Article
Medicine, General & Internal
Jinjun Zhou, Shuangshuang Li, Li Gu, Xiaohua Zhang, Zhen Tang
Summary: The study found a correlation between poor GM scores in preterm infants and low NBNA scores, as well as between abnormal cerebral MRI results and low NBNA scores. Additionally, preterm infants with poor GM scores were more likely to have abnormal results in cerebral MRI assessments.
Article
Computer Science, Interdisciplinary Applications
Thanh-Tu Pham, Minh-Binh Le, Lawrence H. Le, John Andersen, Edmond Lou
Summary: A deep learning approach using CNNs was proposed to automatically measure migration percentage on pelvis radiographs, achieving high accuracy and reliability. The method could assist clinicians in diagnosing hip displacement in children with cerebral palsy.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2021)
Review
Pediatrics
Stephanie Baker, Yogavijayan Kandasamy
Summary: This study provides a systematic review on the application of machine learning in predicting and understanding neurodevelopmental outcomes in preterm infants. Promising initial works have been conducted in this field, but many challenges and opportunities remain.
PEDIATRIC RESEARCH
(2023)
Review
Clinical Neurology
Bernard Dan
Summary: Current societal and technological changes have increased the ethical challenges faced by individuals with cerebral palsy, including shifts in disability representations, the International Classification of Functioning, Disability, and Health, changes in laws and international agreements, and advancements in technology such as robotics, brain-computer interface devices, and artificial intelligence. These developments have altered diagnostic approaches, intervention goals, and created new opportunities, impacting both clinical practice and research priorities.
FRONTIERS IN NEUROLOGY
(2021)
Article
Engineering, Biomedical
Kevin D. McCay, Pengpeng Hu, Hubert P. H. Shum, Wai Lok Woo, Claire Marcroft, Nicholas D. Embleton, Adrian Munteanu, Edmond S. L. Ho
Summary: The early diagnosis of cerebral palsy has been an important area of recent research. Automating diagnostic tools like General Movements Assessment (GMA) can improve accessibility and enhance understanding of infant movement development. This paper proposes new and improved features for classification of infant body movements using pose-based features extracted from RGB video sequences. The proposed framework shows good classification performance across multiple datasets.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Computer Science, Information Systems
Romero Morais, Vuong Le, Catherine Morgan, Alicia Spittle, Nadia Badawi, Jane Valentine, Elizabeth M. Hurrion, Paul A. Dawson, Truyen Tran, Svetha Venkatesh
Summary: FidgetyFind is a method that detects and assesses the quality of general movements in infants. It is highly interpretable and accurate, utilizing measurements of movement variability in short video segments. The method translates these measurements into a single score, similar to the process used by domain experts. Evaluation on a large clinical dataset demonstrated the superior interpretability and accuracy of FidgetyFind compared to other published methods.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Pediatrics
Carlo Mario Bertoncelli, Nathalie Dehan, Domenico Bertoncelli, Sikha Bagui, Subhash C. Bagui, Stefania Costantini, Federico Solla
Summary: This study used a prediction model to identify the factors associated with epilepsy in children with cerebral palsy. The results showed that prenatal CP etiology, spasticity, scoliosis, severe intellectual disabilities, poor motor skills, and communication and feeding disorders were associated with epilepsy in these children.
Review
Biology
Rylea Hart, Heather Smith, Yanxin Zhang
Summary: The study evaluated systems developed for providing objective, automatic assessment for resistance-training movements used to improve physical performance and/or rehabilitation, identifying some methodological errors in the development of the machine learning models. Future machine learning models should adopt the correct developmental methodology and provide interpretable and generalizable models.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Pediatrics
Laura A. Prosser, Julie Skorup, Samuel R. Pierce, Abbas F. Jawad, Andrew H. Fagg, Thubi H. A. Kolobe, Beth A. Smith
Summary: This project aims to understand how infants at high risk for cerebral palsy (CP) learn to move and acquire early locomotor skills over the first 18 months of life. Robotic and sensor technology will be used for intervention and longitudinal study of infant movement during early spontaneous movement, prone locomotion (crawling), and upright locomotion (walking) stages. The study will enroll sixty participants and collect data on locomotor skill, training characteristics, and variables related to locomotor learning. The findings will contribute to the development of predictive models for locomotor skill acquisition in infants at high risk for CP.
