Background: Autism Spectrum Disorder (ASD) is a complex neurodevelopmen-tal disorder that affects social communication, behavior, and cognitive development.Patients with autism have a variety of difficulties, such as sensory impairments, at-tention issues, learning disabilities, mental health issues like anxiety and depression,as well as motor and learning issues. The World Health Organization (WHO) es-timates that one in 100 children have ASD. Although ASD cannot be completelytreated, early identification of its symptoms might lessen its impact. Early identifi-cation of ASD can significantly improve the outcome of interventions and therapies.So, it is important to identify the disorder early. Machine learning algorithms canhelp in predicting ASD. In this thesis, Support Vector Machine (SVM) and RandomForest (RF) are the algorithms used to predict ASD. Objectives: The main objective of this thesis is to build and train the models usingmachine learning(ML) algorithms with the default parameters and with the hyper-parameter tuning and find out the most accurate model based on the comparison oftwo experiments to predict whether a person is suffering from ASD or not. Methods: Experimentation is the method chosen to answer the research questions.Experimentation helped in finding out the most accurate model to predict ASD. Ex-perimentation is followed by data preparation with splitting of data and by applyingfeature selection to the dataset. After the experimentation followed by two exper-iments, the models were trained to find the performance metrics with the defaultparameters, and the models were trained to find the performance with the hyper-parameter tuning. Based on the comparison, the most accurate model was appliedto predict ASD. Results: In this thesis, we have chosen two algorithms SVM and RF algorithms totrain the models. Upon experimentation and training of the models using algorithmswith hyperparameter tuning. SVM obtained the highest accuracy score and f1 scoresfor test data are 96% and 97% compared to other model RF which helps in predictingASD. Conclusions: The models were trained using two ML algorithms SVM and RF andconducted two experiments, in experiment-1 the models were trained using defaultparameters and obtained accuracy, f1 scores for the test data, and in experiment-2the models were trained using hyper-parameter tuning and obtained the performancemetrics such as accuracy and f1 score for the test data. By comparing the perfor-mance metrics, we came to the conclusion that SVM is the most accurate algorithmfor predicting ASD.

No description available.

No description available.

No description available.

No description available.

No description available.

[pt] A teoria da mente (ToM) é definida como a habilidade de inferir estados mentais internos de outras pessoas. Há consenso na literatura de que ToM é um marcador sociocognitivo do Transtorno do Espectro autista-TEA. A testagem é realizada, em grande parte, a partir de um paradigma denominado falsa crença. Contudo, verifica-se a necessidade de instrumentos de avaliação mais apurados, que compreendam: a complexidade do constructo, a relação com outros domínios cognitivos como funções executivas. O objetivo deste trabalho foi desenvolver e verificar evidências de validade de um novo instrumento que avalie os diferentes domínios de ToM para auxílio de diagnóstico em crianças com TEA. Este estudo foi registrado no Comitê de Ética em Pesquisa da Pontifícia Universidade Católica-PUC-Rio. O projeto foi dividido em quatro estudos, que englobavam desde uma revisão bibliográfica sobre as tarefas de ToM utilizadas em avaliações de crianças com diagnóstico de TEA, até mostrar evidências de validade do instrumento de nominado Bateria de avaliação em Teoria da Mente-BToM. Os resultados mostraram que BToM possui evidências de validade de conteúdo e de constructo, bem como de precisão. Além disso, identifica tarefas de Estados Mentais e Verbalizações, como possíveis marcadores sociocognitivos no diagnóstico de fenótipos mais leves do TEA. / [en] Theory of Mind (ToM) is defined as the ability to infer other s internal mental states. There is a consensus in the literature that ToM is a sociocognitive marker of Autism Spectrum Disorder-ASD. Performance is assessed in majority from false belief paradigm. However, there is a need for more accurate assessment tools, which include: complexity of the construct, interface with other cognitive domains as executive functions. The purpose of this work was to develop and verify validity’s evidences of a new instrument who evaluates differents ToM domains for diagnostic support in children with ASD. This study was registered in the Research Ethics Committee of Pontifical Catholical University of Rio de Janeiro-PUC-Rio. The project was divided into five studies, ranging from a literature review of ToM tasks used in assessments of ASD children, to show validity evidences of the instrument nominated Battery of Theory of Mind-BToM. The results showed BToM has evidence of content and construct validity as well as accuracy. In addition, it identifies Mental States and Verbalizations tasks as possible sociocognitive markers on diagnoses of lighter ASD phenotypes.

