Investigating Visual Perception Impairments through Serious Games and Eye Tracking to Anticipate Handwriting Difficulties.

Dysgraphia is a learning disability that causes handwritten production below expectations. Its diagnosis is delayed until the completion of handwriting development. To allow a preventive training program, abilities not directly related to handwriting should be evaluated, and one of them is visual perception. To investigate the role of visual perception in handwriting skills, we gamified standard clinical visual perception tests to be played while wearing an eye tracker at three difficulty levels. Then, we identified children at risk of dysgraphia through the means of a handwriting speed test. Five machine learning models were constructed to predict if the child was at risk, using the CatBoost algorithm with Nested Cross-Validation, with combinations of game performance, eye-tracking, and drawing data as predictors. A total of 53 children participated in the study. The machine learning models obtained good results, particularly with game performances as predictors (F1 score: 0.77 train, 0.71 test). SHAP explainer was used to identify the most impactful features. The game reached an excellent usability score (89.4 ± 9.6). These results are promising to suggest a new tool for dysgraphia early screening based on visual perception skills.

Investigating the effects of COVID-19 lockdown on Italian children and adolescents with and without neurodevelopmental disorders: a cross-sectional study.

We conducted a cross-sectional study to compare the impact of social distancing and lifestyle changes that occurred during Corona Virus Disease 2019 (COVID-19) lockdown on children and adolescents with and without Neurodevelopmental Disorders (NDDs). An online questionnaire was administered in order to investigate the effects of NDD condition, socio-demographic status, familiar/home environment and COVID-19 exposure on their lives during a two months period of social isolation. We used logistic regression, focusing on five endpoints (remote learning, lifestyle, stress/anxiety, sociality, scolding) to define the extent of these effects. Most questions were paired up to parents and children, to verify the occurrence of agreement. 8305 questionnaires were analyzed, 1362 of which completed by NDDs and 6943 by controls. Results showed that the presence of a NDD, compared to controls, had a significant impact on: Remote Learning (i.e. subjects with NDDs experienced more difficulties in attending online classes and studying), Sociality (i.e. subjects with NDDs missed their schoolmates less), Scolding (i.e. subjects with NDDs were scolded more often) and Anxiety (i.e. subjects with NDDs were perceived by their parents as more anxious). Substantial agreement between parents and children arose from questions concerning Remote learning, Lifestyle and Scolding. The current study actually points out that having a NDD gives account for a stronger influence on school performance and on behavioral and psychological aspects, during a two months lockdown. Such results may provide useful information to governments and school authorities on how carrying through supportive strategies for youth affected by NDDs. Supplementary Information: The online version contains supplementary material available at 10.1007/s12144-021-02321-2.

Self-reported impact of the COVID-19 pandemic and lockdown on young patients with tic disorders: findings from a case-control study.

BACKGROUND: Little is known about the perceived impact of the COVID-19 pandemic and subsequent lockdown measures on young patients with tic disorders. Previous studies focused on clinician and parent ratings of tic severity, whereas the only international self-report data are available for adult populations. We present the first findings from a case-control study on children and adolescents with tics during lockdown in Italy. METHODS: We surveyed 49 patients aged 6-18 years and 245 matched controls with a newly developed questionnaire covering socio-demographic and clinical data, as well as lockdown-related changes to daily life activities. RESULTS: About half (53.2%) of the Italian school-age patients who took part in our survey experienced changes in tic severity during lockdown. Perceived increases in tic severity (29.8%) were reported more often than decreases (23.4%). Analogous trends were reported for perceived restlessness and, more significantly, irritability, whereas changes in pain symptoms were less common and were similar in both directions. The presence of tics was associated with increased difficulties with remote learning (p = 0.01), but decreased feelings of missing out on social interactions with schoolmates (p = 0.03). CONCLUSIONS: Self-reported data on the impact of COVID-19 lockdown in school-age patients with tic disorders indicate perceived changes in tic severity, as well as restlessness and irritability, in about half of the cases. These findings could guide both clinicians and teachers in the implementation of targeted adjustments in the delivery of care and educational strategies, respectively.

Medium-term patient's satisfaction after primary total knee arthroplasty: enhancing prediction for improved care.

