Utilizing Deep Learning to Analyze Whole Slide Images of Colonic Biopsies for Associations Between Eosinophil Density and Clinicopathologic Features in Active Ulcerative Colitis
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Background: Eosinophils have been implicated in the pathogenesis of ulcerative colitis and have been associated with disease course and therapeutic response. However, associations between eosinophil density, histologic activity, and clinical features have not been rigorously studied. Methods: A deep learning algorithm was trained to identify eosinophils in colonic biopsies and validated against pathologists’ interpretations. The algorithm was applied to sigmoid colon biopsies from a cross-sectional cohort of 88 ulcerative colitis patients with histologically active disease as measured by the Geboes score and Robarts histopathology index (RHI). Associations between eosinophil density, histologic activity, and clinical features were determined. Results: The eosinophil deep learning algorithm demonstrated almost perfect agreement with manual eosinophil counts determined by 4 pathologists (interclass correlation coefficients: 0.805–0.917). Eosinophil density varied widely across patients (median 113.5 cells per mm2, interquartile range 108.9). There was no association between eosinophil density and RHI (P = 0.5). Significant differences in eosinophil density were seen between patients with Montreal E3 vs E2 disease (146.2 cells per mm2 vs 88.2 cells per mm2, P = 0.005). Patients on corticosteroids had significantly lower eosinophil density (62.9 cells per mm2 vs 124.1 cells per mm2, P = 0.006). No association between eosinophil density and biologic use was observed (P = 0.5). Conclusions: We developed a deep learning algorithm to quantify eosinophils in colonic biopsies. Eosinophil density did not correlate with histologic activity but did correlate with disease extent and corticosteroid use. Future studies applying this algorithm in larger cohorts with longitudinal follow-up are needed to further elucidate the role of eosinophils in ulcerative colitis.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“When applied to colonic biopsies from 88 patients with active UC, this algorithm perfectly agreed with manual eosinophil counts performed by pathologists (ICC=0.81-0.92).”
From Artificial intelligence and endo-histo-omics: new dimensions of precision endoscopy and histology in inflammatory bowel disease (2024) · cites this paper as [57]
Citations
Cites
The Measurement of Observer Agreement for Categorical Data
Landis, J. R., & Koch, G. G. (1977) · Biometrics · doi:10.2307/2529310 · Cited by 81,148
Satsangi, J., Silverberg, M. S., Vermeire, S., & Colombel, J.-F. (2006) · Gut · doi:10.1136/gut.2005.082909 · Cited by 3,176
Peyrin-Biroulet, L., Sandborn, W., Sands, B. E., Reinisch, W., Bemelman, W., Bryant, R. V., D'Haens, G., Dotan, I., Dubinsky, M., Feagan, B., et al. (2015) · American Journal of Gastroenterology · doi:10.1038/ajg.2015.233 · Cited by 1,844
A reproducible grading scale for histological assessment of inflammation in ulcerative colitis
Geboes, K. (2000) · Gut · doi:10.1136/gut.47.3.404 · Cited by 943
Solberg, I. C., Lygren, I., Jahnsen, J., Aadland, E., Høie, O., Cvancarova, M., Bernklev, T., Henriksen, M., Sauar, J., Vatn, M. H., et al. (2009) · Scandinavian Journal of Gastroenterology · doi:10.1080/00365520802600961 · Cited by 731
Efficacy of Dupilumab in a Phase 2 Randomized Trial of Adults With Active Eosinophilic Esophagitis
