Mushroom-Identifier Apps. Accuracy? Help Wanted.
Trying a couple apps to identify mystery flowers sprouting up without invitation in my yard, I've not had much luck w them (but some blame may be laid on user
) . Anyway I wondered about accuracy of M-I apps; article below reinforces my No-Eating-Foraged-Mushroom thinking.
In a scientific article* specific to Victoria, authors** reviewed three M-I apps & found:
--- accurate identification rates of 49%, 33%, and 40% for 78 species of mushrooms.
Sooo the best of three apps equates to a coin flip?
--- accurate identification rates of 67%, 60%, and 27% re specimens of Amanita phalloides.
Okay, better results from two of the apps.
The abstract concludes the apps are “not reliable enough to exclude exposure to potentially poisonous mushrooms when used alone.”
Agreeing w ^.
HELP WANTED in interp'ing one sentence in "Results" below:
"Amanita phalloides was falsely identified, twice by Picture Mushroom and once by iNaturalist."
Does this ^ mean---
A. Some AP mushrooms were falsely identified as other species (presumably edible/safe), twice by one app and once by another app?
Or
B. Other mushroom species were falsely identified as APs, twice by one app and once by another app?
Thoughts, anyone?
I'm curious, but not curious enough to pay $62 for full text*** of article to find out.
Anyone with a subscription or other access?
BTW, if my post misinterprets info from abstract, I welcome correction. TiA.
_____________________________________
* Not so briefly but still just the abstract.
"A comparison of the accuracy of mushroom identification applications using digital photographs"
"Objective: To compare the accuracy of three popular mushroom identification software applications in identifying mushrooms involved in exposures reported to the Victorian Poisons Information Centre and Royal Botanic Gardens Victoria.
"Background: Over the past 10 years, an increasing number of software applications have been developed for use on smart phones and tablet devices to identify mushrooms. We have observed an increase in poisonings after incorrect identification of poisonous species as edible, using these applications.
"Design: We compared the accuracy of three iPhone™ and Android™ mushroom identification applications:...using digital photographs of 78 specimens sent to the Victorian Poisons Information Centre and Royal Botanic Gardens Victoria over a two-year period, 2020-2021.
"Results: Picture Mushroom was the most accurate of the three apps and correctly identified 49% (95% CI [0-100]) of specimens, compared with Mushroom Identificator (35% [15-56]) and iNaturalist (35% [0-76]). Picture Mushroom correctly identified 44% of poisonous mushrooms [0-95], compared with Mushroom Identificator (30% [1-58]) and iNaturalist (40% [0-84), but Mushroom Identificator identified more specimens of Amanita phalloides correctly (67%), compared to Picture Mushroom (60%) and iNaturalist (27%). Amanita phalloides was falsely identified, twice by Picture Mushroom and once by iNaturalist.
"Conclusions: Mushroom identification applications may be useful future tools to assist clinical toxicologists and the general public in the accurate identification of mushrooms species but, at present, are not reliable enough to exclude exposure to potentially poisonous mushrooms when used alone."
Mushroom identification applications may be useful future tools to assist clinical toxicologists and the general public in the accurate identification of mushrooms species but, at present, are not reliable enough to exclude exposure to potentially poisonous mushrooms when used alone.
pubmed.ncbi.nlm.nih.gov
** Authors & Affiliations:
Sarah E Hodgson 1 2, Christine McKenzie 1, Tom W May 3, Shaun L Greene 1 2
1 Victorian Poisons Information Centre, Austin Health, Melbourne, Australia.
2 Emergency Department, Austin Health, Melbourne, Australia.
3 Royal Botanic Gardens Victoria, Melbourne, Australia.
*** to access text, to buy, etc.