The assessment of handwriting is fundamental for identifying difficulties, which may have long-term negative consequences. However, standard evaluation typically focuses only on the final handwritten product. For this reason, Italian guidelines recommended supporting traditional evaluation with digital tools to also analyze the handwriting process. A sensorized ink pen used on paper was employed by over 700 students, ranging from first grade in Italian primary school to third grade in lower secondary school, to execute two tasks of the BVSCO-3, the gold standard for handwriting assessment. From sensorized ink pen data, handwriting indicators in the domains of Time, Force, Smoothness, Tilt, and Frequency were extracted. These indicators were then analyzed to examine their correlation with clinical scores, to model cross-sectional trends across grades, and to identify handwriting difficulties. The correlation analysis revealed significant relationships between the indicators and the clinical score, particularly for the Time domain. A cross-sectional statistical analysis showed that the indicators follow developmental trends compatible with handwriting learning curves reported in the literature: for many indicators, a performance plateau was reached in grade 3, from both motor and processing perspectives. Lastly, binary classification models successfully distinguished subjects with handwriting difficulties (based on BVSCO-3 results) from proficient writers. The sensorized ink pen allowed uncovering relevant characteristics of children's handwriting process, while guaranteeing ecological data acquisition conditions. Its use could pave the way for a prompt identification of handwriting difficulties in school settings, thus facilitating an efficient referral to clinical services.

IntroductionChronic stroke gait disorders involve impaired motor coordination. While high-intensity gait training (HIGT) is supported by current clinical practice guidelines, and Functional Electrical Stimulation (FES) to tibialis anterior addresses foot drop, extending FES to multiple muscles may improve functional outcomes.MethodsUsing a FES neural sleeve capable of recording muscle activity and joint angles, we tested preliminary efficacy and feasibility of a personalized multichannel FES (MFES) intervention based on the individual’s motor coordination impairment paired with HIGT. Fourteen individuals with chronic stroke were randomly assigned to either HIGT or MFES + HIGT for six weeks. Gait speed, endurance, gait biomechanics, and muscle synergies were assessed at baseline, midpoint, post-training, and one-month follow-up.ResultsDespite the small sample, only the MFES + HIGT group demonstrated significant endurance gains from baseline to post-training and follow-up, while both groups improved walking speed, impaired limb step length, and muscle synergy similarity to normative data. Feasibility was evaluated by measuring setup time (therapist putting device on participant and setting stimulation parameters) and collecting feedback from participants and four therapists. System setup time plateaued at 4.53 min by the ninth session. Both participants and therapists rated the intervention highly feasible, acceptable, and usable. Adherence was high in both groups, with only one dropout in the HIGT group due to preexisting medical conditions.DiscussionThis pilot study demonstrates the preliminary effectiveness of synergy-based MFES in improving walking endurance and confirms its feasibility for integration into chronic stroke gait rehabilitation, supporting the need for larger-scale trials to validate clinical efficacy and identify responders.Clinical Trial Registrationhttps://clinicaltrials.gov/study/NCT06099444, identifier NCT0609944.

