Background: Diagnostic disparities significantly impact health outcomes, with various factors influencing differential access and treatment across communities. This paper explores the complex landscape of diagnosis and of variable diagnostic journeys, focusing on the multifaceted nature of diagnostic inequities and proposing a socioecological model to understand and address these disparities. Methods: The authors employed an interdisciplinary approach, synthesising insights from their respective knowledge domains. Through iterative discussions, visual diagramming and narrative development, a new framework was constructed to address the complexity of diagnostic inequities. Results: The ‘diagnostic environment’ model was developed, conceptualising diagnosis beyond the biomedical process to include three levels of influence: atmospheric (broad, pervasive societal factors), surface (direct healthcare interactions) and subterranean (underlying, often invisible societal norms and biases). This model integrates process, social phenomena and multilevel influences to more comprehensively address diagnostic disparities. Two additional frameworks: diagnostic journeys within this environment and issue constellations guiding navigation and intervention were developed. Conclusions: Diagnostic processes are influenced by a range of factors from individual to systemic levels, often leading to significant disparities in health outcomes. The proposed model offers a framework for understanding these disparities and suggests targeted interventions to address them. By integrating diverse perspectives and focusing on multilevel influences, the framework aims to improve diagnostic equity. Implications: This study highlights the need for a more holistic approach to diagnosis, acknowledging the complex interplay of factors that contribute to diagnostic disparities. The socioecological model provides a basis for future research and policy interventions aimed at reducing these disparities and improving overall diagnostic accuracy and equity.
Background: Artificial intelligence in medicine has largely relied on supervised training of disease-specific models, limiting scalability in conditions where labeled data are scarce. Large language models (LLMs), which encode broad medical knowledge through large-scale pretraining, offer an alternative paradigm in which structured physiological measurements can be interpreted directly without task-specific model training. Objective: To evaluate whether smartphone-derived ocular motor biomarkers can be translated into clinically meaningful probabilistic assessments of Huntington’s disease (HD) using general-purpose LLMs operating as inference engines. Methods: In this prospective proof-of-concept study, 26 participants (13 with genetically confirmed HD and 13 age-matched controls) completed a standardized ocular motor assessment using a custom smartphone application. Quantitative eye-movement metrics were validated against expert neurologist ratings. Structured physiological features were then provided to four general-purpose LLMs without task-specific training or diagnostic labels, and the models generated an AI-Assigned HD Probability Score (HAIPS). Discriminative performance and associations with clinical severity measures were evaluated. Results: Smartphone-derived ocular motor metrics showed strong agreement with clinician assessments (Spearman ρ = 0.76–0.95; all p < 0.001), confirming preservation of clinically meaningful physiological signals. LLM-derived HAIPS distinguished HD from controls with high accuracy (AUC 0.879–0.944), with no significant differences across models. Discrimination was statistically equivalent to a supervised logistic regression model trained on the same features. HAIPS correlated strongly with established measures of disease severity, including cognitive (MoCA, ρ = −0.86), functional (TFC, ρ = −0.74), and motor impairment (UHDRS, ρ = 0.85) (all p ≤ 0.003). Conclusions: Structured ocular motor biomarkers acquired using a consumer smartphone can be translated into clinically meaningful probabilistic assessments of HD by general-purpose LLMs without disease-specific model training. These findings support a framework in which physiologically grounded digital biomarkers are coupled with general-purpose inference models, potentially enabling scalable assessment in rare neurological diseases where labeled data are limited.