Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy
Abstract The Prechtl General Movements Assessment (GMA) is increasingly recognized for its role in evaluating the integrity of the developing nervous system and predicting motor dysfunctions, particularly in conditions such as cerebral palsy (CP). However, the necessity for highly trained profession...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-12-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-44141-x |
| _version_ | 1797388184334630912 |
|---|---|
| author | Qiang Gao Siqiong Yao Yuan Tian Chuncao Zhang Tingting Zhao Dan Wu Guangjun Yu Hui Lu |
| author_facet | Qiang Gao Siqiong Yao Yuan Tian Chuncao Zhang Tingting Zhao Dan Wu Guangjun Yu Hui Lu |
| author_sort | Qiang Gao |
| collection | DOAJ |
| description | Abstract The Prechtl General Movements Assessment (GMA) is increasingly recognized for its role in evaluating the integrity of the developing nervous system and predicting motor dysfunctions, particularly in conditions such as cerebral palsy (CP). However, the necessity for highly trained professionals has hindered the adoption of GMA as an early screening tool in some countries. In this study, we propose a deep learning-based motor assessment model (MAM) that combines infant videos and basic characteristics, with the aim of automating GMA at the fidgety movements (FMs) stage. MAM demonstrates strong performance, achieving an Area Under the Curve (AUC) of 0.967 during external validation. Importantly, it adheres closely to the principles of GMA and exhibits robust interpretability, as it can accurately identify FMs within videos, showing substantial agreement with expert assessments. Leveraging the predicted FMs frequency, a quantitative GMA method is introduced, which achieves an AUC of 0.956 and enhances the diagnostic accuracy of GMA beginners by 11.0%. The development of MAM holds the potential to significantly streamline early CP screening and revolutionize the field of video-based quantitative medical diagnostics. |
| first_indexed | 2024-03-08T22:37:05Z |
| format | Article |
| id | doaj.art-1ca84e6e95764455a2b4574f4a1ccacd |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-08T22:37:05Z |
| publishDate | 2023-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-1ca84e6e95764455a2b4574f4a1ccacd2023-12-17T12:21:44ZengNature PortfolioNature Communications2041-17232023-12-0114111110.1038/s41467-023-44141-xAutomating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsyQiang Gao0Siqiong Yao1Yuan Tian2Chuncao Zhang3Tingting Zhao4Dan Wu5Guangjun Yu6Hui Lu7State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic and Developmental Sciences, Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong UniversityState Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic and Developmental Sciences, Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong UniversityDepartment of Health Management, Shanghai Children’s Hospital, School of Medicine, Shanghai Jiao Tong UniversityDepartment of Health Management, Shanghai Children’s Hospital, School of Medicine, Shanghai Jiao Tong UniversityShanghai Engineering Research Center for Big Data in Pediatric Precision Medicine, NHC Key Laboratory of Medical Embryogenesis and Developmental Molecular Biology & Shanghai Key Laboratory of Embryo and Reproduction Engineering, Shanghai Jiao Tong UniversityShanghai Engineering Research Center for Big Data in Pediatric Precision Medicine, NHC Key Laboratory of Medical Embryogenesis and Developmental Molecular Biology & Shanghai Key Laboratory of Embryo and Reproduction Engineering, Shanghai Jiao Tong UniversityShanghai Engineering Research Center for Big Data in Pediatric Precision Medicine, NHC Key Laboratory of Medical Embryogenesis and Developmental Molecular Biology & Shanghai Key Laboratory of Embryo and Reproduction Engineering, Shanghai Jiao Tong UniversityState Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic and Developmental Sciences, Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong UniversityAbstract The Prechtl General Movements Assessment (GMA) is increasingly recognized for its role in evaluating the integrity of the developing nervous system and predicting motor dysfunctions, particularly in conditions such as cerebral palsy (CP). However, the necessity for highly trained professionals has hindered the adoption of GMA as an early screening tool in some countries. In this study, we propose a deep learning-based motor assessment model (MAM) that combines infant videos and basic characteristics, with the aim of automating GMA at the fidgety movements (FMs) stage. MAM demonstrates strong performance, achieving an Area Under the Curve (AUC) of 0.967 during external validation. Importantly, it adheres closely to the principles of GMA and exhibits robust interpretability, as it can accurately identify FMs within videos, showing substantial agreement with expert assessments. Leveraging the predicted FMs frequency, a quantitative GMA method is introduced, which achieves an AUC of 0.956 and enhances the diagnostic accuracy of GMA beginners by 11.0%. The development of MAM holds the potential to significantly streamline early CP screening and revolutionize the field of video-based quantitative medical diagnostics.https://doi.org/10.1038/s41467-023-44141-x |
| spellingShingle | Qiang Gao Siqiong Yao Yuan Tian Chuncao Zhang Tingting Zhao Dan Wu Guangjun Yu Hui Lu Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy Nature Communications |
| title | Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy |
| title_full | Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy |
| title_fullStr | Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy |
| title_full_unstemmed | Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy |
| title_short | Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy |
| title_sort | automating general movements assessment with quantitative deep learning to facilitate early screening of cerebral palsy |
| url | https://doi.org/10.1038/s41467-023-44141-x |
| work_keys_str_mv | AT qianggao automatinggeneralmovementsassessmentwithquantitativedeeplearningtofacilitateearlyscreeningofcerebralpalsy AT siqiongyao automatinggeneralmovementsassessmentwithquantitativedeeplearningtofacilitateearlyscreeningofcerebralpalsy AT yuantian automatinggeneralmovementsassessmentwithquantitativedeeplearningtofacilitateearlyscreeningofcerebralpalsy AT chuncaozhang automatinggeneralmovementsassessmentwithquantitativedeeplearningtofacilitateearlyscreeningofcerebralpalsy AT tingtingzhao automatinggeneralmovementsassessmentwithquantitativedeeplearningtofacilitateearlyscreeningofcerebralpalsy AT danwu automatinggeneralmovementsassessmentwithquantitativedeeplearningtofacilitateearlyscreeningofcerebralpalsy AT guangjunyu automatinggeneralmovementsassessmentwithquantitativedeeplearningtofacilitateearlyscreeningofcerebralpalsy AT huilu automatinggeneralmovementsassessmentwithquantitativedeeplearningtofacilitateearlyscreeningofcerebralpalsy |