SBIR/STTR Award attributes
PROJECT SUMMARY AND ABSTRACTPediatric specialists are often required to identify infants who are likely to suffer poor neurodevelopmental outcomeincluding Cerebral PalsyCPCP is the most common developmental disability among children in the United States and results from several factorsincluding low weight for gestational agepremature birthand strokeAlthough MRI and cranial ultrasoundcUSprovide valuable structural information in the preterm periodthey have moderate sensitivity to CP and require transportation of the infantOver the pastyearsnumerous studies have validated the clinical potential of General Movement AssessmentGMAfor CP risk identificationDuring the early periodweeks toweeks gestational agethe presence of Cramped Synchronized General MovementsCSGMshas demonstrated very high sensitivity and specificity for CPconjointly ranging fromCSGMs are assessed while preterm infants are still in an acute care facilityNICUand can inform the clinician independentlyand in combination with cUS and MRIDespite its potentialGMA is available in only a few clinical centersas adoption and routine application depend on lengthycost intensive observation and availability of specially trained ratersA Cerebral Palsy Risk Identification SystemCPRISis proposed that will automate GMA for bedside evaluations in both preterm and postterm periodsThe CPRIS constitutes a key enabling technology not only for routine risk identificationbut also for establishing disease trajectory and potentially differentiating CP subtypes and assessing efficacy of emerging treatments along the early developmental continuumPreliminary studies at UC Irvine have demonstrated that GMA analysis for CSGMs can be automated by quantifying infant limb movement using highly miniaturizedaxis wireless accelerometers and classifying CSGMs using a patented Markov type approach that merges an application specific Erlang Cox state transition model with a Dynamic Bayesian NetworkEC DBNtreating instantaneous machine learning classification values as observations and explicitly modeling CSGMand non CSGMduration and intervalIn Phase Ithis approach will be utilized in a comparative evaluation of two movement measurement modalities to determine which has the best overall performance and clinical utility at three leading NICU centersInfant movement data will be concurrently acquired using an advancedsecond generation prototype wireless accelerometer systemCPRIS Aand a high definitionDinfraredoptical cameraCPRIS OThe optical modality offers significant potential advantages as it requires no infant contact and can monitor unattendedintermittentlyover weeks or monthsHoweverits potential for GMA automation must be systematically evaluatedClassifier results from both modalities will be compared to expert rater consensus inpreterm infantsThe primary outcome will be CSGM identification accuracyas determined by ROC AUC analyseswith a threshold for success ofAdditional comparative performance measures include reliability and practicability in the NICU environmentAn Advisory Committee of experts in the fields of neonatologypediatrics and cerebral palsy will evaluate project results and advise on the clinical potential of each modalityPROJECT NARRATIVE Cerebral palsy is the most common physical disability in childhoodwith a prevalence ofcases perin high income countriesThe overall project goal is to develop a computerized hardware software system capable of identifying preterm infants at high risk of developing cerebral palsyCPbased on the systematic identification of specific patterns of movement derived featuresThe Cerebral Palsy Risk Identification SystemCPRISwill enable clinical staff with only minimal training to cost effectively implement General Movement AssessmentGMAfor Cramped Synchronous General MovementsCSGMswith interpretive reporting performed automaticallyThe CPRIS constitutes a key enabling technology for advancement in the identificationcharacterization and treatment assessment of CP
