arXiv subjects

Klaus Kraywinkel

Publications and source records attributed to Klaus Kraywinkel.

4 recordsLinked to original sources

arXiv2026

Evaluating quality in synthetic data generation for large tabular health datasets

There is no consensus in the field of synthetic data on concise metrics for quality evaluations or benchmarks on large health datasets, such as historical epidemiological data. This study presents an evaluation of seven recent models from major machine learning families. The models were evaluated using four different datasets, each with a distinct scale. To ensure a fair comparison, we systematically tuned the hyperparameters of each model for each dataset. We propose a methodology for evaluating the fidelity of synthesized joint distributions, aligning metrics with visualization on a single plot. This method is applicable to any dataset and is complemented by a domain-specific analysis of the German Cancer Registries' epidemiological dataset. The analysis reveals the challenges models face in strictly adhering to the medical domain. We hope this approach will serve as a foundational framework for guiding the selection of synthesizers and remain accessible to all stakeholders involved in releasing synthetic datasets.

cs.LG↗

arXiv2026

Explainable histomorphology-based survival prediction of glioblastoma, IDH-wildtype

Glioblastoma, IDH-wildtype (GBM-IDHwt) is the most common malignant brain tumor. While histomorphology is a crucial component of GBM-IDHwt diagnosis, it is not further considered for prognosis. Here, we present an explainable artificial intelligence (AI) framework to identify and interpret histomorphological features associated with patient survival. The framework combines an explainable multiple instance learning (MIL) architecture that directly identifies prognostically relevant image tiles with a sparse autoencoder (SAE) that maps these tiles to interpretable visual patterns. The MIL model was trained and evaluated on a new real-world dataset of 720 GBM-IDHwt cases from three hospitals and four cancer registries across Germany. The SAE was trained on 1,878 whole-slide images from five independent public glioblastoma collections. Despite the many factors influencing survival time, our method showed some ability to discriminate between patients living less than 180 days or more than 360 days solely based on histomorphology (AUC: 0.67; 95% CI: 0.63-0.72). Cox proportional hazards regression confirmed a significant survival difference between predicted groups after adjustment for established prognostic factors (hazard ratio: 1.47; 95% CI: 1.26-1.72). Three neuropathologists categorized the identified visual patterns into seven distinct histomorphological groups, revealing both established prognostic features and unexpected associations, the latter being potentially attributable to surgery-related confounders. The presented explainable AI framework facilitates prognostic biomarker discovery in GBM-IDHwt and beyond, highlighting promising histomorphological features for further analysis and exposing potential confounders that would be hidden in black-box models.

eess.IV↗

arXiv2025

Automatic Extraction of Rules for Generating Synthetic Patient Data From Real-World Population Data Using Glioblastoma as an Example

The generation of synthetic data is a promising technology to make medical data available for secondary use in a privacy-compliant manner. A popular method for creating realistic patient data is the rule-based Synthea data generator. Synthea generates data based on rules describing the lifetime of a synthetic patient. These rules typically express the probability of a condition occurring, such as a disease, depending on factors like age. Since they only contain statistical information, rules usually have no specific data protection requirements. However, creating meaningful rules can be a very complex process that requires expert knowledge and realistic sample data. In this paper, we introduce and evaluate an approach to automatically generate Synthea rules based on statistics from tabular data, which we extracted from cancer reports. As an example use case, we created a Synthea module for glioblastoma from a real-world dataset and used it to generate a synthetic dataset. Compared to the original dataset, the synthetic data reproduced known disease courses and mostly retained the statistical properties. Overall, synthetic patient data holds great potential for privacy-preserving research. The data can be used to formulate hypotheses and to develop prototypes, but medical interpretation should consider the specific limitations as with any currently available approach.

cs.LG↗

arXiv2023

Verbesserung des Record Linkage für die Gesundheitsforschung in Deutschland

Record linkage means linking data from multiple sources. This approach enables the answering of scientific questions that cannot be addressed using single data sources due to limited variables. The potential of linked data for health research is enormous, as it can enhance prevention, treatment, and population health policies. Due the sensitivity of health data, there are strict legal requirements to prevent potential misuse. However, these requirements also limit the use of health data for research, thereby hindering innovations in prevention and care. Also, comprehensive Record linkage in Germany is often challenging due to lacking unique personal identifiers or interoperable solutions. Rather, the need to protect data is often weighed against the importance of research aiming at healthcare enhancements: for instance, data protection officers may demand the informed consent of individual study participants for data linkage, even when this is not mandatory. Furthermore, legal frameworks may be interpreted differently on varying occasions. Given both, technical and legal challenges, record linkage for health research in Germany falls behind the standards of other European countries. To ensure successful record linkage, case-specific solutions must be developed, tested, and modified as necessary before implementation. This paper discusses limitations and possibilities of various data linkage approaches tailored to different use cases in compliance with the European General Data Protection Regulation. It further describes requirements for achieving a more research-friendly approach to linking health data records in Germany. Additionally, it provides recommendations to legislators. The objective of this work is to improve record linkage for health research in Germany.

cs.CY↗