Handwriting Detection Test (HWDT): Android Application for the

Recognition of Neurodegenerative Diseases

Giacomo F. P.

Cuccovillo

, Donato Impedovo

, Alessia Monaco

, Giuseppe Pirlo

Gianfranco Semeraro

and

Davide Veneto

Department of Computer Science, University of Bari, 70125 Bari, Italy

Department of Science, Technology and Society, University School for Advanced Studies IUSS Pavia, 27100 Pavia, Italy

Digital Innovation srl, 70125 Bari, Italy

Keywords: Neurodegenerative Disease, Behavioral Biometrics, Handwriting, Android Application, E-Health.

Abstract: Nowadays there is an increase in the global incidence of dementia, with over 55 million reported cases

worldwide. In Italy, the number is estimated to exceed 1 million individuals. According to evidence, a

therapeutic approach in the pre-clinical stages involves conducting screening tests to identify changes in the

handwriting process. This paper aims to propose an E-Health app named Handwriting Detection Test

(HWDT). The proposed app is a smart-screening solution that reduces time and waiting periods in the

interaction between experts and patients. We implemented screening tests derived from recent advances or

ongoing research. The paper highlights the significant role of handwriting behavior and explains the design

and development phases of the proposed system. This approach offers a more efficient and technologically

advanced method for early detection and monitoring of cognitive changes associated with neurodegenerative

impairments.

1 INTRODUCTION

Artificial Intelligence (AI) and Behavioral

Biometrics systems play increasingly pivotal role in

health-related issue detection. Behavioral Biometrics

tools have opened avenues for groundbreaking

advancements in healthcare diagnostics and

monitoring: These tools can be used as digital

sentinels, providing a proactive approach to

healthcare by flagging potential issues long before

they manifest in overt symptoms.

In recent times, behavioral biometrics tools have

largely impacted Dementia studies by offering a new

approach to improve individual’s quality of life. This

is particularly true in the assessment of

Neurodegenerative Disorders (ND; Cheriet et al.,

2023),defined as an incurable and heterogeneous

group of medical conditions which lead to

progressive modifications of the ability to carry out

essential functions with cognitive dysfunction and

behavioral impairment (Dugger & Dickson, 2017;

Lamptey et al., 2022; Wilson et al., 2023). To date,

clinical criteria are employed to assess cognitive

impairments (Gómez-Río et al., 2016; Mordhorst et

al., 2022): practitioners employ screening tests or

comprehensive neuropsychological assessments,

supported by medical information, or neurological

exams to move from a “possible” to a “probable”

diagnosis(Menéndez-González, 2023; Hansson,

2021).

Evidence shows that the most prevalent

neurodegenerative conditions refer to Alzheimer's

Disease (AD) and Parkinson's Disease (PD). In this

regard, literature provides valid instruments to

investigate changes in cognitive functions. Current

evidence states that The Mini-Mental State

Examination (MMSE; Folstein et al., 1975)or

Montreal Cognitive Assessment (MOCA; Nasreddine

et al., 2005) are the most used for cognitive screening

(Tsoi et al., 2015) even if MoCA is preferred because

it assesses executive function and visuospatial

abilities (Siqueira et al., 2019; Hoops et al., 2009).

The paper is structured as below. The second part

is related to a brief overview about intelligent tools

and applications related to our research purpose. The

third section is focused on the architecture and

development phases of the Handwriting Detection

Test (HWDT) which is the core of this work. The last

section (4) illustrates the conclusions and planned

future work.

Cuccovillo, G., Impedovo, D., Monaco, A., Pirlo, G., Semeraro, G. and Veneto, D.

Handwriting Detection Test (HWDT): Android Application for the Recognition of Neurodegenerative Diseases.

DOI: 10.5220/0012593600003654

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2024), pages 985-994

ISBN: 978-989-758-684-2; ISSN: 2184-4313

985

1.1 Alzheimer’s Disease

Alzheimer's Disease (AD) represents the most

common form of Dementia. AD people from the early

onset mainly suffer from cognitive (e.g. memory,

comprehension, language, attention, reasoning, and

judgment) and functional (e.g. behavioral) deficits

(Kumar et al., 2022) the severity of which shifts

according to the disease stage. Indeed, data shows

that AD is classify into three stages: preclinical, mild

and dementia-stage (Abbatantuono et al., 2023;

Albert et al., 2011). Individuals in the transitional

stage between aging and dementia are diagnosed with

Mild Cognitive Impairment (MCI; Petersen, 2016),

defined as a progressive pathological condition that

increases the likehood to develop AD disease

(Shigemizu et al., 2020; Calub et al., 2023; Chen et

al., 2022; Iachini et al., 2009).

AD can be assessed by combining information

through biomarkers (Hansson, 2021) or imaging

techniques such as Structural Magnetic Resonance

Imaging (MRI; Afzal et al., 2021). Moreover,

neurological exams and cognitive and functional

assessments are use in order to obtain a

comprehensive evaluation of patients. Traditional

methods for diagnosis of dementia rely on medical

history, physical examination, or neurological testing

(Ritchie et al., 2017; Weintraub et al., 2018) resulting

partially subjective evaluations. However the existing

treatments can only postpone the progression of the

disease.

This highlight the need to diagnostic them as early

as possible. In this regard, the analysis of alterations

in handwriting has proved to be fundamental in early

diagnosis and assessment of disease progression

(Impedovo et al., 2019).

1.2 Parkinson's Disease

Parkinson's Disease (PD) is defined as a

neurodegenerative and multisystemic condition

(Chahine et al., 2020) and involve both functional,

cognitive and behavioral disorders. In particular, PD

symptomatology in mainly related to motor

impairments, e.g. Akinesia; Rigidity; Tremor;

Postural instability, bradykinesia, tremors,

gait/balance issues (Armstrong & Okun, 2020;

Marino et al., 2019) and non-motor symptoms, e.g.

difficulties in sleep and attention (Jankovic, 2008),

cognitive decline (Bosboom et al., 2004), a reduced

ability detect smells, voice changes (Aouraghe et al.,

2023). Researchers have identified different PD

stages from early to advanced (Carrarini et al., 2019;

Hoehn & Yahr, 1967).

