Open video data sharing in developmental science and clinical practice

Marschik, Peter B.; Kulvičius, Tomas; Flügge, Sarah; Widmann, Claudius A. A.; Nielsen‐Saines, Karin; Schulte‐Rüther, Martin; Hüning, Britta; Bölte, Sven; Poustka, Luise; Sigafoos, Jeff; Wörgötter, Florentin; Einspieler, Christa; Zhang, Dajie

doi:10.1016/j.isci.2023.106348

Cited by 6 publications

(10 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Until now, no approved public-accessible large datasets are available in the field of researching general movements, although such dataset would be the basis for developing and comparing automated GMA solutions. This urgently calls for pooling and merging high-quality data across sites, which is challenging, partly due to the complex participants’ confidentiality and privacy concerns 52 , 61 . With the pressure sensing data, participants’ privacy protection can be easily achieved since no personal identifiable data is necessary for the analyses.…”

Section: Discussionmentioning

confidence: 99%

“…As a comparison, with vision-based approaches, i.e., using cameras, which are predominantly used in the field 9 – 11 , facial images, being one of the most sensitive personal identifiers, are commonly present in the datasets. Data de-identification and privacy protection can only be done through additional laborious technical manipulations 52 .…”

Section: Discussionmentioning

confidence: 99%

“…Compared to other motion tracking techniques, the application of pressure mats does not require complex and time-consuming setups and is fully non-intrusive to the infants. The pressure mat data can be readily deidentified thus circumvent potential data privacy issues when it comes to data transfer and sharing 52 . If a pressure sensitive mat can reliably detect different infant general movement patterns, it will have great potential for routine clinical applications which may substantially increase the accessibility of GMA.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Infant movement classification through pressure distribution analysis

et al. 2023

Self Cite

View full text Add to dashboard Cite

Background Aiming at objective early detection of neuromotor disorders such as cerebral palsy, we propose an innovative non-intrusive approach using a pressure sensing device to classify infant general movements. Here we differentiate typical general movement patterns of the “fidgety period” (fidgety movements) vs. the “pre-fidgety period” (writhing movements). Methods Participants (N = 45) were sampled from a typically-developing infant cohort. Multi-modal sensor data, including pressure data from a pressure sensing mat with 1024 sensors, were prospectively recorded for each infant in seven succeeding laboratory sessions in biweekly intervals from 4 to 16 weeks of post-term age. 1776 pressure data snippets, each 5 s long, from the two targeted age periods were taken for movement classification. Each snippet was pre-annotated based on corresponding synchronised video data by human assessors as either fidgety present or absent. Multiple neural network architectures were tested to distinguish the fidgety present vs. fidgety absent classes, including support vector machines, feed-forward networks, convolutional neural networks, and long short-term memory networks. Results Here we show that the convolution neural network achieved the highest average classification accuracy (81.4%). By comparing the pros and cons of other methods aiming at automated general movement assessment to the pressure sensing approach, we infer that the proposed approach has a high potential for clinical applications. Conclusions We conclude that the pressure sensing approach has great potential for efficient large-scale motion data acquisition and sharing. This will in return enable improvement of the approach that may prove scalable for daily clinical application for evaluating infant neuromotor functions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Infant movement classification through pressure distribution analysis

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…The use of automated analysis of visual form perception through machine learning could relieve limited resources. Initial results are already available for the fidgety age group 48 . Early identification of infants at risk for later non age-appropriate outcome could protect resources, as only infants in need would receive therapy.…”

Section: Discussionmentioning

confidence: 99%

General Movements trajectories and outcome at 12 months in very preterm infants: An analysis of tendencies and pathological persistence

Teschler,

Dathe,

Heuser-Spura

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Very preterm infants (VPI) < 32 weeks are at increased risk of developmental disorders detectable using the Prechtl General Movements Assessment (GMA) and the Bayley Scales of Infant and Toddler Development-Third Edition (BSID-III). The aim of this study was to investigate General Movements (GMs) trajectories from preterm to fidgety age including GMs tendencies and their association with cognitive and motor outcome. Retrospective analysis of VPI with GMA at preterm (35 ± 2 weeks postmenstrual age (PMA), T1) and fidgety age (12 ± 3 weeks corrected age CA), T2), and BSID-III (12 ± 3 months CA, T3) is performed. Data are analysed using Pearson χ2-test, Fisher-Freeman-Halton Exact test, and residual analyses. This study found significant associations between (a) GMs (T1) and (b) persistent pathological GMs (T1 + T2) with cognitive outcomes at 12 months (T3) considering the tendencies of GMs in addition to the global character (p = 0.007, p = 0.022, respectively), representing medium-sized effects. There were no significant associations between GMs or persistence of pathological GMs and gross and fine motor outcomes, regardless of GMs tendencies. Findings indicate that considering tendencies of GMs and the persistence of pathological GMs may be important in identifying children at risk of cognitive impairments early. This additional assessment parameter may have the potential for early identification of infants with milder motor and/or cognitive impairments. However, more research is needed using larger sample cohorts to generalise the results and to be able to recommend sequential GMA for clinical routine.

show abstract

“…Since the development of GMA, there have been numerous studies on the inter-rater reliability of GMA, based on traditional recording methods [12][13][14][15][16][17][18][19]. However, recently, GMA researchers (i) are optimising existing recording techniques through technological developments; (ii) amending detailed clinical protocols and assessments based on visual Gestalt perception (e.g., [20][21][22]); and (iii) developing computer-based approaches to analyse GMs and changing the research and clinical use of GMA (e.g., [23][24][25][26][27][28][29][30][31][32][33][34][35][36][37]). Even though we observe an increase in 'tech-based' studies on GMs overall and the results from computer-based GMA appear promising, they cannot replace human visual Gestalt perception yet in the evaluation of GMs [24,25,33,37].…”

Section: Introduction How It All Came About-from Prechtl's First Obse...mentioning

confidence: 99%

Mobile Solutions for Clinical Surveillance and Evaluation in Infancy—General Movement Apps

Marschik

Kwong

Silva

et al. 2023

JCM

Self Cite

View full text Add to dashboard Cite

The Prechtl General Movements Assessment (GMA) has become a clinician and researcher toolbox for evaluating neurodevelopment in early infancy. Given that it involves the observation of infant movements from video recordings, utilising smartphone applications to obtain these recordings seems like the natural progression for the field. In this review, we look back on the development of apps for acquiring general movement videos, describe the application and research studies of available apps, and discuss future directions of mobile solutions and their usability in research and clinical practice. We emphasise the importance of understanding the background that has led to these developments while introducing new technologies, including the barriers and facilitators along the pathway. The GMApp and Baby Moves apps were the first ones developed to increase accessibility of the GMA, with two further apps, NeuroMotion and InMotion, designed since. The Baby Moves app has been applied most frequently. For the mobile future of GMA, we advocate collaboration to boost the field’s progression and to reduce research waste. We propose future collaborative solutions, including standardisation of cross-site data collection, adaptation to local context and privacy laws, employment of user feedback, and sustainable IT structures enabling continuous software updating.

show abstract

Open video data sharing in developmental science and clinical practice

Cited by 6 publications

References 55 publications

Infant movement classification through pressure distribution analysis

Infant movement classification through pressure distribution analysis

General Movements trajectories and outcome at 12 months in very preterm infants: An analysis of tendencies and pathological persistence

Mobile Solutions for Clinical Surveillance and Evaluation in Infancy—General Movement Apps

Contact Info

Product

Resources

About