BACKGROUND: Patient-reported satisfaction after total knee arthroplasty (TKA) is low compared to other orthopedic procedures. Although several factors have been reported to influence TKA outcomes, it is still challenging to identify patients who will experience dissatisfaction five years after surgery, thereby improving their management. Indeed, both perioperative information and follow-up questionnaires seem to lack statistical predictive power. HYPOTHESIS: This study aims to demonstrate that machine learning can improve the prediction of patient satisfaction, especially when classical statistics fail to identify complex patterns that lead to dissatisfaction. PATIENTS AND METHODS: Patients who underwent primary TKA were included in a Registry that collected baseline data and clinical outcomes at different follow-ups. The patients were divided into satisfied and dissatisfied groups based on a satisfaction questionnaire administered five years after surgery. Satisfaction was predicted using linear statistical models compared to machine learning algorithms. RESULTS: A total of 147 subjects were analyzed. Regarding statistics, significant differences between satisfaction levels started emerging only six months after the intervention, and the classification was close to random guessing. However, machine learning algorithms could improve the prediction by 72% soon after the intervention, and an improvement of 178% was possible when including follow-ups up to one year. DISCUSSION: This study demonstrates the feasibility of a registry-based approach for monitoring and predicting satisfaction using ML algorithms. LEVEL OF EVIDENCE: III.

Autism in Preschool-Aged Children: The Effects of COVID-19 Lockdown.

The COVID-19 lockdown affected children, especially those with autism spectrum disorder, due to the disruption in rehabilitation and educational activities. We conducted a cross-sectional study of 315 preschool-aged children, 35 of which had autism, to investigate this impact. A questionnaire was administered to explore socio-demographic status, familiar/home environment, and COVID-19 exposure. The clinical features of autistic subjects were also examined. Seven variables were considered to describe the effect of pandemic: Remote learning, Behavior changes, Home activities, Sleep habits, Night awakenings, Physical activity, Information about the virus. The lockdown had a significant impact on Remote learning, Behavior changes, and Information about the virus in participants with autism. Moreover, we found a worsening in repetitive movements, echolalia, restricted interests, and aggressive behaviors.

Deep Learning and Procrustes Analysis for Early Dysgraphia Risk Detection with a Tablet Application.

Dysgraphia is a neurodevelopmental disorder specific to handwriting. Classical diagnosis is based on the evaluation of speed and quality of the final handwritten text: it is therefore delayed as it is conducted only when handwriting is mastered, in addition to being highly language-dependent and not always easily accessible. This work presents a solution able to anticipate dysgraphia screening when handwriting has not been learned yet, in order to prevent negative consequences on the individuals' academic and daily life. To quantitatively measure handwriting-related characteristics and monitor their evolution over time, we leveraged the Play-Draw-Write iPad application to collect data produced by children from the last year of kindergarten through the second year of elementary school. We developed a meta-model based on deep learning techniques (ensemble techniques and Quasi-SVM) which receives as input raw signals collected after a processing phase based on dimensionality reduction techniques (autoencoder and Time2Vec) and mathematical tools for high-level feature extraction (Procrustes Analysis). The final dysgraphia classifier can identify "at-risk" children with 84.62% Accuracy and 100% Precision more than two years earlier than current diagnostic techniques.

Leveraging Deep Learning Techniques to Improve P300-Based Brain Computer Interfaces.

Brain-Computer Interface (BCI) has become an established technology to interconnect a human brain and an external device. One of the most popular protocols for BCI is based on the extraction of the so-called P300 wave from electroencephalography (EEG) recordings. P300 wave is an event-related potential with a latency of 300 ms after the onset of a rare stimulus. In this paper, we used deep learning architectures, namely convolutional neural networks (CNNs), to improve P300-based BCIs. We propose a novel BCI classifier, called P3CNET, that improved P300 classification accuracy performances of the best state-of-the-art classifier. In addition, we explored pre-processing and training choices that improved the usability of BCI systems. For the pre-processing of EEG data, we explored the optimal signal interval that would improve classification accuracies. Then, we explored the minimum number of calibration sessions to balance higher accuracy and shorter calibration time. To improve the explainability of deep learning architectures, we analyzed the saliency maps of the input EEG signal leading to a correct P300 classification, and we observed that the elimination of less informative electrode channels from the data did not result in better accuracy. All the methodologies and explorations were performed and validated on two different CNN classifiers, demonstrating the generalizability of the obtained results. Finally, we showed the advantages given by transfer learning when using the proposed novel architecture on other P300 datasets. The presented architectures and practical suggestions can be used by BCI practitioners to improve its effectiveness.

Identification and characterization of learning weakness from drawing analysis at the pre-literacy stage.

Handwriting learning delays should be addressed early to prevent their exacerbation and long-lasting consequences on whole children's lives. Ideally, proper training should start even before learning how to write. This work presents a novel method to disclose potential handwriting problems, from a pre-literacy stage, based on drawings instead of words production analysis. Two hundred forty-one kindergartners drew on a tablet, and we computed features known to be distinctive of poor handwriting from symbols drawings. We verified that abnormal features patterns reflected abnormal drawings, and found correspondence in experts' evaluation of the potential risk of developing a learning delay in the graphical sphere. A machine learning model was able to discriminate with 0.75 sensitivity and 0.76 specificity children at risk. Finally, we explained why children were considered at risk by the algorithms to inform teachers on the specific weaknesses that need training. Thanks to this system, early intervention to train specific learning delays will be finally possible.