According to Movement Disorder Society-PD

criteria (MDS-PD), the diagnosis relies on clinical

assessment (Heinzel et al., 2019), involving a

thorough examination of medical history and

neurological evaluations (Bloem et al., 2021). Thus,

the diagnosis is challenging: clinical assessment is the

gold standard, supported by brain imaging

approaches and biomarker-supporter diagnostic tools

widely used as valid approaches to confirm suspected

PD (Tolosa et al., 2021).

Despite the extensive use of standardized

assessment tools in healthcare, several studies

highlight that the handwriting analysis is powerful for

the ability to detect subtle changes in cognitive

functioning even in the early stages of

neurodegenerative diseases (Aouraghe et al., 2023;

Drotár et al., 2016; J. Zhang et al., 2023).

The present work aims to provide an app based on

a battery of digital screening based on handwriting

task solutions. In addition, several aspects were

considered, including the level of education of users,

the feasibility of testing and the context of use.

2 RELATED WORK

Nowadays, e-health health tools are employed to

investigate individual health conditions (Sblendorio

et al., 2023). The literature highlighted the significant

role that handwriting analysis can play in assessing

clinical conditions, including neurodegenerative

diseases (Aouraghe et al., 2023; Chai et al., 2023;

Faundez-Zanuy et al., 2021).

Handwriting results from an elaborate human

activity involving cognitive, kinesthetic, and

perceptual-motor components (Cilia et al., 2019).

Handwriting tools can capture information starting

based on an individual’s performance in handwriting

tasks to distinguish healthy subjects from people

affected by ND (Angelillo et al., 2019a; Angelillo et

al., 2019b; Impedovo et al., 2012; Pirlo & Impedovo,

2013).These tools provide more information

compared to traditional assessment (pen-and-paper

tests) which remains a good method to evaluate health

status.

In this work, we focus on the value of handwriting

performance analysis. Indeed, the adoption of a smart

Pen on a digital screen provides data about the

individual’s abilities in performing tasks (axis

coordinates, position, pressure, and time information)

(Ardimento et al., 2021; Aversano et al., 2020;

Faundez-Zanuy et al., 2020). The integration of

digital tools such as smart devices or mobile apps

allows objective, real-time monitoring, and more

NeroPRAI 2024 - Workshop on Medical Condition Assessment Using Pattern Recognition: Progress in Neurodegenerative Disease and

Beyond

986

comprehensive information about an individual's

health status, also taking an active role in managing

their health (Wicks et al., 2014).

In neurodegenerative conditions, signs of

difficulties or alterations in handwriting i.e.,

micrography, slower movements, or tremors are

related to pathology’s biomarkers (Impedovo & Pirlo,

2018; Gattulli et al., 2023a; Gattulli et al., 2023c). De

Stefano et al. (2019) emphasize using handwriting

tasks allows to capture of essential features, including

spatial organization and fine motor control abilities,

and the type of movement (e.g., in-air). For such

problem, several pattern recognition algorithms have

been developed over the years ranging from shallow

learning techniques to advanced deep learning

techniques such as wave nets and

transformers(Cannarile et al., 2022; Carrera et al.,

2022; Dentamaro et al., 2018; Impedovo et al., 2019;

Impedovo et al., 2021).

The existing evidence regarding the development

of applications for detecting impairments in ND is

still limited. Lauraitis et al. (2019) propose an

Android app designed to identify prodromal signs of

neurodegenerative impairment and enhance decision

support in medical contexts, achieving 86.4%

accuracy. The model’s primary focus is to recognize

signs of both motor and cognitive impairment by

using a touch-and-visual task. The data used in the

study were gathered from both healthy individuals

and patients in the early stages of the disease. The

methodology involved the implementation of a back-

propagation neural network classifier.

In a study, Chandra et al. (2021) collected data on

patients using an Apple pen to capture parameters

including pressure and speed. Participants were

invited to perform drawing (spiral and infinity

symbol) and cognitive (recall) tasks. Handwriting

tools show the advantage of detecting also signs of

prodromal impairment. For this purpose, Rosenblum

et al., 2021)introduced a smart tool called

“DailyCog”, an app to identify MCI in PD patients.

The app investigates cognitive abilities by exploiting

simple and daily tasks. Indeed, includes everyday

tasks and tests for the evaluation of executive

functions, visual-spatial, and motor abilities.

3 SYSTEM ARCHITECTURE:

HANDWRITING DETECTION

APPLICATION

The overall application's architecture illustrates the

interaction between the prospective user and the

device, which is a supportive tool for carrying out key

activities. This approach directs users to utilize a

single device, and once chosen it needs to be linked

to a local database for storing and manipulating user

data. Additionally, the device communicates with a

server component for data transmission and result

retrieval. This approach aligns partially with the

MVC pattern (Model-View-Controller; Utpatadevi et

al., 2012),which involves dividing the software

structure of an application into three components:

• Model. Essential component for data management;

• View. Component that will manage the output of the

previously authenticated user interface.

• Controller. Component in charge of management

features.

Figure 1: Application architecture.

The Model component is responsible for the

acquisition and storage of data; the Controller must

allow interface updates in case of input, modification,

or removal of this data, updating the View component

that will be shown to the user. For the implementation

aspect, the use of libraries is crucial to improve the

app’s functionality. Choices include OkHttp for

efficient network operations management, GSON for

JSON data manipulation, MPAndroidChart for

graphical result representation, and Room Persistence

Library for easy access to local SQlite database data.

In addition, Google’s Firebase Authentication SDK

ensures secure access to the application through

different user authentication modes.

