Handwriting speed in juvenile idiopathic arthritis using the detailed assessment of speed of handwriting.

BACKGROUND: Handwriting is a commonly reported functional limitation for children with juvenile idiopathic arthritis (JIA). The aim of this study was to evaluate handwriting in children with JIA. FINDINGS: Twelve children (mean age 13.0 years, SD = 1.9; range 9.1 to 15.6 years) with JIA completed the Detailed Assessment of Speed of Handwriting (DASH). The presence of hand and wrist arthritis, grip strength, disability, pain, and quality of life (QOL) was also assessed. The mean DASH score was 34.5th percentile (SD = 22.5). Eight (75%) scored below the 50th centile. DASH scores were negatively associated with grip strength (r = -0.31). CONCLUSIONS: Handwriting difficulties are common in children with JIA. Handwriting assessment may be helpful to direct treatments, and advocate for support and accommodations in school.

Presentation matters: Surface text features and text quality in written narratives of Dutch high school students with and without dyslexia.

Presentation features such as spelling, punctuation and handwriting can influence the evaluation of general text quality. High school students with dyslexia might therefore be at a disadvantage, as at least their spelling performance is typically poor(er). Furthermore, these students might show less sophisticated linguistic features of texts, such as word length and sentence complexity, that might also be related to text quality. We compared narratives written by Dutch high school students (mean age 13.7 years) with (n = 28) and without (n = 29) dyslexia. Students with dyslexia's texts contained more spelling errors and poorer handwriting quality, but not more punctuation errors. Teacher-rated general text quality was lower for the texts of students with dyslexia in uncorrected versions. When spelling and punctuation errors were corrected, no teacher-rated text quality differences emerged. No differences in linguistic text features were found. Furthermore, spelling, punctuation and, to a lesser extent, number of words per sentence clause were related to ratings of text quality across participants. These results confirm the influence of presentation features on text quality rating. They encourage teachers to be aware of this effect and emphasize the importance of spelling and writing support and interventions for students with dyslexia throughout education.

Contextual bias by Forensic Document Examination trainees: An empirical study from China.

The impact of contextual bias has been repeatedly demonstrated across forensic domains; however, research on this topic in China is scarce. To examine the prevalence of contextual bias in pattern feature-comparison disciplines, we conducted an experiment involving 24 forensic document examination students. The aim was to determine whether knowledge of different contextual information influenced their forensic decision-making. Participants were divided into different context groups and tasked with examining whether questioned signatures with ambiguous features matched reference signatures. The results of independent-samples t-tests for their decision score data in the two context groups exhibited a statistically significant difference (p < 0.05, Cohen's d > 0.8). Moreover, the submitted forensic reports by participants disclosed a biased evaluation of handwriting features. These findings show how contextual information can bias forensic decision-making in handwriting examination. Context management with complementary strategies such as case triage, cognitive training and decision-making transparency must be implemented to minimize bias in handwriting examination.

MXene-Based Skin-Like Hydrogel Sensor and Machine Learning-Assisted Handwriting Recognition.

Conductive hydrogels are widely used in flexible sensors owing to their adjustable structure, good conductivity, and flexibility. The performance of excellent mechanical properties, high sensitivity, and elastic modulus compatible with human tissues is of great interest in the field of flexible sensors. In this paper, the functional groups of trisodium citrate dihydrate (SC) and MXene form multiple hydrogen bonds in the polymer network to prepare a hydrogel with mechanical properties (Young's modulus (23.5-92 kPa) of similar human tissue (0-100 kPa)), sensitivity (stretched GF is 4.41 and compressed S1 is 5.15 MPa-1), and durability (1000 cycles). The hydrogel is able to sensitively detect deformations caused by strain and stress and can be used in flexible sensors to detect human movement in real time such as fingers, wrists, and walking. In addition, the combination of matrix sensing and machine learning was successfully used for handwriting recognition with an accuracy of 0.9744. The combination of machine learning and flexible sensors shows great potential in areas such as healthcare, information security, and smart homes.

SignEEG v1.0: Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems.