FRONTIERS IN PEDIATRICS
(2023)
Article
Medicine, General & Internal
Hyun Jeong Do, Kyoung Min Moon, Hyun-Seung Jin
Summary: This study compared the performance of machine learning methods and logistic regression in predicting mortality of very low birth weight infants. The results showed that artificial neural network, random forest, and logistic regression had similar predictive performance, while support vector machine performed lower.
Article
Computer Science, Artificial Intelligence
Haomiao Ni, Yuan Xue, Liya Ma, Qian Zhang, Xiaoye Li, Sharon X. Huang
Summary: This paper investigates the general movement assessment (GMA) method for infant movement videos (IMVs) and proposes an effective model to improve the performance. The model utilizes infant body parsing and pose estimation information to enhance the results and employs a semi-supervised learning approach to utilize partially labeled video data. The experiments show that the proposed model achieves state-of-the-art results in accuracy and prediction performance.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Surgery
Matthew Q. Miller, Tessa A. Hadlock, Emily Fortier, Diego L. Guarin
Summary: Facial palsy assessment lacks standardized methods. This study compared clinician-graded eFACE scale to machine learning-derived automated assessments (auto-eFACE) and found that automated scores were more accurate in detecting facial asymmetry in normal and palsy patients.
PLASTIC AND RECONSTRUCTIVE SURGERY
(2021)
Review
Medicine, General & Internal
Judy Seesahai, Maureen Luther, Paige Terrien Church, Patricia Maddalena, Elizabeth Asztalos, Thomas Rotter, Rudaina Banihani
Summary: The General Movements Assessment is a valuable tool for predicting cerebral palsy in term infants, with normal results at 3-5 months associated with low risk for moderate/severe cerebral palsy. Absent fidgety movements and cramped synchronized movements are highly specific predictors for cerebral palsy. However, the lack of high-quality research limits the applicability of the assessment and it should not be used in isolation for assessing this population.
SYSTEMATIC REVIEWS
(2021)
Article
Chemistry, Analytical
Ivana Bardino Novosel, Anina Ritterband-Rosenbaum, Georgios Zampoukis, Jens Bo Nielsen, Jakob Lorentzen
Summary: This study developed and trained an image-based Convolutional Neural Network (CNN) to recognize specific movement classifiers relevant to individuals with cerebral palsy (CP). Monitoring and quantifying movement behavior in CP patients using multiple wearable sensors and CNN is of great value for improving their health outcomes.
Article
Pediatrics
Kamini Raghuram, Silvia Orlandi, Paige Church, Maureen Luther, Alex Kiss, Vibhuti Shah
Summary: A novel automated movement analysis, validated in a cohort study, showed promising results in predicting cerebral palsy in preterm infants. The technology demonstrated high specificity and negative predictive value, making it potentially useful for screening purposes.
Article
Clinical Neurology
C. Peyton, E. Yang, M. E. Msall, L. Adde, R. Stoen, T. Fjortoft, A. F. Bos, C. Einspieler, Y. Zhou, M. D. Schreiber, J. D. Marks, A. Drobyshevsky
AMERICAN JOURNAL OF NEURORADIOLOGY
(2017)
Editorial Material
Clinical Neurology
Michael E. Msall
DEVELOPMENTAL MEDICINE AND CHILD NEUROLOGY
(2020)
Article
Clinical Neurology
Colleen Peyton, Michael E. Msall, Kristen Wroblewski, Elizabeth E. Rogers, Michael Kohn, Hannah C. Glass
Summary: The study found significant concurrent validity between WIDEA-FS and Bayley-III, with children scoring lower on WIDEA-FS showing a higher risk of adverse development on all Bayley-III domains. This association varied across different age groups, with stronger correlations in motor and language at <30 months and in cognitive at >=30 months.
DEVELOPMENTAL MEDICINE AND CHILD NEUROLOGY
(2021)
Editorial Material
Clinical Neurology
Michael E. Msall
DEVELOPMENTAL MEDICINE AND CHILD NEUROLOGY
(2021)
Article
Multidisciplinary Sciences
Dmytro Onishchenko, Yi Huang, James van Horne, Peter J. Smith, Michael E. Msall, Ishanu Chattopadhyay
Summary: This study developed digital biomarkers for autism spectrum disorder, which can identify high-risk children early on with high accuracy and outperform traditional questionnaire-based screenings.
Editorial Material
Pediatrics
Michael E. Msall
PEDIATRIC RESEARCH
(2023)