Novel AI driven approach to classify infant motor functions.

The past decade has evinced a boom of computer-based approaches to aid movement assessment in early infancy. Increasing interests have been dedicated to develop AI driven approaches to complement the classic Prechtl general movements assessment (GMA). This study proposes a novel machine learning algorithm to detect an age-specific movement pattern, the fidgety movements (FMs), in a prospectively collected sample of typically developing infants. Participants were recorded using a passive, single camera RGB video stream. The dataset of 2800 five-second snippets was annotated by two well-trained and experienced GMA assessors, with excellent inter- and intra-rater reliabilities. Using OpenPose, the infant full pose was recovered from the video stream in the form of a 25-points skeleton. This skeleton was used as input vector for a shallow multilayer neural network (SMNN). An ablation study was performed to justify the network's architecture and hyperparameters. We show for the first time that the SMNN is sufficient to discriminate fidgety from non-fidgety movements in a sample of age-specific typical movements with a classification accuracy of 88%. The computer-based solutions will complement original GMA to consistently perform accurate and efficient screening and diagnosis that may become universally accessible in daily clinical practice in the future.

A Novel Way to Measure and Predict Development: A Heuristic Approach to Facilitate the Early Detection of Neurodevelopmental Disorders.

PURPOSE OF REVIEW: Substantial research exists focusing on the various aspects and domains of early human development. However, there is a clear blind spot in early postnatal development when dealing with neurodevelopmental disorders, especially those that manifest themselves clinically only in late infancy or even in childhood. RECENT FINDINGS: This early developmental period may represent an important timeframe to study these disorders but has historically received far less research attention. We believe that only a comprehensive interdisciplinary approach will enable us to detect and delineate specific parameters for specific neurodevelopmental disorders at a very early age to improve early detection/diagnosis, enable prospective studies and eventually facilitate randomised trials of early intervention. In this article, we propose a dynamic framework for characterising neurofunctional biomarkers associated with specific disorders in the development of infants and children. We have named this automated detection 'Fingerprint Model', suggesting one possible approach to accurately and early identify neurodevelopmental disorders.

On the Latent Variable Interpretation in Sum-Product Networks.

One of the central themes in Sum-Product networks (SPNs) is the interpretation of sum nodes as marginalized latent variables (LVs). This interpretation yields an increased syntactic or semantic structure, allows the application of the EM algorithm and to efficiently perform MPE inference. In literature, the LV interpretation was justified by explicitly introducing the indicator variables corresponding to the LVs' states. However, as pointed out in this paper, this approach is in conflict with the completeness condition in SPNs and does not fully specify the probabilistic model. We propose a remedy for this problem by modifying the original approach for introducing the LVs, which we call SPN augmentation. We discuss conditional independencies in augmented SPNs, formally establish the probabilistic interpretation of the sum-weights and give an interpretation of augmented SPNs as Bayesian networks. Based on these results, we find a sound derivation of the EM algorithm for SPNs. Furthermore, the Viterbi-style algorithm for MPE proposed in literature was never proven to be correct. We show that this is indeed a correct algorithm, when applied to selective SPNs, and in particular when applied to augmented SPNs. Our theoretical results are confirmed in experiments on synthetic data and 103 real-world datasets.

Fidgety movements – tiny in appearance, but huge in impact / Movimentos irregulares - pequenos na aparência, porém enormes no impacto

Abstract Objectives: To describe fidgety movements (FMs), i.e., the spontaneous movement pattern that typically occurs at 3–5 months after term age, and discuss its clinical relevance. Sources: A comprehensive literature search was performed using the following databases: MEDLINE/PubMed, CINAHL, The Cochrane Library, Science Direct, PsycINFO, and EMBASE. The search strategy included the MeSH terms and search strings (‘fidgety movement*’) OR [(‘general movement*’) AND (‘three month*’) OR (‘3 month*’)], as well as studies published on the General Movements Trust website (www.general-movements-trust.info). Summary of the data: Virtually all infants develop normally if FMs are present and normal, even if their brain ultrasound findings and/or clinical histories indicate a disposition to later neurological deficits. Conversely, almost all infants who never develop FMs have a high risk for neurological deficits such as cerebral palsy, and for genetic disorders with a late onset. If FMs are normal but concurrent postural patterns are not age-adequate or the overall movement character is monotonous, cognitive and/or language skills at school age will be suboptimal. Abnormal FMs are unspecific and have a low predictive power, but occur exceedingly in infants later diagnosed with autism. Conclusions: Abnormal, absent, or sporadic FMs indicate an increased risk for later neurological dysfunction, whereas normal FMs are highly predictive of normal development, especially if they co-occur with other smooth and fluent movements. Early recognition of neurological signs facilitates early intervention. It is important to re-assure parents of infants with clinical risk factors that the neurological outcome will be adequate if FMs develop normally.

