Artificial Intelligence in Eye Movements Analysis for Alzheimer's Disease Early Diagnosis.

As the world's population ages, Alzheimer's disease is currently the seventh most common cause of death globally; the burden is anticipated to increase, especially among middle-class and elderly persons. Artificial intelligence-based algorithms that work well in hospital environments can be used to identify Alzheimer's disease. A number of databases were searched for English-language articles published up until March 1, 2024, that examined the relationships between artificial intelligence techniques, eye movements, and Alzheimer's disease. A novel non-invasive method called eye movement analysis may be able to reflect cognitive processes and identify anomalies in Alzheimer's disease. Artificial intelligence, particularly deep learning, and machine learning, is required to enhance Alzheimer's disease detection using eye movement data. One sort of deep learning technique that shows promise is convolutional neural networks, which need further data for precise classification. Nonetheless, machine learning models showed a high degree of accuracy in this context. Artificial intelligence-driven eye movement analysis holds promise for enhancing clinical evaluations, enabling tailored treatment, and fostering the development of early and precise Alzheimer's disease diagnosis. A combination of artificial intelligence-based systems and eye movement analysis can provide a window for early and non-invasive diagnosis of Alzheimer's disease. Despite ongoing difficulties with early Alzheimer's disease detection, this presents a novel strategy that may have consequences for clinical evaluations and customized medication to improve early and accurate diagnosis.

Frequency and Longitudinal Course of Motor Signs In Genetic Frontotemporal Dementia.

BACKGROUND AND OBJECTIVES: Frontotemporal dementia (FTD) is a highly heritable disorder. The majority of genetic cases are caused by autosomal dominant pathogenic variants in the c9orf72, GRN and MAPT gene. As motor disorders are increasingly recognized as part of the clinical spectrum the current study aimed to describe motor phenotypes caused by genetic FTD, quantify their temporal association, and investigate their regional association with brain atrophy. METHODS: We analyzed baseline visit data of known carriers of a pathogenic variant in the c9orf72, GRN or MAPT gene from the Genetic Frontotemporal dementia Initiative cohort study. Principal component analysis with varimax rotation was performed to identify motor sign clusters that were compared with respect to frequency and severity between groups. Associations with cross-sectional atrophy patterns were determined using voxel-wise regression. We applied linear mixed effects models to assess whether groups differed in the association between motor signs and estimated time to symptom onset. RESULTS: 322 pathogenic variant carriers were included in the analysis: 122 c9orf72 (79 presymptomatic), 143 GRN (112 presymptomatic) and 57 MAPT (43 presymptomatic) pathogenic variant carriers. Principal component analysis revealed five motor clusters, which we call progressive supranuclear palsy like (PSP-like), bulbar amyotrophic lateral sclerosis (ALS) like, mixed/ALS-like, Parkinson's disease like (PD-like), and corticobasal syndrome like motor phenotypes. There was no significant group difference in the frequency of signs of different motor phenotypes. However, mixed/ALS-like motor signs were most frequent, followed by PD-like motor signs. While the PSP-like phenotype was associated with mesencephalic atrophy, the mixed/ALS-like phenotype was associated with motor cortex and corticospinal tract atrophy. The PD-like phenotype was associated with widespread cortical and subcortical atrophy. Estimated time to onset, genetic group and their interaction, influenced motor signs. In c9orf72 pathogenic variant carriers, motor signs could be detected up to 25 years prior to expected symptom onset. DISCUSSION: These results indicate the presence of multiple natural clusters of motor signs in genetic FTD, each correlated with specific atrophy patterns. Their motor severity depends on time and the affected gene. These clinico-genetic associations can guide diagnostic evaluations and the design of clinical trials for new disease-modifying and preventive treatments.

Quantification of gait parameters with inertial sensors and inverse kinematics.

Measuring human gait is important in medicine to obtain outcome parameter for therapy, for instance in Parkinson's disease. Recently, small inertial sensors became available which allow for the registration of limb-position outside of the limited space of gait laboratories. The computation of gait parameters based on such recordings has been the subject of many scientific papers. We want to add to this knowledge by presenting a 4-segment leg model which is based on inverse kinematic and Kalman filtering of data from inertial sensors. To evaluate the model, data from four leg segments (shanks and thighs) were recorded synchronously with accelerometers and gyroscopes and a 3D motion capture system while subjects (n = 12) walked at three different velocities on a treadmill. Angular position of leg segments was computed from accelerometers and gyroscopes by Kalman filtering and compared to data from the motion capture system. The four-segment leg model takes the stance foot as a pivotal point and computes the position of the remaining segments as a kinematic chain (inverse kinematics). Second, we evaluated the contribution of pelvic movements to the model and evaluated a five segment model (shanks, thighs and pelvis) against ground-truth data from the motion capture system and the path of the treadmill. RESULTS: We found the precision of the Kalman filtered angular position is in the range of 2-6° (RMS error). The 4-segment leg model computed stride length and length of gait path with a constant undershoot of 3% for slow and 7% for fast gait. The integration of a 5th segment (pelvis) into the model increased its precision. The advantages of this model and ideas for further improvements are discussed.

Diagnosis of Neurodegenerative Diseases: The Clinical Approach.

There are a number of clinical questions for which there are no easy answers, even for well-trained doctors. The diagnostic tool commonly used to assess cognitive impairment in neurodegenerative diseases is based on established clinical criteria. However, the differential diagnosis between disorders can be difficult, especially in early phases or atypical variants. This takes on particular importance when it is still possible to use an appropriate treatment. To solve this problem, physicians need to have access to an arsenal of diagnostic tests, such as neurofunctional imaging, that allow higher specificity in clinical assessment. However, the reliability of diagnostic tests may vary from one to the next, so the diagnostic validity of a given investigation must be estimated by comparing the results obtained from "true" criteria to the "gold standard" or reference test. While pathological analysis is considered to be the gold standard in a wide spectrum of diseases, it cannot be applied to neurological processes. Other approaches could provide solutions, including clinical patient follow-up, creation of a data bank or use of computer-aided diagnostic algorithms. In this article, we discuss the development of different methodological procedures related to analysis of diagnostic validity and present an example from our own experience based on the use of I-123-ioflupane-SPECT in the study of patients with movement disorders. The aim of this chapter is to approach the problem of diagnosis from the point of view of the clinician, taking into account specific aspects of neurodegenerative disease.