Lateral ventricle volume trajectories predict response inhibition in older age-A longitudinal brain imaging and machine learning approach

Prognostic enrichment for early-stage Huntington's disease: An explainable machine learning approach for clinical trial

BACKGROUND

In Huntington's disease clinical trials, recruitment and stratification approaches primarily rely on genetic load, cognitive and motor assessment scores. They focus less on in vivo brain imaging markers, which reflect neuropathology well before clinical diagnosis. Machine learning methods offer a degree of sophistication which could significantly improve prognosis and stratification by leveraging multimodal biomarkers from large datasets. Such models specifically tailored to HD gene expansion carriers could further enhance the efficacy of the stratification process.

OBJECTIVES

To improve stratification of Huntington's disease individuals for clinical trials.

METHODS

We used data from 451 gene positive individuals with Huntington's disease (both premanifest and diagnosed) from previously published cohorts (PREDICT, TRACK, TrackON, and IMAGE). We applied whole-brain parcellation to longitudinal brain scans and measured the rate of lateral ventricular enlargement, over 3 years, which was used as the target variable for our prognostic random forest regression models. The models were trained on various combinations of features at baseline, including genetic load, cognitive and motor assessment score biomarkers, as well as brain imaging-derived features. Furthermore, a simplified stratification model was developed to classify individuals into two homogenous groups (low risk and high risk) based on their anticipated rate of ventricular enlargement.

RESULTS

The predictive accuracy of the prognostic models substantially improved by integrating brain imaging features alongside genetic load, cognitive and motor biomarkers: a 24 % reduction in the cross-validated mean absolute error, yielding an error of 530 mm3/year. The stratification model had a cross-validated accuracy of 81 % in differentiating between moderate and fast progressors (precision = 83 %, recall = 80 %).

CONCLUSIONS

This study validated the effectiveness of machine learning in differentiating between low- and high-risk individuals based on the rate of ventricular enlargement. The models were exclusively trained using features from HD individuals, which offers a more disease-specific, simplified, and accurate approach for prognostic enrichment compared to relying on features extracted from healthy control groups, as done in previous studies. The proposed method has the potential to enhance clinical utility by: i) enabling more targeted recruitment of individuals for clinical trials, ii) improving post-hoc evaluation of individuals, and iii) ultimately leading to better outcomes for individuals through personalized treatment selection.

Sex Difference in Cigarette-Smoking Status and Its Association with Brain Volumes Using Large-Scale Community-Representative Data

BACKGROUND

Cigarette smoking is believed to accelerate age-related neurodegeneration. Despite significant sex differences in both smoking behaviors and brain structures, the active literature is equivocal in parsing out a sex difference in smoking-associated brain structural changes.

OBJECTIVE

The current study examined subcortical and lateral ventricle gray matter (GM) volume differences among smokers, active, past, and never-smokers, stratified by sex.

METHODS

The current study data included 1959 Dallas Heart Study (DHS) participants with valid brain imaging data. Stratified by gender, multiple-group comparisons of three cigarette-smoking groups were conducted to test whether there is any cigarette-smoking group differences in GM volumes of the selected regions of interest (ROIs).

RESULTS

The largest subcortical GM volumetric loss and enlargement of the lateral ventricle were observed among past smokers for both females and males. However, these observed group differences in GM volumetric changes were statistically significant only among males after adjusting for age and intracranial volumes.

CONCLUSIONS

The study findings suggest a sex difference in lifetime-smoking-associated GM volumetric changes, even after controlling for aging and intracranial volumes.

Functional activity level reported by an informant is an early predictor of Alzheimer's disease

BACKGROUND

Loss of autonomy in day-to-day functioning is one of the feared outcomes of Alzheimer's disease (AD), and relatives may have been worried by subtle behavioral changes in ordinary life situations long before these changes are given medical attention. In the present study, we ask if such subtle changes should be given weight as an early predictor of a future AD diagnosis.