Hirano, I., Dellon, E. S., Hamilton, J. D., Collins, M. H., Peterson, K., Chehade, M., Schoepfer, A. M., Safroneeva, E., Rothenberg, M. E., Falk, G. W., et al. (2020) · Gastroenterology · doi:10.1053/j.gastro.2019.09.042 · Cited by 460
Ozanimod Induction and Maintenance Treatment for Ulcerative Colitis
Sandborn, W. J., Feagan, B. G., Wolf, D. C., D’Haens, G., Vermeire, S., Hanauer, S. B., Ghosh, S., Smith, H., Cravets, M., Frohna, P. A., et al. (2016) · New England Journal of Medicine · doi:10.1056/nejmoa1513248 · Cited by 452
Development and validation of a histological index for UC
Mosli, M. H., Feagan, B. G., Zou, G., Sandborn, W. J., D'Haens, G., Khanna, R., Shackelton, L. M., Walker, C. W., Nelson, S., Vandervoort, M. K., et al. (2017) · Gut · doi:10.1136/gutjnl-2015-310393 · Cited by 350
Self-citationBryant, R. V., Winer, S., SPL, T., & Riddell, R. H. (2014) · Journal of Crohn's and Colitis · doi:10.1016/j.crohns.2014.08.011 · Cited by 300
Anti–Siglec-8 Antibody for Eosinophilic Gastritis and Duodenitis
Dellon, E. S., Peterson, K. A., Murray, J. A., Falk, G. W., Gonsalves, N., Chehade, M., Genta, R. M., Leung, J., Khoury, P., Klion, A. D., et al. (2020) · New England Journal of Medicine · doi:10.1056/nejmoa2012047 · Cited by 268
Cited by
Iacucci, M., Parigi, T. L., Del Amor, R., Meseguer, P., Mandelli, G., Bozzola, A., Bazarova, A., Bhandari, P., Bisschops, R., Danese, S., et al. (2023) · Gastroenterology · doi:10.1053/j.gastro.2023.02.031 · Cited by 127
Artificial intelligence and inflammatory bowel disease: Where are we going?
Rio, L. D., Spadaccini, M., Parigi, T. L., Gabbiadini, R., Buono, A. D., Busacca, A., Maselli, R., Fugazza, A., Colombo, M., Carrara, S., et al. (2023) · World Journal of Gastroenterology · doi:10.3748/wjg.v29.i3.508 · Cited by 94
Iacucci, M., Santacroce, G., Zammarchi, I., Maeda, Y., Del Amor, R., Meseguer, P., Kolawole, B. B., Chaudhari, U., Di Sabatino, A., Danese, S., et al. (2024) · The Lancet Gastroenterology & Hepatology · doi:10.1016/s2468-1253(24)00053-0 · Cited by 73
Artificial intelligence to revolutionize IBD clinical trials: a comprehensive review
Sedaño, R., Solitano, V., Vuyyuru, S. K., Yuan, Y., Hanžel, J., Ma, C., Nardone, O. M., & Jairath, V. (2025) · Therapeutic Advances in Gastroenterology · doi:10.1177/17562848251321915 · Cited by 68
“48 In UC histology, AI models have been used to develop novel scoring indices, 49,50 to replace human readers for established indices, 51,52 and to evaluate individual histological features, such as the presence of eosinophils 53 and basal cell plasmacytosis.”
Rymarczyk, D., Schultz, W., Borowa, A., Friedman, J. R., Danel, T., Branigan, P. J., Chałupczak, M., Bracha, A., Krawiec, T., Warchoł, M., et al. (2023) · Journal of Crohn s and Colitis · doi:10.1093/ecco-jcc/jjad171 · Cited by 55
Challenges in IBD Research 2024: Precision Medicine
Syed, S., Boland, B. S., Bourke, L., Chen, L. A., Churchill, L., Dobes, A., Greene, A., Heller, C. A., Jayson, C., Kostiuk, B., et al. (2024) · Inflammatory Bowel Diseases · doi:10.1093/ibd/izae084 · Cited by 51
Constrained multiple instance learning for ulcerative colitis prediction using histological images
del Amor, R., Meseguer, P., Parigi, T. L., Villanacci, V., Colomer, A., Launet, L., Bazarova, A., Tontini, G. E., Bisschops, R., de Hertogh, G., et al. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.107012 · Cited by 35
Silverman, A. L., Shung, D. L., Stidham, R. W., Kochhar, G. S., & Iacucci, M. (2024) · Clinical Gastroenterology and Hepatology · doi:10.1016/j.cgh.2024.05.048 · Cited by 33
Inflammatory Bowel Diseases: Does One Histological Score Fit All?