Handwritten signatures in biometric authentication leverage unique individual characteristics for identification, offering high specificity through dynamic and static properties. However, this modality faces significant challenges from sophisticated forgery attempts, underscoring the need for enhanced security measures in common applications. To address forgery in signature-based biometric systems, integrating a forgery-resistant modality, namely, noninvasive electroencephalography (EEG), which captures unique brain activity patterns, can significantly enhance system robustness by leveraging multimodality's strengths. By combining EEG, a physiological modality, with handwritten signatures, a behavioral modality, our approach capitalizes on the strengths of both, significantly fortifying the robustness of biometric systems through this multimodal integration. In addition, EEG's resistance to replication offers a high-security level, making it a robust addition to user identification and verification. This study presents a new multimodal SignEEG v1.0 dataset based on EEG and hand-drawn signatures from 70 subjects. EEG signals and hand-drawn signatures have been collected with Emotiv Insight and Wacom One sensors, respectively. The multimodal data consists of three paradigms based on mental, & motor imagery, and physical execution: i) thinking of the signature's image, (ii) drawing the signature mentally, and (iii) drawing a signature physically. Extensive experiments have been conducted to establish a baseline with machine learning classifiers. The results demonstrate that multimodality in biometric systems significantly enhances robustness, achieving high reliability even with limited sample sizes. We release the raw, pre-processed data and easy-to-follow implementation details.

The Improved Biometric Identification of Keystroke Dynamics Based on Deep Learning Approaches.

In an era marked by escalating concerns about digital security, biometric identification methods have gained paramount importance. Despite the increasing adoption of biometric techniques, keystroke dynamics analysis remains a less explored yet promising avenue. This study highlights the untapped potential of keystroke dynamics, emphasizing its non-intrusive nature and distinctiveness. While keystroke dynamics analysis has not achieved widespread usage, ongoing research indicates its viability as a reliable biometric identifier. This research builds upon the existing foundation by proposing an innovative deep-learning methodology for keystroke dynamics-based identification. Leveraging open research datasets, our approach surpasses previously reported results, showcasing the effectiveness of deep learning in extracting intricate patterns from typing behaviors. This article contributes to the advancement of biometric identification, shedding light on the untapped potential of keystroke dynamics and demonstrating the efficacy of deep learning in enhancing the precision and reliability of identification systems.

Evaluating handwriting in children with developmental coordination disorder (DCD): Temporal, spatial, pressure and grip-force measures.

BACKGROUND: Writing involves complex sensorimotor and biomechanical processes that regulate pressure on the writing surface. Researchers analyze writing to understand kinetics and kinematics by evaluating temporal, spatial, and pressure aspects, yet discerning writing surface pressure and pen-grip force remains challenging. AIMS: To compare handwriting kinetics (pen grip-force and surface pressure) and kinematics (temporal-spatial) of children with developmental coordination disorder (DCD) with those of typically developing (TD) children. METHODS AND PROCEDURES: Twenty-seven children with DCD aged 7-12 years and 27 TD children matched by age and gender copied a 29-word passage onto a computerized tablet. Temporal, spatial and surface pressure as well as pen grip-force were measured with a tablet and a wearable device respectively. OUTCOMES AND RESULTS: The DCD group displayed significantly longer total writing time, mean letter time, and greater letter height, width, variance, spacing, area, and erasures than the TD group. Although there were no significant between-group differences in the surface pressure or maintaining pressure, the DCD group displayed weaker grip-force, p = .01, with greater variance. CONCLUSIONS AND IMPLICATIONS: The DCD group's weaker grip-force dynamics correlated with reduced legibility, form, and prolonged writing duration, revealing insights into handwriting mechanisms, particularly grip force, crucial for effective clinical interventions.

Handedness and Its Impact on a Career in Medicine.

ABSTRACT: Left-handedness in a world of right lateral bias can be an invisible barrier both in everyday life as well as in medical career development, and throughout a medical career. Common everyday life actions, including screwing in lightbulbs, inserting a screw, or any action that requires a clockwise rotation, is designed for "righties," making life for "lefties" a challenge. Other examples include writing without a slant or without smudging. In medicine, the physical examination of a patient is taught using the right hand and standing on the right side of the patient, an awkward situation for left handers. Another major concern in medicine specifically, is handwriting-notoriously poor in lefties-impacting legibility in progress notes, prescriptions, and medical records. In surgery and other procedural specialties in particular, using instruments intended for right-handed individuals, including suturing and positioning at the operating room table, presents left-handed individuals with particular challenges. Left-handed medical students and residents are especially vulnerable, as they may feel uncomfortable requesting special accommodations for their "handedness." The significance and impact of handedness often go unrecognized, yet may play a substantial role in career choices: the difficulties of being left-handed may dissuade students from pursuing their desired career. Solutions are available, including using instruments designed for left-handers (or learning to use "righty" instruments), and positioning at the operating room or procedure table as preferred by the left-handed individual. These solutions often require a cooperative attitude by colleagues. The authors describe the significance of handedness, including their own personal experiences, and offer some solutions for left-handed individuals who struggle to adapt to a right-handed world.

