Vincent Jeanselme

Vincent Jeanselme

Machine Learning for Healthcare

Publications

riSCC: A personalized risk model for the development of poor outcomes in cutaneous squamous cell carcinoma

Published in Journal of the American Academy of Dermatology, 2025

Thias paper introduces a novel prognostic model for cutaneous squamous cell carcinoma and compare its performance to commonly used staging systems. To help medical practitioners quantify risk, we release an app to compute riSCC.

Recommended citation: Jambusaria-Pahlajani, A.*, Jeanselme, V.*, Wang, D., Ran, N., Granger, E., Cañueto, J., Brodland, D., Carr, D., Carter, J., Carucci, J., Hirotsu, K., Karn, E., Koyfman, S., Mangold, A., Girardi, F., Shahwan, K., Srivastava, D., Vidimos, A., Willenbrink, T., Wysong, A., Lotter, W., Ruiz, E. (2025). riSCC: A personalized risk model for the development of poor outcomes in cutaneous squamous cell carcinoma. In Journal of the American Academy of Dermatology. https://www.jaad.org/article/S0190-9622(25)00373-1/abstract

Leveraging Expert Consistency to Improve Algorithmic Decision Support

Published in Management Science, 2024

Machine learning (ML) is increasingly being used to support high-stakes decisions, a trend owed in part to its promise of superior predictive power relative to human assessment. However, there is frequently a gap between decision objectives and what is captured in the observed outcomes used as labels to train ML models. As a result, machine learning models may fail to capture important dimensions of decision criteria, hampering their utility for decision support. In this work, we explore the use of historical expert decisions as a rich – yet imperfect – source of information that is commonly available in organizational information systems, and show that it can be leveraged to bridge the gap between decision objectives and algorithm objectives. We consider the problem of estimating expert consistency indirectly when each case in the data is assessed by a single expert, and propose influence function-based methodology as a solution to this problem. We then incorporate the estimated expert consistency into a predictive model through a training-time label amalgamation approach. This approach allows ML models to learn from experts when there is inferred expert consistency, and from observed labels otherwise. We also propose alternative ways of leveraging inferred consistency via hybrid and deferral models. In our empirical evaluation, focused on the context of child maltreatment hotline screenings, we show that (1) there are high-risk cases whose risk is considered by the experts but not wholly captured in the target labels used to train a deployed model, and (2) the proposed approach significantly improves precision for these cases.

Recommended citation: De-Arteaga, M., Jeanselme, V., Dubrawski, A., Chouldechova, A. Leveraging Expert Consistency to Improve Algorithmic Decision Support. https://arxiv.org/abs/2101.09648

Review of Language Models for Survival Analysis

Published in AAAI 2024 Spring Symposium on Clinical Foundation Models, 2024

This paper reviews the different strategies to leverage language models for time-to-event modelling, critical to risk prediction in the healthcare setting.

Recommended citation: Jeanselme, V., Agarwal, N. and Wang, C. (2024, May). Review of Language Models for Survival Analysis. In AAAI 2024 Spring Symposium on Clinical Foundation Models. https://openreview.net/pdf?id=ZLUsZ52ibx

Neural Fine-Gray

Published in Conference on Health, Inference, and Learning (CHIL), 2023

The paper introduces a novel approach using constrained monotonic neural networks to address the challenge of competing risks in survival analysis, which is often overlooked by machine learning methods.

Recommended citation: Jeanselme, V., Yoon, C. H., Tom, B., Barrett, J. (2023, June). Neural Fine-Gray: Monotonic neural networks for competing risks. In Conference on Health, Inference, and Learning (pp. 379-392). PMLR. https://arxiv.org/abs/2305.06703

DeepJoint: Robust Survival Modelling Under Clinical Presence Shift

Published in NeurIPS Workshop TS4H, 2022

This work investigates the impact of patient-healthcare system interactions on medical data and introduces a multi-task recurrent neural network to address potential performance issues caused by changes in this interaction.

