Jean-Marc Alliot
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jean-Marc Alliot has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
Nicolas Durand
12 shared publicationsDavid Gianazza
7 shared publications- Charlie Vanaret
Department of Applied Algorithmic Intelligence Methods Zuse-Institut Berlin 14195 Berlin Germany
6 shared publications - Nicolas Durand
ENAC lab, Ecole Nationale de l’Aviation Civile, Toulouse, France
6 shared publications Jean-Baptiste Gotteland
4 shared publicationsJean‐Baptiste Gotteland
4 shared publications
Latest Publications
- 8 July 2026
- Published by Springer Nature
- p. 193-197
When More Data is Not Better: Physiological Drift Explains Transfer Learning Failure in Rare ICU Populations
- 8 July 2026
- Published by Springer Nature
- p. 193-197
When More Data is Not Better: Physiological Drift Explains Transfer Learning Failure in Rare ICU Populations
- 26 January 2026
- Published by American Association for Cancer Research (AACR) in Blood Cancer Discovery
- Vol. 7 (2) , 171-175
Expectations and Limitations of Artificial Intelligence in Blood Cancer Diagnosis
Summary: In this commentary, we open the debate on what can be expected from artificial intelligence (AI) in the diagnosis of hematologic cancers. We discuss the key factors that make AI solutions robust, trustworthy, and, above all, generalizable, with particular emphasis on the importance of dataset quality in shaping the performance and effectiveness of AI models.
- 26 January 2026
- Published by American Association for Cancer Research (AACR) in Blood Cancer Discovery
- Vol. 7 (2) , 171-175
Expectations and Limitations of Artificial Intelligence in Blood Cancer Diagnosis
Summary: In this commentary, we open the debate on what can be expected from artificial intelligence (AI) in the diagnosis of hematologic cancers. We discuss the key factors that make AI solutions robust, trustworthy, and, above all, generalizable, with particular emphasis on the importance of dataset quality in shaping the performance and effectiveness of AI models.
- Open Access
- 8 January 2026
- Published by Elsevier in ESMO Real World Data and Digital Oncology
- Vol. 11
Automated extraction of temporalized tumor evolution from oncology EMRs using natural language processing
- 8 January 2026
- Published by Elsevier in ESMO Real World Data and Digital Oncology
- Vol. 11
Open AccessAutomated extraction of temporalized tumor evolution from oncology EMRs using natural language processing
- 8 February 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 171, 108130
Bias reduction using combined stain normalization and augmentation for AI-based classification of histological images
- 8 February 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 171, 108130
Bias reduction using combined stain normalization and augmentation for AI-based classification of histological images
- 29 March 2022
- Published by Taylor & Francis
- p. 585-591
Collision Avoidance Using Neural Networks Learned by Genetic Algorithm
As Air Traffic keeps increasing, many research programs focus on collision avoidance techniques. In this paper, a neural network learned by genetic algorithm is introduced to solve conflicts between two aircraft. The learned NN is then tested on different conflicts and compared to the optimal solution. Results are very promising.
- 29 March 2022
- Published by Taylor & Francis
- p. 585-591
Collision Avoidance Using Neural Networks Learned by Genetic Algorithm
As Air Traffic keeps increasing, many research programs focus on collision avoidance techniques. In this paper, a neural network learned by genetic algorithm is introduced to solve conflicts between two aircraft. The learned NN is then tested on different conflicts and compared to the optimal solution. Results are very promising.
