5,000 years of clinical observation, encoded as data. Merging Ayurvedic preventive medicine with modern data science to predict, not just treat.
The synthesis that modern medicine has been missing — formalising millennia of observational medicine into computable clinical intelligence.
A rigorously validated correlation matrix mapping the three Doshas (Vata, Pitta, Kapha) to measurable biomarkers. Built from 14 peer-reviewed studies and 2,800+ annotated patient profiles across BAMS and allopathic practices.
Genome-wide association studies (GWAS) are beginning to validate what Ayurvedic scholars described 3,000 years ago. This module maps Prakriti classifications to known SNP clusters — enabling genomically-anchored constitutional assessment.
Algorithmic generation of 12-month preventive health roadmaps. Combines Prakriti assessment, seasonal Ritucharya guidance, modern risk scores, and locally-stored clinical history into a single personalised prevention document.
Encoding the Charak Samhita — one of Ayurveda's foundational texts — into a structured, machine-readable ontology compatible with modern clinical terminologies.
The Charak Samhita contains descriptions of 341 disease conditions, 1,500+ medicinal plants, and elaborated dietary and lifestyle protocols — all encoded in Sanskrit terminology that has never been systematically mapped to modern medical ontologies. Until now.
The Medpreneur Charak Data Dictionary provides a bidirectional mapping layer: classical Sanskrit terms → ICD-11 codes, SNOMED-CT concepts, and LOINC observation identifiers.
A custom NLP pipeline using transliteration normalisation, compound word decomposition (sandhi splitting), and semantic similarity search to bridge Sanskrit Ayurvedic terminology with modern clinical vocabularies.
Linking classical Dravyaguna (Ayurvedic pharmacognosy) to modern phytochemistry. 4,200+ botanical compounds mapped to their clinical pharmacological actions, drug interactions, and evidence-grade classifications.
A proposed FHIR extension specification for encoding Ayurvedic clinical data. Making Prakriti, Vikriti, Nadi findings, and Aushadha prescriptions interoperable with global health information systems.
Precision nutrition anchored in Ayurvedic Ahara theory and validated against modern nutritional epidemiology and metabolomics research.
Generates individualised dietary protocols based on Prakriti, current Vikriti (imbalance), seasonal context, and available regional food data. Cross-validated against micronutrient databases (IFCT, USDA) for clinical accuracy.
Mapping Ayurvedic Agni types (Sama, Vishama, Tikshna, Manda) to modern gut microbiome signatures and intestinal permeability markers. Enables precise dietary and probiotic interventions informed by both ancient and contemporary clinical science.
Population distribution across 4,200 enrolled patients
Discuss Ayurvedic data science, ontology challenges, or nutritional protocol design.
The Dosha-to-biomarker correlation atlas fills a critical gap in evidence-based Ayurveda. Seeing CRP and IL-6 patterns correlate with Pitta Vikriti classifications in our own patient data has been remarkable. This is the kind of rigorous work the field needs.
The Prakriti-SNP correlation work is directionally correct. We've seen similar patterns in our own GWAS data. Would love to collaborate on extending this to include HLA haplotypes — there's a strong Kapha-HLA-DQ connection we've been tracking.
The Ahara engine output I tested on 12 patients was impressive in its cultural and regional specificity. Finally a clinical tool that doesn't assume Western dietary defaults for everyone.