3.1 Authentication and Patient

Management

User authentication is the initial interface that will be

shown to the user. A CardView has been integrated to

show editable fields. In the Activity section, the user

can register by clicking on the appropriate TextView,

which redirects to the User Registration Activity.

Handwriting Detection Test (HWDT): Android Application for the Recognition of Neurodegenerative Diseases

987

Both processes are connected to Firebase service

methods, implemented within the project's scale, and

configured through the google-service.json file in the

application directory.

In case of a new registration, a filter has been set

to fill in all the fields shown in the CardView;

otherwise, the system notify the user with the help of

a Toast (dynamic widget for messages). Once

communication between the device and the Firebase

service occurs, checks will be carried out with the

condition, followed by the isSuccesful() method,

which will be successful only if the access or

registration is successful; otherwise an error will be

notified. In Firebase Authentication, the user

information object includes the credential entered

when filling in the editable fields on the interface,

resulting in the addition of a property called UUID

(Universally Unique Identifier), used to identify so

that identification is possible within the application

uniquely.

After logging in, users have access to the

following Activities. Managing authentication

operations involves creating a FirebaseAuth object

and using it to verify the user's authentication status

by declaring a FirebaseUser object.

Figure 2: Access activity and user registration.

The process of adding patient data takes place by

creating a local database in the application, using the

Data Access Object (DAO) design pattern to separate

the data access logic from the rest of the application.

The Room library is integrated to facilitate the

implementation of the database with a UUID

generated during authentication. The database

management class declares the entities involved, such

as patients and business data. CRUD operations

(Create, Read, Update, Delete) are declared by

methods in the class, allowing data to be added,

removed, updated, and deleted. For the insertion of

patient data, a Activity similar to that of recording is

used, with a CardView containing widgets such as

Spinner and radiobutton to select gender options.

After completing the fields, the user can confirm

the addition, and receive a notification about entering

the data in the Patients table of the database. CRUD

operations are defined in an interface, allowing

further future database management operations to be

added. Subsequently, the operator can manage patient

data through an Activity called ListPatient, which

displays the list of registered patients.

Operations are implemented with the use of an

AlertDialog widget, which allows the operator to read

patient information and perform operations such as

removal, testing or demo.

Figure 3: Additional patient information.

3.2 Task

After reviewing the drawing and writing activities, it

is presents a concise vision of how the proposed

screening test should be carried out. Considering

potential unfamiliarity with technology, it’s been

incorporated a demo phase with simple tasks to allow

them to become familiar with the system, before

proceeding with the complete test. The demo phase

comprises three activities: written word production,

horizontal and vertical point connection, and

replication of a square shape. This phase, intended to

be user-friendly, spans approximately 4 minutes.

Subsequently, participants complete the screening

tests in digital version, expected for about 15 minutes.

The specified timeline reflects an optimal trajectory

for cognitively healthy individuals.

Figure 4: Flow chart of design application.

NeroPRAI 2024 - Workshop on Medical Condition Assessment Using Pattern Recognition: Progress in Neurodegenerative Disease and

Beyond

988

Screening test:

• Clock Drawing Task (CDT): is a cognitive

functions screening measure. As a detective tool, the

test evaluates a range of cognitive abilities including

several executive functions. The task consists of the

replication of an analogical clock with numbers and

dials (Handzlik et al., 2023; Schejter-Margalit et al.,

2021).

• Pentagon Drawing Test (PDT): the test is a sub-

component of the MMSE test to evaluate visuospatial

function. The evaluation concerns the accuracy of the

drawing, the symmetry and the correct position of the

angles (Hosseini-Kivanani et al., 2023).

• Trail Making Test (TMT): The test requires to

connect a sequence of targets to evaluate working

memory, attention, visual-conceptual and visual-

motor tracking. It is composed of two performance

tasks: one phase involves only numerical targets (1,

2, 3, …), the other phase requires to alternate between

numbers and letters (1, A, 2, B, …) (Zhang et al.,

2023)

• Attentional Matrices test (AMT): The

Attentional Matrix test aims to evaluate selective

attention during a visual task. It consists in a grid of

numbers or words where the subject is invited to

cancel a certain number of target variables (Gattulli

et al., 2022; Gattulli et al., 2023a; Gattulli et al.,

2023b).

• Spiral Drawing and Copying Test: In this task,

individuals are required to replicate or copy the

Archimedes spiral. Indeed, it is used particularly in

assessing motor abnormalities (Thakur et al., 2023).

• Handwriting: this task consists of a simple non-

sense words task. Authors suggest to employ the

pattern involves the repetition of the word "le".

Evidence shows that signs of degradation in

handwriting has been observed during repeated

actions (Impedovo et al., 2019).

3.3 Data Input Acquisition

When the patient starts one of the screening test tasks,

a BottomNavigationView widget is displayed. This

widget allows the operator to navigate linearly during

the execution of the different tasks, allowing you to

return to the previous task, proceed to the next or

cancel the test by pressing on the icon representing a

"home", which reports to the Dashboard.

To collect input data generated with the stylus, the

SpenEventManager class is used, a Java class that

handles pen events. This class adopts the methods of

MotionEvent, the standard class of Android for the

recognition of user input types, allowing the filtering

of data to be acquired. Unlike the

BottomNavigationView, with which you can also

interact using the palm of your hand, to represent the

path traced with the stylus, a custom view has been

implemented within the various layouts, providing a

virtual drawing area. The DrawingView class extends

the View class and initializes objects like Paint, to set

the background color, and SpenEventManager, to get

the data for the graphic representation. When

capturing generated events, it is critical to recognize

cases of onHover or ontouch data, using an Enum

variable to track the status of the stylus relative to the

screen. The data captured by MotionEvent includes

the x and y coordinates, the time stamp, the tilt, the

press and the button used. This data represents a

single point on the screen and is converted to a custom

format, stored as JSON and saved locally in the

application. The manipulation of this data, through

the CustomFormatConverter.java class, is essential to

adapt them to the needs of the artificial intelligence

algorithm, ensuring accuracy and relevance in

analysis and predictions.

