To evaluate AI-assisted GMA performance for (i) prediction of later cerebral palsy (CP) diagnosis and (ii) classification of expert-rated GMA labels, and to assess heterogeneity and risk of bias.
Methods
A systematic review and meta-analysis was conducted in accordance with PRISMA 2020 guidelines. A total of 105 studies were included in qualitative synthesis, of which 28 were eligible for quantitative synthesis. Random-effects meta-analysis of proportions with logit transformation was used to estimate pooled diagnostic accuracy.
Results
Of 105 eligible studies in qualitative synthesis, 28 were included in quantitative synthesis (17 CP diagnosis outcomes; 11 expert GMA label outcomes). For CP diagnosis outcomes, the pooled diagnostic accuracy was 0.884 (95% CI: 0.838–0.918). For expert-rated GMA label outcomes, the pooled classification accuracy was 0.848 (95% CI: 0.761–0.908). Heterogeneity was substantial across analyses.
Interpretation
AI-assisted GMA shows high pooled performance for both CP diagnosis prediction and expert-label classification; however, certainty remains very low due to heterogeneity and risk of bias. No single GM developmental phase, or sensor modality, demonstrated clear superiority, underscoring the importance of standardized protocols, high-quality datasets, and transparent validation. These findings support the clinical potential of AI-enabled GMA as an objective and scalable screening tool, particularly in settings with limited access to specialized expertise.
OskouiMCoutinhoFDykemanJ, et al.An update on the prevalence of cerebral palsy: a systematic review and meta-analysis. Dev Med Child Neurol2013; 55(6): 509–519. https://doi.org/10.1111/dmcn.12080
2.
SadowskaMSarecka-HujarBKopytaI. Cerebral palsy: current opinions on definition, epidemiology, risk factors, classification and treatment options. Neuropsychiatr Dis Treat2020; 16: 1505–1518. https://doi.org/10.2147/NDT.S235165
3.
NovakIMcIntyreSMorganC, et al.A systematic review of interventions for children with cerebral palsy: state of the evidence. Dev Med Child Neurol2013; 55(10): 885–910. https://doi.org/10.1111/dmcn.12246
4.
ZhussupovaZAyaganovDZharmakhanovaG, et al.Future prospects for assessment of general movements in developing countries. West Kazakhst Med J2023; 65(4): 60–72. https://doi.org/10.18502/wkmj.v65i4.14681
5.
ZhussupovaZAyaganovDZharmakhanovaG, et al.The influence of movement imitation therapy on neurological outcomes in children who have experienced adverse perinatal conditions. West Kazakhst Med J2024; 66(4): 331–342. https://doi.org/10.18502/wkmj.v66i4.17766
6.
GaoQYaoSTianY, et al.Automating General Movements Assessment with quantitative deep learning to facilitate early screening of cerebral palsy. Nat Commun2023; 14(1): 8294. https://doi.org/10.1038/s41467-023-44141-x
7.
GroosDAddeLAubertS, et al.Development and validation of a deep learning method to predict cerebral palsy from spontaneous movements in infants at high risk. JAMA Netw Open2022; 5(7): e2221325. https://doi.org/10.1001/jamanetworkopen.2022.21325
8.
IrshadMTNisarMAGouverneurP, et al.AI approaches towards Prechtl's assessment of general movements: a systematic literature review. Sensors2020; 20(18): 5321. https://doi.org/10.3390/s20185321
9.
ZhouYRashidFMat DaudM, et al.Machine learning-based computer vision for depth camera-based physiotherapy movement assessment: a systematic review. Sensors2025; 25(5): 1586. https://doi.org/10.3390/s25051586
10.
KukkaAJSundelinHEKBasnetO, et al.NeuroMotion smartphone application for remote General Movements Assessment: a feasibility study in Nepal. BMJ Open2024; 14(3): e080063. https://doi.org/10.1136/bmjopen-2023-080063
11.
SilvaNZhangDKulviciusT, et al.The future of general movement assessment: the role of computer vision and machine learning - a scoping review. Res Dev Disabil2021; 110: 103854. https://doi.org/10.1016/j.ridd.2021.103854
12.
AddeLHelbostadJLJenseniusAR, et al.Early prediction of cerebral palsy by computer-based video analysis of general movements: a feasibility study. Dev Med Child Neurol2010; 52(8): 773–778. https://doi.org/10.1111/j.1469-8749.2010.03629.x
DevarajanRKKhaderSS. Pose sequence-aware generative adversarial network for augmenting skeleton sequences to improve cerebral palsy detection by deep learner. Int J Intell Eng Syst2023; 16(5): 512–522. https://doi.org/10.22266/ijies2023.1031.44
15.
DoroniewiczILedwonDJAffanasowiczA, et al.Writhing movement detection in newborns on the second and third day of life using pose-based feature machine learning classification. Sensors2020; 20(21): 5986. https://doi.org/10.3390/s20215986
16.
