Intent preserved
The standard concept still carries what the source recorded.
Population analytics platform
Preserving the DNA of Clinical Intent in OMOP
IPI (Intelligent Phenotype Index) is LOFT's population analytics platform. It enhances the OMOP (Observational Medical Outcomes Partnership) common data model (CDM) repositories so diagnoses keep the clinical intent clinicians documented, and cohorts built on them can distinguish more specific patient populations.
Prostate cancer · ICD-10 C61
One diagnosis code can hide distinct clinical populations
- 1Default mapping broad SNOMED resultPrimary malignant neoplasm of prostate · 26,630 patients in this row
- 57Enhanced mapping SNOMED conceptsRecurrence, histology, hormone response and grade · More specific standard concepts
- 146IPI-IMO Health concept layer Full clinical intent preservedMetastatic site, disease state and management context · Finer meaning for cohort definition
Mapped is not the same as AI-ready
In a common OMOP mapping path, the clinician's diagnosis term passes through ICD-10 before reaching SNOMED. This can discard subtype and other clinical detail. A high mapping-coverage score does not show whether that detail survived, and downstream analysis cannot reconstruct it from the broader code alone.
How it works
- Step 1
Clinical intent in
IMO Health interface terminology is loaded into the OHDSI OMOP stack, consumed the same way licensed vocabularies are today.
- Step 2
Enhanced ETL
A two-pass mapping keeps the clinician's documented concept, routes it to the right OMOP domain, and falls back to ICD only when needed.
- Step 3
Nothing else changes
Same CDM, same ATLAS, same phenotype queries and network federation.
What AI-ready means
Cohorts retrievable
Diagnosis detail supports queries for specific populations rather than broader categories.
Post-coordination intact
Combined diagnoses are not silently split apart.
Journey preserved
Clinical events remain linked across the patient record over time.
Evidence In a pilot comparing two OMOP instances built from the same source data, the enhanced instance produced about 3.7 times as many distinct SNOMED condition concepts, and recovered rare diagnoses the standard pipeline could not distinguish.
Standard vs Enhanced OMOP
What is lost, or invented, on the ICD-10 hop
Results from a small de-identified subset of 1,387 patients.
| What the clinician recorded | ICD-10 hop | Standard concept that results | What is lost | Patients affected |
|---|---|---|---|---|
| Diastolic hypertensionDiscarded | I10 Essential (primary) hypertension | Essential hypertension | The subtype. I10 has no diastolic, systolic or borderline distinction, so a diastolic-hypertension query returns no one. | 222 of 664 hypertensives (0 on Standard) |
| Renal impairment / renal insufficiencyDiscarded | N28.9 Disorder of kidney, unspecified | Kidney disease (not a descendant of Renal impairment) | The clinical meaning. The concept lands outside the branch a nephrology query looks in. | 111 on Enhanced vs 16 on Standard |
| Congestive heart failureDiscarded | I50.9 Heart failure, unspecified | Heart failure | The specific diagnosis. The concept sits above Congestive heart failure, so a CHF cohort misses almost everyone. | 98 on Enhanced vs 4 on Standard |
| Loss of appetiteInvented | R63.0 Anorexia | Anorexia nervosa | Accuracy in the other direction: the mapping asserts a psychiatric diagnosis the patient almost certainly does not have. | 62 patients mislabelled |
| Sleep apnea (unspecified)Invented | G47.30 Sleep apnea, unspecified | Central sleep apnea syndrome | The common form. Most of these patients have obstructive sleep apnea; the mapping names the rare one. | 65 patients mislabelled |