2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Portefølje Naturvitenskap og teknologi ikon

The research system

Portefølje Humaniora og samfunnsvitenskap ikon

Ground-breaking research

Portefølje Samisk ikon

Sámi society and culture

Portefølje Demokrati, styring og fornyelse ikon

Democracy and global development

Portefølje Velferd, kultur og samfunn ikon

Welfare, culture and society

Portefølje Helse ikon

Health

Portefølje Klima- og polarforskning ikon

Climate and environment

Portefølje Landbasert mat, miljø og bioressurser ikon

Land-based food, the environment and bioresources

Portefølje Energi, transport og lavutslipp ikon

Energy and transport

Portefølje Muliggjørende teknologier ikon

Enabling technologies

Portefølje Industri og tjenestenæringer ikon

Innovation

LTP Climate, environment and environmentally friendly energy

Climate and loss of natural diversity

Internationalization

Societal security and civil preparedness

Renewal in the public sector

Velferdstjenester

Frontpage Image

Marine icon

Petroleum og mineraler

LTP Hav ikon

Oceans and coastal areas

LTP2 Muliggjørende og industrielle teknologier ikon

Enabling and industrial technologies

Trust and community

Professional environment

High quality and accessibility

LTP Climate

Strengthened competitiveness and innovation capacity

LPT Health

 An innovative business community

LTP3 Helse

Portefolje Petroleum Ikon

Portefølje Hav ikon

Portefølje Utdanning og kompetanse ikon

Portefølje Global utvikling og internasjonale relasjoner ikon

Portefølje Livsvitenskap ikon

LTP2 Styrket konkurransekraft og innovasjonsevne ikon

LTP2 Utvikle fagmiljøer av fremragende kvalitet

LTP2 Samfunnssikkerhet og samhørighet ikon

LTP2 Fornyelse i offentlig sektor ikon

LTP2 Klima, miljø og miljøvennlig energi ikon

Forsidebilde optimalisert

project-bank-technical

Et innovativt næringsliv ikon

Muliggjørende teknologier bakgrunn

Marin bakgrunnsbilde

Marin ikon

Forsidebilde

Statistics

Prosjektbanken presenterer statistikk og informasjon om prosjekter med finansiering fra Forskningsrådet fra 2004. Statistikken er fordelt på blant annet tema, år, geografi og organisasjon. Prosjektbanken gir også detaljert informasjon om de enkelte prosjektene.

...or see the summary and other information about the projects you have selected

Portfolios

En god beskrivelse av denne siden for søkemotoroptimalisering

Forside

How the grants are distributed between organisations, counties, subject areas etc....

Here are some examples of searches you can perform in the Project Databank

All long term plan objectives

About Text Queries

No thematic area or topic related to the project

has received funding in the programme period

No popular science description is available

have received funding in the programme period

The project with project number {{project number}} was not found

Technical description

Woops, something went wrong. Please refresh the page. If the error persists, please contact us.