Villanacci, V., SORDO, R. D., Parigi, T. L., Leoncini, G., & Bassotti, G. (2023) · Diagnostics · doi:10.3390/diagnostics13122112 · Cited by 30
Puga‐Tejada, M., Majumder, S., Maeda, Y., Zammarchi, I., Ditonno, I., Santacroce, G., Capobianco, I., Robles‐Medranda, C., Ghosh, S., & Iacucci, M. (2025) · Journal of Crohn s and Colitis · doi:10.1093/ecco-jcc/jjae198 · Cited by 24
Xiao, B., Liang, Y., Liu, G., Wang, L., Zhang, Z., Qiu, L., Xu, H., Carr, S. M., Shi, X., Reis, R. L., et al. (2024) · Acta Pharmaceutica Sinica B · doi:10.1016/j.apsb.2024.02.008 · Cited by 20
“…of UC remains unknown, the severe rectal bleeding, excessive reactive oxygen/nitrogen species (ROS/ RNS), over-expression of pro-inflammatory cytokines ( e.g. , TNF-a , IL-6, and IL-12), and activation of immune cells are strongly associated with the occurrence and progression of UC 4-6 .”
Liu, X., Reigle, J. K., Prasath, V. B. S., & Dhaliwal, J. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108093 · Cited by 21
Nyholm, I., Sjöblom, N., Pihlajoki, M., Hukkinen, M., Lohi, J., Heikkilä, P., Mutka, A., Jahnukainen, T., Davenport, M., Heikinheimo, M., et al. (2023) · Hepatology Communications · doi:10.1097/hc9.0000000000000333 · Cited by 18
Santacroce, G., Zammarchi, I., Nardone, O. M., Capobianco, I., Puga‐Tejada, M., Majumder, S., Ghosh, S., & Iacucci, M. (2025) · Therapeutic Advances in Gastroenterology · doi:10.1177/17562848251325525 · Cited by 23
Machine and deep learning in inflammatory bowel disease
Zulqarnain, F., Rhoads, S. F., & Syed, S. (2023) · Current Opinion in Gastroenterology · doi:10.1097/mog.0000000000000945 · Cited by 21
“Furthermore, researchers developed a deep-learning model to identify eosinophils in tissue from ulcerative colitis patients and quantify eosinophil density [52].”
BackgroundUrquhart, S. A., Christof, M., & Coelho–Prabhu, N. (2025) · Therapeutic Advances in Gastroenterology · doi:10.1177/17562848251348574 · Cited by 15
Li, X., Yan, L., Wang, X., Ouyang, C., Wang, C., Chao, J., Zhang, J., & Lian, G. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.1043412 · Cited by 15
Maeda, Y., Ditonno, I., Puga‐Tejada, M., Zammarchi, I., Santacroce, G., Ghosh, S., & Iacucci, M. (2024) · eGastroenterology · doi:10.1136/egastro-2024-100090 · Cited by 15
Artificial Intelligence in Advancing Inflammatory Bowel Disease Management: Setting New Standards
Labarile, N., Vitello, A., Sinagra, E., Nardone, O. M., Calabrese, G., Bonomo, F., Maida, M. F., & Iacucci, M. (2025) · Cancers · doi:10.3390/cancers17142337 · Cited by 17
Artificial Intelligence in Inflammatory Bowel Disease Endoscopy
Testoni, S. G. G., Petroni, G. A., Annunziata, M. L., Dell’Anna, G., Puricelli, M., Delogu, C., & Annese, V. (2025) · Diagnostics · doi:10.3390/diagnostics15070905 · Cited by 17
Artificial intelligence and machine learning technologies in ulcerative colitis
Kulkarni, C. V., Liu, D., Fardeen, T., Dickson, E. R., Jang, H., Sinha, S. R., & Gubatan, J. M. B. (2024) · Therapeutic Advances in Gastroenterology · doi:10.1177/17562848241272001 · Cited by 19
Stidham, R. W., Ghanem, L. R., Fletcher, J. G., & Bruining, D. H. (2025) · Gastroenterology · doi:10.1053/j.gastro.2025.02.039 · Cited by 15
Yilmaz, F., Brickman, A., Najdawi, F., Yakirevich, E., Egger, R., & Resnick, M. B. (2024) · Laboratory Investigation · doi:10.1016/j.labinv.2024.102043 · Cited by 11
Artificial intelligence: A new tool in the pathologist's armamentarium for the diagnosis of IBD
