Gross motor function prediction using natural language processing in cerebral palsy.

AIM: To predict ambulatory status and Gross Motor Function Classification System (GMFCS) levels in patients with cerebral palsy (CP) by applying natural language processing (NLP) to electronic health record (EHR) clinical notes. METHOD: Individuals aged 8 to 26 years with a diagnosis of CP in the EHR between January 2009 and November 2020 (~12 years of data) were included in a cross-sectional retrospective cohort of 2483 patients. The cohort was divided into train-test and validation groups. Positive predictive value, sensitivity, specificity, and area under the receiver operating curve (AUC) were calculated for prediction of ambulatory status and GMFCS levels. RESULTS: The median age was 15 years (interquartile range 10-20 years) for the total cohort, with 56% being male and 75% White. The validation group resulted in 70% sensitivity, 88% specificity, 81% positive predictive value, and 0.89 AUC for predicting ambulatory status. NLP applied to the EHR differentiated between GMFCS levels I-II and III (15% sensitivity, 96% specificity, 46% positive predictive value, and 0.71 AUC); and IV and V (81% sensitivity, 51% specificity, 70% positive predictive value, and 0.75 AUC). INTERPRETATION: NLP applied to the EHR demonstrated excellent differentiation between ambulatory and non-ambulatory status, and good differentiation between GMFCS levels I-II and III, and IV and V. Clinical use of NLP may help to individualize functional characterization and management. WHAT THIS PAPER ADDS: Natural language processing (NLP) applied to the electronic health record (EHR) can predict ambulatory status in children with cerebral palsy (CP). NLP provides good prediction of Gross Motor Function Classification System level in children with CP using the EHR. NLP methods described could be integrated in an EHR system to provide real-time information.

Electronic health record and patterns of care for children with cerebral palsy.

AIM: To characterize the patterns of care of children with cerebral palsy (CP) in a tertiary healthcare system. METHOD: Electronic health record data from 2009 to 2019 were extracted for children with CP. Machine learning hierarchical clustering was used to identify clusters of care. The ratio of in-person to care coordination visits was calculated for each specialty. RESULTS: The sample included 6369 children with CP (55.7% males, 44.3% females, 76.2% white, 94.7% non-Hispanic; with a mean age of 8y 2mo [SD 5y 10mo; range 0-21y; median 7y 1mo]) at the time of diagnosis. A total of 3.7 million in-person visits and care coordination notes were identified across 34 specialties. The duration of care averaged 5 years 5 months with five specialty interactions and 21.8 in-person visits per year per child. Seven clusters of care were identified, including: musculoskeletal and function; neurological; high-frequency/urgent care services; procedures; comorbid diagnoses; development and behavioral; and primary care. Network analysis showed shared membership among several clusters. INTERPRETATION: Coordination of care is a central element for children with CP. Medical informatics, machine learning, and big data approaches provide unique insights into care delivery to inform approaches to improve outcomes for children with CP. What this paper adds Seven primary clusters of care were identified: musculoskeletal and function; neurological; high-frequency/urgent care services; procedures; comorbid diagnoses; development and behavioral; and primary care. The in-person to care coordination visit ratio was 1:5 overall for healthcare encounters. Most interactions with care teams occur outside of in-person visits. The ratio of in-person to care coordination activities differ by specialty.

Describing the Delivery of Evidence-Based Physical Therapy Intervention to Individuals With Cerebral Palsy.

PURPOSE: To characterize by evidence grades and examine variation in type of physical therapy intervention delivered in routine clinical care in individuals with cerebral palsy (CP). METHODS: Retrospective data collection from the electronic record over 1 year at a tertiary care pediatric outpatient therapy division. RESULTS: Four hundred sixty-five individuals with CP received 28 344 interventions during 4335 treatment visits. Sixty-six percent of interventions were evidence-based interventions (EBIs). Significant variation was demonstrated across Gross Motor Function Classification System levels, with children classified as level V receiving the least and level III the most. The most frequent EBIs delivered were caregiver education, motor control, functional strengthening, ankle-foot orthoses, treadmill training, and fit of adaptive equipment. CONCLUSIONS: Further work is needed to determine whether amount of EBI is related to better outcomes. Combining this information with other aspects of dose (intensity, time, and frequency) may elucidate the contribution of each with outcomes.

