Representativeness of a German AI‐Enabled Data Network for Secondary Epidemiological Analysis Based on Electronic Health Records
Open accessAbstract
Introduction: The ongoing digitalization of medicine, increased computing power and low-cost storage capacities enable the use of AI-based algorithms for epidemiological big data analysis of electronic patient records. The aim of this study was to evaluate the representativeness of a data network with infrastructure for federated machine learning (ML) across numerous German hospitals. This was done by comparing basic data from the ML data network with publicly available data from the Federal Statistical Office (DESTATIS) to test the scientific validity for future epidemiological analyses. Methods: In a retrospective epidemiological secondary analysis, 8,106,105 case files from the ML network were examined and compared to DESTATIS data regarding age, gender, length of hospital stay, ICD-10 diagnoses, and OPS codes. In addition, ICD-10 codes for substance abuse and the regional distribution were compared to examine socioeconomic confounders. Results: The variables age, gender and length of stay, as well as the most common general ICD-10 and OPS codes and ENT-specific OPS codes, showed a high level of concordance based on clinical relevance. For the ENT-specific ICD-10 codes, 2 out of 11 of the most frequent codes showed a maximum deviation of 3.71%. The analysis of socioeconomic factors and regional distribution showed no evidence for deviations. Discussion: The high level of agreement for the variables examined indicates the representativeness of the ML dataset in comparison to the DESTATIS data. This finding paves the way for future epidemiological studies based on big data, which were previously unavailable in research.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Federated learning networks across hospital systems provide infrastructure for analyzing SDOH at scale.
“Social determinants function as essential predictive signals rather than background context, and federated learning networks across hospital systems provide infrastructure for analyzing SDOH at scale [4].”
From Artificial Intelligence and Machine Learning for Identifying Social Determinants of Health in Low‐Income Populations Within United States Health Systems: A Scoping Review (2026) · cites this paper as [4]
The Methods (Databases; page unavailable) describe a federated machine-learning network spanning German hospitals and roughly 10 million electronic health records. The Results (Socioeconomic confounders; page unavailable) analyze selected socioeconomic proxies, but the Methods (Bias and confounder; page unavailable) say education and income were unavailable. The paper therefore supports large-scale analysis of some socioeconomic indicators, not the broader claim that the network enables analysis of SDOH generally. (LLM, conf=0.85)
Experimental — accuracy not yet measuredSocial determinants function as essential predictive signals rather than background context.
“Social determinants function as essential predictive signals rather than background context, and federated learning networks across hospital systems provide infrastructure for analyzing SDOH at scale [4].”
From Artificial Intelligence and Machine Learning for Identifying Social Determinants of Health in Low‐Income Populations Within United States Health Systems: A Scoping Review (2026) · cites this paper as [4]
Methods (Databases; no page given) describes a federated machine-learning network spanning German hospitals and roughly 10 million electronic health records. Methods (Bias and confounder; no page given) treats socioeconomic position as a possible confounder and says education and income data were unavailable. The paper does not establish that social determinants are essential predictive signals or demonstrate their analysis at scale. (LLM, conf=0.86)
Experimental — accuracy not yet measuredExpanded computing capacity allows AI algorithms to analyze large patient populations.
