Hospital-wide natural language processing summarising the health data of 1 million patients
Open accessPublished version of a preprint
Abstract
Electronic health records (EHRs) represent a major repository of real world clinical trajectories, interventions and outcomes. While modern enterprise EHR’s try to capture data in structured standardised formats, a significant bulk of the available information captured in the EHR is still recorded only in unstructured text format and can only be transformed into structured codes by manual processes. Recently, Natural Language Processing (NLP) algorithms have reached a level of performance suitable for large scale and accurate information extraction from clinical text. Here we describe the application of open-source named-entity-recognition and linkage (NER+L) methods (CogStack, MedCAT) to the entire text content of a large UK hospital trust (King’s College Hospital, London). The resulting dataset contains 157M SNOMED concepts generated from 9.5M documents for 1.07M patients over a period of 9 years. We present a summary of prevalence and disease onset as well as a patient embedding that captures major comorbidity patterns at scale. NLP has the potential to transform the health data lifecycle, through large-scale automation of a traditionally manual task.
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?
The disease profile of Foresight would be weighted to conditions and scenarios in secondary and tertiary care, i.e., weighted towards more comorbidity because patients with lower complexity or early-stage conditions who are completely dealt with in primary care would be under-represented in the dataset.
“the disease profile would be weighted to conditions and scenarios in secondary and tertiary care-ie, it would be weighted towards more comorbidity because patients with lower complexity or earlystage conditions who are completely dealt with in primary care would be underrepresented in our dataset.23”
From Foresight-a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study (2024) · cites this paper as [23]
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
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
MIMIC-III, a freely accessible critical care database
Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L.-W. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Anthony Celi, L., & Mark, R. G. (2016) · Scientific Data · doi:10.1038/sdata.2016.35 · Cited by 8,141 · see citing works
Natural Language Processing of Clinical Notes on Chronic Diseases: Systematic Review
Sheikhalishahi, S., Miotto, R., Dudley, J. T., Lavelli, A., Rinaldi, F., & Osmani, V. (2019) · JMIR Medical Informatics · doi:10.2196/12239 · Cited by 558 · see citing works
Deep learning in clinical natural language processing: a methodical review
Wu, S., Roberts, K. E., Datta, S., Du, J., Ji, Z., Si, Y., Soni, S., Wang, Q., Wei, Q., Xiang, Y., et al. (2019) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocz200 · Cited by 495 · see citing works
Data from clinical notes: a perspective on the tension between structure and flexible documentation
Rosenbloom, S. T., Denny, J. C., Xu, H., Lorenzi, N., Stead, W. W., & Johnson, K. B. (2011) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2010.007237 · Cited by 404 · see citing works
Clinical text data in machine learning: systematic review
Spasic, I., & Nenadic, G. (2020) · JMIR Medical Informatics · doi:10.2196/17984 · Cited by 358 · see citing works
Kuan, V., Denaxas, S., Gonzalez-Izquierdo, A., Direk, K., Bhatti, O., Husain, S., Sutaria, S., Hingorani, M., Nitsch, D., Parisinos, C. A., et al. (2019) · The Lancet Digital Health · doi:10.1016/s2589-7500(19)30012-3 · Cited by 305 · see citing works
Challenges and opportunities beyond structured data in analysis of electronic health records
