Detail
Article
Online article
FT
Medvik - BMC
  • Something wrong with this record ?

An artificial intelligence model to identify snakes from across the world: Opportunities and challenges for global health and herpetology

I. Bolon, L. Picek, AM. Durso, G. Alcoba, F. Chappuis, R. Ruiz de Castañeda

. 2022 ; 16 (8) : e0010647. [pub] 20220815

Language English Country United States

Document type Journal Article, Research Support, Non-U.S. Gov't

Persistent link   https://www.medvik.cz/link/bmc22024834

BACKGROUND: Snakebite envenoming is a neglected tropical disease that kills an estimated 81,000 to 138,000 people and disables another 400,000 globally every year. The World Health Organization aims to halve this burden by 2030. To achieve this ambitious goal, we need to close the data gap in snake ecology and snakebite epidemiology and give healthcare providers up-to-date knowledge and access to better diagnostic tools. An essential first step is to improve the capacity to identify biting snakes taxonomically. The existence of AI-based identification tools for other animals offers an innovative opportunity to apply machine learning to snake identification and snakebite envenoming, a life-threatening situation. METHODOLOGY: We developed an AI model based on Vision Transformer, a recent neural network architecture, and a comprehensive snake photo dataset of 386,006 training photos covering 198 venomous and 574 non-venomous snake species from 188 countries. We gathered photos from online biodiversity platforms (iNaturalist and HerpMapper) and a photo-sharing site (Flickr). PRINCIPAL FINDINGS: The model macro-averaged F1 score, which reflects the species-wise performance as averaging performance for each species, is 92.2%. The accuracy on a species and genus level is 96.0% and 99.0%, respectively. The average accuracy per country is 94.2%. The model accurately classifies selected venomous and non-venomous lookalike species from Southeast Asia and sub-Saharan Africa. CONCLUSIONS: To our knowledge, this model's taxonomic and geographic coverage and performance are unprecedented. This model could provide high-speed and low-cost snake identification to support snakebite victims and healthcare providers in low-resource settings, as well as zoologists, conservationists, and nature lovers from across the world.

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22024834
003      
CZ-PrNML
005      
20221031101141.0
007      
ta
008      
221017s2022 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1371/journal.pntd.0010647 $2 doi
035    __
$a (PubMed)35969634
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Bolon, Isabelle $u Institute of Global Health, Department of Community Health and Medicine, Faculty of Medicine, University of Geneva, Geneva, Switzerland $1 https://orcid.org/0000000159402731
245    13
$a An artificial intelligence model to identify snakes from across the world: Opportunities and challenges for global health and herpetology / $c I. Bolon, L. Picek, AM. Durso, G. Alcoba, F. Chappuis, R. Ruiz de Castañeda
520    9_
$a BACKGROUND: Snakebite envenoming is a neglected tropical disease that kills an estimated 81,000 to 138,000 people and disables another 400,000 globally every year. The World Health Organization aims to halve this burden by 2030. To achieve this ambitious goal, we need to close the data gap in snake ecology and snakebite epidemiology and give healthcare providers up-to-date knowledge and access to better diagnostic tools. An essential first step is to improve the capacity to identify biting snakes taxonomically. The existence of AI-based identification tools for other animals offers an innovative opportunity to apply machine learning to snake identification and snakebite envenoming, a life-threatening situation. METHODOLOGY: We developed an AI model based on Vision Transformer, a recent neural network architecture, and a comprehensive snake photo dataset of 386,006 training photos covering 198 venomous and 574 non-venomous snake species from 188 countries. We gathered photos from online biodiversity platforms (iNaturalist and HerpMapper) and a photo-sharing site (Flickr). PRINCIPAL FINDINGS: The model macro-averaged F1 score, which reflects the species-wise performance as averaging performance for each species, is 92.2%. The accuracy on a species and genus level is 96.0% and 99.0%, respectively. The average accuracy per country is 94.2%. The model accurately classifies selected venomous and non-venomous lookalike species from Southeast Asia and sub-Saharan Africa. CONCLUSIONS: To our knowledge, this model's taxonomic and geographic coverage and performance are unprecedented. This model could provide high-speed and low-cost snake identification to support snakebite victims and healthcare providers in low-resource settings, as well as zoologists, conservationists, and nature lovers from across the world.
650    _2
$a zvířata $7 D000818
650    _2
$a antiveniny $x terapeutické užití $7 D000997
650    _2
$a umělá inteligence $7 D001185
650    _2
$a celosvětové zdraví $7 D014943
650    _2
$a lidé $7 D006801
650    _2
$a opomíjené nemoci $x diagnóza $x epidemiologie $7 D058069
650    12
$a uštknutí hadem $x diagnóza $x epidemiologie $x terapie $7 D012909
650    _2
$a hadi $7 D012911
651    _2
$a subsaharská Afrika $7 D017954
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Picek, Lukáš $u Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czechia $u PiVa AI s.r.o, Plzeň, Czechia
700    1_
$a Durso, Andrew M $u Department of Biological Sciences, Florida Gulf Coast University, Fort Myers, Florida, United States of America
700    1_
$a Alcoba, Gabriel $u Institute of Global Health, Department of Community Health and Medicine, Faculty of Medicine, University of Geneva, Geneva, Switzerland $u Division of Tropical and Humanitarian Medicine, Geneva University Hospitals and University of Geneva, Geneva, Switzerland $u Médecins Sans Frontières-Doctors Without Borders, Geneva, Switzerland
700    1_
$a Chappuis, François $u Division of Tropical and Humanitarian Medicine, Geneva University Hospitals and University of Geneva, Geneva, Switzerland $u Department of Community Health and Medicine, Faculty of Medicine, University of Geneva, Geneva, Switzerland
700    1_
$a Ruiz de Castañeda, Rafael $u Institute of Global Health, Department of Community Health and Medicine, Faculty of Medicine, University of Geneva, Geneva, Switzerland $u Division of Tropical and Humanitarian Medicine, Geneva University Hospitals and University of Geneva, Geneva, Switzerland
773    0_
$w MED00165375 $t PLoS neglected tropical diseases $x 1935-2735 $g Roč. 16, č. 8 (2022), s. e0010647
856    41
$u https://pubmed.ncbi.nlm.nih.gov/35969634 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20221017 $b ABA008
991    __
$a 20221031101138 $b ABA008
999    __
$a ok $b bmc $g 1854514 $s 1176124
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2022 $b 16 $c 8 $d e0010647 $e 20220815 $i 1935-2735 $m PLoS neglected tropical diseases $n PLoS negl. trop. dis. $x MED00165375
LZP    __
$a Pubmed-20221017

Find record

Citation metrics

Archiving options