Juha Koikkalainen

Background: The relationship between neighborhood-level socioeconomic disadvantage and brain health is an emerging area of research with critical implications for public health and clinical practice, yet its influence on brain structure remains unclear. Purpose: To investigate the epidemiological association between neighborhood-level socioeconomic disadvantage [Area Deprivation Index (ADI)] and morphometric neuroimaging variables in a consecutive, non-disease enriched patient population. Materials and Methods: This study, conducted at an academic medical center and associated community partners, used consecutive cross-sectional MRI neuroimaging data from 2,826 inpatient and outpatient individuals without radiological evidence of disease from January 2024 to June 2024. ADI, a geospatially determined index of neighborhood-level disadvantage, was calculated for each individual. Linear regressions tested the relationship between ADI and multiple morphometric variables: brain age gap (BAG; estimated - chronological BA), total brain tissue volume (TBV; total gray + white matter), five subcortical region volumes (hippocampus, thalamus, caudate, putamen, and nucleus accumbens) and four cortical region volumes [anterior cingulate cortex, posterior cingulate cortex, medial prefrontal cortex (MPFC), lateral PFC (LPFC)]. Volumetric measures were normalized to intracranial volume. Models controlled for age, sex, and total white matter hyperintensity volume (WMHV). Results: 2,826 individuals (mean age, 52.7 ± 18.8 [standard deviation]; 1732 women) were evaluated. Residence in the 20% most disadvantaged neighborhoods was associated with a higher BAG (βs > 2.12, Ps < .01) and decreased TBV (βs < −5.12, Ps < .05). Additionally, increased WMHV was higher among those in the most disadvantaged neighborhoods (ts < - 2.50, Ps < .05) and associated with lower volume in most regions. Interaction models showed increased negative associations between WMHV and volumes of the caudate, nucleus accumbens, and lateral prefrontal cortex among those in the most disadvantaged neighborhoods. Conclusions: Neighborhood disadvantage is associated with adverse brain morphometry, including higher BAG, lower TBV, and amplified vascular-related regional volume loss. Key Results: In 2,826 adults (mean age, 53 years ± 19; 1,732 women), residence in the most disadvantaged neighborhoods (national: 116/2,826, 4%; state: 129/2826, 5%) was associated with higher brain age gap at the national (β = 2.12, 95% CI = 0.81 to 3.43, P = .001) and state levels (β = 2.36; 95% CI = 1.10 to 3.61, P < .001). Total brain tissue volume was lower at the national (β = −5.12, 95% CI = −10.13 to −0.11, P = .045) and state levels (β = −6.13, 95% CI = −10.90 to −1.37, P = .011). White matter hyperintensity volume was higher in the most disadvantaged group (national: P = .013; state: P = .003) and demonstrated amplified associations with caudate, nucleus accumbens, and lateral prefrontal cortex volumes in the most disadvantaged group at the national and/or state levels ( P s < .05).

Background: The use of amyloid‐PET in daily clinical practice is upcoming. Yet, ttranslation of the appropriate use criteria (AUC) to clinical practice is challenging, hampering successful implementation of amyloid‐PET. Tools that guide selecting patients for whom amyloid‐PET has most clinical utility are needed. Therefore, we developed and evaluated a computerized decision support approach to select patients for amyloid‐PET testing.Method: We included 286 subjects (136 controls, 116 Alzheimer’s disease (AD) dementia, 26 frontotemporal lobe dementia (FTD), and 8 vascular dementia (VaD) from the Amsterdam Dementia Cohort, with available neuropsychology, APOE, MRI and [¹⁸F]florbetaben amyloid‐PET. In our computerized decision support approach, we first classified the subjects using only neuropsychology, APOE, and MRI data. Then, for uncertain subjects (probability of correct class (PPC) < 0.75) we tested the classification by adding amyloid positive (AD like) and negative (normal) visual PET read results, and assessed whether either of the values makes the diagnosis reliable (PPC≥0.75). If the threshold of PCC was reached, the actual visual PET read result was used in the final classification. We compared the proportion of PET scans and patients diagnosed with sufficient confidence (PPC ≥0.75) in the computerized approach with three scenarios: 1) without amyloid‐PET (only demographics, neuropsychology, APOE and MRI), 2) amyloid‐PET according to the AUC and 3) amyloid‐PET for all patients. The study was performed using five‐fold cross‐validation.Result: The computerized approach advised PET in n = 76(27%) patients, leading to a diagnosis with sufficient confidence in n = 190(66%) patients. This approach outperformed the other three scenarios: 1) without amyloid‐PET, diagnosis was obtained in n = 147(51%), 2) applying the AUC resulted in amyloid‐PET in n = 113(40%) and diagnosis in n = 160(56%), and 3) performing amyloid‐PET in all patients resulted in diagnosis in n = 165(58%).Conclusion: Our computerized data‐driven approach restricted the application of amyloid‐PET to 27% in a memory clinic cohort of controls, AD, FTD, and VaD, without compromising diagnostic accuracy. This approach can support clinicians in making a balanced decision in ordering additional biomarker testing during the dementia workup. Thus, innovative use of resources can be stimulated, which is essential when disease‐modifying drugs increase the demand for biomarker testing.

