CHIRAL Bangladesh CHIRAL Bangladesh
  • About
    • About the centre
    • People
    • Collaborators
    • Support our work
    • Governance & accountability
    • Contact
  • Research
    • Research overview

    • Computational Biology
    • Public Health & Informatics
    • Bio-AI
    • Geospatial Health
  • Publications
    • All research outputs
    • Software & data
  • Training
    • Programmes
    • Learning resources
    • Events & seminars
  • News
  • Join us

Group · Predictive

Bio-AI

Machine learning for biomedicine, built for deployment in clinics that cannot absorb a black box. A model we cannot explain to a clinician is a model we do not consider finished.

Predictive health analytics

Risk prediction and patient stratification from multi-modal electronic health records — early deterioration, readmission, and progression — validated against the shift between the data a model was trained on and the population it will meet.

Biomedical image analysis

Convolutional networks and vision transformers applied to radiographic, histopathological and neurological imaging for computer-aided diagnosis, with careful attention to how little labelled data is available locally.

Interpretability

Feature attribution, saliency and counterfactual explanation, treated as a requirement rather than an appendix. Where a model cannot be made interpretable, we report that as a limitation on its use.

Biomarker discovery pipelines

Ensemble learning and feature selection to isolate diagnostic and prognostic signatures from omics data, with the selection stability reported alongside the performance.

Selected outputs

To be listed

Group Leader
To be listed
Methods
Supervised & ensemble learning · CNNs and vision transformers · survival models · SHAP and attribution · calibration
Stack
Python · PyTorch · scikit-learn · MONAI · Weights & Biases
Practice
External validation before publication · reported calibration, not accuracy alone · model cards for released models
Open to
Students from computer science and statistics, and clinicians with a labelled dataset.

Join this group

 

CHIRAL Bangladesh

কাইরাল বাংলাদেশ

Centre for Health Innovation, Research, Action and Learning. Computational biology, Bio-AI and population health research, based in Dhaka.

Research

  • Overview
  • Computational Biology
  • Public Health & Informatics
  • Bio-AI
  • Geospatial Health

Outputs

  • Publications
  • Software & data
  • Training programmes
  • Learning resources
  • Events

Centre

  • About
  • People
  • Collaborators
  • Join us
  • Support us
  • Governance
  • Contact

Azimpur, Dhaka 1205, Bangladesh · chiralbd@gmail.com © 2025 CHIRAL Bangladesh · Content CC BY 4.0 · Code MIT