- Open Access
- 5 November 2021
- Published by American Society of Hematology in Blood
- Vol. 138 (Supplement) , 3389
Artificial Intelligence-Based Predictive Models for Acute Myeloid Leukemia
Introduction In the acute myeloid leukemia (AML) setting, artificial intelligence has mainly been used to facilitate diagnosis or to identify biological subcategories. In this work, we trained and compared machine learning and deep learning predictive models of outcome on the data of 3687 consecutive adult AML patients included in the DATAML registry between 2000 and 2019. We also trained a model to predict the best treatment for newly diagnosed AML over 70 years. Methods Feature engineering and selection were done to keep the most relevant variables among clinical and biological characteristics at diagnosis. We worked with 54 features per patient, as well as information about the treatment received (intensive chemotherapy (IC) or azacitidine (AZA)), response and survival. We compared the performance of a gradient boosting algorithm (XGBoost) and three neural networks architectures: a multilayer perceptron (MLP), a neural oblivious decision ensemble model (NODE) and a recurrent relational network (RRN). We calibrated XGBoost with a grid search algorithm, and used 5-fold cross-validation on the dataset to evaluate all the models. The Shapley Additive Explanations method (SHAP) was used to showcase the importance and influence of variables on the predictions. The Boruta algorithm was then used to extract the most important features for prediction. Results In our cohort, 3030 patients (82.2%) received IC and 657 (17.8%) AZA as first line treatment. Median overall survival (OS) was 18 and 9 months, respectively. We first designed models for OS prediction. In the IC cohort, we achieved an accuracy of 68.5% on predicting OS at the 18-month mark, an improvement of 17.5% over a naïve predictor. The Boruta algorithm selected 13 variables as the most important, with decreasing order of importance: age, cytogenetic risk, WBC, LDH, platelets count, albumin, MPO, mean corpuscular volume, CD117, NPM1 mutation, AML status, multilineage dysmyelopoiesis, ASXL1 mutation (Figure 1). When training with only these 13 variables, we achieved an accuracy of 67.8%. In the AZA cohort, we achieved an accuracy of 62.1% on predicting OS at the 9-month mark, an improvement of 11.1% over a naïve predictor. Here the Boruta algorithm selected only 7 variables: blood blasts, serum ferritin, CD56, LDH, hemoglobin, CD13 and the presence of a disseminated intravascular coagulation. When training with only these 7 variables, we achieved a 61.9% accuracy. We then designed models to predict the best treatment between IC and AZA for the 1032 patients older than 70 years. We achieved a 88.5% accuracy, which is 37.5% more than a naïve predictor given the distribution of the cohort: 51% having received IC and 49% having received AZA. For this model, 12 features out of 54 were selected by the Boruta algorithm as the most important: age, TP53 mutation, bone marrow blasts, AML status, disseminated intravascular coagulation, blood blasts, cytogenetic risk, IDH2 mutation, IDH1 mutation, presence of an infection at diagnosis, ASXL1 mutation and presence of leukostasis. Conclusion We show that predictive models can be trained on our database to predict with characteristics at diagnosis the treatment that would be chosen by an expert hematologist between IC and AZA in newly diagnosed AML, give an indication of OS with each treatment, and outperform classical statistical analysis or naïve predictors. For the task of predicting OS, the improvement over naïve predictors is maximal at the median time of OS. We show with the Boruta algorithm that a small number of variables can recapitulate the accuracy of neural networks, which renders this type of model of high interest for routine practice, especially with the advent of targeted therapies. Figure 1 Figure 1. Disclosures: Vergez: Pierre Fabre Laboratory: Research Funding; Roche: Research Funding. Dumas: BMS Celgene: Consultancy; Astellas: Consultancy; Daiichi-Sankyo: Consultancy. Tavitian: Novartis: Consultancy. Delabesse: Astellas: Consultancy; Novartis: Consultancy. Pigneux: Amgen: Consultancy; Sunesis: Consultancy, Research Funding; BMS Celgene: Consultancy, Research Funding; Roche: Consultancy, Research Funding; Novartis: Consultancy, Research Funding. Recher: Pfizer: Honoraria, Membership on an entity's Board of Directors or advisory committees; Novartis: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Macrogenics: Honoraria, Membership on an entity's Board of Directors or advisory committees; MaatPharma: Research Funding; Jazz: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Janssen: Honoraria; Incyte: Honoraria; Daiichi Sankyo: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; BMS/Celgene: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Astellas: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Amgen: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Roche: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Takeda: Honoraria, Membership on an entity's Board of Directors or advisory committees; Agios: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; AbbVie: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding. Bertoli: Astellas: Consultancy; BMS Celgene: Consultancy; Abbvie: Consultancy; Jazz Pharmaceuticals: Consultancy.
