Photo: Privat
Karl Øyvind Mikalsen
Job description
Jeg har doktorgrad i medisinsk kunstig intelligens (KI) og forsker på utvikling og bruk av KI i helsetjenesten. Jeg jobber med å analysere medisinske bilder, tale og tekst ved hjelp av språkmodeller og maskinlæring. Et eksempel er bruk av språkmodeller for å anonymisere pasientjournaler.
Jeg tester også nye KI-verktøy, for å vurdere om vi kan bruke dem i helsetjenesten. Forskningen er et samarbeid mellom ulike fagmiljøer på UiT og universitetssykehuset UNN.
Taridzo Chomutare,
Therese Olsen Svenning,
Miguel Angel Tejedor Hernandez,
Phuong Dinh Ngo,
Andrius Budrionis,
Kaisa Markljung
et al.:
Artificial Intelligence to Improve Clinical Coding Practice in Scandinavia: Crossover Randomized Controlled Trial
Kjersti Mevik,
Ashenafi Zebene Woldaregay,
Alexander Ringdal,
Karl Øyvind Mikalsen,
Yuan Xu
:
Exploring surgical infection prediction: A comparative study of established risk indexes and a novel model
Taridzo Fred Chomutare,
Anastasios Lamproudis,
Andrius Budrionis,
Therese Olsen Svenning,
Lill Irene Hind,
Phuong Dinh Ngo
et al.:
Improving Quality of ICD-10 (International Statistical Classification of Diseases, Tenth Revision) Coding Using AI: Protocol for a Crossover Randomized Controlled Trial
Jørgen Aarmo Lund,
Per Joel Burman Burman,
Ashenafi Zebene Woldaregay,
Robert Jenssen,
Karl Øyvind Mikalsen
:
Instruction-guided deidentification with synthetic test cases for Norwegian clinical text
Proceedings of Machine Learning Research (PMLR) 2024 ARKIV
Helge Ingvart Fredriksen,
Per Joel Burman Burman,
Ashenafi Zebene Woldaregay,
Karl Øyvind Mikalsen,
Ståle Haugset Nymo
:
Categorization of phenotype trajectories utilizing transformers on clinical time-series
Marthe Larsen,
Camilla Flåt Olstad,
Christoph I. Lee,
Tone Hovda,
Solveig Kristin Roth Hoff,
Marit Almenning Martiniussen
et al.:
Performance of an Artificial Intelligence System for Breast Cancer Detection on Screening Mammograms from BreastScreen Norway
Marthe Larsen,
Camilla Flåt Olstad,
Henrik Wethe Koch,
Marit Almenning Martiniussen,
Solveig Kristin Roth Hoff,
Håkon Lund-Hanssen
et al.:
AI Risk Score on Screening Mammograms Preceding Breast Cancer Diagnosis
Kristoffer Wickstrøm,
Daniel Johansen Trosten,
Sigurd Eivindson Løkse,
Ahcene Boubekki,
Karl Øyvind Mikalsen,
Michael Kampffmeyer
et al.:
RELAX: Representation Learning Explainability
Ane Blazquez-Garcia,
Kristoffer Knutsen Wickstrøm,
Shujian Yu,
Karl Øyvind Mikalsen,
Ahcene Boubekki,
Angel Conde
et al.:
Selective Imputation for Multivariate Time Series Datasets with Missing Values
Kristoffer Wickstrøm,
Eirik Agnalt Østmo,
Keyur Radiya,
Karl Øyvind Mikalsen,
Michael Kampffmeyer,
Robert Jenssen
:
A clinically motivated self-supervised approach for content-based image retrieval of CT liver images
Keyur Radiya,
Henrik Lykke Joakimsen,
Karl Øyvind Mikalsen,
Eirik Kjus Aahlin,
Rolf Ole Lindsetmo,
Kim Erlend Mortensen
:
Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review
Kristoffer Wickstrøm,
Michael Kampffmeyer,
Karl Øyvind Mikalsen,
Robert Jenssen
:
Mixing up contrastive learning: Self-supervised representation learning for time series
Mathias K. Hauglid,
Karl Øyvind Mikalsen
:
Tilgang til helseopplysninger i maskinlæringsprosjekter
Kristoffer Wickstrøm,
Juan Emmanuel Johnson,
Sigurd Eivindson Løkse,
Gusatu Camps-Valls,
Karl Øyvind Mikalsen,
Michael Kampffmeyer
et al.:
The Kernelized Taylor Diagram
Kristoffer Knutsen Wickstrøm,
Karl Oyvind Mikalsen,
Michael Kampffmeyer,
Arthur Revhaug,
Robert Jenssen
:
Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
Karl Øyvind Mikalsen,
Cristina Soguero Ruiz,
Filippo Maria Bianchi,
Arthur Revhaug,
Robert Jenssen
:
Time series cluster kernels to exploit informative missingness and incomplete label information
Ahcene Boubekki,
Jonas Nordhaug Myhre,
Luigi Tommaso Luppino,
Karl Øyvind Mikalsen,
Arthur Revhaug,
Robert Jenssen
:
Clinically relevant features for predicting the severity of surgical site infections
Karl Øyvind Mikalsen,
Cristina Soguero Ruiz,
Robert Jenssen
:
A Kernel to Exploit Informative Missingness in Multivariate Time Series from EHRs
2020 ARKIV
Primoz Kocbek,
Nino Fijacko,
Cristina Soguero Ruiz,
Karl Øyvind Mikalsen,
Uros Maver,
Petra Povalej Brzan
et al.:
Maximizing Interpretability and Cost-Effectiveness of Surgical Site Infection (SSI) Predictive Models Using Feature-Specific Regularized Logistic Regression on Preoperative Temporal Data
Karl Øyvind Mikalsen,
Cristina Soguero-Ruiz,
Filippo Maria Bianchi,
Robert Jenssen
:
Noisy multi-label semi-supervised dimensionality reduction
Filippo Maria Bianchi,
Lorenzo Livi,
Karl Øyvind Mikalsen,
Michael C. Kampffmeyer,
Robert Jenssen
:
Learning representations of multivariate time series with missing data
Filippo Maria Bianchi,
Karl Øyvind Mikalsen,
Robert Jenssen
:
Learning compressed representations of blood samples time series with missing data
2018 DOI
Karl Øyvind Mikalsen,
Cristina Soguero-Ruiz,
Inmaculada Mora-Jiménez,
Isabel Caballero López Fando,
Robert Jenssen
:
Using multi-anchors to identify patients suffering from multimorbidities
2018 DOI
Andreas Storvik Strauman,
Filippo Maria Bianchi,
Karl Øyvind Mikalsen,
Michael C. Kampffmeyer,
Cristina Soguero-Ruiz,
Robert Jenssen
:
Classification of postoperative surgical site infections from blood measurements with missing data using recurrent neural networks
2018 DOI
Mads Adrian Hansen,
Karl Øyvind Mikalsen,
Michael C. Kampffmeyer,
Cristina Soguero-Ruiz,
Robert Jenssen
:
Towards deep anchor learning
2018 DOI
Karl Øyvind Mikalsen,
Filippo Maria Bianchi,
Cristina Soguero Ruiz,
Robert Jenssen
:
Time series cluster kernel for learning similarities between multivariate time series with missing data
Kasper Jensen,
Soguero-Ruiz Cristina,
Karl Øyvind Mikalsen,
Rolv-Ole Lindsetmo,
Irene Kouskoumvekaki,
Mark Girolami
et al.:
Analysis of free text in electronic health records for identification of cancer patient trajectories
Karl Øyvind Mikalsen,
Cristina Soguero Ruiz,
Kasper Jensen,
Kristian Hindberg,
Mads Gran,
Arthur Revhaug
et al.:
Using anchors from free text in electronic health records to diagnose postoperative delirium
Karl Øyvind Mikalsen,
Filippo Maria Bianchi,
Cristina Soguero Ruiz,
Robert Jenssen
:
The time series cluster kernel
2017
Jonas Nordhaug Myhre,
Robert Jenssen,
Karl Øyvind Mikalsen,
Sigurd Løkse
:
Robust clustering using a kNN mode seeking ensemble
Karl Øyvind Mikalsen,
Bjørn Anton Graff,
Kristine Bø,
Kurt Vanvik
:
I 2025 vil KI-samarbeidet virkelig komme helsepersonell til gode
17. Dezember 2025 DOI
Robert Jenssen,
Rolf Ole Lindsetmo,
Karl Øyvind Mikalsen,
Oddny Johnsen
:
Markerer Tromsøs fortrinn på kunstig intelligens
19. April 2024
Karl Øyvind Mikalsen,
Marte Stoksvik,
Karoline Skrøder,
Agnethe Eltoft,
Tommy Skar
:
Universitetssykehuset Nord-Norge bruker kunstig intelligens for bedre behandling av slag og blodpropp
10. September 2024
Joel Burman,
Elin Kile,
Karl Øyvind Mikalsen,
Samuel Kuttner
:
PET-MRI-based prediction models for classifying prostate cancer
2024
Anita Schumacher,
Lars Kristian Jenvin Hågensen,
Karl Øyvind Mikalsen,
Karl Ivar Lorentzen,
Grete Hansen,
Ken Inge Adolfsen
et al.:
UNN mener kunstig intelligens er veien videre: – Pasientene må ha tillit til at dette er trygt
01. Juli 2023
Kristoffer Knutsen Wickstrøm,
Daniel Johansen Trosten,
Sigurd Eivindson Løkse,
Karl Øyvind Mikalsen,
Michael Kampffmeyer,
Robert Jenssen
:
RELAX: Representation Learning Explainability
2022
Daniel Johansen Trosten,
Sigurd Eivindson Løkse,
Karl Øyvind Mikalsen,
Michael Kampffmeyer,
Robert Jenssen
:
RELAX: Representation Learning Explainability
2022
Kristoffer Wickstrøm,
Juan Emmanuel Johnson,
Sigurd Eivindson Løkse,
Gusatu Camps-Valls,
Karl Øyvind Mikalsen,
Michael Kampffmeyer
et al.:
The Kernelized Taylor Diagram
2022
Kristoffer Wickstrøm,
Eirik Agnalt Østmo,
Karl Øyvind Mikalsen,
Michael Kampffmeyer,
Robert Jenssen
:
Explaining representations for medical image retrieval
2022
Sigurd Eivindson Løkse,
Karl Øyvind Mikalsen,
Michael Kampffmeyer,
Robert Jenssen
:
Towards Explainable Representation Learning
2021
Sigurd Eivindson Løkse,
Michael Kampffmeyer,
Robert Jenssen,
Karl Øyvind Mikalsen
:
Towards Explainable Representation Learning
2021
Oscar Escudero-Arnanz,
Joaquín Rodríguez-Álvarez,
Karl Øyvind Mikalsen,
Robert Jenssen,
Cristina Soguero-Ruiz
:
On the Use of Time Series Kernel and Dimensionality Reduction to Identify the Acquisition of Antimicrobial Multidrug Resistance in the Intensive Care Unit
Karl Øyvind Mikalsen,
Finn Henry Hansen
:
Strategi for kunstig intelligens i Helse Nord 2022-2025
Kristoffer Knutsen Wickstrøm,
Sigurd Eivindson Løkse,
Karl Øyvind Mikalsen,
Michael Kampffmeyer,
Robert Jenssen
:
Towards Explainable Representation Learning
2021
Michael Kampffmeyer,
Robert Jenssen,
Karl Øyvind Mikalsen,
Sigurd Eivindson Løkse
:
Towards Explainable Representation Learning
2021
Kristoffer Knutsen Wickstrøm,
Karl Øyvind Mikalsen,
Michael Kampffmeyer,
Arthur Revhaug,
Robert Jenssen
:
Uncertainty-Aware Deep Ensembles for Explainable Time Series Prediction
2021
Michael Kampffmeyer,
Robert Jenssen,
Karl Øyvind Mikalsen,
Arthur Revhaug
:
Uncertainty-Aware Deep Ensembles for Explainable Time Series Prediction
2020
Karl Øyvind Mikalsen,
Robert Jenssen
:
Advancing Unsupervised and Weakly Supervised Learning with Emphasis on Data-Driven Healthcare
UiT Norges arktiske universitet 15. Februar 2019
Jonas Myhre,
Karl Øyvind Mikalsen,
Sigurd Løkse,
Robert Jenssen
:
Robust Non-Parametric Mode Clustering
2016
Karl Øyvind Mikalsen,
Filippo Maria Bianchi,
Cristina Soguero-Ruiz,
Stein Olav Skrøvseth,
Rolv-Ole Lindsetmo,
Arthur Revhaug
et al.:
Learning similarities between irregularly sampled short multivariate time series from EHRs
2016 ARKIV
The 50 latest publications is shown on this page. See all publications in Cristin here →
Research interests
Utvikling og bruk av kunstig intelligens innen medisin og helse.
Medlem av forskningsgruppen for gastrokirurgi og forskningsgruppen for maskinlæring, se http://machine-learning.uit.no/
Member of research group
CV
Førsteamanuensis, Institutt for klinisk medisin (UiT)
Avdelingsleder, Senter for pasientnær kunstig intelligens (UNN). www.spki.no