dc.contributor.author | Muller, Ashley Elizabeth | |
dc.contributor.author | Ames, Heather Melanie R | |
dc.contributor.author | Himmels, Jan Peter William | |
dc.contributor.author | Jardim, Patricia Sofia Jacobsen | |
dc.contributor.author | Nguyen, Hong Lien | |
dc.contributor.author | Rose, Christopher James | |
dc.contributor.author | van de Velde, Stijn Rita Patrick | |
dc.date.accessioned | 2021-09-17T06:43:30Z | |
dc.date.available | 2021-09-17T06:43:30Z | |
dc.date.created | 2021-09-15T10:10:40Z | |
dc.date.issued | 2021 | |
dc.identifier.isbn | 978-82-8406-234-1 | |
dc.identifier.uri | https://hdl.handle.net/11250/2778777 | |
dc.description.abstract | Key messages: In 2020-2021, a team in the Cluster for Reviews and Health Technology Assessments, Division for Health Services at the Norwegian Institute of Public Health (NIPH) ran a project on machine learning (ML) related to the conduct of evidence syntheses. Part of the work involved creating a vision and proposals for expanding ML activities in 2021-2022. This report describes the team’s suggestion for a strategic approach to meeting the continued need for innovation, evaluation, and implementation of ML for health technology assessments, systematic reviews, and other evidence syntheses. We propose a vision and goals, and a novel and flexible team structure. We divide activities into innovation, evaluation, and implementation, and present a risk assessment to inform the roll-out of a future team working on ML activities. | |
dc.description.abstract | Hovedbudskap: Et lag i Klynge for vurdering av tiltak, Område for helsetjenester ved Folkehelseinstituttet undersøkte i 2020-2021 bruken av maskinlæring i kunnskapsoppsummeringer. En del av arbeidet var å utforme et overordnet mål og en strategi for å kunne oppskalere maskinlæring i framtida. Denne rapporten beskriver lagets forslag til en strategisk tilnærming for å møte behovet for ytterligere bruk av maskinlæring i metodevurderinger, systematiske oversikter, og andre typer kunnskapsoppsummeringer. Vi forslår en visjon og flere mål, samt en ny og fleksibel lagstruktur. Vi beskriver nøkkelaktiviteter når det gjelder innovasjon, evaluering, og implementering, og presenterer en risikovurdering som kan støtte framtidig oppstart av et nytt maskinlæringslag. | |
dc.language.iso | eng | |
dc.publisher | Norwegian Institute of Public Health, NIPH | |
dc.relation.uri | https://www.fhi.no/globalassets/dokumenterfiler/rapporter/2021/aims-and-strategy-for-the-implementation-of-machine-learning-in-evidence-synthesis-report-2021.pdf | |
dc.subject.mesh | Machine learning | en |
dc.subject.mesh | Technology Assessment, Biomedical | en |
dc.subject.mesh | Unsupervised Machine Learning | en |
dc.subject.mesh | Supervised machine learning | en |
dc.subject.mesh | Systematic review | en |
dc.subject.mesh | Deep Learning | en |
dc.subject.mesh | Dyp læring | no |
dc.subject.mesh | Hierarkisk læring | no |
dc.subject.mesh | Ikke-overvåket maskininlæring | no |
dc.subject.mesh | Veiledet maskinlæring | no |
dc.subject.mesh | Systematisk oversikt | no |
dc.title | Aims and strategy for the implementation of machine learning in evidence synthesis in the Cluster for Reviews and Health Technology Assessments for 2021-2022 | |
dc.title.alternative | Mål og strategi for implementering av maskinlæring i kunnskapsoppsummeringer i klynge for vurdering av tiltak 2021- 2022 | |
dc.type | Research report | |
dc.description.version | publishedVersion | |
dc.source.pagenumber | 19 | |
dc.identifier.cristin | 1934431 | |
cristin.ispublished | true | |
cristin.fulltext | original | |