Dataset Information

Development and Validation of a Deep Learning Method to Predict Cerebral Palsy From Spontaneous Movements in Infants at High Risk.

ABSTRACT:

Importance

Early identification of cerebral palsy (CP) is important for early intervention, yet expert-based assessments do not permit widespread use, and conventional machine learning alternatives lack validity.

Objective

To develop and assess the external validity of a novel deep learning-based method to predict CP based on videos of infants' spontaneous movements at 9 to 18 weeks' corrected age.

Design, setting, and participants

This prognostic study of a deep learning-based method to predict CP at a corrected age of 12 to 89 months involved 557 infants with a high risk of perinatal brain injury who were enrolled in previous studies conducted at 13 hospitals in Belgium, India, Norway, and the US between September 10, 2001, and October 25, 2018. Analysis was performed between February 11, 2020, and September 23, 2021. Included infants had available video recorded during the fidgety movement period from 9 to 18 weeks' corrected age, available classifications of fidgety movements ascertained by the general movement assessment (GMA) tool, and available data on CP status at 12 months' corrected age or older. A total of 418 infants (75.0%) were randomly assigned to the model development (training and internal validation) sample, and 139 (25.0%) were randomly assigned to the external validation sample (1 test set).

Exposure

Video recording of spontaneous movements.

Main outcomes and measures

The primary outcome was prediction of CP. Deep learning-based prediction of CP was performed automatically from a single video. Secondary outcomes included prediction of associated functional level and CP subtype. Sensitivity, specificity, positive and negative predictive values, and accuracy were assessed.

Results

Among 557 infants (310 [55.7%] male), the median (IQR) corrected age was 12 (11-13) weeks at assessment, and 84 infants (15.1%) were diagnosed with CP at a mean (SD) age of 3.4 (1.7) years. Data on race and ethnicity were not reported because previous studies (from which the infant samples were derived) used different study protocols with inconsistent collection of these data. On external validation, the deep learning-based CP prediction method had sensitivity of 71.4% (95% CI, 47.8%-88.7%), specificity of 94.1% (95% CI, 88.2%-97.6%), positive predictive value of 68.2% (95% CI, 45.1%-86.1%), and negative predictive value of 94.9% (95% CI, 89.2%-98.1%). In comparison, the GMA tool had sensitivity of 70.0% (95% CI, 45.7%-88.1%), specificity of 88.7% (95% CI, 81.5%-93.8%), positive predictive value of 51.9% (95% CI, 32.0%-71.3%), and negative predictive value of 94.4% (95% CI, 88.3%-97.9%). The deep learning method achieved higher accuracy than the conventional machine learning method (90.6% [95% CI, 84.5%-94.9%] vs 72.7% [95% CI, 64.5%-79.9%]; P < .001), but no significant improvement in accuracy was observed compared with the GMA tool (85.9%; 95% CI, 78.9%-91.3%; P = .11). The deep learning prediction model had higher sensitivity among infants with nonambulatory CP (100%; 95% CI, 63.1%-100%) vs ambulatory CP (58.3%; 95% CI, 27.7%-84.8%; P = .02) and spastic bilateral CP (92.3%; 95% CI, 64.0%-99.8%) vs spastic unilateral CP (42.9%; 95% CI, 9.9%-81.6%; P < .001).

Conclusions and relevance

In this prognostic study, a deep learning-based method for predicting CP at 9 to 18 weeks' corrected age had predictive accuracy on external validation, which suggests possible avenues for using deep learning-based software to provide objective early detection of CP in clinical settings.

SUBMITTER: Groos D

PROVIDER: S-EPMC9274325 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Machine learning (ML) and deep learning (DL) can successfully predict high prevalence events in very large databases (big data), but the value of this methodology for risk prediction in smaller cohorts with uncommon diseases and infrequent events is uncertain. The clinical course of spontaneous coronary artery dissection (SCAD) is variable, and no reliable methods are available to predict mortality. Based on the hypothesis that machine learning (ML) and deep learning (DL) techniques could enhance the identification of patients at risk, we applied a deep neural network to information available in electronic health records (EHR) to predict in-hospital mortality in patients with SCAD. We extracted patient data from the EHR of an extensive urban health system and applied several ML and DL models using candidate clinical variables potentially associated with mortality. We partitioned the data into training and evaluation sets with cross-validation. We estimated model performance based on the area under the receiver-operator characteristics curve (AUC) and balanced accuracy. As sensitivity analyses, we examined results limited to cases with complete clinical information available. We identified 375 SCAD patients of which mortality during the index hospitalization was 11.5%. The best-performing DL algorithm identified in-hospital mortality with AUC 0.98 (95% CI 0.97-0.99), compared to other ML models (P < 0.0001). For prediction of mortality using ML models in patients with SCAD, the AUC ranged from 0.50 with the random forest method (95% CI 0.41-0.58) to 0.95 with the AdaBoost model (95% CI 0.93-0.96), with intermediate performance using logistic regression, decision tree, support vector machine, K-nearest neighbors, and extreme gradient boosting methods. A deep neural network model was associated with higher predictive accuracy and discriminative power than logistic regression or ML models for identification of patients with ACS due to SCAD prone to early mortality.