Tayefi, M., Ngo, P. D., Chomutare, T., Dalianis, H., Salvi, E., Budrionis, A., & Godtliebsen, F. (2021) · Wiley Interdisciplinary Reviews Computational Statistics · doi:10.1002/wics.1549 · Cited by 300 · see citing works
Denaxas, S., George, J., Herrett, E. L., Shah, A. D., Kalra, D., Hingorani, A. D., Mika Kivimaki, B., Timmis, A., Smeeth, L. L., & Hemingway, H. (2012) · International Journal of Epidemiology · doi:10.1093/ije/dys188 · Cited by 228 · see citing works
Kraljević, Ž., Searle, T., Shek, A., Roguski, Ł., Noor, K., Bean, D. M., Mascio, A., Zhu, L., Folarin, A., Roberts, A., et al. (2021) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102083 · Cited by 224 · see citing works
Self-citationrevising, M. D. A., Wood, A., Denholm, R., Hollings, S., Cooper, J., Ip, S. S., Walker, V. M., Denaxas, S., Akbari, A., Sterne, J. A. C., et al. (2021) · BMJ · doi:10.1136/bmj.n826 · Cited by 191 · see citing works
Jackson, R., Kartoglu, I., Stringer, C., Gorrell, G., Roberts, A., Song, X., Wu, H., Agrawal, A., Lui, K., Groza, T., et al. (2018) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-018-0623-9 · Cited by 134 · see citing works
Self-citationThe Value of Unstructured Electronic Health Record Data in Geriatric Syndrome Case Identification
Kharrazi, H., Anzaldi, L. J., Hernandez, L., Davison, A., Boyd, C. M., Leff, B., Kimura, J., & Weiner, J. P. (2018) · Journal of the American Geriatrics Society · doi:10.1111/jgs.15411 · Cited by 128 · see citing works
A comparison of phenotype definitions for diabetes mellitus
Richesson, R., Rusincovitch, S. A., Wixted, D., Batch, B. C., Feinglos, M. N., Miranda, M. L., Hammond, W. E., Califf, R. M., & Spratt, S. E. (2013) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2013-001952 · Cited by 127 · see citing works
Misclassification of Myocardial Injury as Myocardial Infarction
McCarthy, C. P., Murphy, S., Cohen, J. A., Rehman, S. C., Jones‐O’Connor, M., Olshan, D. S., Singh, A., Vaduganathan, M., Januzzi, J. L., & Wasfy, J. H. (2019) · JAMA Cardiology · doi:10.1001/jamacardio.2019.0716 · Cited by 108 · see citing works
The Revival of the Notes Field: Leveraging the Unstructured Content in Electronic Health Records
Assale, M., Dui, L. G., Cina, A., Seveso, A., & Cabitza, F. (2019) · Frontiers in Medicine · doi:10.3389/fmed.2019.00066 · Cited by 94 · see citing works
McCoy, T. H., Castro, V. M., Cagan, A., Roberson, A. M., Kohane, I. S., & Perlis, R. H. (2015) · PLoS ONE · doi:10.1371/journal.pone.0136341 · Cited by 90 · see citing works
Best practices in the real-world data life cycle
Zhang, J., Symons, J., Agapow, P., Teo, J., Paxton, C. A., Abdi, J., Mattie, H., Davie, C., Torres, A. Z., Folarin, A., et al. (2022) · PLOS Digital Health · doi:10.1371/journal.pdig.0000003 · Cited by 68 · see citing works
Self-citationChang, T. E., Lichtman, J. H., Goldstein, L. B., & George, M. G. (2016) · Journal of the American Heart Association · doi:10.1161/jaha.115.003056 · Cited by 60 · see citing works
Ford, E., Oswald, M., Hassan, L., Bozentko, K., Nenadic, G., & Cassell, J. (2020) · Journal of Medical Ethics · doi:10.1136/medethics-2019-105472 · Cited by 59 · see citing works
A Natural Language Processing Framework for Assessing Hospital Readmissions for Patients With COPD
Agarwal, A., Baechle, C., Behara, R. S., & Xingquan Zhu, A. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2684121 · Cited by 58 · see citing works
Prediction of venous thromboembolism using semantic and sentiment analyses of clinical narratives
Sabra, S., Malik, K. M., & Alobaidi, M. (2018) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2017.12.026 · Cited by 47 · see citing works
van Dijk, W. B., Fiolet, A. T. L., Schuit, E., Sammani, A., Groenhof, T. K. J., van der Graaf, R., de Vries, M. C., Alings, M., Schaap, J., Asselbergs, F. W., et al. (2020) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2020.11.014 · Cited by 38 · see citing works
