Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
teaam:start [2019/06/28 07:39]
gjn [Paper submission] sched
teaam:start [2020/04/15 17:52] (current)
gjn [Transparent, Explainable and Affective AI in Medical Systems (TEAAM)]
Line 1: Line 1:
 ====== Transparent,​ Explainable and Affective AI in Medical Systems (TEAAM) ====== ====== Transparent,​ Explainable and Affective AI in Medical Systems (TEAAM) ======
  
-TEAAM 2019 is a workshop to be held on the [[http://aime19.aimedicine.info|17th Conference on AI in Medicine (AIME)]]+**The permanent webpage for TEAAM is [[http://teaam.geist.re]]**
  
-Chairs: [[http://​gjn.re|Grzegorz J. Nalepa]], [[http://​www.ri.fzv.um.si/​gstiglic/​|Gregor Stiglic]], [[http://​islab.hh.se/​slanow|Sławomir Nowaczyk]], [[https://​webs.um.es/​jmjuarez|Jose M. Juarez]], [[http://​www.cs.put.poznan.pl/​jstefanowski/​|Jerzy Stefanowski]] 
  
-{{ :teaam:aime2019teaam-cfp2.pdf |Call for papers}}+TEAAM 2020 is the 2nd edition of workshop to be held on the [[http://​icdm2020.bigke.org/​|ICDM 202020th IEEE International Conference on Data Mining]] 
 + 
 +Chairs:  
 +[[https://​webs.um.es/​jmjuarez|Jose M. Juarez]],  
 +[[http://​gjn.re|Grzegorz J. Nalepa]],  
 +[[http://​islab.hh.se/​slanow|Sławomir Nowaczyk]],  
 +[[http://​www.cs.put.poznan.pl/​jstefanowski/​|Jerzy Stefanowski]],​ 
 +[[http://​www.ri.fzv.um.si/​gstiglic/​|Gregor Stiglic]]. 
 + 
 +The 1st edition TEAAM 2019 was held on the [[http://​aime19.aimedicine.info|17th Conference on AI in Medicine (AIME)]]. 
 +Workshop proceedings [[https://​link.springer.com/​book/​10.1007%2F978-3-030-37446-4]]
  
  
 ===== Organizers ===== ===== Organizers =====
-Grzegorz J. Nalepa, AGH University of Science and Technology, Jagiellonian University, Poland\\ 
-Gregor Stiglic, University of Maribor, Slovenia\\ 
-Sławomir Nowaczyk, Halmstad University, Sweden\\ 
 Jose M. Juarez, University of Murcia, Spain\\ Jose M. Juarez, University of Murcia, Spain\\
-Jerzy Stefanowski,​ Poznan University of Technology, Poland+Grzegorz J. Nalepa, Jagiellonian University, Poland\\ 
 +Sławomir Nowaczyk, Halmstad University, Sweden\\ 
 +Jerzy Stefanowski,​ Poznan University of Technology, Poland\\ 
 +Gregor Stiglic, University of Maribor, Slovenia\\
  
