (in: G.A. Gamez, S. Moral, A. Salmeron (eds.). Advances in Bayesian Networks, Studies in Fuzziness and Soft Computing, vol. 146, Springer-Verlag, Berlin, 2004, pp. 217-232). )
• Markov equivalence in Bayesian networks (Technical Report, NIII-R0436, 2004)
• Bayesian analysis, pattern analysis, and data mining in health care (Current Opinion in Critical Care 2004, vol. 10, pp. 399-403)
• Integrating logical reasoning and probabilistic chain graphs (Proceedings ECML PKDD 2009, volume 5781 of LNAI, pages 548-563, 2009)
• Using local context information to improve automatic mammographic mass detection (Proceedings of MEDINFO-2010, IOS Press, Amsterdam, pp. 1291-1295)
• Critiquing knowledge representation in medical Image interpretation using structure learning (KR4HC-2010, volume 6512 of LNAI, Springer, 2011)
• Exploiting Experts' Knowledge for Structure Learning of Bayesian Networks (IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017)
• A comparison between discrete and continuous time Bayesian networks in learning from clinical time series data with irregularity (Artificial Intelligence In Medicine 95 (2019) 104-117)
• A probabilistic framework for predicting disease dynamics: A case study of psychotic depression (Journal of Biomedical Informatics 95 (2019) 103232)

Medicine

• Computer-assisted decision support for the diagnosis and treatment of infectious diseases in intensive care units (The Lancet of Infectious Disease 2005, vol. 5, 305-312)
• Effects of systemic antibiotic therapy on bacterial resistence in the repiratory tract of mechanically ventilated patients (Intensive Care Medicine 2008, vol. 34, pp. 692-699)
• Predicting pathogens causing ventilator-associated pneumonia using a Bayesian network model (Journal of Antimicrobial Chemotherapy 2008, vol. 62, 184-188)
• Multilevel temporal Bayesian networks can model longitudinal change in multimorbidity (Journal of Clinical Epidemiology 2013, vol. 66, pp. 1405-1416)
• Preoperative risk stratification in endometrial cancer (ENDORISK) by a Bayesian network model: A development and validation study (PLoS Med 17 (5) 2020: e1003111. https://doi.org/10.1371/journal. pmed.1003111)

Teaching Material

• ACAI09: The Model-based Approach to Medical Decision Support
• Machine Learning and Data Mining
• SIKS course Learning and Reasoning:
  Probabilistic Reasoning: Uncertainty and Bayesian Networks
• SIKS course Computational Intelligence:
  Expert Systems: a knowledge-based approach to intelligent systems
• Bayesian Networks
• Programming in Prolog
• Intelligent Systems
• Knowledge Representation and Reasoning
• Medical Informatics