“Expanded computing capacity allows AI algorithms to analyze large patient populations [4].”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
von Elm, E., Altman, D. G., Egger, M., Pocock, S. J., Gøtzsche, P. C., & Vandenbroucke, J. P. (2007) · The Lancet · doi:10.1016/s0140-6736(07)61602-x · Cited by 21,320 · see citing works
Benchimol, E. I., Smeeth, L., Guttmann, A., Harron, K., Moher, D., Petersen, I., Sørensen, H. T., von Elm, E., Langan, S. M., & RECORD Working Committee (2015) · PLOS Medicine · doi:10.1371/journal.pmed.1001885 · Cited by 5,749 · see citing works
Measuring Social Class in US Public Health Research: Concepts, Methodologies, and Guidelines
Krieger, N., Williams, D. R., & Moss, N. (1997) · Annual Review of Public Health · doi:10.1146/annurev.publhealth.18.1.341 · Cited by 2,680 · see citing works
Big data and machine learning algorithms for health-care delivery
Ngiam, K. Y., & Khor, I. W. (2019) · The Lancet Oncology · doi:10.1016/s1470-2045(19)30149-4 · Cited by 1,424 · see citing works
Social justice, epidemiology and health inequalities
Marmot, M. (2017) · European Journal of Epidemiology · doi:10.1007/s10654-017-0286-3 · Cited by 306 · see citing works
Emulating Randomized Clinical Trials With Nonrandomized Real-World Evidence Studies
Franklin, J. M., Patorno, E., Desai, R. J., Glynn, R. J., Martin, D., Quinto, K., Pawar, A. M., Bessette, L. G., Lee, H., Garry, E. M., et al. (2020) · Circulation · doi:10.1161/circulationaha.120.051718 · Cited by 301 · see citing works
Protecting against researcher bias in secondary data analysis: challenges and potential solutions
Baldwin, J. R., Pingault, J.-B., Schoeler, T., Sallis, H. M., & Munafò, M. R. (2022) · European Journal of Epidemiology · doi:10.1007/s10654-021-00839-0 · Cited by 178 · see citing works
Sozioökonomischer Status und Gesundheit
Lampert, T., Kroll, L. E., von der Lippe, E., Müters, S., & Stolzenberg, H. (2013) · Bundesgesundheitsblatt - Gesundheitsforschung - Gesundheitsschutz · doi:10.1007/s00103-013-1695-4 · Cited by 144 · see citing works
A review of big data and medical research
Mallappallil, M. C., Sabu, J., Gruessner, A. C., & Salifu, M. (2020) · SAGE Open Medicine · doi:10.1177/2050312120934839 · Cited by 95 · see citing works
Socioeconomic indicators in epidemiologic research: A practical example from the LIFEPATH study
d’Errico, A., Ricceri, F., Stringhini, S., Carmeli, C., Mika Kivimaki, B., Bartley, M., McCrory, C., Bochud, M., Vollenweider, P., Tumino, R., et al. (2017) · PLoS ONE · doi:10.1371/journal.pone.0178071 · Cited by 77 · see citing works
Real-World Evidence—Current Developments and Perspectives
Schad, F., & Thronicke, A. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph191610159 · Cited by 73 · see citing works
Sharp, M. K., Bertizzolo, L., Rius, R., Wager, E., Melis, G. G., & Hren, D. (2019) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2019.07.019 · Cited by 56 · see citing works
GetReal: from efficacy in clinical trials to relative effectiveness in the real world
Egger, M., Moons, K. G. M., Fletcher, C., & 4, G. W. (2016) · Research Synthesis Methods · doi:10.1002/jrsm.1207 · Cited by 30 · see citing works
Acha, V., Barefoot, B., García, A. J., Lehner, V., Monno, R., Sandler, S., Spooner, Á., & Verpillat, P. (2023) · Therapeutic Innovation & Regulatory Science · doi:10.1007/s43441-023-00544-y · Cited by 18 · see citing works
Bedir, A., Abera, S. F., Vordermark, D., & Medenwald, D. (2022) · Journal of Cancer Research and Clinical Oncology · doi:10.1007/s00432-021-03908-9 · Cited by 11 · see citing works
Stricker, B. H. C. (2017) · European Journal of Epidemiology · doi:10.1007/s10654-017-0294-3 · Cited by 9 · see citing works
Balancing statistical significance and clinical relevance
Morgan, C. J. (2018) · Journal of Nuclear Cardiology · doi:10.1007/s12350-018-1267-y · Cited by 8 · see citing works
Disclosing progress in cancer survival with less delay
Jansen, L., Schröder, C. C., Emrich, K., Holleczek, B., Pritzkuleit, R., & Brenner, H. (2019) · International Journal of Cancer · doi:10.1002/ijc.32816 · Cited by 5 · see citing works
Grundmann, S., Kaier, K., Maier, A., Rilinger, J., Steinfurt, J., Stiller, B., Westermann, D., Mühlen, C. V. Z., & Jäckel, M. (2025) · Clinical Research in Cardiology · doi:10.1007/s00392-025-02614-7 · Cited by 5 · see citing works
Forschung mit Krebsregistern – was geht, was (noch) nicht?
