Machine Learning to predict tuberculosis in cattle from the state of Sao Paulo, Brazil
Abstract Tuberculosis is a well-known and worldwide spread zoonosis. In Brazil 1.594.787 cases were confirmed cases since 2001, where, in Sao Paulo state, 8.226 deaths were reported. This study aims to present steps related to the use of machine learning algorithms for predictive analysis for bovine...
Gespeichert in:
| Veröffentlicht in: | European journal of public health 2020-09, Vol.30 (Supplement_5) |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | Supplement_5 |
| container_start_page | |
| container_title | European journal of public health |
| container_volume | 30 |
| creator | Pereira, L E C Ferraudo, A S Panosso, A R Carvalho, A A B Mathias, L A Saches, A C Hellwig, K S Ancêncio, R A |
| description | Abstract
Tuberculosis is a well-known and worldwide spread zoonosis. In Brazil 1.594.787 cases were confirmed cases since 2001, where, in Sao Paulo state, 8.226 deaths were reported. This study aims to present steps related to the use of machine learning algorithms for predictive analysis for bovine tuberculosis. For this, an application was made based on data from farms in state of São Paulo, Brazil, of an epidemiological survey, using a specific questionnaire, carried out on farms (n = 1,743). Response variable was presented by apparent prevalence of positive properties for disease, and predictors by (k = 77) predictors related to type of farm, type of lactation, number of animals on property. Application was organized according to following steps: division of data in training (75%) and testing (25%), pre-processing of predictors, learning and model evaluation. In the learning step, algorithm for adjusting gradient boosted trees models was used. The hyperparameters of algorithms were optimized by 10-fold cross-validation, to select those corresponding to best models. Models showed an accuracy of 88.07%, with an error in learning process equal to 3%. In the test / model validation procedure (n = 436), an error in 12% estimate was observed. Five important predictors were daily milk production, number of cows, type of farm, bovine breed and slaughter of adult animals. Proportion of false positives among all individuals whose response of interest was observed was 2.06%, and proportion of false negatives among those with a response of absent interest was 9.86%. It is hoped that, with increase in trained surveillance to detect the disease and availability of data, it will be possible to develop predictive models of machine learning with potential to efficiently assist professionals in disease control and assist in education program in animal health
Key messages
Predictive analyzes in health: application for tuberculosis in cattle from the state of Sao Paulo, Brazil.
An infectious disease and zoonosis important to the world that needs support to develop means to control and consequently eradicate it. |
| doi_str_mv | 10.1093/eurpub/ckaa166.849 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2476167871</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><oup_id>10.1093/eurpub/ckaa166.849</oup_id><sourcerecordid>2476167871</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2029-6e9aeb93462897ea090ec24bb6798757a229f44d25d5741aedc973e264960ced3</originalsourceid><addsrcrecordid>eNqNkMlOwzAURS0EEqXwA6wssSWt7Th2vATEJBWBxCB2luO80JQ0Dh4W8PUEpR_A6t3FufdJB6FTShaUqHwJyQ-pWtpPY6gQi5KrPTSjXPAsF-R9f8yU0IwywQ7RUQgbQkghSzZDbw_Grtse8AqM79v-A0eHBw91ayOOqQJvU-dCG3DbY2ti7AA33m1xXAMO0UTArsHPxuEnM4Ln-NKbn7Y7RgeN6QKc7O4cvd5cv1zdZavH2_uri1VmGWEqE6AMVCrngpVKgiGKgGW8qoRUpSykYUw1nNesqAvJqYHaKpkDE1wJYqHO5-hs2h28-0oQot645PvxpWZcCipkKelIsYmy3oXgodGDb7fGf2tK9J8_PfnTO3969DeWsqnk0vAf_hfo0nUF</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2476167871</pqid></control><display><type>article</type><title>Machine Learning to predict tuberculosis in cattle from the state of Sao Paulo, Brazil</title><source>PAIS Index</source><source>Oxford Journals Open Access Collection</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><source>Alma/SFX Local Collection</source><creator>Pereira, L E C ; Ferraudo, A S ; Panosso, A R ; Carvalho, A A B ; Mathias, L A ; Saches, A C ; Hellwig, K S ; Ancêncio, R A</creator><creatorcontrib>Pereira, L E C ; Ferraudo, A S ; Panosso, A R ; Carvalho, A A B ; Mathias, L A ; Saches, A C ; Hellwig, K S ; Ancêncio, R A</creatorcontrib><description>Abstract
