arXiv subjects

Félicien Hêche

Publications and source records attributed to Félicien Hêche.

3 recordsLinked to original sources

arXiv2026

Early Risk Stratification of Dosing Errors in Clinical Trials Using Machine Learning

Objective: The objective of this study is to develop a machine learning (ML)-based framework for early risk stratification of clinical trials (CTs) according to their likelihood of exhibiting a high rate of dosing errors, using information available prior to trial initiation. Materials and Methods: We constructed a dataset from ClinicalTrials.gov comprising 42,112 CTs. Structured, semi-structured trial data, and unstructured protocol-related free-text data were extracted. CTs were assigned binary labels indicating elevated dosing error rate, derived from adverse event reports, MedDRA terminology, and Wilson confidence intervals. We evaluated an XGBoost model trained on structured features, a ClinicalModernBERT model using textual data, and a simple late-fusion model combining both modalities. Post-hoc probability calibration was applied to enable interpretable, trial-level risk stratification. Results: The late-fusion model achieved the highest AUC-ROC (0.862). Beyond discrimination, calibrated outputs enabled robust stratification of CTs into predefined risk categories. The proportion of trials labeled as having an excessively high dosing error rate increased monotonically across higher predicted risk groups and aligned with the corresponding predicted probability ranges. Discussion: These findings indicate that dosing error risk can be anticipated at the trial level using pre-initiation information. Probability calibration was essential for translating model outputs into reliable and interpretable risk categories, while simple multimodal integration yielded performance gains without requiring complex architectures. Conclusion: This study introduces a reproducible and scalable ML framework for early, trial-level risk stratification of CTs at risk of high dosing error rates, supporting proactive, risk-based quality management in clinical research.

cs.LG↗

arXiv2025

Risk-averse policies for natural gas futures trading using distributional reinforcement learning

Financial markets have experienced significant instabilities in recent years, creating unique challenges for trading and increasing interest in risk-averse strategies. Distributional Reinforcement Learning (RL) algorithms, which model the full distribution of returns rather than just expected values, offer a promising approach to managing market uncertainty. This paper investigates this potential by studying the effectiveness of three distributional RL algorithms for natural gas futures trading and exploring their capacity to develop risk-averse policies. Specifically, we analyze the performance and behavior of Categorical Deep Q-Network (C51), Quantile Regression Deep Q-Network (QR-DQN), and Implicit Quantile Network (IQN). To the best of our knowledge, these algorithms have never been applied in a trading context. These policies are compared against five Machine Learning (ML) baselines, using a detailed dataset provided by Predictive Layer SA, a company supplying ML-based strategies for energy trading. The main contributions of this study are as follows. (1) We demonstrate that distributional RL algorithms significantly outperform classical RL methods, with C51 achieving performance improvement of more than 32\%. (2) We show that training C51 and IQN to maximize CVaR produces risk-sensitive policies with adjustable risk aversion. Specifically, our ablation studies reveal that lower CVaR confidence levels increase risk aversion, while higher levels decrease it, offering flexible risk management options. In contrast, QR-DQN shows less predictable behavior. These findings emphasize the potential of distributional RL for developing adaptable, risk-averse trading strategies in volatile markets.

cs.LG↗

arXiv2025

Assessing the impact of external factors on the occurrence of emergencies

This study investigates the impact of 19 external factors, related to weather, road traffic conditions, air quality, and time, on the occurrence of emergencies using historical data provided by the dispatch center of the Centre Hospitalier Universitaire Vaudois (CHUV). This center is responsible for managing Emergency Medical Service (EMS) resources in the majority of the French-speaking part of Switzerland. First, classical statistical methods, such as correlation, Chi-squared test, Student's $t$-test, and information value, are employed to identify dependencies between the occurrence of emergencies and the considered parameters. Additionally, SHapley Additive exPlanations (SHAP) values and permutation importance are computed using eXtreme Gradient Boosting (XGBoost) and Multilayer Perceptron (MLP) models. The results indicate that the hour of the day, along with correlated parameters, plays a crucial role in the occurrence of emergencies. Conversely, other factors do not significantly influence emergency occurrences. Subsequently, a simplified model that considers only the hour of the day is compared with our XGBoost and MLP models. These comparisons reveal no significant difference between the three models in terms of performance, supporting the use of the basic model in this context. These observations provide valuable insights for EMS resource relocation strategies, benefit predictive modeling efforts, and inform decision-making in the context of EMS. The implications extend to enhancing EMS quality, making this research essential.

cs.CY↗