Subventions et des contributions :

Titre :
Medical Diagnosis using Raman Spectrographs and Machine Learning
Numéro de l’entente :
EGP
Valeur d'entente :
25 000,00 $
Date d'entente :
7 mars 2018 -
Organisation :
Conseil de recherches en sciences naturelles et en génie du Canada
Location :
Nouvelle-Écosse, Autre, CA
Numéro de référence :
GC-2017-Q4-01077
Type d'entente :
subvention
Type de rapport :
Subventions et des contributions
Informations supplémentaires :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier (2017-2018 à 2018-2019).

Nom légal du bénéficiaire :
Lingras, Pawan (Saint Mary’s University)
Programme :
Subventions d'engagement partenarial pour les universités
But du programme :

MedMira is the developer and owner of Rapid Vertical Flow (RVF) Technology. The Company's rapid testx000D
applications built on RVF Technology provide hospitals, labs, clinics and individuals with instant diagnosis forx000D
diseases such as HIV and hepatitis C in just three easy steps. Together with a Tier II Canada Research Chair,x000D
Dr. Christa Brosseau, Medmira has identified rules based on sharpest peaks and preceding troughs in Ramanx000D
spectrographs of surrogate blood samples. Data analysis via application of these rules can accuratelyx000D
distinguish positive samples from negative samples. Such an analysis requires an experienced chemist tox000D
process the results from a Raman spectrometer; up to half an hour. The proposed project plans to automate thex000D
data processing and explore the possibility of using machine learning to automatically generate the rules thatx000D
were identified by the expert chemists. The machine learning approach is especially important for extendingx000D
test from laboratory generated surrogate samples to complex human blood samples. Unlike the laboratoryx000D
generated surrogate samples, Raman spectrographs of human blood samples can vary significantly from personx000D
to person. The heterogeneous blood samples may have additional peaks and troughs which could complicatex000D
interpretation. More sophisticated machine learning techniques are more likely to replicate the diagnosticx000D
process facilitated by experts. The outputs of the project will enable MedMira to initiate development of toolsx000D
allowing non-experts to obtain diagnostics results in non-traditional health care settings without sacrificingx000D
quality.