=Paper=
{{Paper
|id=Vol-2849/paper-18
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-2849/paper-18.pdf
|volume=Vol-2849
|dblpUrl=https://dblp.org/rec/conf/swat4ls/0001JSCWSHK19
}}
==None==
https://ceur-ws.org/Vol-2849/paper-18.pdf
Babylon Health’s Medical Knowledge Graph:
Why, What, and How
Claudia Schulz, Damir Juric, Jetendr Shamdasani, Martin Coste, Szymon
Wartak, Aleksandar Savkov, Nils Hammerla, and Mohammed Khodadadi
Babylon Health, London SW3 3DD, UK
https://www.babylonhealth.com
Babylon Health offers digital healthcare services through a mobile appli-
cation. Besides video consultations with doctors, the app is equipped with a
chatbot able to provide medical information and perform triage.
To realise this digital healthcare experience, various services within Babylon
generate, exchange, and consume health data and clinical knowledge. For exam-
ple, text understanding services process the user’s chatbot input and recognise
relevant medical terms therein. These terms may need to be matched with pre-
defined symptoms and risk factors that form the input to the triaging engine, or
with past diagnoses stored in user profiles. Furthermore, consultation notes are
labelled with clinical codes to allow for easy processing and retrieval.
To ensure that a uniform medical terminology is used throughout Babylon’s
services and to allow reasoning over medical data, a large medical knowledge
graph was created [1], realised as the materialisation of an RDF triple store.
Building the Babylon Knowledge Graph As illustrated in Figure 1, the
Babylon Knowledge Graph was constructed by integrating information from
multiple existing medical ontologies. To ensure accurate alignment of these het-
erogeneous ontologies, we developed a novel iterative approach for ontology in-
tegration [3], where SNOMED served as the seed ontology. Our approach tackles
the problem of hierarchy incompatibility between ontologies by prioritising the
current ontology over the one to be integrated thus minimising the amount of
inconsistent mappings being dropped.
We furthermore augmented the integrated ontologies with information ex-
tracted from biomedical papers. Since SNOMED and other ontologies mainly
provide hierarchical relationships between concepts, this information extraction
was focused on other types of relationships between medical concepts, e.g. that
between diseases and their symptoms or risk factors.
Knowledge Graph Validation To ensure the syntactic and semantic validity
of the Babylon Knowledge Graph, we apply both automatic [4] and manual
evaluation methods. Checking for (undesirable) cycles and investigating average
path length are two of the straight-forward automatic syntax analyses performed.
An example of ensuring semantic validity is to check that there is no label overlap
between concepts. A manual evaluation of a sample of the Babylon Knowledge
Graph was performed with the help of doctors, focusing on the correctness of
the hierarchy and concept labels.
Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
2 Schulz et al.
NCI Babylon
Knowledge
Graph
Language
Understanding
Alignment &
SNOMED What’s
Entity Linking your
symptom?
I have a
headache
CHV Babylon
Validation App
Information
Extraction
Fig. 1. Creation and usage of the Babylon Knowledge Graph
Knowledge Graph Powered Triage To enable the understanding and pro-
cessing of user input in a chatbot conversation, we employ various Natural Lan-
guage Processing (NLP) techniques: dependency parsing combined with entity
linking identifies medical terms in text and links them to concepts in the Baby-
lon Knowledge Graph. These concepts are then matched with symptoms and
risk factors represented in Babylon’s triage system. However, the combination
of multiple concepts in the user input may correspond to a single concept in the
triage system and triage concepts may be more general than the very specific
symptoms provided by a user. For example, the concepts ‘severe pain’ and ‘fore-
head’ may have been identified in the user input, which have to be matched to
the single and more general triage concept ‘headache’. To realise this advanced
reasoning, we developed a hybrid reasoning method that combines NLP methods
with logic-based subsumption [2].
References
1. Barisevičius, G., Coste, M., Geleta, D., Juric, D., Khodadadi, M., Stoilos, G., Za-
ihrayeu, I.: Supporting Digital Healthcare Services Using Semantic Web Technolo-
gies. In: ISWC’18. pp. 291–306 (2018)
2. Juric, D., Stoilos, G., Wartak, S., Khodadadi, M.: Reasoning with Textual Queries:
A Case of Medical Text. In: ISWC’18 Poster (2018)
3. Stoilos, G., Geleta, D., Shamdasani, J., Khodadadi, M.: A Novel Approach and
Practical Algorithms for Ontology Integration. In: ISWC’18. pp. 458–476 (2018)
4. Stoilos, G., Geleta, D., Wartak, S., Hall, S., Khodadadi, M., Zhao, Y., Alghamdi,
G., Schmidt, R.A.: Methods and Metrics for Knowledge Base Engineering and In-
tegration. In: WOP’18. pp. 72–86 (2018)