Background: When MRI images of patients with memory problems are assessed, the presence of lacunar infarcts is evaluated. Lacunar infarcts, fluid‐filled cavities of 3‐15 mm in diameter, are one possible result of cerebral small vessel disease and therefore relevant in dementia diagnostics. In this study, we propose an automated tool for detecting lacunar infarcts on MRI images.Method: We adapted our previous approach [1] in three ways: 1) post‐processing steps were added to the convolutional neural network segmentation pipeline, e.g., to exclude enlarged perivascular spaces and segmentations located inside sulci or ventricles, 2) memory clinic data from the Amsterdam Dementia Cohort and PredictND cohort were included in addition to the LADIS cohort data, and 3) the ground truth was defined by three experienced neuroradiologists (A, B, C) instead of one rater. T1 and T2‐FLAIR images were available for all cases and T2 for a subset in visual rating. The dataset was composed of 393 subjects and each expert rated 1156 potential lacunar infarcts as “1 = no”, “2 = probably no”, “3 = probably yes” or “4 = yes”. A consensus (CO) was created by calculating the average and using a cutoff at 2.5. The agreement was measured between individual raters (A‐B, B‐C, A‐C), between automatic rating and individual raters (AU‐A, AU‐B, AU‐C), and between the automatic rating and the consensus rating (AU‐CO) using Kappa. Correlation coefficient for the number of lacunar infarcts per subject was defined. Cross‐validation was used in training the algorithm.Result: Out of 1156 candidate regions evaluated, 540 were considered as lacunar infarcts based on consensus. The individual raters agreed with each other in 74% of cases whether the shown lesion was lacunar infarct (kappa = 0.48). Correspondingly, automatic rating agreed with the individual raters in 74% of cases (kappa = 0.47). When automatic rating was compared with consensus, agreement/accuracy was 78% (kappa = 0.55). The correlation coefficient for the number of lacunar infarcts detected automatically from the whole image and visually (consensus) was 0.85 (Figure 1).Conclusion: This study suggests that the agreement in detecting lacunar infarcts automatically is comparable to inter‐rater variability between experienced neuroradiologists. [1] Jokinen et al. Stroke 2020 Nov 9; 50(1)

Background and purpose: Neuropsychiatric symptoms are related to disease progression and cognitive decline over time in cerebral small vessel disease (SVD) but their significance is poorly understood in covert SVD. We investigated neuropsychiatric symptoms and their relationships between cognitive and functional abilities in subjects with varying degrees of white matter hyperintensities (WMH), but without clinical diagnosis of stroke, dementia or significant disability. Methods: The Helsinki Small Vessel Disease Study consisted of 152 subjects, who underwent brain magnetic resonance imaging (MRI) and comprehensive neuropsychological evaluation of global cognition, processing speed, executive functions and memory. Neuropsychiatric symptoms were evaluated with the Neuropsychiatric Inventory Questionnaire (NPI-Q, n=134) and functional abilities with the Amsterdam Instrumental Activities of Daily Living questionnaire (A-IADL, n=132), both filled in by a close informant. Results: NPI-Q total score correlated significantly with WMH volume (r _s =0.20, p=0.019) and inversely with A-IADL score (r _s =-0.41, p<0.001). In total, 38% of the subjects had one or more informant evaluated neuropsychiatric symptoms. Linear regressions adjusted for age, sex and education revealed no direct associations between neuropsychiatric symptoms and cognitive performance. However, there were significant synergistic interactions between neuropsychiatric symptoms and WMH volume on cognitive outcomes. Neuropsychiatric symptoms were also associated with A-IADL score irrespective of WMH volume. Conclusions: Neuropsychiatric symptoms are associated with an accelerated relationship between WMH and cognitive impairment. Furthermore, the presence of neuropsychiatric symptoms is related to worse functional abilities. Neuropsychiatric symptoms should be routinely assessed in covert SVD as they are related to worse cognitive and functional outcomes.

Objective and early detection of Alzheimer's disease (AD) is a demanding problem requiring consideration of manymodal observations. Potentially, many features could be used to discern between people without AD and those at different stages of the disease. Such features include results from cognitive and memory tests, imaging (MRI, PET) results, cerebral spine fluid data, blood markers etc. However, in order to define an efficient and limited set of features that can be employed in classifiers requires mining of data from many patient cases. In this study we used two databases, ADNI and Kuopio LMCI, to investigate the relative importance of features and their combinations. Optimal feature combinations are to be used in a Clinical Decision Support System that is to be used in clinical AD diagnosis practice.