Background People with intellectual and developmental disabilities (IDDs) face difficulties in being included in activities with their peers due to differences in cognitive abilities and social skills. Video games offer a promising medium to support inclusion, physical activity, and social engagement, but current solutions struggle to provide equitable experiences to heterogeneous groups of users, especially in multiplayer real-time contexts. Objective This study aims to co-design and develop an inclusive collaborative real-time multiplayer exergame, assessing its usability, the impact of accessibility features, and players’ satisfaction and enjoyment. Methods The exergame Elemental was co-designed following the CeHRes (Centre for eHealth and Wellbeing Research) Roadmap, involving clinicians, educators, engineers, and individuals with IDDs. A total of 2 cooperative minigames were developed: Igloo (focused on stimulus collection) and Volcano (focused on enhancing collaboration), playable with 4 different input devices (buttons, tablet, hand-tracking, and full-body tracking). Customizable facilitation options were implemented to adapt gameplay to sensory, cognitive, and motor needs. Young adults with IDDs participated in a 2-phase study testing whether personalized accommodations could eliminate performance disparities: (1) Igloo in homogeneous groups, based on functioning and expected behavior and interaction with stimuli, without facilitations, using all devices to identify optimal input methods, and (2) Volcano in heterogeneous groups using their best-performing devices with individualized facilitations tailored by educators. Data collected included in-game performance (accuracy, reaction time, and collaboration contributions), behavioral observations, and questionnaires on satisfaction and usability from players. Nonparametric analyses were used to assess relationships between disability severity, performance, and the impact of facilitations. Results A total of 11 individuals (2 male and 9 female; mean age 25.1, SD 4.4 years) with different IDD diagnoses were recruited from an association supporting individuals with cognitive impairments. In the Igloo sessions, performance was negatively correlated with intellectual disability severity (ρ=–0.87, 95% CI –1.00 to –0.56; P<.001) and reaction time was positively correlated (ρ=0.69, 95% CI 0.08-0.94; P=.02). Instead, no significant correlation between performance and intellectual disability severity was observed in the Volcano sessions (ρ=0.24, 95% CI –0.48 to 0.79; P=.48). These results highlight that tailored support (personalized facilitations and best-suited devices) can foster equitable participation even in heterogeneous groups. Behavioral analysis revealed frequent peer collaboration. Participants reported high usability and satisfaction (median 4/5, IQR 0.5). Conclusions This study introduces an inherently accessible, co-designed multiplayer exergame. Unlike approaches that adapt games or create separate disability-specific solutions, Elemental was conceived as inclusive from the outset. By demonstrating that personalized features can eliminate performance disparities, this work highlights how inclusive co-design can transform an activity into an inclusive, collaborative, and enjoyable experience for individuals with different abilities and intellectual impairments, supporting the shift from fitting individuals into existing digital spaces to designing environments able to embrace diversity.

Handwriting difficulties affect a significant proportion of primary school children and, when persistent, may indicate dysgraphia. Early, structured intervention is essential, yet individualized training remains challenging to implement at scale in classroom settings. This paper presents the co-design and field testing of a serious game platform for handwriting training in first-grade children. Following a simplified CeHRes Roadmap, a multidisciplinary team of engineers, clinicians, and educators co-designed five games targeting distinct handwriting prerequisites: visuomotor integration, writing fluency, letter and number formation, and writing speed. The platform was deployed in authentic classroom settings across two primary schools, involving 67 first-grade children over a 78-day period. Results demonstrated high compliance (87.7

Physical activity is essential for children’s development, yet those with disabilities often face barriers that limit their participation in school-based motor activities. The ActivE3 project aimed to promote accessibility and inclusion in primary school physical education using technology. A multidisciplinary approach involving researchers, clinicians, and teachers was adopted to identify needs and design suitable solutions. Technological systems were implemented and tested in both controlled and real-world school settings. This paper focuses on the results obtained from the Nirvana interactive environment and collaborative exergames. The project involved approximately 760 children. Results showed high levels of engagement and positive feedback across all groups. No significant differences emerged be-tween typically developing children and those with cognitive or motor difficulties, suggesting that the proposed technologies can support inclusive participation. Although some limitations remain, including the small number of participants with motor disabilities and the use of a non-validated questionnaire, the findings highlight the potential of technology to encourage inclusive and engaging physical activity in primary schools.

BackgroundTechnology use is increasingly integrated into daily life, including among older adults, whose adoption and engagement with technology warrant closer examination. According to the matching person and technology model, technology adoption is more likely when a person’s preferences and needs align with a device’s functions and features, as well as the environment in which it is used. However, factors such as age-related changes, evolving preferences, and the rapid pace of digital transformation complicate this process. Additionally, older adults often rely on support from family members and health professionals, yet their perspectives remain largely unexplored. ObjectiveThis study aimed to examine the daily technology use of older adults in Israel from a triangle perspective, incorporating the views of older adults, family members, and health professionals. It explored preferred technology-based activities, device features, the shift from in-person to technology-based interactions, and responses to mismatches between preferences, device characteristics, and social support. MethodsNine web-based focus groups, each with 6 to 7 participants, were conducted during the COVID-19 pandemic (February 2021 to July 2022). Participants included 20 healthy, independent older adults (10 women, aged 66-80 years), 19 family members (children and grandchildren, aged 21-55 years), and 20 health professionals with at least 5 years of experience working with older adults. ResultsOlder adults demonstrated diverse preferences for technology use in daily activities, shaped by urgency, significance, and device characteristics. This perspective was reinforced by family members and health professionals, who highlighted the importance of distinguishing between technology types based on their users and features. Additionally, older adults expressed mixed views on shifting from in-person interactions to digital alternatives, while family members and health professionals emphasized the importance of social interaction for well-being. Finally, older adults described significant emotional challenges when navigating technology. Family members and health professionals identified key contributors, including the gap between perceived and actual technological abilities, generational differences in digital exposure, and cognitive demands associated with technology use. ConclusionsThis study highlights the significant variability in older adults’ daily activity preferences, which strongly influences their technology use. It suggests shifting the focus from technology to its practical application in meeting individual needs. In this context, it is important to consider the need for social interactions. Addressing social interaction needs and emotional challenges is crucial, as unmet technological needs can lead to frustration and disengagement. These insights can inform strategies to enhance technology use among older adults by aligning technology design and support systems with their preferences and needs.

