Research at Mizan Labs

Pioneering the Future of Healthcare with AI/ML to make patient care safer, smarter, and more accessible across borders.

Our Research Pillars

Our work is built on four foundational pillars that guide our innovation in healthcare AI.

-> AI-Powered Translation

Breaking down language barriers between patients and providers with real-time interpretation and translated documentation for smoother, safer communication.

-> Ethical & Transparent AI

Prioritizing fairness, privacy, and transparency. Patients receive clear, understandable explanations to build trust in AI-driven recommendations.

-> Personal Health Concierges

Specialized AI agents acting as personal health guides, answering questions, scheduling appointments, and providing emotional reassurance.

-> Predictive Analytics

Forecasting treatment success, complication risks, and recovery timelines to empower patients with evidence-based choices.

Selected Publications

Our commitment to advancing healthcare AI is reflected in our peer-reviewed research.

  • Explores how conversational AI can adapt to individual personalities in therapeutic settings.

    [Link]

  • Developed and validated a digital twin of a hospital using AI models.

    [Link]

  • Advocated for transparent and standardized reporting of healthcare AI models.

    [Link]

  • Investigated methods to reduce false outputs ("hallucinations") in large language models.

    [Link]

  • Predicted when patients are likely to delay treatment and the consequences of doing so.

    [Link]

  • Created models to predict emergency department load and optimize workflows.

    [Link]

  • Addressed issues of bias and equity in medical AI applications.

    [Link]

  • Developed explainable methods to identify patient subgroups in EHRs.

    [Link]

  • Explored regulatory frameworks for treating AI systems as medical devices.

    [Link]

  • Examined fairness concerns in healthcare-focused machine learning systems.

    [Link]

  • Validated a model predicting hospital readmissions.

    [Link]

  • Studied how missing data complicates explainability in AI.

    [Link]

Close-up of a young woman with curly hair, wearing glasses and hoop earrings, smiling in an indoor setting.

Join the Journey

We collaborate with healthcare innovators around the world. If you are a researcher, provider, or facilitator, we would love to hear from you.

Contact Research Team