Release Notes

Release Notes

v2.37 - 2026-08-17T22-13

Detailed release notes for v2.37

NLP API version 2 Release 37.

v2.36p3 - 2025-11-13

Compatibility:

Ontology updates:

  • Added new synonyms for SNOMED-CT.

v2.36p2 - 2025-11-13

Compatibility:

Fixes:

  • Fixed a bug where certain section headings could cause a crash.
  • Ignore null matches for relation concept links
  • Bug fix: relation arguments from context sometimes had an empty string for UMLS entity type.

Model updates:

  • Negation detection improvements.

Ontology updates:

  • Added new synonyms for SNOMED-CT and RxNorm.
  • Updates to HGNC, LOINC and NCI ontologies.
  • Fixes issue with spurious concept matches for herself and himself.

v2.36p1 - 2025-09-27

Compatibility:

Model updates:

  • New measurement relation model with improved coverage and accuracy for lab measurements.
  • New temporality relation model with improved coverage and accuracy for lab events on multiple dates.

Ontology updates:

  • Added new synonyms for SNOMED-CT.
  • Updates to HGNC, LOINC and NCI ontologies.

v2.36 - 2025-08-03

Detailed release notes for v2.36

Compatibility:

  • NLP API version 2 Release 36.
  • Python SDK and client v6.10.0.
  • NLP API specification v2.20.0: added single API key authentication for some deployments.
  • JSON result output schema v2.34.0 for emtellipro-json-2: added concept links for relations.
  • visualclient version v2025.07.02-8e1c4f: minor visualization improvements and bug fixes.

v2.35 - 2025-03-12

Detailed release notes for v2.35

Compatibility:

  • NLP API version 2 Release 35.
  • Python SDK and client v6.9.0.
  • Java SDK and client v5.15.0.
  • NLP API specification v2.20.0: added support for new processing feature entity-concept-link-confidence.
  • JSON result output schema v2.33.0 for emtellipro-json-2: added support for new processing feature entity-concept-link-confidence and new output attribute heading_status and new location headings; added confidence scores for relations.
  • visualclient version v2025.01.07-184b7f: added support for new processing feature entity-concept-link-confidence.

v2.34 - 2024-09-22

Detailed release notes for v2.34

Compatibility:

  • NLP API version 2 Release 34.
  • Python SDK and client v6.4.0.
  • Java SDK and client v5.15.0.
  • NLP API specification v2.18.0: added support for new processing features anatomicsite-relations.
  • JSON result output schema v2.29.0 for emtellipro-json-2: added support for new processing features anatomicsite-relations.
  • visualclient version v2024.07.22-8d7966 added support for new processing features anatomicsite-relations.

v2.33p2 - 2024-05-04

Compatibility:

Added:

  • Experimental support for anatomic site relation added.

Ontology updates:

  • Added new synonyms for SNOMED-CT.
  • Improved handling of RadLex synonym matching.
  • Improved MEDCIN section based disambiguation.

v2.33p1 - 2024-03-23

Compatibility:

Changes:

  • Improved handling of errors in deidentification output.

Ontology updates:

  • Added new synonyms for SNOMED-CT, RxNorm and RadLex ontologies.

Model updates:

  • Polarity (negation) improvements.
  • Support for new section headings.
  • Improvements to imagelink relations.

v2.33 - 2024-03-20

Compatibility:

Changes:

  • Input type is no longer required as input when processing a document with the NLP API.
  • Update qualifier relation output format in emtellipro-json-2 to allow any string for qualifier type. Added new qualifier type called unknown.
  • Model inference improvements in production deployments related to GPU memory management.
  • Improved de-identification error correction in cases where son{{last name}} actually refers to sonography.
  • Improved section parsing and ensuring FINDINGS sections in Radiology reports when they are missing.
  • history of x entity spans which where previously mapped to a single entity are now extracted as 2 entities (history of and x) wth a temporality relation between these two mentions.