After conversion, the new string is again

encapsulated in a JSON file and saved locally on the

device. The saved files are accessible to the operator

via the File Explorer option in the Dashboard, which

shows a list of folders related to registered patients

and, within them, the test files performed with

indication of the date and time. To manage folder

creation and file saving, a file management logic has

been implemented with variables that consider the

relative path.

During the early stages of development, the

execution of the drawing was not fluid. The drawing,

or "pattern", was created by touching the screen with

the stylus, generating a "Canvas" inside a "Path"

object. At this stage, there was a delay in the

execution of complex drawings. To overcome this

difficulty, the RDP (Ramer-Douglas-Peucker)

algorithm has been implemented, which simplifies

the representation of a line by removing non-

significant intermediate points. The algorithm selects

key points, calculates the distance between the

intermediate points and the straight line between the

key points, keeping only the significant points. The

integration of this algorithm, instead of using a

Bitmap object, optimizes efficiency based on the

device. The code presents a main cycle that simplifies

the path, obtaining simplified coordinates and adding

them to the simplified path with a specific sampling

distance.

Handwriting Detection Test (HWDT): Android Application for the Recognition of Neurodegenerative Diseases

989

Figure 5: Example of task.

3.4 Sending Data to the Web Service

The process described is about sending samples for

screening testing to a web service. Using the OkHttp

library, a connection to the server is opened via a

Runnable object. Files in the directory are iterated and

sent to the microservice via an asynchronous thread,

showing the user an upload interface. During

iteration, progress is monitored via a progress bar.

For each JSON file, a Callback object is created

to handle successful notification or any errors, such

as IOException in case of problems reading the file or

InterruptedException for thread handling.

3.5 Final Report

To develop an interface to visualize the results,

methods have been implemented to represent the

speed, pressure and acceleration data obtained during

the drawing tasks. The results are presented through

a table using the ReciclerView component, extracted

from a Room database. Given the complexity of the

data (15 tasks in one session), a ReciclerView with an

Adapter was chosen to efficiently handle large

datasets.

To improve the representation, the

MPAndroidChart library was introduced to create a

Radar Chart, allowing multidimensional visualization

of prediction data on a series of rays. The graph

includes a static red line to indicate the minimum gap

for the severity index of the disease and a blue line to

represent data that exceeds the gap. Crossing the red

line indicates a potential dementia patient. In

addition, tables containing kinematic data specific to

each task have been implemented, using a class that

extends ReciclerView.Adapter.

When the report is presented, the tables show data

related to the task, such as drawing a clock or copying

two pentagons, along with their kinematic values.

3.6 AI Service

The Web Server is fundamental in the internet

infrastructure, separating calculation and data

evaluation from the device. The AI Service uses

different systems, allowing the creation of an

environment with a framework to receive data, make

predictions and obtain numerical results. Machine

Learning, part of AI, develops algorithms to learn

from past data. It adopts supervised learning,

classification in specific context. It follows a

structured life cycle: problem study, data collection

and preparation, choice of model.

MLOps (Machine Learning Operations)

facilitates the implementation, management and

maintenance of Machine Learning models, ensuring a

smooth transition from development to deployment.

METHODS: the Random Forest algorithm was

implemented for classification. Studies show an

average accuracy of 94.5%, exceeding individual

Decision Trees (92.5%).

SET UP: The algorithm is evaluated considering

the speed in the execution of drawing tasks as

biomarker.

Kinematic features such as the Fourier Discrete

Transform are used for the Maxwell-Boltzmann

speed profile and distribution to recognize deficits

related to neurodegenerative diseases.

4 CONCLUSION

This paper introduces innovative E-Health tools to

detect signs of neurodegenerative impairment.

Specifically, an Android App was developed to

collect data on individual performance in handwriting

tasks. The App includes a battery of standardized tests

that measure performance by testing different

cognitive domains. The instrument has demonstrated

its effectiveness in acquiring data generated by digital

pens.

The AI application's model has exhibited positive

outcomes in classification avoiding values exceeding

the "minimum gap" threshold, as indicated in the

radar chart. Moreover, the model can detect

individuals with no form of ND and classify them as

healthy. During user evaluation scales conducted in

the testing phases, favorable results emerged

regarding usability and user satisfaction with the

interface implemented in the prototype.

Despite the results, this work presents some

limits. The current configuration lacks of immediate

communication between the server and the

application, leading to delays exceeding 5 minutes in

NeroPRAI 2024 - Workshop on Medical Condition Assessment Using Pattern Recognition: Progress in Neurodegenerative Disease and

Beyond

990

obtaining results from the artificial intelligence

model. Recognizing its early stage of development,

there is a concerted effort to craft a prototype ready

for user deployment. This step aims to assess

functionalities and interactions, providing an initial

glimpse into the application's performance.

Further studies could implement a framework that

manages requests made by the application to the

microservice. This approach aims to reduce the

current computational burden and response time

imposed on the device. The adaptability in the

Android development environment is noteworthy,

allowing scalability across various hardware

resources. This flexibility enables the testing of the

prototype on different products with varying

hardware characteristics, offering a broader

perspective on its performance and usability.

The insights gained from these observations will

guide potential enhancements in subsequent

iterations, ensuring the continuous refinement and

optimization of the application.

ACKNOWLEDGMENTS

This article and related research have also been

conducted with the support of Alessia Monaco, a

Ph.D. student enrolled in the National PhD program

in Artificial Intelligence, XXXIX cycle, course on

Health and life sciences, organized by Università

Campus Bio-Medico di Roma.

More, Gianfranco Semeraro Ph.D. student

enrolled in the Italian National Inter-University Ph.D.

course in Sustainable Development and Climate

Change organized by University School for

Advanced Studies IUSS Pavia.

