Structuring Medical Records with Apache Stanbol Rafa Haro, Senior - - PowerPoint PPT Presentation

Structuring Medical Records with Apache Stanbol

Rafa Haro, Senior Software Engineer, Athento Antonio Pérez Morales, Senior Software Engineer, Ixxus


• Committer, PMC Member @ Apache

Stanbol, Apache ManifoldCF

• Topics: Document Analysis, NLP, Machine

Learning, Semantic Technologies, ECM

• Committer @ Apache Stanbol, Apache

ManifoldCF

• Topics: ECM, Semantic Search, ETL,

Machine Learning

Apache Stanbol provides a set of reusable components for semantic content management. It extends existing CMSs with a number of semantic services.

CMS

Traditional Semantic

Software Architecture for Semantically Enabled CM and ECM systems

Apache Stanbol Story

• Started within FP7 European Project IKS (Interactive

Knowledge Stack. 2009 - 2012)


• IKS project brought together an Open Source Community for

Defining and Building Platforms in the Semantic CMS Space


• Incubated in November 2010

• Successfully promoted within CMS and ECM industry through

IKS Early Adopters Program


• Graduated to Top-Level Apache Project in October 2012

What is a Semantic CMS?

Traditional CMS Atomic Unit: Document Properties as meta-data (key-value schemas) Keyword Search Document Management Document Types Document Workflow Semantic CMS Atomic Unit: Entity Semantic meta-data (RDF) Semantic Search Knowledge Management Entity Management Ontologies

Source: What Apache Stanbol Can Do for You?. Fabian Christ. ApacheCon Europe 2012

Key Points

• Designed to bring Semantic Technologies to existing CMS

• Non-intrusive set of RESTful ‘Semantic’ Services 

• Extremely Modular: Use only the modules you need

• Main Features:
• Multilingual Content Enhancement: Structure Content through Semantic

Metadata


• Knowledge Bases Management

• Knowledge Models and Reasoning

• Semantic Indexing and Search

Stanbol Components

• Stanbol components provide:
• RESTful API
• Java APIs and OSGi services
• Stanbol components do NOT depend on each other
• however they can be easily combined to

Apache Stanbol Component Layer

Apache Stanbol Reasoners Apache Stanbol Enhancer Apache Stanbol Rules Apache Stanbol Ontology Manager Apache Stanbol ContentHub Apache Stanbol EntityHub Apache Stanbol FactStore Stanbol Enhancement Engines Apache Stanbol CMS Adapter

Stanbol Components (II)

• Enhancer: Extracts Knowledge from unstructured parsed content

• EntityHub: Manage Domain Entities and Topics (Knowledge Bases)

• ContentHub: Semantic Indexing / Search over your - semantic enhanced - Content

• CMS Adapter: Sync. your CMS with Apache Stanbol (JCR/CMIS)

• Ontology Manager: Manage you formal Domain Knowledge

• Reasoners & Rules: Apply Domain Knowledge to improve / validate extracted Information. Refactor /

refine knowledge to align it to public schemas such as schema.org

Built on Top of Apache….

• Apache Felix as OSGi environment
• Apache Sling launchers and OSGi Tools
• Apache Maven for building
• Apache Clerezza as RDF Framework
• Apache Jena as TripleStore
• Apache Solr for Knowledge Bases Management
• Apache Tika for converting input
• Apache OpenNLP for NLP Processing

Integration Scenarios

Source: What Apache Stanbol Can Do for You?. Fabian Christ. ApacheCon Europe 2012

• Stand-Alone Server

(Stanbol Launchers)

• Web Application

(Servlet-Container)

• Embedded within an

OSGi environment

Project Current Status

Contributions (commits) to Trunk Since Incubation

Incubation (Nov 2010) Apache Stanbol 0.9.0-incubating (Aug 2012) Graduation (October 2012) IKS Project Ending (Dec 2012) Apache Stanbol 0.12.0 (March 2014) Apache Stanbol 1.0.0 (October 2016)

Project Current Status (II)

• 22 PMC Members (Last Addition Jul 2016)
• 26 Committers (Last Addition May 2015)
• 3-5 active committers last 2 years
• dev@stanbol.apache.org: 228 subscribers
• Activity has been gradually decreasing
• 3 major releases