Benin, A. L., Fenick, A. M., Herrin, J. S., Vitkauskas, G., Chen, J., & Brandt, C. (2011) · American Journal of Medical Quality · doi:10.1177/1062860611403136 · Cited by 31 · see citing works
Semantic computational analysis of anticoagulation use in atrial fibrillation from real world data
Bean, D. M., Teo, J., Wu, H., Oliveira, R., Patel, R., Bendayan, R., Shah, A. M., Dobson, R., & Scott, P. A. (2019) · PLoS ONE · doi:10.1371/journal.pone.0225625 · Cited by 23 · see citing works
Self-citationRodrigues, J. M., Schulz, S., Rector, A. L., Spackman, K. A., Üstün, B., Chute, C. G., Mea, V. D., Millar, J., & Persson, K. B. (2013) · PubMed · Cited by 18 · see citing works
Haue, A. D., Armenteros, J. J. A., Holm, P. C., Eriksson, R., Moseley, P. L., Køber, L., Bundgaard, H., & Brunak, S. (2022) · Cardiovascular Diabetology · doi:10.1186/s12933-022-01527-3 · Cited by 13 · see citing works
Real-time clinician text feeds from electronic health records
Teo, J., Dinu, V., Bernal, W. E., Davidson, P., Oliynyk, V., Breen, C. P., Barker, R. D., & Dobson, R. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00406-7 · Cited by 9 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Kraljevic, Z., Bean, D., Shek, A., Bendayan, R., Hemingway, H., Yeung, J. A., Deng, A., Balston, A., Ross, J., Idowu, E., et al. (2024) · The Lancet Digital Health · doi:10.1016/s2589-7500(24)00025-6 · Cited by 118 · see citing works
“23 We also note that our dataset does not fully encompass the patient medical history; patients could visit multiple institutions or move between countries, or some concepts might simply be missing because of the NER+L model we are using.”
Self-citationWu, J., Biswas, D., Ryan, M. J., Bernstein, B. S., Rizvi, M., Fairhurst, N., Kaye, G., Baral, R., Searle, T., Melikian, N., et al. (2023) · European Journal of Heart Failure · doi:10.1002/ejhf.3115 · Cited by 59 · see citing works
Self-citationNatural language processing data services for healthcare providers
Yeung, J. A., Shek, A., Searle, T., Kraljević, Ž., Dinu, V., Ratas, M., Al-Agil, M., Foy, A., Rafferty, B., Oliynyk, V., et al. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02713-x · Cited by 23 · see citing works
Self-citationArtificial intelligence (AI) for neurologists: do digital neurones dream of electric sheep?
Yeung, J. A., Wang, Y. Y., Kraljević, Ž., & Teo, J. (2023) · Practical Neurology · doi:10.1136/pn-2023-003757 · Cited by 23 · see citing works
Self-citationDuminuco, A., Yeung, J. A., Vaghela, R., Virdee, S. S., Woodley, C., Asirvatham, S., Curto‐García, N., Sriskandarajah, P., O’Sullivan, J., de Lavallade, H., et al. (2024) · HemaSphere · doi:10.1002/hem3.143 · Cited by 16 · see citing works
Artificial intelligence and machine learning in rheumatology
Dubey, S., Chan, A. T. Y., Adebajo, A., Walker, D., & Bukhari, M. A. S. (2024) · Lara D. Veeken · doi:10.1093/rheumatology/keae092 · Cited by 16 · see citing works
Retracted: Applying Natural Language Processing in Healthcare Using Data Science
Sett, S., & Singh, A. V. (2024) · International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) · doi:10.1109/icrito61523.2024.10522196 · Cited by 6 · see citing works
RetractedScoping review of knowledge graph applications in biomedical and healthcare sciences
Budhdeo, S., Zhang, J., Abdulle, Y., Agapow, P., McKechnie, D. G., Archer, M., Shah, V., Forte, E., Noori, A., Žitnik, M., et al. (2025) · Wellcome Open Research · doi:10.12688/wellcomeopenres.23599.1 · Cited by 6 · see citing works
Wu, J., Biswas, D., Brown, S., Ryan, M., Bernstein, B. S., To, B. T., Searle, T., Rizvi, M., Fairhurst, N., Kaye, G., et al. (2025) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztaf107 · Cited by 8 · see citing works
