Artificial Intelligence, Causality and Personalized Medicine (AICPM 2022)

Workshop on AI, Causality, and Personalized Medicine

The AICPM workshop aims to bring together researchers interested in AI, Causality and Personalized Medicine, and move forward discussions on integrating causal reasoning into machine learning methods to tackle challenging AI problems in personalized medicine. We welcome researchers from all relevant disciplines, including but not limited to computer science, statistics, physics, philosophy, and medicine. Although personalized medicine is the primary focus application area for the workshop, researchers applying AI and Causality methods to other application areas (e.g., Earth Sciences, Finance etc.) are welcome.


Machine learning methods have been immensely successful in tackling several problems across different domains such as computer vision, natural language processing, signal processing and many more. With the advent of deep neural networks, the performance of these methods have been pushed even further. However, in domains such as personalized medicine, increasingly it is being recognized that a fundamental piece is missing among these methods, which is causal reasoning. Cause and effect relationships are central in how we humans make sense of the world around us, how we act upon it, and how we respond to changes in our environment.

Current machine learning systems have no understanding of the relationship between causes and effects in their domain. As a result, they are brittle, cannot transfer to new domains, do not generalize except from one data point to the next (sampled from the same distribution) and they cannot explain their actions to users. Consequently, a new research direction has emerged: Integrating causality into machine learning methods, to pave the way for designing next generation intelligent systems. Given their causal reasoning, these methods will be suitable to tackle the issues affecting current methods such as explainability, generalizability and robustness, and allow researchers to represent medical background knowledge in an appropriate way.

Register here


The workshop will be held in a hybrid way, taking place at the Leibniz AI Lab & L3S Research Center, Leibniz Universität Hannover, Germany as well as online.


Avishek Anand, TU Delft and L3S
Gjergji Kasneci, University of Tübingen
Marco Zaffalon, IDSIA and Artificialy
Philip Dawid, University of Cambridge
Prasenjit Mitra, Penn State University and L3S
Roi Reichert,  Technion – Israel Institute of Technology
Tim Friede, Universitätsmedizin Göttingen
Ricardo Silva, University College London
Andreas Gerhardus, German Aerospace Center
Gourab Patro, IIT Kharagpur and L3S
Jalal Etesami, EPFL
Amit Sharma, Microsoft Research
Jonas Peters, University of Copenhagen
Stefan Bauer, KTH Stockholm
Zhiliang Wu, Siemens Technology
Sara Magliacane, University of Amsterdam and MIT-IBM Watson AI lab
Tom Claassen, Radboud University


Day 1

09:00 - 09:15Opening and Welcome
09:15 - 10:00Philip DawidWhat Should be the Focus of Statistical Personalized MedicinePhilip Dawid
10:00 - 10:45Stefan BauerTowards Learning Causal Representations & Interactive Benchmarks
10:45 - 10:55Break
10:55 - 11:30Sara MagliacaneCausality-inspired ML: what can causality do for ML? The domain adaptation caseSara Magliacane
11:30 - 12:15Jonas PetersExploiting Invariance: from Causal Discovery to Robust Decision Making Jonas Peters
12:15 - 13:25Lunch Break
13:25 - 14:10Jalal EtesamiFoundations of Causal Inference: Challenges and Opportunities
14:10 - 14:45Andreas GerhardusReliable causal discovery in time seriesAndreas Gerhardus
14:45 - 15:00Break
15:00 - 15:45Gjergji KasneciTowards realistic and robust counterfactual explanations for tabular dataGjergji Kasneci
15:45 - 16:20Gourab PatroFair ranking: a critical review, challenges, and an impact-oriented research agenda for futureGourab Patro
16:20 - 16:55Roi ReichartCausal models for NLP applicationsRoi Reichart

Day 2

09:00 - 09:45Amit Sharma Causal Machine Learning: A necessary ingredient for building generalizable modelsAmit Sharma
09:45 - 10:30Marco ZaffalonCausal EM for counterfactual inference, with an application to palliative care.Marco Zaffalon
10:30 - 10:40Break
10:40 - 11:15Tom ClaassenCausal discovery from medical data: challenges and opportunitiesTom Claassen
11:15 - 11:50Avishek AnandExplainable Information Retrieval
11:50 - 13:00Lunch Break
13:00 - 13:45Prasenjit MitraAdapting Tools of Causality to Analyze the Obesity ParadoxPrasenjit Mitra
13:45 - 14:30Tim FriedeAI/ML in Clinical researchTim Friede
14:30 - 14:45Break
14:45 - 15:30Ricardo SilvaCauses with many moving partsRicardo Silva
15:30 - 16:15Zhiliang WuLearning Individualized Treatment Rules with Estimated Translated Inverse Propensity ScoreZhilliang Wu
16:15 - 16:30Closing
Artificial Intelligence, Causality and Personalized Medicine (AICPM 2022)
  • Date : 08 Sep 2022 - 09 Sep 2022


Michael Marschollek

Profile :

Wolfgang Nejdl

Profile :

Niloy Ganguly

Profile :

Sandipan Sikdar

Profile :

Manolis Koubarakis

Profile :

Alexander Dockhorn

Profile :