Data enrichment: Ontologies, taxonomies, controlled vocabularies

Data enrichment

Ontologies, taxonomies, and controlled vocabularies

Conduct granular searches with unparalleled flexibility and subject-specific semantic expansion.

How does ResoluteAI enrich content?

ResoluteAI's data enrichment process combines our own proprietary, scientific taxonomy with a growing number of industry-specific ontologies, taxonomies, and controlled vocabularies (OTCVs) to provide a remarkable research experience.

Incorporating these scientific OCTVs into ResoluteAI's enterprise search and research platforms, facilitates:
  • + Highly specific and fine-tuned searching 
  • + Identification of connections between disparate datasets
  • + Browsing through data when you're not sure what you're looking for
  • + Semantic expansion and conceptual search
  • + Serendipitous discovery

“It’s really useful how searching for topics, like nanobots, ResoluteAI will search for alternative naming conventions and also identify connected topics so we can understand how newer technologies are connected to one another.”
- Science and Innovation Director, Fortune 500 pharmaceutical company

How can enriched data help you? Request a demo and find out!

ResoluteAI's ontologies, taxonomies, and controlled vocabularies

ResoluteAI pink symbol 11012021

ResoluteAI

ResoluteAI's proprietary tagging system is based on DBpedia and has been developed by conducting machine learning on tens of millions of scientific documents.

NIH MeSH lgo

MeSH

The National Library of Medicine (NLM) controlled vocabulary thesaurus used for indexing articles for PubMed ​​representing concepts found in the biomedical literature.

Learn more about MeSH
What is MeSH? 
The U.S. National Library of Medicine (NLM) controlled vocabulary thesaurus used for indexing articles for PubMed ​​representing concepts found in the biomedical literature.

Who developed MeSH?
U.S. National Library of Medicine (NLM)

Who uses MeSH?
Researchers using PubMed.

Why use MeSH?
MeSH uses a controlled system for searching literature headings ensuring correct results:
  • Class 1 Descriptors - Main Headings
  • Class 2 Descriptors - Publication Types
  • Class 3 Descriptors - Tags
  • Class 4 Descriptors - Geographics
MedDRA logo_crop

MedDRA

Medical Dictionary for Regulatory Activities Terminology (MedDRA), the recommended and required system by the FDA and European authorities for regulatory submissions.

Learn more about MedDRA

What is MedDRA? 
Medical Dictionary for Regulatory Activities Terminology (MedDRA), the recommended and required system by the FDA and European authorities for regulatory submissions.

Who developed MedDRA?
International Conference on Harmonisation (ICH) of Technical Requirements for Registration of Pharmaceuticals for Human Use.

Who uses MedDRA?
Regulatory authorities, pharmaceutical companies, clinical research organizations, and health care professionals.

Why use MedDRA?
MedDRA allows better global protection of patient health. Each MedDRA term has an associated 8-digit numerical code which remains the same irrespective of the language. Multiple languages allow a wide number of users to operate in their native language which promotes accuracy and precision in assigning codes. This interoperability is very powerful and allows easy sharing of data internationally.
Specifically, some of the applications for MedDRA are:
  • Aggregate reported terms in medically meaningful groupings for review, analysis and/or summary of safety data
  • Facilitate identification of common data sets for evaluation of clinical and safety information
  • Facilitate consistent retrieval of specific cases or medical conditions from a database
  • Improve consistency in comparing and understanding safety signals and aggregated clinical data
  • Facilitate electronic data interchange of clinical safety information.
NIH MeSH lgo

RxNorm

Standardized nomenclature for human-use clinical drugs providing a single standardized system for naming drugs with unique identifiers for both brand-name and generic drugs.

Learn more about RxNorm

What is RxNorm? 
Standardized nomenclature for human-use clinical drugs providing a single standardized system for naming drugs with unique identifiers for both brand-name and generic drugs.

RxNorm provides a set of codes for clinical drugs, which are the combination of active ingredients, dose form, and strength of a drug.

Example: RxNorm code for ciprofloxacin 500 mg 24-hour extended-release tablet (the generic name for Cipro XR 500 mg) is RX10359383, regardless of brand or packaging.


Who developed RxNorm?
U.S. National Library of Medicine (NLM)

Who uses RxNorm?
Principal investigators, statisticians, data managers, and other clinical trial personnel.

Why use RxNorm?
RxNorm is particularly important because it allows information about medications to be exchanged across electronic health records (EHRs).

PubChem_logo

PubChem

PubChem is a database of chemical molecules and their activities against biological assays. It is maintained by the National Center for Biotechnology Information, a component of the NLM.

Learn more about PubChem

What is PubChem? 
PubChem is an open chemistry database at the National Institutes of Health (NIH). Since the launch in 2004, PubChem has become a key chemical information resource for scientists, students, and the general public.

Where does the data in PubChem come from?
PubChem records are contributed by hundreds of data sources. Examples include: government agencies, chemical vendors, journal publishers, and more.

