The course is customized for PhD and MA students in the biomedical informatics program and also open to other interested students at Columbia. It provides an in-depth overview of symbolic methods.

Readings (Subject to Changes for including latest advances in the field)

Course Overview — Semantic Knowledge Representation, Terminology, Ontology

• https://protege.stanford.edu/conference/2004/slides/Ontology101_tutorial.pdf
• https://protege.stanford.edu/publications/ontology_development/ontology101.pdf
• Medical Concept Representation, Chapter 6, Medical Information Management. https://link.springer.com/chapter/10.1007/0-387-25739-x_6

Semantic Interoperability, Concept Mapping Importance and Challenges

• Dolin, R. H., and L. Alschuler. 2011. 'Approaching semantic interoperability in Health Level Seven', J Am Med Inform Assoc, 18: 99-103.
• El Ghosh M, Kalokyri V, Sambres M, Vaterkowski M, Duclos C, Tannier X, Tsakou G, Tsiknakis M, Daniel C, Dhombres F. From Syntactic to Semantic Interoperability Using a Hyperontology in the Oncology Domain. Stud Health Technol Inform. 2024 Aug 22;316:1385-1389. doi: 10.3233/SHTI240670. PMID: 39176639.

Desiderata for Clinical Terminology

• Cimino, J. J. 1998. 'Desiderata for controlled medical vocabularies in the twenty-first century', Methods Inf Med, 37: 394-403.
• Cimino JJ. In defense of the Desiderata. J Biomed Inform. 2006 Jun;39(3):299-306. doi: 10.1016/j.jbi.2005.11.008. Epub 2005 Dec 9. PMID: 16386470; PMCID: PMC7185649.
• Evans DA, Cimino JJ, Hersh WR, Huff SM, Bell DS. Toward a medical-concept representation language. The Canon Group. J Am Med Inform Assoc. 1994 May-Jun;1(3):207-17. doi: 10.1136/jamia.1994.95236153. PMID: 7719804; PMCID: PMC116200.
• Cimino JJ. Controlled medical vocabulary construction: methods from the Canon Group. J Am Med Inform Assoc. 1994 May-Jun;1(3):296-7. doi: 10.1136/jamia.1994.95236160. PMID: 7719811; PMCID: PMC116207.
• Zhang J. Representations of health concepts: a cognitive perspective. J Biomed Inform. 2002 Feb;35(1):17-24. doi: 10.1016/s1532-0464(02)00003-5. PMID: 12415723.

Terminology: Reference and Interface Terminologies

• Campbell JR. Semantic features of an enterprise interface terminology for SNOMED RT. Stud Health Technol Inform. 2001;84(Pt 1):82-5. PMID: 11604710.
• Hashemian Nik D, Kasáč Z, Goda Z, Semlitsch A, Schulz S. Building an Experimental German User Interface Terminology Linked to SNOMED CT. Stud Health Technol Inform. 2019 Aug 21;264:153-157. doi: 10.3233/SHTI190202. PMID: 31437904.
• Zini EM, Lanzola G, Quaglini S, Cornet R. Standardization of immunotherapy adverse events in patient information leaflets and development of an interface terminology for outpatients' monitoring. J Biomed Inform. 2018 Jan;77:133-144. doi: 10.1016/j.jbi.2017.12.009. Epub 2017 Dec 18. PMID: 29269275.

International Classification of Diseases (ICD)

• http://www.who.int/classifications/icd/factsheet/en/
• http://www.who.int/classifications/icd/en/HistoryOfICD.pdf (Israel 1978; Gersenovic 1995)
• http://www.openclinical.org/medTermICD.html
• http://icd9cm.chrisendres.com

Systematized Nomenclature of Medicine - Clinical Terms (SNOMED-CT)

• Côté RA, Robboy S. Progress in medical information management. Systematized nomenclature of medicine (SNOMED). JAMA. 1980 Feb 22-29;243(8):756-62. doi: 10.1001/jama.1980.03300340032015. PMID: 6986000.
• Chang E, Mostafa J. The use of SNOMED CT, 2013-2020: a literature review. J Am Med Inform Assoc. 2021 Aug 13;28(9):2017-2026. doi: 10.1093/jamia/ocab084. PMID: 34151978; PMCID: PMC8363812.
• http://browser.ihtsdotools.org

RxNorm

• RxNorm Overview https://www.nlm.nih.gov/research/umls/rxnorm/overview.html

UMLS Part 1

• Humphreys, B. L., et al. 1998. 'The Unified Medical Language System: an informatics research collaboration', J Am Med Inform Assoc, 5: 1-11.
• McCray, A. T., A. M. Razi, et al. 1996. 'The UMLS Knowledge Source Server: a versatile Internet-based research tool', Proc AMIA Annu Fall Symp: 164-8.