We could not find what you were looking for

See statistics related to this LTP objective

See projects related to this LTP objective

related to this LTP objective have received grants

has been granted to projects related to this LTP objective

has been granted to projects related to this portfolio

related to this portfolio have received grants

About Prosjektbanken

Kunnskapsdepartement

Helse- og omsorgsdep

Arbeids- og inkluder

Barne- og familedepa

Justis- og beredskap

Diverse

Forsvarsdepartemente

Kommunal-og distrikt

Samferdselsdeparteme

Digitaliserings- og 

Nærings- og fiskerid

Medisin og helsefag

Matematikk og naturvitenskap

Akershus

Oslo

LTP3 Styrket konkurransekraft og innovasjonsevne

LTP3 Et kunnskapsintensivt næringsliv i hele landet

LTP3 Innovasjon i stat og kommune

LTP3 Høy kvalitet og tilgjengelighet

LTP3 Fagmiljøer og talenter

LTP3 Muliggjørende og industrielle teknologier

LTP3 IKT og digital transformasjon

Helseforetak

Instituttsektor

Portefølje Helse

Portefølje Forskningssystemet

Portefølje Banebrytende forskning

Portefølje Innovasjon

Portefølje Muliggjørende teknologier

Programmer

Storbritannia

Sverige

Forskerprosjekt

Kompetanse- og samarbeidsprosjekt

Politikk- og forvaltningsområder

Helse

Internasjonalisering

IKT forskningsområde

Anvendt forskning

Bransjer og næringer

Digitalisering og bruk av IKT

Fornyelse og innovasjon i offentlig sektor

Kjønnsperspektiver i forskning

Responsible Research & Innovation

Grunnforskning

Tjenesterettet FoU

Integrated Research Infrastructure Services for Climate Change risks

Adaptation to climate change requires in-depth understanding of climate change driven risks, including their determinants (hazards, exposure and vulnerabilities) and impacts to human, production and natural systems. Integrated Research Infrastructure Services for Climate Change Risks (IRISCC) is a consortium of diverse and complementary leading research infrastructures (RIs) covering disciplines from natural sciences to social sciences, across different domains and sectors. IRISCC provides scientific and knowledge services to foster cutting-edge research and evidence-based policymaking to improve Europe's resilience to climate change. IRISCC ensures a “one-stop-shop” for various user communities on climate change risk related RI services by setting up a dedicated Catalogue of services and related access management system both for granting transnational (onsite and remote) and offering virtual access. The Catalogue of services will be built through three consecutive releases, each delivering increasingly integrated services to its user communities. The IRISCC service integration will include Service Design Labs employing co-design and transdisciplinary action, and Service Demonstrators benchmarking the integrated cross-RI services. In addition to services aimed towards the scientific community, IRISCC will offer knowledge services aimed towards policymakers and other stakeholders. This is done together with risk management platforms. The research enabled by IRISCC contributes to future reports on climate change effects (IPCC, IPBES) as well as policy- and decision-making to meet the targets of climate adaptation strategies. IRISCC contributes to training a new generation of scientists to efficiently use RI services and for data stewardship. Data from IRISCC will be open and made available in compliance with FAIR principles and linked to European initiatives such as EOSC. Strong links will be created between IRISCC and current and future efforts under Horizon Europe.

International Platform on Obstetric Violence (IPOV): an innovative tool for a respectful maternity and  childbirth care

Over-medicalisation and disrespect in maternity and childbirth care have been identified by international research as an urgent global public health topic (WHO 2014, Simonovic 2019, Council of Europe 2019). The IPOV-RESPECTFUL CARE project intends to bring attention to obstetric violence and respectful maternity and childbirth care by implementing a concrete tool—the International Platform on Obstetric Violence—to bridge academic research and public policy, training for health professionals, women’s perspectives and public engagement on the matter. The Platform will be an innovative, international, interdisciplinary, intersectoral and cross-cultural digital and interactive tool for producing, sharing and transferring knowledge, systematising and exchanging good practices, acquiring skills and planning gender -based innovative training packages on respectful maternity and childbirth care among health professionals, health training managers, decision makers, researchers, women and all of society. To achieve these goals, a network of 39 breakthrough experts, from 19 participating organisations and 9 countries (universities, research centres, civil organisations and health maternity care institutions) will be established.

Concept development for a research infrastructure to manage, integrate and sustain large medical cohort studies

The INTEGRATE-LMedC consortium will develop a new concept to guide and support decision-making for the next-generation research infrastructure (RI) to facilitate efficient utilization and harmonization of large medical cohorts (LMedC), and to accelerate scientific and medical breakthroughs in Europe and beyond. Achievement of the ambitious objectives will only be possible through the integration of 11 highly interdisciplinary partners including established ERIC / ESFRI infrastructures such BBMRI,  ECRIN, EIRENE and EBRAINS with unique expertise in conceptualizing and implementing European RIs. The partners will generate a gap analysis to identify what is missing of cohort data and samples, RI tools and services, quality measures, governance models, user needs and the barriers for efficient utilization of these cohorts and RI, including ethical and legal frameworks. To identify IT technologies and architecture for suitable data stewardship and long-term availability of European RIs, the partners will prepare for a feasibility study for federated data analysis of LMedC. The feasibility study will be based on two examples of use-cases: one stroke case using data from medical health registry data and one case using data from longitudinal population-based studies with different technical, legal, and ethical challenges. To ensure availability of data and samples related to existing and future LMedC studies and their re-use for secondary research, the partners will develop a concept outline including a governance plan and guiding principles for data access policies and data protection policy, whilst considering the FAIR principles and ELSI issues. An overarching RI concept to manage, integrate, and sustain LMedC studies will be developed, including an initial financial and operational plan for the implementation of the new RI outlining new services and access opportunities for the research community.