REFERENCES

Abbatantuono, C., Alfeo, F., Clemente, L., Lancioni, G., De

Caro, M. F., Livrea, P., & Taurisano, P. (2023). Current

Challenges in the Diagnosis of Progressive

Neurocognitive Disorders: A Critical Review of the

Literature and Recommendations for Primary and

Secondary Care. Brain Sciences 2023, Vol. 13, Page

1443, 13(10), 1443. https://doi.org/10.3390/

BRAINSCI13101443

Afzal, S., Maqsood, M., Khan, U., Mehmood, I., Nawaz,

H., Aadil, F., Song, O. Y., & Nam, Y. (2021).

Alzheimer Disease Detection Techniques and Methods:

A Review. International Journal of Interactive

Multimedia and Artificial Intelligence, 6(7), 26–38.

https://doi.org/10.9781/IJIMAI.2021.04.005

Albert, M. S., DeKosky, S. T., Dickson, D., Dubois, B.,

Feldman, H. H., Fox, N. C., ... & Phelps, C. H. (2011).

The diagnosis of mild cognitive impairment due to

Alzheimer's disease: recommendations from the

National Institute on Aging‐Alzheimer's Association

workgroups on diagnostic guidelines for Alzheimer's

disease. Alzheimer's & dementia, 7(3), 270-279.

Angelillo, M. T., Balducci, F., Impedovo, D., Pirlo, G., &

Vessio, G. (2019). Attentional Pattern Classification for

Automatic Dementia Detection. IEEE Access, 7,

57706–57716. https://doi.org/10.1109/ACCESS.

2019.291368 5

Angelillo, M. T., Impedovo, D., Pirlo, G., & Vessio, G.

(2019). Performance-driven handwriting task selection

for Parkinson’s disease classification. In AI* IA 2019–

Advances in Artificial Intelligence: XVIIIth

International Conference of the Italian Association for

Artificial Intelligence, Rende, Italy, November 19–22,

2019, Proceedings 18 (pp. 281-293). Springer

International Publishing.

Aouraghe, I., Khaissidi, G., & Mrabti, M. (2023). A

literature review of online handwriting analysis to

detect Parkinson’s disease at an early stage. Multimedia

Tools and Applications, 82(8), 11923–11948.

https://doi.org/10.1007/S11042- 022-13759-

2/TABLES/5

Ardimento, P., Aversano, L., Bernardi, M. L., Cimitile, M.,

& Iammarino, M. (2021). Temporal convolutional

networks for just-in-time design smells prediction using

fine-grained software metrics. Neurocomputing, 463,

454-471.

Armstrong, M. J., & Okun, M. S. (2020). Diagnosis and

treatment of Parkinson disease: a review. Jama, 323(6),

548-560.

Aversano, L., Bernardi, M. L., Cimitile, M., Iammarino,

M., & Romanyuk, K. (2020). Investigating on the

Relationships between Design Smells Removals and

Refactorings. International Conference on Software

and Data Technologies, 212–219. https://doi.org/10.

5220/0009887102120219

Bloem, B. R., Okun, M. S., & Klein, C. (2021). Parkinson's

disease. Lancet (London, England), 397(10291), 2284–

2303. https://doi.org/10.1016/S0140-6736(21)00218-X

Bosboom, J. L. W., Stoffers, D., & Wolters, E. C. (2004).

Cognitive dysfunction and dementia in Parkinson’s

disease. Journal of neural transmission, 111, 1303-

1315.

Calub, G. I. A., Elefante, E. N., Galisanao, J. C. A., Iguid,

S. L. B. G., Salise, J. C., & Prado, S. V. (2023, June).

EEG-based classification of stages of alzheimer’s

disease (AD) and mild cognitive impairment (MCI). In

2023 5th International Conference on Bio-engineering

for Smart Technologies (BioSMART) (pp. 1-6). IEEE.

Cannarile, A., Dentamaro, V ., Galantucci, S., Iannacone,

A., Impedovo, D., & Pirlo, G. (2022). Comparing Deep

Learning and Shallow Learning Techniques for API

Calls Malware Prediction: A Study. Applied Sciences

(Switzerland), 12(3). https://doi.org/10.3390/

APP12031645

Handwriting Detection Test (HWDT): Android Application for the Recognition of Neurodegenerative Diseases

991

Carrarini, C., Russo, M., Dono, F., Di Pietro, M., Rispoli,

M. G., Di Stefano, V., Ferri, L., Barbone, F., Vitale, M.,

Thomas, A., Sensi, S. L., Onofrj, M., & Bonanni, L.

(2019). A Stage-Based Approach to Therapy in

Parkinson's Disease. Biomolecules, 9(8), 388.

https://doi.org/10.3390/biom9080388

Carrera, F ., Dentamaro, V ., Galantucci, S., Iannacone, A.,

Impedovo, D., & Pirlo, G. (2022). Combining

Unsupervised Approaches for Near Real-Time

Network Traffic Anomaly Detection. Applied Sciences

2022, V ol. 12, Page 1759, 12(3), 1759.

https://doi.org/10.3390/APP12031759

Chahine, L. M., Beach, T. G., Brumm, M. C., Adler, C. H.,

Coffey, C. S., Mosovsky, S., Caspell-Garcia, C.,

Serrano, G. E., Munoz, D. G., White, C. L., Crary, J. F.,

Jennings, D., Taylor, P., Foroud, T., Arnedo, V., Kopil,

C. M., Riley, L., Dave, K. D., & Mollenhauer, B.

(2020). In vivo distribution of α-synuclein in multiple

tissues and biofluids in Parkinson disease. Neurology,

95(9), E1267–E1284. https://doi.org/10.1212/

WNL.0000000000010404/ASSET/9180DD2D-0B1F-

49B1-AB62-0F2D21F3218D/ASSETS/GRAPHIC/

18TTU2B.JPEG

Chai, J., Wu, R., Li, A., Xue, C., Qiang, Y., Zhao, J., Zhao,

Q., & Yang, Q. (2023). Classification of mild cognitive

impairment based on handwriting dynamics and qEEG.

