No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Human-Centered AI Goals for Speech Therapy Tools
Abstract
With the advent of improved Artificial Intelligence (AI) algorithms and the availability of large datasets, researchers worldwide are developing numerous AI-based applications to replicate human capabilities. One such application is automating the task of Speech Language Pathologists (SLPs) and building automated speech therapy tools for children with Speech Sound Disorder (SSD). However, this development of AI focused on imitating human capabilities brings concerns such as algorithmic discrimination or biased algorithms, job displacements, and privacy issues. To address these challenges, researchers advocate for Human-Centered AI (HCAI) and have proposed various frameworks for AI-based systems. Although the proposed frameworks were developed for generalized AI application, it is not clear about its relevance in specialized AI application such as speech therapy. This study aims to establish HCAI goals and a goal hierarchy specific to an HCAI-based Speech Therapy Tool (HCAI-STT) designed for children with SSD. Through an Affinity Mapping exercise, we identify seven top-level goals and sub-goals, which include fairness, responsibility and accountability, human-centered empowerment, trustworthiness, privacy, unbiased funding, and security. Our findings highlight the importance of considering not only the technical capabilities of AI systems, but also their ethical and social implications. By prioritizing these goals, we can help ensure that AI-based speech therapy tools are developed and deployed in a responsible and ethical manner that aligns with the needs and values of their users. Our findings have broader implications for the development and deployment of AI systems across domains, and future research can build on our findings by exploring how the goal hierarchy we developed can be operationalized in practice.
... Thanks to the development of machine learning algorithms and programs, medical AI technologies are now capable of building symbolic models of diseases to represent patient symptoms (Koh & Tan, 2005;Ramesh et al., 2004;Wimmer et al., 2016). In diagnosing and treating communication disorders, integration of AI techniques has been shown to be successful in improving diagnosis accuracy (Azevedo et al., 2024;Girardi et al., 2023), offering customized therapies (Deka et al., 2023;Pierce, 2024), and enhancing the effects of recovery (Jia et al., 2022). Patients, researchers, and therapists can all gain great benefits from the integration of AI techniques in the discipline of CSD (Mahmoud et al., 2020;Sakin & Bal, 2022). ...
Purpose
As artificial intelligence (AI) takes an increasingly prominent role in health care, a growing body of research is being dedicated to its application in the investigation of communication sciences and disorders (CSD). This study aims to provide a comprehensive overview, serving as a valuable resource for researchers, developers, and professionals seeking to comprehend the evolving landscape of AI in CSD research.
Method
We conducted a bibliometric analysis of AI-based research in the discipline of CSD published up to December 2023. Utilizing the Web of Science and Scopus databases, we identified 15,035 publications, with 4,375 meeting our inclusion criteria. Based on the bibliometric data, we examined publication trends and patterns, characteristics of research activities, and research hotspot tendencies.
Results
From 1985 onwards, there has been a consistent annual increase in publications, averaging 16.51%, notably surging from 2012 to 2023. The primary communication disorders studied include autism, aphasia, dysarthria, Parkinson's disease, and Alzheimer's disease. Noteworthy AI models instantiated in CSD research encompass support vector machine, convolutional neural network, and hidden Markov model, among others.
Conclusions
Compared to AI applications in other fields, the adoption of AI in CSD has lagged slightly behind. While CSD studies primarily use classical machine learning techniques, there is a growing trend toward the integration of deep learning methods. AI technology offers significant benefits for both research and clinical practice in CSD, but it also presents certain challenges. Moving forward, collaboration among technological, research, and clinical domains is essential to empower researchers and speech-language pathologists to effectively leverage AI technology for the study, diagnosis, assessment, and rehabilitation of CSD.
Supplemental Material
https://doi.org/10.23641/asha.27162564
This article reports the findings of AI4People, a year-long initiative designed to lay the foundations for a “Good AI Society”. We introduce the core opportunities and risks of AI for society; present a synthesis of five ethical principles that should undergird its development and adoption; and offer 20 concrete recommendations – to assess, to develop, to incentivise, and to support good AI – which in some cases may be undertaken directly by national or supranational policy makers, while in others may be led by other stakeholders. If adopted, these recommendations would serve as a firm foundation for the establishment of a Good AI Society.