Resumo Objetivos: Descrever os movimentos irregulares (FMs), ou seja, o padrão de movimentos espontâneos que normalmente ocorrem entre três e cinco meses após o nascimento e discutir sua relevância clínica. Fontes: Uma pesquisa abrangente na literatura foi feita nas seguintes bases de dados: Medline/PubMed, Cinahl, The Cochrane Library, Science Direct, PsycINFO e Embase. A estratégia de busca incluiu os termos e cadeias de pesquisa do MeSH [(“fidgety movement*”) OU [(“general movement*”) E (“three month*”) OU (“3 month*”)], bem como estudos publicados no website da General Movements Trust (www.general-movements-trust.info). Resumo dos dados: Praticamente todos os neonatos se desenvolveram normalmente se os FMs estiveram presentes e foram normais, mesmo se seus resultados do ultrassom do cérebro e/ou históricos clínicos indicassem tendência a déficits neurológicos posteriores. Por outro lado, quase todos os neonatos que nunca desenvolveram FMs apresentaram maior risco de déficits neurológicos, como paralisia cerebral, e doenças genéticas de início tardio. Caso os FMs fossem normais, porém simultâneos a padrões posturais não adequados para a idade, ou o caráter geral dos movimentos fosse monótono, as capacidades cognitivas e/ou de linguagem na idade escolar seriam abaixo do ideal. Os FMs anormais não são específicos e têm baixo poder preditivo, porém ocorrem em grande parte em neonatos posteriormente diagnosticados com autismo. Conclusões: FMs anormais, ausentes ou esporádicos indicam um risco maior de disfunções neurológicas posteriores, ao passo que FMs normais são altamente preditivos de desenvolvimento normal, principalmente se forem simultâneos a outros movimentos suaves e fluentes. O reconhecimento precoce de sinais neurológicos facilita a intervenção antecipada. É importante garantir aos pais de neonatos com fatores de risco clínicos que o resultado neurológico será adequado se os FMs se desenvolverem normalmente.

Fidgety movements - tiny in appearance, but huge in impact.

OBJECTIVES: To describe fidgety movements (FMs), i.e., the spontaneous movement pattern that typically occurs at 3-5 months after term age, and discuss its clinical relevance. SOURCES: A comprehensive literature search was performed using the following databases: MEDLINE/PubMed, CINAHL, The Cochrane Library, Science Direct, PsycINFO, and EMBASE. The search strategy included the MeSH terms and search strings ('fidgety movement*') OR [('general movement*') AND ('three month*') OR ('3 month*')], as well as studies published on the General Movements Trust website (www.general-movements-trust.info). SUMMARY OF THE DATA: Virtually all infants develop normally if FMs are present and normal, even if their brain ultrasound findings and/or clinical histories indicate a disposition to later neurological deficits. Conversely, almost all infants who never develop FMs have a high risk for neurological deficits such as cerebral palsy, and for genetic disorders with a late onset. If FMs are normal but concurrent postural patterns are not age-adequate or the overall movement character is monotonous, cognitive and/or language skills at school age will be suboptimal. Abnormal FMs are unspecific and have a low predictive power, but occur exceedingly in infants later diagnosed with autism. CONCLUSIONS: Abnormal, absent, or sporadic FMs indicate an increased risk for later neurological dysfunction, whereas normal FMs are highly predictive of normal development, especially if they co-occur with other smooth and fluent movements. Early recognition of neurological signs facilitates early intervention. It is important to re-assure parents of infants with clinical risk factors that the neurological outcome will be adequate if FMs develop normally.