Ontology updates:

  • Update SNOMED-CT ontologies to 2023-09-01 US release.
  • The SNOMED-CT description and relationship tables have been updated on the downloads page to the 2023-09-01 US release.
  • Added 23372 new synonyms across all ontologies and entity disambiguation and updates to an additional 8567 entries.
  • All relations now prefer SNOMED-CT concept mentions as the main argument.

Model updates:

  • SNOMED-CT entity disambiguation now handles 61 additional ambiguous SNOMED-CT concepts.
  • Qualifier relation.
  • Measurement relation.
  • Sentence boundary detection model improvements to handle very long run-on sentences.
  • Fix some pronoun issues with experiencer relation.
  • Polarity (negation) attribute improvements.
  • Uncertainty attribute improvements.

Processing time and output size:

  • Data: 1000 discharge summaries, average size 10.13KB, total size 13MB
  • 32x CPU: Intel(R) Xeon(R) Silver 4310 CPU @ 2.10 - 3.30 GHz w/18 MB Cache
  • 1x GPU: Nvidia L4 w/24GB of RAM
  • Per-report time: 2.091675s
  • Processing time: 34:51.67s
  • JSON output file size: 151MB
  • NLP API database size using Python database client: 1364MB

v2.32 - 2023-08-22

Compatibility:

Changes:

  • Improved person name and occupation, address and telephone number detection in CCDs.
  • Used address and telephone number entities to improve specific temporality relation precision.
  • Improved accuracy of specific temporality relation with new models fine-tuned on human expert annotations.
  • Improved accuracy of historical temporality relation with new models fine-tuned on human expert annotations.
  • Improved accuracy of experiencer relations with new models fine-tuned on human expert annotations.
  • Improved accuracy of measurement relations with new models fine-tuned on human expert annotations.
  • Improved accuracy of entity disambiguation for highly ambiguous mentions in SNOMED with new models fine-tuned on human expert annotations.
  • Improved polarity (negation) detection fine-tuned on human expert annotations.
  • Improved polarity (negation) scope detection in long linearized table rows in CCDs.
  • Tuned memory and speed using a limit on sentence length which truncates very long sentences for Transformer models.
  • Implemented quantization for inference on CPUs and FP16 for inference on GPUs for Transformer models.
  • Improved section parsing for Radiology reports.
  • Improved section parsing for subcategory generic in document categories Radiology and Clinical.
  • Bug fix for empty spans that used to cause a crash.
  • Added copies/ml, IU/mL and organisms/mL as a measurement unit.

Ontology updates:

  • Impoved entity matching for Medcin, RadLex, RxNorm, SNOMED, LOINC and NCI Thesaurus ontologies.
  • SNOMED CT version 2023-03-01 US Edition.
  • Improved long string matching for SNOMED mentions.
  • Improved ambiguity resolution on highly ambiguous mentions for the SNOMED ontology.
  • Added ~26K synonyms for SNOMED and RadLex ontology. Modified 25K synonyms with new SNOMED concepts.
  • RxNorm version 2022-11-07.
  • RadPlaybook version 2023-02-22.
  • RadLex version 4 2020-11.
  • UMLS ontologies (LOINC, NCI, HGNC) 2023-03-01 aka 2023AA.
  • SNOMED CT to ICD-10 version 2023-03-01.
  • SNOMED CT to ICD-10-CM version 2023-03-01 US Edition.
  • Added molecular document category for HGNC ontology matching.
  • Fixed matching for double quotes in entity linking when there are unmatched quotes such as for r" haplotype.

v2.31p2 - 2023-04-03

Compatibility:

  • NLP API version 2 Release 31 post2.
  • Python SDK and client v5.26.0.
  • Java SDK and client v5.14.0.
  • Python SDK CCD reader plugin v2.5.0: updated to new version to handle datetime information in CCD coded entries.
  • NLP API specification v2.17.0.
  • JSON result output schema v2.26.1 for emtellipro-json-2.
  • visualclient version vc-v2023.03.17-dadc23b8.