Population pharmacokinetics of oral baclofen in pediatric patients with cerebral palsy.

OBJECTIVE: To characterize the population pharmacokinetics (PK) of oral baclofen and assess impact of patient-specific covariates in children with cerebral palsy (CP) in order to support its clinical use. SUBJECTS DESIGN: Children (2-17 years of age) with CP received a dose of titrated oral baclofen from 2.5 mg 3 times a day to a maximum tolerated dose of up to 20 mg 4 times a day. PK sampling followed titration of 10-12 weeks. Serial R- and S-baclofen plasma concentrations were measured for up to 16 hours in 49 subjects. Population PK modeling was performed using NONMEM 7.1 (ICON PLC; Ellicott City, Maryland). RESULTS: R- and S-baclofen showed identical concentration-time profiles. Both baclofen enantiomers exhibited linear and dose/kg-proportional PK, and no sex differences were observed. Average baclofen terminal half-life was 4.5 hours. A 2-compartment PK model with linear elimination and transit absorption steps adequately described concentration-time profiles of both baclofen enantiomers. The mean population estimate of apparent clearance/F was 0.273 L/h/kg with 33.4% inter-individual variability (IIV), and the apparent volume of distribution (Vss/F) was 1.16 L/kg with 43.9% IIV. Delayed absorption was expressed by a mean transit time of 0.389 hours with 83.7% IIV. Body weight, a possible genetic factor, and age were determinants of apparent clearance in these children. CONCLUSION: The PK of oral baclofen exhibited dose-proportionality and were adequately described by a 2-compartment model. Our population PK findings suggest that baclofen dosage can be based on body weight (2 mg/kg per day) and the current baclofen dose escalation strategy is appropriate in the treatment of children with CP older than 2 years of age.

Homozygous mutation in SAMHD1 gene causes cerebral vasculopathy and early onset stroke.

We describe an autosomal recessive condition characterized with cerebral vasculopathy and early onset of stroke in 14 individuals in Old Order Amish. The phenotype of the condition was highly heterogeneous, ranging from severe developmental disability to normal schooling. Cerebral vasculopathy was a major hallmark of the condition with a common theme of multifocal stenoses and aneurysms in large arteries, accompanied by chronic ischemic changes, moyamoya morphology, and evidence of prior acute infarction and hemorrhage. Early signs of the disease included mild intrauterine growth restriction, infantile hypotonia, and irritability, followed by failure to thrive and short stature. Acrocyanosis, Raynaud's phenomenon, chilblain lesions, low-pitch hoarse voice, glaucoma, migraine headache, and arthritis were frequently observed. The early onset or recurrence of strokes secondary to cerebral vasculopathy seems to always be associated with poor outcomes. The elevated erythrocyte sedimentation rate (ESR), IgG, neopterin, and TNF-α found in these patients suggested an immune disorder. Through genomewide homozygosity mapping, we localized the disease gene to chromosome (Chr) 20q11.22-q12. Candidate gene sequencing identified a homozygous mutation, c.1411-2A > G, in the SAMHD1 gene, being associated with this condition. The mutation appeared at the splice-acceptor site of intron 12, resulted in the skipping of exon 13, and gave rise to an aberrant protein with in-frame deletion of 31 amino acids. Immunoblotting analysis showed lack of mutant SAMHD1 protein expression in affected cell lines. The function of SAMHD1 remains unclear, but the inflammatory vasculopathies of the brain found in the patients with SAMHD1 mutation indicate its important roles in immunoregulation and cerebral vascular hemeostasis.

A big data approach to evaluate receipt of optimal care in childhood cerebral palsy.

