A novel tool for standardizing clinical data in a semantically rich model

Freedman, H. T.; Williams, Heather; Miller, Mark A.; Birtwell, David; Mowery, Danielle L.; Stoeckert, Christian J.

doi:10.1016/j.yjbinx.2020.100086

Cited by 13 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And as we apply this tool to less engineered input features and harder problems, the search space will be very large. The approach would benefit considerably from learning on top of a framework that encodes expert clinical knowledge, such as ontologies and knowledge graphs 50 . The incorporation of expert knowledge would improve search efficiency and potentially performance, while maintaining interpretability.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Application of concise machine learning to construct accurate and interpretable EHR computable phenotypes

Lee

Ajmal

et al. 2020

Preprint

View full text Add to dashboard Cite

ObjectiveElectronic health records (EHRs) can improve patient care by enabling systematic identification of patients for targeted decision support. But, this requires scalable learning of computable phenotypes. To this end, we developed the feature engineering automation tool (FEAT) and assessed it in targeting screening for the under-diagnosed, under-treated disease primary aldosteronism.Materials and MethodsWe selected 1199 subjects receiving longitudinal care in one health system between 2007 and 2017 and classified them for hypertension (N=608), hypertension with unexplained hypokalemia (N=172), and apparent treatment-resistant hypertension (N=176) by chart review. We derived 331 features from EHR encounters, diagnoses, laboratories, medications, vitals, and notes. We modified FEAT to encourage model parsimony and compared its models’ performance and interpretability to that of expert-curated heuristics and conventional machine learning.ResultsFEAT models trained to replicate expert-curated heuristics had higher AUPRC scores than all other models (p < 0.001) except random forests and were smaller than all other models (p < 1e-6) except decision trees. FEAT models trained to predict chart review phenotypes exhibited similar AUPRC scores to penalized logistic regression while being substantially simpler than all other models (p < 1e-6). For treatment-resistant hypertension, FEAT learned a six-feature, clinically intuitive model that demonstrated an adjusted PPV of 0.73 and sensitivity of 0.54 in testing.DiscussionFEAT learns computable phenotypes that approach the performance of expert-curated heuristics and conventional machine learning without sacrificing interpretability.ConclusionBy constructing accurate and interpretable computable phenotypes at scale, FEAT has the potential to facilitate widespread, systematic clinical decision support.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Finally, this approach could benefit considerably from learning on top of standard frameworks for representing and querying both clinical data and expert clinical knowledge. [53,54] The incorporation of expert knowledge would improve search efficiency while maintaining interpretability.…”

Section: Discussionmentioning

confidence: 99%

Application of concise machine learning to construct accurate and interpretable EHR computable phenotypes

Lee

Ajmal

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Current semantic integration approaches are based on ontologies. As mentioned in [3], well-designed ontologies, which focus on logical consistency and represent concepts within a hierarchy are useful for the creation of clinical data representations that are semantically rich, unambiguous, and not dependent on specific CDMs.…”

Section: Semantic Common Data Modelmentioning

confidence: 99%

“…This data is then transformed into a semantically rich representation and harmonized. While multiple data modelling standards and proposals exist to integrate and share data, they still fail in providing semantically rich representations [3]. The semantic CDM proposed integrates content from well-known biomedical ontologies like SNOMED CT (SCT) by using a biomedical top-level ontology.…”

Section: Introductionmentioning

confidence: 99%

Towards a Semantic Data Harmonization Federated Infrastructure

Martínez-Costa

Abad-Navarro

2021

Studies in Health Technology and Informatics

View full text Add to dashboard Cite

Data integration is an increasing need in medical informatics projects like the EU Precise4Q project, in which multidisciplinary semantically and syntactically heterogeneous data across several institutions needs to be integrated. Besides, data sharing agreements often allow a virtual data integration only, because data cannot leave the source repository. We propose a data harmonization infrastructure in which data is virtually integrated by sharing a semantically rich common data representation that allows their homogeneous querying. This common data model integrates content from well-known biomedical ontologies like SNOMED CT by using the BTL2 upper level ontology, and is imported into a graph database. We successfully integrated three datasets and made some test queries showing the feasibility of the approach.

show abstract

“…Sun et al present the architecture of their semantic processing approach where data is transmitted through the semantic layer with clinical ontologies inside (Sun et al 2015). Most solutions for data interoperability are based on ontologies (Sun et al 2015;Roberts and Demner-Fushman 2016;Freedman et al 2020;Kersloot et al 2020). Moreover, Kersloot et al (2020) show the statistics for mapping clinical text fragments to ontology concepts that are described in reviewed papers.…”

Section: Related Workmentioning

confidence: 99%

Citywide quality of health information system through text mining of electronic health records

et al. 2021

View full text Add to dashboard Cite

A system of hospitals in large cities can be considered a large and diverse but interconnected system. Widely applied in hospitals, electronic health records (EHR) are crucially different from each other because of the use of different health information systems, internal hospital rules, and individual behavior of physicians. The unstructured (textual) data of EHR is rarely used to assess the citywide quality of healthcare. Within the study, we analyze EHR data, particularly textual unstructured data, as a reflection of the complex multi-agent system of healthcare in the city of Saint Petersburg, Russia. Through analyzing the data collected by the Medical Information and Analytical Center, a method was proposed and evaluated for identifying a common structure, understanding the diversity, and assessing information quality in EHR data through the application of natural language processing techniques.

show abstract

A novel tool for standardizing clinical data in a semantically rich model

Cited by 13 publications

References 20 publications

Application of concise machine learning to construct accurate and interpretable EHR computable phenotypes

Application of concise machine learning to construct accurate and interpretable EHR computable phenotypes

Towards a Semantic Data Harmonization Federated Infrastructure

Citywide quality of health information system through text mining of electronic health records

Contact Info

Product

Resources

About