Changes:

  • New CCD plugin v2.5.0 that can handle more sections in CCDs that are linked to effective times from coded entries.
  • Improved accuracy of specific temporality relation.
  • Improved SNOMED qualifier detection and qualifier relation.
  • Fixed an issue in sentence detection with roman numerals.
  • Added ~400 synonyms for SNOMED ontology.

v2.31p1 - 2023-03-27

Compatibility:

Changes:

  • Fixed race condition when Azure data disks were not available to the virtual machine on startup.
  • Improved accuracy of guidance attribute.
  • Improved accuracy of negation detection.
  • Improved accuracy of imagelink relation.
  • Improved accuracy of specific temporality relation.
  • Fix bug that affected SQL queries when there were some specific RxNorm entities that should not be matched.

v2.31 - 2023-03-20

Detailed release notes for v2.31

Compatibility:

v2.30p1 - 2022-11-02

Added:

  • Synonyms added for SNOMED and LOINC ontologies.

v2.30 - 2022-10-17

Changes:

  • Improved measurement relation model.
  • Improved sentence boundary model.
  • Improved entity linking for various ontologies.
  • Improved recall for negation finding.
  • Improved recall for reported events relation.
  • Improved handling of generic report kind subcategories in section parsing.
  • Improved section parsing for CCDs. See the CCD plugin documentation for more information.
  • Improved tokenization for cases with missing whitespace between tokens.
  • Pickup SNOMED “medicinal product” annotations as drugs when generating medication relations (beta).
  • Added measurement relations to LOINC ontology (beta).

Ontology updates:

  • SNOMED updated to US version 2022-03-01.
  • RxNorm updated to August 2022 release.
  • UMLS updated to 2022AA.

Compatibility:

v2.30a4 - 2022-10-05

Added:

  • Python CCD plugin v1.12.0 added to the Downloads page.

v2.29p3 - 2022-09-21

emtelliNote documentation updated to v2022.09.21.

Changes:

  • No changes to emtellipro v2.29.

v2.29p3 - 2022-07-19

post3 release of API v2 release 29 with faster audit log downloads.

Changes:

  • Faster audit log downloads for on-premises customers.

Compatibility:

v2.29p2 - 2022-07-14

post2 release of API v2 release 29 with bug fix for no evidence for negation and new Java SDK release.

Changes:

  • Bug fix for no evidence for negation
  • Updated downloads page to include Java SDK v5.10.0.

Compatibility:

v2.29p1 - 2022-07-13

post1 release of API v2 release 29 with some minor improvements and a bug fix for question_status.

Changes:

  • Bug fix for question_status not appearing in HISTORY: sections in Radiology reports.
  • Add some more synonyms for SNOMED CT concepts.
  • Updated downloads page in the documentation to include MS-SQL downloads for description and relationship tables.

Compatibility:

v2.29 - 2022-07-05

Detailed release notes for v2.29

Compatibility:

v2.28 - 2022-03-23

Detailed release notes for v2.28

Compatibility:

  • API version 2 Release 28.
  • Python SDK and client v4.3.0 to v5.22.0.
  • Java SDK and client v3.0.2 to v5.8.0.
  • Python SDK CCD reader plugin v1.7.0.
  • NLP API specification v2.15.0
  • JSON result output schema v2.19.0 for emtellipro-json-2: added support for new processing features TemporalityRelation and QuestionStatus.
  • visualclient version vc-v2022.07.04-ef5da396. v2021-08-05-9e7468“

v2.27 - 2021-10-13

Detailed release notes for v2.27

Compatibility:

v2.26 - 2021-08-04

Changed:

  • Audit service for on-site NLP API redesigned to store job size and other metadata useful for billing.
  • Principled section level smoothing (so that level 2 sections are nested inside level 1 sections which are nested inside level 0 sections).
  • Block any annotations from any ontology except emtelligent ontology that have empty concept identifiers.
  • Entities that contain without within the span of the entity are marked as asserted.