REGULAR AND UNPLANNED CARE ADAPTIVE DASHBOARD FOR CROSS–BORDER EMERGENCIES

During cross-border health emergencies, health and care services may be overwhelmed by high numbers of patients requiring unplanned care. Delays and backlogs in regular care, as a result of the stretched health care system, leave millions of patients with regular care needs unattended, resulting in disastrous healthcare outcomes. If poor healthcare outcomes across the population are to be avoided, healthcare systems must become more resilient and flexible and allow for rapid changes in the care delivery services. RAPIDE’s aim is to develop, validate and demonstrate a portfolio of powerful tools that enable healthcare systems to build in robustness of decisions, resilience of the health care professionals and patients and flexibility in the modalities of care delivery, thereby maintaining access to regular care during health emergencies.   RAPIDE emphasises opportunities for optimising in-hospital care, but also for relocating care from hospitals to community and home environments without loss of care quality. Thus, the project focuses on two closely-linked challenges – 1: Identifying and predicting how much care, and which care, needs to be moved along the care chain; 2: Identifying and verifying effective, feasible and acceptable ways to make this reconfiguration of care a reality. This will be achieved by (a) resource modelling, which builds comprehensive foresight and forecasting solutions and links them to patient flows optimization, along the whole chain of care, (b) selecting and implementing the best available tools to deliver regular care in new ways. To ensure usability, acceptability and equitable real-world value, RAPIDE will be co-designed and co-validated with stakeholders, from patients, GPs, clinicians and hospital managers to health ministries, pandemic-management and public health agencies. A Table Top Exercise and extensive communication and dissemination will raise awareness of the project’s successes.

Transition to safe & sustainable food systems through new & innovative detection methods & digital solutions for plant-based products derived from new genomic techniques, under a co-creation approach

DARWIN aims to contribute to a fair, healthy, safe and environmentally friendly food system by co-developing an innovative detection strategy by integrating targeted analytical PCR-based methods, untargeted sequencing methods, and digital solutions. A new generation of innovative and reliable DNA-based analytical detection methods, ranging from enhanced PCR methods for NGT detection, identification and quantification in single and multi-target systems, to untargeted sequencing methods related to whole-genome sequencing, laser capture microdissection-based sequencing and high throughput metagenomics sequencing for NGT screening and characterization. DARWIN will bring a cutting-edge approach developing genetic fingerprints using artificial intelligence to overcome challenges related to event-specific targeted methods, unambiguously identifying specific NGT lines. DARWIN also brings innovation in the new application of digital solutions such as data spaces and documentation-based screening to increase the data evidence to NGTs; blockchains to enable transparent and traceable detection along the food chain; AI models; and a Decision Support System to improve accuracy and support the selection of the best fit for purpose detection methods. DARWIN will reach TRL4-5 though validation including in-house, transferability and full trials, and presenting 3 cases representative of real situations relevant for NGT products in the EU agri-food market. After methods validation and the definition of a clear oriented detection strategy, DARWIN will theoretically extrapolate its finding to more complex scenarios encountering the diversity of NGT lines and food products that might reach EU markets. All this, under an interdisciplinary co-creation ecosystem based on Responsible Research and innovation (RRI) principals, empowering a wide variety of stakeholders - including consumers - in Europe and internationally; and robustly contributing to the policy making.

Internal Fortress: Regulating European Freedom of Movement within the Nation-State, 1950-1980

Against the prevailing view that freedom of movement lowered internal barriers to movement while raising walls against outsiders to create a ‘fortress Europe,’ this project investigates how the introduction of freedom of movement may have strengthened national political authority over European migration within the member states of the European Economic Community (EEC). InternalFortress suggests that as governments gradually lifted entry restrictions across the EEC, they also built out new internal administrative machinery to insert ‘Community migrants’ into key areas of social and economic life, placing migrants from outside the bloc at a disadvantage within local communities. The project explores this hypothesis in three key areas: social security, skill development, and union participation. The PI will lead a team of two PhD researchers and one postdoc to deploy a methodologically innovative multi-layered research program that analyses the interplay between national, European, and international institutions, as well as the private NGO networks that flowed between those formal frameworks. In contrast to previous histories of freedom of movement, which explain policy outcomes leading up to today’s regime of European citizenship, InternalFortress makes an important interpretive innovation by focusing squarely on the early process of transition from the 1950s to the 1970s. The project will investigate how the improvised nature of early integration created gaps and tensions that were consolidated in the 1970s as national and regional migration policies settled into more rigid patterns. InternalFortress suggests that policies behind the border matter as much as policies at the border for understanding the acrimonious debates around European migration that continue through the present.