In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence , namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
→ The third wave of AI can be characterized by technological enhancement and application + a human-centered approach.
→ HCI professionals should take a leading role by providing
explainable and comprehensible AI, and useful and usable AI.
→ HCI professionals should proactively participate in AI R&D to increase their influence, enhance their AI knowledge, and integrate methods between the two fields.
The European Commission’s report ‘Ethics guidelines for trustworthy AI’ provides a clear benchmark to evaluate the responsible development of AI systems, and facilitates international support for AI solutions that are good for humanity and the environment, says Luciano Floridi.
Research and debate on the impacts of AI have often been divided into two sets of issues, associated with two seemingly separate communities of researchers. One relates to the near-term -- that is, immediate or imminent challenges, such as privacy and algorithmic bias. A second set of issues relates to longer-term concerns that are less certain, such as risks of AI developing broad superhuman capabilities. These two sets of issues are often seen as entirely disconnected. We argue that this perception of disconnect is a mistake. There are many connections between the nearer and longer-term issues, and researchers focused on one have good reasons to take seriously work done on the other. Long-termists should look to the near-term because research directions, policies, and collaborations developed on a range of issues now could significantly affect long-term outcomes. At the same time, near-termists could benefit from the long-termists’ big picture forecasting and contingencies work.
Issues regarding explainable AI involve four components: users, laws and regulations, explanations and algorithms. Together these components provide a context in which explanation methods can be evaluated regarding their adequacy. The goal of this chapter is to bridge the gap between expert users and lay users. Different kinds of users are identified and their concerns revealed, relevant statements from the General Data Protection Regulation are analyzed in the context of Deep Neural Networks (DNNs), a taxonomy for the classification of existing explanation methods is introduced, and finally, the various classes of explanation methods are analyzed to verify if user concerns are justified. Overall, it is clear that (visual) explanations can be given about various aspects of the influence of the input on the output. However, it is noted that explanation methods or interfaces for lay users are missing and we speculate which criteria these methods/interfaces should satisfy. Finally it is noted that two important concerns are difficult to address with explanation methods: the concern about bias in datasets that leads to biased DNNs, as well as the suspicion about unfair outcomes.
This article reports the findings of AI4People, a year-long initiative designed to lay the foundations for a "Good AI Society". We introduce the core opportunities and risks of AI for society; present a synthesis of five ethical principles that should undergird its development and adoption; and offer 20 concrete recommendations-to assess, to develop, to incentivise, and to support good AI-which in some cases may be undertaken directly by national or supranational policy makers, while in others may be led by other stakeholders. If adopted, these recommendations would serve as a firm foundation for the establishment of a Good AI Society.
In recent years, there has been increased attention on the possible impact of future robotics and AI systems. Prominent thinkers have publicly warned about the risk of a dystopian future when the complexity of these systems progresses further. These warnings stand in contrast to the current state-of-the-art of the robotics and AI technology. This article reviews work considering both the future potential of robotics and AI systems, and ethical considerations that need to be taken in order to avoid a dystopian future. References to recent initiatives to outline ethical guidelines for both the design of systems and how they should operate are included.
Purpose
The purpose of this study was to determine prevalence and predictors of persistent speech sound disorder (SSD) in children aged 8 years after disregarding children presenting solely with common clinical distortions (i.e., residual errors).
Method
Data from the Avon Longitudinal Study of Parents and Children (Boyd et al., 2012) were used. Children were classified as having persistent SSD on the basis of percentage of consonants correct measures from connected speech samples. Multivariable logistic regression analyses were performed to identify predictors.
Results
The estimated prevalence of persistent SSD was 3.6%. Children with persistent SSD were more likely to be boys and from families who were not homeowners. Early childhood predictors identified as important were weak sucking at 4 weeks, not often combining words at 24 months, limited use of word morphology at 38 months, and being unintelligible to strangers at age 38 months. School-age predictors identified as important were maternal report of difficulty pronouncing certain sounds and hearing impairment at age 7 years, tympanostomy tube insertion at any age up to 8 years, and a history of suspected coordination problems. The contribution of these findings to our understanding of risk factors for persistent SSD and the nature of the condition is considered.
