Ulf Näslund

Tabular synthetic data generation (SDG) can facilitate research and development in the health domain, as access to health data is restricted. To accommodate for its structural complexity, such as multimodal distributions and fragmentation, transformer models provides an alternative to conventional SDG methods since they are better equipped to infer global spatial coherence due to textual context of tabular records. However, methods for optimising their adaption to tabular SDG are still largely unexplored. We contribute to the understanding of transformer-based SDG by evaluating fidelity and privacy of three prompting regimes, zero shot, one shot and few shot training, for tabular health SDG using small transformer models. We evaluated llama 3.2 (1B and 3B parameters) and Phi (1.3B and 2.7B parameters), on a real clinical dataset. Our results showed that zero shot learning was less prone to hallucinations and performed overall better for fidelity, but at the loss of privacy in comparison to the other regimes. Our results showed no differences between model sizes and families. Future studies should extend the analysis to other models and datasets, and explore strategies to reduce hallucinations.

This study investigated the long-term risk of cardiovascular events and all-cause mortality among participants with calcified carotid artery atheroma (CCAA) on panoramic radiographs (PRs) in the Periodontitis and its Relation to Coronary Artery Disease (PAROKRANK) study. In the multicentre, multidisciplinary PAROKRANK study, 805 patients with a first myocardial infarction (MI) and 805 matched controls without MI were recruited at 17 hospitals in Sweden. At baseline, the participants were examined with panoramic radiography, and in 737 patients and 739 controls, the carotid artery region was assessable. CCAAs were identified in 251 (34%) patients and 205 (28%) controls at baseline. The primary endpoint was defined as the first occurrence of all-cause mortality, non-fatal MI, non-fatal stroke, or hospitalization following heart failure after a mean follow-up of 10 years. The risks of cardiovascular events and death were evaluated using event survival analysis and regression models. Participants with bilateral CCAAs, regardless of whether they were patients or controls, had significantly higher mortality and morbidity than those without CCAA (P < 0.001). The risk of cardiovascular events was increased in the presence of bilateral CCAAs among both controls (hazard ratio, 1.96 [95% confidence interval : 1.21–3.16], P = 0.006) and patients (1.67 [1.15–2.43], P = 0.007). Bilateral CCAAs on PRs were an indicator of an increased risk of future cardiovascular events and early death among both controls and patients in the PAROKRANK study. Therefore, dentists can detect CCAA on PR and contribute to identifying individuals in need of medical attention and treatment of cardiovascular disease to prevent morbidity and early death.

Detecting and segmenting arterial plaques in ultrasound images is essential for the early diagnosis and prevention of cardiovascular diseases. This paper presents Hybrid Stable AnoGAN (HS-AnoGAN), an enhanced anomaly detection framework based on AnoGAN (Anomaly Generative Adversarial Network), which utilizes generative adversarial learning to model normal anatomical structures and identify abnormal regions indicative of pathology. The proposed approach introduces key improvements, including direct latent space encoding, hybrid reconstruction loss, feature matching in the discriminator, and adaptive thresholding, leading to more precise anomaly localization. Additionally, spectral normalization and Wasserstein loss with gradient penalty are incorporated to improve training stability and prevent mode collapse. To the best of our knowledge, this is the first attempt to apply anomaly detection techniques for arterial plaque detection and segmentation in ultrasound images. Comparative experiments demonstrate that HS-AnoGAN outperforms state-of-the-art methods, achieving a 9.8% increase in detection accuracy, and a 7.5% enhancement in Dice score for segmentation quality. These results highlight the effectiveness of HS-AnoGAN in improving both plaque detection and segmentation in ultrasound imaging, making it a promising tool for clinical applications.

Background: The role of cognitive abilities in the development of arteriosclerotic disease is still not fully understood. The purpose of the present study was to evaluate the mediating role of lifestyle, socioeconomic status (SES) and conventional cardiovascular disease (CVD) risk factors in the association between cognitive ability at age 19 and subclinical atherosclerosis at age 60 years. Methods: An observational study design was employed. Data on the results from cognitive tests of conscripts tested at age 19 were collected for 1009 men. At the age of 60, they were included in the trial VIsualiZation of asymptomatic Atherosclerotic disease for optimum cardiovascular prevention, which was conducted as part of the Västerbotten Intervention Program (VIPVIZA). VIPVIZA is a randomised controlled trial, aimed at primary prevention of CVD in Västerbotten County, Sweden. Prior to any intervention, they underwent carotid ultrasonography and CVD risk factor assessment. Lifestyle habits and marital status were self-reported, and education and urban or rural residency were registered. Crude associations between cognitive ability at age 19 and the risk of CVD, assessed with the European Systematic Coronary Risk Evaluation 2 (SCORE2), as well as subclinical atherosclerosis, as demonstrated by the presence of carotid plaques (no plaque, plaque unilateral, or plaque bilateral), were evaluated. A path-analytic model tested mediating factors from cognitive ability in young adulthood to subclinical atherosclerosis at age 60. Results: Results from cognitive tests at age 19 were in separate unadjusted analyses inversely and linearly associated with SCORE2 and with subclinical atherosclerosis. The association with carotid plaque at age 60 was mainly indirect and mediated by adult SES, which in turn had its main effect through adherence to healthy lifestyle habits via CVD risk of carotid plaques. Conclusions: Cognitive ability at age 19 is a factor that is upstream of adult SES and our study indicates that cognitive ability at a young age has long-term consequences via SES and lifestyle habits for CVD risk and atherosclerosis. Clinical Trial Registration: NCT01849575, https://clinicaltrials.gov/study/NCT01849575?term=NCT01849575&rank=1.

