Evaluating semantic similarity methods for comparison of text-derived phenotype profiles

BMC Medical Informatics and Decision Making

Alexander Carberry¹  Sophie Russell¹  Silver Makepeace¹  Luke T. Slater²  Andreas Karwath²  Georgios V. Gkoutos³  John A. Williams⁴  Robert Hoehndorf⁵  Simon Ball⁶  Hilary Fanning⁷ 

[1] College of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK;Institute of Translational Medicine, University Hospitals Birmingham, NHS Foundation Trust, Birmingham, UK;College of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK;Institute of Translational Medicine, University Hospitals Birmingham, NHS Foundation Trust, Birmingham, UK;MRC Health Data Research UK (HDR UK) Midlands, Birmingham, UK;University Hospitals Birmingham NHS Foundation Trust, Edgbaston, Birmingham, UK;College of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK;Institute of Translational Medicine, University Hospitals Birmingham, NHS Foundation Trust, Birmingham, UK;NIHR Experimental Cancer Medicine Centre, Birmingham, UK;NIHR Surgical Reconstruction and Microbiology Research Centre, Birmingham, UK;NIHR Biomedical Research Centre, Birmingham, UK;MRC Health Data Research UK (HDR UK) Midlands, Birmingham, UK;University Hospitals Birmingham NHS Foundation Trust, Edgbaston, Birmingham, UK;College of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK;Institute of Translational Medicine, University Hospitals Birmingham, NHS Foundation Trust, Birmingham, UK;University Hospitals Birmingham NHS Foundation Trust, Edgbaston, Birmingham, UK;Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia;Institute of Translational Medicine, University Hospitals Birmingham, NHS Foundation Trust, Birmingham, UK;MRC Health Data Research UK (HDR UK) Midlands, Birmingham, UK;University Hospitals Birmingham NHS Foundation Trust, Edgbaston, Birmingham, UK;Institute of Translational Medicine, University Hospitals Birmingham, NHS Foundation Trust, Birmingham, UK;University Hospitals Birmingham NHS Foundation Trust, Edgbaston, Birmingham, UK;

关键词: Semantic web;    Ontology;    Differential diagnosis;    MIMIC-III;    Semantic similarity;   

DOI  :  10.1186/s12911-022-01770-4

来源: Springer

【 摘 要 】

BackgroundSemantic similarity is a valuable tool for analysis in biomedicine. When applied to phenotype profiles derived from clinical text, they have the capacity to enable and enhance ‘patient-like me’ analyses, automated coding, differential diagnosis, and outcome prediction. While a large body of work exists exploring the use of semantic similarity for multiple tasks, including protein interaction prediction, and rare disease differential diagnosis, there is less work exploring comparison of patient phenotype profiles for clinical tasks. Moreover, there are no experimental explorations of optimal parameters or better methods in the area.MethodsWe develop a platform for reproducible benchmarking and comparison of experimental conditions for patient phentoype similarity. Using the platform, we evaluate the task of ranking shared primary diagnosis from uncurated phenotype profiles derived from all text narrative associated with admissions in the medical information mart for intensive care (MIMIC-III).Results300 semantic similarity configurations were evaluated, as well as one embedding-based approach. On average, measures that did not make use of an external information content measure performed slightly better, however the best-performing configurations when measured by area under receiver operating characteristic curve and Top Ten Accuracy used term-specificity and annotation-frequency measures.ConclusionWe identified and interpreted the performance of a large number of semantic similarity configurations for the task of classifying diagnosis from text-derived phenotype profiles in one setting. We also provided a basis for further research on other settings and related tasks in the area.

【 授权许可】

CC BY