Proximate-Cause Disease Ontology Engine
A clinical decision-support layer that organizes diseases into a strict hierarchical taxonomy (class → order → genus → species) keyed to their proximate biological causes, automatically surfacing mechanism-matched treatments rather than symptom-matched ones.
Concept
Darwin's Zoonomia demonstrates that diseases can be sorted into "natural classes" by their proximate causes, then subdivided into orders, genera, and species — a Linnaean hierarchy applied to pathology. A modern software service could encode this logic as a computable ontology: clinicians or algorithms input a mechanistic cause profile (e.g., inflammatory mediator excess, ion-channel dysfunction) and the engine traverses the taxonomy to return the matching disease class with associated cure methods. Unlike ICD codes, which are primarily administrative, this ontology would be etiologically organized, making treatment selection structurally explicit.
Why now
Paper [0] shows that a full catalogue of diseases distributed by proximate causes — with explicit linkage to methods of cure — was feasible even in the 18th century using purely conceptual tools. Modern biomedical knowledge graphs (e.g., UniProt, DisGeNET) now supply the mechanistic data needed to populate such a taxonomy computationally, making machine-readable proximate-cause classification achievable at scale for the first time.
AI assessment
A historically-framed disease ontology built on a single 18th-century text with no modern research corroboration, entering a space already occupied by mature etiological ontologies (SNOMED-CT, HPO, Disease Ontology) and CDS platforms, leaving little clear differentiation or investable wedge.
- Evidence strength 1/5
- The sole cited source is Darwin's Zoonomia (~1796) — a single, 200-year-old conceptual text — and no modern peer-reviewed papers are cited to validate the proximate-cause classification approach or its clinical utility.
- Market pull 3/5
- Clinical decision support is a real, multi-billion-dollar market, but naming Epic, NLM, and Babylon Health as co-equal targets signals the team has not segmented the market or identified a specific beachhead customer.
- Novelty & moat 2/5
- Etiological disease classification is not novel — SNOMED-CT, Human Phenotype Ontology, OMIM, and DisGeNET already encode mechanistic and causal disease relationships computationally, making the core claim of doing this 'for the first time' factually dubious.
- Feasibility 2/5
- Building a computable ontology is technically tractable, but diseases routinely have disputed, multi-factorial proximate causes, and EHR integration with Epic requires regulatory compliance and contracting cycles that dwarf early-stage capacity.
- Wedge clarity 2/5
- The proposed differentiation from ICD codes is a straw man — existing CDS tools already go far beyond administrative codes — and there is no articulated reason why an incumbent like NLM or Epic could not replicate this atop knowledge graphs they already license.
- Simplicity / focus 3/5
- The core product (a traversable causal-taxonomy engine) is reasonably scoped and not a sprawling platform, but the conflation of SaaS API, ontology standard, and EHR plugin into one pitch blurs the actual deliverable.
Scored by AI against a fixed rubric (evidence, market, novelty, feasibility, wedge, simplicity). A prior estimate to compare ideas before real-world signal arrives.
Persona discussion
AI personas trained on real people's expertise debate this idea as it evolves.
View the discussion →Act on this idea
Ideas only matter if someone runs with them. Your message goes straight to the founder's inbox — nothing is stored on our servers.
Who benefits
- Epic Systemscompany
Epic's clinical decision-support modules sit inside EHR workflows; an etiology-first disease taxonomy could be licensed as an ontology layer that improves treatment recommendation accuracy inside their existing physician-facing tools.
- National Library of Medicineorganization
NLM maintains MeSH and SNOMED CT; a proximate-cause ontology derived from historical and modern sources would complement and enrich those controlled vocabularies for research indexing.
- Babylon Healthcompany
Babylon's AI triage product benefits directly from a mechanistic disease classification that maps symptoms to root causes, reducing misclassification in automated diagnostic pathways.
Research it builds on
- Zoonomia, or, The Laws of Organic LifeErasmus Darwin · 2024 · 463 citationsAll ideas from this paper →
Related ideas
- Disease Taxonomy Mapping Tool
A digital classification system that organizes diseases by proximate cause and species to streamline the identification of targeted cures.
same research - Standardized Disease Taxonomy Database
A structured digital reference system that categorizes diseases by proximate cause, genus, and species to standardize medical diagnosis and treatment mapping.
same research - Materia Medica Interaction Registry
A specialized database mapping specific medicinal substances to their physiological operations and therapeutic outcomes.
same research - Taxonomy-Based Diagnostic Tool
A structured medical classification system that maps diseases to their proximate causes to streamline the identification of specific cures.
same research - Chronic-Disease Patient Digital Twin for Personalized Treatment Planning
A clinical AI service that builds a continuously updated virtual model of an individual patient with a chronic condition — diabetes, heart failure, or respiratory disease — enabling clinicians to simulate treatment adjustments before prescribing them.
- Hospital & Commercial Building HVAC Scenario Optimizer
A scenario-testing SaaS service that runs ontology-based digital twin simulations of a building's HVAC system, letting facility managers compare energy cost vs. occupant comfort trade-offs before making any physical changes.