En analys av en studie gjord av Lorenz och Heinitz (2014) på autistiska personers uppfattning om sig själva, sina förmågor och behov och en kartläggningsrapport av Specialpedagogiska skolmyndigheten från 2013 har belyst hur det hos dessa individer finns en potential långt utöver det normala. Skolmyndigheten (2013) rapporterar om att lärare saknar verktyg för att förstå elever med neuropsykiatriska funktionsvariationer, framförallt vid autismspektrumtillstånd där sådana verktyg ofta behöver vara individanpassade och därför varierar från elev till elev. Önskan om att hitta metoder för att använda tillgängliga läromedel eller önskan om handledning för att förstå eleverna bättre är någonting som lyfts upp då lärare menar sig vara vilsna kring vad man ska göra i den egna undervisningen med de metoder som finns. Med detta som grund motiverades jag till att utforma ett fortbildningsmaterial för lärare inom matematik som förhoppningsvis ska kunna stötta lärarna i deras kommunikation med elever med autismspektrumtillstånd. Som ett led i utvecklingsarbetet gjordes djupintervjuer med två lärare inom matematik och teknik och med fyra personer diagnosticerade med AST. Därefter analyserades intervjuerna med hjälp av tematisk analys för att sedan användas som underlag för diskussion kring några faktorer som påverkar elevens lärande. Faktorer som framkom var lärarnas undervisningsform, föreställningar av sin och elevens roll i lärandet och hur lärarens relation till de övriga lärare i kollegieteamet påverkar kvalitén av lärarens undervisning. Resultatet från djupintervjuerna visade att det hos elever med AST finns behov av tydlighet, struktur och tidsplanering. Vill man som lärare säkerställa en bra kommunikation med dessa elever behöver en förståelse för hur läraren kan förmedla förväntningar uppmärksammas. Sådana förväntningar kan vara såväl implicita och explicita. Förväntningar som t.ex. kan vara att läraren tilldelar uppgifter som befinner sig på en lägre nivå än elevens egen föreställning av sin förmåga. Läraren behöver också vara införstådd i elevens problematik och för det krävs ett mer omfattande arbete inom kollegiet som läraren är en del av. Detta eftersom ett bra stöd för eleven inte kan förväntas ges enbart av elevens egna lärare då elevens behov av stöd kräver insatser från flera olika yrkesgrupper. Vidare visade resultat från djupintervjuerna hur det hos elever med AST finns ett behov av social inkludering, däremot var det mindre tydligt hur eleverna skulle uppnå detta. Man hänvisade till att läraren saknar kunskap om hur elevens personligheter och intressen måste beaktas tillsammans innan man sammanför grupper. Också underströks hur eleven behöver lära sig hantera vissa sociala situationer, vad den ska säga och hur. Om inte det sker vågar eleven sällan inleda samtal med övriga klasskamrater och det i sin tur har jag kunnat visa påverka elevens fortsatta förståelse av matematik. Utvärdering av det utvecklade fortbildningsmaterialet gav värdefull återkoppling för att förbättra materialet. Utvärderingen genomfördes bland tre verksamma lärare. En lärare hade förstått det avsedda syftet och angav att materialet gav hen idéer om hur undervisning kan genomföras, t.ex. genom att omformulera sina uppgifter eller addera material inför vissa moment som kan göra det lättare för AST-elever att sätta sig in i dem. För de andra två lärarna var syftet otydligt och de angav att det saknades tillräckligt med uppgifter som läraren kunde använda för sina elever med AST, men att de förslagen som gavs ändå var uppskattade. / A study conducted by Lorenz and Heinitz (2014) on the view that autistic people have of themselves, their attributes as well as a survey done by Specialpedagogiska Skolmyndigheten (2013) suggest that a lot of individuals on the spectrum may own a potential far beyond what is considered normal. The report from Skolmyndigheten (2013) paints an image of how present material for students with neuropsychiatric disorders are lacking, especially for those students who are on the autistic spectrum. These students are specially a challenge since every individual on the spectrum and thus a one-way solution is considered virtually impossible. Using this knowledge as a building block, I was motivated to construct an introductory material for teachers in mathematics to effectively communicate with students on the autistic spectrum. The material is based on surveys done in the form of deep interviews. These deep interviews were conducted with 2 teachers in math and technology and with 4 people diagnosed with ASD. Furthermore, the data from the interviews were analysed with the help of a tool called thematic analysis. Afterwards the data was used to discuss some of the factors that affect students learning. The factors involved in my discussion were the specific form of teaching, preconceptions about ones and students’ involvement in their own learning and how teacher interaction with the other teachers in the colleague team may impact the quality of student learning. Looking at the results from the deep interviews, we see that for people with ASD there is a desire for precision, structure and adequate time-planning. Good communication with these students requires the teachers’ understanding of how she can convey her conceptions, explicit as well as implicit, by her form of teaching, for example by recognizing how the distribution of lower level problems could downgrade a students’ perception of their own10ability. Teachers need to consider and understand the problems of specific students and in order to do that a more extensive cooperation is required with the rest of the team. Such cooperation is required since one need to consider how a complex diagnosis such as autism spectrum involves appropriate intervention regulated and influenced by people in different occupation groups. The final results concerned the opinions received by teachers regarding the realization of the introductory material. With regards to the intention to construct a material which can support understanding of the communication problems associated with autism, the results of evaluation from three teachers in mathematics and technology showed mix of responses. One of the three teachers had understood the purpose and commented on how the material inspired his own taking on how to teach for these students, for instance by reformulating problems or add material in the making of problems to make it easier for students on the autistic spectrum to engage with them. The other two teachers mentioned the lack of sufficient amount of math problems which could be of any use in their own teaching, although they saw how some of the parts were useful for other purposes. I suggest that the responses were mixed as an effect of misunderstanding of the real purpose of the introductory material. Since the making of a new introductory material given the feedback was not tested, the conclusions regarding how well this material meets the context cannot be properly validated.