Cannarozzi, A. L., Massimino, L., Latiano, A., Parigi, T. L., Giuliani, F., Bossa, F., Brina, A. L. D., Ungaro, F., Biscaglia, G., Danese, S., et al. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.09.003 · Cited by 12
Evaluating the potential of artificial intelligence in ulcerative colitis
Sinonquel, P., Schilirò, A., Verstockt, B., Vermeire, S., & Bisschops, R. (2023) · Expert Review of Gastroenterology & Hepatology · doi:10.1080/17474124.2023.2166928 · Cited by 16
“Vande Casteele et al. focused on training a deep learning algorithm that detects eosinophils in biopsies from the sigmoid colon in patients with UC and correlating the eosinophilic density with histological disease activity and clinical features [28].”
BackgroundHistological healing in IBD: Ready for prime time?
Villanacci, V., SORDO, R. D., Mino, S., Locci, G., & Bassotti, G. (2025) · Digestive and Liver Disease · doi:10.1016/j.dld.2025.01.039 · Cited by 12
Caputo, A., Parente, P., Cadei, M., Fassan, M., Rispo, A., Leoncini, G., Bassotti, G., SORDO, R. D., Metelli, C., Daperno, M., et al. (2022) · Techniques in Coloproctology · doi:10.1007/s10151-022-02628-7 · Cited by 10
“Eosinophils, intermingled with plasma cells, are present at variable frequency in active and quiescent IBD [15, 16].”
Carreras, J., Roncador, G., & Hamoudi, R. (2024) · Cancers · doi:10.3390/cancers16244230 · Cited by 19
Technological advances in inflammatory bowel disease endoscopy and histology
Alfarone, L., Parigi, T. L., Gabbiadini, R., Buono, A. D., Spinelli, A., Hassan, C., Iacucci, M., Repici, A., & Armuzzi, A. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.1058875 · Cited by 10
“(46) who trained a deep learning algorithm to quantify eosinophils in colonic biopsies.”
BackgroundGregorio, V., Maeda, Y., Kudo, S., Kawabata, Y., Kuroki, T., Santacroce, G., Puga‐Tejada, M., Takenaka, K., Takabayashi, K., Ohara, J., et al. (2025) · Digestive Endoscopy · doi:10.1111/den.15081 · Cited by 10
Das, A., Shukla, T., Tomita, N., Richards, R., Vidis, L. J., Ren, B., & Hassanpour, S. (2025) · American Journal Of Pathology · doi:10.1016/j.ajpath.2024.12.010 · Cited by 12
Artificial intelligence in inflammatory bowel disease
Ran, J., Zhou, M., & Wen, H. (2025) · Saudi Journal of Gastroenterology · doi:10.4103/sjg.sjg_46_25 · Cited by 7
Artificial intelligence in inflammatory bowel disease: Current applications and future directions
Minea, H. O., Sîngeap, A.-M., Minea, M., Chiriac, S. A., Stanciu, C., & Trifan, A. V. (2025) · World Journal of Gastroenterology · doi:10.3748/wjg.v31.i39.111353 · Cited by 8
AI and endoscopy/histology in UC: the rise of machine
Nardone, O. M., Maeda, Y., & Iacucci, M. (2024) · Therapeutic Advances in Gastroenterology · doi:10.1177/17562848241275294 · Cited by 6
Sinonquel, P., Lenfant, M., Eelbode, T., Watanabe, H., Callaerts, B., Bossuyt, P. J., Verstockt, B., Sabino, J. P. G., Hertogh, G. D., Maes, F., et al. (2024) · Journal of Crohn s and Colitis · doi:10.1093/ecco-jcc/jjae180 · Cited by 6
Liu, Y., Deng, R., Xiong, J., Tyree, R. N., Correa, H., Hiremath, G. S., Wang, Y., & Huo, Y. (2024) · SPIE Medical Imaging: Digital and Computational Pathology · doi:10.1117/12.3005995 · Cited by 4
Serum Periostin is Able to Stratify Type 2-Dominant Ulcerative Colitis
Takedomi, H., Nunomura, S., Nanri, Y., Honda, Y., Yokomizo, K., Akutagawa, T., Tsuruoka, N., Sakata, Y., Conway, S. J., Kawaguchi, A., et al. (2025) · Inflammatory Bowel Diseases · doi:10.1093/ibd/izaf009 · Cited by 7
“17,23 Therefore, we examined whether the efficacy of oral prednisolone was different between type 2-dominant and non-type 2-dominant UC patients, as defined by serum periostin.”