METHODS

Longitudinal data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were used to define a group of adults with a mild cognitive impairment (MCI) diagnosis remaining stable across several visits (sMCI, n=360; 55-91 years at baseline), and a group of adults who over time converted from having an MCI diagnosis to an AD diagnosis (cAD, n=320; 55-88 years at baseline). Eleven features were used as input in a Random Forest (RF) binary classifier (sMCI vs. cAD) model. This model was tested on an unseen holdout part of the dataset, and further explored by three different permutation-driven importance estimates and a comprehensive post hoc machine learning exploration.

RESULTS

The results consistently showed that measures of daily life functioning, verbal memory function, and a volume measure of hippocampus were the most important predictors of conversion from an MCI to an AD diagnosis. Results from the RF classification model showed a prediction accuracy of around 70% in the test set. Importantly, the post hoc analyses showed that even subtle changes in everyday functioning noticed by a close informant put MCI patients at increased risk for being on a path toward the major cognitive impairment of an AD diagnosis.

CONCLUSION

The results showed that even subtle changes in everyday functioning should be noticed when reported by relatives in a clinical evaluation of patients with MCI. Information of these changes should also be included in future longitudinal studies to investigate different pathways from normal cognitive aging to the cognitive decline characterizing different stages of AD and other neurodegenerative disorders.

Magnetic resonance brain volumetry biomarkers of CLN2 Batten disease identified with miniswine model

Late-infantile neuronal ceroid lipofuscinosis type 2 (CLN2) disease (Batten disease) is a rare pediatric disease, with symptom development leading to clinical diagnosis. Early diagnosis and effective tracking of disease progression are required for treatment. We hypothesize that brain volumetry is valuable in identifying CLN2 disease at an early stage and tracking disease progression in a genetically modified miniswine model. CLN2R208X/R208X miniswine and wild type controls were evaluated at 12- and 17-months of age, correlating to early and late stages of disease progression. Magnetic resonance imaging (MRI) T1- and T2-weighted data were acquired. Total intercranial, gray matter, cerebrospinal fluid, white matter, caudate, putamen, and ventricle volumes were calculated and expressed as proportions of the intracranial volume. The brain regions were compared between timepoints and cohorts using Gardner-Altman plots, mean differences, and confidence intervals. At an early stage of disease, the total intracranial volume (- 9.06 cm3), gray matter (- 4.37% 95 CI - 7.41; - 1.83), caudate (- 0.16%, 95 CI - 0.24; - 0.08) and putamen (- 0.11% 95 CI - 0.23; - 0.02) were all notably smaller in CLN2R208X/R208X miniswines versus WT, while cerebrospinal fluid was larger (+ 3.42%, 95 CI 2.54; 6.18). As the disease progressed to a later stage, the difference between the gray matter (- 8.27%, 95 CI - 10.1; - 5.56) and cerebrospinal fluid (+ 6.88%, 95 CI 4.31; 8.51) continued to become more pronounced, while others remained stable. MRI brain volumetry in this miniswine model of CLN2 disease is sensitive to early disease detection and longitudinal change monitoring, providing a valuable tool for pre-clinical treatment development and evaluation.

Different loneliness types, cognitive function, and brain structure in midlife: Findings from the Framingham Heart Study

Background

It remains unclear whether persistent loneliness is related to brain structures that are associated with cognitive decline and development of Alzheimer's disease (AD). This study aimed to investigate the relationships between different loneliness types, cognitive functioning, and regional brain volumes.

Methods

Loneliness was measured longitudinally, using the item from the Center for Epidemiologic Studies Depression Scale in the Framingham Heart Study, Generation 3, with participants' average age of 46·3 ± 8·6 years. Robust regression models tested the association between different loneliness types with longitudinal neuropsychological performance (n = 2,609) and regional magnetic resonance imaging brain data (n = 1,829) (2002-2019). Results were stratified for sex, depression, and Apolipoprotein E4 (ApoE4).

