Merge branch 'master' of https://github.com/honghan/KGPhenotyping.git

Honghan · Nov 6, 2019 · c6b4358 · c6b4358
2 parents 4f29e31 + bd6b079
commit c6b4358
Show file tree

Hide file tree

Showing 9 changed files with 236 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -1,3 +1,12 @@
-## Knowledge Graph based Phenotyping on Heterogenous/Distributed Data Sources
+## Knowledge Graph based Phenotyping on Heterogenous Data Sources
 - towards interpretable, reusable, reproducible phenotype computation in clinical data science.
-- a project funded by Health Data Research UK
+- a project funded by [Health Data Research UK: Graph-Based Data Federation for Healthcare Data Science](https://www.hdruk.ac.uk/projects/graph-based-data-federation-for-healthcare-data-science/)
+
+### Why & What
+Extracting patient phenotypes from routinely collected health data (such as Electronic Health Records) requires translating clinically-sound phenotype definitions into queries/computations executable on the underlying data sources by clinical researchers. This requires significant knowledge and skills to deal with heterogeneous and   often *imperfect* data. Translations are time-consuming,  error-prone and, most importantly, hard to share and reproduce across different settings. This project implements a **knowledge driven phenotyping framework** that  
+1. decouples the specification of phenotype semantics from underlying data sources; 
+2. can automatically populate and conduct phenotype computations on heterogeneous data spaces. 
+
+### Architecture & Deployment
+This framework has been deployed on five Scottish health datasets.
+![alt text](https://raw.githubusercontent.com/Honghan/KGPhenotyping/master/assets/kg-phenotyping-arch.png "Architecture of Knowledge Driven Phenotyping")
diff --git a/assets/kg-phenotyping-arch.png b/assets/kg-phenotyping-arch.png
diff --git a/evaluation/MEI2020-queries.MD b/evaluation/MEI2020-queries.MD
@@ -0,0 +1,74 @@
+# Evaluation Queries for MIE 2020 Submission
+
+## Q1:  patients prescribed Fluoxetine (SNOMED CT code: 321949006)
+SPARQL:
+```SPARQL
+PREFIX : <http://www.hdruk.ac.uk/sprint/graph/> 
+PREFIX test: 	<http://www.hdruk.ac.uk/sprint/graph/ontology/test/> 
+PREFIX onto: 	<http://www.hdruk.ac.uk/sprint/graph/ontology/>
+PREFIX icd: <http://www.hdruk.ac.uk/sprint/graph/ontology/ICD/> 
+PREFIX patient: <http://www.hdruk.ac.uk/sprint/graph/patient/> 
+PREFIX RCTV2: <http://purl.bioontology.org/ontology/RCTV2/>
+PREFIX bnf: <http://www.hdruk.ac.uk/sprint/graph/ontology/bnf/> 
+PREFIX snomed: <http://www.hdruk.ac.uk/sprint/graph/ontology/snomed/> 
+
+ SELECT DISTINCT * 
+ WHERE { 
+   ?x onto:hasPrescription ?p .
+   ?p a snomed:321949006 .
+ }
+```
+SQL:
+```SQL
+select CHI from graph.Prescription where BnfCode='0403030E0AAAAAA'
+```
+
+## Q2: patients diagnosed as Type II Diabetes (ICD10 E11 and its sub-codes)
+SPARQL:
+```SPARQL
+PREFIX : <http://www.hdruk.ac.uk/sprint/graph/> 
+PREFIX test: 	<http://www.hdruk.ac.uk/sprint/graph/ontology/test/> 
+PREFIX onto: 	<http://www.hdruk.ac.uk/sprint/graph/ontology/>
+PREFIX icd: <http://www.hdruk.ac.uk/sprint/graph/ontology/ICD/> 
+PREFIX patient: <http://www.hdruk.ac.uk/sprint/graph/patient/> 
+PREFIX RCTV2: <http://purl.bioontology.org/ontology/RCTV2/>
+PREFIX bnf: <http://www.hdruk.ac.uk/sprint/graph/ontology/bnf/> 
+PREFIX snomed: <http://www.hdruk.ac.uk/sprint/graph/ontology/snomed/> 
+
+ SELECT DISTINCT * 
+ WHERE { 
+   ?x a icd:E11 .
+ }
+```
+SQL:
+```SQL
+select CHI from graph.HospitalAdmissions where maincondition like 'E11%' or maincondition in 
+('-25000', '-25002', '-25010', '-25012', '-25020', '-25022', '-25030', '-25032', '-25040', '-25042', '-25050', '-25052', '-25060', '-25062', '-25070', '-25072', '-25080', '-25082', '-25090', '-25092')
+```
+
+## Q3: patients have potential Diabetes coding errors
+SPARQL:
+```SPARQL
+PREFIX : <http://www.hdruk.ac.uk/sprint/graph/> 
+PREFIX test: 	<http://www.hdruk.ac.uk/sprint/graph/ontology/test/> 
+PREFIX onto: 	<http://www.hdruk.ac.uk/sprint/graph/ontology/>
+PREFIX icd: <http://www.hdruk.ac.uk/sprint/graph/ontology/ICD/> 
+PREFIX patient: <http://www.hdruk.ac.uk/sprint/graph/patient/> 
+PREFIX RCTV2: <http://purl.bioontology.org/ontology/RCTV2/>
+PREFIX bnf: <http://www.hdruk.ac.uk/sprint/graph/ontology/bnf/> 
+PREFIX snomed: <http://www.hdruk.ac.uk/sprint/graph/ontology/snomed/> 
+
+ SELECT DISTINCT * 
+ WHERE { 
+   ?x a onto:DiabetesConflictPatient .
+ }
+```
+SQL:
+```SQL
+select h1.CHI from graph.HospitalAdmissions h1,  graph.HospitalAdmissions h2 where (h1.maincondition like 'E11%' or h1.maincondition in 
+('-25000', '-25002', '-25010', '-25012', '-25020', '-25022', '-25030', '-25032', '-25040', '-25042', '-25050', '-25052', '-25060', '-25062', '-25070', '-25072', '-25080', '-25082', '-25090', '-25092'))
+and 
+(h2.maincondition like 'E10%' or h1.maincondition in 
+('-25001', '-25003', '-25011', '-25013', '-25021', '-25023', '-25031', '-25033', '-25041', '-25043', '-25051', '-25053', '-25061', '-25063', '-25071', '-25073', '-25081', '-25083', '-25091', '-25093'))
+and h1.CHI = h2.CHI
+```
diff --git a/evaluation/RE1.png b/evaluation/RE1.png
diff --git a/evaluation/RE2.png b/evaluation/RE2.png
diff --git a/evaluation/RE4.png b/evaluation/RE4.png
diff --git a/evaluation/readme.MD b/evaluation/readme.MD
diff --git a/evaluation/result_table.PNG b/evaluation/result_table.PNG
diff --git a/pom.xml b/pom.xml
@@ -43,7 +43,7 @@
         <dependency>
 		    <groupId>com.fasterxml.jackson.core</groupId>
 		    <artifactId>jackson-databind</artifactId>
-		    <version>2.8.7</version>
+		    <version>2.9.10</version>
 		</dependency>
 
 		<dependency>
@@ -89,4 +89,4 @@
   <organization>
   	<name>HDRUK Scotland</name>
   </organization>
-</project>
+</project>