Core symptoms of Autism Spectrum Disorder (ASD) impact the child's abilities to interact with others, especially with the primary caregivers. Most research has focused on investigating the mother-child dyad, but the paternal role in interaction with children with ASD is mainly unexplored (e.g., Rankin, Paisley, Tomeny & Eldred, 2019; Flippin & Crais, 2011). For this, the project's first aim is to examine paternal interactive characteristics and behaviors and compare father-child and mother-child interactions with children with ASD, delineating the strengths and weaknesses of both caregivers in a complementary system. Based on this investigation, we implemented a personalized and parent-specific early intensive intervention that may guarantee better developmental trajectories for children with ASD. Consequently, the project's second aim is to assess the impact of intervention with parental involvement through cognitive, socio-communicative, and dyadic behavioral measures using a longitudinal study with pre- and post-assessments. At this point, it is fundamental to evaluate how several traits of children and caregivers might impact the treatment response. To reach this aim, while assessing developmental trajectories, we wanted to identify a-priori individual differences at both child and caregiver’s level and dyad dynamics that may influence intervention outcomes. We identified markers of better developmental trajectories and discussed implications for clinical practice in providing practitioners with more information about areas to be targeted during the intervention.

Yes / A study has been carried out to investigate controlled release performance of caplet shaped injection moulded (IM) amorphous solid dispersion (ASD) tablets based on the model drug AZD0837 and polyethylene oxide (PEO). The physical/chemical storage stability and release robustness of the IM tablets were characterized and compared to that of conventional extended release (ER) hydrophilic matrix tablets of the same raw materials and compositions manufactured via direct compression (DC). To gain an improved understanding of the release mechanisms, the dissolution of both the polymer and the drug were studied. Under conditions where the amount of dissolution media was limited, the controlled release ASD IM tablets demonstrated complete and synchronized release of both PEO and AZD0837 whereas the release of AZD0837 was found to be slower and incomplete from conventional direct compressed ER hydrophilic matrix tablets. Results clearly indicated that AZD0837 remained amorphous throughout the dissolution process and was maintained in a supersaturated state and hence kept stable with the aid of the polymeric carrier when released in a synchronized manner. In addition, it was found that the IM tablets were robust to variation in hydrodynamics of the environment and PEO molecular weight. / The research was funded by AstraZeneca, Sweden.