Added:

  • New admin UI option for audit log downloads as CSV files.
  • New admin UI option to put engine into maintenance mode.
  • Several entitylinking updates based on new in-house annotated data.
  • Section parsing updated to handle many more corner cases. Radiology report section parsing improved significantly.
  • Add necessity and modifier as two new argument types to medication relations (see the emtellipro-json-2 output format for the specification). They were also added to the Python database client which added two new tables to the NLP API output database called medicationrelationnecessity and medicationrelationmodifier which have the same schema as the other medication relation arguments, namely id | medication_id | entity_id which lists the argument entities for each medication relation identified by medication_id.
  • Added controlled and uncontrolled as concepts for the status qualifier relation.
  • The Python SDK v5.14 includes a new version of the database client that supports direct export to CSV files using UUIDs, or direct export of NLP API output to JSONL files.
  • Improved precision in experiencer relations.
  • Added P: PLAN and other SOAP Note section headings.
  • Improved biomarker detection when there is ambiguity.
  • More complex multi-word qualifier relation modifiers.

Fixed:

  • Warning on unknown report kinds in input.
  • Avoid possible conflicts between reports with the same ID (the possible bug was not known to have caused any concrete problem, since annotation ID is not used anywhere internally).
  • Fixes for some negation issues.
  • Create full entities for all relation arguments (previously some entities used in relations did not have entity type info or attributes).

Compatibility:

  • API version 2 Release 26.
  • Python SDK and client v4.3.0 to v5.14.0.
  • Java SDK and client v3.0.2 to v5.5.0.
  • Python SDK CCD reader plugin v1.0.
  • NLP API specification v2.14.0
  • JSON result output schema v2.18.0 for emtellipro-json-2: added two new args for medication relations (see above).
  • visualclient version v2021-08-05-d9b754 which supports the following features:

    • New medication relation arguments (see above).

    • PDF and text uploads.

    • Supports advanced mode so expert users can select individual
      processing features.

v2.25 - 2021-05-20

Changed:

  • Newly redesigned audit subsystem.
  • Ground-up redesign and reimplementation of section parsing.
  • Negation updates for non- prefix and -free suffix; for negative margins; for can't; for denies; for not detected.
  • Include snomed ontology description in the snomed-icd10 ontology description.
  • Improve HGNC ontology matching.

Added:

  • Extended section parsing to handle new document sources.
  • Improve SNOMED, HGNC and Medcin ontology entity finding.
  • Better consistency and improvements to measurement relations.
  • Qualifier relations update.
  • Improvements in sentence detection for noisy text.
  • Improved imagelink references.
  • Add new synonyms for location qualifiers.
  • The emtelligent ontology now includes the experiencer and imagelink trigger entities.

Compatibility:

v2.24p2 - 2021-04-28

Added:

  • Improved precision and coverage for SNOMED ontology matching.

v2.24p1 - 2021-04-22

Added:

  • Improved precision and coverage for SNOMED ontology matching.

v2.24 - 2021-03-23

Added:

  • Config option for text PDF handling to control line margin to adjust when paragraphs are split.
  • Improved recall for HGNC ontology.
  • Behaviour of HGNC ontology matching now changed to improve recall. While recall is improved, precision is decreased due to the large number of dictionary words and medical acronyms that are also gene names.
  • Improve precision in SNOMED ontology matching.
  • Improved sentence boundary detection.
  • Improved Radiology and Cardiology section parsing.
  • Improve SNOMED, HGNC and Medcin ontology entity finding.

Changed:

  • Changed dev environment to support Ubuntu 20.04
  • Switch to 2020ab versions of the NCI, HGNC and LOINC ontologies

Compatibility:

v2.23 - 2021-02-27

Detailed release notes for v2.23

Added:

  • New known_ambiguity entity attribute for found entities. Added in NLP API specification v2.13.0; JSON result output schema v2.15.0.
  • New qualifier relation type called location which identifies the location of various concepts, e.g. left, right, bilateral. Added in JSON result output schema v2.16.0
  • Support for new ontology snomed_icd10. Added in NLP API specification v2.14.0; JSON result output schema v2.17.0.
  • Updated medication relation model.
  • Several annotation updates to SNOMED and Medcin ontologies.