The role of handwriting in English word acquisition among elementary students.

In order to investigate whether handwriting has an advantage in learning word form, sound, and meaning, this study randomly selected 40 elementary school student participants (20 males, 20 females, aged 11.4 ± 1.34 years). Using an experimental approach, we compared the learning outcomes of word sound matching, word meaning matching, and word form judgment tasks under two conditions: handwriting and visual learning. After three consecutive days of learning and testing, we found that handwriting generally outperformed visual learning in terms of accuracy and response time in word form, sound, and meaning learning. Additionally, we observed differences in the timing of significant discrepancies in learning outcomes between the two methods across the three tasks. Specifically, in terms of accuracy, discrepancies first appeared in the word sound matching task on the first day, followed by the word form judgment task, and lastly the word meaning matching task. Regarding response time, significant differences between learning methods first emerged in the word form judgment task, followed by the word sound and word meaning tasks. Thus, combining accuracy and response time data, we conclude that handwriting is more advantageous than visual learning for word acquisition, with a differential impact on word form, sound, and meaning, where word form and sound are prioritized over meaning.

ET-Network: A novel efficient transformer deep learning model for automated Urdu handwritten text recognition.

Automatic Urdu handwritten text recognition is a challenging task in the OCR industry. Unlike printed text, Urdu handwriting lacks a uniform font and structure. This lack of uniformity causes data inconsistencies and recognition issues. Different writing styles, cursive scripts, and limited data make Urdu text recognition a complicated task. Major languages, such as English, have experienced advances in automated recognition, whereas low-resource languages, such as Urdu, still lag. Transformer-based models are promising for automated recognition in high- and low-resource languages such as Urdu. This paper presents a transformer-based method called ET-Network that integrates self-attention into EfficientNet for feature extraction and a transformer for language modeling. The use of self-attention layers in EfficientNet helps to extract global and local features that capture long-range dependencies. These features proceeded into a vanilla transformer to generate text, and a prefix beam search is used for the finest outcome. NUST-UHWR, UPTI2.0, and MMU-OCR-21 are three datasets used to train and test the ET Network for a handwritten Urdu script. The ET-Network improved the character error rate by 4% and the word error rate by 1.55%, while establishing a new state-of-the-art character error rate of 5.27% and a word error rate of 19.09% for Urdu handwritten text.

Direct Retrieval of Orthographic Representations in Chinese Handwritten Production: Evidence from a Dynamic Causal Modeling Study.

This present study identified an optimal model representing the relationship between orthography and phonology in Chinese handwritten production using dynamic causal modeling, and further explored how this model was modulated by word frequency and syllable frequency. Each model contained five volumes of interest in the left hemisphere (angular gyrus [AG], inferior frontal gyrus [IFG], middle frontal gyrus [MFG], superior frontal gyrus [SFG], and supramarginal gyrus [SMG]), with the IFG as the driven input area. Results showed the superiority of a model in which both the MFG and the AG connected with the IFG, supporting the orthography autonomy hypothesis. Word frequency modulated the AG → SFG connection (information flow from the orthographic lexicon to the orthographic buffer), and syllable frequency affected the IFG → MFG connection (information transmission from the semantic system to the phonological lexicon). This study thus provides new insights into the connectivity architecture of neural substrates involved in writing.

Handwriting difficulties in children with dyslexia: Poorer legibility in dictation and alphabet tasks, slowness in the alphabet task.

Several studies have shown that children with dyslexia (DYS), in addition to their reading and spelling deficits, encounter handwriting difficulties that are still poorly understood in terms of their nature and origin. The present study aimed to better understand the handwriting difficulties of children with DYS by comparing their handwriting quality and speed in two tasks, a dictation task and an alphabet task, which required fewer spelling skills than the dictation task. Twenty-nine French-speaking children (Mage = 9.5 years) participated in the study, including 18 children with DYS and nine typically developing (TD) children matched on chronological age. The children performed control tasks, a dictation task with words varying in graphic and orthographic complexity and an alphabet writing task. Accuracy, handwriting quality (legibility), and fluency (speed, writing and pause time) were carefully measured using a digital tablet. GLMM analysis and t tests showed that children with DYS made more aesthetic errors (handwriting quality) in both the dictation and alphabet task than TD children. They also wrote more slowly than TD children in the alphabet task (speed, pause time). These findings suggest that children with DYS present handwriting difficulties, even in a simple alphabet task. In dictation, they seem to favour speed at the expense of handwriting quality.