Conclusion
Variables identified as predictive of persistent SSD suggest that factors across motor, cognitive, and linguistic processes may place a child at risk.
Supplemental Material
https://doi.org/10.23641/asha.14963811
This essay is a discussion of the KJ method developed by a Japanese ethnologist, Jiro Kawakita. A brief biography of Kawakita and the history of the KJ method is described. The KJ method was developed as a result of having difficulties in interpreting ethnographic data in Nepal. The KJ method builds upon Charles Pierce's notions of abduction and relies upon intuitive non-logical thinking processes. Kawakita's methods were developed and diffused throughout Japanese management and educational circles. Kawakita believes that his methodology has the potential of liberating humanity from the mechanistic philosophy imposed by Western Civilization. The KJ mthod, according to Kawakita has universal applicability and does not only conform to Japanese culture and management decision-making processes which are generally based on the group-orientation model. This simplistic group-orientation model of Japanese society is being criticized by anthropologists such as Harumi Befu. Kawakita argues that human nature is universal, and that the KJ method, as a means of decision-making can be utilized in all societies throughout the world to implement social and economic development.
Communication disorder is a widespread disabling problems and associated with adverse, long term outcome that impact on individuals, families and academic achievement of children in the school years and affect vocational choices later in adulthood. The aim of this study was to determine prevalence of speech disorders specifically stuttering, voice, and speech-sound disorders in primary school students in Iran-Yazd. In a descriptive study, 7881 primary school students in Yazd evaluated in view from of speech disorders with use of direct and face to face assessment technique in 2005. The prevalence of total speech disorders was 14.8% among whom 13.8% had speech-sound disorder, 1.2% stuttering and 0.47% voice disorder. The prevalence of speech disorders was higher than in males (16.7%) as compared to females (12.7%). Pattern of prevalence of the three speech disorders was significantly different according to gender, parental education and by number of family member. There was no significant difference across speech disorders and birth order, religion and paternal consanguinity. These prevalence figures are higher than more studies that using parent or teacher reports.
It is estimated that 10% of the world's population, approximately 650 million people, have some form of disability. Population growth, aging, and medical advances that preserve and prolong life have increased demands for health and rehabilitation services. Recent predictions indicate a shortage of speech-language pathologists and other rehabilitation specialists to provide care for individuals with disabilities. The application of telemedicine and telehealth technologies offers effective solutions to this challenge. An extensive literature review was conducted that included technical reports, websites, publications from the American Speech-Language-Hearing Association, and peer-reviewed journal articles of telehealth applications in speech-language pathology. Various applications of telehealth in speech-language pathology are described including types of technology, patient and clinician satisfaction, advantages of using telehealth, challenges and barriers to application, and future directions. This review provides a strong foundation for broader applications of telehealth technologies in this area of healthcare.
Purpose
The primary focus of this study was to elicit the perspectives of speech-language pathologists (SLPs) regarding features of the work environment that contribute to and/or hinder recruitment and retention in the public school setting.
Method
A questionnaire was distributed to SLPs employed in 10 school districts in Central Florida representing small, medium, and large school districts. The primary goal of the questionnaire was to elicit the perspectives of school-based SLPs regarding (a) factors in the work environment that contribute to retention, (b) factors in the work environment that hinder retention, and (c) issues that may contribute to the recruitment and retention of SLPs in the school setting. A total of 382 questionnaires was obtained, yielding a 64.5% response rate.
Results
The participants ranked working with children, school schedule, and educational setting as primary reasons for their satisfaction with working in the public school setting. The participants ranked workload, role ambiguity, salary, and caseload as primary reasons for their dissatisfaction with working in the public school setting.
Conclusion
Themes emerged from the data that provide insight into several factors that serve as powerful influences in understanding issues of recruitment and retention of SLPs in the public school setting.