Findings

Persistent loneliness, but not transient loneliness, was strongly associated with cognitive decline, especially memory and executive function. Persistent loneliness was negatively associated with temporal lobe volume (β = -0.18, 95%CI [-0.32, -0.04], P = 0·01). Among women, persistent loneliness was associated with smaller frontal lobe (β = -0.19, 95%CI [-0.38, -0.01], P = 0·04), temporal lobe (β = -0.20, 95%CI [-0.37, -0.03], P = 0·02), and hippocampus volumes (β = -0.23, 95%CI [-0.40, -0.06], P = 0·007), and larger lateral ventricle volume (β = 0.15, 95%CI [0.02, 0.28], P = 0·03). The higher cumulative loneliness scores across three exams, the smaller parietal, temporal, and hippocampus volumes and larger lateral ventricle were evident, especially in the presence of ApoE4.

Interpretation

Persistent loneliness in midlife was associated with atrophy in brain regions responsible for memory and executive dysfunction. Interventions to reduce the chronicity of loneliness may mitigate the risk of age-related cognitive decline and AD.

Funding

US National Institute on Aging.

Predicting conversion to Alzheimer's disease in individuals with Mild Cognitive Impairment using clinically transferable features

Patients with Mild Cognitive Impairment (MCI) have an increased risk of Alzheimer's disease (AD). Early identification of underlying neurodegenerative processes is essential to provide treatment before the disease is well established in the brain. Here we used longitudinal data from the ADNI database to investigate prediction of a trajectory towards AD in a group of patients defined as MCI at a baseline examination. One group remained stable over time (sMCI, n = 357) and one converted to AD (cAD, n = 321). By running two independent classification methods within a machine learning framework, with cognitive function, hippocampal volume and genetic APOE status as features, we obtained a cross-validation classification accuracy of about 70%. This level of accuracy was confirmed across different classification methods and validation procedures. Moreover, the sets of misclassified subjects had a large overlap between the two models. Impaired memory function was consistently found to be one of the core symptoms of MCI patients on a trajectory towards AD. The prediction above chance level shown in the present study should inspire further work to develop tools that can aid clinicians in making prognostic decisions.

Brain atrophy in middle age using magnetic resonance imaging scans from Japan’s health screening programme

Although health screening plays a key role in the management of chronic diseases associated with lifestyle choices, brain health is not generally monitored, remaining a black box prior to the manifestation of clinical symptoms. Japan is unique in this regard, as brain MRI scans have been widely performed for more than two decades as part of Brain Dock, a comprehensive health screening programme. A vast number of stored images (well over a million) of longitudinal scans and extensive health data are available, offering a valuable resource for investigating the prevalence of various types of brain-related health conditions occurring throughout adulthood.

In this paper, we report on the findings of our preliminary quantitative analysis of T₁-weighted MRIs of the brain obtained from 13 980 subjects from three participating sites during the period 2015–19. We applied automated segmentation analysis and observed age-dependent volume loss of various brain structures. We subsequently investigated the effects of scan protocols and the feasibility of calibration for pooling the data. Last, the degree of brain atrophy was correlated with four known risk factors of dementia; blood glucose level, hypertension, obesity, and alcohol consumption.

In this initial analysis, we identified brain ventricular volume as an effective marker of age-dependent brain atrophy, being highly sensitive to ageing and evidencing strong robustness against protocol variability. We established the normal range of ventricular volumes at each age, which is an essential first step for establishing criteria used to interpret data obtained for individual participants. We identified a subgroup of individuals at midlife with ventricles that substantially exceeded the average size. The correlation studies revealed that all four risk factors were associated with greater ventricular volumes at midlife, some of which reached highly significant sizes.

This study demonstrates the feasibility of conducting a large-scale quantitative analysis of existing Brain Dock data in Japan. It will importantly guide future efforts to investigate the prevalence of large ventricles at midlife and the potential reduction of this prevalence, and hence of dementia risk, through lifestyle changes.

