Computational approaches to support comparative analysis of multiparametric tests: Modelling versus Training

Research output: Contribution to journalArticlepeer-review

Authors

  • OPTIMA Trial Management Group

External organisations

  • Transformative Pathology, Ontario Institute for Cancer Research
  • University of Toronto
  • Edinburgh Cancer Research Centre
  • Tom Baker Cancer Centre
  • Warwick Medical School
  • UCL
  • Diagnostic Development
  • Beatson West Of Scotland Cancer Centre
  • Bristol Medical School
  • University of Cambridge
  • University College London Hospitals NHS Foundation Trust
  • University Hospitals Birmingham NHS Trust
  • Academic Unit of Health Economics
  • University of Leeds
  • Imperial College Healthcare NHS Trust
  • Mount Vernon Hospital
  • Department of Emergency Medicine
  • University of Alberta
  • Independent Cancer Patients Voice
  • King's College London
  • University Hospitals Coventry and Warwickshire NHS Trust

Abstract

Multiparametric assays for risk stratification are widely used in the management of breast cancer, with applications being developed for a number of other cancer settings. Recent data from multiple sources suggests that different tests may provide different risk estimates at the individual patient level. There is an increasing need for robust methods to support cost effective comparisons of test performance in multiple settings. The derivation of similar risk classifications using genes comprising the following multi-parametric tests Oncotype DX® (Genomic Health.), Prosigna™ (NanoString Technologies, Inc.), MammaPrint® (Agendia Inc.) was performed using different computational approaches. Results were compared to the actual test results. Two widely used approaches were applied, firstly computational “modelling” of test results using published algorithms and secondly a “training” approach which used reference results from the commercially supplied tests. We demonstrate the potential for errors to arise when using a “modelling” approach without reference to real world test results. Simultaneously we show that a “training” approach can provide a highly cost-effective solution to the development of real-world comparisons between different multigene signatures. Comparisons between existing multiparametric tests is challenging, and evidence on discordance between tests in risk stratification presents further dilemmas. We present an approach, modelled in breast cancer, which can provide health care providers and researchers with the potential to perform robust and meaningful comparisons between multigene tests in a cost-effective manner. We demonstrate that whilst viable estimates of gene signatures can be derived from modelling approaches, in our study using a training approach allowed a close approximation to true signature results.

Details

Original languageEnglish
Article numbere0238593
JournalPLoS ONE
Volume15
Issue number9 September
Publication statusPublished - 3 Sep 2020