Automating autism assessment: What <scp>AI</scp> can bring to the diagnostic process

Erden, Yasemin J.; Hummerstone, Harriet; Rainey, Stephen

doi:10.1111/jep.13527

Cited by 12 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Less optimistically, Miller proposed scrapping the DSM and replacing it with a diagnostic manual that simply documents complexity ( 81 ). But because the heterogeneity of autism symptoms and causes and comorbidities reflects a very complex web of relationships, it might be that only advanced artificial intelligence ( 82 , 83 ) will be able to discover clearly defined significant subgroups with explanatory power for the creation of effective drug regimens and effective behavioral treatments.…”

Section: Discussionmentioning

confidence: 99%

Heterogeneity thwarts autism explanatory power: A proposal for endophenotypes

Waterhouse

2022

Front. Psychiatry

View full text Add to dashboard Cite

Many researchers now believe that autism heterogeneity is likely to include many disorders, but most research is based on samples defined by the DSM-5 Autism Spectrum Disorder (ASD) criteria. However, individuals diagnosed with autism have complex and varied biological causes for their symptoms. Therefore, autism is not a unitary biological entity. And although autism is significantly different from typical development, autism is not a unitary clinical disorder because diagnosed individuals vary in symptom patterns, comorbidities, biomarkers, and gene variants. The DSM-5 ASD criteria were designed to reduce heterogeneity, and there have been many other efforts to reduce autism heterogeneity including using more stringent clinical criteria, dividing autism into low and high functioning groups, creating subgroups, and by studying larger samples. However, to date these efforts have not been successful. Heterogeneity is extensive and remains unexplained, and no autism pathophysiology has been discovered. Most importantly, heterogeneity has hindered the explanatory power of the autism diagnosis to discover drug regimens and effective behavioral treatments. The paper proposes that possible transdiagnostic endophenotypes may reduce autism heterogeneity. Searching for transdiagnostic endophenotypes requires exploring autism symptoms outside of the framework of the DSM-5 autism diagnosis. This paper proposes that researchers relax diagnostic criteria to increase the range of phenotypes to support the search for transdiagnostic endophenotypes. The paper proposes possible candidates for transdiagnostic endophenotypes. These candidates are taken from DSM-5 ASD criteria, from concepts that have resulted from researched theories, and from symptoms that are the result of subtyping. The paper then sketches a possible basis for a future transdiagnostic endophenotypes screening tool that includes symptoms of autism and other neurodevelopmental disorders.

show abstract

Section: Discussionmentioning

confidence: 99%

Heterogeneity thwarts autism explanatory power: A proposal for endophenotypes

Waterhouse

2022

Front. Psychiatry

View full text Add to dashboard Cite

show abstract

“…According to the latest statistics from NHS Digital dated August 2020, people over 18 waiting for referral and diagnosis between April 2019 and January 2020 waited for an average of 361 days from first contact with a doctor for diagnosis. The older the patient, the longer the diagnostic process took, with those aged 45-54 and 55-64 waiting for an average of 480 days [74].…”

Section: Benefits Associated With the Use Of Artificial Intelligencementioning

confidence: 99%

Application of artificial intelligence tools in diagnosis and treatmentof mental disorders

KISTER

Jakub

Makarewicz

et al. 2023

Curr Probl Psychiatry

View full text Add to dashboard Cite

Introduction: Artificial intelligence research is increasing its application in mental health services. Machine learning, deep learning, semantic analysis in the form of transcriptions of patients' statements enable early diagnosis of psychotic disorders, ADHD, anorexia nervosa. Of great importance are the so-called digital therapists. This paper aims to show the use of AI tools in diagnosing, treating, the benefits and limitations associated with mental disorders. Material and methodS: This literature review was conducted by searching scientific articles from 2015 to 2022. The basis were PubMED, OpenKnowledge, Web of Science, using the following keywords: artificial intelligence, digital therapy, psychiatry, machine learning. Results: A review indicates the widespread use of AI tools in screening for mental disorders. These tools advance the clinical diagnosis medical specialists make up for several years. They impact solving medical staff shortages, lack of access to medical facilities and leveling patient resistance to treatment. The benefits are ultra-fast analysis of large sets of information, effective screening of people in need of specialized psychiatric care, reduction of doctors' duties and maximization of their work efficiency. During the current COVID 19 pandemic, robots in the form of digital psychotherapists are playing a special role. Conclusions: The need for further research, testing and clarification of regulations related to the use of AI tools is indicated. Ethical and social problems need to be resolved. The tools should not form the basis of autonomous therapy without the supervision of highly trained professionals. Human beings should be at the center of analysis just as their health and well-being. Keywords: artificial intelligence, digital therapy, psychiatry, machine learning

show abstract

“…However, despite that machine learning offers promising solutions for ASD diagnosis and is becoming complementary to the clinician-led diagnostic processes, its performance largely depends on the amount and quality of the historical data for model training. In many cases, machine learning simply represents "the same biases, conceptual flaws, and practical weaknesses evident in existing diagnostic processes" of the historical data generated (80). Therefore, the application in clinical settings is still limited and in development.…”

Section: Machine Learning Tools For Future Studies and Therapeutic Treatment Developmentmentioning

confidence: 99%

Autism Spectrum Disorders: The Mitochondria Connection

Wen

Yao

2021

Autism Spectrum Disorders

View full text Add to dashboard Cite

Autism spectrum disorders (ASD) are considered neurodevelopmental disorders characterized by restricted patterns of behavior and difficulties with communication and social interaction.Cumulative evidence suggests ASD have a wide range of co-occurring multisystemic conditions beyond the primary diagnosis. However, the etiology of ASD still eludes us. Finding a key cellular process responsible for the cognitive features, specific behaviors, and abnormalities in multiple systems presents major challenges to researchers. Mitochondria are multifaceted organelles involved in many cellular functions. The relationship between mitochondria and ASD has been studied for many years. Mitochondria may play a crucial role in ASD pathophysiology. By reviewing the connections between mitochondria and ASD from genes, pathways, biological activities, and clinical manifestations, we hope to provide clues for future studies that elucidate the biological basis of ASD symptoms and behaviors.

show abstract

Automating autism assessment: What AI can bring to the diagnostic process

Cited by 12 publications

References 41 publications

Heterogeneity thwarts autism explanatory power: A proposal for endophenotypes

Heterogeneity thwarts autism explanatory power: A proposal for endophenotypes

Application of artificial intelligence tools in diagnosis and treatmentof mental disorders

Autism Spectrum Disorders: The Mitochondria Connection

Contact Info

Product

Resources

About