Brain aging mechanisms with mechanical manifestations

Brain aging is a complex process that affects everything from the subcellular to the organ level, begins early in life, and accelerates with age. Morphologically, brain aging is primarily characterized by brain volume loss, cortical thinning, white matter degradation, loss of gyrification, and ventricular enlargement. Pathophysiologically, brain aging is associated with neuron cell shrinking, dendritic degeneration, demyelination, small vessel disease, metabolic slowing, microglial activation, and the formation of white matter lesions. In recent years, the mechanics community has demonstrated increasing interest in modeling the brain's (bio)mechanical behavior and uses constitutive modeling to predict shape changes of anatomically accurate finite element brain models in health and disease. Here, we pursue two objectives. First, we review existing imaging-based data on white and gray matter atrophy rates and organ-level aging patterns. This data is required to calibrate and validate constitutive brain models. Second, we review the most critical cell- and tissue-level aging mechanisms that drive white and gray matter changes. We focuse on aging mechanisms that ultimately manifest as organ-level shape changes based on the idea that the integration of imaging and mechanical modeling may help identify the tipping point when normal aging ends and pathological neurodegeneration begins.

A predictive framework based on brain volume trajectories enabling early detection of Alzheimer's disease

We present a framework for constructing predictive models of cognitive decline from longitudinal MRI examinations, based on mixed effects models and machine learning. We apply the framework to detect conversion from cognitively normal (CN) to mild cognitive impairment (MCI) and from MCI to Alzheimer's disease (AD), using a large collection of subjects sourced from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Australian Imaging, Biomarkers and Lifestyle Flagship Study of Aging (AIBL). We extract subcortical segmentation and cortical parcellation from corresponding T1-weighted images using FreeSurfer v.6.0, select bilateral 3D regions of interest relevant to neurodegeneration/dementia, and fit their longitudinal volume trajectories using linear mixed effects models. Features describing these model-based trajectories are then used to train an ensemble of machine learning classifiers to distinguish stable CN from converters to MCI, and stable MCI from converters to AD. On separate test sets the models achieved an average of accuracy/precision/recall score of 69/73/60% for converted to MCI and 75/74/77% for converted to AD, illustrating the framework's ability to extract predictive imaging-based biomarkers from routine T1-weighted MRI acquisitions.

Cognitive and MRI trajectories for prediction of Alzheimer's disease

The concept of Mild Cognitive Impairment (MCI) is used to describe the early stages of Alzheimer's disease (AD), and identification and treatment before further decline is an important clinical task. We selected longitudinal data from the ADNI database to investigate how well normal function (HC, n= 134) vs. conversion to MCI (cMCI, n= 134) and stable MCI (sMCI, n=333) vs. conversion to AD (cAD, n= 333) could be predicted from cognitive tests, and whether the predictions improve by adding information from magnetic resonance imaging (MRI) examinations. Features representing trajectories of change in the selected cognitive and MRI measures were derived from mixed effects models and used to train ensemble machine learning models to classify the pairs of subgroups based on a subset of the data set. Evaluation in an independent test set showed that the predictions for HC vs. cMCI improved substantially when MRI features were added, with an increase in [Formula: see text]-score from 60 to 77%. The [Formula: see text]-scores for sMCI vs. cAD were 77% without and 78% with inclusion of MRI features. The results are in-line with findings showing that cognitive changes tend to manifest themselves several years after the Alzheimer's disease is well-established in the brain.

Systematic and Comprehensive Automated Ventricle Segmentation on Ventricle Images of the Elderly Patients: A Retrospective Study

Background and Objective: Ventricle volume is closely related to hydrocephalus, brain atrophy, Alzheimer's, Parkinson's syndrome, and other diseases. To accurately measure the volume of the ventricles for elderly patients, we use deep learning to establish a systematic and comprehensive automated ventricle segmentation framework.

Methods: The study participation included 20 normal elderly people, 20 patients with cerebral atrophy, 64 patients with normal pressure hydrocephalus, and 51 patients with acquired hydrocephalus. Second, get their imaging data through the picture archiving and communication systems (PACS) system. Then use ITK software to manually label participants' ventricular structures. Finally, extract imaging features through machine learning.

Results: This automated ventricle segmentation method can be applied not only to CT and MRI images but also to images with different scan slice thicknesses. More importantly, it produces excellent segmentation results (Dice > 0.9).

Conclusion: This automated ventricle segmentation method has wide applicability and clinical practicability. It can help clinicians find early disease, diagnose disease, understand the patient's disease progression, and evaluate the patient's treatment effect.