Project description:IntroductionCerebral palsy (CP) is the most common childhood physical disability with rates approximately 50% higher in First Nations Australian children. This study aims to evaluate a culturally-adapted parent-delivered early intervention programme for First Nations Australian infants at high risk of CP (Learning through Everyday Activities with Parents for infants with CP; LEAP-CP).Methods and analysisThis study is a randomised assessor masked controlled trial. Infants with birth/postnatal risk factors will be eligible for screening. Infants at high risk of CP ('absent fidgety' on General Movements Assessment, and/or 'suboptimal score' on the Hammersmith Infant Neurological Examination) aged 12-52 weeks corrected age will be recruited. Infants and their caregivers will be randomised to receive LEAP-CP (intervention) or health advice (comparator). LEAP-CP is a culturally-adapted programme of 30 home visits delivered by a peer trainer (First Nations Community Health Worker); and includes goal-directed active motor/cognitive strategies, CP learning games and caregiver educational modules. The control arm receives a monthly health advice visit, based on the Key Family Practices, WHO. All infants continue to receive standard (mainstream) Care as Usual. Dual child primary outcomes are Peabody Developmental Motor Scales-2 (PDMS-2) and Bayley Scales of Infant Development-III. The primary caregiver outcome is the Depression, Anxiety and Stress Scale. Secondary outcomes include function, goal attainment, vision, nutritional status and emotional availability.Sample sizetotal of 86 children (43/group) will enable an effect size of 0.65 on the PDMS-2 to be detected (80% power, α=0.05; 10% attrition).Ethics and disseminationEthics approval through Queensland ethics committees and Aboriginal Controlled Community Health Organisation Research Governance Groups, with families providing written informed consent. Findings will be disseminated with guidance from the Participatory Action Research, in collaboration with First Nations communities; peer-reviewed journal publications and national/international conference presentations.Trial registration numberACTRN12619000969167p.

Project description:BackgroundAssessment of bimanual movements, which are frequently impaired in children with cerebral palsy, is highly challenging in clinical practice. Instrumented measures have been developed to evaluate and help to understand impaired upper limb movement during bimanual tasks in these children. The aim of this review was to report instrumented measurement tools (3D motion analysis, sensors, etc.) used for bimanual task movement analysis, and the metrological properties of the measures in children with cerebral palsy.MethodsA systematic review was conducted (Prospero CRD42022308517). PubMed, Web of Science, Cochrane and Scopus databases were searched with relevant keywords and inclusion/exclusion criteria. Article quality and biomechanical methods were evaluated with a customized scale and metrological properties with the COSMIN checklist.ResultsIn total, 452 children, mostly with unilateral cerebral palsy, mean age 10.9 (SD 3.2) years, underwent quantitative bimanual assessments in the 31 included studies (mean quality score 22/32 points [SD 4.7]). The tools used were 3D motion analysis (n = 26), accelerometers (n = 2), and other instruments (cube, digitizer, etc.) (n = 3). Children performed 1-5 bimanual tasks in laboratory settings, mostly activities of daily living or game scenarios. Analyses focused mostly on spatiotemporal variables, 6 of which were specifically developed for bilateral measures (task completion time, goal synchronization, movement overlap time, interlimb coupling, continuous relative phase and asynchrony). These instrumented measurements had moderate to good discriminant and convergent validity, but reliability and responsiveness assessments were lacking.ConclusionsA large number of quantitative bimanual assessments involving different tools, bimanual tasks and specific variables developed to evaluate bimanual function were found. Development of other relevant variables and validation of these tools are needed to further determine their usefulness, both as research outcomes and to guide therapies in clinical practice. Future research, involving younger children and real-life assessments, will improve our understanding of bimanual function in children with cerebral palsy.