Questions re cardiac imaging, VPT, and possible competition
Ok-so while I haven’t taken the plunge to buy yet, there is no question, my interest is raised in the area of artificial intelligence and cardiac imaging, since I was recently advised of this stock, when ithe VPT was recommended on a different board in stock house.
When I first read about this it seemed like a great opportunity.
BUT I have learned to check my enthusiasm and research
Still Health care IPOs are hot right now in Canada , and AI based companies are getting attention esp if COVID is linked.
But I was thinking-why has this stock-And this software not discovered?
After all its market cap is valued at only ~7million
Is it the lack of revenues?
Is there something else I am missing ?
I get it that many here are interested in the story, and not the financial facts, but what is the story -relating to the future of cardiac imaging? (and rational discussion is considered bashing)
Still I think AI and imaging is a massive opportunity, and the question is how to profit, and whether VPT can execute, given the story has evolved over about 10 years with minimal sales,imo, as determined from recent financials.
(Was the recent placement in London a sale or for promotion/KOL?)
(Also given my recent posts on the serious solvency concerns , where there is a stated going concern, based on the financials, and based on ability to place machines and get sales revenue to date).
Sorting through the literature this weekend trying to see if while VPT waits for sales, if anyone could eat their lunch.
Turns out there are other cardiac imaging programs-including FDA approvals
https://www.businesswire.com/news/home/20180619005552/en/Bay-Labs%E2%80%99-EchoMD-AutoEF-Software-Receives-FDA
Other groups even here:
https://www.theglobeandmail.com/business/article-toronto-health-tech-firm-think-research-goes-public-as-value-nears-180/
But there appears, in my view, to be many others actively looking into some of these areas :
This paper looks at 3D AI, using a “HeartModelA·I·” software package ,but seems to directly compete with VPT, except of course 2D vs 3D
“3D echocardiographic automated analysis can be performed thanks to HeartModelA·I·, a software package that uses a model-based algorithm. The algorithm that is integrated in the software is capable of automatically calculate the following in few seconds: (i) the volumes of the left chambers (atrium and ventricle), (ii) the systolic flow, and (iii) the ejection fraction of the LV from the data acquired with 3D echocardiographic techniques” (https://www.ultrasound-heartmodel.it).
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7336209/
This high impact article published in Nature by Dr. Ouyang from Stanford and colleagues uses a video-based AI for assessment of cardiac function(relevant to claims of ejection fraction and potentially cardio toxic effects of chemotherapy And possibly COVID story:
…”we present a video-based deep learning algorithm—EchoNet-Dynamic—that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice similarity coefficient of 0.92, predicts ejection fraction with a mean absolute error of 4.1% and reliably classifies heart failure with reduced ejection fraction (area under the curve of 0.97” https://www.nature.com/articles/s41586-020-2145-8
In addition, a group from Beijing university, has a article in press (scheduled for Jan 2021) , that uses deep learning to segment cardiac structures:
“The proposed PLANet was extensively evaluated on the dataset of cardiac acquisitions for multi-structure ultrasound segmentation (CAMUS) and sub-EchoNet-Dynamic, which are two large-scale and public 2D echocardiography datasets. The experimental results show that PLANet performs better than traditional and deep learning-based segmentation methods on geometrical and clinical metrics. Moreover, PLANet can complete the segmentation of heart structures in 2D echocardiography in real time, indicating a potential to assist cardiologists accurately and efficiently.” Source: https://www.sciencedirect.com/science/article/pii/S1361841520302371?via%3Dihub
How does this compare to Ventripoints system?
What do others know of the key scientific differences of VPT vis a vis these new AI initiatives?
How does this differ (especially regarding accuracy (ie ICC using VPTs system-which are excellent, IMV, according to the Uof A study with 0.98 for LVEF, for example )
So asking questions, and of course-I am not an expert(whom you should talk with) in this area, nor should anyone buy/sell based on what they read here(especially anything I say).
So my 2 cents-which are probably worthless, as I am the board idiot I was told.