Emergency department visits and boarding for pediatric patients with suicidality before and during the COVID-19 pandemic

Zipursky, Amy R.; Olson, Karen L.; Bode, Louisa; Geva, Alon; Jones, James; Mandl, Kenneth D.; McMurry, Andrew

doi:10.1371/journal.pone.0286035

Cited by 5 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…17 Computable phenotypes were derived from FHIR observation vital signs at critical values of 140/90 mm/hg. Custom value sets were user defined for self-harm in the domains of mental health study 18 and opioid overdose.…”

Section: Resultsmentioning

confidence: 99%

Cumulus: A federated EHR-based learning system powered by FHIR and AI

McMurry,

Gottlieb,

Miller

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Objective. To address challenges in large-scale electronic health record (EHR) data exchange, we sought to develop, deploy, and test an open source, cloud-hosted app 'listener' that accesses standardized data across the SMART/HL7 Bulk FHIR Access application programming interface (API). Methods. We advance a model for scalable, federated, data sharing and learning. Cumulus software is designed to address key technology and policy desiderata including local utility, control, and administrative simplicity as well as privacy preservation during robust data sharing, and AI for processing unstructured text. Results. Cumulus relies on containerized, cloud-hosted software, installed within a healthcare organization's security envelope. Cumulus accesses EHR data via the Bulk FHIR interface and streamlines automated processing and sharing. The modular design enables use of the latest AI and natural language processing tools and supports provider autonomy and administrative simplicity. In an initial test, Cumulus was deployed across five healthcare systems each partnered with public health. Cumulus output is patient counts which were aggregated into a table stratifying variables of interest to enable population health studies. All code is available open source. A policy stipulating that only aggregate data leave the institution greatly facilitated data sharing agreements. Discussion and Conclusion. Cumulus addresses barriers to data sharing based on (1) federally required support for standard APIs, (2) increasing use of cloud computing, and (3) advances in AI. There is potential for scalability to support learning across myriad network configurations and use cases.

show abstract

Section: Resultsmentioning

confidence: 99%

Cumulus: A federated EHR-based learning system powered by FHIR and AI

McMurry,

Gottlieb,

Miller

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Pediatric Hospitalizations and Emergency Department Visits Related to Mental Health Conditions and Self-Harm

Valtuille,

Trebossen,

Ouldali

et al. 2024

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceMental disorders among the pediatric population are a major area of public health concern. Little is known regarding changes in pediatric hospital resource use related to mental health (MH) long after the onset of the COVID-19 pandemic in March 2020.ObjectiveTo assess rates and trends of hospitalizations and emergency department (ED) visits related to MH and self-harm (SH) among children before and during the 3 years following the pandemic onset.Design, Setting, and ParticipantsThis cross-sectional study used national hospital data. The study sample included all MH- and SH-related hospitalizations and ED visits among children aged 6 to 17 years in France between January 1, 2016, to May 31, 2023.Main Outcomes and MeasuresInterrupted time-series analysis of monthly rates of MH- and SH-related hospitalizations and ED visits per 100 000 children was conducted to assess changes before and every year after the pandemic onset. Rate ratios (RRs) between estimated and expected rates were calculated.ResultsOverall, 583 244 hospitalizations (81.4% for MH and 18.6% for SH) and 432 725 ED visits (79.9% for MH and 20.1% for SH) were analyzed. The mean (SD) age of the children was 13.7 (2.9) and 14.8 (1.7) years for MH-related and SH-related hospitalizations, respectively, and 14.2 (2.6) and 14.6 (2.1) years for MH-related and SH-related ED visits, respectively. For MH-related hospitalizations, 52.6% were female and 47.4% were male; for SH-related hospitalizations, 83.1% were female and 16.9% were male. For MH-related ED visits, 62.8% were female and 37.2% were male; for SH-related ED visits, 77.4% were female and 22.6% were male. Before the pandemic, an increasing trend in all monthly rates, except that of MH-related hospitalizations, was observed. After an immediate decrease in hospitalization and ED visit rates during the initial pandemic period (March 1 to May 31, 2020), trends increased in the first 2 years following the pandemic onset and decreased thereafter. Overall, rates of MH-related hospitalizations and ED visits exceeded expected rates in only the second year after the pandemic onset, with increases of 6.0% (RR, 1.06 [95% CI, 1.05-1.06]) and 5.0% (RR, 1.05 [95% CI, 1.04-1.05]), respectively. However, rates of hospitalizations and ED visits for behavioral syndromes (mainly eating and sleeping disorders) persistently exceeded expected rates, with increases of 29.0% (RR, 1.29 [95% CI, 1.25-1.34]) and 26.0% (RR, 1.26 [95% CI, 1.21-1.31]) in the third year, respectively. Likewise, rates of SH-related hospitalizations and ED visits persistently rose above expected rates, with increases of 29.0% (RR, 1.29 [95% CI, 1.26-1.32]) and 43.0% (RR, 1.43 [95% CI, 1.40-1.47]) in the third year, respectively.Conclusions and RelevanceIn this cross-sectional study, persistent increases in the use of hospital resources to treat eating and sleeping disorders and intentional SH among pediatric patients were observed long after the onset of the COVID-19 pandemic. These findings warrant future research to identify persistent stress factors in children.

show abstract

Cumulus: a federated electronic health record-based learning system powered by Fast Healthcare Interoperability Resources and artificial intelligence

McMurry,

Gottlieb,

Miller

et al. 2024

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

Objective To address challenges in large-scale electronic health record (EHR) data exchange, we sought to develop, deploy, and test an open source, cloud-hosted app “listener” that accesses standardized data across the SMART/HL7 Bulk FHIR Access application programming interface (API). Methods We advance a model for scalable, federated, data sharing and learning. Cumulus software is designed to address key technology and policy desiderata including local utility, control, and administrative simplicity as well as privacy preservation during robust data sharing, and artificial intelligence (AI) for processing unstructured text. Results Cumulus relies on containerized, cloud-hosted software, installed within a healthcare organization’s security envelope. Cumulus accesses EHR data via the Bulk FHIR interface and streamlines automated processing and sharing. The modular design enables use of the latest AI and natural language processing tools and supports provider autonomy and administrative simplicity. In an initial test, Cumulus was deployed across 5 healthcare systems each partnered with public health. Cumulus output is patient counts which were aggregated into a table stratifying variables of interest to enable population health studies. All code is available open source. A policy stipulating that only aggregate data leave the institution greatly facilitated data sharing agreements. Discussion and Conclusion Cumulus addresses barriers to data sharing based on (1) federally required support for standard APIs, (2) increasing use of cloud computing, and (3) advances in AI. There is potential for scalability to support learning across myriad network configurations and use cases.

show abstract

Emergency department visits and boarding for pediatric patients with suicidality before and during the COVID-19 pandemic

Cited by 5 publications

References 35 publications

Cumulus: A federated EHR-based learning system powered by FHIR and AI

Cumulus: A federated EHR-based learning system powered by FHIR and AI

Pediatric Hospitalizations and Emergency Department Visits Related to Mental Health Conditions and Self-Harm

Cumulus: a federated electronic health record-based learning system powered by Fast Healthcare Interoperability Resources and artificial intelligence

Contact Info

Product

Resources

About