Cross-sectional assessment of mild cognitive impairment in pre-dialysis chronic kidney disease and its association with inflammation and changes seen on MRI: what the eyes cannot see

Deep learning enables accurate brain tissue microstructure analysis based on clinically feasible diffusion magnetic resonance imaging

Diffusion magnetic resonance imaging (dMRI) allows non-invasive assessment of brain tissue microstructure. Current model-based tissue microstructure reconstruction techniques require a large number of diffusion gradients, which is not clinically feasible due to imaging time constraints, and this has limited the use of tissue microstructure information in clinical settings. Recently, approaches based on deep learning (DL) have achieved promising tissue microstructure reconstruction results using clinically feasible dMRI. However, it remains unclear whether the subtle tissue changes associated with disease or age are properly preserved with DL approaches and whether DL reconstruction results can benefit clinical applications. Here, we provide the first evidence that DL approaches to tissue microstructure reconstruction yield reliable brain tissue microstructure analysis based on clinically feasible dMRI scans. Specifically, we reconstructed tissue microstructure from four different brain dMRI datasets with only 12 diffusion gradients, a clinically feasible protocol, and the neurite orientation dispersion and density imaging (NODDI) and spherical mean technique (SMT) models were considered. With these results we show that disease-related and age-dependent alterations of brain tissue were accurately identified. These findings demonstrate that DL tissue microstructure reconstruction can accurately quantify microstructural alterations in the brain based on clinically feasible dMRI.

Comparing the Efficacy of Two Cognitive Screening Tools in Identifying Gray and White Matter Brain Damage among Older Adults

Background

Ageing is associated with structural changes in brain regions and functional decline in cognitive domains. Noninvasive tools for identifying structural damage in the brains of older adults are relevant for early treatment.

Aims

This study aims to evaluate and compare the accuracy of the Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA©) in identifying gray and white matter brain damage in older individuals with varying degrees of cognitive impairment.

Methods

Ninety older adults (62 women) with an average age of 69 ± 7 years were enrolled and categorized as having no cognitive impairment (NCI), mild cognitive impairment (MCI), or moderate cognitive impairment (MoCI). Magnetic resonance imaging (MRI) was utilized to assess the number, volume, and distribution of brain damage. The Fazekas and Scheltens scales were applied to the brain MRIs, and inferential statistics were employed to compare variables among the groups.

Results

Cognitive impairment was observed in 56.7% of the participants (95% confidence interval (CI): 46.4-66.4%), with thirty-six older adults (40%) classified as MCI and 15 (17%) as MoCI. Cognitive impairment and medial temporal lobe (MTL) atrophy were found to be associated (p=0.001), exhibiting higher mean volume scales of the MTL atrophied area in the MoCI group (p < 0.001). The MMSE accurately revealed MTL atrophy based on the Scheltens (p < 0.05) and Fazekas (p < 0.05) scales. At the same time, the MoCA accurately identified periventricular white matter (PWM) abnormalities according to the Fazekas scale (p < 0.05).

Conclusions

The MMSE and MoCA screening tools effectively identified gray and white matter brain damage in older adults with varying degrees of cognitive impairment. Lower MMSE scores are associated with MTL atrophy and lesions, and lower MoCA scores are related to PWM lesions. The concurrent use of MMSE and MoCA is recommended for assessing structural changes in distinct brain regions.

Risk Prediction Performance of the Thai Cardiovascular Risk Score for Mild Cognitive Impairment in Adults with Metabolic Risk Factors in Thailand

Individuals with metabolic risks are at high risk of cognitive impairment. We aimed to investigate whether the Thai Cardiovascular Risk (TCVR) score can be used to predict mild cognitive impairment (MCI) in Thai adults with metabolic risks. The study was conducted using secondary data of patients with metabolic risks from Maharaj Nakorn Chiang Mai Hospital. MCI was indicated by an MoCA score of less than 25. Six different TCVR models were used with various combinations of ten different variables for predicting the risk of MCI. The area under the receiver operator characteristic curve (AuROC) and Hosmer–Lemeshow goodness of fit tests were used for determining discriminative performance and model calibration. The sensitivity of the discriminative performance was further evaluated by stratifying by age and gender. From a total of 421 participants, 348 participants had MCI. All six TCVR models showed a similar AuROC, varying between 0.58 and 0.61. The anthropometric-based model showed the best risk prediction performance in the older age group (AuROC 0.69). The laboratory-based model provided the highest discriminative performance for the younger age group (AuROC 0.60). There is potential for the development of an MCI risk model based on values from routine cardiovascular risk assessments among patients with metabolic risks.