 ===== Abstract ===== ===== Abstract =====
-Medical systems highlight important requirements and challenges for the AI solutions. In particular, demands for interpretability of models and knowledge representations are much higher than in other domains. The current health-related AI applications rarely provide ​an integrated yet transparent and humanized solutions. However, from both patient'​s and doctor'​s perspective,​ there is need for approaches that are comprehensive,​ credible and trusted. By explaining the reasoning behind recommendations,​ the medical ​AI systems support users to accept or reject their predictions. Furthermore,​ healthcare is particularly challenging due to medicine ​and ethical requirements,​ laws and regulations and the real caution taken by physicians while treating the patients. Improving individual'​s health is a complex process, requiring understanding and collaboration between the doctor ​and the patient. Building up this collaboration not only requires individualized ​personalization, but also a proper adaptation to the gradual changes of patient’s condition, including their emotional state. Recently, AI solutions have been playing an important mediating role in understanding how both medical and personal factors interact with respect to diagnosis and treatment adherence. As the number of such applications is expected to rapidly grow in next years, their humanized aspect will play a critical role in their adoption. This workshop will bring together researchers from academia and industry to discuss current topics of interest in interpretability,​ explainability and affect related to AI based systems present in different healthcare domains.+Medical systems highlight important requirements and challenges for AI and data mining ​solutions. In 
 +particular, demands for interpretability of models and knowledge representations are much higher than 
 +in other domains. The current health-related AI/​ML/​DM ​applications rarely provide integrated yet 
 +transparent and humanized solutions. However, from both patient'​s and doctor'​s perspective,​ there is 
 +need for approaches that are comprehensive,​ credible and trusted. By explaining the reasoning behind 
 +recommendations,​ the medical ​intelligent ​systems support users to accept or reject their predictions. 
 + 
 +Furthermore,​ healthcare is particularly challenging due to medical ​and ethical requirements,​ laws and 
 +regulations and the real caution taken by physicians while treating the patients. Improving ​an 
 +individual'​s health is a complex process, requiring understanding and collaboration between the 
 +healthcare team and the patient. Building up this collaboration not only requires individualized 
 +personalisation, but also a proper adaptation to the gradual changes of patient’s condition, including 
 +their emotional state. Recently, AI solutions have been playing an important mediating role in 
 +understanding how both medical and personal factors interact with respect to diagnosis and treatment 
 +adherence. As the number of such applications is expected to rapidly grow in the next few years, their 
 +humanized aspect will play a critical role in their adoption. 
 + 
 +This workshop will bring together researchers from academia and industry to discuss current topics of 
 +interest in interpretability,​ explainability and affect related to intelligent ​systems present in different 
 +healthcare domains. 
  
 ===== Topics of interest =====  ===== Topics of interest ===== 
Line 22: Line 51:
   * comprehensive and interpretable knowledge representations   * comprehensive and interpretable knowledge representations
   * interpretable machine learning in medical applications   * interpretable machine learning in medical applications
-  * explanatory user interfaces and human computer interaction for explainable ​AI +  * human-computer interaction for explainable ​machine learning and pattern recognition 
-  * consequences of black-box ​AI systems in medicine+  * consequences of black-box ​intelligent ​systems in medicine
   * ethical aspects, law and social responsibility   * ethical aspects, law and social responsibility
   * emotion-based personalization and affective computing solutions in medicine   * emotion-based personalization and affective computing solutions in medicine
Line 30: Line 59:
   * context-aware interpretable medical systems   * context-aware interpretable medical systems
   * empowering patients and self-management through understandable AI   * empowering patients and self-management through understandable AI
 +  * person-centred health care enabled by explainable data mining and machine learning
  
 ===== Motivation =====  ​ ===== Motivation =====  ​
-The investment and development of AI in the clinical field offers huge societal benefits in the current era of digital medicine, with a significant amount of data around healthcare processes captured in the form of Electronic Health Records, health insurance claims, medical imaging databases, disease registries, spontaneous reporting sites, clinical trials, etc. This positive impact is put under the spotlight regarding the medical responsibilities,​ the potentially harmful use, the emerging interest in the regulation of algorithms and the need of explanations. Predictive ​modeling ​becomes increasingly necessary for both data analysts and health care professionals,​ as it offers unique opportunities for deriving health care insights. At the same time, these opportunities come with significant dangers and risks that are unlike anything we have seen in the past. This controversial discussion provides a number of research challenges such as1) interpretability in Machine Learning/​AI,​ 2) affective AI in medicine, 3) Data safety - patient data are highly sensitive and require appropriate safety measures and regulation, 4) Data heterogeneity - medical data comes in many forms including: structured, unstructured,​ text, images, continuous signals from sensors, etc., 5) Sparsity, imperfectness and data gaps – patient records ​maybe sparse due to infrequent clinical visits, and often, data are not equally collected at each medical encounter as well as they are affected by various ​ sources of imperfectness.+The investment and development of AI, machine learning and data mining ​in the clinical field offers 
 +huge societal benefits in the current era of digital medicine, with a significant amount of data around 
 +healthcare processes captured in the form of Electronic Health Records, health insurance claims, 
 +medical imaging databases, disease registries, spontaneous reporting sites, clinical trials, etc. This 
 +positive impact is put under the spotlight regarding the medical responsibilities,​ the potentially harmful 
 +use, the emerging interest in the regulation of algorithms and the need for explanations. Predictive 
 +modelling ​becomes increasingly necessary for both data analysts and health care professionals,​ as it 
 +offers unique opportunities for deriving health care insights. At the same time, these opportunities come 
 +with significant dangers and risks that are unlike anything we have seen in the past. This controversial 
 +discussion provides a number of research challenges such as 1) interpretability in Machine Learning/​AI,​ 
 +2) affective AI in medicine ​and healthcare, 3) Data safety - patient data are highly sensitive and require 
 +appropriate safety measures and regulation, 4) Data heterogeneity - medical data comes in many forms 
 +including: structured, unstructured,​ text, images, continuous signals from sensors, etc., 5) Sparsity, 
 +imperfectness and data gaps – patient records ​may be sparse due to infrequent clinical visits, and often, 
 +data are not equally collected at each medical encounter as well as they are affected by various sources 
 +of imperfectness.
  
