Pubmed du 07/05/18

lundi 7 mai 2018

1. Abbas H, Garberson F, Glover E, Wall DP. Machine learning approach for early detection of autism by combining questionnaire and home video screening. Journal of the American Medical Informatics Association : JAMIA. 2018.

Background : Existing screening tools for early detection of autism are expensive, cumbersome, time- intensive, and sometimes fall short in predictive value. In this work, we sought to apply Machine Learning (ML) to gold standard clinical data obtained across thousands of children at-risk for autism spectrum disorder to create a low-cost, quick, and easy to apply autism screening tool. Methods : Two algorithms are trained to identify autism, one based on short, structured parent-reported questionnaires and the other on tagging key behaviors from short, semi-structured home videos of children. A combination algorithm is then used to combine the results into a single assessment of higher accuracy. To overcome the scarcity, sparsity, and imbalance of training data, we apply novel feature selection, feature engineering, and feature encoding techniques. We allow for inconclusive determination where appropriate in order to boost screening accuracy when conclusive. The performance is then validated in a controlled clinical study. Results : A multi-center clinical study of n = 162 children is performed to ascertain the performance of these algorithms and their combination. We demonstrate a significant accuracy improvement over standard screening tools in measurements of AUC, sensitivity, and specificity. Conclusion : These findings suggest that a mobile, machine learning process is a reliable method for detection of autism outside of clinical settings. A variety of confounding factors in the clinical analysis are discussed along with the solutions engineered into the algorithms. Final results are statistically limited and will benefit from future clinical studies to extend the sample size.

Lien vers le texte intégral (Open Access ou abonnement)

2. Akhavan Aghdam M, Sharifi A, Pedram MM. Combination of rs-fMRI and sMRI Data to Discriminate Autism Spectrum Disorders in Young Children Using Deep Belief Network. Journal of digital imaging. 2018.

In recent years, the use of advanced magnetic resonance (MR) imaging methods such as functional magnetic resonance imaging (fMRI) and structural magnetic resonance imaging (sMRI) has recorded a great increase in neuropsychiatric disorders. Deep learning is a branch of machine learning that is increasingly being used for applications of medical image analysis such as computer-aided diagnosis. In a bid to classify and represent learning tasks, this study utilized one of the most powerful deep learning algorithms (deep belief network (DBN)) for the combination of data from Autism Brain Imaging Data Exchange I and II (ABIDE I and ABIDE II) datasets. The DBN was employed so as to focus on the combination of resting-state fMRI (rs-fMRI), gray matter (GM), and white matter (WM) data. This was done based on the brain regions that were defined using the automated anatomical labeling (AAL), in order to classify autism spectrum disorders (ASDs) from typical controls (TCs). Since the diagnosis of ASD is much more effective at an early age, only 185 individuals (116 ASD and 69 TC) ranging in age from 5 to 10 years were included in this analysis. In contrast, the proposed method is used to exploit the latent or abstract high-level features inside rs-fMRI and sMRI data while the old methods consider only the simple low-level features extracted from neuroimages. Moreover, combining multiple data types and increasing the depth of DBN can improve classification accuracy. In this study, the best combination comprised rs-fMRI, GM, and WM for DBN of depth 3 with 65.56% accuracy (sensitivity = 84%, specificity = 32.96%, F1 score = 74.76%) obtained via 10-fold cross-validation. This result outperforms previously presented methods on ABIDE I dataset.

Lien vers le texte intégral (Open Access ou abonnement)

3. Bishop-Fitzpatrick L, Movaghar A, Greenberg JS, Page D, DaWalt LS, Brilliant MH, Mailick MR. Using machine learning to identify patterns of lifetime health problems in decedents with autism spectrum disorder. Autism Res. 2018.