Human Phenotype Ontology and Summary of Clinical Terminologies

• Köhler S, Vasilevsky NA, Engelstad M, et al. The Human Phenotype Ontology in 2017. Nucleic Acids Res 2017; 45: D865–D876. doi:10.1093/nar/gkw1039.

Semantic Representation in Cognitive Science

• Zhang J. Representations of health concepts: a cognitive perspective. J Biomed Inform. 2002 Feb;35(1):17-24. doi: 10.1016/s1532-0464(02)00003-5. PMID: 12415723.

UMLS Part 2

• Ying H, Zhao Z, Zhao Y, Zeng S, Yu S. CoRTEx: contrastive learning for representing terms via explanations with applications on constructing biomedical knowledge graphs. J Am Med Inform Assoc. 2024 Sep 1;31(9):1912-1920. doi: 10.1093/jamia/ocae115. PMID: 38777805; PMCID: PMC11339518.
• Afshar M, Gao Y, Gupta D, Croxford E, Demner-Fushman D. On the role of the UMLS in supporting diagnosis generation proposed by Large Language Models. J Biomed Inform. 2024 Aug 13;157:104707. doi: 10.1016/j.jbi.2024.104707. Epub ahead of print. PMID: 39142598.

Concept Extraction and Annotation Using Symbolic Methods

• Friedman C. A broad-coverage natural language processing system. Proc AMIA Symp 2000: 270–274.

Applications – EHR Phenolyzer for Disease Diagnostic Decision Support

• Son JH, Xie G, Yuan C, Ena L, Li Z, Goldstein A, Huang L, Wang L, Shen F, Liu H, Mehl K, Groopman EE, Marasa M, Kiryluk K, Gharavi AG, Chung WK, Hripcsak G, Friedman C, Weng C, Wang K. Deep Phenotyping on Electronic Health Records Facilitates Genetic Diagnosis by Clinical Exomes. Am J Hum Genet. 2018 Jul 5;103(1):58-73. doi: 10.1016/j.ajhg.2018.05.010. Epub 2018 Jun 28. PMID: 29961570; PMCID: PMC6035281.
• Yang H, Robinson PN, Wang K. Phenolyzer: phenotype-based prioritization of candidate genes for human diseases. Nat Methods. 2015 Sep;12(9):841-3. doi: 10.1038/nmeth.3484. Epub 2015 Jul 20. PMID: 26192085; PMCID: PMC4718403.

Applications – Large Language Models for Concept Normalization

• Wang A, Liu C, Yang J, Weng C. Fine-tuning large language models for rare disease concept normalization. J Am Med Inform Assoc. 2024 Sep 1;31(9):2076-2083. doi: 10.1093/jamia/ocae133. PMID: 38829731; PMCID: PMC11339522.

Applications - Large Language Models for Ontology Development

• Fang Y, Ryan P, Weng C. Knowledge-guided generative artificial intelligence for automated taxonomy learning from drug labels. J Am Med Inform Assoc. 2024 Sep 1;31(9):2065-2075. doi: 10.1093/jamia/ocae105. PMID: 38787964; PMCID: PMC11339527.

Large Language Models for Concept Extraction

• Lu Z, Peng Y, Cohen T, Ghassemi M, Weng C, Tian S. Large language models in biomedicine and health: current research landscape and future directions. J Am Med Inform Assoc. 2024 Sep 1;31(9):1801-1811. doi: 10.1093/jamia/ocae202. PMID: 39169867; PMCID: PMC11339542.
• Yang J, Liu C, Deng W, Wu D, Weng C, Zhou Y, Wang K. Enhancing phenotype recognition in clinical notes using large language models: PhenoBCBERT and PhenoGPT. Patterns (N Y). 2023 Dec 5;5(1):100887. doi: 10.1016/j.patter.2023.100887. PMID: 38264716; PMCID: PMC10801236.
• Groza T, Caufield H, Gration D, Baynam G, Haendel MA, Robinson PN, Mungall CJ, Reese JT. An evaluation of GPT models for phenotype concept recognition. BMC Med Inform Decis Mak. 2024 Jan 31;24(1):30. doi: 10.1186/s12911-024-02439-w. PMID: 38297371; PMCID: PMC10829255.