Signatures as an object of autoforgery (self-forgery). / Podpisy jako obiekt autofalszerstwa.

The study presents the results of research aimed at isolating the graphic features most frequently and least frequently modified by people committing autoforgery (self-forgery) of signatures in situations where the appearance of their natural signatures is not known to the recipient. The research covered a total of over 12,000 signatures from 200 individuals. The most successful attempts at autoforgery of legible and illegible signatures of each test subject were selected for the final evaluation. It was found that autoforgery changes are most often focused on the most striking features of the signatures, such as the structure of letters in the initial part of the signature, size, readability, impulse, and slope. Secondary features, more difficult to notice or those whose existence the writers are not aware of (such as the presence or absence of additions, the arrangement of letters in relation to each other, the shape and direction of signature lines, the format of legible signatures) are usually omitted in autoforgery activities. Detecting autoforgery can be a big challenge for experts, because in practice, any significant differences between the questioned signature and comparative signatures are often mistakenly considered to be the result of forgery. Therefore, in order to detect autoforgery, it is necessary to analyze the structure of easily noticeable features that most influence the so-called pictorial effect of the signature in combination with the unattractive features that remain unchanged in most cases of autoforgery. The more characteristic the latter are, the more their consistency in the questioned and comparative material proves self-forgery, regardless of the differences in the primary features. In the case of a forged signature, the opposite is true: the most easily noticeable features of the signature are imitated by the forger, and the differences occur mainly in secondary features.

Handwriting Movement Abnormalities in Older Adults with Silent Cerebral Small Vessel Disease-A Preliminary Study.

BACKGROUND: The features of cerebral small vessel disease (CSVD) range from occurrence of asymptomatic radiological markers to symptomatic characteristics that include cognitive deficits and gait decline. The aim of the present study was to examine whether handwriting movement is abnormal in older people with CSVD through handwriting and drawing tasks using digitized handwriting kinematic assessment technology. METHODS: Older subjects (n = 60) were grouped according to Fazekas score, with 16 in the Severe CSVD group, 12 in the Non-severe group and 32 in the Healthy group. Kinematic data were recorded and analyzed during handwriting and drawing tasks: signature; writing of Chinese characters ("" and ""); and Archimedes' spiral drawing. RESULTS: The Severe CSVD group showed lower velocity and higher tortuosity during signature writing, lower velocity of stroke #4 of "" and vertical size of "" than did the Non-severe and Healthy groups. Both Severe CSVD and Non-severe CSVD subjects displayed higher average normalized jerk than did the Healthy group. Partial correlation analysis adjusting for age, gender, education, and mini-mental state evaluation (MMSE) showed that CSVD burden was positively associated with tortuosity of signature and average normalized jerk of Archimedes' spiral, and was negatively associated with velocity of strokes #3 and #4 of "", as well as vertical size of "". CONCLUSIONS: Older adults with CSVD showed abnormal handwriting movement. And the handwriting abnormalities captured by digitized handwriting analysis were correlated with CSVD severity in users of simplified Chinese characters.

LSTM-CNN: An efficient diagnostic network for Parkinson's disease utilizing dynamic handwriting analysis.

BACKGROUND AND OBJECTIVES: Dynamic handwriting analysis, due to its noninvasive and readily accessible nature, has emerged as a vital adjunctive method for the early diagnosis of Parkinson's disease (PD). An essential step involves analysing subtle variations in signals to quantify PD dysgraphia. Although previous studies have explored extracting features from the overall signal, they may ignore the potential importance of local signal segments. In this study, we propose a lightweight network architecture to analyse dynamic handwriting signal segments of patients and present visual diagnostic results, providing an efficient diagnostic method. METHODS: To analyse subtle variations in handwriting, we investigate time-dependent patterns in local representation of handwriting signals. Specifically, we segment the handwriting signal into fixed-length sequential segments and design a compact one-dimensional (1D) hybrid network to extract discriminative temporal features for classifying each local segment. Finally, the category of the handwriting signal is fully diagnosed through a majority voting scheme. RESULTS: The proposed method achieves impressive diagnostic performance on the new DraWritePD dataset (with an accuracy of 96.2%, sensitivity of 94.5% and specificity of 97.3%) and the well-established PaHaW dataset (with an accuracy of 90.7%, sensitivity of 94.3% and specificity of 87.5%). Moreover, the network architecture stands out for its excellent lightweight design, occupying a mere 0.084M parameters, with only 0.59M floating-point operations. It also exhibits nearly real-time CPU inference performance, with the inference time for a single handwriting signal ranging from 0.106 to 0.220 s. CONCLUSIONS: We present a series of experiments with extensive analysis, which systematically demonstrate the effectiveness and efficiency of the proposed method in quantifying dysgraphia for a precise diagnosis of PD.

