JAJakob Kristian Holm Andersen

Jakob Kristian Holm Andersen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jakob Kristian Holm Andersen has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Evaluation of spatial distribution of initial marking strategy among inexperienced graders in diabetic retinopathy: A retrospective cross‐sectional analysis

    by Simon Joel Ellerup Lowater, Andrea Blasi Núñez, Jakob Kristian Holm Andersen, Sebastian Dinesen, Thiusius Rajeeth Savarimuthu, Jakob Grauslund

    Background: Manual diabetic retinopathy (DR) grading may prefer certain regions and underestimate others. It is unclear if inexperienced graders' initial marking strategy reflects a specialist's marking pattern. Aims: By the virtual ocular learning platform (VIOLA), we evaluated if initial DR‐lesion markings among inexperienced graders spatially corresponded to a specialist‐based lesion map. Materials and Methods: We used retinal 6‐field VIOLA images with at least 500 DR‐lesion markings covering all DR‐levels (0–4) according to the international clinical diabetic retinopathy (ICDR) scale. We divided images into quadrants and counted the initial three markings per lesion type, per image, per grader. A retinal specialist served reference for annotation of all DR‐lesions. The primary outcome was difference in spatial distribution of DR‐markings across quadrants relative to the reference, further characterised with spatial metrics. p ‐Value < 0.05 indicated statistical significance. Results: Across 24 images, 97 graders marked 16 925 DR‐lesions: 1633 microaneurysms (MA), 3228 haemorrhages, 1549 hard exudates (HE), 3081 cotton wool spots (CWS), 3844 intraretinal microvascular abnormalities (IRMA), 1832 new vessels (NV) and 1758 panretinal photocoagulation scars (PRP). A difference was observed across all lesion types ( χ 2 ‐test, p < 0.001) relative to the reference lesion map. Discussion: Most lesion types demonstrated high sensitivity, but low PPV, indicating a liberal marking approach. Distribution of initial markings from inexperienced graders spatially misaligns with a specialist‐derived lesion map across all lesion types. Conclusion: As the ICDR‐scale depends on identifying the most severe lesion type, systematically inconsistent search strategies may pose a risk for overlooking important lesions under time constraints. The results support the promotion of attention guiding during DR‐training.

  • Open Access

    Grading‐labour cost analysis of AI ‐assisted versus human‐only diabetic retinopathy screening in two Danish healthcare settings

    by Lars Grønlykke, Sebastian Wiberg, Alex Carter, Peter Heilbo Ratgen, Simon Joel Lowater, Jakob Kristian Holm Andersen, Thiusius Rajeeth Savarimuthu, Jakob Grauslund

    Purpose: Diabetic retinopathy (DR) screening is essential to prevent vision loss, yet rising diabetes prevalence threatens to outpace ophthalmology capacity. Artificial intelligence (AI) systems can triage retinal images to reduce clinician workload, but economic evidence from high‐income, tax‐funded health systems remains limited. This study presents a cost‐minimisation analysis (CMA) of clinician grading labour comparing deep‐learning models (DLM)‐assisted screening versus human‐only DR screening. Methods: This CMA evaluates two Danish healthcare settings differing in DR prevalence: In tertiary diabetes centres with DR grade 2–4 prevalence of 41% and in publicly contracted private ophthalmology practices with DR grade 2–4 prevalence of 6%. Costs were estimated from the healthcare‐system perspective over a one‐year horizon, including clinician time and wages for image assessment and verification. Sensitivity analyses explored variations in staff time, DR prevalence, DLM false‐positive rate, and reimbursement effect. Results: In the tertiary‐centre setting (23 696 screens), total annual grading‐labour costs were €282 192 for AI‐assisted versus €421 425 for human‐only screening (33% reduction). In private practice (84 494 screens), the AI‐assisted pathway costs were €569 692 versus €1 502 698 (62% reduction). Savings were driven by reduced ophthalmologist time on cases the DLM classified as DR negative. Across all sensitivity analyses, the AI‐assisted strategy remained cost‐saving. Conclusion: AI‐assisted DR screening was cost‐minimising in both high‐ and low‐prevalence settings within Denmark's tax‐funded health system, with greater savings in lower‐prevalence populations. Tariff structures strongly influence payer impact, suggesting that reimbursement models must align with efficiency gains to realise health‐system savings from AI triage in routine DR screening.

