ObjectiveTo develop an Overall Pediatric Health Standard Set (OPH-SS) of outcome measures that captures what matters to young people and their families and recognising the biopsychosocial aspects of health for all children and adolescents regardless of health condition.DesignA modified Delphi process.SettingThe International Consortium for Health Outcomes Measurement convened an international Working Group (WG) comprised of 23 international experts from 12 countries in the field of paediatrics, family medicine, psychometrics as well as patient advisors. The WG participated in 11 video-conferences, through a modified Delphi process and 9 surveys between March 2018 and January 2020 consensus was reached on a final recommended health outcome standard set. By a literature review conducted in March 2018, 1136 articles were screened for clinician and patient-reported or proxy-reported outcomes. Further, 4315 clinical trials and 12 paediatric health surveys were scanned. Between November 2019 and January 2020, the final standard set was endorsed by a patient validation (n=270) and a health professional (n=51) survey.ResultsFrom a total of 63 identified outcomes, consensus was formed on a standard set of outcome measures that comprises 10 patient-reported outcomes, 5 clinician-reported measures, and 6 case-mix variables. The four developmental age-specific packages (ie, 0–5, 6–12, 13–17, 18–24 years) include either five or six measures with an average time for completion of 20 min.ConclusionsThe OPH-SS is a starting point to drive value-based paediatric healthcare delivery from a global perspective for enhancing child and adolescent physical health and psychosocial well-being.

Objective: To identify barriers and facilitators to international implementation of a prospective system for standardized outcomes measurement in cleft care. Design: Cleft teams that have implemented the International Consortium for Health Outcomes Measurement Standard Set for cleft care were invited to participate in this 2-part qualitative study: (1) an exploratory survey among clinicians, health information technology professionals, and project coordinators, and (2) semistructured interviews of project leads. Thematic content analysis was performed, with organization of themes according to the dimensions of the reach, effectiveness, adoption, implementation and maintenance (RE-AIM) framework: reach, effectiveness, adoption, implementation, and maintenance. Results: Four cleft teams in Europe and North America participated in this study. Thirteen participants completed exploratory questionnaires and 5 interviewees participated in follow-up interviews. Survey responses and thematic content analysis revealed common facilitators and barriers to implementation at all sites. Teams reach patients either via email or during the clinic visit to capture patient-reported outcomes. Adopting routine data collection is enhanced by aligning priorities at the organizational and cleft team level. Streamlining workflows and developing an efficient data collection platform are necessary early on, followed by pilot testing or stepwise implementation. Regular meetings and financial resources are crucial for implementing, sustaining, analyzing collected data, and providing feedback to health care professionals and patients. Fostering patient-centered care was articulated as a positive outcome, whereas time presented challenges across all RE-AIM dimensions. Conclusions: Identified themes can inform ongoing implementation efforts. Intentionally investing time to lay a sound foundation early on will benefit every phase of implementation and help overcome barriers such as lack of support or motivation.

<b><i>Introduction:</i></b> Approximately, one in ten infants is born preterm or requires hospitalization at birth. These complications at birth have long-term consequences that can extend into childhood and adulthood. Timely detection of developmental delay through surveillance could enable tailored support for these babies and their families. However, the possibilities for follow-up are limited, especially in middle- and low-income countries, and the tools to do so are either not available or too expensive. A standardized and core set of outcomes for neonates, with feasible tools for evaluation and follow-up, could result in improving quality, enhance shared decision-making, and enable global benchmarking. <b><i>Methods:</i></b> The International Consortium for Health Outcomes Measurement (ICHOM) convened an international working group, which was comprised of 14 health-care professionals (HCP) and 6 patient representatives in the field of neonatal care. An outcome set was developed using a three-round modified Delphi process, and it was endorsed through a patient representative-validation survey and an HCP survey. <b><i>Results:</i></b> A literature review revealed 1,076 articles and 26 registries which were screened for meaningful outcomes, patient-reported outcome measures, clinical measures, and case mix variables. This resulted in a neonatal set with 21 core outcomes covering three domains (physical, social, and mental functioning) and 14 tools to assess these outcomes at three timepoints. <b><i>Discussion:</i></b> This set can be implemented globally and it will allow comparison of outcomes across different settings and countries. The transparent consensus-driven development process which involved stakeholders and professionals from all over the world ensures global relevance.

No abstract

Introduction: Clinical data within the electronic health record (EHR) combined with artificial intelligence (AI) and machine learning (ML) offer the promise of rapid advancement of knowledge at the point of care. Hypothesis: We hypothesized that aggregating clinical data with preservation of relational elements will yield a more precise and less biased representation of patient data for predictive analytics. We leveraged these data to predict clinically significant bleeding in the ECMO-supported population. Methods: The data of children 0-19 years managed on ECMO for first run cardiac indications in a single center between 1/2010-12/2020 were analyzed. Bleeding Day was defined as any 24-hour period which included pulmonary, gastrointestinal, intracranial or surgical wound hemorrhage, and/or surgical intervention or Factor VIIa administration for hemorrhage control. EHR data documenting the ECMO episode and embedding relational elements were used to inform 1) a multivariable logistic regression model matching a previously- performed analysis using manually extracted data [1], and 2) a feature-limited graph neural network (GNN) model of bleeding. Results: There were 272 patients supported with ECMO for total 2,012 days which informed the analysis, with median age 0.4 [IQR 0.03, 3.30] years, 56% male and 14% of days including a bleeding event. Direct comparison of the EHR-derived logistic regression model with previously published manual results are presented in Table 1. Inclusion of the EHR-derived covariates in a GNN model achieved similar operating characteristics. Conclusions: EHR-derived AI-prediction models of bleeding in this complex patient population are at least as accurate as models with manual data and traditional statistical analysis, but with a known pathway to potentially more accurate predictions. This methodology can be replicated to other conditions, allowing rapid insights towards a learning healthcare system.

No abstract