  
-===== Schedule =====  ​ 
- 
- 
-{{:​teaam:​mgrzegorzek-photo.jpg?​150 |}} 
-**Keynote speaker:** Prof. Marcin Grzegorzek, Universität zu Lübeck, Institut für Medizinische Informatik 
- 
-**Title:** //​Human-centred Pattern Recognition for Assistive Health Technologies//​ 
- 
-**Abstract:​** We live in a data-driven society and significantly contribute to this concept by voluntarily generating terabytes of data everyday. Pattern recognition algorithms that automatically analyse and interpret that huge amount of heterogeneous data towards prevention (early risk detection), diagnosis, assistance in therapy/​aftercare/​rehabilitation as well as nursing have achieved an extremely high scientific, societal and economic importance. In this talk, Marcin Grzegorzek will present his research in the area motivated above considering,​ apart from machine learning, aspects of hardware, participatory design and ELSI (Ethical, Legal and Social Implications). Two of Marcin'​s projects, (1) Cognitive Village: Adaptively Learning Technical Support Platform for Elderly (funded by the German Federal Ministry of Education and Research) and (2) My-AHA: My Active and Healthy Ageing (EC Horizon 2020), will serve as concrete application scenarios. 
- 
-===== Proceedings =====  
-We are aiming at proving CEUR WS proceedings containg all the papers presented at the workshop. Furthermore,​ we are considering a proposal of a special issue of a JCR journal. 
  
 ===== Program Committee =====  ===== Program Committee ===== 
 (tentative)\\ (tentative)\\
-Martin Atzmueller, ​Univeristy ​of Tilburg, The Netherlands\\+Martin Atzmueller, ​University ​of Tilburg, The Netherlands\\
 Piotr Augustyniak,​ AGH University of Science and Technology, Poland\\ Piotr Augustyniak,​ AGH University of Science and Technology, Poland\\
-Jerzy Błaszczyński,​ Poznań ​University of Technology, Poland\\+Jerzy Błaszczyński,​ Poznań ​Supercomputing and Networking Center, Poland\\
 David Camacho, Universidad Autonoma de Madrid, Spain\\ David Camacho, Universidad Autonoma de Madrid, Spain\\
 Manuel Campos, University of Murcia, Spain\\ Manuel Campos, University of Murcia, Spain\\
Line 58: Line 91:
 Alejandro Rodríguez González, Universidad Politecnica de Madrid\\ Alejandro Rodríguez González, Universidad Politecnica de Madrid\\
 Marcin Grzegorzek, Universität zu Lübeck, Germany\\ Marcin Grzegorzek, Universität zu Lübeck, Germany\\
-Jean-Baptiste Lamy,  University Paris 13, France\\+Jean-Baptiste Lamy, University Paris 13, France\\
 Giorgio Leonardi, University Piemonte Orientale, Italy\\ Giorgio Leonardi, University Piemonte Orientale, Italy\\
 Helena Lindgren, Umeå University, Sweden\\ Helena Lindgren, Umeå University, Sweden\\
 Zachary Lipton, Carnegie Mellon University, USA\\ Zachary Lipton, Carnegie Mellon University, USA\\
-Peter Lucas Leiden University, The Netherlands\\ 
 Agnieszka Ławrynowicz,​ Poznań University of Technology, Poland\\ Agnieszka Ławrynowicz,​ Poznań University of Technology, Poland\\
 Juan Carlos Nieves, Umeå University, Sweden\\ Juan Carlos Nieves, Umeå University, Sweden\\
Line 72: Line 104:
 Myra Spiliopoulou,​ Otto-von-Guericke-University Magdeburg, Germany\\ Myra Spiliopoulou,​ Otto-von-Guericke-University Magdeburg, Germany\\
 Stephen Swift, Brunel University, United Kingdom\\ Stephen Swift, Brunel University, United Kingdom\\
 +Szymon Wilk, Poznań University of Technology, Poland\\
 Allan Tucker, Brunel University, United Kingdom\\ Allan Tucker, Brunel University, United Kingdom\\
-Cristina Soguero Ruiz, Universidad Rey Juan Carlos, Spain\\+Cristina Soguero Ruiz, Universidad Rey Juan Carlos, Spain 
  
