Preprint: PhenoSS: Phenotype semantic similarity-based approach for rare disease prediction and patient clustering

WHY IT MATTERS

If this tool becomes available in clinical practice, patients with rare diseases could receive accurate diagnoses faster by having their symptom patterns analyzed more intelligently, potentially reducing the average diagnostic odyssey timeline.

Researchers developed a new computer tool called PhenoSS that helps doctors diagnose rare diseases more accurately by analyzing patient symptoms in a smarter way. Instead of just matching symptoms one-by-one, this tool understands how symptoms relate to each other and accounts for differences in how different doctors record patient information. This could help patients get diagnosed faster and more correctly.

PhenoSS: Phenotype semantic similarity-based approach for rare disease prediction and patient clustering Authors: Chen, S. et al. Server: medRxiv Category: health informatics Abstract: ObjectiveSystematic clinical phenotyping using Human Phenotype Ontology (HPO) is central to rare disease diagnosis. However, current disease prioritization (ranking candidate diseases from HPO for a patient) methods face key challenges: they often fail to account for the hierarchical structure of HPO terms, ignore dependencies among correlated terms, and do not adjust for batch effects arising from systematic differences in phenotype documentation across cohorts, institutions, or clinicians. We aim to develop a scalable and statistically principled framework to address these limitations for ra