A Tablet App for Handwriting Skill Screening at the Preliteracy Stage: Instrument Validation Study.

BACKGROUND: Difficulties in handwriting, such as dysgraphia, impact several aspects of a child's everyday life. Current methodologies for the detection of such difficulties in children have the following three main weaknesses: (1) they are prone to subjective evaluation; (2) they can be administered only when handwriting is mastered, thus delaying the diagnosis and the possible adoption of countermeasures; and (3) they are not always easily accessible to the entire community. OBJECTIVE: This work aims at developing a solution able to: (1) quantitatively measure handwriting features whose alteration is typically seen in children with dysgraphia; (2) enable their study in a preliteracy population; and (3) leverage a standard consumer technology to increase the accessibility of both early screening and longitudinal monitoring of handwriting difficulties. METHODS: We designed and developed a novel tablet-based app Play Draw Write to assess potential markers of dysgraphia through the quantification of the following three key handwriting laws: isochrony, homothety, and speed-accuracy tradeoff. To extend such an approach to a preliteracy age, the app includes the study of the laws in terms of both word writing and symbol drawing. The app was tested among healthy children with mastered handwriting (third graders) and those at a preliterate age (kindergartners). RESULTS: App testing in 15 primary school children confirmed that the three laws hold on the tablet surface when both writing words and drawing symbols. We found significant speed modulation according to size (P<.001), no relevant changes to fraction time for 67 out of 70 comparisons, and significant regression between movement time and index of difficulty for 44 out of 45 comparisons (P<.05, R2>0.28, 12 degrees of freedom). Importantly, the three laws were verified on symbols among 19 kindergartners. Results from the speed-accuracy exercise showed a significant evolution with age of the global movement time (circle: P=.003, square: P<.001, word: P=.001), the goodness of fit of the regression between movement time and accuracy constraints (square: P<.001, circle: P=.02), and the index of performance (square: P<.001). Our findings show that homothety, isochrony, and speed-accuracy tradeoff principles are present in children even before handwriting acquisition; however, some handwriting-related skills are partially refined with age. CONCLUSIONS: The designed app represents a promising solution for the screening of handwriting difficulties, since it allows (1) anticipation of the detection of alteration of handwriting principles at a preliteracy age and (2) provision of broader access to the monitoring of handwriting principles. Such a solution potentially enables the selective strengthening of lacking abilities before they exacerbate and affect the child's whole life.

Opportunities to improve feasibility, effectiveness and costs associated with a total joint replacements high-volume hospital registry.

BACKGROUND: Clinical registries are powerful tools for collecting uniform data longitudinally, thus making it possible to evaluate the outcome of patients affected by a specific pathology. In the context of total joint arthroplasty, registries serve also as post-market surveillance. Adoption of registries is a heavy burden for clinical settings in terms of resources and infrastructures. Excessive workload leads to incomplete data collection which undermines the effectiveness of a registry and consequently the workload needs to be optimised. METHODS: Starting from the use case of the Istituto Ortopedico Galeazzi, the time and personnel dedicated to the registry was estimated. Analysis of the data collected in the first years enabled us to propose a methodology for workload reduction. Different Machine Learning models were leveraged to predict patients with excellent satisfaction to reduce the number of assessments in their clinical post-operative follow-up. Moreover, feature selection was used to identify any unnecessary clinical scale to collect. RESULTS: Given an acceptance rate of 3500 patients per year, 22 doctors and 6 non-medical employees were required to adopt a registry properly. Among the tested models, the Naïve Bayes gave the best performance (AUPRC = 0.81) in predicting patient satisfaction at six months. Moreover, we found that the 12-item Short Form was poorly informative in predicting satisfaction at six-months. CONCLUSIONS: In this study machine learning was leveraged to provide a methodology to reduce workload in the use of pathology registries. Such workload reduction can have a considerable impact at a larger scale, and improve registry feasibility in high-volume hospitals.

PROs in the wild: Assessing the validity of patient reported outcomes in an electronic registry.

