Natural Language Processing and Machine Learning Supporting the Work of a Psychologist and Its Evaluation on the Example of Support for Psychological Diagnosis of Anorexia

Objective: This study sought to address the use of computer-aided diagnosis and therapy for anorexia nervosa. This paper presents the means by which the use of natural language processing methods can augment the work of psychologists. Method: We evaluated this method based on its efficacy when diagnosing anorexia nervosa. Using natural language processing and machine learning, we developed methods for analyzing five basic emotions, analyzing a patient’s body perception, and detecting six potential areas of difficulties for computer support of psychological diagnosis of anorexia. We surveyed 43 psychologists to obtain feedback on these tools. Results: We evaluated efficacy in terms of patient relationship, substantive aspects of the diagnosis, and diagnostic procedures. In terms of patient relationship, we found a noticeable decrease in the patient’s resistance and better support in verifying the substantive scope of the diagnostic thesis. Discussion: The presented methods can be a supporting tool for monitoring the diagnostic process and increasing the degree of self-diagnosis and self-reflection by the patient. This tool can increase the accuracy of the diagnostic process by reducing patient resistance. This will increase access to the patient’s psychopathology.

Person-Oriented Research Ethics to Address the Needs of Participants on the Autism Spectrum

Research ethics scholarship often attends to vulnerability. People with autism may be vulnerable in research, but are also vulnerable to unjust exclusion from participation. Addressing the needs of participants with autism can facilitate inclusion and honor the bioethics principle of respect for persons while accounting for risk and vulnerability. Drawing from a review of the literature and informed by a moral deliberation process involving a task force of stakeholders (including autistic people and parents of autistic people), we use the model of person-oriented research ethics to identify several practical strategies researchers can use to address these needs and foster inclusion. Strategies include using multiple means of communication, addressing the sensory environment, preparing participants in advance, and accounting for social context. These practical strategies are not just methodological or design choices; they are inherently related to ethical issues. Method and design choices fulfill ethical aspirations by facilitating inclusion, reducing discomfort, and focusing on individuals.

"My cheeks get red and my brain gets scared": A computer assisted interview to explore experiences of anxiety in young children on the autism spectrum

BACKGROUND

Anxiety symptoms are common in children on the autism spectrum and may be present at an early age. While a multi-informant approach is considered best practice in the assessment of anxiety, self-reports from young children on the autism spectrum are rarely included.

AIMS

The aim of this study was to utilise a computer-assisted interview procedure incorporating visual prompts to elicit the viewpoints of children about their experiences of anxiety.

METHODS AND PROCEDURES

Ten children aged 5-8 years who were diagnosed on the autism spectrum completed the interview. Directed content analysis was used to explore the data generated in the interview.

OUTCOMES AND RESULTS

A wide range of situations that trigger anxiety, and responses to anxiety, were reported across the participant group. These responses may be unrecognised as anxiety by others. The children provided positive feedback on the use of the computer-assisted interview.

CONCLUSIONS AND IMPLICATIONS

The child's own self-report can inform parents and professionals of the situations which make them more or less anxious and the behaviours that they use to communicate their anxiety in that specific situation. The use of a computer-assisted interview may be an effective method to support self-report of anxiety-related experiences for young children on the autism spectrum.

Person-oriented ethics for autism research: Creating best practices through engagement with autism and autistic communities

Research ethics is an important part of any study. Ethics goes beyond ethics committee approval and consent documents. It addresses broader issues of respect, inclusion, and empowerment in the everyday context of research. This article focuses on everyday aspects of research ethics for studies involving autistic participants. It draws on a review of the literature and a process of ethical deliberation involving a task force of researchers, professionals, autistic self-advocates, and parents. These methods led to the creation of suggestions for researchers. This article describes the community engagement process, briefly presents the task force suggestions, and provides more detailed discussion of select items for illustration. Suggestions are organized around five “person-oriented research ethics” guideposts: (1) individualization (e.g. providing individualized support for participants), (2) acknowledgment of lived world (e.g. acknowledging barriers to care that impact research ethics), (3) empowerment in decision-making (e.g. creating accessible consent processes that address specific communication needs), (4) respect for holistic personhood (e.g. addressing sensory and processing needs and strengths), and (5) focus on researcher–participant relationships (e.g. involving autistic people in ways other than research participants, including but not limited to via participatory research). This project highlights the value of researcher–community partnerships in discussions about research ethics.

