Towards similarity-based differential diagnostics for common diseases. (June 2021)

• Record Type: Journal Article
• Authors: Slater, Luke T.; Karwath, Andreas; Williams, John A.; Russell, Sophie; Makepeace, Silver; Carberry, Alexander; Hoehndorf, Robert; Gkoutos, Georgios V.
• Is Part Of: Computers in biology and medicine. Volume 133(2021)
• Publication Date: 2021-06
• Subjects: Semantic web -- Ontology -- Differential diagnosis -- Mimic-iii -- Semantic similarity; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104360
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Ontology-based phenotype profiles have been utilised for the purpose of differential diagnosis of rare genetic diseases, and for decision support in specific disease domains. Particularly, semantic similarity facilitates diagnostic hypothesis generation through comparison with disease phenotype profiles. However, the approach has not been applied for differential diagnosis of common diseases, or generalised clinical diagnostics from uncurated text-derived phenotypes. In this work, we describe the development of an approach for deriving patient phenotype profiles from clinical narrative text, and apply this to text associated with MIMIC-III patient visits. We then explore the use of semantic similarity with those text-derived phenotypes to classify primary patient diagnosis, comparing the use of patient-patient similarity and patient-disease similarity using phenotype-disease profiles previously mined from literature. We also consider a combined approach, in which literature-derived phenotypes are extended with the content of text-derived phenotypes we mined from 500 patients. The results reveal a powerful approach, showing that in one setting, uncurated text phenotypes can be used for differential diagnosis of common diseases, making use of information both inside and outside the setting. While the methods themselves should be explored for further optimisation, they could be applied to a variety of clinical tasks, such as differential diagnosis, cohort discovery, document and text classification, and outcome prediction. Highlights: Semantic similarity is an effective method for multiple tasks, including differential diagnosis of rare diseases. It has not been applied for differential diagnosis of common diseases, or over a large uncurated text-derived phenotype. We explore and contrast two methods of classifying text-derived phenotypes for differential diagnosis of common diseases. We synthesise these methods, creating optimised disease profiles with in-context training, leading to a superior classifier. Semantic similarity is a promising method for differential diagnosis of common disease from text, warranting further exploration.