Konferenzpaper | 2023 | Peer reviewed

Federated Learning to Improve Counterfactual Explanations for Sepsis Treatment Prediction

Autor(en)

Düsing, Christoph ; Cimiano, Philipp

Titel des Konferenzbandes

Artificial Intelligence in Medicine: 21st International Conference on Artificial Intelligence in Medicine

Name der Konferenz

AIME: 21st International Conference on Artificial Intelligence in Medicine

DOI

10.1007/978-3-031-34344-5_11

URL

https://pub.uni-bielefeld.de/record/2979412

Weitere Details

Sprache

englisch

Darstellungsform

Text

Schlagwörter

Counterfactual explanations , Federated learning , Generative models , Sepsis treatment

In recent years, we have witnessed both artificial intelligence obtaining remarkable results in clinical decision support systems (CDSSs) and explainable artificial intelligence (XAI) improving the interpretability of these models. In turn, this fosters the adoption by medical personnel and improves trustworthiness of CDSSs. Among others, counterfactual explanations prove to be one such XAI technique particularly suitable for the healthcare domain due to its ease of interpretation, even for less technically proficient staff. However, the generation of high-quality counterfactuals relies on generative models for guidance. Unfortunately, training such models requires a huge amount of data that is beyond the means of ordinary hospitals. In this paper, we therefore propose to use federated learning to allow multiple hospitals to jointly train such generative models while maintaining full data privacy. We demonstrate the superiority of our approach compared to locally generated counterfactuals on a CDSS for sepsis treatment prescription using various metrics. Moreover, we prove that generative models for counterfactual generation that are trained using federated learning in a suitable environment perform only marginally worse compared to centrally trained ones while offering the benefit of data privacy preservation.

Entwicklung eines KI-basierten Entscheidungsunterstützungssystems zur individualisierten Vorhersage wirksamer Antibiotikatherapien

Zitierstile

Düsing C, Cimiano P. Federated Learning to Improve Counterfactual Explanations for Sepsis Treatment Prediction. In: Artificial Intelligence in Medicine: 21st International Conference on Artificial Intelligence in Medicine. Lecture Notes in Computer Science . Springer Link; 2023.

In die Zwischenablage einfügen

Düsing, C., & Cimiano, P. (2023). Federated Learning to Improve Counterfactual Explanations for Sepsis Treatment Prediction. Artificial Intelligence in Medicine: 21st International Conference on Artificial Intelligence in Medicine, Lecture Notes in Computer Science Springer Link. https://doi.org/10.1007/978-3-031-34344-5_11

In die Zwischenablage einfügen

Düsing, Christoph, and Cimiano, Philipp. 2023. “Federated Learning to Improve Counterfactual Explanations for Sepsis Treatment Prediction”. In Artificial Intelligence in Medicine: 21st International Conference on Artificial Intelligence in Medicine. Lecture Notes in Computer Science . Springer Link.

In die Zwischenablage einfügen

Düsing, C., and Cimiano, P. (2023). “Federated Learning to Improve Counterfactual Explanations for Sepsis Treatment Prediction” in Artificial Intelligence in Medicine: 21st International Conference on Artificial Intelligence in Medicine Lecture Notes in Computer Science (Springer Link).

In die Zwischenablage einfügen

Düsing, C., & Cimiano, P., 2023. Federated Learning to Improve Counterfactual Explanations for Sepsis Treatment Prediction. In Artificial Intelligence in Medicine: 21st International Conference on Artificial Intelligence in Medicine. Lecture Notes in Computer Science . Springer Link.

In die Zwischenablage einfügen

C. Düsing and P. Cimiano, “Federated Learning to Improve Counterfactual Explanations for Sepsis Treatment Prediction”, Artificial Intelligence in Medicine: 21st International Conference on Artificial Intelligence in Medicine, Lecture Notes in Computer Science , Springer Link, 2023.

In die Zwischenablage einfügen

Düsing, C., Cimiano, P.: Federated Learning to Improve Counterfactual Explanations for Sepsis Treatment Prediction. Artificial Intelligence in Medicine: 21st International Conference on Artificial Intelligence in Medicine. Lecture Notes in Computer Science . Springer Link (2023).

In die Zwischenablage einfügen

Düsing, Christoph, and Cimiano, Philipp. “Federated Learning to Improve Counterfactual Explanations for Sepsis Treatment Prediction”. Artificial Intelligence in Medicine: 21st International Conference on Artificial Intelligence in Medicine. Springer Link, 2023. Lecture Notes in Computer Science .

In die Zwischenablage einfügen

Download
RDF/XML-Format
JSON-LD-Format
Turtle-Format
N3-Format

Entwicklung eines KI-basierten Entscheidungsunterstützungssystems zur individualisierten Vorhersage wirksamer Antibiotikatherapien

Zitierstile

In die Zwischenablage einfügen

Download
RDF/XML-Format
JSON-LD-Format
Turtle-Format
N3-Format

AMA

APA (6th ed.)

Chicago

Frontiers

Harvard

IEEE

LNCS

MLA