PURPOSE: Through automated electronic health record (EHR) data extraction and analysis, this project systematically quantified actual care delivery for children with cerebral palsy (CP) and evaluated alignment with current evidence-based recommendations. METHODS: Utilizing EHR data for over 8000 children with CP, we developed an approach to define and quantify receipt of optimal care, and pursued proof-of-concept with two children with unilateral CP, Gross Motor Function Classification System (GMFCS) Level II. Optimal care was codified as a cluster of four components including physical medicine and rehabilitation (PMR) care, spasticity management, physical therapy (PT), and occupational therapy (OT). A Receipt of Care Score (ROCS) quantified the degree of adherence to recommendations and was compared with the Pediatric Outcomes Data Collection Instrument (PODCI) and Pediatric Quality of Life Inventory (PEDS QL). RESULTS: The two children (12 year old female, 13 year old male) had nearly identical PMR and spasticity component scores while PT and OT scores were more divergent. Functional outcomes were higher for the child who had higher adjusted ROCS. CONCLUSIONS: ROCSs demonstrate variation in real-world care delivered over time and differentiate between components of care. ROCSs reflect overall function and quality of life. The ROCS methods developed are novel, robust, and scalable and will be tested in a larger sample.IMPLICATIONS FOR REHABILITATIONOptimal practice, with an emphasis on integrated multidisciplinary care, can be defined and quantified utilizing evidence-based recommendations.Receipt of optimal care for childhood cerebral palsy can be scored using existing electronic health record data.Big Data approaches can contribute to the understanding of current care and inform approaches for improved care.

White matter characteristics in children with cerebral palsy prior to selective dorsal rhizotomy: a multicenter diffusion tensor imaging study.

OBJECTIVE: The aims of this study were to 1) assess and quantify white matter (WM) microstructural characteristics derived from diffusion tensor imaging (DTI) in children with cerebral palsy (CP) prior to selective dorsal rhizotomy (SDR), and 2) investigate potential associations between WM diffusion properties and gross motor function and spasticity in children with spastic CP who underwent SDR. METHODS: This study is a multisite study based on DT images acquired prior to SDR as well as postoperative outcome data. DTI data collected from two sites were harmonized using the ComBat approach to minimize intersite scanner difference. The DTI abnormalities between children with spastic CP and controls were analyzed and correlated with the severity of impaired mobility based on the Gross Motor Function Classification System (GMFCS). The improvement in gross motor function and spasticity after SDR surgery was assessed utilizing the Gross Motor Function Measure-66 (GMFM-66), the Modified Tardieu Scale (MTS), and the modified Ashworth scale (MAS). Alterations in these outcome measures were quantified in association with DTI abnormalities. RESULTS: Significant DTI alterations, including lower fractional anisotropy (FA) in the genu of the corpus callosum (gCC) and higher mean diffusivity (MD) in the gCC and posterior limb of the internal capsule (PLIC), were found in children in the SDR group when compared with the age-matched control group (all p < 0.05). Greater DTI alterations (FA in gCC and MD in gCC and PLIC) were associated with lower mobility levels as determined based on GMFCS level (p < 0.05). The pre- to post-SDR improvement in motor function based on GMFM-66 was statistically significant (p = 0.006 and 0.002 at 6-month and 12-month follow-ups, respectively). The SDR efficacy was also identified as improving spasticity in lower-extremity muscle groups assessed with the MTS and MAS. Partial correlation analysis presented a significant association between pre- to post-SDR MTS alteration and DTI abnormalities. CONCLUSIONS: The findings in the present study provided initial quantitative evidence to establish the WM microstructural characteristics in children with spastic CP prior to SDR surgery. The study generated data for the association between baseline DTI characteristics and mobility in children with CP prior to SDR surgery. The study also demonstrated SDR efficacy in improving motor function and spasticity based on the GMFM-66, MTS, and MAS, respectively, in association with DTI data.

Early Cerebral Palsy Detection and Intervention.

Early identification of cerebral palsy (CP) facilitates optimal care, support, and outcomes for children and their families. Ideally, infants with risk factors or developmental deviations should be evaluated early using standardized assessments of neurodevelopment and brain imaging. If a diagnosis of CP or high risk for CP (HRCP) is established, specialized, evidence-informed therapy and family support should be initiated. With task-specific motor skill training and an enriched environment, infants with CP show greater gross motor and cognitive gains. These enhanced outcomes are only achievable with early diagnosis and subsequent intervention.

Assessments and Interventions for Sleep Disorders in Infants With or at High Risk for Cerebral Palsy: A Systematic Review.