Self-citationExploring the role of artificial intelligence in orthopedic medical education: A narrative review
Das, L. S., Das, D., Chandrakar, D., Bhavani, P., Dubepuria, A., & Barik, S. (2025) · Journal of Clinical Orthopaedics and Trauma · doi:10.1016/j.jcot.2025.103100 · Cited by 4 · see citing works
Electronic health record-enhanced signal detection using tree-based scan statistic methods
Russo, M., Sreedhara, S. K., Smith, J., Davis, S. E., Maro, J. C., DeRamus, T. P., Lii, J., Yang, J., Desai, R. J., Hernández‐Muñoz, J. J., et al. (2025) · American Journal of Epidemiology · doi:10.1093/aje/kwaf199 · Cited by 1 · see citing works
Rubio-Martín, S., Crespo-Álvaro, A., García-Ordás, M. T., García, A. S., Pato, C. M. F., & Benítez‐Andrades, J. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-10661-2_22 · Cited by 1 · see citing works
Wu, J., Biswas, D., Brown, S., Ryan, M., Bernstein, B. S., To, B. T., Searle, T., Rizvi, M., Fairhurst, N., Kaye, G., et al. (2024) · medRxiv · doi:10.1101/2024.12.24.24319603 · Cited by 1 · see citing works
Self-citationHouston, A., Williams, S., Ricketts, W. M., Gutteridge, C., Tackaberry, C., & Conibear, J. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02790-y
Houston, A., Williams, S., Ricketts, W. M., Gutteridge, C., Tackaberry, C., & Conibear, J. (2024) · medRxiv · doi:10.1101/2024.02.20.24303084
Grim, S., Fuhlbrigge, A. L., Thomas, J. F., & Kessler, R. S. (2025) · Health Informatics Journal · doi:10.1177/14604582251345319
Singh, D., Singh, R., Masum, H., Kumar, A., & Rathee, S. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-33028-5.00012-4
Saha, S., Singh, M. K., Obhrai, S., & Astuti, Y. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45252-9.00020-7
Strengthening E-Collaboration in Healthcare Through AI
Billingsley, F. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5906-9.ch009
Artificial intelligence in quality of life (QOL) assessment for oral cancer patients
Jayasinghe, R. M., Attygalla, A. M., Kanmodi, K. K., & Jayasinghe, R. D. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-34423-7.00006-7
Asgari, E., & Zakri, R. H. (2026) · Springer eBooks · doi:10.1007/978-3-032-17572-4_24
Advancing Patient‐Centred AI With Adaptive Machine Learning
Kalogeropoulos, D., Barach, P. R., Downing, A., Verhulst, S., & Lustberg, M. B. (2026) · Cancer Medicine · doi:10.1002/cam4.72371
- Authors
- Bean, D. M., Kraljevic, Z., Shek, A., Teo, J., & Dobson, R. J. B.
- Affiliations
- King's College London (GB)
- University College London Hospitals NHS Foundation Trust (GB)
- Corresponding author
- Bean, Daniel M.
- Venue
- PLOS Digital Health
- Publisher
- Public Library of Science (PLoS)
- Published
- 2023-05-09
- Volume
- 2
- Issue
- 5
- Pages
- e0000218
- ISSN
- 2767-3170 (ISSN-L)
- PMC
- PMC10168555
- OpenAlex
- W4376133440
- Cited by
- 22
- References
- 27
- Citations by year
- 2026: 7 · 2025: 5 · 2024: 8 · 2023: 2
- FWCI
- 1.96
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLOS Digital Health (publishedVersion, cc-by)
- medRxiv (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- UCL Discovery (University College London) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Research Portal (King's College London) (submittedVersion, cc-by)
- Research Portal (King's College London) (submittedVersion, cc-by-nc-nd)
- Funders
- Medical Research Council (MR/S00310X/1)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Biomedical Text Mining and Ontologies
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Medical Coding and Health Information
- Keywords
- natural language processing, electronic health records, named entity recognition, entity linking, clinical text, comorbidity patterns, disease onset, patient embeddings, clinical information extraction
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