NeuroDiag: Software for Automated Diagnosis of Parkinson's Disease Using Handwriting.

OBJECTIVE: A change in handwriting is an early sign of Parkinson's disease (PD). However, significant inter-person differences in handwriting make it difficult to identify pathological handwriting, especially in the early stages. This paper reports the testing of NeuroDiag, a software-based medical device, for the automated detection of PD using handwriting patterns. NeuroDiag is designed to direct the user to perform six drawing and writing tasks, and the recordings are then uploaded onto a server for analysis. Kinematic information and pen pressure of handwriting are extracted and used as baseline parameters. NeuroDiag was trained based on 26 PD patients in the early stage of the disease and 26 matching controls. METHODS: Twenty-three people with PD (PPD) in their early stage of the disease, 25 age-matched healthy controls (AMC), and 7 young healthy controls were recruited for this study. Under the supervision of a consultant neurologist or their nurse, the participants used NeuroDiag. The reports were generated in real-time and tabulated by an independent observer. RESULTS: The participants were able to use NeuroDiag without assistance. The handwriting data was successfully uploaded to the server where the report was automatically generated in real-time. There were significant differences in the writing speed between PPD and AMC (P<0.001). NeuroDiag showed 86.96% sensitivity and 76.92% specificity in differentiating PPD from those without PD. CONCLUSION: In this work, we tested the reliability of NeuroDiag in differentiating between PPD and AMC for real-time applications. The results show that NeuroDiag has the potential to be used to assist neurologists and for telehealth applications. Clinical and Translational Impact Statement - This pre-clinical study shows the feasibility of developing a community-wide screening program for Parkinson's disease using automated handwriting analysis software, NeuroDiag.

Handwriting Markers for the Onset of Alzheimer's Disease.

INTRODUCTION: Alzheimer's disease has an impact on handwriting (AD). Numerous researchers reported that fact. Therefore, examining handwriting characteristics could be a useful way to screen for AD. The aim of the article is to present the reliability and effectiveness of the AD-HS tool. METHODS: Most of the existing studies examine either linguistic manifestations of writing or certain motor functions. However, handwriting is a complex of cognitive and motor activities. Since the influence of AD on handwriting is individual, it is important to analyze the complete set of handwriting features. The AD-HS instrument is based on this principle. Validation of the AD-HS instrument for revealing cognitive impairment in AD-diagnosed persons in comparison to the control group. The study is based on the evaluation of free handwritten texts. AD-HS includes 40 handwriting and 2 linguistic features of handwritten texts. It is based on the standard protocol for handwriting analysis. The cumulative evaluation of all features builds a quantitative AD-Indicator (ADI) as a marker of possible AD conditions. The analyzed experiment includes 53 AD-diagnosed persons and a control group of 192 handwriting specimens from the existing database. RESULTS: AD-HS shows a distinct difference in evaluated ADI for the participants (the mean value equals 0.49) and the control group (the mean value equals 0.28). CONCLUSION: The handwriting marker of AD could be an effective supplement instrument for earlier screening. It is also useful when traditional biomarkers and neurological tests could not be applied. AD-HS can accompany therapy as an indication of its effect on a person.

Kindergarten Visual-Perceptual and Motor Skills and Behavioral Traits Predict First-Grade Chinese Handwriting Legibility and Speed.