BACKGROUND: Children with cerebral palsy (CP) are five times more likely than typically developing children to have sleep problems, resulting in adverse outcomes for both children and their families. The purpose of this systematic review was to gather current evidence regarding assessments and interventions for sleep in children under age 2 years with or at high risk for CP and integrate these findings with parent preferences. METHODS: Five databases (CINAHL, EMBASE, OVID/Medline, SCOPUS, and PsycINFO) were searched. Included articles were screened using preferred reporting items for systematic reviews and meta-analyses guidelines, and quality of the evidence was reviewed using best evidence tools by two independent reviewers at minimum. An online survey was conducted regarding parent preferences through social media channels. RESULTS: Eleven articles met inclusion criteria. Polysomnography emerged as the only high-quality assessment for the population. Three interventions (medical cannabis, surgical interventions, and auditory, tactile, visual, and vestibular stimulations) were identified; however, each only had one study of effectiveness. The quality of evidence for polysomnography was moderate, while the quality and quantity of the evidence regarding interventions was low. Survey respondents indicated that sleep assessments and interventions are highly valued, with caregiver-provided interventions ranked as the most preferable. CONCLUSIONS: Further research is needed to validate affordable and feasible sleep assessments compared to polysomnography as the reference standard. In the absence of diagnosis-specific evidence of safety and efficacy of sleep interventions specific to young children with CP, it is conditionally recommended that clinicians follow guidelines for safe sleep interventions for typically developing children.

Assessments and Interventions for Spasticity in Infants With or at High Risk for Cerebral Palsy: A Systematic Review.

BACKGROUND: The majority of children with cerebral palsy develop spasticity, which interferes with motor development, function, and participation. This systematic review appraised current evidence regarding assessments and interventions for spasticity in children aged less than two years with or at high risk for cerebral palsy and integrated findings with parent preferences. METHODS: Five databases (CINAHL, EMBASE, OVID/Medline, SCOPUS, and PsycINFO) were searched. Included articles were screened using PRISMA guidelines. Quality of the evidence was reviewed by two independent reviewers using Quality Assessment of Diagnostic Accuracy Studies, second edition (QUADAS-2), the RTI Item Bank on Risk of Bias and Precision of Observational Studies (RTI), or The Cochrane Collaboration's tool for assessing risk of bias in randomized trials (RoB). An online survey was conducted regarding parent preferences through social media channels. RESULTS: Twelve articles met inclusion criteria. No high-quality assessment tool emerged for this population. Six interventions (botulinum toxin-A, orthotic use, radial extracorporeal shock wave therapy, erythropoietic stimulating agents, medical cannabis, and homeopathy) were identified. There was low-quality evidence for the use of botulinum toxin-A and radial extracorporeal shock wave therapy to improve short-term outcomes. Survey respondents indicated that spasticity assessments and interventions are highly valued, with nonpharmacologic interventions ranked most preferably. CONCLUSIONS: Further research is needed to validate assessments for spasticity in children younger than two years. Conditional recommendations can be made for botulinum toxin-A and radial extracorporeal shock wave therapy based on low level of evidence to reduce spasticity in children aged less than two years.

A Systematic Review of Assessments and Interventions for Chronic Pain in Young Children With or at High Risk for Cerebral Palsy.

BACKGROUND: Pain is common in children with cerebral palsy. The purpose of this systematic review was to evaluate the evidence regarding assessments and interventions for chronic pain in children aged ≤2 years with or at high risk for cerebral palsy. METHODS: A comprehensive literature search was performed. Included articles were screened using PRISMA guidelines and quality of evidence was reviewed using best-evidence tools by independent reviewers. Using social media channels, an online survey was conducted to elicit parent preferences. RESULTS: Six articles met criteria. Parent perception was an assessment option. Three pharmacologic interventions (gabapentin, medical cannabis, botulinum toxin type A) and 1 nonpharmacologic intervention were identified. Parent survey report parent-comfort and other nonpharmacologic interventions ranked as most preferable. CONCLUSION: A conditional GRADE recommendation was in favor of parent report for pain assessment. Clinical trials are sorely needed because of the lack of evidence for safety and efficacy of pharmacologic interventions.

Outcome Assessment and Function in Cerebral Palsy.