Lay abstract

Research ethics means issues that concern the welfare and wellbeing of people who take part in research. It is important in all scientific studies. Ethics helps people who do research treat people who take part in research fairly and with respect. This article is about day-to-day ethics when autistic people take part in research. We present tips for researchers who want to do this type of study. We used two methods to create these tips. First, we wanted to know what other people said about this topic. We used a literature review to find out. Second, we wanted to know what autistic people, parents, and professionals thought, and had a working group meet to discuss it. The working group provided advice that researchers could consider around day-to-day ethics in research. This article talks about these methods and advice. The advice fits into five big groups: Tailor the research process for the unique needs of each person. Think about the world in which people who take part in research live. Make it easier for people to make their own choices. Value what people who take part in research have to share and consider their needs and strengths. Think about how researchers and people who take part in research work together. This project shows why it is useful for researchers and communities to talk about research ethics together.

Exploring Anxiety at Home, School, and in the Community Through Self-Report From Children on the Autism Spectrum

Research investigating anxiety in children on the autism spectrum usually reports caregiver rather than self-report perspectives. This study aimed to document children's own descriptions of their anxiety symptomatology by combining profiles on a standardized autism-specific self-report measure of anxiety (ASC-ASD-C) with the answers from closed- and open-answer questions about anxiety across home, school, and community settings. Across the sample of 113 children on the spectrum aged 6-14 years, the two most frequently endorsed items on the ASC-ASD-C were from the Uncertainty and Performance Anxiety subscales, and the least endorsed were both from the Anxious Arousal subscale. Almost all (96.5%) of the children on the spectrum reported experiencing anxiety in at least one setting, with 40.7% reporting anxiety in all three contexts (home, school, and community). Approximately half of the sample felt their anxiety goes unrecognized by others at school and almost 60% felt it was unrecognized by others when out in the community. The proportion of children reporting having someone to help reduce their anxiety differed across home (86%), school (76%), and community (45%) settings. This highlights the importance of understanding anxiety and its impact, not only within the context of autism but also for each particular child. Autism Res 2020, 13: 603-614. © 2019 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: There has been a lot of research focusing on anxiety and autism, but most of it has used parent reports, rather than asking the child themselves. This study summarizes data from 113 children on the autism spectrum, aged 6-14 years. It reports the symptoms of anxiety that these children most and least commonly experience. The results suggest only 40-50% of children feel that others are able to recognize their anxiety at school and when out in the community, suggesting that more training is needed to help adults in these settings to recognize and support anxiety.

The school experiences of bilingual children on the autism spectrum: An interpretative phenomenological analysis

BACKGROUND

With growing numbers of bilingual children on the autism spectrum in UK classrooms, the interaction between autism and bilingualism is becoming a pressing issue for practitioners, researchers and families. In this study, we report the school experiences of bilingual, autistic children in the UK through their own voice with focus on five aspects of their school life.

METHOD

Using interpretative phenomenological analysis (IPA) as a methodological framework, semi-structured, computer-assisted interviews were conducted with 11 children aged 7 to 14 from across England and Wales. Interviews were carried out in English and took place in mainstream schools or the children's home, depending on their preference.

RESULTS

Results indicate that, while children's school experiences vary widely, there were commonalities in this population's identity formation, including being bilingual, and their classroom experiences. Most notably, children educated in more multilingual environments (i.e. in schools with larger multilingual populations) expressed more positive views about multilingualism than those in more monolingual settings. In line with previous studies, limited social circles and classroom anxiety were present in participants' school experiences.

IMPLICATIONS

The findings of this paper suggest that giving autistic children from bilingual backgrounds opportunities to explore their linguistic identities in the classroom may enhance their experiences of school. Further research should focus on parents' and practitioners' attitudes and perspectives towards the support available for this population.

