Statistical Design and Analysis for Robust Machine Learning: A Case Study from COVID-19
Since early in the coronavirus disease 2019 (COVID-19) pandemic, there has been interest in using artificial intelligence methods to predict COVID-19 infection status based on vocal audio signals, for example cough recordings. However, existing studies have limitations in terms of data collection an...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2023-02 |
|---|---|
| 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 | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Pigoli, Davide Baker, Kieran Budd, Jobie Butler, Lorraine Coppock, Harry Egglestone, Sabrina Gilmour, Steven G Holmes, Chris Hurley, David Jersakova, Radka Kiskin, Ivan Koutra, Vasiliki Mellor, Jonathon Nicholson, George Packham, Joe Patel, Selina Payne, Richard Roberts, Stephen J Schuller, Björn W Tendero-Cañadas, Ana Thornley, Tracey Titcomb, Alexander |
| description | Since early in the coronavirus disease 2019 (COVID-19) pandemic, there has been interest in using artificial intelligence methods to predict COVID-19 infection status based on vocal audio signals, for example cough recordings. However, existing studies have limitations in terms of data collection and of the assessment of the performances of the proposed predictive models. This paper rigorously assesses state-of-the-art machine learning techniques used to predict COVID-19 infection status based on vocal audio signals, using a dataset collected by the UK Health Security Agency. This dataset includes acoustic recordings and extensive study participant meta-data. We provide guidelines on testing the performance of methods to classify COVID-19 infection status based on acoustic features and we discuss how these can be extended more generally to the development and assessment of predictive methods based on public health datasets. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2755693450</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2755693450</sourcerecordid><originalsourceid>FETCH-proquest_journals_27556934503</originalsourceid><addsrcrecordid>eNqNzb0KwjAUQOEgCBb1HS44F9Kk8W8rVVFQBCs6SmxTjdREc5Ohb6-DD-B0lg9Oh0SM8ySepoz1yBDxQSll4wkTgkfkXHjpNXpdygYWCvXNgDQVZEY2LWqE2jo42GtADztZ3rVRsFXSGW1uc8ggl6ig8KFqoXb2Cfn-tFnEyWxAurVsUA1_7ZPRannM1_HL2XdQ6C8PG9x3ghc2EWI846mg_D_1AXq0P4k</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2755693450</pqid></control><display><type>article</type><title>Statistical Design and Analysis for Robust Machine Learning: A Case Study from COVID-19</title><source>Free E- Journals</source><creator>Pigoli, Davide ; Baker, Kieran ; Budd, Jobie ; Butler, Lorraine ; Coppock, Harry ; Egglestone, Sabrina ; Gilmour, Steven G ; Holmes, Chris ; Hurley, David ; Jersakova, Radka ; Kiskin, Ivan ; Koutra, Vasiliki ; Mellor, Jonathon ; Nicholson, George ; Packham, Joe ; Patel, Selina ; Payne, Richard ; Roberts, Stephen J ; Schuller, Björn W ; Tendero-Cañadas, Ana ; Thornley, Tracey ; Titcomb, Alexander</creator><creatorcontrib>Pigoli, Davide ; Baker, Kieran ; Budd, Jobie ; Butler, Lorraine ; Coppock, Harry ; Egglestone, Sabrina ; Gilmour, Steven G ; Holmes, Chris ; Hurley, David ; Jersakova, Radka ; Kiskin, Ivan ; Koutra, Vasiliki ; Mellor, Jonathon ; Nicholson, George ; Packham, Joe ; Patel, Selina ; Payne, Richard ; Roberts, Stephen J ; Schuller, Björn W ; Tendero-Cañadas, Ana ; Thornley, Tracey ; Titcomb, Alexander</creatorcontrib><description>Since early in the coronavirus disease 2019 (COVID-19) pandemic, there has been interest in using artificial intelligence methods to predict COVID-19 infection status based on vocal audio signals, for example cough recordings. However, existing studies have limitations in terms of data collection and of the assessment of the performances of the proposed predictive models. This paper rigorously assesses state-of-the-art machine learning techniques used to predict COVID-19 infection status based on vocal audio signals, using a dataset collected by the UK Health Security Agency. This dataset includes acoustic recordings and extensive study participant meta-data. We provide guidelines on testing the performance of methods to classify COVID-19 infection status based on acoustic features and we discuss how these can be extended more generally to the development and assessment of predictive methods based on public health datasets.