Fixed:

  • Fix for temporal entities like 62 year old.
  • Bug fix for some entities that used to have empty SNOMED concept IDs.
  • Avoid false positives with adjectives and essential punctuation like commas and semi-colons.
  • Better detection of biomarkers and temporal expressions.

New versions:

  • NLP API specification emtellipro.yaml v2.14.0
  • emtellipro-result-json-v2.schema.json v2.17.0

v2.22 - 2021-01-26

Detailed release notes for v2.22

Fixed:

  • Fixed some issues with complex overlapping entity spans.
  • Fixed bugs related to mentions that are ambiguous but disambiguated wrt document category, subcategory, etc.
  • Bug fix: sentence ending for a double period bug fixed.
  • Bug fix: text spans in section and sub-section presents.
  • Bug fix: qualifer relation configuration bug
  • Bug fix: do not make sections on multi-word BIRADS labels in radiology reports.
  • Fixed bug that caused a crash in followup relations in some cases.
  • Fix for missing annotations due to disambiguation bug in entitylink.
  • Bug fix: Missing annotations attributed to UTF8 handling.
  • Bug fix: Fixed an issue where some biomarkers were linked to incorrect concepts.
  • Bug fix: Corrected the concept used for some unitless measurements.
  • Fixed bug in qualifier relations related to config file loading.
  • Fixed some entity text span bugs in engine output JSON.
  • Bug fix: correct disambiguation in entitylink case sensitive matching.
  • Double period sentence ending bugfix
  • Force OCR worker to use only one thread, avoiding overload.
  • Fixes to PDF handling to handle more parsing cases.
  • Fixed a bug that caused a rare crash in the NLP processing.
  • Proper raw spans for section locations.
  • Bug fix: imagelinks were being associated with procedure mentions.
  • Bug fix: prevent spurious imagelinks relations.

Added:

  • Added support for SNOMED CT 2020-2021 version.
  • Better section finding for Cardiology/Echocardiology.
  • Relations are now reported for cardiology echocardiogram report types as well.
  • Added feature support for spellchecking but it is disabled by default.
  • Support for new timeout parameter on status endpoint.
  • Handle time expressions that have underscores in them, e.g. __4__ weeks.
  • Added functionality to unitless measurements.
  • Add spellchecker support (it is currently turned off by default).
  • Add new semantic types “observable entity” and “regime/therapy” to SNOMED linking.
  • Improved concept linking for the HGNC ontology.
  • Tokenizer updated to handle combined route and frequency in medication relations.
  • Support PATCH as a verb on the cancel endpoint.

Changed:

  • Better support for unitless measurements.
  • Improvements to sentence boundary detection.
  • Improvements to negation detection.
  • Improvements to medication relations.
  • Large number of SNOMED, RadLex, Medcin, HGNC accuracy updates.
  • Allow only one to one trigger and subject in stage/grade type of qualifier relations.

v2.21p1 - 2020-09-02

Detailed release notes for v2.21p1

Added:

  • Annotation updates for SNOMED and Medcin.
  • User permissions and special flags in user/ result.

Fixed:

  • Fixed comma splitting if mentions occur with a comma in between without any whitespace.

v2.21 - 2020-07-15

Detailed release notes for v2.21

Added:

  • Two new qualifier relation types: “compliance” and “stage/grade”.
  • Added class NUM qualifiers to the stage/grade qualifier relation type.
  • Annotation updates for status type qualifiers for fractures.
  • New Clinical document subcategory called CCD.
  • Annotation updates for referrals/consults and biomarkers.
  • Added new measurement units.
  • Added section based entity disambiguation.
  • Multiple annotation updates for SNOMED, RxNorm, HGNC.

