Forskningsartikler

Abstract:

The aim of this study was to assess the diagnostic validity of a deep learning-based method estimating brain age based on magnetic resonance imaging (MRI) and to compare it with volumetrics obtained using NeuroQuant (NQ) in a clinical cohort. Brain age prediction was performed on minimally processed MRI data using deep convolutional neural networks and an independent training set. The brain age gap (difference between chronological and biological age) was calculated, and volumetrics were performed in 110 patients with dementia (Alzheimer’s disease, frontotemporal dementia (FTD), and dementia with Lewy bodies), and 122 with non-dementia (subjective and mild cognitive impairment). Area-under-the-curve (AUC) based on receiver operating characteristics and logistic regression analyses were performed. The mean age was 67.1 (9.5) years and 48.7% (113) were females. The dementia versus non-dementia sensitivity and specificity of the volumetric measures exceeded 80% and yielded higher AUCs compared to BAG. The explained variance of the prediction of diagnostic stage increased when BAG was added to the volumetrics. Further, BAG separated patients with FTD from other dementia etiologies with > 80% sensitivity and specificity. NQ volumetrics outperformed BAG in terms of diagnostic discriminatory power but the two methods provided complementary information, and BAG discriminated FTD from other dementia etiologies.

Karin Persson, Esten H Leonardsen, Trine Holt Edwin, Anne-Brita Knapskog, Gro Gujord Tangen, Geir Selbæk, Thomas Wolfers, Lars T Westlye, Knut Engedal

Background: High levels of occupational physical activity (PA) have been linked to an increased risk of dementia. We assessed the association of trajectories of occupational PA at ages 33–65 with risk of dementia and mild cognitive impairment (MCI) at ages 70+.

Methods: We included 7005 participants (49.8% were women, 3488/7005) from the HUNT4 70+ Study. Group-based trajectory modelling was used to identify four trajectories of occupational PA based on national registry data from 1960 to 2014: stable low (30.9%, 2162/7005), increasing then decreasing (8.9%, 625/7005), stable intermediate (25.1%, 1755/7005), and stable high (35.2%, 2463/7005). Dementia and MCI were clinically assessed in 2017–2019. We performed adjusted multinomial regression to estimate relative risk ratios (RRR) with 95% confidence intervals (CI) for dementia and MCI.

Findings: 902 participants were diagnosed with dementia and 2407 were diagnosed with MCI. Absolute unadjusted risks for dementia and MCI were 8.8% (95% CI: 7.6–10.0) and 27.4% (25.5–29.3), respectively, for those with a stable low PA trajectory, 8.2% (6.0–10.4) and 33.3% (29.6–37.0) for those with increasing, then decreasing PA; while they were 16.0% (14.3–17.7) and 35% (32.8–37.2) for those with stable intermediate, and 15.4% (14.0–16.8) and 40.2% (38.3–42.1) for those with stable high PA trajectories. In the adjusted model, participants with a stable high trajectory had a higher risk of dementia (RRR 1.34, 1.04–1.73) and MCI (1.80, 1.54–2.11), whereas participants with a stable intermediate trajectory had a higher risk of MCI (1.36, 1.15–1.61) compared to the stable low trajectory. While not statistically significant, participants with increasing then decreasing occupational PA had a 24% lower risk of dementia and 18% higher risk of MCI than the stable low PA group.

Interpretation: Consistently working in an occupation with intermediate or high occupational PA was linked to an increased risk of cognitive impairment, indicating the importance of developing strategies for individuals in physically demanding occupations to prevent cognitive impairment.

Ekaterina Zotcheva, Bernt Bratsberg, Bjørn Heine Strand, Astanand Jugessur, Bo Lars Engdahl, Catherine Bowen, Geir Selbæk, Hans-Peter Kohler, Jennifer R. Harris, Jordan Weiss, Sarah E. Tom, Steinar Krokstad, Teferi Mekonnen, Trine Holt Edwin, Yaakov Stern, Asta Kristine Håberg, Vegard Skirbekk