Very little is known about the health problems experienced by individuals with autism spectrum disorder (ASD) throughout their life course. We retrospectively analyzed diagnostic codes associated with de-identified electronic health records using a machine learning algorithm to characterize diagnostic patterns in decedents with ASD and matched decedent community controls. Participants were 91 decedents with ASD and 6,186 sex and birth year matched decedent community controls who had died since 1979, the majority of whom were middle aged or older adults at the time of their death. We analyzed all ICD-9 codes, V-codes, and E-codes available in the electronic health record and Elixhauser comorbidity categories associated with those codes. Diagnostic patterns distinguished decedents with ASD from decedent community controls with 75% sensitivity and 94% specificity solely based on their lifetime ICD-9 codes, V-codes, and E-codes. Decedents with ASD had higher rates of most conditions, including cardiovascular disease, motor problems, ear problems, urinary problems, digestive problems, side effects from long-term medication use, and nonspecific lab tests and encounters. In contrast, decedents with ASD had lower rates of cancer. Findings suggest distinctive lifetime diagnostic patterns among decedents with ASD and highlight the need for more research on health outcomes across the lifespan as the population of individuals with ASD ages. As a large wave of individuals with ASD diagnosed in the 1990s enters adulthood and middle age, knowledge about lifetime health problems will become increasingly important for care and prevention efforts. Autism Res 2018. (c) 2018 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY : This study looked at patterns of lifetime health problems to find differences between people with autism who had died and community controls who had died. People with autism had higher rates of most health problems, including cardiovascular, urinary, respiratory, digestive, and motor problems, in their electronic health records. They also had lower rates of cancer. More research is needed to understand these potential health risks as a large number of individuals with autism enter adulthood and middle age.

Lien vers le texte intégral (Open Access ou abonnement)

4. Kanne SM, Carpenter LA, Warren Z. Screening in toddlers and preschoolers at risk for autism spectrum disorder : Evaluating a novel mobile-health screening tool. Autism Res. 2018.

There are many available tools with varying levels of accuracy designed to screen for Autism Spectrum Disorder (ASD) in young children, both in the general population and specifically among those referred for developmental concerns. With burgeoning waitlists for comprehensive diagnostic ASD assessments, finding accurate methods and tools for advancing diagnostic triage becomes increasingly important. The current study compares the efficacy of four oft used paper and pencil measures, the Modified Checklist for Autism in Toddlers Revised with Follow-up, the Social Responsiveness Scale, Second Edition, and the Social Communication Questionnaire, and the Child Behavior Checklist to a novel mobile-health screening tool developed by Cognoa, Inc. (Cognoa) in a group of children 18-72 months of age. The Cognoa tool may have potential benefits as it integrates a series of parent-report questions with remote clinical ratings of brief video segments uploaded via parent’s smartphones to calculate level of ASD risk. Participants were referred to one of three tertiary care diagnostic centers for ASD-related concerns (n = 230) and received a best estimate ASD diagnosis. Analysis and comparison of psychometric properties indicated potential advantages for Cognoa within this clinical sample across age ranges not often covered by another single measure/tool. Autism Res 2018. (c) 2018 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY : With the wait times getting longer for comprehensive Autism Spectrum Disorder (ASD) diagnostic assessments, it is becoming increasingly important to find accurate tools to screen for ASD. The current study compares four screening measures that have been in use for some time to a novel mobile-health screening tool, called Cognoa. The Cognoa tool is novel because it integrates parent-report questions with clinical ratings of brief video segments uploaded via parent’s smartphones to calculate ASD risk. Two hundred thirty children who were referred to one of three ASD specialty diagnostic centers to see if they had ASD participated in the study. A direct comparison indicated potential advantages for Cognoa not often covered by another single measure/tool.

Lien vers le texte intégral (Open Access ou abonnement)

5. Lassalle A, Zurcher NR, Porro CA, Benuzzi F, Hippolyte L, Lemonnier E, Asberg Johnels J, Hadjikhani N. Influence of anxiety and alexithymia on brain activations associated with the perception of others’ pain in autism. Social neuroscience. 2018 : 1-19.

