SNOMED CT is one of a suite of designated standards for use in U.S. Federal Government systems for the electronic exchange of clinical health information and is also a required standard in interoperability specifications of the U.S. Healthcare Information Technology Standards Panel.

The VSAC is a repository and authoring tool for public value sets created by external programs. Value sets are lists of codes and corresponding terms, from NLM-hosted standard clinical vocabularies (such as SNOMED CT®, RxNorm, LOINC® and others), that define clinical concepts to support effective and interoperable health information exchange. The VSAC does not create value set content. The VSAC also provides downloadable access to all official versions of value sets specified by the Centers for Medicare & Medicaid Services (CMS) electronic Clinical Quality Measures (eCQMs). For information on CMS eCQMs, visit the eCQI Resource Center. The VSAC is provided by the National Library of Medicine (NLM), in collaboration with the Office of the National Coordinator for Health Information Technology (ONC) and CMS.

This dataset contains the SNOMED-CT medical concept embeddings trained using the following text and graph embedding methods.

Averaged Word Embedding (300)

ELMo (1024)

Universal Sentence Encoder (512)

BERT (768)

Deepwalk (128)

Node2Vec (128)

HARP (128)

LINE (128)

The tar file contains eight JSON files corresponding to the aforementioned embedding techniques. The number (in parenthesis) besides each embedding method represents the dimensionality of the embedding. Each JSON file contains a python dictionary of the form

SNOMED concept ID (String): Embedding (List).

If you find this resource useful in your research, please consider citing our paper:

"Pattisapu, N., Patil, S., Palshikar, G. and Varma, V., Medical Concept Normalization by Encoding Target Knowledge, Proceedings of Machine Learning Research 116:246–259, 2020 Machine Learning for Health (ML4H) at NeurIPS 2019"

Warning: The dataset size is large (~12 GB). Please ensure that you have sufficient network bandwidth and disk space before requesting a download.

This statistical release makes available the most recent monthly data on NHS-funded maternity services in England, using data submitted to the Maternity Services Data Set (MSDS). This is the latest report from the newest version of the data set, MSDS.v.2, which has been in place since April 2019. The new data set was a significant change which added support for key policy initiatives such as continuity of carer, as well as increased flexibility through the introduction of new clinical coding. This was a major change, so data quality and coverage initially reduced from the levels seen in earlier publications. MSDS.v.2 data completeness improved over time, and we are looking at ways of supporting further improvements. This publication also includes the National Maternity Dashboard, which can be accessed via the link below. Data derived from SNOMED codes is used in some measures such as those for birthweight, and others will follow in later publications. SNOMED data is also included in some of the published Clinical Quality Improvement Metrics (CQIMs), where rules have been applied to ensure measure rates are calculated only where data quality is high enough. System suppliers are at different stages of development and delivery to trusts. In some cases, this has limited the aspects of data that can be submitted in the MSDS. This month, for the first time, this publication contains a new Clinical Quality Improvement Metric (CQIM) called CQIMReadmissions. This new metric reports the number of babies born in hospital then discharged home, who were then readmitted to hospital while still under 30 days old. This is supported by five new data quality metrics to ensure we only publish CQIMReadmissions figures where the underlying data is of sufficient completeness and quality. The new data quality metrics are CQIMDQ46 to CQIMDQ50. Further information about this new readmissions metric can found in this publication’s Data Quality Statement. This new data can be found in the Measures file available for download and in the CQIM and CQIM+ pages in the National Maternity Dashboard, and further information on the new metrics can be found in the accompanying Metadata file. To help Trusts understand to what extent they met the Clinical Negligence Scheme for Trusts (CNST) Maternity Incentive Scheme (MIS) Data Quality Criteria for Safety Action 2, we have been producing a CNST Scorecard Dashboard showing trust performance against this criteria. This dashboard has been updated following the release of CNST Y6 criteria, and can be accessed via the link below. The percentages presented in this report are based on rounded figures and therefore may not total to 100%.

This dataset contains the human readable form of the SNOMED CT to ICD-10-CM cross map. The Map can be used in real-time by the healthcare providers and by coding professionals for retrospective coding purposes.

Maternity Services Monthly Statistics August 2021, experimental statistics This is a report on NHS-funded maternity services in England for August 2021, using data submitted to the Maternity Services Data Set (MSDS). This is the latest report from the new version of the data set, MSDSv2. The new data set is a significant change which adds support for key policy initiatives such as personalised care plans and continuity of carer, as well as increased flexibility through the introduction of new clinical coding. This is a major change, so data quality and coverage has reduced from the levels seen in previous publications. The data derived from SNOMED codes is still being developed. We have included data on smoking at booking and birth weight and others such as BMI and alcohol consumption will follow in later publications. SNOMED data is also included in some of the published Clinical Quality Improvement Metrics (CQIMs) where rules have been applied to ensure rates are calculated only where data quality is high enough. System suppliers are at different stages of developing their new solution and delivering that to trusts. In some cases this has limited the aspects of data that could be submitted to NHS Digital. This month, data quality measures to validate the data used for the measures counting the number of women receiving Continuity of Carer support and counting the number of women with Personalised Care and Support Plans have been included for the first time and can be found in the measures file available for download. Information on the construction of these new data quality tests and how they have been applied to the existing Continuity of Carer and Personalised Care Plan measures can be found in the metadata file available for download. Similar changes were already implemented for the measure counting the number of women placed on a Continuity of Carer pathway by 29 weeks gestation in the June 2021 publication. These statistics are classified as experimental and should be used with caution. Experimental statistics are new official statistics undergoing evaluation. More information about experimental statistics can be found on the UK Statistics Authority website.