Ambient Clinical
Documentation System

Revolutionizing Omani healthcare with AI-powered Arabic medical transcription. Secure, local processing that automates documentation to restore the doctor-patient connection.

Read More Contact Us
2-3 Hours
Daily documentation time per clinician
40-50%
Time taken away from patient care
15-20 min
Manual SOAP note writing per patient
No Solution
Existing systems lack Arabic support

The Documentation Burden

Clinicians spend excessive time on manual documentation, reducing patient interaction and contributing to burnout. Current cloud-based solutions often compromise privacy or fail to address the specific linguistic needs of the region.

The Local AI Solution

An automated ambient documentation system specifically designed for Arabic medical conversations and Omani dialect, running entirely on local hardware.

  • 100% Local Processing - No Cloud Data Transfer
  • Fine-tuned for Omani Medical Terminology
  • Continuous Learning from Clinician Feedback
Privacy-First Architecture

Secure Local Intelligence

Our system runs on local servers, ensuring patient data never leaves the hospital. It learns and adapts from user corrections to improve accuracy over time.

Adaptive Learning

Continuous Improvement

The system gets smarter with every use, learning from doctor's edits to better understand local dialect and specific medical contexts.

  • Learns from user feedback
  • Adapts to individual speaking styles

How It Works

Watch the AI transform spoken Arabic into structured clinical notes

Record
Local Processing
Translation
Review & Learn
Medical Translation

Arabic Context

المريض يشتكي من ألم حاد في الجهة اليسرى للصدر مع انتشار للكتف.

ضيق التنفس الجهدية (Dyspnea on exertion) ملاحظ بعد صعود الدرج.

English Output

Patient complains of acute left-sided chest pain with radiation to the shoulder.

Exertional dyspnea noted after climbing stairs, requiring rest.

Research Team

A collaborative effort driving innovation in Omani healthcare.

Dr. Abdullah M. Al Alawi
Dr. Abdullah M. Al Alawi
Principal Investigator
Senior Consultant in General Internal Medicine and Program Director of the Internal Medicine Residency at OMSB. An active clinician–researcher focused on hospital medicine, patient outcomes, and AI in medicine.
Dr. Mohamed Najeeb Al-Rawahi
Dr. Mohamed Najeeb Al-Rawahi
Cardiac Electrophysiologist
A cardiac electrophysiologist at Sultan Qaboos University Hospital and the National Heart Center. Interests include AI in cardiovascular care, arrhythmia detection, and clinical decision support.
Dr. Salim Al-Busaidi
Dr. Salim Al-Busaidi
Specialist Physician, Internal Medicine
Specialist Physician in Internal Medicine with interests in clinical research, medical education, and digital health innovation.
Dr. Zubaida Al Falahi
Dr. Zubaida Al Falahi
Acute Medicine Professional
Medical professional in acute medicine with an interest in clinical excellence, medical education, and service development.
Dr. Muhammad Shoaib
Dr. Muhammad Shoaib
Consultant, General Internal Medicine
Consultant at Sultan Qaboos University Hospital. Interests span hospital medicine, lipidology, preventive cardiovascular care, and AI-based risk prediction.
Dr. Tamadhir Al-Mahrouqi
Dr. Tamadhir Al-Mahrouqi
Psychiatry Physician
Psychiatry physician at SQUH, engaged in clinical care, research, and medical education. Focus on digital mental health innovations and AI integration in psychiatric practice.
Dr. Kawthar Al Lawati
Dr. Kawthar Al Lawati
Internal Medicine Resident
Third year Internal Medicine Resident at Oman Medical Specialty Board (OMSB). Keen about the world of medical research.
HK
Dr. Hour Al Kaabi
Internal Medicine Specialist
Internal Medicine Specialist at MCMSS, with a focus on leadership, medical education, research, and AI integration in medicine.
Dr. Noor Alkaabi
Dr. Noor Alkaabi
Internal Medicine Resident
Internal Medicine Resident at OMSB, graduate of SQU, interested in medical research and AI in healthcare.
Mohammed Al Habsi
Mohammed Al Habsi
Medical Student & Researcher
Medical student at Sultan Qaboos University, researcher with interests in cardiology, AI, and population-based clinical studies.
AB
Afra Albadi
AI Engineer
AI student at GUtech experienced in full-stack development, machine learning, and hardware configuration. Skilled in building RAG pipelines, deploying local LLMs, and developing applications using Python and React.

Project Roadmap

A comprehensive 24-month plan to transform clinical documentation.

1

Setup & Data

System installation, IRB approval, and initial data collection. Training 50-100 hours of Omani medical conversations.

2

Multi-User Platform

Collaborative web system with continuous self-training capabilities. Clinicians review outputs to fine-tune models monthly.

3

Expansion

Deploy to specialty clinics, ward rounds, and other hospitals. Testing hardware options from high-end GPUs to CPU-only servers.

4

Testing & Validation

Comprehensive accuracy testing, clinical validation, and usability assessment. Comparing AI vs manual SOAP notes.