DoroniewiczILedwońDDanch-WierzchowskaM, et al.Temporal and spatial variability of the fidgety movement descriptors and their relation to head position in automized general movement assessment. Acta Bioeng Biomech2021; 23(3): 69–78. https://doi.org/10.37190/abb-01839-2021-02
17.
KulviciusTZhangDNielsen-SainesK, et al.Infant movement classification through pressure distribution analysis. Commun Med2023; 3(1): 112. https://doi.org/10.1038/s43856-023-00342-5
18.
KulviciusTZhangDPoustkaL, et al.Deep learning empowered sensor fusion boosts infant movement classification. Commun Med2025; 5(1): 16. https://doi.org/10.1038/s43856-024-00701-w
19.
McCayKDHoESLShumHPH, et al.Abnormal infant movements classification with deep learning on pose-based features. IEEE Access2020; 8: 51582–51592. https://doi.org/10.1109/access.2020.2980269
20.
McCayKDHuPShumHPH, et al.A pose-based feature fusion and classification framework for the early prediction of cerebral palsy in infants. IEEE Trans Neural Syst Rehabil Eng2022; 30: 8–19. https://doi.org/10.1109/TNSRE.2021.3138185
21.
MeineckeLBreitbach-FallerNBartzC, et al.Movement analysis in the early detection of newborns at risk for developing spasticity due to infantile cerebral palsy. Hum Mov Sci2006; 25(2): 125–144. https://doi.org/10.1016/j.humov.2005.09.012
22.
Nguyen-ThaiBLeVMorganC, et al.A spatio-temporal attention-based model for infant movement assessment from videos. IEEE J Biomed Health Inform2021; 25(10): 3911–3920. https://doi.org/10.1109/JBHI.2021.3077957
23.
PhilippiHKarchDKangKS, et al.Computer-based analysis of general movements reveals stereotypies predicting cerebral palsy. Dev Med Child Neurol2014; 56(10): 960–967. https://doi.org/10.1111/dmcn.12477
24.
RaghuramKOrlandiSShahV, et al.Automated movement analysis to predict motor impairment in preterm infants: a retrospective study. J Perinatol2019; 39(10): 1362–1369. https://doi.org/10.1038/s41372-019-0464-0
25.
RaghuramKOrlandiSChurchP, et al.Automated movement analysis to predict cerebral palsy in very preterm infants: an ambispective cohort study. Children2022; 9(6): 843. https://doi.org/10.3390/children9060843
26.
RahmatiHMartensHAamoOM, et al.Frequency analysis and feature reduction method for prediction of cerebral palsy in young infants. IEEE Trans Neural Syst Rehabil Eng2016; 24(11): 1225–1234. https://doi.org/10.1109/TNSRE.2016.2539390
27.
SakkosDMcCayKDMarcroftC, et al.Identification of abnormal movements in infants: a deep neural network for body part-based prediction of cerebral palsy. IEEE Access2021; 9: 94281–94292. https://doi.org/10.1109/access.2021.3093469
28.
SchmidtWTReganMFaheyMC, et al.General movement assessment by machine learning: why is it so difficult?J Med Artif Intell2019; 2: 15. https://doi.org/10.21037/jmai.2019.06.02
29.
SchroederASHesseNWeinbergerR, et al.General movement Assessment from videos of computed 3D infant body models is equally effective compared to conventional RGB video rating. Early Hum Dev2020; 144: 104967. https://doi.org/10.1016/j.earlhumdev.2020.104967
30.
ShinHIShinHIBangMS, et al.Deep learning-based quantitative analyses of spontaneous movements and their association with early neurological development in preterm infants. Sci Rep2022; 12(1): 3138. https://doi.org/10.1038/s41598-022-07139-x
31.
StahlASchellewaldCStavdahlO, et al.An optical flow-based method to predict infantile cerebral palsy. IEEE Trans Neural Syst Rehabil Eng2012; 20(4): 605–614. https://doi.org/10.1109/TNSRE.2012.2195030
32.
SukhadiaNKambojP. IMU-based approach to detect spastic cerebral palsy in infants at early stages. EAI Endorsed Trans Pervasive Health Technol2024; 10: 5258. https://doi.org/10.4108/eetpht.10.5258
33.
TsujiTNakashimaSHayashiH, et al.Markerless measurement and evaluation of general movements in infants. Sci Rep2020; 10(1): 1422. https://doi.org/10.1038/s41598-020-57580-z
34.
WuQXuGWeiF, et al.RGB-D videos-based early prediction of infant cerebral Palsy via general movements complexity. IEEE Access2021; 9: 42314–42324. https://doi.org/10.1109/access.2021.3066148
WuQQinPKuangJ, et al.A training-free infant spontaneous movement assessment method for cerebral palsy prediction based on videos. IEEE Trans Neural Syst Rehabil Eng2023; 31: 1670–1679. https://doi.org/10.1109/TNSRE.2023.3255639
37.
ZhangHHoESLShumHPH. CP-AGCN: Pytorch-based attention informed graph convolutional network for identifying infants at risk of cerebral palsy. Softw Impacts2022; 14: 100419. https://doi.org/10.1016/j.simpa.2022.100419
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