IMPORTANCE: Clarifying the relationship between kindergarteners' characteristics and their future handwriting performance is beneficial for the early detection of children at risk of handwriting difficulties. OBJECTIVE: To determine which visual-perceptual and motor skills and behavioral traits significantly predict kindergartners' Chinese handwriting legibility and speed in the first grade. DESIGN: One-year longitudinal, observational design. SETTING: Kindergarten and elementary schools. PARTICIPANTS: One hundred six kindergarten children (53 boys and 53 girls; ages 5 or 6 yr) were recruited. OUTCOMES AND MEASURES: The participants completed two subtests of the Bruininks-Oseretsky Test of Motor Proficiency-Second Edition, Test of Visual Perceptual Skills-Third Edition, Beery-Buktenica Developmental Test of Visual-Motor Integration (Beery™ VMI), and the Attention-Deficit/Hyperactivity Disorder Test-Chinese Version in kindergarten. Their handwriting legibility (character accuracy and construction) and speed were assessed by investigator-developed Chinese handwriting tests in the first grade. RESULTS: Multivariate regression analyses indicated the independent predictive power of spatial relationships (p = .042) and inattention (p = .004) for character accuracy. Visual-motor integration (VMI; p = .008) and inattention (p = .002) were the key predictors of character construction. Manual dexterity (p = .001) was the only significant predictor of writing speed. CONCLUSIONS AND RELEVANCE: Kindergarteners who perform poorly in spatial relationships, VMI, manual dexterity, and attention are likely to have less legible Chinese handwriting and slow writing speed in first grade. Plain-Language Summary: Children's visual-perceptual and motor skills and behavioral traits in kindergarten can predict their Chinese handwriting legibility and speed in first grade. This study found that kindergarteners who performed poorly in spatial relationships, VMI, manual dexterity, and attention were likely to have less legible Chinese handwriting and slow writing speed in the first grade.

The internal structure of handwriting proficiency in beginning writers.

Fluent and automatized handwriting frees cognitive resources for more complex elements of writing (i.e., spelling or text generation) or even math tasks (i.e., operating) and is therefore a central objective in primary school years. Most previous research has focused on the development of handwriting automaticity across the school years and characteristics of handwriting difficulties in advanced writers. However, the relative and absolute predictive power of the different kinematic aspects for typically developing beginning handwriting remains unclear. The purpose of the present study was to investigate whether and to what extent different kinematic aspects contribute to handwriting proficiency in typically developing beginning handwriters. Further, we investigated whether gender, socioeconomic background, or interindividual differences in executive functions and visuomotor integration contribute to children's acquisition of handwriting. Therefore, 853 first-grade children aged seven copied words on a digitized tablet and completed cognitive performance tasks. We used a confirmatory factor analysis to investigate how predefined kinematic aspects of handwriting, specifically the number of inversions in velocity (NIV), pen stops, pen lifts, and pressure on the paper, are linked to an underlying handwriting factor. NIV, pen stops, and pen lifts showed the highest factor loadings and therefore appear to best explain handwriting proficiency in beginning writers. Handwriting proficiency was superior in girls than boys but, surprisingly, did not differ between children from low versus high socioeconomic backgrounds. Handwriting proficiency was related to working memory but unrelated to inhibition, shifting, and visuomotor integration. Overall, these findings highlight the importance of considering different kinematic aspects in children who have not yet automatized pen movements. Results are also important from an applied perspective, as the early detection of handwriting difficulties has not yet received much research attention, although it is the base for tailoring early interventions for children at risk for handwriting difficulties.

How word semantics and phonology affect handwriting of Alzheimer's patients: A machine learning based analysis.

Using kinematic properties of handwriting to support the diagnosis of neurodegenerative disease is a real challenge: non-invasive detection techniques combined with machine learning approaches promise big steps forward in this research field. In literature, the tasks proposed focused on different cognitive skills to elicitate handwriting movements. In particular, the meaning and phonology of words to copy can compromise writing fluency. In this paper, we investigated how word semantics and phonology affect the handwriting of people affected by Alzheimer's disease. To this aim, we used the data from six handwriting tasks, each requiring copying a word belonging to one of the following categories: regular (have a predictable phoneme-grapheme correspondence, e.g., cat), non-regular (have atypical phoneme-grapheme correspondence, e.g., laugh), and non-word (non-meaningful pronounceable letter strings that conform to phoneme-grapheme conversion rules). We analyzed the data using a machine learning approach by implementing four well-known and widely-used classifiers and feature selection. The experimental results showed that the feature selection allowed us to derive a different set of highly distinctive features for each word type. Furthermore, non-regular words needed, on average, more features but achieved excellent classification performance: the best result was obtained on a non-regular, reaching an accuracy close to 90%.