Katalinic, A., Pritzkuleit, R., & Kraywinkel, K. (2023) · Die Onkologie · doi:10.1007/s00761-023-01426-6 · Cited by 4 · see citing works
AlZahmi, A., Cenzer, I. S., Mansmann, U., Ostermann, H., Theurich, S., Schleinkofer, T., & Berger, K. (2022) · PLoS ONE · doi:10.1371/journal.pone.0271754 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 7
- [10]Ayaz M, Pasha MF, Alzahrani MY, Budiarto R, Stiawan D. The Fast Health Interoperability Resources (FIHR) Standard: Systematic Literature Review of Implementations, Applications, Challenges and Opportunities. JMIR Medical Informatics. 2021; 9. PMC8367140 34328424
- [11]Lesch W, Richter G, Semler SC. Daten teilen für die Forschung: Einstellungen und Perspektiven zur Datenspende in Deutschland. In: Datenreiche Medizin und das Problem der Einwilligung. Berlin, Heidelberg: Springer Berlin Heidelberg; 2022: 211– 26.
- [14]Krieger N, Williams DR, Moss NE. Measuring social class in US public health research. Annu Rev Public Health. 1997; 18: 341– 78. 9143723
- [19]Lampert T, Hoebel J, Kuntz B, Müters S, Kroll KE. Measurement of socioeconomic status and subjective social status in KiGGS wave 2. J Health Monit. 2018; 3(1): 114– 33. PMC8848848 35586179
- [21]Partido BB. Formalized Curiosity for Knowledge and Innovation. https://ohiostate.pressbooks.pub/formalizedcuriosity/chapter/chapter-15-clinical-versus-statistical-significance/. Accessed 2025 August 26.
- [22]Rothman KJ, Greenland S ander, Lash TL. Modern epidemiology. Wolters Kluwer Health/Lippincott Williams & Wilkins. 2008.
- [30]Neugebauer EAM, Stausberg J. What can and cannot be achieved by registries: Perspective of the registry working group of the German Network of Health Services Research. Unfallchirurg. 2016; 119(6): 493– 500. doi: 10.1007/s00113-016-0176-2 27169850 · DOI
Cited by
Sorted by citations
Razzano, A. V. (2026) · Health Science Reports · doi:10.1002/hsr2.73083
Eichhorn, S., Stöckert, A., Mitze, F. N., Bucksch, M., Erdogan, E., Seuthe, I. M. C., Dastur, M., & Park, J. J. (2026) · European Archives of Oto-Rhino-Laryngology · doi:10.1007/s00405-026-10583-4
Self-citation
- Authors
- Eichhorn, S., Mitze, F. N., Wagner, F., Seuthe, I. M. C., Brinks, R., Zimmermann, A., Dastur, M., Ladenbauer, J., & Park, J. J.-H.
- Affiliations
- Witten/Herdecke University (DE)
- Corresponding author
- Eichhorn, Sabine
- ORCID
- Venue
- PLOS One
- Publisher
- Public Library of Science (PLoS)
- Published
- 2026-01-06
- Volume
- 21
- Issue
- 1
- Pages
- e0339647
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC12773821
- OpenAlex
- W7118674282
- Cited by
- 2
- References
- 20
- Citations by year
- 2026: 2
- FWCI
- 15.01
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS ONE (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- European Union (16DTM309)
- German Federal Ministry of Education and Research (16DTM309)
- Topics
- Health Sciences › Health Professions › Health Information Management › Medical Coding and Health Information
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Keywords
- representativeness, federated learning, electronic health records, big data, German hospitals, ICD-10 codes, OPS codes, substance abuse, regional distribution
- MeSH terms
- Machine Learning, Adolescent, Adult, Aged, Female, Germany, Humans, Length of Stay, Male, Middle Aged, Retrospective Studies, International Classification of Diseases, Young Adult, Electronic Health Records
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