Fixed:

  • Improvements to ejection fraction and FEV1 measurement relations.
  • Improved measurement unit handling.
  • Improved qualifier relations.
  • Improved measurement relations.
  • Remove unitless measurements not in measurement relations.
  • Entity finding bug fixes for trailing + or - and hyphenated terms and dangling single quotes.
  • Fixed false positive unitless measurement relations.
  • Fixed a bug that raised ValueError exception in followup relation finding.
  • Improved negation handling.

Changed:

  • Remove punctuation insertion for faster processing.
  • Bare/unitless measurements entities that are not in a relation are pruned from the engine output.
  • Tokenizer improvements for better word splitting.
  • Improve plain/Clinical/generic section handling.
  • Added qualifier relations detection in Clinical documents.
  • Improved plain/Clinical/generic section handling to avoid false positives on “alcohol” and other sub-section headings.
  • HGNC ontology limited to entitylink matches.

v2.20 - 2020-05-21

Detailed release notes for v2.20

Added:

  • Added support for the LOINC ontology.
  • Added support for medication relations.
  • New type of qualifier relation: duration/time for new/old/chronic/acute qualifier values
  • Improved support for age expressions like x year old
  • Annotation updates for SNOMED-CT, Medcin and RxNorm

Changed:

  • Updated RadLex ontology database and lookup.

Fixed:

  • Fixed default processing features for meaurement-relations, imagelink-relations, qualifier-relations, followup-relations so that the emtelligent-ontology is selected by default to populate the arguments needed for the relations.
  • Fixed qualifier relations bug related to multiple qualifier relations with different types on the same argument
  • Uncertainty and Negation bug fixes.

Security:

  • Removed flask-cors allowed_headers argument (which seemingly has never done anything).

v2.19 - 2020-04-04

Detailed release notes for v2.19

Added:

  • Option to enable or disable processing features per instance.
  • Annotation updates for MEDCIN, RadLex, RxNorm, SNOMED-CT ontologies
  • Added more informal measurement units such as mm2, cm2, etc.
  • Option to control which processing features all users can access.
  • Support for new generic subcategory for Pathology reports.

Changed:

  • MEDCIN measurement entity type changed to “measurement”
  • Improved precision and recall for unitless measurements
  • JSON result schema changed (see detailed release notes)

Fixed:

  • Negation accuracy improvements
  • Measurement accuracy improvements
  • Measurement entity units are now reported as raw text
  • MEDCIN concepts no longer showing up with SNOMED concept identifiers
  • Bug fix for multiple concept identifiers appears for same span and ontology
  • Measurement relations are not identified any more for MEDCIN medications
  • Measurements now identify body weight and BMI

Compatibility:

  • API version 2 Release 19
  • Python SDK and client v4.3.0 to v4.6.0
  • Java SDK and client v3.0.2 to v3.1.0
  • JSON result output schema v2.11 for emtellipro-json-2

v2.18 - 2020-03-13

Added:

  • Measurement relations for numbers without units (“bare number” measurements)
  • HTTP response error message if web browser attempts to connect to API
  • Add measurement unit (returned as a list of strings) attribute to measurement entities
  • Ontology matching updates for medcin, rxnorm, snomed

Fixed:

  • Negation detection bug fixes
  • Prefer SNOMED Findings and Morphological Abnormalities over Body Structure in measurement relations

Changed:

  • Output version now 2.8.0 due to addition of measurement units

v2.17 - 2020-02-27

Added:

  • False positives fix for several ontologies, including snomed, rxnorm and medcin
  • New annotation update for several ontologies, including snomed, rxnorm and medcin
  • Enable measurement relations in clinical reports
  • Add error checks for empty category/subcategory
  • Added matching for Canadian vaccine data

Changed:

  • Pick up medcin “lab test” for measurement relations

Fixed:

  • Fix for follow-up relation detects multiple variations of the same relation
  • Relation finding bug fixes

v2.16 - 2020-02-03

Added:

  • Improved measurement relation identification by adding additional measurement types (matching more units of measurement)
  • MEDCIN ontology now returns relations
  • Support for new API single-section document feature. On job submission, users can now specify a subsection label that they want the entire submission to be treated as, without any section or subsection parsing. This feature is explained more comprehensively as the process_with_section_labels option in the API Submit task.