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial intelligence ; Audio signals ; Data collection ; Datasets ; Machine learning ; Prediction models ; Public health ; Viral diseases</subject><ispartof>arXiv.org, 2023-02</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Pigoli, Davide</creatorcontrib><creatorcontrib>Baker, Kieran</creatorcontrib><creatorcontrib>Budd, Jobie</creatorcontrib><creatorcontrib>Butler, Lorraine</creatorcontrib><creatorcontrib>Coppock, Harry</creatorcontrib><creatorcontrib>Egglestone, Sabrina</creatorcontrib><creatorcontrib>Gilmour, Steven G</creatorcontrib><creatorcontrib>Holmes, Chris</creatorcontrib><creatorcontrib>Hurley, David</creatorcontrib><creatorcontrib>Jersakova, Radka</creatorcontrib><creatorcontrib>Kiskin, Ivan</creatorcontrib><creatorcontrib>Koutra, Vasiliki</creatorcontrib><creatorcontrib>Mellor, Jonathon</creatorcontrib><creatorcontrib>Nicholson, George</creatorcontrib><creatorcontrib>Packham, Joe</creatorcontrib><creatorcontrib>Patel, Selina</creatorcontrib><creatorcontrib>Payne, Richard</creatorcontrib><creatorcontrib>Roberts, Stephen J</creatorcontrib><creatorcontrib>Schuller, Björn W</creatorcontrib><creatorcontrib>Tendero-Cañadas, Ana</creatorcontrib><creatorcontrib>Thornley, Tracey</creatorcontrib><creatorcontrib>Titcomb, Alexander</creatorcontrib><title>Statistical Design and Analysis for Robust Machine Learning: A Case Study from COVID-19</title><title>arXiv.org</title><description>Since early in the coronavirus disease 2019 (COVID-19) pandemic, there has been interest in using artificial intelligence methods to predict COVID-19 infection status based on vocal audio signals, for example cough recordings. However, existing studies have limitations in terms of data collection and of the assessment of the performances of the proposed predictive models. This paper rigorously assesses state-of-the-art machine learning techniques used to predict COVID-19 infection status based on vocal audio signals, using a dataset collected by the UK Health Security Agency. This dataset includes acoustic recordings and extensive study participant meta-data. We provide guidelines on testing the performance of methods to classify COVID-19 infection status based on acoustic features and we discuss how these can be extended more generally to the development and assessment of predictive methods based on public health datasets.</description><subject>Artificial intelligence</subject><subject>Audio signals</subject><subject>Data collection</subject><subject>Datasets</subject><subject>Machine learning</subject><subject>Prediction models</subject><subject>Public health</subject><subject>Viral diseases</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNzb0KwjAUQOEgCBb1HS44F9Kk8W8rVVFQBCs6SmxTjdREc5Ohb6-DD-B0lg9Oh0SM8ySepoz1yBDxQSll4wkTgkfkXHjpNXpdygYWCvXNgDQVZEY2LWqE2jo42GtADztZ3rVRsFXSGW1uc8ggl6ig8KFqoXb2Cfn-tFnEyWxAurVsUA1_7ZPRannM1_HL2XdQ6C8PG9x3ghc2EWI846mg_D_1AXq0P4k</recordid><startdate>20230227</startdate><enddate>20230227</enddate><creator>Pigoli, Davide</creator><creator>Baker, Kieran</creator><creator>Budd, Jobie</creator><creator>Butler, Lorraine</creator><creator>Coppock, Harry</creator><creator>Egglestone, Sabrina</creator><creator>Gilmour, Steven G</creator><creator>Holmes, Chris</creator><creator>Hurley, David</creator><creator>Jersakova, Radka</creator><creator>Kiskin, Ivan</creator><creator>Koutra, Vasiliki</creator><creator>Mellor, Jonathon</creator><creator>Nicholson, George</creator><creator>Packham, Joe</creator><creator>Patel, Selina</creator><creator>Payne, Richard</creator><creator>Roberts, Stephen J</creator><creator>Schuller, Björn W</creator><creator>Tendero-Cañadas, Ana</creator><creator>Thornley, Tracey</creator><creator>Titcomb, Alexander</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>COVID</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20230227</creationdate><title>Statistical Design and Analysis for Robust Machine Learning: A Case Study from COVID-19</title><author>Pigoli, Davide ; Baker, Kieran ; Budd, Jobie ; Butler, Lorraine ; Coppock, Harry ; Egglestone, Sabrina ; Gilmour, Steven G ; Holmes, Chris ; Hurley, David ; Jersakova, Radka ; Kiskin, Ivan ; Koutra, Vasiliki ; Mellor, Jonathon ; Nicholson, George ; Packham, Joe ; Patel, Selina ; Payne, Richard ; Roberts, Stephen J ; Schuller, Björn W ; Tendero-Cañadas, Ana ; Thornley, Tracey ; Titcomb, Alexander</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27556934503</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial intelligence</topic><topic>Audio signals</topic><topic>Data collection</topic><topic>Datasets</topic><topic>Machine learning</topic><topic>Prediction models</topic><topic>Public health</topic><topic>Viral diseases</topic><toplevel>online_resources</toplevel><creatorcontrib>Pigoli, Davide</creatorcontrib><creatorcontrib>Baker, Kieran</creatorcontrib><creatorcontrib>Budd, Jobie</creatorcontrib><creatorcontrib>Butler, Lorraine</creatorcontrib><creatorcontrib>Coppock, Harry</creatorcontrib><creatorcontrib>Egglestone, Sabrina</creatorcontrib><creatorcontrib>Gilmour, Steven G</creatorcontrib><creatorcontrib>Holmes, Chris</creatorcontrib><creatorcontrib>Hurley, David</creatorcontrib><creatorcontrib>Jersakova, Radka</creatorcontrib><creatorcontrib>Kiskin, Ivan</creatorcontrib><creatorcontrib>Koutra, Vasiliki</creatorcontrib><creatorcontrib>Mellor, Jonathon</creatorcontrib><creatorcontrib>Nicholson, George</creatorcontrib><creatorcontrib>Packham, Joe</creatorcontrib><creatorcontrib>Patel, Selina</creatorcontrib><creatorcontrib>Payne, Richard</creatorcontrib><creatorcontrib>Roberts, Stephen J</creatorcontrib><creatorcontrib>Schuller, Björn W</creatorcontrib><creatorcontrib>Tendero-Cañadas, Ana</creatorcontrib><creatorcontrib>Thornley, Tracey</creatorcontrib><creatorcontrib>Titcomb, Alexander</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>Coronavirus Research Database</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Pigoli, Davide</au><au>Baker, Kieran</au><au>Budd, Jobie</au><au>Butler, Lorraine</au><au>Coppock, Harry</au><au>Egglestone, Sabrina</au><au>Gilmour, Steven G</au><au>Holmes, Chris</au><au>Hurley, David</au><au>Jersakova, Radka</au><au>Kiskin, Ivan</au><au>Koutra, Vasiliki</au><au>Mellor, Jonathon</au><au>Nicholson, George</au><au>Packham, Joe</au><au>Patel, Selina</au><au>Payne, Richard</au><au>Roberts, Stephen J</au><au>Schuller, Björn W</au><au>Tendero-Cañadas, Ana</au><au>Thornley, Tracey</au><au>Titcomb, Alexander</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Statistical Design and Analysis for Robust Machine Learning: A Case Study from COVID-19</atitle><jtitle>arXiv.org</jtitle><date>2023-02-27</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Since early in the coronavirus disease 2019 (COVID-19) pandemic, there has been interest in using artificial intelligence methods to predict COVID-19 infection status based on vocal audio signals, for example cough recordings. However, existing studies have limitations in terms of data collection and of the assessment of the performances of the proposed predictive models. This paper rigorously assesses state-of-the-art machine learning techniques used to predict COVID-19 infection status based on vocal audio signals, using a dataset collected by the UK Health Security Agency. This dataset includes acoustic recordings and extensive study participant meta-data. We provide guidelines on testing the performance of methods to classify COVID-19 infection status based on acoustic features and we discuss how these can be extended more generally to the development and assessment of predictive methods based on public health datasets.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2023-02 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2755693450 |
| source | Free E- Journals |
| subjects | Artificial intelligence Audio signals Data collection Datasets Machine learning Prediction models Public health Viral diseases |
| title | Statistical Design and Analysis for Robust Machine Learning: A Case Study from COVID-19 |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T17%3A33%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Statistical%20Design%20and%20Analysis%20for%20Robust%20Machine%20Learning:%20A%20Case%20Study%20from%20COVID-19&rft.jtitle=arXiv.org&rft.au=Pigoli,%20Davide&rft.date=2023-02-27&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2755693450%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2755693450&rft_id=info:pmid/&rfr_iscdi=true |