- 5 November 2021
- Published by American Society of Hematology in Blood
- Vol. 138 (Supplement) , 3389
Open AccessArtificial Intelligence-Based Predictive Models for Acute Myeloid Leukemia
Introduction In the acute myeloid leukemia (AML) setting, artificial intelligence has mainly been used to facilitate diagnosis or to identify biological subcategories. In this work, we trained and compared machine learning and deep learning predictive models of outcome on the data of 3687 consecutive adult AML patients included in the DATAML registry between 2000 and 2019. We also trained a model to predict the best treatment for newly diagnosed AML over 70 years. Methods Feature engineering and selection were done to keep the most relevant variables among clinical and biological characteristics at diagnosis. We worked with 54 features per patient, as well as information about the treatment received (intensive chemotherapy (IC) or azacitidine (AZA)), response and survival. We compared the performance of a gradient boosting algorithm (XGBoost) and three neural networks architectures: a multilayer perceptron (MLP), a neural oblivious decision ensemble model (NODE) and a recurrent relational network (RRN). We calibrated XGBoost with a grid search algorithm, and used 5-fold cross-validation on the dataset to evaluate all the models. The Shapley Additive Explanations method (SHAP) was used to showcase the importance and influence of variables on the predictions. The Boruta algorithm was then used to extract the most important features for prediction. Results In our cohort, 3030 patients (82.2%) received IC and 657 (17.8%) AZA as first line treatment. Median overall survival (OS) was 18 and 9 months, respectively. We first designed models for OS prediction. In the IC cohort, we achieved an accuracy of 68.5% on predicting OS at the 18-month mark, an improvement of 17.5% over a naïve predictor. The Boruta algorithm selected 13 variables as the most important, with decreasing order of importance: age, cytogenetic risk, WBC, LDH, platelets count, albumin, MPO, mean corpuscular volume, CD117, NPM1 mutation, AML status, multilineage dysmyelopoiesis, ASXL1 mutation (Figure 1). When training with only these 13 variables, we achieved an accuracy of 67.8%. In the AZA cohort, we achieved an accuracy of 62.1% on predicting OS at the 9-month mark, an improvement of 11.1% over a naïve predictor. Here the Boruta algorithm selected only 7 variables: blood blasts, serum ferritin, CD56, LDH, hemoglobin, CD13 and the presence of a disseminated intravascular coagulation. When training with only these 7 variables, we achieved a 61.9% accuracy. We then designed models to predict the best treatment between IC and AZA for the 1032 patients older than 70 years. We achieved a 88.5% accuracy, which is 37.5% more than a naïve predictor given the distribution of the cohort: 51% having received IC and 49% having received AZA. For this model, 12 features out of 54 were selected by the Boruta algorithm as the most important: age, TP53 mutation, bone marrow blasts, AML status, disseminated intravascular coagulation, blood blasts, cytogenetic risk, IDH2 mutation, IDH1 mutation, presence of an infection at diagnosis, ASXL1 mutation and presence of leukostasis. Conclusion We show that predictive models can be trained on our database to predict with characteristics at diagnosis the treatment that would be chosen by an expert hematologist between IC and AZA in newly diagnosed AML, give an indication of OS with each treatment, and outperform classical statistical analysis or naïve predictors. For the task of predicting OS, the improvement over naïve predictors is maximal at the median time of OS. We show with the Boruta algorithm that a small number of variables can recapitulate the accuracy of neural networks, which renders this type of model of high interest for routine practice, especially with the advent of targeted therapies. Figure 1 Figure 1. Disclosures: Vergez: Pierre Fabre Laboratory: Research Funding; Roche: Research Funding. Dumas: BMS Celgene: Consultancy; Astellas: Consultancy; Daiichi-Sankyo: Consultancy. Tavitian: Novartis: Consultancy. Delabesse: Astellas: Consultancy; Novartis: Consultancy. Pigneux: Amgen: Consultancy; Sunesis: Consultancy, Research Funding; BMS Celgene: Consultancy, Research Funding; Roche: Consultancy, Research Funding; Novartis: Consultancy, Research Funding. Recher: Pfizer: Honoraria, Membership on an entity's Board of Directors or advisory committees; Novartis: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Macrogenics: Honoraria, Membership on an entity's Board of Directors or advisory committees; MaatPharma: Research Funding; Jazz: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Janssen: Honoraria; Incyte: Honoraria; Daiichi Sankyo: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; BMS/Celgene: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Astellas: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Amgen: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Roche: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Takeda: Honoraria, Membership on an entity's Board of Directors or advisory committees; Agios: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; AbbVie: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding. Bertoli: Astellas: Consultancy; BMS Celgene: Consultancy; Abbvie: Consultancy; Jazz Pharmaceuticals: Consultancy.
- Open Access
A framework for modelling Molecular Interaction Maps
Metabolic networks, formed by a series of metabolic pathways, are made of intracellular and extracellular reactions that determine the biochemical properties of a cell, and by a set of interactions that guide and regulate the activity of these reactions. Most of these pathways are formed by an intricate and complex network of chain reactions, and can be represented in a human readable form using graphs which describe the cell cycle checkpoint pathways. This paper proposes a method to represent Molecular Interaction Maps (graphical representations of complex metabolic networks) in Linear Temporal Logic. The logical representation of such networks allows one to reason about them, in order to check, for instance, whether a graph satisfies a given property $\phi$, as well as to find out which initial conditons would guarantee $\phi$, or else how can the the graph be updated in order to satisfy $\phi$. Both the translation and resolution methods have been implemented in a tool capable of addressing such questions thanks to a reduction to propositional logic which allows exploiting classical SAT solvers.Open AccessA framework for modelling Molecular Interaction Maps
Metabolic networks, formed by a series of metabolic pathways, are made of intracellular and extracellular reactions that determine the biochemical properties of a cell, and by a set of interactions that guide and regulate the activity of these reactions. Most of these pathways are formed by an intricate and complex network of chain reactions, and can be represented in a human readable form using graphs which describe the cell cycle checkpoint pathways. This paper proposes a method to represent Molecular Interaction Maps (graphical representations of complex metabolic networks) in Linear Temporal Logic. The logical representation of such networks allows one to reason about them, in order to check, for instance, whether a graph satisfies a given property $\phi$, as well as to find out which initial conditons would guarantee $\phi$, or else how can the the graph be updated in order to satisfy $\phi$. Both the translation and resolution methods have been implemented in a tool capable of addressing such questions thanks to a reduction to propositional logic which allows exploiting classical SAT solvers. - Open Access
Wind Mill Pattern Optimization using Evolutionary Algorithms
When designing a wind farm layout, we can reduce the number of variables by optimizing a pattern instead of considering the position of each turbine. In this paper we show that when reducing the problem to only two variables defining a grid, we can gain up to 3% of energy output on simple examples of wind farms dealing with many turbines (up to 1000) while dramatically reducing computation time. To achieve these results, we compared both a genetic algorithm and a differential evolution algorithm to previous results from the literature. These preliminary results should be extended to examples involving non-rectangular farm layouts and wind distributions that may require pattern deformation variables in order to increase solution diversity.