BACKGROUND AND OBJECTIVES: Collecting Patient-Reported Outcomes (PROs) is an important way to get first-hand information by patients on the outcome of treatments and surgical procedure they have undergone, and hence about the quality of the care provided. However, the quality of PRO data cannot be given for granted and cannot be traced back to the dimensions of timeliness and completeness only. While the reliability of these data can be guaranteed by adopting standard and validated questionnaires that are used across different health care facilities all over the world, these facilities must take responsibility to assess, monitor and ensure the validity of PROs that are collected from their patients. Validity is affected by biases that are hidden in the data collected. This contribution is then aimed at measuring bias in PRO data, for the impact that these data can have on clinical research and post-marketing surveillance. METHODS: We considered the main biases that can affect PRO validity: Response bias, in terms of Acquiescence bias and Fatigue bias; and Non-Response bias. To assess Acquiescence bias, phone interviews and online surveys were compared, adjusted by age. To assess Fatigue bias, we proposed a specific item about session length and compared PROs scores stratifying according to the responses to this item. We also calculated the intra-patient agreement by conceiving an intra-interview test-retest. To assess Non-Response bias, we considered patients who participated after the saturation of the response-rate curve as proxy of potential non respondents and compared the outcomes in these two strata. All methods encompassed common statistical techniques and are cost-effective at any facility collecting PRO data. RESULTS: Acquiescence bias resulted in significantly different scores between patients reached by either phone or email. In regard to Fatigue bias, stratification by perceived fatigue resulted in contrasting results. A relevant difference was found in intra-patient agreement and an increasing difference in average scores as a function of interview length (or completion time). In regard to Non-Response bias, we found non-significant differences both in scores and variance. CONCLUSIONS: In this paper, we present a set of cost-effective techniques to assess the validity of retrospective PROs data and share some lessons learnt from their application at a large teaching hospital specialized in musculoskeletal disorders that collects PRO data in the follow-up phase of surgery performed therein. The main finding suggests that response bias can affect the PRO validity. Further research on the effectiveness of simple and cost-effective solutions is necessary to mitigate these biases and improve the validity of PRO data.

The Revival of the Notes Field: Leveraging the Unstructured Content in Electronic Health Records.

Problem: Clinical practice requires the production of a time- and resource-consuming great amount of notes. They contain relevant information, but their secondary use is almost impossible, due to their unstructured nature. Researchers are trying to address this problems, with traditional and promising novel techniques. Application in real hospital settings seems not to be possible yet, though, both because of relatively small and dirty dataset, and for the lack of language-specific pre-trained models. Aim: Our aim is to demonstrate the potential of the above techniques, but also raise awareness of the still open challenges that the scientific communities of IT and medical practitioners must jointly address to realize the full potential of unstructured content that is daily produced and digitized in hospital settings, both to improve its data quality and leverage the insights from data-driven predictive models. Methods: To this extent, we present a narrative literature review of the most recent and relevant contributions to leverage the application of Natural Language Processing techniques to the free-text content electronic patient records. In particular, we focused on four selected application domains, namely: data quality, information extraction, sentiment analysis and predictive models, and automated patient cohort selection. Then, we will present a few empirical studies that we undertook at a major teaching hospital specializing in musculoskeletal diseases. Results: We provide the reader with some simple and affordable pipelines, which demonstrate the feasibility of reaching literature performance levels with a single institution non-English dataset. In such a way, we bridged literature and real world needs, performing a step further toward the revival of notes fields.

Collecting Patient Reported Outcomes in the Wild: Opportunities and Challenges.

Collecting Patient Reported Outcomes (PROs) is generally seen as an effective way to assess the efficacy and appropriateness of medical interventions, from the patients' perspective. In 2016 the Galeazzi Orthopaedic Institute established a digitized program of PROs collection from spine, hip and knee surgery patients. In this work, we re-port the findings from the data analysis of the responses collected so far about the complementarity of PROs with respect to the data reported by the clinicians, and about the main biases that can undermine their validity and reliability. Although PROs collection is recognized as being far more complex than just asking the patients "how they feel" on a regular basis and it entails costs and devoted electronic platforms, we advocate their further diffusion for the assessment of health technology and clinical procedures.

Minimal Important Difference in Outcome of Disc Degenerative Disease Treatment: The Patients' Perspective.

Evaluation of treatments effectiveness in a context of value-based health care is based on outcomes, and in their assessment. The patient perspective is gaining renovated interest, as demonstrated by the increasing diffusion of Patient Reported Outcome Measure (PROMs) collection initiatives. The concept of Minimal Clinically Important Dif-ference (MID) is generally seen as the basis to estimate the actual effect perceived by the patient after a treatment, like a surgical intervention, but a universally recognized threshold has not yet been established. At the Orthopedic Institute Galeazzi (Milan, Italy) we began a digitized program of PROM collection in spine surgery by means of a digital platform, called Datareg. In this work we aim to investigate MID in the treatment of degenerated disc in terms of patients' perceptions as these are collected through the above electronic registry. We proposed a computation of MID on the basis of two PROM scores, and a critical comparison with a domain expert's proposal.