Tuberculosis is a well-known and worldwide spread zoonosis. In Brazil 1.594.787 cases were confirmed cases since 2001, where, in Sao Paulo state, 8.226 deaths were reported. This study aims to present steps related to the use of machine learning algorithms for predictive analysis for bovine tuberculosis. For this, an application was made based on data from farms in state of São Paulo, Brazil, of an epidemiological survey, using a specific questionnaire, carried out on farms (n = 1,743). Response variable was presented by apparent prevalence of positive properties for disease, and predictors by (k = 77) predictors related to type of farm, type of lactation, number of animals on property. Application was organized according to following steps: division of data in training (75%) and testing (25%), pre-processing of predictors, learning and model evaluation. In the learning step, algorithm for adjusting gradient boosted trees models was used. The hyperparameters of algorithms were optimized by 10-fold cross-validation, to select those corresponding to best models. Models showed an accuracy of 88.07%, with an error in learning process equal to 3%. In the test / model validation procedure (n = 436), an error in 12% estimate was observed. Five important predictors were daily milk production, number of cows, type of farm, bovine breed and slaughter of adult animals. Proportion of false positives among all individuals whose response of interest was observed was 2.06%, and proportion of false negatives among those with a response of absent interest was 9.86%. It is hoped that, with increase in trained surveillance to detect the disease and availability of data, it will be possible to develop predictive models of machine learning with potential to efficiently assist professionals in disease control and assist in education program in animal health
Key messages
Predictive analyzes in health: application for tuberculosis in cattle from the state of Sao Paulo, Brazil.
An infectious disease and zoonosis important to the world that needs support to develop means to control and consequently eradicate it.</description><identifier>ISSN: 1101-1262</identifier><identifier>EISSN: 1464-360X</identifier><identifier>DOI: 10.1093/eurpub/ckaa166.849</identifier><language>eng</language><publisher>Oxford: Oxford University Press</publisher><subject>Algorithms ; Animal health ; Animals ; Cattle ; Cow's milk ; Dairy cattle ; Data processing ; Disease control ; Epidemiology ; Farms ; Health education ; Infectious diseases ; Lactation ; Learning algorithms ; Livestock industry ; Machine learning ; Milk ; Milk production ; Model accuracy ; Model testing ; Prediction models ; Property ; Public health ; Surveillance ; Training ; Tuberculosis ; Validity ; Zoonoses</subject><ispartof>European journal of public health, 2020-09, Vol.30 (Supplement_5)</ispartof><rights>The Author(s) 2020. Published by Oxford University Press on behalf of the European Public Health Association. All rights reserved. 2020</rights><rights>The Author(s) 2020. Published by Oxford University Press on behalf of the European Public Health Association. All rights reserved.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2029-6e9aeb93462897ea090ec24bb6798757a229f44d25d5741aedc973e264960ced3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27866,27924,27925</link.rule.ids></links><search><creatorcontrib>Pereira, L E C</creatorcontrib><creatorcontrib>Ferraudo, A S</creatorcontrib><creatorcontrib>Panosso, A R</creatorcontrib><creatorcontrib>Carvalho, A A B</creatorcontrib><creatorcontrib>Mathias, L A</creatorcontrib><creatorcontrib>Saches, A C</creatorcontrib><creatorcontrib>Hellwig, K S</creatorcontrib><creatorcontrib>Ancêncio, R A</creatorcontrib><title>Machine Learning to predict tuberculosis in cattle from the state of Sao Paulo, Brazil</title><title>European journal of public health</title><description>Abstract
Tuberculosis is a well-known and worldwide spread zoonosis. In Brazil 1.594.787 cases were confirmed cases since 2001, where, in Sao Paulo state, 8.226 deaths were reported. This study aims to present steps related to the use of machine learning algorithms for predictive analysis for bovine tuberculosis. For this, an application was made based on data from farms in state of São Paulo, Brazil, of an epidemiological survey, using a specific questionnaire, carried out on farms (n = 1,743). Response variable was presented by apparent prevalence of positive properties for disease, and predictors by (k = 77) predictors related to type of farm, type of lactation, number of animals on property. Application was organized according to following steps: division of data in training (75%) and testing (25%), pre-processing of predictors, learning and model evaluation. In the learning step, algorithm for adjusting gradient boosted trees models was used. The hyperparameters of algorithms were optimized by 10-fold cross-validation, to select those corresponding to best models. Models showed an accuracy of 88.07%, with an error in learning process equal to 3%. In the test / model validation procedure (n = 436), an error in 12% estimate was observed. Five important predictors were daily milk production, number of cows, type of farm, bovine breed and slaughter of adult animals. Proportion of false positives among all individuals whose response of interest was observed was 2.06%, and proportion of false negatives among those with a response of absent interest was 9.86%. It is hoped that, with increase in trained surveillance to detect the disease and availability of data, it will be possible to develop predictive models of machine learning with potential to efficiently assist professionals in disease control and assist in education program in animal health
Key messages
Predictive analyzes in health: application for tuberculosis in cattle from the state of Sao Paulo, Brazil.
