Data of perfect quality means, in my opinion, data and their complete context. A diagnosis by a nurse is not the same as one by a patiente, or strting intern, or one MD with 20m years experience. Just mentioning one example.
Gerard Freriks +31 620347088 gf...@luna.nl Kattensingel 20 2801 CA Gouda the Netherlands > On 30 Jun 2018, at 17:16, Philippe Ameline <philippe.amel...@free.fr> wrote: > > Le 27/06/2018 à 22:26, Bert Verhees a écrit : > >> On 27-06-18 16:43, Philippe Ameline wrote: >>> 1) you can find a bunch of practitioners that agree on working extra >>> hours to comment a big bunch of images, or >> >> Did I tell you about the plant-app? I believe I did. 700.000 pictures >> are reviewed, often by volunteers. >> >> The app recognizes 16000 plants. Important is how you do it, and that >> it does not cost effort by the volunteers, for example in relation to >> what they do anyway. >> >> https://plantnet.org/ <https://plantnet.org/> >> >> It is a French product. > > Dear Bert, > > The plant-app was the subject of your initial post. > > The math in support of deep learning are being studied. To make it > short, it remains somewhat mysterious since such classification > algorithms "should not work", but actually, they do ;-) > > From an article I just read, such NP complete algorithms are similar to > finding a needle in a hay stack and shouldn't provide valuable > answers... unless the conditions (large enough needle, correctly ordered > stack) make the problem handy. > > To sum it up, data quality (signal over noise ratio) is paramount. In > the plant-app you mentioned, adding a certain level of fuzziness > (improperly labeling images or adding images of objects that are not > plants) could probably make the whole app plainly crappy. > > Just to say that building a deep learning system starts from making > certain that the data it will be fed with are of proper quality. This is > usually not the case in medicine, largely because IT is considered a > back office concept and there is seldom the kind of feedback loop that > could lead to having errors fixed. > > My point is that you can perfectly (but with considerable efforts) > organize a trained network of practitioners to feed a "data lake" in > order to train a neural network... but will probably be disappointed if > you try to process existing information. > > Best, > > Philippe >
signature.asc
Description: Message signed with OpenPGP
_______________________________________________ openEHR-clinical mailing list openEHR-clinical@lists.openehr.org http://lists.openehr.org/mailman/listinfo/openehr-clinical_lists.openehr.org