BACKGROUND:Functional Electrical Stimulation Assisted Cycling (FES-cycling) is a rehabilitation intervention for individuals with Spinal Cord Injury (SCI), offering benefits like increased muscle trophism, improved cardiopulmonary function, and reduced bone demineralization. Despite numerous studies on its physical advantages, few have focused on user experience. This study evaluates the user experience, usability, acceptability, and human-device interaction of two FES-cycling systems: a recumbent FES-bike prototype from Politecnico di Milano and the commercial BerkelBike Pro. METHODS:We recruited 15 participants with SCI, aged 18-65, with varying injury levels. The user experience (primary outcome), acceptability, usability, human-device interaction, and ergonomics of both systems were investigated by means of 4 questionnaires: the User Experience Questionnaire (UEQ), the Technological Acceptance Measure 3 (TAM-3), the System Usability Scale (SUS), and a customized questionnaire to evaluate human-device interaction both in terms of ergonomic aspects and psychological factors. RESULTS:The user experience received positive evaluations across all dimensions (scores ≥ 1.5 on a scale from -3 to 3), with slightly higher, though not statistically significant, scores for the FB. Secondary outcomes indicated strong acceptability (global TAM-3 scores > 5.5/7 for both devices), high usability ratings (SUS scores ≥ 75/100 for both devices), and favorable interaction and ergonomics, emphasizing ease of use, comfort, and alignment with user expectations. CONCLUSIONS:The study underscores the positive user experience as the primary outcome, along with strong acceptance and usability of both devices, emphasizing their potential to enhance Sport-Therapy and the value of integrating user perspectives in future development.

The growing global elderly population is expected to increase the prevalence of frailty, posing significant challenges to healthcare systems. Frailty, a syndrome associated with ageing, is characterised by progressive health decline, increased vulnerability to stressors and increased risk of mortality. It represents a significant burden on public health and reduces the quality of life of those affected. The lack of a universally accepted method to assess frailty and a standardised definition highlights a critical research gap. Given this lack and the importance of early prevention, this study presents an innovative approach using an instrumented ink pen to ecologically assess handwriting for age group classification. Content-free handwriting data from 80 healthy participants in different age groups (20-40, 41-60, 61-70 and 70+) were analysed. Fourteen gesture- and tremor-related indicators were computed from the raw data and used in five classification tasks. These tasks included discriminating between adjacent and non-adjacent age groups using Catboost and Logistic Regression classifiers. Results indicate exceptional classifier performance, with accuracy ranging from 82.5% to 97.5%, precision from 81.8% to 100%, recall from 75% to 100% and ROC-AUC from 92.2% to 100%. Model interpretability, facilitated by SHAP analysis, revealed age-dependent sensitivity of temporal and tremor-related handwriting features. Importantly, this classification method offers potential for early detection of abnormal signs of ageing in uncontrolled settings such as remote home monitoring, thereby addressing the critical issue of frailty detection and contributing to improved care for older adults.