Purpose
The aims of this study were threefold: to report teachers' estimates of the prevalence of speech disorders (specifically, stuttering, voice, and speech-sound disorders); to consider correspondence between the prevalence of speech disorders and gender, grade level, and socioeconomic status; and to describe the level of support provided to schoolchildren with speech disorders.
Method
Students with speech disorders were identified from 10,425 students in Australia using a 4-stage process: training in the data collection process, teacher identification, confirmation by a speech-language pathologist, and consultation with district special needs advisors.
Results
The prevalence of students with speech disorders was estimated; specifically, 0.33% of students were identified as stuttering, 0.12% as having a voice disorder, and 1.06% as having a speech-sound disorder. There was a higher prevalence of speech disorders in males than in females. As grade level increased, the prevalence of speech disorders decreased. There was no significant difference in the pattern of prevalence across the three speech disorders and four socioeconomic groups; however, students who were identified with a speech disorder were more likely to be in the higher socioeconomic groups. Finally, there was a difference between the perceived and actual level of support that was provided to these students.
Conclusion
These prevalence figures are lower than those using initial identification by speech-language pathologists and similar to those using parent report.
With the widespread use of artificial intelligence (AI) systems and applications in our everyday lives, accounting for fairness has gained significant importance in designing and engineering of such systems. AI systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that these decisions do not reflect discriminatory behavior toward certain groups or populations. More recently some work has been developed in traditional machine learning and deep learning that address such challenges in different subdomains. With the commercialization of these systems, researchers are becoming more aware of the biases that these applications can contain and are attempting to address them. In this survey, we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and ways they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.
Today’s artificial intelligence still faces two major challenges. One is that, in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these challenges: secure federated learning. Beyond the federated-learning framework first proposed by Google in 2016, we introduce a comprehensive secure federated-learning framework, which includes horizontal federated learning, vertical federated learning, and federated transfer learning. We provide definitions, architectures, and applications for the federated-learning framework, and provide a comprehensive survey of existing works on this subject. In addition, we propose building data networks among organizations based on federated mechanisms as an effective solution to allowing knowledge to be shared without compromising user privacy.
In this paper, we propose data statements as a design solution and professional practice for natural language processing technologists, in both research and development. Through the adoption and widespread use of data statements, the field can begin to address critical scientific and ethical issues that result from the use of data from certain populations in the development of technology for other populations. We present a form that data statements can take and explore the implications of adopting them as part of regular practice. We argue that data statements will help alleviate issues related to exclusion and bias in language technology, lead to better precision in claims about how natural language processing research can generalize and thus better engineering results, protect companies from public embarrassment, and ultimately lead to language technology that meets its users in their own preferred linguistic style and furthermore does not misrepresent them to others.
Trained machine learning models are increasingly used to perform high-impact tasks in areas such as law enforcement, medicine, education, and employment. In order to clarify the intended use cases of machine learning models and minimize their usage in contexts for which they are not well suited, we recommend that released models be accompanied by documentation detailing their performance characteristics. In this paper, we propose a framework that we call model cards, to encourage such transparent model reporting. Model cards are short documents accompanying trained machine learning models that provide benchmarked evaluation in a variety of conditions, such as across different cultural, demographic, or phenotypic groups (e.g., race, geographic location, sex, Fitzpatrick skin type [15]) and intersectional groups (e.g., age and race, or sex and Fitzpatrick skin type) that are relevant to the intended application domains. Model cards also disclose the context in which models are intended to be used, details of the performance evaluation procedures, and other relevant information. While we focus primarily on human-centered machine learning models in the application fields of computer vision and natural language processing, this framework can be used to document any trained machine learning model. To solidify the concept, we provide cards for two supervised models: One trained to detect smiling faces in images, and one trained to detect toxic comments in text. We propose model cards as a step towards the responsible democratization of machine learning and related artificial intelligence technology, increasing transparency into how well artificial intelligence technology works. We hope this work encourages those releasing trained machine learning models to accompany model releases with similar detailed evaluation numbers and other relevant documentation.