Open AccessWind Mill Pattern Optimization using Evolutionary Algorithms
When designing a wind farm layout, we can reduce the number of variables by optimizing a pattern instead of considering the position of each turbine. In this paper we show that when reducing the problem to only two variables defining a grid, we can gain up to 3% of energy output on simple examples of wind farms dealing with many turbines (up to 1000) while dramatically reducing computation time. To achieve these results, we compared both a genetic algorithm and a differential evolution algorithm to previous results from the literature. These preliminary results should be extended to examples involving non-rectangular farm layouts and wind distributions that may require pattern deformation variables in order to increase solution diversity.
- Open Access
Certified Global Minima for a Benchmark of Difficult Optimization Problems
We provide the global optimization community with new optimality proofs for six deceptive benchmark functions (five bound-constrained functions and one nonlinearly constrained problem). These highly multimodal nonlinear test problems are among the most challenging benchmark functions for global optimization solvers; some have not been solved even with approximate methods. The global optima that we report have been numerically certified using Charibde (Vanaret et al., 2013), a hybrid algorithm that combines an evolutionary algorithm and interval-based methods. While metaheuristics generally solve large problems and provide sufficiently good solutions with limited computation capacity, exact methods are deemed unsuitable for difficult multimodal optimization problems. The achievement of new optimality results by Charibde demonstrates that reconciling stochastic algorithms and numerical analysis methods is a step forward into handling problems that were up to now considered unsolvable. We also provide a comparison with state-of-the-art solvers based on mathematical programming methods and population-based metaheuristics, and show that Charibde, in addition to being reliable, is highly competitive with the best solvers on the given test functions.
Open AccessCertified Global Minima for a Benchmark of Difficult Optimization Problems
We provide the global optimization community with new optimality proofs for six deceptive benchmark functions (five bound-constrained functions and one nonlinearly constrained problem). These highly multimodal nonlinear test problems are among the most challenging benchmark functions for global optimization solvers; some have not been solved even with approximate methods. The global optima that we report have been numerically certified using Charibde (Vanaret et al., 2013), a hybrid algorithm that combines an evolutionary algorithm and interval-based methods. While metaheuristics generally solve large problems and provide sufficiently good solutions with limited computation capacity, exact methods are deemed unsuitable for difficult multimodal optimization problems. The achievement of new optimality results by Charibde demonstrates that reconciling stochastic algorithms and numerical analysis methods is a step forward into handling problems that were up to now considered unsolvable. We also provide a comparison with state-of-the-art solvers based on mathematical programming methods and population-based metaheuristics, and show that Charibde, in addition to being reliable, is highly competitive with the best solvers on the given test functions.
- 23 January 2018
- Published by EasyChair
(The Final) Countdown
The Countdown game is one of the oldest TV show in theworld. It started broadcasting in 1972 on the french televisionand in 1982 on British channel 4, and it has been running since inboth countries.The game, while extremely popular, never received any seriousscientific attention, probably because it seems too simple at first sight.We present in this article an in-depth analysis of thenumbers round of the countdown game. This includes a complexityanalysis of the game, an analysis of existing algorithms and the presentationof a new algorithm that increases resolution speed by a large factor.It also includes some leads on how to turn the game into amore difficult one, both for a human player and for a computer, andeven to transform it into a possibly undecidable problem.
- 23 January 2018
- Published by EasyChair
(The Final) Countdown
The Countdown game is one of the oldest TV show in theworld. It started broadcasting in 1972 on the french televisionand in 1982 on British channel 4, and it has been running since inboth countries.The game, while extremely popular, never received any seriousscientific attention, probably because it seems too simple at first sight.We present in this article an in-depth analysis of thenumbers round of the countdown game. This includes a complexityanalysis of the game, an analysis of existing algorithms and the presentationof a new algorithm that increases resolution speed by a large factor.It also includes some leads on how to turn the game into amore difficult one, both for a human player and for a computer, andeven to transform it into a possibly undecidable problem.