Predicting Crohn’s disease severity in the colon using mixed cell nucleus density from pseudo labels
Remedios, L. W., Bao, S., Kerley, C. I., Cai, L. Y., Rheault, F., Deng, R., Cui, C., Chiron, S., Lau, K. S., Roland, J. T., et al. (2023) · SPIE Medical Imaging: Digital and Computational Pathology · doi:10.1117/12.2653918 · Cited by 4
“In ulcerative colitis, deep learning has been used to assess eosinophil density which was found to correlate with certain disease features but not with histologic activity 12 which refers to mucosal neutrophils existing in specific locations within the tissue 13 .”
MethodElhalaby, R. E., Sivasubramaniam, P., Treeck, B. J. V., Smith, L., Stokes, N. L., Choi, W., Ko, H. M., Moreira, R. K., Hartley, C., & Hagen, C. E. (2025) · Histopathology · doi:10.1111/his.15521 · Cited by 3
“33,34 To our knowledge, no prior studies have used an AI model to help distinguish GVHD from other differential considerations.”
Self-citationArtificial intelligence in gastroenterology and hepatology
Ahn, J. C., & Shah, V. H. (2023) · Elsevier eBooks · doi:10.1016/b978-0-443-15688-5.00016-4 · Cited by 4
Dignass, A. U., Narula, N., Pratap, K., Danese, S., Dotan, I., Iacucci, M., Jairath, V., Loftus, E. V., Magro, F., Mantzaris, G. J., et al. (2026) · Journal of Crohn s and Colitis · doi:10.1093/ecco-jcc/jjag007 · Cited by 3
Gomes, L. E. M., Genaro, L. M., de Castro, M. M., Ricci, R. L., Pascoal, L. B., Silva, F. B. C., Bonfitto, P. H. L., Camargo, M. G., Corona, L. P., Ayrizono, M. D. L. S., et al. (2024) · Therapeutic Advances in Gastroenterology · doi:10.1177/17562848241251949 · Cited by 3
“67,71 Furthermore, a deep learning diagnostic system trained on a large number of colonoscopy images to distinguish UC and CD was developed and validated in a recent study.”
