Making use of longitudinal information in pattern recognition

Essential New Complexity-Based Themes for Patient-Centered Diagnosis and Treatment of Dementia and Predementia in Older People: Multimorbidity and Multilevel Phenomenology

Dementia is a highly prevalent condition with devastating clinical and socioeconomic sequela. It is expected to triple in prevalence by 2050. No treatment is currently known to be effective. Symptomatic late-onset dementia and predementia (SLODP) affects 95% of patients with the syndrome. In contrast to trials of pharmacological prevention, no treatment is suggested to remediate or cure these symptomatic patients. SLODP but not young onset dementia is intensely associated with multimorbidity (MUM), including brain-perturbating conditions (BPCs). Recent studies showed that MUM/BPCs have a major role in the pathogenesis of SLODP. Fortunately, most MUM/BPCs are medically treatable, and thus, their treatment may modify and improve SLODP, relieving suffering and reducing its clinical and socioeconomic threats. Regrettably, the complex system features of SLODP impede the diagnosis and treatment of the potentially remediable conditions (PRCs) associated with them, mainly due to failure of pattern recognition and a flawed diagnostic workup. We suggest incorporating two SLODP-specific conceptual themes into the diagnostic workup: MUM/BPC and multilevel phenomenological themes. By doing so, we were able to improve the diagnostic accuracy of SLODP components and optimize detecting and favorably treating PRCs. These revolutionary concepts and their implications for remediability and other parameters are discussed in the paper.

Machine Learning Classification Identifies Cerebellar Contributions to Early and Moderate Cognitive Decline in Alzheimer's Disease

Alzheimer's disease (AD) is one of the most common forms of dementia, marked by progressively degrading cognitive function. Although cerebellar changes occur throughout AD progression, its involvement and predictive contribution in its earliest stages, as well as gray or white matter components involved, remains unclear. We used MRI machine learning-based classification to assess the contribution of two tissue components [volume fraction myelin (VFM), and gray matter (GM) volume] within the whole brain, the neocortex, the whole cerebellum as well as its anterior and posterior parts and their predictive contribution to the first two stages of AD and typically aging controls. While classification accuracy increased with AD stages, VFM was the best predictor for all early stages of dementia when compared with typically aging controls. However, we document overall higher cerebellar prediction accuracy when compared to the whole brain with distinct structural signatures of higher anterior cerebellar contribution to mild cognitive impairment (MCI) and higher posterior cerebellar contribution to mild/moderate stages of AD for each tissue property. Based on these different cerebellar profiles and their unique contribution to early disease stages, we propose a refined model of cerebellar contribution to early AD development.

A survey on machine and statistical learning for longitudinal analysis of neuroimaging data in Alzheimer's disease

BACKGROUND AND OBJECTIVES

Recently, longitudinal studies of Alzheimer's disease have gathered a substantial amount of neuroimaging data. New methods are needed to successfully leverage and distill meaningful information on the progression of the disease from the deluge of available data. Machine learning has been used successfully for many different tasks, including neuroimaging related problems. In this paper, we review recent statistical and machine learning applications in Alzheimer's disease using longitudinal neuroimaging.

METHODS

We search for papers using longitudinal imaging data, focused on Alzheimer's Disease and published between 2007 and 2019 on four different search engines.

RESULTS

After the search, we obtain 104 relevant papers. We analyze their approach to typical challenges in longitudinal data analysis, such as missing data and variability in the number and extent of acquisitions.

CONCLUSIONS

Reviewed works show that machine learning methods using longitudinal data have potential for disease progression modelling and computer-aided diagnosis. We compare results and models, and propose future research directions in the field.

Methodological considerations for developmental longitudinal fMRI research

There has been a large spike in longitudinal fMRI studies in recent years, and so it is essential that researchers carefully assess the limitations and challenges afforded by longitudinal designs. In this article, we provide an overview of important considerations for longitudinal fMRI research in developmental samples, including task design, sampling strategies, and group-level analyses. We first discuss considerations for task designs, weighing the pros and cons of many commonly used tasks, as well as outlining how the tasks may be impacted by repeated exposure. Secondly, we review the types of group-level analyses that can be conducted on longitudinal fMRI data, analyses which must account for repeated measures. Finally, we review and critique recent longitudinal studies that have emerged in the past few years.