Fast Healthcare Interoperability Resources (FHIR) Apps in Symbolic AI

• Mandel JC, Kreda DA, Mandl KD, et al. SMART on FHIR: a standards-based, interoperable apps platform for electronic health records. Journal of the American Medical Informatics Association. 2016 Sep 1;23(5):899-908.

OMOP CDM Part 1

• CommonDataModel: Definition and DDLs for the OMOP Common Data Model (CDM). Observational Health Data Sciences and Informatics, 2018. Available at: https://github.com/OHDSI/CommonDataModel
• Stang PE, Ryan PB, Racoosin JA, et al. Advancing the science for active surveillance: rationale and design for the Observational Medical Outcomes Partnership. Ann Intern Med 2010; 153: 600–606. doi:10.7326/0003-4819-153-9-201011020-00010.
• Hripcsak G, Duke JD, Shah NH, et al. Observational Health Data Sciences and Informatics (OHDSI): Opportunities for Observational Researchers. Stud Health Technol Inform 2015; 216: 574–578.

OMOP CDM Part 2

• Ahmadi N, Zoch M, Guengoeze O, Facchinello C, Mondorf A, Stratmann K, Musleh K, Erasmus HP, Tchertov J, Gebler R, Schaaf J, Frischen LS, Nasirian A, Dai J, Henke E, Tremblay D, Srisuwananukorn A, Bornhäuser M, Röllig C, Eckardt JN, Middeke JM, Wolfien M, Sedlmayr M. How to customize common data models for rare diseases: an OMOP-based implementation and lessons learned. Orphanet J Rare Dis. 2024 Aug 14;19(1):298. doi: 10.1186/s13023-024-03312-9. PMID: 39143600; PMCID: PMC11325822.

Applications - Neuro-Symbolic AI for Clinical Evidence Extraction

• Zhang G, Fang Y, Chen F, Ta C, Hripcsak G, Ryan P, Peng Y, Weng C. A neural-symbolic AI agent system for biomedical concept mapping. NPJ Digit Med. 2026 Apr 4. doi: 10.1038/s41746-026-02594-6. Epub ahead of print. PMID: 41935204.
• Zhang G, Xu Z, Jin Q, Chen F, Fang Y, Liu Y, Rousseau JF, Xu Z, Lu Z, Weng C, Peng Y. Leveraging long context in retrieval augmented language models for medical question answering. NPJ Digit Med. 2025 May 2;8(1):239. doi: 10.1038/s41746-025-01651-w. PMID: 40316710; PMCID: PMC12048518.
• Kang T, Turfah A, Kim J, Perotte A, Weng C. A neuro-symbolic method for understanding free-text medical evidence. J Am Med Inform Assoc. 2021 Jul 30;28(8):1703-1711. doi: 10.1093/jamia/ocab077. PMID: 33956981; PMCID: PMC8135980.

Useful Resources

• Bioportal: https://bioportal.bioontology.org
• Bioportal annotator: https://bioportal.bioontology.org/annotator
• UMLS Terminology Services: https://uts.nlm.nih.gov/home.html
• ICD9/ICD10 lookup: https://www.icd10data.com/ICD10CM/Codes
• SNOMED browser: http://browser.ihtsdotools.org
• RxNav (for RxNorm): https://rxnav.nlm.nih.gov/
• UMLS Resources: https://www.nlm.nih.gov/research/umls/
• Publically available OHDSI data: http://www.ohdsi.org/web/atlas/#/home
• HPO: https://hpo.jax.org/app/
• PheKB: https://phekb.org/phenotypes
• Ensembl: https://academic.oup.com/bioinformatics/article/31/1/143/2366240 ; https://www.ncbi.nlm.nih.gov/pubmed/24316576
• BLAST: https://blast.ncbi.nlm.nih.gov/Blast.cgi
• BioMart: http://www.biomart.org/
• BioProject: https://www.ncbi.nlm.nih.gov/bioproject
• Galaxy: https://usegalaxy.org/
• FHIR Documentation: https://www.hl7.org/fhir/documentation.html
• Phenolyzer: http://phenolyzer.wglab.org/

Data Resources

1. Rare Disease Patient Data: A corpus of GA4GH Phenopackets: case-level phenotyping for genomic diagnostics and discovery
   https://github.com/monarch-initiative/phenopacket-store
   https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11160806/
2. MIMIC IV
   https://physionet.org/content/mimiciv/3.0/
   Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.
3. Open Annotation for Rare Disease (OARD)
   https://www.dbmi.columbia.edu/oard-rare-disease-research/
   https://rare.cohd.io
4. Columbia Open Health Data (COHD)
   https://cohd.io/about.html
5. PubMed
6. ClinicalTrials.gov
7. The AACT database