The computer-assisted interview In My Shoes can benefit shy preschool children's communication

Interviewing children is a cognitively, socially, and emotionally challenging situation, especially for young and shy children. Thus, finding methods that aid rapport and increase these children's communication is important. The present study investigated whether children's verbal and non-verbal communicative behavior developed differently during the rapport phase, depending on whether children were situationally shy or not, and whether the interview was conducted using the computer-assisted interview In My Shoes (IMS) or a Standard verbal interview. The sample consisted of 60 children aged 4 to 5-years-old. The results showed that for the shy children in the IMS group their talkativeness increased and their answer latency decreased including the amount of encouragement the child needed to talk, while no changes were observed for the shy children in the Standard verbal interview group. There were no significant differences in the non-verbal behavior for the shy children regardless of the interview method used. For the non-shy children, overall, the interview method did not affect either the verbal or the non-verbal outcomes. Our findings indicate that IMS can be a useful tool during the rapport-building phase with shy children as it helps these children to improve their verbal communication.

In My Shoes - Validation of a computer assisted approach for interviewing children

Interviewing young children presents a challenge because they tend to provide incomplete accounts and are easily misled. Therefore there is a need for techniques to improve young children's recall, while maintaining accuracy and increasing completeness. The computer-assisted interview In My Shoes (IMS) is an aid that potentially offers a way for young children to provide accounts of their experiences. This study examined the validity of IMS, by comparing it with a forensic best practice interview approach using a real-life clinical situation to ensure high ecological validity. Children were randomly assigned to either method and both accuracy and completeness of statements made by 4- and 5-year-olds (N=54) regarding a video-documented health check-up were assessed. The In My Shoes interviews were as good as best practice interviews on all accuracy measures for both age groups, except for object accuracy that was better in the forensic interview condition. Events description completeness was similar in both interview conditions; however, IMS interviews generated more complete statements about people present at the visit. The findings suggest that the IMS approach yields comparable results to a best practice interview, and it can be used as an alternative aid in child interviews.

'I felt a little bubbly in my tummy': eliciting pre-schoolers' accounts of their health visit using a computer-assisted interview method

BACKGROUND

In the health care services, children's rights to participate in all matters that concern them are considered important. However, in practice this can be challenging with young children. In My Shoes (IMS) is a computer-assisted interview tool developed to help children talk about their experiences. The aim of the study was to evaluate the IMS' ability to elicit pre-schoolers' subjective experiences and accurate accounts of a routine health visit as well as the children's engagement in the interview process.

METHODS

Interviews were conducted with 23 children aged 4-5 years, 2-4 weeks after their health visit. The interviews were transcribed verbatim and analysed using a method inspired by Content Analysis to evaluate IMS's ability to elicit accounts about subjective experiences. Accurate accounts were assessed by comparing the transcribed interviews with the filmed visits at the child health centre. The children's engagement was defined by the completion and length of the interviews, and the children's interaction with the software.

RESULTS

All children gave accounts about their subjective experiences, such as their emotional state during the visit, available toys or rewards they received. All children related to the correct event, they all named at least one person who was present and 87% correctly named at least one examination procedure. The majority of children (91%) completed the interview, which lasted 17-39 min (M = 24), and 96% interacted with the IMS software.

CONCLUSIONS

IMS was feasible to help children describe their health care experiences, in both detail and depth. The children interacted with the software and maintained their interest for an extended period of time.

Utility of the International Classification of Functioning, Disability and Health (ICF) for educational psychologists' work

Despite embracing a bio-psycho-social perspective, the World Health Organization's International Classification of Functioning, Disability and Health (ICF) assessment framework has had limited application to date with children who have special educational needs (SEN). This study examines its utility for educational psychologists' work with children who have Autism Spectrum Disorders (ASD). Mothers of 40 children with ASD aged eight to 12 years were interviewed using a structured protocol based on the ICF framework. The Diagnostic Interview for Social and Communication Disorder (DISCO) was completed with a subset of 19 mothers. Internal consistency and inter-rater reliability of the interview assessments were found to be acceptable and there was evidence for concurrent and discriminant validity. Despite some limitations, initial support for the utility of the ICF model suggests its potential value across educational, health and care fields. Further consideration of its relevance to educational psychologists in new areas of multi-agency working is warranted.