BackgroundMild cognitive impairment (MCI) is a precursor of dementia. Therefore, MCI identification and monitoring are crucial to delaying dementia onset. Given the limits of existing clinical tests, objective support tools are needed. ObjectiveThis work investigates quantitative handwriting analysis, tailored to enable domestic monitoring, as a noninvasive approach for MCI screening and assessment. MethodsA sensorized ink pen, used on paper and equipped with sensors, memory, and a communication unit, was used for data acquisition. The tasks included writing a grocery list and free text to mimic daily life handwriting, and a clinical dictation test (parole-non-parole [PnP] test), featuring regular, irregular, and made-up words, aimed at assessing MCI dysgraphia. From the recorded data, 106 indicators describing the performance in terms of time, fluency, exerted force, and pen inclination were computed. A total of 57 patients with MCI were recruited, of whom 45 performed a test-retest protocol. The indicators were examined to assess their test-retest reliability. The indicators from the test repetition were used to assess their relationship with the scores of clinical tests via correlation analysis. For the PnP test, differences in the indicators among the 3 types of words were statistically investigated. These analyses were conducted separately for the cursive (2/3 of the sample) and block letters (1/3 of the sample) allographs, with the level of significance set at 5%. Data from healthy older adults were available for the grocery list (34 participants) and free text (45 participants) tasks. These were exploited to build machine learning classification models for the distinction between patients with MCI and healthy controls. ResultsWhen dealing with reliability, 93% and 44% of the indicators were characterized by a significant reliability of at least moderate intensity for cursive and block letters respectively. As for the correlation analysis, patients with preserved cognitive status and daily life functionality were associated with significantly better temporal performances, both in free writing and PnP. The analysis of PnP highlighted the presence of surface dysgraphia in the recruited sample, as irregular words showed significantly worse temporal indicators with respect to regular and made-up ones. The classification models’ built-in free writing data achieved accuracies ranging from 0.80 to 0.93 and F1-scores from 0.81 to 0.92 according to the input dataset. ConclusionsThe presented results suggest the suitability of ecological handwriting analysis for the all-around monitoring of MCI, from early screening to disease progression evaluation.

Extrauterine growth restriction (EUGR) affects 30–97% of preterm infants and is associated with poor outcomes. We used machine learning (ML) to assess how clinical and nutritional factors, particularly during the transition from parenteral to enteral nutrition, influence EUGR. This retrospective observational study included 1165 patients (46% with EUGR) born below 33 weeks’ gestation or 1500 g. We developed 10 models to predict EUGR combining two sets of features (all and nutritional features only) across five subgroups of patients (all, extremely preterm, very preterm, moderately preterm, small for gestational age). Model accuracy was 0.71 (F1-score = Recall = AUROC = 0.71, Precision = 0.72) with nutritional features and 0.79 (F1-score = AUROC = 0.79, Precision = 0.80, Recall = 0.79) with all features. Lower EUGR risk was linked to female sex, higher growth velocity, and lipid intake in week one. Influential factors differed by subgroup. ML models accurately predicted EUGR across preterm subgroups, highlighting the role of early nutritional and clinical variables.

Technology use is increasingly integrated into daily life, including among older adults, whose adoption and engagement with technology warrant closer examination. According to the matching person and technology model, technology adoption is more likely when a person’s preferences and needs align with a device’s functions and features and the environment in which it is used. However, factors such as age-related changes, evolving preferences, and the rapid pace of digital transformation complicate this process. Additionally, older adults often rely on support from family members and health professionals, yet their perspectives remain largely unexplored. : This study examined older adults’ daily technology use from a triangle perspective, incorporating the views of older adults, family members, and health professionals. It explored preferred technology-based activities, device features, the shift from in-person to technology-based interactions, and responses to mismatches between preferences, device characteristics, and social support. Nine online focus groups, each with six to seven participants, were conducted during COVID-19 (02/2021–07/2022). Participants included 20 healthy, independent older adults (10 women, aged 66–80 years), 19 family members (children and grandchildren, aged 21–55 years), and 20 health professionals with at least five years of experience working with older adults. Older adults demonstrated diverse preferences for technology use in daily activities, shaped by urgency, significance, and device characteristics. This perspective was reinforced by family members and health professionals, who highlighted the importance of distinguishing between technology types based on their functions and features. Additionally, older adults expressed mixed views on shifting from in-person interactions to digital alternatives, while family members and health professionals emphasized the importance of social interaction for well-being. Finally, older adults described significant emotional challenges when navigating technology. Family members and health professionals identified key contributors, including the gap between perceived and actual technological abilities, generational differences in digital exposure, and cognitive demands associated with technology use. This study highlights the significant variability in older adults’ daily activity preferences, which strongly influences their technology use. It suggests shifting the focus from technology to its practical application in meeting individual needs. In this context, it is important to consider the need for social interactions. Addressing social interaction needs and emotional challenges is crucial, as unmet technological needs can lead to frustration and disengagement. These insights can inform strategies to enhance technology use among older adults by aligning technology design and support systems with their preferences and needs.

