I don't think the patent filing is the delay as NaNose filed a patent application in 2020, and it is possible that further patent applications have been filed in the last 18 months which would not be public yet.
The Akida/NaNose cooperation was announced in February 2021.
Aliso Viejo, California – February 24, 2021 – BrainChip Holdings Ltd (ASX:BRN), a leading provider of ultra-low power high performance artificial intelligence technology, today announced progress in testing with the NaNose (Nano Artificial Nose) where patients’ exhaled breath samples were tested for COVID-19.
NaNose Medical technology, based on the artificial nose developed at the Technion Israel Institute of Technology, has the same sensitivity to minute quantities of Volatile Organic Compounds (VOCs) as a dog’s nose. It has been tested by the Technion since 2017 to identify diseases including Parkinson’s, cancers, kidney failure, multiple sclerosis and infectious diseases such as COVID-19. NaNose Medical collected samples from 130 patients and sent nanomaterial sensor data to BrainChip’s Research Institute in Perth, Western Australia, which configured and trained its Akida™ neuromorphic processor to interpret the data using AI/ML. The system detected the instances of COVID-19 between a disease group and a healthy control group and Akida learned to recognize patterns of VOC biomarkers associated with an infection within seconds with a high level of accuracy in a minimal time frame. NaNose Medical is currently collecting samples from three primary worldwide locations and will work with BrainChip to evaluate the data
Now of course it's possible that the samples were sent to Akida at some time after the patient trials were conducted.
Nanose Medical et al filed a patent on 21 April 2020 which was published on 28 October 2021.
It includes a description of a trial of 140 participants from which 10 were excluded (leaving 130, the number mentioned in the BRN press release). The patent description refers to transmitting samples to "a processor", and provides a range of options including neural networks
WO2021214763A1DEVICE AND METHOD FOR RAPID DETECTION OF VIRUSES
Applicants TECHNION RES & DEVELOPMENT FOUND LTD [IL]; NANOSE MEDICAL LTD [IL] Inventors HAICK HOSSAM [IL]; MAROM ALBECK ORIT [IL]; SELLA TAVOR OSNAT [IL]
The invention proposes an approach utilizing novel and artificially intelligent hybrid sensor arrays with multiplexed detection capabilities for disease-specific biomarkers from the exhaled breath of a subject. The technology provides a rapid and highly accurate diagnosis in various COVID-19 infection and transmission scenarios.
... a change in the VOC profile, e.g., as compared to a control, may be determined by utilizing an algorithm such as, but not limited to, artificial neural networks, multi layer perception (MLP), generalized regression neural network (GRNN), fuzzy inference systems (FIS), self-organizing map (SOM), radial bias function (RBF), genetic algorithms (GAS), neuro-fuzzy systems (NFS), adaptive resonance theory (ART) and statistical methods including, but not limited to, principal component analysis (PCA), partial least squares (PFS), multiple linear regression (MFR), principal component regression (PCR), discriminant function analysis (DFA) including linear discriminant analysis (FDA) or cluster analysis including nearest neighbor.
Note that the description refers to "an algorithm", which suggests a CPU program rather than SoC, even though the PCT application was not filed until two months after the BRN press release. This is underlined by the fact thact that Hossam Haick's 2012 US 2012/0326092 (referenced in this patent application) also refers to artificial NNs etc.
US2012326092A1VOLATILE ORGANIC COMPOUNDS AS DIAGNOSTIC MARKERS FOR VARIOUS TYPES OF CANCER [0078] The pattern can be analyzed with a pattern recognition analyzer which utilizes various algorithms including, but not limited to, artificial neural networks, multi-layer perception (MLP), generalized regression neural network (GRNN), fuzzy inference systems (FIS), self-organizing map (SOM), radial bias function (RBF), genetic algorithms (GAS), neuro-fuzzy systems (NFS), adaptive resonance theory (ART) and statistical methods including, but not limited to, principal component analysis (PCA), partial least squares (PLS), multiple linear regression (MLR), principal component regression (PCR), discriminant function analysis (DFA) including linear discriminant analysis (LDA), and cluster analysis including nearest neighbor. Each possibility represents a separate embodiment of the invention.
BRN Price at posting:
66.0¢ Sentiment: Buy Disclosure: Held
(20min delay)