 ===== Important Dates ===== ===== Important Dates =====
  
-  * Paper submission:​ 2019-04-29 +  * Paper submission:​  
-  * Notification:​ 2019-05-13 +  * Notification:​ 
-  * Camera-ready:​ 2019-05-31 +  * Camera-ready:​ 
-  * Workshop: 2019-06-26-29+  * Workshop:
  
 ===== Paper submission ===== ===== Paper submission =====
  
-The Easychair installation at https://​easychair.org/​conferences/?​conf=teaam2019 shoud be used for submissions. We encourage full (12pp) as well as short (6pp) original research papers. Springer LNCS format of PDF submissions is required.+The Easychair installation at https://​easychair.org/​conferences/?​conf=teaam2020 should ​be used for submissions. ​ 
 +We encourage full (12pp) as well as short (6pp) original research papers. ​ 
 +Springer LNCS format of PDF submissions is required.
  
 ===== Schedule ===== ===== Schedule =====
  
-<​pre>​ +TBA
-    9:00-10:30 Opening session (Chair: J. Stefanowski) +
- +
-    9:00 TEAAM Opening: Workshop chairs +
-    9:15 Marcin Grzegorzek: Human-centred Pattern Recognition for Assistive Health Technologies +
- +
-    10:30-10:50 Coffee Break +
- +
-    10:50-11:50 Session 1 (Chair: J. Juarez) +
- +
-    10:50 Olga Kamińska, et al.: Self organizing maps using acoustic features for prediction of state change in bipolar disorder +
-    11:10 Alexander Galozy, et al.: Towards Understanding ICU Treatments using Patient Health Trajectories +
-    11:30 Erica Ramirez, et al.: Interpretable Anomaly Detection and Classification of Multivariate Time Series  +
-                                 for Transparent Human Gait Analysis +
- +
-    11:50-12:50 Session 2 (Chair: S. Nowaczyk) +
- +
-    11:50 Leon Kopitar, et al.: Local vs. Global Interpretability of Machine Learning Models in Type 2 Diabetes Mellitus Screening +
-    12:10 Bernardo Cánovas Segura, et al.: Exploring antimicrobial resistance prediction using post-hoc interpretable methods +
-    12:30 Katarzyna Kobylińska,​ et al.: Explainable machine learning for modeling of early postoperative mortality  +
-                                        in lung cancer +
- +
-    12:50 - 14:00 Lunch Break +
- +
-    14:00 - 15:30 Session 3 (Chair: G. Stiglic) +
- +
-    14:00 Keyuan Jiang, et al.: An Explainable Approach of Inferring Potential Medication Effects from Social Media Data +
-    14:20 Xuwen Wang, et al.: A Computational Framework towards Medical Image Explanation +
-    14:40 Discussion and workshop closing +
- +
- +
-    15:30 - 16:00  (farewell) Coffee Break +
-</​pre>​+
  
teaam/start.1561700358.txt.gz · Last modified: 2019/06/28 07:39 by gjn
Driven by DokuWiki Recent changes RSS feed Valid CSS Valid XHTML 1.0