Computers in Biology and Medicine, 152, 106418.

https://doi.org/10.1016/j.compbiomed.2022.106418

Chandra, J., Muthupalaniappan, S., Shang, Z., Bose, S.,

Deng, R., Pecyna, E., Chen, A., Lin, R., Butts, D., &

Capo-Battaglia, A. (2021). Validation of dementia

diagnostics toolbox using interactive iPad technology.

Alzheimer’s & Dementia, 17, e052988.

https://doi.org/10.1002/ALZ.052988

Chen, Y., Qian, X., Zhang, Y., Su, W., Huang, Y., Wang,

X., Chen, X., Zhao, E., Han, L., & Ma, Y. (2022).

Prediction Models for Conversion From Mild

Cognitive Impairment to Alzheimer’s Disease: A

Systematic Review and Meta-Analysis. Frontiers in

Aging Neuroscience, 14, 840386.

https://doi.org/10.3389/fnagi.2022.840386

Cheriet, M., Dentamaro, V., Hamdan, M., Impedovo, D., &

Pirlo, G. (2023). Multi-speed transformer network for

neurodegenerative disease assessment and activity

recognition. Computer Methods and Programs in

Biomedicine, 230, 107344.

Cilia, N. D., De Stefano, C., Fontanella, F., Molinara, M.,

& Scotto Di Freca, A. (2019). Handwriting analysis to

support alzheimer’s disease diagnosis: a preliminary

study. In Computer Analysis of Images and Patterns:

18th International Conference, CAIP 2019, Salerno,

Italy, September 3–5, 2019, Proceedings, Part II

18 (pp. 143-151). Springer International Publishing.

De Stefano, C., Fontanella, F., Impedovo, D., Pirlo, G., &

Scotto di Freca, A. (2019). Handwriting analysis to

support neurodegenerative diseases diagnosis: A

review. Pattern Recognition Letters, 121, 37–45.

https://doi.org/10.1016/j.patrec.2018.05.013

Dentamaro, V., Impedovo, D., & Pirlo, G. (2018). LICIC:

Less important components for imbalanced multiclass

classification. Information (Switzerland), 9(12).

https://doi.org/10.3390/info9120317

Drotár, P., Mekyska, J., Rektorová, I., Masarová, L.,

Smékal, Z., & Faundez-Zanuy, M. (2016). Evaluation

of handwriting kinematics and pressure for differential

diagnosis of Parkinson's disease. Artificial intelligence

in Medicine, 67, 39-46.

Dugger, B. N., & Dickson, D. W. (2017). Pathology of

Neurodegenerative Diseases. Cold Spring Harbor

Perspectives in Biology, 9(7).

https://doi.org/10.1101/CSHPERSPECT.A028035

Faundez-Zanuy, M., Fierrez, J., Ferrer, M. A., Diaz, M.,

Tolosana, R., & Plamondon, R. (2020). Handwriting

Biometrics: Applications and Future Trends in e-

Security and e-Health. Cognitive Computation, 12(5),

940–953. https://doi.org/10.1007/s12559-020-09755-z

Faundez-Zanuy, M., Mekyska, J., & Impedovo, D. (2021).

Online Handwriting, Signature and Touch Dynamics:

Tasks and Potential Applications in the Field of

Security and Health. Cognitive Computation, 13(5),

1406– 1421. https://doi.org/10.1007/s12559-021-

09938-2

Folstein, M. F., Folstein, S. E., & McHugh, P. R. (1975).

‘Mini-mental state’. A practical method for grading the

cognitive state of patients for the clinician. Journal of

Psychiatric Research, 12(3), 189–198.

https://doi.org/10.1016/0022- 3956(75)90026-6

Gattulli, V., Impedovo, D., Pirlo, G., & Sarcinella, L.

(2023a). Human Activity Recognition for the

Identification of Bullying and Cyberbullying Using

Smartphone Sensors. Electronics, 12(2), 261.

https://doi.org/10.3390/ELECTRONICS12020261

Gattulli, V., Impedovo, D., Pirlo, G., & Semeraro, G.

(2022). Early Dementia Identification: On the Use of

Random Handwriting Strokes. In International

Graphonomics Conference (pp. 285-300). Cham:

Springer International Publishing.

Gattulli, V., Impedovo, D., Pirlo, G., & Semeraro, G.

(2023b). Handwriting Task-Selection based on the

Analysis of Patterns in Classification Results on

Alzheimer Dataset.

Gattulli, V., Impedovo, D., Pirlo, G., & Volpe, F. (2023c).

Touch events and human activities for continuous

authentication via smartphone. Scientific Reports 2023

13:1, 13(1), 1–7. https://doi.org/10.1038/s41598-023-

36780-3

Gmez-Ro, M., Moreno Caballero, M., Manuel Grriz

Sez, J., & Mnguez-Castellanos, A. (2016). Diagnosis

of Neurodegenerative Diseases: The Clinical

Approach. Current Alzheimer Research, 13(5), 469–

474. https://doi.org/10.2174/

1567205013666151116141603

Handzlik, D., Richmond, L. L., Skiena, S., Carr, M. A.,

Clouston, S. A. P., & Luft, B. J. (2023). Explainable

automated evaluation of the clock drawing task for

memory impairment screening. Alzheimer’ s &

Dementia: Diagnosis, Assessment & Disease

Monitoring, 15(2), e12441. https://doi.org/10.

1002/DAD2.12441

NeroPRAI 2024 - Workshop on Medical Condition Assessment Using Pattern Recognition: Progress in Neurodegenerative Disease and

Beyond

992

Hansson, O. (2021). Biomarkers for neurodegenerative

diseases. Nature Medicine 2021 27:6, 27(6), 954–963.

https://doi.org/10.1038/s41591-021-01382-x

Heinzel, S., Berg, D., Gasser, T., Chen, H., Yao, C.,

Postuma, R. B., & MDS Task Force on the Definition

of Parkinson's Disease (2019). Update of the MDS

research criteria for prodromal Parkinson's disease.

