QML/QiML for Medical Regulatory Agency Review PDF + Discussion 11/9/23.

'Simulator specific algorithms' in a current survey are the leading aspect that colleagues would like to see developed the most by the QML/QiML industry. Further implementation would mark a shift towards increasing development of practical algorithm architectures for potential near-term improvements or new utilities for Medical. 1

A potential QML/QiML use case would be using a better non-gate based quantum algorithm architecture for validation accuracy improvements. New utility(s) may also be available using quantum libraries that are not implemented with standard CNNs or Transformers deep learning due to the inherent processing differences of medical data with quantum mechanics. In addition, End-to-end differentiability featuring both trainable classical parameters and trainable quantum parameters across several models should be an obtainable near-term goal based on the R&D progress in the last 4 years.

'QML/QiML' is the proposed term at this current stage in industry - As existing classical processing methods already use the 'QML' term, and 'QiML' is less known but refers to quantum machine learning implemented on classical hardware. Related resources are available through GitHub.

Lastly, Thank you PennyLane, Qiskit, and PyTorch for the continued innovations to improve QiML workflows for important healthcare applications.