Interoperable applications suite to enhance European identity and document Security and fraud detection

Combatting frauds on identity and travel documents is a key mission of law enforcement agencies and border guards. Industries have been working on new means to combat frauds on identity, and public authorities are using numerous technologies to accomplish their mission, but permanent innovation is required to fight highly skilled defrauders. A number of European innovation projects have tested new ways to combat fraud but few of them reached an operational level. EINSTEIN objectives is to enhance significantly existing public authorities’ means through innovation, building on technologies proven in the labs but not mature for an operational usage yet. EINSTEIN will deliver six applications essential to fight identity frauds: 1) online ID issuance using a secure cloud-based server for real-time biometric quality checks and fraud detection, 2) mobile document and identity checks using commercially available smartphones, 3) document authentication module to detect fraudulent documents, 4) pre-registration for land-border crossings including biometrics and DTC, 5) EES kiosk with advanced fraud detection using video surveillance, 6) fast track for enrolled travelers using on-the-move face and iris. To ensure TRL7 at a minimum, practitioners will run six different pilot use cases in their own environment. A key objective is also to ensure interoperability and flexibility of all the components developed in the project so that they can be reused in different contexts, possibly by different providers. Design of open, well-defined, standardized interfaces will allow achieving this objective. Privacy being an essential concern of all European citizens and governments, EINSTEIN will take into account privacy-by-design principles, developing flexible components to ease their customization in order to meet not only the European legislation on data protection but also national legislations on this matter, which vary significantly from one country to the other. 

Waste in humanitarian Operations: Reduction and Minimisation

Waste in humanitarian Operations: Reduction and Minimisation (WORM)'s overall objective is designing guidelines and support actions for circular economy in the humanitarian sector. WORM focuses on two selected settings: field hospital deployments, and humanitarian livelihood programmes with a waste picking component. Across these settings, the project focuses on several cross-cutting focus areas:  •	the integration of bio-based technological innovation solutions in the humanitarian context,  •	using procurement as a gatekeeper for waste avoidance, and gateway to integrate innovative solutions,  •	improvements in waste management, and the use of less polluting waste treatment methods,  •	a specific focus on the sustainable livelihoods of waste pickers, and  •	policy development, advocacy and a heightened local awareness of improved waste management in the relevant local contexts. Following a multi-actor approach, WORM brings together medical humanitarian organisations and humanitarian organisations with livelihood programmes with innovation and supplier clusters, procurement service providers, logistics service providers, waste management service providers and academic partners. WORM seeks to involve a myriad of different stakeholders in data collection and policy development, including but not limited to, humanitarian actors positioned in the field during an operation, local waste management companies, start-ups focusing on bio-based solutions, policymakers (both local and global), and research institutions. WORM includes partners from low- and middle-income countries (esp. Kenya, Viet Nam) since humanitarian operations are often implemented in these contexts. WORM will focus on these contexts in their local awareness campaigns for improved waste management.

Supporting Policy Regulations and Interventions to Negate aggravated Global diarrheal disease due to future climate Shocks

BACKGROUND: Global warming and climate extremes such as heavy precipitation, flooding, and drought are increasing risks for waterborne diarrheal disease. While these effects already burden low- and middle-income countries, where diarrheal diseases are the second leading cause of childhood deaths, Europe has shared and underappreciated vulnerabilities. There is an urgent need to prepare and protect our water and communities from these threats. AIM: To inform key climate, environmental, and health adaptation policies, in order to support and prepare citizens, communities and governments by better measuring the impact of future climate shocks on the burden of water-borne diarrheal diseases. APPROACH: We bring together scientists from climate, environment, health, and social sciences to collaborate with communities, industry, public authorities and policy makers across socioeconomic settings. We will model the future impact of global climate change, on local water quality and quantity, and diarrheal disease outcomes. In case studies in Ghana, Tanzania, Italy, and Romania, we will measure current interactions of climate, behaviour, and water quality on pathogen-specific diarrheal disease risks and the safety of water supply systems. We will engage individuals and communities to understand situated understandings and practices to improve risk communication and ownership. With policy makers, we will design appraisal structures to assess the economic impact and value of planetary health interventions to prevent climate-related diarrheal disease. IMPACT: SPRINGS will improve integrated climate and health surveillance, create climate-resilient water supply systems, engage citizens and stakeholders, and use evidence-based value assessments to prioritise interventions to prevent climate-induced diarrheal disease.  Long term adaptive capacity and climate-resilience will increase in Europe and beyond, preventing unnecessary illness and deaths from waterborne diarrheal disease.

