We aim to support monitoring of the current guidelines and scientific evidence in the management of Age-Related Macular Degeneration (AMD) in order to augment retinal specialists to develop a clinically oriented and consensual protocol for therapeutic approaches for AMD. First, we are engineering an ontology for AMD retinal condition using information from literature, related medical ontologies and domain knowledge from ophthalmologists. Second, we augment the knowledge engineer capabilities to populate and enrich the ontology using structured knowledge extracted from medical literature with the GPT-3 language model. Third, we perform reasoning to signal to the ophthalmologist diferences or inconsistencies among diferent clinical studies, protocols or therapeutic approaches.
∃ℎ. ≥ 125 ∃ℎ. ≥ 63 ⊓ ∃ℎ. ≥ 63 , respectively ≡ ⊓ ∃ℎ. ≤ 63 , ≡ ⊓ One issue is that these axioms do not always correspond to clinical practice. For instance an eye with a drusen measured by an AI algorithm at 124μm (i.e. slightly below the 125μm limit) is classified according to the definition as a
ophthalmologist still treats the disease as an , and hence an
, but the . To map the clinical practice we are also considering axioms in Fuzzy Description Logic. The AMD ontology reuses concepts and relations from BioVerbNet (https://github.com/cambridgeltl/bioverbnet) and medical ontologies, e.g.: (i) ⊑ ℎ ℎ ⊑ ⊑ ℎ ℎ ⊑ ℎ ⊑ ⊑
Second, we enrich the AMD ontology with structured data automatically extracted from
scientific studies [
Epidemiological classification (Wisconsin grading) ≡ ⊓ ∃ℎ.( ⊔ ⊔
) ≡ ⊔ ℎ ≡ ≡ ≡ ≡ ∀ℎ.⊥ ⊓ ∀ℎ.¬ ∀ℎ. ⊓ ∀ℎ.¬ ∀ℎ.¬ ⊔ ∀ℎ.¬ ∃ℎ.¬ ⊔ (= 1)ℎ.
Extracting structured information on morphological features using language models (i.e. GPT3)
Mowatt et al. (2014)
Association with disease activity unlikely to be cost-efective for diagnosis/monitoring inferior prognostic biomarker for guiding retreatment negatively associated with VA associated with superior visual benefits and a lower rate of progression towards atrophy blog-cacm/267674-ais-jurassic-park-moment/fulltext), we are aware of the risks that such models to propagate misinformation. Our stance is that it is easier for the human agent to verify the information in Table 2 and to annotate it with provenance data, instead of manually collecting it from literature. From the technical perspective, the burden is how to feed the GPT-3 with relevant ”prompts” (e.g. based on BioVerbNet) to get relevant information. In line with C. Baquero (https://bit.ly/3ElW1J7, prompt design was critical for querying of such language models. The job of Prompt Designer may become relevant in populating ontologies.
Third, we apply reasoning to signal diferences and inconsistencies among the knowledge within the ontology. These diferences reflect the current understanding of the AMD disease: quantitative vs. qualitative fluid assessments, intraretinal fluid vs. subretinal fluid (SRF), exudative vs. nonexudtive fluid. For instance, for SRF both negative and positive but also no-association have been reported [2]. Moreover, heterogeneity of therapeutic approaches has been increased in the context of personalised care. This heterogeneity rises the question of inconsistent information, detected in our approach by the Racer reasoning tool.