A review on generative AI models for synthetic medical text, time series, and longitudinal data

Abstract 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 modalit...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammad Loni, Fatemeh Poursalim, Mehdi Asadi, Arash Gharehbaghi
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-024-01409-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849326890827907072
author Mohammad Loni
Fatemeh Poursalim
Mehdi Asadi
Arash Gharehbaghi
author_facet Mohammad Loni
Fatemeh Poursalim
Mehdi Asadi
Arash Gharehbaghi
author_sort Mohammad Loni
collection DOAJ
description Abstract 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 Article
id doaj-art-e51c3552fd5745a88a5748a90a4cd03a
institution Kabale University
issn 2398-6352
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-e51c3552fd5745a88a5748a90a4cd03a2025-08-20T03:48:02ZengNature Portfolionpj Digital Medicine2398-63522025-05-018111010.1038/s41746-024-01409-wA review on generative AI models for synthetic medical text, time series, and longitudinal dataMohammad Loni0Fatemeh Poursalim1Mehdi Asadi2Arash Gharehbaghi3School of Innovation, Design and Engineering, Mälardalen UniversityServicehälsan Familjeläkare i Västerås ABICT Department, Turku University of Applied SciencesDepartment of Biomedical Engineering, Linköping UniversityAbstract 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.https://doi.org/10.1038/s41746-024-01409-w
spellingShingle Mohammad Loni
Fatemeh Poursalim
Mehdi Asadi
Arash Gharehbaghi
A review on generative AI models for synthetic medical text, time series, and longitudinal data
npj Digital Medicine
title A review on generative AI models for synthetic medical text, time series, and longitudinal data
title_full A review on generative AI models for synthetic medical text, time series, and longitudinal data
title_fullStr A review on generative AI models for synthetic medical text, time series, and longitudinal data
title_full_unstemmed A review on generative AI models for synthetic medical text, time series, and longitudinal data
title_short A review on generative AI models for synthetic medical text, time series, and longitudinal data
title_sort review on generative ai models for synthetic medical text time series and longitudinal data
url https://doi.org/10.1038/s41746-024-01409-w
work_keys_str_mv AT mohammadloni areviewongenerativeaimodelsforsyntheticmedicaltexttimeseriesandlongitudinaldata
AT fatemehpoursalim areviewongenerativeaimodelsforsyntheticmedicaltexttimeseriesandlongitudinaldata
AT mehdiasadi areviewongenerativeaimodelsforsyntheticmedicaltexttimeseriesandlongitudinaldata
AT arashgharehbaghi areviewongenerativeaimodelsforsyntheticmedicaltexttimeseriesandlongitudinaldata
AT mohammadloni reviewongenerativeaimodelsforsyntheticmedicaltexttimeseriesandlongitudinaldata
AT fatemehpoursalim reviewongenerativeaimodelsforsyntheticmedicaltexttimeseriesandlongitudinaldata
AT mehdiasadi reviewongenerativeaimodelsforsyntheticmedicaltexttimeseriesandlongitudinaldata
AT arashgharehbaghi reviewongenerativeaimodelsforsyntheticmedicaltexttimeseriesandlongitudinaldata