and the issue of small numbers in the primary outcome is...

Currently unlisted. Proposed listing date: 4 SEPTEMBER 2024 #

First 329 Last

Share
Profile

Follow
MightyChina

388 Posts.

12/08/17

00:31

Post #: 26453475
Share

Originally posted by TerribleTadpole ↑

"You still need to cough and get confirm whether the diagnosis are correct or not"

Yes, absolutely. Say you have data for 50 patients, all diagnosed with croup. You use 49 of those to train the algorithm. Then you get the algorithm to predict the condition of the 50th patient. You measure success or fail for the prediction. Then you take a different 49, train with those, then test the different 50th patient. Another success or fail. Once you've given each of the 50 patients a chance at prediction you can say "we got it right 84% of the time". This is the "leave-one-out" test methodology.

You'll note that the numbers for each condition are pretty low in the Australian study, which makes it hard to do larger test groups (e.g. train with 70, test with 30).

In the double-blind trial you need to have a pre-trained algorithm because you aren't given the diagnosis (so you can't train during the trial). You run the algorithm for each patient and provide the predicted condition back to the test team. The test team then get the diagnoses back from the lab. They then match your predictions to the diagnoses and let you know how you went.

Expand

and the issue of small numbers in the primary outcome is important, perhaps most important?

you may already know from your involvement early on, how many coughs from how many cases were used to create a sonic definition of pneumonia

I tried looking through the RAP thread list to find the technical talk but it escaped a screening look. Your own posts stop for me in April this year, though that is likely a functional setting on HC.

Can you link your old threads on the tech?

RAP Price at posting: 8.8¢ Sentiment: None Disclosure: Not Held
1 Upvote

0 Great analysis

Reply

Top Stories

IMU

Imugene kicks off Australian trial for blood cancer treatment

MMI

Metro Mining inks bauxite offtake contracts into 2026 with Chinese m

Trump is President Again: What Does This Mean for Crypto?

Week 45 Wrap: Combat sports usher in Trump 2.0 – or is it male insecurity?; RBA boring; Propane suggests China alive

UBI

Universal Biosensors flat despite fresh deal with US medical product distributor

FG1

Flynn Gold reaches milestone exploration target for Golden Ridge

Trump Victory Sends Bitcoin Surging Above $75K – Is $100K Next?

MKT

The ASX can overlook its Telecomm small-caps. Here’s one diversified brand with an international footprint

Palladium's the newest geopolitical hot commodity. But ASX exposure is limited

HotCopper Highlights: Your most watched and most discussed stocks this week