Medical physics. Practical expertise.
radmedbd@gmail.com 01765036297

ML-Based Patient-Specific Quality Assurance (PSQA)

Predict patient-specific QA outcomes from treatment-plan and complexity features to support radiotherapy QA review, prioritization and clinical decision-making.

Evaluate the RadMed ML-Based PSQA tool, designed to support patient-specific quality assurance in advanced radiotherapy using machine-learning models trained on treatment-plan, complexity and dosimetric features. The application can assist in predicting QA-related outcomes such as gamma passing rate, dose agreement or other validated plan-quality indicators before measurement-based verification.

The tool is intended as a clinical decision-support and QA prioritization aid. It does not replace measurement-based patient-specific QA, independent dose verification, commissioning, or locally established departmental QA procedures unless the model has been prospectively validated and formally adopted within an approved clinical workflow.

Using this calculator

Upload or enter the required treatment-plan and QA-related parameters supported by the validated model. Review the model output together with the predicted QA metric, confidence or risk category, and any available explanation of influential features.

Use only models validated for the same treatment technique, machine, treatment planning system, beam model, QA device and clinical workflow for which they are intended. Predictions must be independently reviewed by a qualified medical physicist and should not be used as the sole basis for releasing a patient plan for treatment.

Version 1.0

WhatsApp