Care and research in childhood cerebral palsy (CP) continue to evolve. As our understanding of CP grows more nuanced, so grows our need to describe function, activities, challenges, adaptations of children with CP. In CP, robust means of measuring outcomes are vital to understanding utility of treatments. Research must accurately measure meaningful constructs of children with CP as a reliable ruler to establish if interventions produce useful effects. This article addresses the challenges of outcome measurement in CP, current status of outcome measurement in CP, and issues of understanding change in childhood CP.

Measuring what matters in cerebral palsy: a breadth of important domains and outcome measures.

UNLABELLED: Vargus-Adams JN, Martin LK. Measuring what matters in cerebral palsy: a breadth of important domains and outcome measures. OBJECTIVE: To establish domains of importance for evaluating therapeutic effects in childhood cerebral palsy (CP) and the best means of evaluating those domains. DESIGN: Delphi iterative survey. SETTING: Tertiary pediatric hospital with assessments conducted via mail or Internet. PARTICIPANTS: Youth with CP (n=21), parents of children with CP (n=23), and medical professionals (n=39). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Identification of "the things you find most important to consider when you evaluate the effects of an intervention for yourself/your child/your patient with cerebral palsy" as domains of concern, followed by the best outcome measures to assess each of the domains, including preference rankings of those measures. RESULTS: Eight domains of importance were identified: impairment, general health, gross motor skills, self-care/fine motor skills, speech/communication, integration/participation, quality of life, and caregiver issues. All domains were viewed as important with no clear demarcation to allow reduction in number. Only quality of life emerged as being most important. Medical professionals suggested 10 to 27 different outcome measures for assessing each domain. Few of these measures, including the Gross Motor Function Measure and the Cerebral Palsy Quality of Life Questionnaire, were broadly endorsed by the medical professionals. CONCLUSIONS: Parents, youth, and medical professionals identify a wide range of arenas that they would like to see impacted by interventions for CP. These arenas can be consolidated into 8 domains. Although many outcome measures are available to evaluate these domains, few of the measures are widely preferred. Further work may determine optimal assessment strategies and provide guidance for therapeutic decisions.

Inconsistencies with physical functioning and the child health questionnaire in children with cerebral palsy.

OBJECTIVES: To explore the performance of the Physical Functioning (PF) subscale of the Child Health Questionnaire (CHQ) in children with cerebral palsy (CP). STUDY DESIGN: Parents of 177 children and adolescents (age 3 to 18 years) with CP completed the CHQ -Parent Form 50. Severity of CP was assessed using the 5-level Gross Motor Function Classification System (GMFCS), in which higher levels reflect more severe impairment. RESULTS: PF scores were negatively correlated with GMFCS classification (R = -0.62) and were distributed bimodally in subjects with severe motor impairment. For GMFCS classifications IV and V (n = 59), PF scores were very low (means, 9 to 28; medians, 0 to 8); however, 12% of these subjects had excellent PF scores (> 88) despite being nonambulatory. CONCLUSIONS: Although the CHQ PF subscale correlated well with the GMFCS, the CHQ questions on physical functioning resulted in unexpected responses in approximately 1 in 8 subjects with severe CP. These unanticipated responses to the PF subscale questions may be due to ambiguity in the questions (which do not differentiate between health problems and disability) or to alternative parental interpretation of physical functioning. Confusion in differentiating health status and functional status may make the CHQ less useful in children with significant disabilities.

Overview of Four Functional Classification Systems Commonly Used in Cerebral Palsy.

Cerebral palsy (CP) is the most common physical disability in childhood. CP comprises a heterogeneous group of disorders that can result in spasticity, dystonia, muscle contractures, weakness and coordination difficulty that ultimately affects the ability to control movements. Traditionally, CP has been classified using a combination of the motor type and the topographical distribution, as well as subjective severity level. Imprecise terms such as these tell very little about what a person is able to do functionally and can impair clear communication between providers. More recently, classification systems have been created employing a simple ordinal grading system of functional performance. These systems allow a more precise discussion between providers, as well as better subject stratification for research. The goal of this review is to describe four common functional classification systems for cerebral palsy: the Gross Motor Function Classification System (GMFCS), the Manual Ability Classification System (MACS), the Communication Function Classification System (CFCS), and the Eating and Drinking Ability Classification System (EDACS). These measures are all standardized, reliable, and complementary to one another.