Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Loni, Mohammad, Poursalim, Fatemeh, Asadi, Mehdi, Gharehbaghi, Arash
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.12274
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912126288789504
author Loni, Mohammad
Poursalim, Fatemeh
Asadi, Mehdi
Gharehbaghi, Arash
author_facet Loni, Mohammad
Poursalim, Fatemeh
Asadi, Mehdi
Gharehbaghi, Arash
contents This paper presents the results of a novel scoping review on the practical models for generating three different types of synthetic health records (SHRs): medical text, time series, and longitudinal data. The innovative aspects of the review, which incorporate study objectives, data modality, and research methodology of the reviewed studies, uncover the importance and the scope of the topic for the digital medicine context. In total, 52 publications met the eligibility criteria for generating medical time series (22), longitudinal data (17), and medical text (13). Privacy preservation was found to be the main research objective of the studied papers, along with class imbalance, data scarcity, and data imputation as the other objectives. The adversarial network-based, probabilistic, and large language models exhibited superiority for generating synthetic longitudinal data, time series, and medical texts, respectively. Finding a reliable performance measure to quantify SHR re-identification risk is the major research gap of the topic.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12274
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Review on Generative AI Models for Synthetic Medical Text, Time Series, and Longitudinal Data
Loni, Mohammad
Poursalim, Fatemeh
Asadi, Mehdi
Gharehbaghi, Arash
Machine Learning
Computation and Language
This paper presents the results of a novel scoping review on the practical models for generating three different types of synthetic health records (SHRs): medical text, time series, and longitudinal data. The innovative aspects of the review, which incorporate study objectives, data modality, and research methodology of the reviewed studies, uncover the importance and the scope of the topic for the digital medicine context. In total, 52 publications met the eligibility criteria for generating medical time series (22), longitudinal data (17), and medical text (13). Privacy preservation was found to be the main research objective of the studied papers, along with class imbalance, data scarcity, and data imputation as the other objectives. The adversarial network-based, probabilistic, and large language models exhibited superiority for generating synthetic longitudinal data, time series, and medical texts, respectively. Finding a reliable performance measure to quantify SHR re-identification risk is the major research gap of the topic.
title A Review on Generative AI Models for Synthetic Medical Text, Time Series, and Longitudinal Data
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2411.12274