An infectious disease and zoonosis important to the world that needs support to develop means to control and consequently eradicate it.</description><subject>Algorithms</subject><subject>Animal health</subject><subject>Animals</subject><subject>Cattle</subject><subject>Cow's milk</subject><subject>Dairy cattle</subject><subject>Data processing</subject><subject>Disease control</subject><subject>Epidemiology</subject><subject>Farms</subject><subject>Health education</subject><subject>Infectious diseases</subject><subject>Lactation</subject><subject>Learning algorithms</subject><subject>Livestock industry</subject><subject>Machine learning</subject><subject>Milk</subject><subject>Milk production</subject><subject>Model accuracy</subject><subject>Model testing</subject><subject>Prediction models</subject><subject>Property</subject><subject>Public health</subject><subject>Surveillance</subject><subject>Training</subject><subject>Tuberculosis</subject><subject>Validity</subject><subject>Zoonoses</subject><issn>1101-1262</issn><issn>1464-360X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>7TQ</sourceid><recordid>eNqNkMlOwzAURS0EEqXwA6wssSWt7Th2vATEJBWBxCB2luO80JQ0Dh4W8PUEpR_A6t3FufdJB6FTShaUqHwJyQ-pWtpPY6gQi5KrPTSjXPAsF-R9f8yU0IwywQ7RUQgbQkghSzZDbw_Grtse8AqM79v-A0eHBw91ayOOqQJvU-dCG3DbY2ti7AA33m1xXAMO0UTArsHPxuEnM4Ln-NKbn7Y7RgeN6QKc7O4cvd5cv1zdZavH2_uri1VmGWEqE6AMVCrngpVKgiGKgGW8qoRUpSykYUw1nNesqAvJqYHaKpkDE1wJYqHO5-hs2h28-0oQot645PvxpWZcCipkKelIsYmy3oXgodGDb7fGf2tK9J8_PfnTO3969DeWsqnk0vAf_hfo0nUF</recordid><startdate>20200901</startdate><enddate>20200901</enddate><creator>Pereira, L E C</creator><creator>Ferraudo, A S</creator><creator>Panosso, A R</creator><creator>Carvalho, A A B</creator><creator>Mathias, L A</creator><creator>Saches, A C</creator><creator>Hellwig, K S</creator><creator>Ancêncio, R A</creator><general>Oxford University Press</general><general>Oxford Publishing Limited (England)</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7T2</scope><scope>7TQ</scope><scope>C1K</scope><scope>DHY</scope><scope>DON</scope><scope>K9.</scope><scope>NAPCQ</scope></search><sort><creationdate>20200901</creationdate><title>Machine Learning to predict tuberculosis in cattle from the state of Sao Paulo, Brazil</title><author>Pereira, L E C ; Ferraudo, A S ; Panosso, A R ; Carvalho, A A B ; Mathias, L A ; Saches, A C ; Hellwig, K S ; Ancêncio, R A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2029-6e9aeb93462897ea090ec24bb6798757a229f44d25d5741aedc973e264960ced3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Animal health</topic><topic>Animals</topic><topic>Cattle</topic><topic>Cow's milk</topic><topic>Dairy cattle</topic><topic>Data processing</topic><topic>Disease control</topic><topic>Epidemiology</topic><topic>Farms</topic><topic>Health education</topic><topic>Infectious diseases</topic><topic>Lactation</topic><topic>Learning algorithms</topic><topic>Livestock industry</topic><topic>Machine learning</topic><topic>Milk</topic><topic>Milk production</topic><topic>Model accuracy</topic><topic>Model testing</topic><topic>Prediction models</topic><topic>Property</topic><topic>Public health</topic><topic>Surveillance</topic><topic>Training</topic><topic>Tuberculosis</topic><topic>Validity</topic><topic>Zoonoses</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Pereira, L E C</creatorcontrib><creatorcontrib>Ferraudo, A S</creatorcontrib><creatorcontrib>Panosso, A R</creatorcontrib><creatorcontrib>Carvalho, A A B</creatorcontrib><creatorcontrib>Mathias, L A</creatorcontrib><creatorcontrib>Saches, A C</creatorcontrib><creatorcontrib>Hellwig, K S</creatorcontrib><creatorcontrib>Ancêncio, R A</creatorcontrib><collection>CrossRef</collection><collection>Health and Safety Science Abstracts (Full archive)</collection><collection>PAIS Index</collection><collection>Environmental Sciences and Pollution Management</collection><collection>PAIS International</collection><collection>PAIS International (Ovid)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Premium</collection><jtitle>European journal of public health</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Pereira, L E C</au><au>Ferraudo, A S</au><au>Panosso, A R</au><au>Carvalho, A A B</au><au>Mathias, L A</au><au>Saches, A C</au><au>Hellwig, K S</au><au>Ancêncio, R A</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine Learning to predict tuberculosis in cattle from the state of Sao Paulo, Brazil</atitle><jtitle>European journal of public health</jtitle><date>2020-09-01</date><risdate>2020</risdate><volume>30</volume><issue>Supplement_5</issue><issn>1101-1262</issn><eissn>1464-360X</eissn><abstract>Abstract