Movement disorders : official journal of the Movement

Disorder Society, 34(10), 1464–1470.

https://doi.org/10.1002/mds.27802

Hoehn, M. M., & Yahr, M. D. (1967). Parkinsonism: Onset,

progression, and mortality. Neurology, 17(5), 427–442.

https://doi.org/10.1212/WNL.17.5.427

Hoops, S., Nazem, S., Siderowf, A. D., Duda, J. E., Xie, S.

X., Stern, M. B., & Weintraub, D. (2009). Validity of

the MoCA and MMSE in the detection of MCI and

dementia in Parkinson disease. Neurology, 73(21),

1738-1745.

Hosseini-Kivanani, N., Salobrar-García, E., Elvira-

Hurtado, L., López-Cuenca, I., de Hoz, R., Ramírez, J.

M., ... & Leiva, L. A. (2023, October). Better Together:

Combining Different Handwriting Input Sources

Improves Dementia Screening. In 2023 IEEE 19th

International Conference on e-Science (e-Science) (pp.

1-7). IEEE.

Iachini, I., Iavarone, A., Senese, V. P., Ruotolo, F., &

Ruggiero, G. (2009). Visuospatial memory in healthy

elderly, AD and MCI: a review. Current aging

science, 2(1), 43–59. https://doi.org/10.2174/

1874609810902010043

Impedovo, D., & Pirlo, G. (2018). Dynamic Handwriting

Analysis for the Assessment of Neurodegenerative

Diseases: A Pattern Recognition Perspective. IEEE

Reviews in Biomedical Engineering, 12, 209–220.

https://doi.org/10.1109/RBME.2018.2840679

Impedovo, D., & Pirlo, G. (2019). Online Handwriting

Analysis for the Assessment of Alzheimer’s Disease

and Parkinson’s Disease: Overview and Experimental

Investigation. Frontiers in Pattern Recognition and

Artificial Intelligence, 113–128. https://doi.org/10.

1142/9789811203527_0007

Impedovo, D., Dentamaro, V ., Abbattista, G., Gattulli, V.,

& Pirlo, G. (2021). A comparative study of shallow

learning and deep transfer learning techniques for

accurate fingerprints vitality detection. Pattern

Recognition Letters, 151, 11–18. https://doi.org/10.

1016/j.patrec.2021.07.025

Impedovo, D., Dentamaro, V., Pirlo, G., & Sarcinella, L.

(2019). TrafficWave: Generative deep learning

architecture for vehicular traffic flow prediction.

Applied Sciences (Switzerland), 9(24).

https://doi.org/10.3390/app9245504

Impedovo, D., Pirlo, G., Sarcinella, L., Stasolla, E., &

Trullo, C. A. (2012). Analysis of stability in static

signatures using cosine similarity. Proceedings -

International Workshop on Frontiers in Handwriting

Recognition, IWFHR, 231–235. 10.1109/

ICFHR.2012.180

Impedovo, D., Pirlo, G., Vessio, G., & Angelillo, M. T.

(2019). A Handwriting-Based Protocol for Assessing

Neurodegenerative Dementia. Cognitive Computation,

11(4), 576–586. https://doi.org/10.1007/S12559-019-

09642- 2/TABLES/7

Jankovic J. (2008). Parkinson's disease: clinical features

and diagnosis. Journal of neurology, neurosurgery, and

psychiatry, 79(4), 368–376. https://doi.org/10.1136/

jnnp.2007.131045

Kumar, A., Sidhu, J., Goyal, A., Tsao, J. W., & Doerr, C.

(2022). Alzheimer Disease (Nursing). In StatPearls.

StatPearls Publishing.

Lamptey, R. N. L., Chaulagain, B., Trivedi, R., Gothwal,

A., Layek, B., & Singh, J. (2022). A Review of the

Common Neurodegenerative Disorders: Current

Therapeutic Approaches and the Potential Role of

Nanotherapeutics. International Journal of Molecular

Sciences, 23(3). https://doi.org/10.3390/

IJMS23031851

Lauraitis, A., Maskeliunas, R., Damasevicius, R., Polap, D.,

& Wozniak, M. (2019). A Smartphone Application for

Automated Decision Support in Cognitive Task Based

Evaluation of Central Nervous System Motor

Disorders. IEEE Journal of Biomedical and Health

Informatics, 23(5), 1865–1876. https://doi.org/10.

1109/JBHI.2019.2891729

Marino, B. L., de Souza, L. R., Sousa, K., Ferreira, J. V.,

Padilha, E. C., da Silva, C. H., ... & Hage-Melim, L. I.

(2020). Parkinson’s disease: a review from

pathophysiology to treatment. Mini reviews in

medicinal chemistry, 20(9), 754-767.

Menndez-Gonzlez, M. (2023). Toward a new nosology

of neurodegenerative diseases. Alzheimer’ s &

Dementia, 19(8), 3731–3737. https://doi.org/10.

1002/ALZ.13041

Mordhorst, S., Coulehan, K., & Roseman, E. C. (2022).

Neuropsychology Assessment in Dementia and

Neurodegenerative Disease. Hybrid PET/MR

Neuroimaging: A Comprehensive Approach, 247-255.

Nasreddine, Z. S., Phillips, N. A., Bédirian, V.,

Charbonneau, S., Whitehead, V., Collin, I., Cummings,

J. L., & Chertkow, H. (2005). The Montreal Cognitive

Assessment, MoCA: A Brief Screening Tool For Mild

Cognitive Impairment. Journal of the American

Geriatrics Society, 53(4), 695–699. https://doi.org/10.

1111/J.1532-5415.2005.53221.X

Petersen, R. C. (2016). Mild cognitive impairment.

CONTINUUM: Lifelong Learning in Neurology, 22(2

Dementia), 404. https://doi.org/10.1212/

CON.0000000000000313

Pirlo, G., & Impedovo, D. (2013). A new class of monotone

functions of the residue number system. International

journal of mathematical models and methods in applied

sciences, 7(9), 802-809.