Source: Apache Stanbol Committee Report Helper (https://reporter.apache.org/?stanbol)

Stanbol Enhancer

RDF

Stanbol Enhancer (II)

Stanbol Enhancer (III)

Stanbol Enhancement Chains

• Define how Content is processed by the Enhancer through an ExecutionPlan
• Different Implementations:
• ListChain: in order sequential enhancement engines execution. Parallel Execution of engines not

supported

• WeightedChain: ExecutionPlan is calculated using the engines order metadata. Parallel Execution of

engines allowed

• API:
• /enhancer: executes the default chain
• /enhancer/chain/{chain-name}: executes a concrete named chain
• /enhancer/engine/{engine-name}: executes a concrete named engine

Current Enhancement Engines

• Preprocessing
• Tika Engine
• content type detection
• text extraction from several document formats
• metadata extraction from several document formats
• Natural Language Processing
• Language Detection (different implementations)
• Sentence Detection (OpenNLP, SmartCN, REST)
• Tokenizer (OpenNLP, SmartCN, REST)
• POS Tagging (OpenNLP, REST)
• Chunking (OpenNLP, REST)
• NER (OpenNLP, OpenCalais, REST)
• Entity Linking
• Named Entity Linking
• EntityHub Linking Engine
• FST (Lucene Finit State Transducer) Linking Engine
• Entity Co-mention
• Commercial Engines (OpenCalais, Zemanta, CELI…)
• Sentiment Analysis
• Disambiguation
• DBPedia Spotlight
• Solr MLT based
• PostProcessing:
• Dereferencing

Stanbol EntityHub

Stanbol EntityHub (II)

• Manage Multiple Entity Sources (Knowledge Bases)
• Allows Fast Entity-Lookup using Apache Solr

• Referenced Site (Remote LD + Local Caches) Vs Managed Site (Entity CRUD Api
• ver manually configured Sites)

• API:
• Query for Entities (used by Entity Linking Engines)


• CRUD for Managed Sites
• LDPath support for:
• Graph Path Retrieval (Used for dereferencing)
• Schema Translation
• Simple Reasoning

schema:name = rdfs:label[@en]; friend-names = foaf:knows/foaf:name curl -X POST -d "name=lyon&limit=10" \ http://localhost:8080/entityhub/site/dbpedia/find

Use Case: Hexin Project - Structuring Medical Records

• R&D Project for Sergas (Galician Public Health Office)
• Clinical Data Analysis Platform for supporting:
• Clinical Assistance
• Epidemiology studies
• Medical Research
• Big Data approach for analyzing both structured historical

clinical data and unstructured medical records

• Medical Records are written in Spanish and Galician

Hexin: Architecture

Validation Analysis Patient

Data Source

URX ETL BIG DATA (HDFS + HIVE)

Event Detection Process

Cassandra Reference Cases Detection Process

New Case

BI

PatientId Date Structured Events Semantic Events Symptoms:

• Cough
• Unrest

Unrest Cough Fever>38 Rules

Hexin: Semantic Tagging

Hexin: Objective

“Paciente diabético desde los 5 años y con EPOC moderada grado 2 de la GOLD”

Hexin:Solution Design

• Structure Medical Records using Apache Stanbol Enhancer
• Custom Ontology:
• Symptoms
• Diseases
• Diagnosis Tests
• Family and Personal History
• Custom Enhancement Chain:
• Language Detection > NLP > Entity Linking > Negation

Detection > Fact Extraction

Hexin: Ontology

Hexin: Ontology Indexing

• For supporting the Entity Linking process against Hexin Ontology,

an EntityHub site must be created

• 2 options:
• ManagedSite: full CRUD storage <-> DYNAMIC
• ReferencedSite: READ-ONLY remote site + local index
• Stanbol EntityHub Indexing Tool:
• RDF —> JenaTDB —> Solr Index
• Configure Custom Namespaces, Mappings and Properties
• Generates an OSGi Bundle with the Yard and YardSite default

configurations

• Copy the index to Stanbol /datafiles folder and install the bundle

using Apache Felix OSGi Web Console

hexin:* hexin:label > rdfs:label

Negex Fact Extract. Hexin Linking

Hexin: Enhancement Chain

OpenNLP-Chunker OpenNLP-POS OpenNLP-Token OpenNLP-Sent.