This is a forum for perspectives on designing for communities marginalized by economics, social status, infrastructure, or policies. It will discuss design methods, theoretical and conceptual contributions, and methodological engagements for underserved communities. --- Nithya Sambasivan, Editor
This paper presents Apraxia World, a remote therapy tool for speech sound disorders that integrates speech exercises into an engaging platformer-style game. In Apraxia World, the player controls the avatar with virtual buttons/joystick, whereas speech input is associated with assets needed to advance from one level to the next. We tested performance and child preference of two strategies for delivering speech exercises: during each level, and after it. Most children indicated that doing exercises after completing each level was less disruptive and preferable to doing exercises scattered through the level. We also found that children liked having perceived control over the game (character appearance, exercise behavior). Our results indicate that (i) a familiar style of game successfully engages children, (ii) speech exercises function well when decoupled from game control, and (iii) children are willing to complete required speech exercises while playing a game they enjoy.
Concerns that algorithms may discriminate against certain groups have led to numerous efforts to 'blind' the algorithm to race. We argue that this intuitive perspective is misleading and may do harm. Our primary result is exceedingly simple, yet often overlooked. A preference for fairness should not change the choice of estimator. Equity preferences can change how the estimated prediction function is used (e.g., different threshold for different groups) but the function itself should not change. We show in an empirical example for college admissions that the inclusion of variables such as race can increase both equity and efficiency.
Children born with cleft lip and palate (CL/P) disorder go through several years of corrective surgeries, dental procedures, and jaw correction. These children suffer from varying degrees of speech impediment. Current treatments include speech therapy, but such treatments are not equally accessible for children from different socio-economic backgrounds. When available, speech therapists find it difficult to evaluate the children's progress in articulation over time. Buddy is a therapy robot for CL/P children that can provide contextual speech therapy in a gamified story-building format. To improve articulation, Buddy will provide robust visual feedback during these sessions and guide the children in enunciating tough words while collecting data of speech pattern for further analysis by the speech therapist.
Background
Multiple interventions have been developed to address speech sound disorder (SSD) in children. Many of these have been evaluated but the evidence for these has not been considered within a model which categorizes types of intervention. The opportunity to carry out a systematic review of interventions for SSD arose as part of a larger scale study of interventions for primary speech and language impairment in preschool children.
Aims
To review systematically the evidence for interventions for SSD in preschool children and to categorize them within a classification of interventions for SSD.
Methods & Procedures
Relevant search terms were used to identify intervention studies published up to 2012, with the following inclusion criteria: participants were aged between 2 years and 5 years, 11 months; they exhibited speech, language and communication needs; and a primary outcome measure of speech was used. Studies that met inclusion criteria were quality appraised using the single case experimental design (SCED) or PEDro-P, depending on their methodology. Those judged to be high quality were classified according to the primary focus of intervention.
Outcomes & Results
The final review included 26 studies. Case series was the most common research design. Categorization to the classification system for interventions showed that cognitive–linguistic and production approaches to intervention were the most frequently reported. The highest graded evidence was for three studies within the auditory–perceptual and integrated categories.
Conclusions & Implications
The evidence for intervention for preschool children with SSD is focused on seven out of 11 subcategories of interventions. Although all the studies included in the review were good quality as defined by quality appraisal checklists, they mostly represented lower-graded evidence. Higher-graded studies are needed to understand clearly the strength of evidence for different interventions.
According to the United Nations International Children’s Emergency Fund (UNICEF), nowadays in several developing countries there is a lack of essential services for children with disabilities in important fields such as speech-language therapy, physiotherapy, and sign language instruction. Likewise, the UNICEF points that in low income countries only between 5 and 15% of children and adults who require assistive technologies have access to them. In this line, in this paper we present a system that provides three main functionalities for speech-language therapists: a decision support system for planning therapy sessions (ontologies), a robotic assistant to motivate children with disabilities to work in therapy activities, and a module to automatically create groups of patients with similar profiles and needs (agglomerative clustering). In order to validate our proposal we worked with two groups: a first one consisting on 111 youth to validate the robot’s appearance and functionalities, and a second group of 70 children with communication disorders and disabilities to determine their response to therapies provided through robot. In the same way, we have used the children’s profiles to populate the ontology and feed the decision support module based on clustering.
