Neurodegenerative disorders, including Parkinson’s disease and Alzheimer’s disease, are some of the crucial global health issues prevalent today. In the United States, nearly 6.2 million people may have Alzheimer’s disease, according to a report from the Alzheimer’s Disease Association 2022. Almost a million Americans are living with Parkinson’s disease, according to the Parkinson’s Foundation, and these numbers are expected to continue to increase steeply in prevalence in the next few decades.
Currently, there is no cure for these disorders, but multi-domain interventions are promising results in slowing the progression of neurodegenerative disorders. The effectiveness of the outcomes increases with earlier intervention and greater individualization. Therefore, early diagnosis of neurodegenerative illnesses is a significant clinical and research problem.
The COVID-19 global pandemic has presented additional difficulties due to the lockdown restrictions, complicating the therapeutic management of patients with neurological disorders and necessitating creative telemedicine strategies. Regarding this, a study presented remote handwriting evaluation as a telemedicine tool for diagnosing neurodegenerative illnesses in the Frontiers in Aging Neuroscience journal.
The COVID-19 pandemic’s restrictions and the prevalence of neurodegenerative diseases necessitate the development of novel telemedicine strategies that will enable early and accurate diagnosis, monitor disease severity, and enhance remote clinical management of patients with neurodegenerative diseases. The equipment used in an ideal telemedicine setting should be safe, affordable, and simple to collect physiologically important data in an ecological setting.
The authors of the Frontiers article, therefore, proposed remote handwriting evaluation. They assert that learning complex cognitive and motor skills results from activating a wide brain network during handwriting development. Hence, handwriting may provide medical details about a person’s health. Additionally, safe, inexpensive, and readily available methods can collect handwriting in a natural environment.
Therefore, an innovative strategy would be using artificial intelligence to impartially assess handwriting for telemedicine purposes in healthy individuals and those experiencing neurological diseases.
The preliminary evaluation of a sizable dataset of healthy controls and research into the impact of pertinent biological parameters, such as physiologic aging, on handwriting is vital for the prospective use of handwriting analysis as a new telemedicine tool for neurodegenerative illnesses.
Regarding this, numerous research has indicated the efficiency of machine learning as a trustworthy method for evaluating handwriting in healthy persons and enabling inference of attributes, such as gender, left- or right-handedness, certain personality traits, and unique fingerprints.
In a sizable group of healthy people, the researchers looked at the relationship between handwriting and physiologic aging and the potential of machine learning as a valid method for evaluating handwriting and determining age in healthy subjects. One hundred and fifty-six healthy participants were separated into three age subgroups for the study: younger adults (YA), middle-aged adults (MA), and older people (OA).
The participants completed a digitalized ecological handwriting assignment on their smartphones. The results were then fed into a convolutional neural network (CNN) method to automatically validate machine learning analysis’s age-based handwriting sample classification capabilities. In each comparison, the artificial classifier’s performance was carefully evaluated in terms of sensitivity, specificity, accuracy, and positive and negative predictive values. Finally, to evaluate the effectiveness of the algorithm, receiver operating characteristic (ROC) curves, sensitivity, specificity, positive and negative predictive values (PPV, NPV), accuracy, and area under the curve (AUC) were computed.
The researchers’ investigation revealed that handwriting skill gradually deteriorates with human aging. Machine learning algorithms can be used to remotely and impartially detect the impact of physiological aging on handwriting ability. Also, the classification of handwriting from YA and MA collections by machine learning revealed a high degree of accuracy, according to the researchers. These results show that handwriting is a simple task that can be dependably used in telemedicine purposes in a real-world scenario.
Asci, F., Scardapane, S., Zampogna, A., D’Onofrio, V., Testa, L., Patera, M., Falletti, M., Marsili, L., & Suppa, A. (2022). Handwriting declines with human aging: A machine learning study. Frontiers in Aging Neuroscience, 14. https://doi.org/10.3389/fnagi.2022.889930