Changed:

  • Removed case sensitive search for HGNC terms
  • Improved precision of RxNorm matching
  • Negation and uncertainty bug fixes
  • Improved named entity recognition through lemmatizer improvements

Fixed:

  • Preprocessor bug related to subsections appearing without sections

v2.15 - 2019-11-13

Added:

  • New report types: ‘Molecular/generic’, ‘Clinical/SOAP Note’, and ‘Clinical/Nutrition Assessment’
  • New entity types for date/time extraction in emtelligent ontology
  • New Python SDK with enhanced RDBMS support

Changed:

  • Updated Java SDK to handle sub-sections
  • Improved followup relation extraction
  • Improved throughput in negation processing

Fixed:

  • Fix for NSTEMI negation detection

v2.14 - 2019-10-02

Fixed:

  • Bug fix in postprocessor to produce correct result JSON version in the output

v2.13 - 2019-10-02

Added:

  • MEDCIN ontology now uses custom annotated data
  • Internal changes to handle sections and sub-sections
  • Engine now outputs section and sub-section spans
  • Measurement entities now output under emtelligent ontology

Fixed:

  • Fixed case sensitive matching for entities
  • Fix for callback URL handling
  • Avoid duplicate entity references in relation arguments that should be sets
  • Bug fix for slowdown after nrocessing large report volumes

Changed:

  • New models for some ontologies

v2.12 - 2019-08-26

Fixed:

  • Various bug fixes to NCI and SNOMED-CT entity matching
  • Various bug fixes to negation
  • Bug fix for UMLS HGNC concept labels
  • Fixed bug on a submission with no documents

Added:

  • New updates for snomed and NCI
  • New medcin ontology
  • Support for UMLS HGNC ontology

Changed:

  • Sphinx docs for Python and Java SDK changed to full width
  • Allow per-document type in JSON submission uploads

v2.11 - 2019-08-15

Changed:

  • New models for some ontologies

v2.10 - 2019-07-07

Added:

  • New pathology section “SUPPLEMENTAL REPORTS”
  • New MEDCIN ontology added to engine.
  • New UMLS NCI Thesaurus ontology added to engine.
  • New “Tissue” section in Pathology reports

Changed:

  • Check submissions against new API type/category/subcategory enumerations.
  • Report contextual error messages on 400 error from submit endpoint.

Fixed:

  • Bug fix for disambiguation based on category/subcategory values
  • Some negation bug fixes.
  • Measurement relation bug fixes
  • Engine no longer expects filename headers in upload mime multipart parts.

v2.9 - 2019-05-17

Added:

  • New Java sdk with data model for parsing the result json from the engine
  • The result json now contains the full major.minor.patch version
  • Version field in JSON result formats.

Changed:

  • Changes to apostrophe insertion

v2.8 - 2019-05-13

Changed:

  • Improved synonym handling
  • Internal improvements

v2.6 - 2019-04-02

Changed:

  • Added new entity matching for Pathology

Fixed:

  • Fix some tokenization errors (e.g. Colles’)
  • Assume Content-type: text/plain for submits to engine
  • Fixed bug in storing reports

v2.5 - 2019-03-25

Added:

  • Qualifier relations added with corresponding new feature

v2.4 - 2019-03-15

Added:

  • Image-based PDF (OCR) support added
  • Initial implementation of debug mode for the Python SDK example client

Fixed:

  • Various bug fixes
  • Font encoding update to Python SDK

Compatibility:

  • API version v2 Release 4
  • Python SDK version v2.2.0
  • JSON result output schame v2.0

v2.3 - 2019-03-06

Fixed:

  • Various bug fixes

v2.1 - 2019-02-25

Added:

  • Text-based PDF support added to engine and Python SDK
  • Added case insensitive headings detector for Radiology reports in preprocessor

Fixed:

  • Engine assumed that polarity always exists in processor output