• Lang. Detect.

Custom Hexin Engine. Implemented for the project Entity Linking Engine. Available in Stanbol with a Custom Configuration for this use case NLP Engines. Available in Stanbol. Default Configuration Pre-Processing Engine. Available in Stanbol

Hexin: Linking

Hexin: Linking (II)

Hexin: Custom Engines

@Component @Service public class MyEngine implements EnhancementEngine { @Activate public void activate(ComponentContext c) { // initialize, configure, ... } public int canEnhance(ContentItem item) { if(...item matches our expectations...) { return ENHANCE_SYNCHRONOUS; } else { return CANNOT_ENHANCE; } } public void computeEnhancements(ContentItem item) { // run the engine and add results to item’s // RDF graph based on the item’s InputStream } }

maven-bundle- plugin

adds OSGI metadata

Maven build

maven-scr-plugin

adds services metadata

registered by OSGi

MyEngine
 Service

MANIFEST.MF

OSGi
 metadata

OSGi bundle

Install in
 Stanbol


no restart
 needed

NLP at Apache Stanbol

NLP at Apache Stanbol (II)

• Browsable Map with Spans
• Spans sorted by Natural Order
• Iterator based API that allows 


concurrent Modifications

• Annotations supported at Spans Level
• POS Annotation
• PosTag


tag (e.g. NE)
 lexical category (e.g. Noun)

• Phrase Annotation (chunks)
• PhraseTag


tag (e.g. NP)
 lexical-category (e.g. NounPhrase)

• Sentiment Annotation
• SentimentTag:: Double


Stanbol is an Amazing Tool

Sentence Chunk Token

Span Types:

• Token
• Chunk
• Sentence
• Text Section
• Analyzed Text

Hexin Custom Engine: Negex

• Context/Negex: Algorithm for Negation Detection
• Based on Triggers-Terms + Regex

Chapman WW, Bridewell W, Hanbury P, Cooper GF, Buchanan BG. A simple algorithm for identifying negated findings and diseases in discharge summaries. J Biomed Inform. Oct 2001;34(5):301-310. public abstract class AbstractNegexDetector implements NegexDetector { @Override
 public Set<IRI> detectNegations(String language, Graph metadata, AnalysedText at) throws NegexException{} protected abstract boolean isNegated(String language, String concept, String sentence);

}

Hexin Custom Engine: Negex (II)

• Triggers Types:
• Pre-condition Negation terms (e.g. absence of)
• Pseudo Negation terms (e.g. no increase)
• Pre-condition possibility phrase (e.g. rule him out)
• Post-condition negation terms (e.g. unlikely)
• Termination terms (e.g. but, however)
• Implementation available under Apache License 2.0
• Engine Implementation Challenges:
• Entity Annotations as Targets
• AnalyzedText and EntityAnnotations relationships are currently obfuscated
• GLUE CODE for locating Entity Annotations Spans by using START - END Text

Annotations properties

• Once Entity Annotation sentence is located, is used as context along with the Entity

surface-form (mention) for applying the algorithm

• Negation Returned as a Custom Property for the TextAnnotation (negated = True or False)

Hexin Custom Engine: Fact Extraction

“Paciente diabético desde los 5 años y con EPOC moderada grado 2 de la GOLD”

Hexin Custom Engine: Fact Extraction (II)

• In-Context Entity Fact Extraction
• Facts returned as Entity RDF Metadata like the rest of Entity

Properties

• Different Implementations of Context (all extracted from

AnalyzedText structure)

• Sentence Context (default and usually enough)
• Window of Text Context
• Paragraph Context
• Rule Based Approach:
• Regex over RAW Text or POS tags Sequence
• ENTITY reserved word -> OR expression for all ENTITY labels

Hexin Custom Engine: Fact Extraction (III)

• Supported Expressions:
• diabetes|diabético|DM desde los N años
• diabetes|diabético|DM a los N años
• Debut diabetes|diabético|DM a los N años

Hexin Custom Engine: Fact Extraction (IV)

• POS based Rules:

Diabetes diagnosed when he was 5 years old

NNS VB WRB PRP VBD CD NNS JJ



 
 ENTITY \s VB * VB[be] (CD) years old

• r simply

ENTITY \s VB * VB[be] (CD)

Thanks for your attention!