Early detection of autism using digital behavioral phenotyping. Perochon, S., Di Martino, J. M., Carpenter, K. L. H., Compton, S., Davis, N., Eichner, B., Espinosa, S., Franz, L., Krishnappa Babu, P. R., Sapiro, G., & Dawson, G. Nature Medicine, 29(10):2489–2497, Nature Publishing Group, October, 2023. Number: 10![Early detection of autism using digital behavioral phenotyping [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Early detection of autism, a neurodevelopmental condition associated with challenges in social communication, ensures timely access to intervention. Autism screening questionnaires have been shown to have lower accuracy when used in real-world settings, such as primary care, as compared to research studies, particularly for children of color and girls. Here we report findings from a multiclinic, prospective study assessing the accuracy of an autism screening digital application (app) administered during a pediatric well-child visit to 475 (17–36 months old) children (269 boys and 206 girls), of which 49 were diagnosed with autism and 98 were diagnosed with developmental delay without autism. The app displayed stimuli that elicited behavioral signs of autism, quantified using computer vision and machine learning. An algorithm combining multiple digital phenotypes showed high diagnostic accuracy with the area under the receiver operating characteristic curve = 0.90, sensitivity = 87.8%, specificity = 80.8%, negative predictive value = 97.8% and positive predictive value = 40.6%. The algorithm had similar sensitivity performance across subgroups as defined by sex, race and ethnicity. These results demonstrate the potential for digital phenotyping to provide an objective, scalable approach to autism screening in real-world settings. Moreover, combining results from digital phenotyping and caregiver questionnaires may increase autism screening accuracy and help reduce disparities in access to diagnosis and intervention.
@article{perochon_early_2023,
title = {Early detection of autism using digital behavioral phenotyping},
volume = {29},
copyright = {2023 The Author(s)},
issn = {1546-170X},
url = {https://www.nature.com/articles/s41591-023-02574-3},
doi = {10.1038/s41591-023-02574-3},
abstract = {Early detection of autism, a neurodevelopmental condition associated with challenges in social communication, ensures timely access to intervention. Autism screening questionnaires have been shown to have lower accuracy when used in real-world settings, such as primary care, as compared to research studies, particularly for children of color and girls. Here we report findings from a multiclinic, prospective study assessing the accuracy of an autism screening digital application (app) administered during a pediatric well-child visit to 475 (17–36 months old) children (269 boys and 206 girls), of which 49 were diagnosed with autism and 98 were diagnosed with developmental delay without autism. The app displayed stimuli that elicited behavioral signs of autism, quantified using computer vision and machine learning. An algorithm combining multiple digital phenotypes showed high diagnostic accuracy with the area under the receiver operating characteristic curve = 0.90, sensitivity = 87.8\%, specificity = 80.8\%, negative predictive value = 97.8\% and positive predictive value = 40.6\%. The algorithm had similar sensitivity performance across subgroups as defined by sex, race and ethnicity. These results demonstrate the potential for digital phenotyping to provide an objective, scalable approach to autism screening in real-world settings. Moreover, combining results from digital phenotyping and caregiver questionnaires may increase autism screening accuracy and help reduce disparities in access to diagnosis and intervention.},
language = {en},
number = {10},
urldate = {2023-10-26},
journal = {Nature Medicine},
publisher = {Nature Publishing Group},
author = {Perochon, Sam and Di Martino, J. Matias and Carpenter, Kimberly L. H. and Compton, Scott and Davis, Naomi and Eichner, Brian and Espinosa, Steven and Franz, Lauren and Krishnappa Babu, Pradeep Raj and Sapiro, Guillermo and Dawson, Geraldine},
month = oct,
year = {2023},
note = {Number: 10},
keywords = {Disability, Machine learning},
pages = {2489--2497},
}
Downloads: 0
{"_id":"cBqhMKWthJBX5Hy9u","bibbaseid":"perochon-dimartino-carpenter-compton-davis-eichner-espinosa-franz-etal-earlydetectionofautismusingdigitalbehavioralphenotyping-2023","author_short":["Perochon, S.","Di Martino, J. M.","Carpenter, K. L. H.","Compton, S.","Davis, N.","Eichner, B.","Espinosa, S.","Franz, L.","Krishnappa Babu, P. R.","Sapiro, G.","Dawson, G."],"bibdata":{"bibtype":"article","type":"article","title":"Early detection of autism using digital behavioral phenotyping","volume":"29","copyright":"2023 The Author(s)","issn":"1546-170X","url":"https://www.nature.com/articles/s41591-023-02574-3","doi":"10.1038/s41591-023-02574-3","abstract":"Early detection of autism, a neurodevelopmental condition associated with challenges in social communication, ensures timely access to intervention. Autism screening questionnaires have been shown to have lower accuracy when used in real-world settings, such as primary care, as compared to research studies, particularly for children of color and girls. Here we report findings from a multiclinic, prospective study assessing the accuracy of an autism screening digital application (app) administered during a pediatric well-child visit to 475 (17–36 months old) children (269 boys and 206 girls), of which 49 were diagnosed with autism and 98 were diagnosed with developmental delay without autism. The app displayed stimuli that elicited behavioral signs of autism, quantified using computer vision and machine learning. An algorithm combining multiple digital phenotypes showed high diagnostic accuracy with the area under the receiver operating characteristic curve = 0.90, sensitivity = 87.8%, specificity = 80.8%, negative predictive value = 97.8% and positive predictive value = 40.6%. The algorithm had similar sensitivity performance across subgroups as defined by sex, race and ethnicity. These results demonstrate the potential for digital phenotyping to provide an objective, scalable approach to autism screening in real-world settings. Moreover, combining results from digital phenotyping and caregiver questionnaires may increase autism screening accuracy and help reduce disparities in access to diagnosis and intervention.","language":"en","number":"10","urldate":"2023-10-26","journal":"Nature Medicine","publisher":"Nature Publishing Group","author":[{"propositions":[],"lastnames":["Perochon"],"firstnames":["Sam"],"suffixes":[]},{"propositions":[],"lastnames":["Di","Martino"],"firstnames":["J.","Matias"],"suffixes":[]},{"propositions":[],"lastnames":["Carpenter"],"firstnames":["Kimberly","L.","H."],"suffixes":[]},{"propositions":[],"lastnames":["Compton"],"firstnames":["Scott"],"suffixes":[]},{"propositions":[],"lastnames":["Davis"],"firstnames":["Naomi"],"suffixes":[]},{"propositions":[],"lastnames":["Eichner"],"firstnames":["Brian"],"suffixes":[]},{"propositions":[],"lastnames":["Espinosa"],"firstnames":["Steven"],"suffixes":[]},{"propositions":[],"lastnames":["Franz"],"firstnames":["Lauren"],"suffixes":[]},{"propositions":[],"lastnames":["Krishnappa","Babu"],"firstnames":["Pradeep","Raj"],"suffixes":[]},{"propositions":[],"lastnames":["Sapiro"],"firstnames":["Guillermo"],"suffixes":[]},{"propositions":[],"lastnames":["Dawson"],"firstnames":["Geraldine"],"suffixes":[]}],"month":"October","year":"2023","note":"Number: 10","keywords":"Disability, Machine learning","pages":"2489–2497","bibtex":"@article{perochon_early_2023,\n\ttitle = {Early detection of autism using digital behavioral phenotyping},\n\tvolume = {29},\n\tcopyright = {2023 The Author(s)},\n\tissn = {1546-170X},\n\turl = {https://www.nature.com/articles/s41591-023-02574-3},\n\tdoi = {10.1038/s41591-023-02574-3},\n\tabstract = {Early detection of autism, a neurodevelopmental condition associated with challenges in social communication, ensures timely access to intervention. Autism screening questionnaires have been shown to have lower accuracy when used in real-world settings, such as primary care, as compared to research studies, particularly for children of color and girls. Here we report findings from a multiclinic, prospective study assessing the accuracy of an autism screening digital application (app) administered during a pediatric well-child visit to 475 (17–36 months old) children (269 boys and 206 girls), of which 49 were diagnosed with autism and 98 were diagnosed with developmental delay without autism. The app displayed stimuli that elicited behavioral signs of autism, quantified using computer vision and machine learning. An algorithm combining multiple digital phenotypes showed high diagnostic accuracy with the area under the receiver operating characteristic curve = 0.90, sensitivity = 87.8\\%, specificity = 80.8\\%, negative predictive value = 97.8\\% and positive predictive value = 40.6\\%. The algorithm had similar sensitivity performance across subgroups as defined by sex, race and ethnicity. These results demonstrate the potential for digital phenotyping to provide an objective, scalable approach to autism screening in real-world settings. Moreover, combining results from digital phenotyping and caregiver questionnaires may increase autism screening accuracy and help reduce disparities in access to diagnosis and intervention.},\n\tlanguage = {en},\n\tnumber = {10},\n\turldate = {2023-10-26},\n\tjournal = {Nature Medicine},\n\tpublisher = {Nature Publishing Group},\n\tauthor = {Perochon, Sam and Di Martino, J. Matias and Carpenter, Kimberly L. H. and Compton, Scott and Davis, Naomi and Eichner, Brian and Espinosa, Steven and Franz, Lauren and Krishnappa Babu, Pradeep Raj and Sapiro, Guillermo and Dawson, Geraldine},\n\tmonth = oct,\n\tyear = {2023},\n\tnote = {Number: 10},\n\tkeywords = {Disability, Machine learning},\n\tpages = {2489--2497},\n}\n\n\n\n\n\n\n\n","author_short":["Perochon, S.","Di Martino, J. M.","Carpenter, K. L. H.","Compton, S.","Davis, N.","Eichner, B.","Espinosa, S.","Franz, L.","Krishnappa Babu, P. R.","Sapiro, G.","Dawson, G."],"key":"perochon_early_2023","id":"perochon_early_2023","bibbaseid":"perochon-dimartino-carpenter-compton-davis-eichner-espinosa-franz-etal-earlydetectionofautismusingdigitalbehavioralphenotyping-2023","role":"author","urls":{"Paper":"https://www.nature.com/articles/s41591-023-02574-3"},"keyword":["Disability","Machine learning"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/warren.pettine","dataSources":["zYjFbyFmZWKpRCD4j"],"keywords":["disability","machine learning"],"search_terms":["early","detection","autism","using","digital","behavioral","phenotyping","perochon","di martino","carpenter","compton","davis","eichner","espinosa","franz","krishnappa babu","sapiro","dawson"],"title":"Early detection of autism using digital behavioral phenotyping","year":2023}