Involuntary admissions to psychiatric hospitals are on the rise. If patients at elevated risk of involuntary admission could be identified, prevention may be possible. Our aim was to develop and validate a prediction model for involuntary admission of patients receiving care within a psychiatric service system using machine learning trained on routine clinical data from electronic health records (EHRs).

EHR data from all adult patients who had been in contact with the Psychiatric Services of the Central Denmark Region between 2013 and 2021 were retrieved. We derived 694 patient predictors (covering e.g. diagnoses, medication, and coercive measures) and 1134 predictors from free text using term frequency-inverse document frequency and sentence transformers. At every voluntary inpatient discharge (prediction time), without an involuntary admission in the 2 years prior, we predicted involuntary admission 180 days ahead. XGBoost and elastic net models were trained on 85% of the dataset. The models with the highest area under the receiver operating characteristic curve (AUROC) were tested on the remaining 15% of the data.

The model was trained on 50 634 voluntary inpatient discharges among 17 968 patients. The cohort comprised of 1672 voluntary inpatient discharges followed by an involuntary admission. The best XGBoost and elastic net model from the training phase obtained an AUROC of 0.84 and 0.83, respectively, in the test phase.

A machine learning model using routine clinical EHR data can accurately predict involuntary admission. If implemented as a clinical decision support tool, this model may guide interventions aimed at reducing the risk of involuntary admission.

More than 5 million children in the United States experience food insecurity (FI), yet little guidance exists regarding screening for FI. A prediction model of FI could be useful for healthcare systems and practices working to identify and address children with FI. Our objective was to predict FI using demographic, geographic, medical, and historic unmet health-related social needs data available within most electronic health records.

This was a retrospective longitudinal cohort study of children evaluated in an academic pediatric primary care clinic and screened at least once for FI between January 2017 and August 2021. American Community Survey Data provided additional insight into neighborhood-level information such as home ownership and poverty level. Household FI was screened using two validated questions. Various combinations of predictor variables and modeling approaches, including logistic regression, random forest, and gradient-boosted machine, were used to build and validate prediction models.

A total of 25,214 encounters from 8521 unique patients were included, with FI present in 3820 (15%) encounters. Logistic regression with a 12-month look-back using census block group neighborhood variables showed the best performance in the test set (C-statistic 0.70, positive predictive value 0.92), had superior C-statistics to both random forest (0.65, p < 0.01) and gradient boosted machine (0.68, p = 0.01), and showed the best calibration. Results were nearly unchanged when coding missing data as a category.

Although our models could predict FI, further work is needed to develop a more robust prediction model for pediatric FI.

Recruitment of participants into research studies remains a major concern for investigators. Using clinical teams to identify potentially eligible patients can present a significant barrier. To overcome this, we implemented a process for using our patient portal, called MyChart, as a new institutional recruitment option utilizing our electronic health record’s existing functionality.

To streamline the institutional approval process, we established a working group comprised of representatives from human subject protection, information technology, and privacy and vetted our process with many stakeholder groups. Our specific process for study approval is described and started with a consultation with our recruitment and retention function funded through our Clinical and Translational Science Award.

The time from consultation to the first message(s) sent ranged from 84 to 442 days and declined slightly over time. The overall patient response rate to MyChart messages about available research studies was 23% with one third of those saying they were interested in learning more. The response rate for Black and Hispanic patients was about 50% that of White patients.

Many different types of studies from any medical specialty successfully identified interested patients using this option. Study teams needed support in defining appropriate inclusion/exclusion criteria to identify the relevant population in the electronic health records and they needed assistance writing study descriptions in plain language. Using MyChart for recruitment addressed a critical barrier and opened up the opportunity to provide a full recruitment consultation to identify additional recruitment channels the study teams would not have considered otherwise.

Participation in the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC) has numerous benefits, yet many eligible children remain unenrolled. This qualitative study sought to explore perceptions of a novel electronic health record (EHR) intervention to facilitate referrals to WIC and improve communication/coordination between WIC staff and healthcare professionals.

WIC staff in three counties were provided EHR access and recruited to participate. An automated, EHR-embedded WIC participation screening and referral tool was implemented within 8 healthcare clinics; healthcare professionals within these clinics were eligible to participate. The interview guide was developed using the Consolidated Framework for Implementation Research to elicit perceptions of this novel EHR-based intervention. Semi-structured interviews were conducted via telephone. Interviews were recorded, transcribed, coded, and analyzed using thematic analysis.

Twenty semi-structured interviews were conducted with eight WIC staff, seven pediatricians, four medical assistants, and one registered nurse. Most participants self-identified as female (95%) and White (55%). We identified four primary themes: (1) healthcare professionals had a positive view of WIC but communication and coordination between WIC and healthcare professionals was limited prior to WIC having EHR access; (2) healthcare professionals favored WIC screening using the EHR but workflow challenges existed; (3) EHR connections between WIC and the healthcare system can streamline referrals to and enrollment in WIC; and (4) WIC staff and healthcare professionals recommended that WIC have EHR access.

A novel EHR-based intervention has potential to facilitate healthcare referrals to WIC and improve communication/coordination between WIC and healthcare systems.

Obtaining complete and accurate information in recruitment registries is essential for matching potential participants to research studies for which they qualify. Since electronic health record (EHR) systems are required to make patient data available to external systems, an interface between EHRs and recruitment registries may improve accuracy and completeness of volunteers’ profiles. We tested this hypothesis on ResearchMatch (RM), a disease- and institution-neutral recruitment registry with 1357 studies across 255 institutions.