Ritchie, K., Carriere, I., Su, L., O'Brien, J. T., Lovestone,

S., Wells, K., & Ritchie, C. W. (2017). The midlife

cognitive profiles of adults at high risk of late-onset

Alzheimer's disease: The PREVENT

study. Alzheimer's & Dementia, 13(10), 1089-1097.

Rosenblum, S., Richardson, A., Meyer, S., Nevo, T., Sinai,

M., & Hassin-Baer, S. (2021). DailyCog: A Real-World

Functional Cognitive Mobile Application for

Handwriting Detection Test (HWDT): Android Application for the Recognition of Neurodegenerative Diseases

993

Evaluating Mild Cognitive Impairment (MCI) in

Parkinson’s Disease. Sensors 2021, Vol. 21, Page 1788,

21(5), 1788. https://doi.org/10.3390/S21051788

Sblendorio, E., Simonetti, V., Comparcini, D., D’accolti,

D., Germini, F., Imbriaco, G., Lo Cascio, A., Milani,

A., Napolitano, D., Israr, A., & Cicolini, G. (2023).

Assessment of Stress Levels using technological tools:

A Review and Prospective Analysis of Heart Rate

Variability and Sleep Quality Parameters.

neurodegenerative diseases, 4, 5.

Schejter-Margalit, T., Kizony, R., Shirvan, J., Cedarbaum,

J. M., Bregman, N., Thaler, A., Giladi, N., & Mirelman,

A. (2021). Quantitative digital clock drawing test as a

sensitive tool to detect subtle cognitive impairments in

early stage Parkinson’s disease. Parkinsonism &

Related Disorders, 90, 84–89. https://doi.org/10.

1016/j.parkreldis.2021.08.002

Shigemizu, D., Akiyama, S., Higaki, S., Sugimoto, T.,

Sakurai, T., Boroevich, K. A., Sharma, A., Tsunoda, T.,

Ochiya, T., Niida, S., & Ozaki, K. (2020). Prognosis

prediction model for conversion from mild cognitive

impairment to Alzheimer’s disease created by

integrative analysis of multi-omics data. Alzheimer’ s

Research and Therapy, 12(1), 1–12.

Siqueira, G. S. A., Hagemann, P. D. M. S., Coelho, D. D.

S., Santos, F. H. Dos, Bertolucci, P. H. F., & Heyn, P.

C. (2019). Can MoCA and MMSE Be Interchangeable

Cognitive Screening Tools? A Systematic Review. The

Gerontologist, 59(6), E743–E763. https://doi.org/10.

1093/geront/gny126

Thakur, M., Dhanalakshmi, S., Kuresan, H., Senthil, R.,

Narayanamoorthi, R., & Lai, K. W. (2023). Automated

restricted Boltzmann machine classifier for early

diagnosis of Parkinson’s disease using digitized spiral

drawings. Journal of Ambient Intelligence and

Humanized Computing, 14(1), 175–189.

Tolosa, E., Garrido, A., Scholz, S. W., & Poewe, W. (2021).

Challenges in the diagnosis of Parkinson’s disease. The

Lancet Neurology, 20(5), 385–397. 10.1016/S1474-

4422(21)00030-2

Tsoi, K. K. F., Chan, J. Y. C., Hirai, H. W., Wong, S. Y. S.,

& Kwok, T. C. Y. (2015). Cognitive Tests to Detect

Dementia: A Systematic Review and Meta-analysis.

JAMA Internal Medicine, 175(9), 1450–1458.

10.1001/jamainternmed.2015.2152

Utpatadevi, N.L., Sudana, A.A., & Cahyawan, A.A. (2012).

Implementation of MVC (Model-View-Controller)

Architectural to Academic Management Information

System with Android Platform Base. International

Journal of Computer Applications, 57, 1-6.

Weintraub, S., Carrillo, M. C., Farias, S. T., Goldberg, T.

E., Hendrix, J. A., Jaeger, J., Knopman, D. S.,

Langbaum, J. B., Park, D. C., Ropacki, M. T., Sikkes,

S. A. M., Welsh- Bohmer, K. A., Bain, L. J., Brashear,

R., Budur, K., Graf, A., Martenyi, F., Storck, M. S., &

Randolph, C. (2018). Measuring cognition and function

in the preclinical stage of Alzheimer’s disease.

Alzheimer’ s Translational Research Interventions,

https://doi.org/10.1016/J.TRCI.2018.01.003

Wicks, P., Stamford, J., Grootenhuis, M. A., Haverman, L.,

& Ahmed, S. (2014). Innovations in e-health. Quality

of Life Research, 23, 195-203.

Wilson, D. M., 3rd, Cookson, M. R., Van Den Bosch, L.,

Zetterberg, H., Holtzman, D. M., & Dewachter, I.

(2023). Hallmarks of neurodegenerative diseases. Cell,

186(4), 693–714. https://doi.org/10.1016/j.cell.

2022.12.032

Zhang, J., Lee, Y., Chung, T. M., & Park, H. (2023,

November). Development of a Handwriting Drawings

Assessment System for Early Parkinson’s Disease

Identification with Deep Learning Methods.

In International Conference on Future Data and

Security Engineering (pp. 484-499). Singapore:

Springer Nature Singapore.

Zhang, W., Zheng, X., Tang, Z., Wang, H., Li, R., Xie, Z.,

Yan, J., Zhang, X., Yu, Q., Wang, F., & Li, Y. (2023).

Combination of Paper and Electronic Trail Making

Tests for Automatic Analysis of Cognitive Impairment:

Development and Validation Study. Journal of Medical

Internet Research, 25(1), e42637. https://doi.org/10.

2196/42637

NeroPRAI 2024 - Workshop on Medical Condition Assessment Using Pattern Recognition: Progress in Neurodegenerative Disease and

Beyond

994