Tuberculosis is a well-known and worldwide spread zoonosis. In Brazil 1.594.787 cases were confirmed cases since 2001, where, in Sao Paulo state, 8.226 deaths were reported. This study aims to present steps related to the use of machine learning algorithms for predictive analysis for bovine tuberculosis. For this, an application was made based on data from farms in state of São Paulo, Brazil, of an epidemiological survey, using a specific questionnaire, carried out on farms (n = 1,743). Response variable was presented by apparent prevalence of positive properties for disease, and predictors by (k = 77) predictors related to type of farm, type of lactation, number of animals on property. Application was organized according to following steps: division of data in training (75%) and testing (25%), pre-processing of predictors, learning and model evaluation. In the learning step, algorithm for adjusting gradient boosted trees models was used. The hyperparameters of algorithms were optimized by 10-fold cross-validation, to select those corresponding to best models. Models showed an accuracy of 88.07%, with an error in learning process equal to 3%. In the test / model validation procedure (n = 436), an error in 12% estimate was observed. Five important predictors were daily milk production, number of cows, type of farm, bovine breed and slaughter of adult animals. Proportion of false positives among all individuals whose response of interest was observed was 2.06%, and proportion of false negatives among those with a response of absent interest was 9.86%. It is hoped that, with increase in trained surveillance to detect the disease and availability of data, it will be possible to develop predictive models of machine learning with potential to efficiently assist professionals in disease control and assist in education program in animal health
Key messages
Predictive analyzes in health: application for tuberculosis in cattle from the state of Sao Paulo, Brazil.
An infectious disease and zoonosis important to the world that needs support to develop means to control and consequently eradicate it.</abstract><cop>Oxford</cop><pub>Oxford University Press</pub><doi>10.1093/eurpub/ckaa166.849</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1101-1262 |
| ispartof | European journal of public health, 2020-09, Vol.30 (Supplement_5) |
| issn | 1101-1262 1464-360X |
| language | eng |
| recordid | cdi_proquest_journals_2476167871 |
| source | PAIS Index; Oxford Journals Open Access Collection; EZB-FREE-00999 freely available EZB journals; PubMed Central; Alma/SFX Local Collection |
| subjects | Algorithms Animal health Animals Cattle Cow's milk Dairy cattle Data processing Disease control Epidemiology Farms Health education Infectious diseases Lactation Learning algorithms Livestock industry Machine learning Milk Milk production Model accuracy Model testing Prediction models Property Public health Surveillance Training Tuberculosis Validity Zoonoses |
| title | Machine Learning to predict tuberculosis in cattle from the state of Sao Paulo, Brazil |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T20%3A55%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20Learning%20to%20predict%20tuberculosis%20in%20cattle%20from%20the%20state%20of%20Sao%20Paulo,%20Brazil&rft.jtitle=European%20journal%20of%20public%20health&rft.au=Pereira,%20L%20E%20C&rft.date=2020-09-01&rft.volume=30&rft.issue=Supplement_5&rft.issn=1101-1262&rft.eissn=1464-360X&rft_id=info:doi/10.1093/eurpub/ckaa166.849&rft_dat=%3Cproquest_cross%3E2476167871%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2476167871&rft_id=info:pmid/&rft_oup_id=10.1093/eurpub/ckaa166.849&rfr_iscdi=true |