  • Open Access

    Training and validation of an automated algorithm to differentiate no and minimal diabetic retinopathy from more severe stages in wide‐field images

    by Lars Morten Skollerud, Jakob Kristian Andersen, Sebastian Dinesen, Thiusius Rajeeth Savarimuthu, Jakob Grauslund

    Purpose: Diabetic retinopathy (DR) is a leading cause of blindness in the working‐age population. Screening is essential to identify and treat sight‐threatening stages prior to irreversible visual loss. This study aimed to train and validate an automated algorithm to identify no or minimal DR, potentially saving resources for specialist evaluation. Methods: We included 307 wide‐field images (Optomap, Dunfermline, Scotland) classified by a certified retinal expert according to the International Clinical Diabetic retinopathy (ICDR) scale. The expert manually annotated 26 995 diabetic‐related retinal lesions using the Computer Vision Annotation Tool (CVAT). A segmentation model was trained to detect lesions using a 70/15/15 split for training, tuning, and validation. A classification model used the outputs of the segmentation model as input features for a decision tree classifier, categorizing patients into Group 0 (DR level 0–1) or Group 1 (DR level 2–4). Classifier hyperparameters and input feature selection were optimized based on binary classification performance using cross‐validation. The classifier was evaluated on 48 validation images and further validated with 200 images graded by up to four independent certified graders. Results: The area under the curve was 0.94 for the 48 validation images, with specificity, sensitivity, and kappa values of 0.89, 0.93, and 0.83, respectively. For the 200 expert‐validated images, the values were 0.91, 0.98, 0.82, and 0.79, respectively. Conclusion: The combined method of segmentation followed by feature count analysis shows promising results for binary DR classification in Optomap wide‐field images without requiring a large dataset for model development.

  • Open Access

    Grading of diabetic retinopathy using a pre‐segmenting deep learning classification model: Validation of an automated algorithm

    by Dyllan Edson Similié, Jakob K. H. Andersen, Sebastian Dinesen, Thiusius R. Savarimuthu, Jakob Grauslund

    Purpose: To validate the performance of autonomous diabetic retinopathy (DR) grading by comparing a human grader and a self‐developed deep‐learning (DL) algorithm with gold‐standard evaluation.Methods: We included 500, 6‐field retinal images graded by an expert ophthalmologist (gold standard) according to the International Clinical Diabetic Retinopathy Disease Severity Scale as represented with DR levels 0–4 (97, 100, 100, 103, 100, respectively). Weighted kappa was calculated to measure the DR classification agreement for (1) a certified human grader without, and (2) with assistance from a DL algorithm and (3) the DL operating autonomously. Using any DR (level 0 vs. 1–4) as a cutoff, we calculated sensitivity, specificity, as well as positive and negative predictive values (PPV and NPV). Finally, we assessed lesion discrepancies between Model 3 and the gold standard.Results: As compared to the gold standard, weighted kappa for Models 1–3 was 0.88, 0.89 and 0.72, sensitivities were 95%, 94% and 78% and specificities were 82%, 84% and 81%. Extrapolating to a real‐world DR prevalence of 23.8%, the PPV were 63%, 64% and 57% and the NPV were 98%, 98% and 92%. Discrepancies between the gold standard and Model 3 were mainly incorrect detection of artefacts (n = 49), missed microaneurysms (n = 26) and inconsistencies between the segmentation and classification (n = 51).Conclusion: While the autonomous DL algorithm for DR classification only performed on par with a human grader for some measures in a high‐risk population, extrapolations to a real‐world population demonstrated an excellent 92% NPV, which could make it clinically feasible to use autonomously to identify non‐DR patients.


  • Open Access

    A digital online platform for education and certification of diabetic retinopathy health care professionals in the Region of Southern Denmark

    by Jakob Kristian Holm Andersen, Martin Slusarczyk Hubel, Thiusius Rajeeth Savarimuthu, Malin Lundberg Rasmussen, Simon Lyck Bjært Sørensen, Jakob Grauslund

    Purpose: The incidence of diabetes continues to increase across the world. As the number of patients rises, so does the need for educated health care professionals. Diabetic retinopathy (DR) remains one of the primary complications in diabetes, and screening has proved to be a cost‐effective measure to avoid DR‐related blindness. Denmark has an established screening programme, but no formal training of the people responsible for analysing retinal images.Methods: We here present an online learning platform that offers a diabetic eye screening course for health care professionals undertaking screening responsibility in the Region of Southern Denmark. The course is divided into lectures, each focussed on identifying different levels of DR or detecting related lesions. The course is free to use on‐demand, contains instructional videos, interactive tests and exercises, and it is concluded with a certification test. The tools on the platform can in addition be used to generate data for research purposes, such as comparing users or experts in detection of lesions or annotating data for the development of machine learning models.Results: More than 150 participants have so far completed the course, and the platform is being adopted for education in other regions of Denmark.