Recommended citation: Jeanselme, V., Martin, G., Peek, N., Sperrin, M., Tom, B., Barrett, J. (2022). DeepJoint: Robust Survival Modelling Under Clinical Presence Shift . In NeurIPS 2022 Workshop on Learning from Time Series for Health. https://arxiv.org/abs/2205.13481

Imputation Strategies Under Clinical Presence: Impact on Algorithmic Fairness

Published in Machine Learning for Health (ML4H), 2022

This work investigates how biases are not only present in the data we observe but also it was is missing from the data.

Recommended citation: Jeanselme, V., De-Arteaga, M., Zhang, Z., Barrett, J., Tom, B, (2022, November). Imputation Strategies Under Clinical Presence: Impact on Algorithmic Fairness. In Machine Learning for Health (pp. 12-34). PMLR. https://proceedings.mlr.press/v193/jeanselme22a/jeanselme22a.pdf

Constrained clustering and multiple kernel learning without pairwise constraint relaxation

Published in Springer - Advances in Data Analysis and Classification, 2022

This research presents a novel clustering algorithm that uses pairwise constraints to enhance clustering performance and kernel learning without the common practice of transforming constraints into continuous domains, leading to improved generalization and scalability for large datasets.

Recommended citation: Boecking, B., Jeanselme, V., Dubrawski, A (2022). Constrained clustering and multiple kernel learning without pairwise constraint relaxation. In Advances in Data Analysis and Classification, 1-16. https://doi.org/10.1007/s11634-022-00507-5

Neural Survival Clustering: Non-parametric mixture of neural networks for survival clustering

Published in Conference on Health, Inference, and Learning (CHIL), 2022

This research presents a novel clustering algorithm that uses pairwise constraints to enhance clustering performance and kernel learning without the common practice of transforming constraints into continuous domains, leading to improved generalization and scalability for large datasets.

Recommended citation: Jeanselme, V., Tom, B., Barrett, J. (2022, April). Neural Survival Clustering: Non-parametric mixture of neural networks for survival clustering. In Conference on Health, Inference, and Learning (pp. 92-102). PMLR. https://proceedings.mlr.press/v174/jeanselme22a/jeanselme22a.pdf

Sex differences in post cardiac arrest discharge locations

Published in Resuscitation Plus, 2021

This study investigated sex-based differences in discharge location after cardiac arrest resuscitation and found that female sex was weakly associated with an unfavorable discharge location, suggesting a potential disparity.

Recommended citation: Jeanselme, V., De-Arteaga, M., Elmer, J., Perman, S. M., Dubrawski, A. (2021). Sex differences in post cardiac arrest discharge locations. In Resuscitation plus, 8, 100185. https://www.sciencedirect.com/science/article/pii/S2666520421001107

Deep Parametric Time-to-Event Regression with Time-Varying Covariates

Published in AAAI Spring Symposium on Survival Analysis, 2021

This paper introduces a parametric approach using Recurrent Neural Networks (RNNs) to model censored time-to-event outcomes with time-varying covariates, demonstrating its competitive performance in predicting ICU stay durations and short-term life expectancy compared to traditional time-to-event regression models on MIMIC III.

Recommended citation: Nagpal, C.*, Jeanselme, V.*, Dubrawski, A. (2021, May). Deep parametric time-to-event regression with time-varying covariates. In Survival Prediction-Algorithms, Challenges and Applications (pp. 184-193). PMLR. https://proceedings.mlr.press/v146/nagpal21a.html

Prediction of Hypotension Events with Physiologic Vital Sign Signatures in The Intensive Care Unit

Published in Critical Care, 2020

The study developed a machine learning model using vital signs data from ICU patients to predict the risk of hypotension events, achieving high accuracy with alerts generated up to 1 hour before the episode, indicating potential real-life utility in improving patient care.

Recommended citation: Yoon, J. H.*, Jeanselme, V.*, Dubrawski, A., Hravnak, M., Pinsky, M. R., Clermont, G. (2020). Prediction of Hypotension Events with Physiologic Vital Sign Signatures in The Intensive Care Unit. In Critical Care, 24(1), 1-9. https://ccforum.biomedcentral.com/articles/10.1186/s13054-020-03379-3