Age-related physiological and cognitive changes significantly affect older adults' participation in day-to-day functioning. This interview study aimed to uncover and illuminate the intricate dynamics between individuals' responses to aging restrictions and day-to-day functioning, and how they relate to successful aging. We used a qualitative research design to explore the various responses to aging decline and their implications for daily functioning among older adults. Eighteen in-depth interviews were conducted with older adults, focusing on their occupational characteristics, needs, and responses to aging constraints. The transcripts were analyzed using principles of constructivist grounded theory. Three main categories were identified regarding older adults' responses to the decline in abilities that come with age: (a) acceptance, reflecting the individual's ability to adapt to the age-related changes and constraints; (b) personal resources, including a positive mindset and self-efficacy; and (c) coping strategies, including meaningful roles and occupational adaptation. This study's findings indicate three types of responses to aging restrictions that may contribute to greater engagement in daily life and, consequently, be a key to successful aging. Developing individually tailored interventions that focus on occupational adaptations according to individual needs and preferences is vital in helping older adults maintain their daily functioning and quality of life.

BACKGROUND:Spinal cord injury (SCI) severely affects physical function, leading to muscle atrophy and reduced bone density. Sport-therapy, incorporating recreational and competitive activities, has shown promise in enhancing recovery for individuals with SCI. Functional Electrical Stimulation (FES)-cycling combines exercise benefits with stimulation advantages, and recent integration with mobile recumbent trikes adds further potential. This study aimed to evaluate the effects of a 6-month FES-cycling sport therapy using a recumbent trike on individuals with motor complete SCI. METHODS:Five participants engaged in bi-weekly FES-cycling sessions using an instrumented recumbent trike. A comprehensive assessment was conducted before training, at 3 and 6 months of training, and at 1-month follow-up. Outcome measures included maximal muscle Cross-Sectional Area (maxCSA) from Magnetic Resonance Images, bone mineral density, clinical scales, and questionnaires on spasticity, pain, bowel dysfunction, psychological well-being, and sport motivation. Additionally, maximal power output and cycling endurance were assessed. RESULTS:The FES-cycling program led to a significant increase in muscle mass of 34% after 6 months of training, correlated to an improved cycling performance (maxCSA versus peak power). A slight decrease of muscle mass was observed as expected at follow-up. Participants reported high well-being and strong motivation throughout the training program. Bone health, spasticity, bowel dysfunction, and pain levels did not significantly change overall. CONCLUSIONS:FES-cycling on a recumbent trike shows potential as a therapeutic and recreational activity for individuals with SCI. It significantly improved muscle mass and physical performance while positively impacting psychological well-being and motivation. Further research with larger cohorts is necessary to confirm these benefits and optimize protocols, establishing FES-cycling as a valuable sport-therapy model for SCI. TRIAL REGISTRATION:The study protocol was retrospectively registered on clinicaltrials.gov (NCT06321172).

BackgroundEarly administration of reading, writing and math standardised tests allows us to assess the risk of developing a learning disorder and to plan a specific intervention. The ease of access to technological tools and past pandemic restrictions have led to the abandonment of face-to-face assessment in favour of teleassessment methods. Although these kinds of assessments sometimes seem comparable in the literature, their equivalence is not clearly defined. The first aim of our research was to test the comparability of the two modalities using a complete battery of neuropsychological tests. Second, we addressed whether the administration order could influence performance.MethodsUsing a within-subject sample design, we compared face-to-face and teleassessment performance in reading, writing and math tasks in 64 children attending first and second year of primary school.ResultsTeleassessment scores were lower than face-to-face; math tests weighted on difference. Differences were mitigated by previous experience with face-to-face modality.ConclusionsAlthough there was considerable overlap between the two administration methods, teleassessment could lead to overestimation of the risk for learning disorders.

