Federated Learning for Mortality Prediction in Intensive Care Units

Show full item record


Title: Federated Learning for Mortality Prediction in Intensive Care Units
Author: Pelttari, Hannu
Other contributor: Helsingin yliopisto, Matemaattis-luonnontieteellinen tiedekunta
University of Helsinki, Faculty of Science
Helsingfors universitet, Matematisk-naturvetenskapliga fakulteten
Publisher: Helsingin yliopisto
Date: 2020
Language: eng
URI: http://urn.fi/URN:NBN:fi:hulib-202009254145
Thesis level: master's thesis
Degree program: Teoreettisten ja laskennallisten menetelmien maisteriohjelma
Master's Programme in Theoretical and Computational Methods
Magisterprogrammet i teoretiska och beräkningsmetoder
Specialisation: ei opintosuuntaa
no specialization
ingen studieinriktning
Discipline: none
Abstract: Federated learning is a method to train a machine learning model on multiple remote datasets without the need to gather the data from the remote sites to a central location. In healthcare, gathering the data from different hospitals into a central location can be a difficult and time-consuming task, due to privacy concerns and regulations regarding the use of sensitive data, making federated learning an attractive alternative to more traditional methods. This thesis adapted an existing federated gradient boosting model and developed a new federated random forest model and applied them to mortality prediction in intensive care units. The results were then compared to the centralized counterparts of the models. The results showed that while the federated models did not perform as well as the centralized models on a similar sized dataset, the federated random forest model can achieve superior performance when trained on multiple hospitals' data compared to centralized models trained on a single hospital. In scenarios where the centralized models had data from multiple hospitals the federated models could not perform as well as the centralized models. It was also found that the performance of the centralized models could not be improved with further federated training. In addition to practical advantages such as possibility of parallel or asynchronous training without modifications to the algorithm, the federated random forest performed better in all scenarios compared to the federated gradient boosting. The performance of the federated random forest was also found to be more consistent over different scenarios than the performance of federated gradient boosting, which was highly dependent on factors such as the order with the hospitals were traversed.
Subject: Federated Learning
Random Forest
Gradient Boosting
Mortality Prediction
Intensive Care Unit

Files in this item

Total number of downloads: Loading...

Files Size Format View
Pelttari_Hannu_masters_thesis_2020.pdf 1.939Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record