Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19
Abstract Individual testing of samples is time- and cost-intensive, particularly during an ongoing pandemic. Better practical alternatives to individual testing can significantly decrease the burden of disease on the healthcare system. Herein, we presented the clinical validation of Segtnan™ on 3929...
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-59068-6 |
| _version_ | 1797199482003128320 |
|---|---|
| author | Farzin Kamari Esben Eller Mathias Emil Bøgebjerg Ignacio Martínez Capella Borja Arroyo Galende Tomas Korim Pernille Øland Martin Lysbjerg Borup Anja Rådberg Frederiksen Amir Ranjouriheravi Ahmed Faris Al-Jwadi Mostafa Mansour Sara Hansen Isabella Diethelm Marta Burek Federico Alvarez Anders Glent Buch Nima Mojtahedi Richard Röttger Eivind Antonsen Segtnan |
| author_facet | Farzin Kamari Esben Eller Mathias Emil Bøgebjerg Ignacio Martínez Capella Borja Arroyo Galende Tomas Korim Pernille Øland Martin Lysbjerg Borup Anja Rådberg Frederiksen Amir Ranjouriheravi Ahmed Faris Al-Jwadi Mostafa Mansour Sara Hansen Isabella Diethelm Marta Burek Federico Alvarez Anders Glent Buch Nima Mojtahedi Richard Röttger Eivind Antonsen Segtnan |
| author_sort | Farzin Kamari |
| collection | DOAJ |
| description | Abstract Individual testing of samples is time- and cost-intensive, particularly during an ongoing pandemic. Better practical alternatives to individual testing can significantly decrease the burden of disease on the healthcare system. Herein, we presented the clinical validation of Segtnan™ on 3929 patients. Segtnan™ is available as a mobile application entailing an AI-integrated personalized risk assessment approach with a novel data-driven equation for pooling of biological samples. The AI was selected from a comparison between 15 machine learning classifiers (highest accuracy = 80.14%) and a feed-forward neural network with an accuracy of 81.38% in predicting the rRT-PCR test results based on a designed survey with minimal clinical questions. Furthermore, we derived a novel pool-size equation from the pooling data of 54 published original studies. The results demonstrated testing capacity increase of 750%, 60%, and 5% at prevalence rates of 0.05%, 22%, and 50%, respectively. Compared to Dorfman’s method, our novel equation saved more tests significantly at high prevalence, i.e., 28% (p = 0.006), 40% (p = 0.00001), and 66% (p = 0.02). Lastly, we illustrated the feasibility of the Segtnan™ usage in clinically complex settings like emergency and psychiatric departments. |
| first_indexed | 2024-04-24T07:16:27Z |
| format | Article |
| id | doaj.art-8b205d56f7c44995a2bc9312d4d3f0b4 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T07:16:27Z |
| publishDate | 2024-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-8b205d56f7c44995a2bc9312d4d3f0b42024-04-21T11:16:29ZengNature PortfolioScientific Reports2045-23222024-04-0114111510.1038/s41598-024-59068-6Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19Farzin Kamari0Esben Eller1Mathias Emil Bøgebjerg2Ignacio Martínez Capella3Borja Arroyo Galende4Tomas Korim5Pernille Øland6Martin Lysbjerg Borup7Anja Rådberg Frederiksen8Amir Ranjouriheravi9Ahmed Faris Al-Jwadi10Mostafa Mansour11Sara Hansen12Isabella Diethelm13Marta Burek14Federico Alvarez15Anders Glent Buch16Nima Mojtahedi17Richard Röttger18Eivind Antonsen Segtnan19Department of Neurophysiology, Institute of Physiology, Eberhard Karls University of TübingenEllergyDepartment of Mathematics and Computer Science, University of Southern DenmarkInnovation Unit, IdISSC, Hospital Clínico San CarlosGrupo de Aplicación de Telecomunicaciones Visuales, Universidad Politécnica de MadridEasyrobotHospital of PsychiatryHospital of PsychiatryHospital of PsychiatryResearch Center for Translational Medicine (KUTTAM), Graduate School of Sciences and Engineering, Koç UniversitySchool of Medicine, University of Southern DenmarkSDU Health Informatics and Technology, Maersk Mc-Kinney Moller Institute, Faculty of Engineering, University of Southern DenmarkSDU Health Informatics and Technology, Maersk Mc-Kinney Moller Institute, Faculty of Engineering, University of Southern DenmarkSDU Health Informatics and Technology, Maersk Mc-Kinney Moller Institute, Faculty of Engineering, University of Southern DenmarkSDU Health Informatics and Technology, Maersk Mc-Kinney