1568 Background: Implementing a mass screening program for lung cancer using low-dose chest CT presents significant challenges, including financial constraints and concerns about radiation exposure. Nonetheless, recent evidence reveals that lung cancer is not limited to smokers, as it also affects non-smoker populations who are currently excluded from existing screening programs. As part of the I3LUNG study (NCT05537922), we investigated the use of AI-based forced cough analysis as a non-invasive approach to distinguish NSCLC patients undergoing immunotherapy (IO) from healthy individuals. Additionally, we examined whether cough features could differentiate patients based on their baseline clinical features. Methods: Machine Learning-based preprocessing isolated meaningful cough events and extracted 39 acoustic features from the time and frequency domains. To reduce redundancy and improve model performance, highly correlated features ( > 85%) were eliminated. Support Vector Machines (SVM) and Deep Learning (DL) models were then employed to distinguish NSCLC patients from healthy controls. Additional statistical analyses of acoustic features were conducted on cough recordings from patients to evaluate differences based on smoking status (current, former, or never smokers) using the Kruskal-Wallis test with Benjamini-Hochberg post-hoc correction. Similarly, differences based on the presence or absence of lung metastases were assessed using the Mann-Whitney test. Results: A total of 200 individuals were enrolled in the study, including 91 stage IIIB-IV NSCLC patients undergoing IO and 109 healthy controls. Cough recordings were analyzed, with the SVM model achieving an accuracy of 82% and a specificity of 92% on the test set. The DL model demonstrated superior performance, with an accuracy of 95% and a specificity of 100%. Significant differences were observed in the peak-to-root-mean-square value ratio and cough duration among smokers (current, former, or never), with P-values of 0.026 and 0.042, respectively. Furthermore, spectral features - including centroid, rolloff, spread, kurtosis, bandwidth, and flatness - differed significantly between patients with and without lung metastases (P < 0.01). Conclusions: These findings highlight the potential of cough as a valuable digital biomarker for NSCLC diagnosis. The tool's high sensitivity facilitates the effective identification of individuals at risk for lung cancer, while its exceptional specificity makes it a promising initial screening method, efficiently triaging positive cases for follow-up chest CT scans. Future studies should validate these results on larger cohorts. Moreover, the correlation of specific cough features with smoking status and the presence of lung metastases suggests that this tool could extend beyond screening to monitoring disease progression over time.

The screening of specific learning disabilities faces many challenges, such as: 1) the lack of an educational alliance between schools, families, and clinicians; 2) the lack of quantitative data about children's difficulties and their progression over time; or 3) the inefficiency of access to care when it is truly needed. To address these issues, this work presents ESSENCE, a platform aimed at supporting schools throughout the entire process, from identifying children with difficulties to reporting cases to child neuropsychiatrists. Following an iterative co-design process with all relevant stakeholders, several system components were defined, developed, and refined with users' feedback. The final prototype was field-tested over one year by approximately 70 children, their teachers, and some clinicians. Compliance, the System Usability Scale, and custom satisfaction questionnaires were used to evaluate the system. Compliance was high, with at least five sessions conducted in 80% of the weeks. 82% of children reported good usability, and 92% were satisfied with the experience. The quantitative data collected through ESSENCE enhance the process of identifying specific learning disabilities, making it more targeted and beneficial for both children in need and the health-care system.

A prompt diagnosis of specific learning disabilities (SLDs) is prevented by an overwhelmed healthcare system. As teachers lack clinical preparation, school-based screening needs to be improved. This work proposes methods to (1) identify children’s profiles, (2) select children who need a visit, and (3) provide a better understanding of the characteristics connected with the start of the clinical pathway. We analyzed data from 364 children referred to clinical consultation. Starting from a 96-item screening questionnaire filled in by teachers at school, we computed a severity score for 19 different sub-domains of learning leveraging item response theory. Then, we performed cluster analysis with K-means to segment the population according to children’s capabilities. For each cluster, we leveraged leave-one-out on balanced outcomes (clinical pathway VS school training) with different machine learning models, and we leveraged Shapley values to explain the results. Cluster analysis revealed two children’s profiles, grouped by severity. Though, the proportion of children who started the clinical pathway was not statistically different. Indeed, also children with less difficulties should be taken into consideration, as they may suffer from SLDs without comorbidities. As for the classification, median area under the precision-recall curve was 0.96 for one cluster with a Support Vector Classifier (SVC), and 0.69 for the other cluster with Naive Bayes (NB). Between-cluster differences in performance suggest different degrees of complexity in children’s profiles. Yet, also the latter can be considered a good results, considering the heterogeneity of data creators. Shapley values revealed that the SVC on the first cluster tended to rank children by severity, whilst NB on the second cluster shows that the difficulties can interact in a more complex way. This work represents a step forward in the management of SLDs, from an early and preclinical setting.Clinical relevanceThis work provides methods to get insights on the reasons for referring children with specific learning disabilities to the clinic.