Den økende digitaliseringen av grunnleggende offentlige og private tjenester har ført med seg enorme fremskritt. Samtidig har det økt risikoen for flere og mer sofistikerte cyberangrep. Cyberangrep rettet mot kritiske sektorer som helse, finans og energi setter befolkningens liv i fare når de lykkes og er derfor blitt en stor bekymring. For å håndtere disse truslene har EU forslått flere lover for å forbedre både den digitale og fysiske motstandskraften til kritiske enheter og nettverk, inkludert Network and Information Systems Directive (NIS 2), Critical Entities Resilience Directive (CER) og Cyber Resilience Act (CRA). Fordi dette er et fagområde i utvikling med lite rettspraksis og annen veiledning, er det mangel på jurirdisk forskning. Der det er forskning er det ofte fragmentert mellom institusjoner og disipliner, noe som reduserer rekkevidden og påvirkningskraften.
CyberReg-nettverket samler et tverrfaglig team av forskere med mål om å fremme vitenskapelig utveksling og påvirkning ved å (1) stimulere til kollektiv forskningsinnsats og utvikle en felles forståelse for virkningen av lovforslag innen cybersikkerhet og (2) bygge broer mellom akademikere, beslutningstakere og industri for å bidra til et mer motstandsdyktig samfunn. For å nå disse målene vil nettverket fokusere på å besvare følgende spørsmål: (1) i hvilken grad adresserer de overnevnte lovforslagene cybertruslene samfunnet står overfor i dag? (2) Hvordan påvirker disse lovforslagene hverandre og eksisterende regler? (3) Hvordan skal vi bygge bro mellom generelle juridiske krav til cybersikkerhet og organisasjoners behov for å ha konkrete og handlingsrettede elementer? Nettverkets forskingsinnsats vil først og fremst fokusere på regulatorisk utvikling i EU og Norge, men vil også holde seg oppdatert på den globale utviklingen innen cybersikkerhetsnormer.

Cyberthreats have become a great societal concern. The increasing digitalisation of vital public and private services, together with the Russian invasion of Ukraine, has expanded the cyberthreat landscape, giving rise to new vulnerabilities and risks. To deal with this new reality, the EU has unveiled several legislative proposals that aim to bolster cyber and physical resilience of critical entities and networks. Key among these initiatives are the proposals for NIS 2 Directive, the Critical Entities Resilience Directive, the Cyber Resilience Act and the Secure Connectivity Act. These initiatives come on top of existing and upcoming legislative initiatives that address security such as the GDPR, proposals for eIDAS Regulation and the Artificial Intelligence Act. This creates a complex and dense regulatory landscape that requires scrutiny. The CyberReg Network brings together researchers with the aim of stimulating harmonized research efforts on these legislative initiatives and increase impact by engaging with, and disseminating insights to, key change agents from the public and private sectors. 

The activities of the Network will focus on the follwoing three key areas: 1) creating avenues to foster knowledge exchange with a view to developing shared understanding of the regulatory developments, their interaction and impact in addressing the cyberthreats; 2) creating support system for researchers to increase visibility and collaboration internationally, encourage publication in international journals, and thereby strengthen the quality of research; 3) increase the discovery and accessibility of research on cyberthreats and associated regulatory developments and thereby improve the ability of industry, policymakers, and students to better understand and respond to the threats. The network will run for four years and will bring together an interdisciplinary team comprising researchers from BI, UiO, UiT, Politihøyskolen, TUM and University of Luzern.

Research Network on Regulatory Developments in Cybersecurity

STUD: Cookie Switch AS
Verktøy for administrasjon av informasjonskapsler

Midlene fra FORNY20-FORNY2020 fordelt på år

Midlene fra FORNY20-FORNY2020 fordelt på fylker

Midlene fra FORNY20-FORNY2020 fordelt på fagområde

Student

Cookie Switch gjør det mulig for bedrifter å bli kompatible med EUs personvern- og databeskyttelseslover som regulerer bruken av informasjonskapsler (cookies) på nettstedet deres. Den gjør det ved å gi hvem som helst mulighet til enkelt å lage et juridisk kompatibelt og etisk informasjonskapselbanner, samtidig som det ikke går på bekostning av besøkende på nettstedet til å ta en informert beslutning om hvilke informasjonskapsler og lignende sporingsteknologier de samtykker til.

