Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol for a Human-in-the-Loop Machine Learning Study
BackgroundA considerable number of minors in the United States are diagnosed with developmental or psychiatric conditions, potentially influenced by underdiagnosis factors such as cost, distance, and clinician availability. Despite the potential of digital phenotyping tools w...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2024-02-01
|
| Series: | JMIR Research Protocols |
| Online Access: | https://www.researchprotocols.org/2024/1/e52205 |
| _version_ | 1797320079662120960 |
|---|---|
| author | Aditi Jaiswal Ruben Kruiper Abdur Rasool Aayush Nandkeolyar Dennis P Wall Peter Washington |
| author_facet | Aditi Jaiswal Ruben Kruiper Abdur Rasool Aayush Nandkeolyar Dennis P Wall Peter Washington |
| author_sort | Aditi Jaiswal |
| collection | DOAJ |
| description |
BackgroundA considerable number of minors in the United States are diagnosed with developmental or psychiatric conditions, potentially influenced by underdiagnosis factors such as cost, distance, and clinician availability. Despite the potential of digital phenotyping tools with machine learning (ML) approaches to expedite diagnoses and enhance diagnostic services for pediatric psychiatric conditions, existing methods face limitations because they use a limited set of social features for prediction tasks and focus on a single binary prediction, resulting in uncertain accuracies.
ObjectiveThis study aims to propose the development of a gamified web system for data collection, followed by a fusion of novel crowdsourcing algorithms with ML behavioral feature extraction approaches to simultaneously predict diagnoses of autism spectrum disorder and attention-deficit/hyperactivity disorder in a precise and specific manner.
MethodsThe proposed pipeline will consist of (1) gamified web applications to curate videos of social interactions adaptively based on the needs of the diagnostic system, (2) behavioral feature extraction techniques consisting of automated ML methods and novel crowdsourcing algorithms, and (3) the development of ML models that classify several conditions simultaneously and that adaptively request additional information based on uncertainties about the data.
ResultsA preliminary version of the web interface has been implemented, and a prior feature selection method has highlighted a core set of behavioral features that can be targeted through the proposed gamified approach.
ConclusionsThe prospect for high reward stems from the possibility of creating the first artificial intelligence–powered tool that can identify complex social behaviors well enough to distinguish conditions with nuanced differentiators such as autism spectrum disorder and attention-deficit/hyperactivity disorder.
International Registered Report Identifier (IRRID)PRR1-10.2196/52205 |
| first_indexed | 2024-03-08T04:33:52Z |
| format | Article |
| id | doaj.art-4f06668cb11f42a28fc5eb9501737d86 |
| institution | Directory Open Access Journal |
| issn | 1929-0748 |
| language | English |
| last_indexed | 2024-03-08T04:33:52Z |
| publishDate | 2024-02-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Research Protocols |
| spelling | doaj.art-4f06668cb11f42a28fc5eb9501737d862024-02-08T13:30:34ZengJMIR PublicationsJMIR Research Protocols1929-07482024-02-0113e5220510.2196/52205Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol for a Human-in-the-Loop Machine Learning StudyAditi Jaiswalhttps://orcid.org/0000-0003-1367-818XRuben Kruiperhttps://orcid.org/0000-0002-2288-3743Abdur Rasoolhttps://orcid.org/0000-0001-5334-9001Aayush Nandkeolyarhttps://orcid.org/0009-0005-3780-8526Dennis P Wallhttps://orcid.org/0000-0002-7889-9146Peter Washingtonhttps://orcid.org/0000-0003-3276-4411 BackgroundA considerable number of minors in the United States are diagnosed with developmental or psychiatric conditions, potentially influenced by underdiagnosis factors such as cost, distance, and clinician availability. Despite the potential of digital phenotyping tools with machine learning (ML) approaches to expedite diagnoses and enhance diagnostic services for pediatric psychiatric conditions, existing methods face limitations because they use a limited set of social features for prediction tasks and focus on a single binary prediction, resulting in uncertain accuracies. ObjectiveThis study aims to propose the development of a gamified web system for data collection, followed by a fusion of novel crowdsourcing algorithms with ML behavioral feature extraction approaches to simultaneously predict diagnoses of autism spectrum disorder and attention-deficit/hyperactivity disorder in a precise and specific manner. MethodsThe proposed pipeline will consist of (1) gamified web applications to curate videos of social interactions adaptively based on the needs of the diagnostic system, (2) behavioral feature extraction techniques consisting of automated ML methods and novel crowdsourcing algorithms, and (3) the development of ML models that classify several conditions simultaneously and that adaptively request additional information based on uncertainties about the data. ResultsA preliminary version of the web interface has been implemented, and a prior feature selection method has highlighted a core set of behavioral features that can be targeted through the proposed gamified approach. ConclusionsThe prospect for high reward stems from the possibility of creating the first artificial intelligence–powered tool that can identify complex social behaviors well enough to distinguish conditions with nuanced differentiators such as autism spectrum disorder and attention-deficit/hyperactivity disorder. International Registered Report Identifier (IRRID)PRR1-10.2196/52205https://www.researchprotocols.org/2024/1/e52205 |
| spellingShingle | Aditi Jaiswal Ruben Kruiper Abdur Rasool Aayush Nandkeolyar Dennis P Wall Peter Washington Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol for a Human-in-the-Loop Machine Learning Study JMIR Research Protocols |
| title | Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol
for a Human-in-the-Loop Machine Learning Study |
| title_full | Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol
for a Human-in-the-Loop Machine Learning Study |
| title_fullStr | Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol
for a Human-in-the-Loop Machine Learning Study |
| title_full_unstemmed | Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol
for a Human-in-the-Loop Machine Learning Study |
| title_short | Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol
for a Human-in-the-Loop Machine Learning Study |
| title_sort | digitally diagnosing multiple developmental delays using crowdsourcing fused with machine learning protocol 13 for a human in the loop machine learning study |
| url | https://www.researchprotocols.org/2024/1/e52205 |
| work_keys_str_mv | AT aditijaiswal digitallydiagnosingmultipledevelopmentaldelaysusingcrowdsourcingfusedwithmachinelearningprotocol13forahumanintheloopmachinelearningstudy AT rubenkruiper digitallydiagnosingmultipledevelopmentaldelaysusingcrowdsourcingfusedwithmachinelearningprotocol13forahumanintheloopmachinelearningstudy AT abdurrasool digitallydiagnosingmultipledevelopmentaldelaysusingcrowdsourcingfusedwithmachinelearningprotocol13forahumanintheloopmachinelearningstudy AT aayushnandkeolyar digitallydiagnosingmultipledevelopmentaldelaysusingcrowdsourcingfusedwithmachinelearningprotocol13forahumanintheloopmachinelearningstudy AT dennispwall digitallydiagnosingmultipledevelopmentaldelaysusingcrowdsourcingfusedwithmachinelearningprotocol13forahumanintheloopmachinelearningstudy AT peterwashington digitallydiagnosingmultipledevelopmentaldelaysusingcrowdsourcingfusedwithmachinelearningprotocol13forahumanintheloopmachinelearningstudy |