Handwriting Declines With Human Aging: A Machine Learning Study

Asci, Francesco; Scardapane, Simone; Zampogna, Alessandro; D'Onofrio, Valentina; Testa, Lucia; Patera, Martina; Falletti, Marco; Marsili, Luca; Suppa, Antonio

doi:10.3389/fnagi.2022.889930

Cited by 3 publications

(2 citation statements)

References 82 publications

(138 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Behavioral biomarkers may be used in cognitive screening. When testing average stroke sizes, handwriting, a type of fine motor control, was found to progressively decline with human aging [97]. During non-alphabetical and alphabetical writing, Alzheimer's disease patients showed less automated movements, decreased writing velocity and decreased frequency of up-and-down strokes [98].…”

Section: Performing Cognitive Screening Before MCImentioning

confidence: 99%

Ultra-Early Screening of Cognitive Decline Due to Alzheimer’s Pathology

Wei

2023

Biomedicines

View full text Add to dashboard Cite

Alzheimer’s pathology can be assessed and defined via Aβ and tau biomarkers. The preclinical period of Alzheimer’s disease is long and lasts several decades. Although effective therapies to block pathological processes of Alzheimer’s disease are still lacking, downward trends in the incidence and prevalence of dementia have occurred in developed countries. Accumulating findings support that education, cognitive training, physical exercise/activities, and a healthy lifestyle can protect cognitive function and promote healthy aging. Many studies focus on detecting mild cognitive impairment (MCI) and take a variety of interventions in this stage to protect cognitive function. However, when Alzheimer’s pathology advances to the stage of MCI, interventions may not be successful in blocking the development of the pathological process. MCI individuals reverting to normal cognitive function exhibited a high probability to progress to dementia. Therefore, it is necessary to take effective measures before the MCI stage. Compared with MCI, an earlier stage, transitional cognitive decline, may be a better time window in which effective interventions are adopted for at-risk individuals. Detecting this stage in large populations relies on rapid screening of cognitive function; given that many cognitive tests focus on MCI detection, new tools need to be developed.

show abstract

Section: Performing Cognitive Screening Before MCImentioning

confidence: 99%

Ultra-Early Screening of Cognitive Decline Due to Alzheimer’s Pathology

Wei

2023

Biomedicines

View full text Add to dashboard Cite

show abstract

“…Providing clinicians with quantitative and automatic measures of motor and postural performance through portable sensors would allow the early detection and management of postural instability in PD. By automatically managing large volumes of data, machine learning algorithms have shown remarkable success in making accurate predictions for complex problems, including healthcare issues [16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning and Wearable Sensors for the Early Detection of Balance Disorders in Parkinson’s Disease

Zubiena

Menna

Mileti

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Dynamic posturography combined with wearable sensors has high sensitivity in recognizing subclinical balance abnormalities in patients with Parkinson’s disease (PD). However, this approach is burdened by a high analytical load for motion analysis, potentially limiting a routine application in clinical practice. In this study, we used machine learning to distinguish PD patients from controls, as well as patients under and not under dopaminergic therapy (i.e., ON and OFF states), based on kinematic measures recorded during dynamic posturography through portable sensors. We compared 52 different classifiers derived from Decision Tree, K-Nearest Neighbor, Support Vector Machine and Artificial Neural Network with different kernel functions to automatically analyze reactive postural responses to yaw perturbations recorded through IMUs in 20 PD patients and 15 healthy subjects. To identify the most efficient machine learning algorithm, we applied three threshold-based selection criteria (i.e., accuracy, recall and precision) and one evaluation criterion (i.e., goodness index). Twenty-one out of 52 classifiers passed the three selection criteria based on a threshold of 80%. Among these, only nine classifiers were considered “optimum” in distinguishing PD patients from healthy subjects according to a goodness index ≤ 0.25. The Fine K-Nearest Neighbor was the best-performing algorithm in the automatic classification of PD patients and healthy subjects, irrespective of therapeutic condition. By contrast, none of the classifiers passed the three threshold-based selection criteria in the comparison of patients in ON and OFF states. Overall, machine learning is a suitable solution for the early identification of balance disorders in PD through the automatic analysis of kinematic data from dynamic posturography.

show abstract