STUD-ENT-tilskuddet var sentralt for å utvikle Cookie Management Platform som hjelper virksomheten med å: 1) identifisere informasjonskapsler og lignende teknologier som brukes av deres nettsteder; 2) raskt generere et juridisk kompatibelt, etisk og tilpassbart informasjonskapselbanner og 3) publisere et informasjonskapselbanner som kun vil tillate informasjonskapsler som en besøkende på nettstedet godtar. Dessuten er plattformen designet for brukere uten teknisk og juridisk ekspertise for å lette og demokratisere overholdelse av lover.

Målet med prosjektet var å fjerne det nåværende problemet som er at små og mellomstore bedrifter uten programmering og juridisk ekspertise ikke kan gjøre nettstedet sitt i samsvar med EUs personvern- og databeskyttelseslover uten å ansette konsulenter, selv være eksperter på juss og teknologi eller bruke eksisterende kostbare. løsninger som kanskje ikke sikrer overholdelse av relevante lover. I tillegg var målet også å lage en plattform som vil gjøre det mulig å lage eksklusivt etiske by-design cookie-bannere som gir besøkende like muligheter til å enten godta eller avslå informasjonskapsler uten å bli dyttet og presset av «dark patterns» og «cookie walls» slik det er i dag.

I løpet av prosjektets varighet har teamet nådd alle fastsatte milepæler. Den første var å utvikle en innovativ cookie bot-løsning som skanner nettsiden for informasjonskapsler og leverer rapporter om brukte informasjonskapsler etter kategori (essensielt, funksjonelt, analytisk, markedsføring). Den andre var etableringen av etisk design og lovlig kompatible tilpassbare informasjonskapselbannere som gjør det lettere for nettstedeiere å overholde personvernlovgivningen. Den tredje milepælen var å utvikle et nettsted der enkeltpersoner kan teste nettstedet sitt for informasjonskapsler gratis, lære hvilke informasjonskapsler de bruker og om de trenger et informasjonskapselbanner eller ikke. Den fjerde milepælen var å utvikle en plattform for håndtering av informasjonskapsler som vil gjøre det mulig for brukere å lage et etisk banner for informasjonskapsler og administrere informasjonskapsler. Den femte og siste milepælen var produktlanseringen og å gjøre det tilgjengelig for et bredere publikum. Takk til STUD-ENT som gjorde det mulig for oss å utvikle en plattform som tjener interessene til både kundene og sluttbrukerne.

STUD: Cookie Switch AS
Cookie Management Tool

AIforScreening: Robust og pålitelig AI for brystkreftscreening
Dette forskningsprosjektet ser på metoder og tilnærminger for å oppnå robust og pålitelig kunstig intelligens (AI) til bruk for analyse av mammogrammer i brystkreftscreening. Prosjektet ledes av Norsk Regnesentral, med eksperter innen bildeanalyse og AI, og gjennomføres i samarbeid med et team av medisinske eksperter fra Kreftregisteret, de norske brystsentrene og Karolinska Universitetssykehus. 

Prosjektet har som mål å bidra til forskning og utvikling av metoder som kan gi robuste og pålitelige AI-metoder for mammografi-screening. Bruk av AI innenfor slik screening kan gi økt kapasitet og bidra til å oppdage flere krefttilfeller. Det kan igjen bety sparte liv og en forbedret helsetjeneste, men krever at en har AI-løsninger som virker over tid og er pålitelige. Det er også et behov for å forstå effektene av å introdusere og bruke AI i en slik sammenheng.

Kunstig intelligens ved bruk av dype nevrale nettverk har vist et potensiale til å kunne øke sensitiviteten for å oppdage kreft i mammografi-screening. Det antyder at AI kan ha en rolle som bidrag til å oppdage kreft tidlig. Den virkelige verden er imidlertid mye mer kompleks og mangfoldig enn de kontrollerte forskningsomgivelsene der dette har vært testet. Det er derfor et behov for å se nærmere på hva som skal til for å bringe dagens lovende resultater videre ut til den virkelige verden og sykehushverdagen.