Objectives: We examined the magnitude of transcription errors in lipid variables in the VIPVIZA study and assessed whether education among the research personnel reduced the error frequency at follow-up. We also examined how the errors affected the SCORE2 risk prediction algorithm for cardiovascular disease, which includes lipid parameters, as this could lead to an incorrect treatment decision. Methods: The VIPVIZA study includes assessment of lipid parameters, where results for total cholesterol, triglycerides, HDL cholesterol, and calculated LDL cholesterol are transcribed into the research database by research nurses. Transcription errors were identified by recalculating LDL cholesterol, and a difference>0.15 indicated a transcription error in any of the four lipid parameters. To assess the presence of risk category misclassification, we compared the individual’s SCORE2 risk category based on incorrect lipid levels to the SCORE2 categories based on the correct lipid levels. Results: The transcription error frequency was 0.55 % in the 2019 VIPVIZA research database and halved after the educational intervention to 0.25 % in 2023. Of the 39 individuals who had a transcription error in total or HDL cholesterol (with the possibility of affecting the SCORE2 risk category based on non-HDL cholesterol), six individuals (15 %) received an incorrect risk category due to the error. Conclusions: Transcription errors persist despite digitalisation improvements. It is essential to minimise transcriptions in fields outside the laboratory environment, as we observed that critical decisions also rely on accurate information such as the SCORE2-risk algorithm, which is dependent on lab results but not necessarily reported by the laboratory.

Background: The ABO blood group system has shown an association with cardiovascular disease. The susceptibility to CVD is proposed to be partly mediated by dyslipidaemia in non-O individuals. Previous studies are scarce for the RhD blood group, but we recently showed that RhD − young individuals are associated with subclinical atherosclerosis. Hence, we sought to examine whether the ABO blood groups and RhD factor are associated with dyslipidaemia. Methods: All participants were part of the VIPVIZA study, including 3532 individuals with available plasma lipid levels. Lipids were assessed as total, LDL, HDL, remnant, non-HDL cholesterol and triglycerides. Information about ABO and RhD was retrieved by linking VIPVIZA with the SCANDAT-3 database, where 85% of VIPVIZA participants were registered. Results: For the ABO blood groups, no significant differences in lipid levels between non-O and O individuals were seen. In 40-year-old males, RhD − individuals compared to RhD + had higher levels of non-HDL cholesterol, LDL cholesterol, and remnant cholesterol, with ratios of geometric means of 1.21 (CI95% 1.03; 1.43), 1.20 (1.02; 1.41) and 1.38 (1.00; 1.92), respectively. No differences in lipid levels depending on the RhD blood group were seen in women or the older age groups. Conclusion: Our study indicates that younger RhD − men have increased non-HDL, LDL, and remnant cholesterol levels. Thus, the RhD blood group, but not ABO, seems to be associated with dyslipidaemia and may act as a future possible risk marker of cardiovascular disease. Graphical

Deep learning has been used extensively for medical image analysis applications, assuming the training and test data adhere to the same probability distributions. However, a common challenge arises when dealing with medical images generated by different systems or even the same system with varying parameter settings. Such images often contain diverse textures and noise patterns, violating the assumption. Consequently, models trained on data from one machine or setting usually struggle to perform effectively on data from another. To address this issue in ultrasound images, we proposed a Generative Adversarial Network (GAN) based model in this paper. We formulated image harmonization and denoising tasks as an image-to-image translation task, wherein we modified the texture pattern and reduced noise in Carotid ultrasound images while keeping the image content (the anatomy) unchanged. The performance was evaluated using feature distribution and pixel-space similarity metrics. In addition, blood-to-tissue contrast and influence on computed risk markers (Gray scale median, GSM) were evaluated. The results showed that domain adaptation was achieved in both tasks (histogram correlation 0.920 and 0.844), as compared to no adaptation (0.890 and 0.707), and that the anatomy of the images was retained (structure similarity index measure of the arterial wall 0.71 and 0.80). In addition, the image noise level (contrast) did not change in the image harmonization task (-34.1 vs 35.2 dB) but was improved in the noise reduction task (-23.5 vs -46.7 dB). The model outperformed the CycleGAN in both tasks. Finally, the risk marker GSM increased by 7.6 (p<0.001) in task 1 but not in task 2. We conclude that domain translation models are powerful tools for ultrasound image improvement while retaining the underlying anatomy but that downstream calculations of risk markers may be affected.

Background: People with intermediate CVD risk constitute most of the population. Within this group, the proportion of events is lower compared to the high-risk group, but they contribute with the largest absolute number of events. Atherosclerosis is a dynamic process and progression can be slowed or even reversed with medication and lifestyle changes, but adherence to prescribed treatment is crucial. Aim: To investigate the long-term effects of interventions with pictorial risk communication of cardiovascular (CVD) risk on average adherence in a group of statin users. Compare response in adherence over time between men and women after intervention. Methods: Participants on active statin treatment were followed up to 5 years after being randomly assigned to an intervention program aimed at raising CVD risk awareness among participants and their physicians. Merging prescribed medication databases with VIPVIZA study to study adherence over time. A moving average adherence was used to compare groups. Results: Generally, the average adherence to statins among the 512 participants was high. Men had a higher average adherence over time, while women had a sharper increase in adherence in conjuncture with the intervention program. Conclusions: Both men and women were receptive to pictorial information regarding CVD risk, but the intervention effect was more pronounced in women. Sex differences are important when considering risk communication strategies. Periodically repeating the intervention was beneficial for maintaining the intervention effect over time. Trial registration: The VIPVIZA study is registered with ClinicalTrials.gov, May 8, 2013, number NCT01849575.