Authors: Katariina Perkonoja, Kari Auranen, Joni Virta

Published on: September 21, 2023

Impact Score: 7.8

Arxiv code: Arxiv:2309.12380

Summary

• What is new: This research systematically reviews methods for generating and evaluating synthetic longitudinal patient data, a topic with growing importance due to data privacy concerns in healthcare.
• Why this is important: The challenge of utilizing abundant data in industries with strict privacy regulations, like healthcare.
• What the research proposes: The paper presents a comprehensive examination of methods for creating and evaluating synthetic data to mimic sensitive real-world data legally and effectively.
• Results: The review identifies and describes 17 different methods, from traditional simulations to advanced deep learning techniques, and provides practical guidelines for their application.

Technical Details

Technological frameworks used: PRISMA guidelines for systematic reviews

Models used: Traditional simulation techniques, deep learning methods

Data used: Literatures from five databases until the end of 2022

Potential Impact

Healthcare, legal services, data analysis companies, and businesses in industries with significant privacy concerns could benefit or be disrupted.

Want to implement this idea in a business?

We have generated a startup concept here: MediSynth.