In this paper, a systematic review of relevant published studies on computer-based speech therapy systems or virtual speech therapists (VSTs) for people with speech disorders is presented. We structured this work based on the PRISMA framework. The advancements in speech technology and the increased number of successful real-world projects in this area point to a thriving market for VSTs in the near future; however, there is no standard roadmap to pinpoint how these systems should be designed, implemented, customized, and evaluated with respect to the various speech disorders. The focus of this systematic review is on articulation and phonological impairments. This systematic review addresses three research questions: what types of articulation and phonological disorders do VSTs address, how effective are virtual speech therapists, and what technological elements have been utilized in VST projects. The reviewed papers were sourced from comprehensive digital libraries, and were published in English between 2004 and 2014. All the selected studies involve computer-based intervention in the form of a VST regarding articulation or phonological impairments, followed by qualitative and/or quantitative assessments. To generate this review, we encountered several challenges. Studies were heterogeneous in terms of disorders, type and frequency of therapy, sample size, level of functionality, etc. Thus, overall conclusions were difficult to draw. Commonly, publications with rigorous study designs did not describe the technical elements used in their VST, and publications that did describe technical elements had poor study designs. Despite this heterogeneity, the selected studies reported the effectiveness of computers as a more engaging type of intervention with more tools to enrich the intervention programs, particularly when it comes to children; however, it was emphasized that virtual therapists should not drive the intervention but must be used as a medium to deliver the intervention planned by speech-language pathologists. Based on the reviewed papers, VSTs are significantly effective in training people with a variety of speech disorders; however, it cannot be claimed that a consensus exists in the superiority of VSTs over speech-language pathologists regarding rehabilitation outcomes. Our review shows that hearing-impaired cases were the most frequently addressed disorder in the reviewed studies. Automatic speech recognition, speech corpus, and speech synthesizers were the most popular technologies used in the VSTs.
Nearly 8% of children aged 3-17 years had a communication disorder during the past 12 months. • Children aged 3-6 years, boys, and non-Hispanic black children were more likely than other children to have had any communication disorder. • Approximately 55% of children aged 3-17 years who had any communication disorder received an intervention service during the past 12 months. • Among those with any communication disorder, younger children, boys, and non-Hispanic white children were more likely than other children to receive an intervention service for their disorder.
All material appearing in this report is in the public domain and may be reproduced or copied without permission; citation as to source, however, is appreciated.
AimThe epidemiology of preschool speech sound disorder is poorly understood. Our aims were to determine: the prevalence of idiopathic speech sound disorder; the comorbidity of speech sound disorder with language and pre-literacy difficulties; and the factors contributing to speech outcome at 4 years.Method
One thousand four hundred and ninety-four participants from an Australian longitudinal cohort completed speech, language, and pre-literacy assessments at 4 years. Prevalence of speech sound disorder (SSD) was defined by standard score performance of ≤79 on a speech assessment. Logistic regression examined predictors of SSD within four domains: child and family; parent-reported speech; cognitive-linguistic; and parent-reported motor skills.ResultsAt 4 years the prevalence of speech disorder in an Australian cohort was 3.4%. Comorbidity with SSD was 40.8% for language disorder and 20.8% for poor pre-literacy skills. Sex, maternal vocabulary, socio-economic status, and family history of speech and language difficulties predicted SSD, as did 2-year speech, language, and motor skills. Together these variables provided good discrimination of SSD (area under the curve=0.78).InterpretationThis is the first epidemiological study to demonstrate prevalence of SSD at 4 years of age that was consistent with previous clinical studies. Early detection of SSD at 4 years should focus on family variables and speech, language, and motor skills measured at 2 years.
A pluralistic approach, design computers from the user's point of view
Project management body of knowledge. Project Management Institute. 5ª Edição
- P Guide
Guide, P.: Project management body of knowledge. Project Management Institute.
5ª Edição. Versão em português (2000)