Who uses PubChem?
Chemists and biologists in both academia and industry, intellectual property attorneys, business development and innovation executives, and others.

Why use PubChem?
The data in PubChem are organized into three interlinked databases: Substance (as of writing more than 286 million substance descriptions), Compound (over 111 million unique chemical structures) and BioAssay (1.2 million biological assays covering more than 10,000 target protein sequences). PubChem is comprehensive in both depth and breadth.

go-logo crop

GO

Gene Ontology (GO) describes gene products in terms of their associated biological processes, cellular components, and molecular functions in a species-independent manner.

Learn more about GO

What is GO? 
Gene Ontology (GO) describes gene products in terms of their associated biological processes, cellular components, and molecular functions in a species-independent manner.

Who developed GO?
GO Consortium.

Who uses GO?
Bioinformatic researchers.

Why use GO?
GO is an essential resource for computational gene data analysis providing precise terms.

SNOMED

SNOMED

Systematized Nomenclature of Medicine-Clinical Terms used for searching on clinical information, electronic health records, research, and clinical trials.

Learn more about SNOMED

What is SNOMED? 
Systematized Nomenclature of Medicine-Clinical Terms used for searching on clinical information, electronic health records, research, and clinical trials.

Who developed SNOMED?
International Health Terminology Standards Development Organization (IHTSDO) owns all the Intellectual Property of SNOMED CT and all antecedent SNOMED versions.

Who uses SNOMED?
Standards-setting organizations in a variety of healthcare applications along with developers of electronic health data exchange applications.

Why use SNOMED?
SNOMED includes more than 300,000 unique concepts. There are over 1,000,000 descriptions, including synonyms that can be used to refer to a concept. In addition, there are approximately 903,000 links or semantic relationships between the SNOMED CT concepts.

CDC_ICD-10

ICD-10

The International Classification of Diseases, Tenth Revision used by healthcare policy makers and researchers to analyze diagnoses and medical procedures.

Learn more about ICD-10

What is ICD-10? 
The International Classification of Diseases, Tenth Revision used by healthcare policy makers and researchers to analyze diagnoses and medical procedures

Who created ICD-10?
Healthcare Cost and Utilization Project (HCUP) and reviewed by World Health Organization (WHO) every 10 years

Who uses ICD-10?
Healthcare policy makers and general researchers and clinical research scientists. It is internationally adopted as a diagnostic classification coding system.

Why use ICD-10?
CDC mandates U.S. mortality data be coded using ICD-10 since 2015.

Analyze diagnoses and medical procedures with the 14,000 diagnosis codes and 3,900 procedure codes - all collapsed into a smaller number of clinically meaningful categories, available in ICD-10. Identify populations for disease, or procedure-specific studies, or develop statistical reports providing information analyze costs, usage, and outcomes associated with patient diagnoses and procedures

Medical terms reported by physicians, the medical examiners, and coroners on death certificates can be grouped together for statistical purposes

Used to communicate:

  • Evidence-based information easily stored and readily available
  • Medical information made public and can be compared between regions, countries, and hospitals
  • Data tracked at different periods of time in the same locations to identify trends
  • Assessing and monitoring the safety, efficacy, and quality of care
  • Identifying public health risks
  • Preventing and discovering fraud
  • Researching and performing clinical trials and epidemiological studies
  • Streamlining performance in departments of finance, administration, and clinical areas
  • Tracking disease prevalence and occurrences of death
OMIM_50_logo_badge

OMIM

Online Mendelian Inheritance in Man (OMIM) is a catalog of Mendelian traits and disorders, with a focus on the relationship between phenotype and genotype.

Learn more about OMIM

What is OMIM? 
Online Mendelian Inheritance in Man (OMIM) is a catalog of Mendelian traits and disorders, with a focus on the relationship between phenotype and genotype.

Who developed OMIM?
McKusick-Nathans Institute of Genetic Medicine, Johns Hopkins School of Medicine. It is made available online by the National Center for Biotechnology Information (NCBI) at the U.S. National Library of Medicine (NLM).

Who uses OMIM?
Genetic researchers.

Why use OMIM?
OMIM focuses on the relationship between phenotype and genotype and is the authoritative compendium of all Mendelian traits and disorders. It is critical in genetic disorder research.

semantics crop
What are ontologies, taxonomies, and controlled vocabularies?

Ontologies - A set of terms mapping to one another via relationships. Maps of words/terms/phrases (can be cyclical).

Taxonomies - A set of terms relating to one another through strict hierarchies – often a subset of ontologies, but not always.

Controlled Vocabularies - A set of terms with no mappings, hierarchies, or set of rules but are agreed upon by the people or persons that manage them. 

How did ResoluteAI help Aditx Therapeutics, Inc. tag and classify decades of research in record time? View the Aditxt case study

See how ResoluteAI can enrich your data.
Request a product tour