For å adressere dette ser vi på hvordan en kan oppnå robust AI-screening over tid gjennom utvikling av metoder som kan håndtere variasjoner i bilder mellom laboratorier og over tid, som kan utnytte data fra flere undersøkelser og som er tilpasset bruk i en klinisk sammenheng i kombinasjon med radiologens analyse. Vi vil også se på hvordan vi kan sikre at tilnærmingene er pålitelige gjennom å se på metoder for å forklare og forstå AI-resultatene og studere hvordan integrasjon av AI i prosessen kan påvirke radiologens beslutninger.

Prosjektet startet i sommer og hittil var vi arbeidet meste med å få tilgang til data og godkjenninger av hensyn til personvernet. Vi har laget en første AI-algoritme som har lovende resultater og et godt utgangspunkt for videre arbeid.

This research project will develop AI methods and approaches for robust, sustainable and trustworthy breast cancer screening with mammography. We expect findings will be transferable to other medical screening programs.

Breast cancer is the most common cancer and the leading cause of cancer death among women worldwide. Early detection of breast cancer through screening is recommended by international health organizations to reduce this mortality. It is considered to expand the screening program by examining more women. The use of AI can lead to a larger capacity to do screening and detect cancers, reduce overdiagnosis, and by this save lives and give new opportunities for improved health services.

Furthermore, we need to understand the effects of using AI in this context. To address this, the project will involve AI experts, medical experts, organizers and practitioners within mammographic screening to create a strong interdisciplinary team.

The main novelties of the proposed project are:
* Develop methods that can handle domain shifts without costly annotation of new data. Current methods have problems handing images from different equipment, operators and cohorts. 
* Exploitation of time series in AI breast cancer screening. Radiologists exploit prior mammograms when doing their manual reading, while it is rarely used in current AI-based models.
* Interpretation of predictions from AI breast cancer models such that radiologists can understand the predictions. This gives trust and makes it easier to improve the AI method and combine this with manual reading by radiologists.
* Find the differences in the prediction between radiologist and AI both statistically and using data collected in the screening program as a basis when we combine the two methods. 
* Develop AI systems that is usable for radiologists in mammographic screening utilizing the strength of each approach. A new screening program should give better predictions and use less radiology resources.

AIforScreening: Robust and trustworthy AI for breast cancer screening with mammography

Hjerneslag er en vanlig årsak til sykdom, uførhet og død. I Norge anslås det at ca. 12 000 personer rammes årlig. Samspillet mellom sykehus, rehabiliteringsinstitusjoner og kommunale tjenester er omfattende og komplisert. I dette prosjektet studeres disse utfordringene for slagpasienter i Norge ved hjelp av statistisk modellering og simulering. Data som allerede er samlet inn for ca. 2 000 innleggelser ved slagenheten ved Akershus universitetssykehus, kombineres med nasjonale pasientdatabaser. Med statistiske modeller undersøkes det hvordan pasientegenskaper som alder, kjønn og bostedskommune henger sammen med utfallsmål som varighet av sykehusopphold, utnyttelse av rehabilitering, angst, depresjon og helserelatert livskvalitet. Det er også samlet inn opplysninger om pårørende til slagpasientene, blant annet for å undersøke om deres mentale og fysiske helse påvirkes av slagtilfellet. I tillegg studeres tidstrender i forekomsten av slag. Analysene viser at det er betydelige regionale forskjeller, men også en sterk nedadgående trend, som mer enn oppveier effekten av eldrebølgen. For yngre folk (under 45 år) er forekomsten lav, men mer uendret over tid. Antall innleggelser i slagenhet av pasienter som viste seg ikke å ha slag er derimot på vei opp, så det blir ikke nødvendigvis lavere behov for kapasitet i landets slagenheter framover. De statistiske modellene som er utviklet, vil sammen med befolkningsmodeller fra Statistisk sentralbyrå kunne gi prognoser for pasientstrømmen gjennom behandlings- og rehabiliteringstilbudene for slagpasienter i Norge. Prosjektet har samarbeidet med et forskningsmiljø i Melbourne og undersøkt forskjeller og likheter i behandling av slag i Norge og Australia.