  • Applying cascaded convolutional neural network design further enhances automatic scoring of arthritis disease activity on ultrasound images from rheumatoid arthritis patients

    by Anders Bossel Holst Christensen, Søren Andreas Just, Jakob Kristian Holm Andersen, Thiusius Rajeeth Savarimuthu

    Objectives We have previously shown that neural network technology can be used for scoring arthritis disease activity in ultrasound images from rheumatoid arthritis (RA) patients, giving scores according to the EULAR-OMERACT grading system. We have now further developed the architecture of this neural network and can here present a new idea applying cascaded convolutional neural network (CNN) design with even better results. We evaluate the generalisability of this method on unseen data, comparing the CNN with an expert rheumatologist. Methods The images were graded by an expert rheumatologist according to the EULAR-OMERACT synovitis scoring system. CNNs were systematically trained to find the best configuration. The algorithms were evaluated on a separate test data set and compared with the gradings of an expert rheumatologist on a per-joint basis using a Kappa statistic, and on a per-patient basis using a Wilcoxon signed-rank test. Results With 1678 images available for training and 322 images for testing the model, it achieved an overall four-class accuracy of 83.9%. On a per-patient level, there was no significant difference between the classifications of the model and of a human expert (p=0.85). Our original CNN had a four-class accuracy of 75.0%. Conclusions Using a new network architecture we have further enhanced the algorithm and have shown strong agreement with an expert rheumatologist on a per-joint basis and on a per-patient basis. This emphasises the potential of using CNNs with this architecture as a strong assistive tool for the objective assessment of disease activity of RA patients.


  • Open Access

    OP0349 NEURAL NETWORKS FOR AUTOMATED SCORING OF JOINT DISEASE ACTIVITY ON DOPPLER ULTRASOUND IMAGES

    by Jakob K. H. Andersen, Jannik S. Pedersen, Martin S. Laursen, Kathrine Holtz, Jakob Grauslund, Thiusius Rajeeth Savarimuthu, Søren Andreas Just

    Background The development of standardized methods for ultrasound (US) scanning and evaluation of synovitis activity by the OMERACT-EULAR Synovitis Scoring (OESS) system, is a major step forward in the use of US in the diagnosis and monitoring of patients with inflammatory arthritis. The variation in interpretation of disease activity on US images can affect diagnosis, treatment and outcomes in clinical trials. Objectives To investigate if we could utilize neural network architecture for the interpretation of disease activity on Doppler US images, using the OESS scoring system. Methods Two state-of-the-art neural networks were used to extract information from 1342 Doppler US images from Rheumatoid Arthritis (RA) patients. One neural network that divided images as either healthy (Doppler OESS score 0 or 1) or diseased (Doppler OESS score 2 or 3). The other to score images across all four of the OESS systems Doppler US scores (0-3). The neural networks were hereafter tested on a new set of RA Doppler US images (n=176). Agreement between rheumatologist’s scores and network scores was measured with the kappa statistic. Results For the neural network assessing healthy/diseased score, the highest accuracies compared to an expert rheumatologist were 86.4% and 86.9% with a sensitivity of 0.864 and 0.875 and specificity of 0.864 and 0.864, respectively. The other neural network developed to four class Doppler OESS scoring achieved an average per class accuracy of 75.0%, and a quadratically weighted kappa score of 0.84. Conclusion This study is the first to show that neural network technology can be used in the scoring of disease activity on Doppler US images according to the OESS system. Disclosure of Interests None declared

  • Deep Learning–Based Algorithms in Screening of Diabetic Retinopathy: A Systematic Review of Diagnostic Performance

    by Katrine B. Nielsen, Mie L. Lautrup, Jakob K.H. Andersen, Thiusius R. Savarimuthu, Jakob Grauslund


  • Open Access

    Neural networks for automatic scoring of arthritis disease activity on ultrasound images

    by Jakob Kristian Holm Andersen, Jannik Skyttegaard Pedersen, Martin Sundahl Laursen, Kathrine Holtz, Jakob Grauslund, Thiusius Rajeeth Savarimuthu, Søren Andreas Just

    Background The development of standardised methods for ultrasound (US) scanning and evaluation of synovitis activity by the OMERACT-EULAR Synovitis Scoring (OESS) system is a major step forward in the use of US in the diagnosis and monitoring of patients with inflammatory arthritis. The variation in interpretation of disease activity on US images can affect diagnosis, treatment and outcomes in clinical trials. We, therefore, set out to investigate if we could utilise neural network architecture for the interpretation of disease activity on Doppler US images, using the OESS scoring system. Methods Two state-of-the-art neural networks were used to extract information from 1342 Doppler US images from patients with rheumatoid arthritis (RA). One neural network divided images as either healthy (Doppler OESS score 0 or 1) or diseased (Doppler OESS score 2 or 3). The other to score images across all four of the OESS systems Doppler US scores (0–3). The neural networks were hereafter tested on a new set of RA Doppler US images (n=176). Agreement between rheumatologist’s scores and network scores was measured with the kappa statistic. Results For the neural network assessing healthy/diseased score, the highest accuracies compared with an expert rheumatologist were 86.4% and 86.9% with a sensitivity of 0.864 and 0.875 and specificity of 0.864 and 0.864, respectively. The other neural network developed to four class Doppler OESS scoring achieved an average per class accuracy of 75.0% and a quadratically weighted kappa score of 0.84. Conclusion This study is the first to show that neural network technology can be used in the scoring of disease activity on Doppler US images according to the OESS system.