Global Health · Open Source · Clinical AI

Evidence based Clinical AI

ClinicDx is an offline Clinical AI that integrates scribe, clinical decision support and imaging analysis within OpenMRS.

Runs locally OpenMRS native integration Works without internet

One OpenMRS module. Four features.
Every critical point of care covered.

ClinicDx plugs directly into the OpenMRS workflow clinicians already use, adding AI intelligence at the moment of decision, without internet, without cloud dependency.

Our Approach

Built to a Clinical Standard

ClinicDx is not a general-purpose AI adapted for healthcare. It is designed from the ground up around the constraints and obligations of clinical practice.

  • Interoperable by Design

    Built on FHIR R4 and REST API standards. ClinicDx connects to existing health information infrastructure without proprietary connectors, enabling integration with national EMRs and referral networks.

  • Adapts to Clinical Context

    Differential rankings, drug guidance, and clinical protocols are configurable to local disease burden, formulary, and care level. ClinicDx does not impose a single global model on diverse clinical environments.

  • Fully Open Source

    The complete codebase is publicly available, auditable, and free to deploy. Ministries of Health and implementing partners retain full ownership with no licensing fees and no vendor dependency.

The Problem

Where Healthcare Falls Short

Clinicians in the developing world face compounding challenges at every point of care delivery.

Documentation

Manual EMR entry is slow, error-prone, and often happens hours after care, losing clinical nuance.

Knowledge

Clinical officers make life-or-death decisions alone, with no specialist and no protocol library.

Lab

Paper lab results don't get digitized, interpreted in context, or flagged for critical values.

Imaging

DICOM files go unread. 3.6 radiologists per million means most images are never reviewed.

4 billion people in the developing world
1 : 50,000 clinician-to-patient ratio
3% of global clinical workforce
25% global disease burden
Features

Four integrated intelligence features

Click any feature to see its capabilities and a live simulation.

How It Works

Built into OpenMRS. No new app, no new login.

Work in OpenMRS as usual

ClinicDx is an OpenMRS module, installed directly into the existing deployment. Clinicians never leave the interface they already use.

Select a ClinicDx feature

From within the patient encounter, the clinician selects a feature: decision support, lab capture, imaging review, or voice documentation. Patient context is read automatically.

Output writes back to OpenMRS

Structured results appear in seconds and are written back into the OpenMRS record. Fully offline. No data leaves the facility.

Outcomes

Measured impact for clinicians and health systems

0%

Reduction in documentation time

Multilingual phrase-based scribe converts spoken input to structured SOAP notes in seconds.

0%

Data sovereignty maintained

Patient data never leaves the facility. No cloud, no external API, no privacy exposure.

0%

Reduction in diagnostic uncertainty

Structured differentials and discriminating features guide every clinical assessment.

Who It’s For

Purpose-built for every layer of care delivery

Clinical Officers & Nurses

  • Second opinion at point of care
  • Differential diagnosis support
  • Drug dosing & safety guidance
  • Documentation in native language

Physicians & Medical Officers

  • Complex case decision support
  • Lab & imaging interpretation
  • Referral decision support
  • Multilingual scribe workflow

NGOs & Aid Organizations

  • Rapid deploy on commodity hardware
  • No internet dependency
  • Consistent evidence-based protocols
  • Multi-site rollout ready

Ministries of Health

  • National OpenMRS integration
  • Anonymized population analytics
  • WHO guideline alignment
  • Scalable, modular rollout

Patient data never leaves the facility.

No cloud. No external API. No privacy exposure. ClinicDx operates entirely within the four walls of your facility, clinical intelligence without surveillance.

On-device inference

All AI computation happens locally on facility hardware. No data ever leaves the machine.

OpenMRS native

Patient data stays inside the national health system’s own infrastructure, not a third-party cloud.

WHO alignment

Structured outputs and audit trails support national digital health governance frameworks.

FAQ

Common questions from deployment teams

No. ClinicDx is designed from the ground up to operate fully offline. All AI inference runs on local hardware at the facility. There is no dependency on external servers, cloud APIs, or internet connectivity of any kind.

ClinicDx runs on commodity hardware: a standard workstation or rugged laptop with a modern CPU. No GPU is required for CDS and scribe functionality. Imaging analysis benefits from a mid-range discrete GPU but can operate in CPU-only mode.

ClinicDx is an OpenMRS module, installed directly into OpenMRS 3.x. It reads structured patient data from the active encounter and writes outputs back into the record, maintaining all data within the national health information system.

The scribe feature supports Swahili, Amharic, French, Hausa, and English out of the box. CDS outputs are available in English and French, with localization roadmap prioritized by deployment region.

Completely. Patient data never leaves the facility. ClinicDx performs all AI computation locally, with no external API calls, no cloud uploads, and no telemetry. Outputs are structured and auditable, meeting WHO and national health data governance standards.

Yes. The CDS knowledge base is curated and aligned to WHO and MSF clinical protocols, including WHO Essential Medicines List, WHO Malaria Guidelines, and IMCI protocols. Every CDS output includes citations so clinicians can verify the evidence basis.

Help us bring specialist-level care to facilities that have never had one.

Pilot ClinicDx in your facilities to reduce diagnostic uncertainty, preserve data sovereignty, and return clinician time to patient care.