This project will study the treatment and rehabilitation of stroke patients in Norway through statistical and simulation based modelling.
We will use standard statistical modelling techniques to analyze and represent associations and causal effects among  patient parameters like age, sex, socio-economic status and ethnicity and dependent variables like length of hospital stay, duration of rehabilitation, level of anxiety and depression and health related quality of life. We will develop discrete event simu lation models to describe the different paths that stroke patients follow through treatment and rehabilitation. We plan to make separate sub-models for the different phases of the disease: An Incidence model represents the random events of new stroke case s in the population. A Pre-hospital model represents the phase until hospitalization. A hospital?s stroke unit model represents internal queues, radiology and treatment processes. A rehabilitation model describes factors that govern the utilization of reh abilitation resources. A long-term care model represents duration and level of care, while a municipality model describes the local support that the patient receives. On top of all this we develop a demography model that represents time trends in the popu lation, which enables us to analyze how the treatment-rehabilitation machinery will respond to an ageing population. The analysis will uncover social and ethnic inequalities, as well as suboptimal current use of resources, which can be rectified. The pred ictions of future demands for treatment and rehabilitation will help us to identify bottlenecks before they become a problem. The Ahus project NOR-SPOT has collected detailed follow-up data from 1908 admissions to the stroke unit. In addition we will util ize national databases like the Norwegian Patient Registry. The combination of NOR-SPOT data and more coarse data for the entire Norwegian stroke population will enable us to analyze both in depth and width.

Modelling treatment and rehabilitation of stroke patients - 
Using simulation to evaluate the present and plan for the future

En del av prosjektet dreide seg om modellering av pasientbehandling i sykehussektoren, for å beregne hvordan kostnadene sannsynligvis vil endre seg over de neste 10-årene. Dette er komplisert, fordi kostnadene påvirkes av befolkningens alderssammensetning, samtidig som teknologiske endringer og omorganisering spiller inn. Generelt viser undersøkelser at sykehuskostnadene pr år er høyere for eldre enn yngre innbyggere. Et spørsmål er om dette skyldes alderen i seg selv, eller om det er gjenstående levetid som er avgjørende for kostnadene. Dette er viktig, fordi forventet levealder stadig er på vei opp, og hvis det er avslutningen på livet som trekker kostnader, heller enn alder i seg selv, betyr det at eldrebølgen ikke vil bli så kostbar som kan kunne frykte. Prosjektet har analysert data over sykehusinnleggelser i Norge i perioden 1998 - 2010, og blant annet funnet ut at det siste leveåret står for ca 10 % av kostnadene. I tillegg viser dataene at kurven som viser kostnader som funksjon av alder stadig blir brattere (kalt "steepening"), som betyr at kostnadene til behandling av eldre øker mer enn for yngre innbyggere. Denne delen av prosjektet har resultert i en doktorgrad for Fredrik Alexander Gregersen, basert på fire publiserte vitenskapelige arbeider.
Den andre hoveddelen av prosjektet har omhandlet slagpasienter. Det er gjennomført en datainnsamling i slagenheten ved Akershus universitetssykehus, hvor nær 2000 innleggelser er registrert. Medisinske data er samlet inn og pasientene har fylt inn spørreskjemaer om funksjon og livskvalitet. Oppfølgingsdata om helsetilstand og rehabilitering er samlet inn etter 3 og 12 måneder, og inkluderer informasjon om arbeidsbelastning og helsetilstand for pårørende til pasientene. Foreløpige analyser viser interessante sammenhenger blant annet mellom depresjon og ønske om rehabilitering, som vil publiseres i vitenskapelige tidsskrifter.
Prosjektet har også bidratt med løpende analyser av sykehusets pasientlogistikk innen operasjonsaktivitet og akuttmottak.


To reach important health policy goals the Norwegian health care system has undergone comprehensive reforms the latest years, and in policy documents further changes and adjustments are suggested. With the complexity and interdependency that characterize  the health care system it might be difficult to predict the exact consequences of changes, and it follows that unexpected effects on patient flow and health care costs might occur. The aim of this project is to develop problem oriented simulation models f or the health care sector that can be a tool for policymakers in their striving to adjust and develop health policy means. The project is important, as health care is a large sector, for which policymakers lack valid prediction models.

0 projects

IKTPLUSS-IKT og digital innovasjon

AIforScreening: Robust and trustworthy AI for breast cancer screening with mammography

Awarded: NOK 12.0 mill.

Project Period: 2021-2025

Location: Oslo

HELSEVEL-H-Gode og effektive helse-, omsorgs- og velferdstjenester

Modelling treatment and rehabilitation of stroke patients - Using simulation to evaluate the present and plan for the future

Awarded: NOK 6.7 mill.

Project Period: 2015-2019

Location: Akershus

TJENESTER-Helse- og omsorgstjenester

Simulating patient flow and health care costs in Norway

Awarded: NOK 5.4 mill.

Project Period: 2010-2014

Location: Akershus