Li, F., Wu, X., Yao, M.-F., Zhang, J., & Mo, Y.-J. (2024) · Medicine · doi:10.1097/md.0000000000039552 · Cited by 2
Priorities for advancing artificial intelligence in inflammatory bowel disease: a technology update
Silverman, A. L., Stidham, R. W., Parasa, S., Sharma, P., & Mahadevan, U. (2026) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2025.12.248 · Cited by 1
Artificial intelligence in the diagnostics and treatment of inflammatory bowel diseases (review)
Fil, T. S., & Бакулин, И. Г. (2024) · Koloproktologia · doi:10.33878/2073-7556-2024-23-3-136-149 · Cited by 2
Colitis eosinofílica como diagnóstico diferencial de desnutrición en pacientes pediátricos
Vélez, A. G. J., Bustos, F. A. M., Alvarez, D. G. A., & Torres, M. T. E. (2023) · RECIMUNDO · doi:10.26820/recimundo/7.(1).enero.2023.617-628 · Cited by 1
Windell, D., Magness, A. J., Li, R., Davis, T., Thomaides-Brears, H. B., Larkin, S. J., Beyer, C., Aljabar, P., Kainth, R., Wakefield, P., et al. (2026) · medRxiv · doi:10.64898/2026.01.27.26344949 · Cited by 1
Augustin, J., McLellan, P., & Caldéraro, J. (2023) · Annales de Pathologie · doi:10.1016/j.annpat.2023.02.009
Artificial intelligence in the management of inflammatory bowel disease: What’s next?
Bilotta, A. J., Trebilcock, J., Hebda, N., Sasan, C., Cooper, K. M., & Rupawala, A. (2026) · World Journal of Gastrointestinal Pharmacology and Therapeutics · doi:10.4292/wjgpt.v17.i1.112640
Reigle, J. K., Liu, X., Lopez‐Nunez, O. F., Drysdale, E., Abuquteish, D., Walters, T. D., Mack, D., Boyle, B. M., Kugathasan, S., Denson, N. K., et al. (2026) · Clinical and Translational Gastroenterology · doi:10.14309/ctg.0000000000001031
“Conversely, other studies have reported no signi fi cant association between baseline tissue eosinophil counts and long-term disease outcomes, including disease severity, need for advanced therapies, or colectomy, nor with histologic activity indices (4,7,8).”
Hamamoto, Y., Nakazawa, Y., Kinoshita, N., Kakimoto, K., Miyazaki, T., Nishikawa, H., & Hirose, Y. (2026) · Human Pathology Reports · doi:10.1016/j.hpr.2026.300838
Lee, J. M., Kweon, H., Jang, D., Park, K., Kim, D. H., & Lee, S. (2026) · Research Square · doi:10.21203/rs.3.rs-9764769/v1
Metadata
- Authors
- Vande Casteele, N., Leighton, J. A., Pasha, S. F., Cusimano, F., Mookhoek, A., Hagen, C. E., Rosty, C., Pai, R. K., & Pai, R. K.
- Affiliations
- Department of Medicine, University of California San Diego , La Jolla, California , USA
- Mayo Clinic in Arizona (US)
- Amsterdam UMC Location Vrije Universiteit Amsterdam (NL)
- Mayo Clinic (US)
- The University of Queensland (AU)
- Corresponding author
- Pai, Rish K
- ORCID
- Venue
- Inflammatory Bowel Diseases
- Publisher
- Oxford University Press (OUP)
- Published
- 2021-06-09
- Volume
- 28
- Issue
- 4
- Pages
- 539-546
- ISSN
- 1078-0998 (ISSN-L)
- 1536-4844
- OpenAlex
- W3172402727
- Cited by
- 52
- References
- 41
- Citations by year
- 2026: 7 · 2025: 13 · 2024: 17 · 2023: 11 · 2022: 4
- FWCI
- 4.52
- Type
- journal article
- Language
- en
- Open access
- green
- pure.amsterdamumc.nl
- Locations
- Inflammatory Bowel Diseases (publishedVersion)
- PubMed (publishedVersion)
- Pure Amsterdam UMC (submittedVersion, other-oa)
- Amsterdam UMC (VU Amsterdam) - Institutional Repository (submittedVersion)
- Data Archiving and Networked Services (DANS) (submittedVersion)
- Topics
- Health Sciences › Medicine › Gastroenterology › Inflammatory Bowel Disease
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Dermatology › Autoimmune and Inflammatory Disorders
- Keywords
- ulcerative colitis, eosinophils
- MeSH terms
- Deep Learning, Biopsy, Colitis, Ulcerative, Cross-Sectional Studies, Eosinophils, Humans
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.