The circumstances under which empathy is altered in ASD remain unclear, as previous studies did not systematically find differences in brain activation between ASD and controls in empathy-eliciting paradigms, and did not always monitor whether differences were primarily due to ASD "per se", or to conditions overlapping with ASD, such as alexithymia and anxiety. Here, we collected fMRI data from 47 participants (22 ASD) viewing pictures depicting hands and feet of unknown others in painful, disgusting, or neutral situations. We computed brain activity for painful and disgusting stimuli (vs. neutral) in whole brain and in regions of interest among the brain areas typically activated during the perception of nociceptive stimuli. Group differences in brain activation disappeared when either alexithymia or anxiety - both elevated in the ASD group - were controlled for. Regression analyses indicated that the influence of symptoms was mainly shared between autistic symptomatology, alexithymia and anxiety or driven by unique contributions from alexithymia or anxiety. Our results suggest that affective empathy may be affected in ASD, but that this association is complex. The respective contribution of alexithymia and anxiety to decreased affective empathy of people with ASD may be due to the association of those psychiatric conditions with reduced motor resonance/Theory of Mind.

Lien vers le texte intégral (Open Access ou abonnement)

6. Mason D, McConachie H, Garland D, Petrou A, Rodgers J, Parr JR. Predictors of quality of life for autistic adults. Autism Res. 2018.

Research with adults on the autism spectrum is as yet limited in scope and quality. The present study describes quality of life (QoL) of a large sample of autistic adults in the UK and investigates characteristics that may be predictive of QoL. A total of 370 autistic adults from the Adult Autism Spectrum Cohort-UK (ASC-UK) completed the WHOQoL-BREF, and the Social Responsiveness Scale (SRS, autism symptom severity), along with the ASC-UK registration questionnaire giving information on mental health and their life situation. QoL for autistic adults was lower than for the general population for each WHOQoL domain. Younger participants reported higher QoL than older participants in psychological and environment domains. Males reported higher physical QoL than females, and females reported higher social QoL than males. Significant positive predictors of QoL were : being employed (physical QoL), receiving support (social and environment QoL), and being in a relationship (social QoL). Having a mental health condition and higher SRS total score were negative predictors of QoL across all four domains. Autistic adults require access to effective mental health interventions, and informal and formal support for their social difficulties, to improve their quality of life. Autism Res 2018. (c) 2018 The Authors Autism Research published by International Society for Autism Research and Wiley Periodicals, Inc. LAY SUMMARY : There has been limited research into the lived experience of autistic adults. Using the World Health Organization quality of life measure, we found that autistic people (370) in the UK reported their quality of life to be lower than that of the general population. Better quality of life was associated with being in a relationship ; those with a mental health condition had poorer quality of life. This research suggests some ways in which autistic people can be helped to improve their quality of life.

Lien vers le texte intégral (Open Access ou abonnement)

7. Nystrom P, Gliga T, Nilsson Jobs E, Gredeback G, Charman T, Johnson MH, Bolte S, Falck-Ytter T. Enhanced pupillary light reflex in infancy is associated with autism diagnosis in toddlerhood. Nat Commun. 2018 ; 9(1) : 1678.

Autism spectrum disorder (ASD) is a neurodevelopmental condition affecting around 1% of the population. We previously discovered that infant siblings of children with ASD had stronger pupillary light reflexes compared to low-risk infants, a result which contrasts sharply with the weak pupillary light reflex typically seen in both children and adults with ASD. Here, we show that on average the relative constriction of the pupillary light reflex is larger in 9-10-month-old high risk infant siblings who receive an ASD diagnosis at 36 months, compared both to those who do not and to low-risk controls. We also found that the magnitude of the pupillary light reflex in infancy is associated with symptom severity at follow-up. This study indicates an important role of sensory atypicalities in the etiology of ASD, and suggests that pupillometry, if further developed and refined, could facilitate risk assessment in infants.

Lien vers le texte intégral (Open Access ou abonnement)

8. Takamuku S, Forbes PAG, Hamilton AFC, Gomi H. Typical use of inverse dynamics in perceiving motion in autistic adults : Exploring computational principles of perception and action. Autism Res. 2018.