Moller Institute, Faculty of Engineering, University of Southern DenmarkGrupo de Aplicación de Telecomunicaciones Visuales, Universidad Politécnica de MadridDepartment of Engineering, Maersk Mc-Kinney Moller Institute, Faculty of Engineering, University of Southern DenmarkDepartment of Neurophysiology, Institute of Physiology, Eberhard Karls University of TübingenDepartment of Mathematics and Computer Science, University of Southern DenmarkDepartment of Neurosurgery, Odense University HospitalAbstract Individual testing of samples is time- and cost-intensive, particularly during an ongoing pandemic. Better practical alternatives to individual testing can significantly decrease the burden of disease on the healthcare system. Herein, we presented the clinical validation of Segtnan™ on 3929 patients. Segtnan™ is available as a mobile application entailing an AI-integrated personalized risk assessment approach with a novel data-driven equation for pooling of biological samples. The AI was selected from a comparison between 15 machine learning classifiers (highest accuracy = 80.14%) and a feed-forward neural network with an accuracy of 81.38% in predicting the rRT-PCR test results based on a designed survey with minimal clinical questions. Furthermore, we derived a novel pool-size equation from the pooling data of 54 published original studies. The results demonstrated testing capacity increase of 750%, 60%, and 5% at prevalence rates of 0.05%, 22%, and 50%, respectively. Compared to Dorfman’s method, our novel equation saved more tests significantly at high prevalence, i.e., 28% (p = 0.006), 40% (p = 0.00001), and 66% (p = 0.02). Lastly, we illustrated the feasibility of the Segtnan™ usage in clinically complex settings like emergency and psychiatric departments.https://doi.org/10.1038/s41598-024-59068-6 |
| spellingShingle | Farzin Kamari Esben Eller Mathias Emil Bøgebjerg Ignacio Martínez Capella Borja Arroyo Galende Tomas Korim Pernille Øland Martin Lysbjerg Borup Anja Rådberg Frederiksen Amir Ranjouriheravi Ahmed Faris Al-Jwadi Mostafa Mansour Sara Hansen Isabella Diethelm Marta Burek Federico Alvarez Anders Glent Buch Nima Mojtahedi Richard Röttger Eivind Antonsen Segtnan Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19 Scientific Reports |
| title | Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19 |
| title_full | Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19 |
| title_fullStr | Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19 |
| title_full_unstemmed | Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19 |
| title_short | Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19 |
| title_sort | clinical performance of ai integrated risk assessment pooling reveals cost savings even at high prevalence of covid 19 |
| url | https://doi.org/10.1038/s41598-024-59068-6 |
| work_keys_str_mv | AT farzinkamari clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT esbeneller clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT mathiasemilbøgebjerg clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT ignaciomartinezcapella clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT borjaarroyogalende clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT tomaskorim clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT pernilleøland clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT martinlysbjergborup clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT anjaradbergfrederiksen clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT amirranjouriheravi clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT ahmedfarisaljwadi clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT mostafamansour clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT sarahansen clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT isabelladiethelm clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT martaburek clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT federicoalvarez clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT andersglentbuch clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT nimamojtahedi clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT richardrottger clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 AT eivindantonsensegtnan clinicalperformanceofaiintegratedriskassessmentpoolingrevealscostsavingsevenathighprevalenceofcovid19 |