Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0583
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-07-29T06:07:58.719487Z
status: published
lens: g_space
sector: science
headline: Anonymized but Useful Synthetic Tabular Health Data for AI based Fall Risk Assessment
dek: Artificial Intelligence (AI) bears potential for improving health care, but this depends on the availability of open-access, realistic, and useful data. To facilitate AI model development in health care we release SynTabFall, a novel synthetic dataset for fall risk assessment. With a total of 745,380 samples and 44 attributes such as demographics, diseases, mobility and cognition related risk factors, this tabular dataset allows for training fall risk prediction models without access to the original patient data…
gain_title: Release of SynTabFall synthetic dataset with 745,380 samples allows training fall-risk prediction models without original patient data while achieving performance on par with models trained on real data.
problem_title: (none)
trace_subject: (none)
gain_reading: Release of SynTabFall synthetic dataset with 745,380 samples allows training fall-risk prediction models without original patient data while achieving performance on par with models trained on real data.
gain_evidence: Models trained on our synthetic dataset can reach predictive performance scores in fall risk assessment which are on par with models trained on real data. | allows for training fall risk prediction models without access to the original patient data
problem_reading: (none)
problem_evidence: (none)
quick_read: On 2026-07-24, researchers described SynTabFall, a synthetic tabular health dataset of 745,380 samples and 44 attributes covering demographics, diseases, mobility and cognition risk factors for fall risk assessment. They reported that models trained on the synthetic data can reach predictive performance on par with models trained on real data, without requiring access to original patient records.

The approach matters because it offers a pathway to share health care data responsibly while preserving utility for AI development, developed with hospital data protection and clinical staff. What remains unproven in this text is how the synthetic data performs across different hospitals, populations, or fall-prevention workflows beyond the reported assessment scores.
limitation: 
tag: Evidence-backed gain
key_points: SynTabFall contains 745,380 samples and 44 attributes such as demographics, diseases, mobility and cognition related risk factors. | Dataset and generation/evaluation software were released to support AI model development in health care. | Data sharing approach was developed over multiple years in one of Germany's largest hospitals with data protection officers, health care staff, informaticians and AI engineers.
rundown: The authors describe SynTabFall as a novel synthetic tabular dataset for fall risk assessment, built to address lack of open-access realistic data for health AI. The generation process combines established anonymization methods and modern generative AI methods for synthesizing tabular data.

The work was developed over multiple years in one of Germany's largest hospitals in close collaboration between data protection officers, health care staff, informaticians and AI engineers, and includes release of both the dataset and the software for generation and evaluation.
sources:
- peer_reviewed | Scientific Data | https://doi.org/10.1038/s41597-026-07910-z | 2026-07-24
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

c460f7522c812894f9970acef0b7fb9f009f007779ff40178b7a6b182c2fea3f

previous

0000000000000000000000000000000000000000000000000000000000000000