Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental Disorders
<b>Background/Objectives:</b> The early identification of neurodevelopmental disorders (NDDs) in infants is crucial for effective intervention and improved long-term outcomes. Recent evidence indicates a correlation between deficits in spontaneous movements in newborns and the likelihood...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/2/136 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588672183042048 |
|---|---|
| author | Roberta Bruschetta Angela Caruso Martina Micai Simona Campisi Gennaro Tartarisco Giovanni Pioggia Maria Luisa Scattoni |
| author_facet | Roberta Bruschetta Angela Caruso Martina Micai Simona Campisi Gennaro Tartarisco Giovanni Pioggia Maria Luisa Scattoni |
| author_sort | Roberta Bruschetta |
| collection | DOAJ |
| description | <b>Background/Objectives:</b> The early identification of neurodevelopmental disorders (NDDs) in infants is crucial for effective intervention and improved long-term outcomes. Recent evidence indicates a correlation between deficits in spontaneous movements in newborns and the likelihood of developing NDDs later in life. This study aims to address this aspect by employing a marker-less Artificial Intelligence (AI) approach for the automatic assessment of infants’ movements from single-camera video recordings. <b>Methods:</b> A total of 74 high-risk infants were selected from the Italian Network for Early Detection of Autism Spectrum Disorders (NIDA) database and closely observed at five different time points, ranging from 10 days to 24 weeks of age. Automatic motion tracking was performed using deep learning to capture infants’ body landmarks and extract a set of kinematic parameters. <b>Results:</b> Our findings revealed significant differences between infants later diagnosed with NDD and typically developing (TD) infants in three lower limb features at 10 days old: ‘Median Velocity’, ‘Area differing from moving average’, and ‘Periodicity’. Using a Support Vector Machine (SVM), we achieved an accuracy rate of approximately 85%, a sensitivity of 64%, and a specificity of 100%. We also observed that the disparities in lower limb movements diminished over time points. Furthermore, the tracking accuracy was assessed through a comparative analysis with a validated semi-automatic algorithm (Movidea), obtaining a Pearson correlation (R) of 93.96% (88.61–96.60%) and a root mean square error (RMSE) of 9.52 pixels (7.29–12.37). <b>Conclusions:</b> This research highlights the potential of AI movement analysis for the early detection of NDDs, providing valuable insights into the motor development of infants at risk. |
| format | Article |
| id | doaj-art-11e6a8482b04450c98a7237e1f48fe4d |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-11e6a8482b04450c98a7237e1f48fe4d2025-01-24T13:28:51ZengMDPI AGDiagnostics2075-44182025-01-0115213610.3390/diagnostics15020136Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental DisordersRoberta Bruschetta0Angela Caruso1Martina Micai2Simona Campisi3Gennaro Tartarisco4Giovanni Pioggia5Maria Luisa Scattoni6Italian National Research Council, Institute for Biomedical Research and Innovation, Via Leanza, Istituto Marino, 98164 Messina, ItalyResearch Coordination and Support Service, Istituto Superiore di Sanità, Viale Regina Elena 299, 00161 Rome, ItalyResearch Coordination and Support Service, Istituto Superiore di Sanità, Viale Regina Elena 299, 00161 Rome, ItalyItalian National Research Council, Institute for Biomedical Research and Innovation, Via Leanza, Istituto Marino, 98164 Messina, ItalyItalian National Research Council, Institute for Biomedical Research and Innovation, Via Leanza, Istituto Marino, 98164 Messina, ItalyItalian National Research Council, Institute for Biomedical Research and Innovation, Via Leanza, Istituto Marino, 98164 Messina, ItalyResearch Coordination and Support Service, Istituto Superiore di Sanità, Viale Regina Elena 299, 00161 Rome, Italy<b>Background/Objectives:</b> The early identification of neurodevelopmental disorders (NDDs) in infants is crucial for effective intervention and improved long-term outcomes. Recent evidence indicates a correlation between deficits in spontaneous movements in newborns and the likelihood of developing NDDs later in life. This study aims to address this aspect by employing a marker-less Artificial Intelligence (AI) approach for the automatic assessment of infants’ movements from single-camera video recordings. <b>Methods:</b> A total of 74 high-risk infants were selected from the Italian Network for Early Detection of Autism Spectrum Disorders (NIDA) database and closely observed at five different time points, ranging from 10 days to 24 weeks of age. Automatic motion tracking was performed using deep learning to capture infants’ body landmarks and extract a set of kinematic parameters. <b>Results:</b> Our findings revealed significant differences between infants later diagnosed with NDD and typically developing (TD) infants in three lower limb features at 10 days old: ‘Median Velocity’, ‘Area differing from moving average’, and ‘Periodicity’. Using a Support Vector Machine (SVM), we achieved an accuracy rate of approximately 85%, a sensitivity of 64%, and a specificity of 100%. We also observed that the disparities in lower limb movements diminished over time points. Furthermore, the tracking accuracy was assessed through a comparative analysis with a validated semi-automatic algorithm (Movidea), obtaining a Pearson correlation (R) of 93.96% (88.61–96.60%) and a root mean square error (RMSE) of 9.52 pixels (7.29–12.37). <b>Conclusions:</b> This research highlights the potential of AI movement analysis for the early detection of NDDs, providing valuable insights into the motor development of infants at risk.https://www.mdpi.com/2075-4418/15/2/136artificial intelligenceanalysis of infants’ movementsneurodevelopmental disordersautomatic motion trackingdeep learningearly identification of neurodevelopmental disorders |
| spellingShingle | Roberta Bruschetta Angela Caruso Martina Micai Simona Campisi Gennaro Tartarisco Giovanni Pioggia Maria Luisa Scattoni Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental Disorders Diagnostics artificial intelligence analysis of infants’ movements neurodevelopmental disorders automatic motion tracking deep learning early identification of neurodevelopmental disorders |
| title | Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental Disorders |
| title_full | Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental Disorders |
| title_fullStr | Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental Disorders |
| title_full_unstemmed | Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental Disorders |
| title_short | Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental Disorders |
| title_sort | marker less video analysis of infant movements for early identification of neurodevelopmental disorders |
| topic | artificial intelligence analysis of infants’ movements neurodevelopmental disorders automatic motion tracking deep learning early identification of neurodevelopmental disorders |
| url | https://www.mdpi.com/2075-4418/15/2/136 |
| work_keys_str_mv | AT robertabruschetta markerlessvideoanalysisofinfantmovementsforearlyidentificationofneurodevelopmentaldisorders AT angelacaruso markerlessvideoanalysisofinfantmovementsforearlyidentificationofneurodevelopmentaldisorders AT martinamicai markerlessvideoanalysisofinfantmovementsforearlyidentificationofneurodevelopmentaldisorders AT simonacampisi markerlessvideoanalysisofinfantmovementsforearlyidentificationofneurodevelopmentaldisorders AT gennarotartarisco markerlessvideoanalysisofinfantmovementsforearlyidentificationofneurodevelopmentaldisorders AT giovannipioggia markerlessvideoanalysisofinfantmovementsforearlyidentificationofneurodevelopmentaldisorders AT marialuisascattoni markerlessvideoanalysisofinfantmovementsforearlyidentificationofneurodevelopmentaldisorders |