There is increasing evidence for motor difficulties in many people with autism spectrum condition (ASC). These difficulties could be linked to differences in the use of internal models which represent relations between motions and forces/efforts. The use of these internal models may be dependent on the cerebellum which has been shown to be abnormal in autism. Several studies have examined internal computations of forward dynamics (motion from force information) in autism, but few have tested the inverse dynamics computation, that is, the determination of force-related information from motion information. Here, we examined this ability in autistic adults by measuring two perceptual biases which depend on the inverse computation. First, we asked participants whether they experienced a feeling of resistance when moving a delayed cursor, which corresponds to the inertial force of the cursor implied by its motion-both typical and ASC participants reported similar feelings of resistance. Second, participants completed a psychophysical task in which they judged the velocity of a moving hand with or without a visual cue implying inertial force. Both typical and ASC participants perceived the hand moving with the inertial cue to be slower than the hand without it. In both cases, the magnitude of the effects did not differ between the two groups. Our results suggest that the neural systems engaged in the inverse dynamics computation are preserved in ASC, at least in the observed conditions. Autism Res 2018. (c) 2018 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY : We tested the ability to estimate force information from motion information, which arises from a specific "inverse dynamics" computation. Autistic adults and a matched control group reported feeling a resistive sensation when moving a delayed cursor and also judged a moving hand to be slower when it was pulling a load. These findings both suggest that the ability to estimate force information from motion information is intact in autism.

Lien vers le texte intégral (Open Access ou abonnement)

9. van der Miesen AIR, Hurley H, Bal AM, de Vries ALC. Prevalence of the Wish to be of the Opposite Gender in Adolescents and Adults with Autism Spectrum Disorder. Archives of sexual behavior. 2018.

Several studies have suggested an overrepresentation of (symptoms of) autism spectrum disorder (ASD) among individuals with gender dysphoria. Three studies have taken the inverse approach in children with ASD and showed increased parent report of the wish to be of the opposite gender in this group. This study compared the self-reported wish to be of the opposite gender (one item of the Youth Self-Report [YSR] and the Adult Self-Report [ASR]) of 573 adolescents (469 assigned boys and 104 assigned girls) and 807 adults (616 assigned males and 191 assigned females) with ASD to 1016 adolescents and 846 adults from the general population. Emotional and behavioral problems were measured by the DSM-oriented scales of the YSR and ASR. In addition, the Children’s Social Behavior Questionnaire and the Adult Social Behavior Questionnaire were used to measure specific subdomains of the ASD spectrum to test whether specific subdomains of ASD were particularly involved. Significantly more adolescents (6.5%) and adults (11.4%) with ASD endorsed this item as compared to the general population (3-5%). In adolescents, assigned girls endorsed this item more than assigned boys. No significant gender differences were found in the adults with ASD. In addition, on all DSM-oriented scales of both the YSR and ASR, adolescents and adults with ASD who endorsed the gender item had significantly higher scores compared to those without. There were no significant associations between endorsement of the gender item and any specific subdomain of ASD, providing no evidence for a sole role of one of the ASD subdomains and endorsement of the wish to be the opposite gender.

Lien vers le texte intégral (Open Access ou abonnement)


Accès direct au catalogue en ligne !

Vous pouvez accéder directement au catalogue en ligne du centre de documentation du CRA Rhône-Alpes en cliquant sur l’image ci-dessous :

Cliquez pour consulter le catalogue

Formations pour les Familles et les Proches

le détail des programmes de formation à l’attention des familles et des proches de personnes avec TSA est disponible en cliquant sur l’image ci-dessous.

Formation pour les Aidants Familiaux {JPEG}

Sensibilisation à l’usage des tablettes au CRA !

Toutes les informations concernant les sensibilisations du CRA aux tablettes numériques en cliquant sur l’image ci-dessous :

1-Formation à l’état des connaissances de l’autisme

Plus d’information sur la formation gratuite que dispense le CRA en cliquant sur l’image ci-dessous :

Formation à l'état des connaissances de l'autisme {JPEG}

4-Livret Autisme Rhône-Alpes® (LARA) - Message à l’attention des directeurs

Prenez connaissance du Livret Autisme Rhône-Alpes, projet de répertoire régional des structures médico-sociales. En cliquant sur l’image ci-dessous :

Cliquez sur l'image pour découvrir le Livret LARA