We developed an interface where volunteers signing up for RM can authorize transfer of demographic data, medical conditions, and medications from the EHR into a registration form. We obtained feedback from a panel of community members to determine acceptability of the planned integration. We then developed the EHR interface and performed an evaluation study of 100 patients to determine whether RM profiles generated with EHR-assisted adjudication included more conditions and medications than those without the EHR connection.

Community member feedback revealed that members of the public were willing to authenticate into the EHR from RM with proper messaging about choice and privacy. The evaluation study showed that out of 100 participants, 75 included more conditions and 69 included more medications in RM profiles completed with the EHR connection than those without. Participants also completed the EHR-connected profiles in 16 fewer seconds than non-EHR-connected profiles.

The EHR to RM integration could lead to more complete profiles, less participant burden, and better study matches for many of the over 148,000 volunteers who participate in ResearchMatch.

Interventions to address social needs in clinical settings can improve child and family health outcomes. Electronic health record (EHR) tools are available to support these interventions but are infrequently used. This mixed-methods study sought to identify approaches for implementing social needs interventions using an existing EHR module in pediatric primary care.

We conducted focus groups and interviews with providers and staff (n = 30) and workflow assessments (n = 48) at four pediatric clinics. Providers and staff completed measures assessing the acceptability, appropriateness, and feasibility of social needs interventions. The Consolidated Framework for Implementation Research guided the study. A hybrid deductive-inductive approach was used to analyze qualitative data.

Median scores (range 1–5) for acceptability (4.9) and appropriateness (5.0) were higher than feasibility (3.9). Perceived barriers to implementation related to duplicative processes, parent disclosure, and staffing limitations. Facilitators included the relative advantage of the EHR module compared to existing documentation practices, importance of addressing social needs, and compatibility with clinic culture and workflow. Self-administered screening was seen as inappropriate for sensitive topics. Strategies identified included providing resource lists, integrating social needs assessments with existing screening questionnaires, and reducing duplicative documentation.

This study offers insight into the implementation of EHR-based social needs interventions and identifies strategies to promote intervention uptake. Findings highlight the need to design interventions that are feasible to implement in real-world settings. Future work should focus on integrating multiple stakeholder perspectives to inform the development of EHR tools and clinical workflows to support social needs interventions.

The electronic health record (EHR) and patient portal are used increasingly for clinical research, including patient portal recruitment messaging (PPRM). Use of PPRM has grown rapidly; however, best practices are still developing. In this study, we examined the use of PPRM at our institution and conducted qualitative interviews among study teams and patients to understand experiences and preferences for PPRM.

We identified study teams that sent PPRMs and patients that received PPRMs in a 60-day period. We characterized these studies and patients, in addition to the patients’ interactions with the PPRMs (e.g., viewed, responded). From these groups, we recruited study team members and patients for semi-structured interviews. A pragmatic qualitative inquiry framework was used by interviewers. Interviews were audio-recorded and analyzed using a rapid qualitative analysis exploratory approach.

Across ten studies, 35,037 PPRMs were sent, 33% were viewed, and 17% were responded to. Interaction rates varied across demographic groups. Six study team members completed interviews and described PPRM as an efficient and helpful recruitment method. Twenty-eight patients completed interviews. They were supportive of receiving PPRMs, particularly when the PPRM was relevant to their health. Patients indicated that providing more information in the PPRM would be helpful, in addition to options to set personalized preferences.

PPRM is an efficient recruitment method for study teams and is acceptable to patients. Engagement with PPRMs varies across demographic groups, which should be considered during recruitment planning. Additional research is needed to evaluate and implement recommended changes by study teams and patients.

To identify implementation strategies for collaborative care (CC) that are successful in the context of perinatal care.

Perinatal depression is one of the most common complications of pregnancy and is associated with adverse maternal, obstetric, and neonatal outcomes. Although treating depressive symptoms reduces risks to mom and baby, barriers to accessing psychiatric treatment remain. CC has demonstrated benefit in primary care, expanding access, yet few studies have examined the implementation of CC in perinatal care which presents unique characteristics and challenges.

We conducted qualitative interviews with 20 patients and 10 stakeholders from Collaborative Care Model for Perinatal Depression Support Services (COMPASS), a perinatal collaborative care (pCC) program implemented since 2017. We analyzed interview data by employing the Exploration, Preparation, Implementation, Sustainment (EPIS) framework to organize empirically selected implementation strategies from Expert Recommendations for Implementing Change (ERIC) to create a guide for the development of pCC programs.

We identified 14 implementation strategies used in the implementation of COMPASS. Strategies were varied, cutting across ERIC domains (eg, plan, educate, finance) and across EPIS contexts (eg, inner context – characteristics of the pCC program). The majority of strategies were identified by patients and staff as facilitators of pCC implementation. In addition, findings show opportunities for improving the implementation strategies used, such as optimal dissemination of educational materials for obstetric clinicians. The implementation of COMPASS can serve as a model for the process of building a pCC program. The identified strategies can support the implementation of this evidence-based practice for addressing postpartum depression.

The coronavirus disease 2019 (COVID-19) pandemic has required healthcare systems to meet new demands for rapid information dissemination, resource allocation, and data reporting. To help address these challenges, our institution leveraged electronic health record (EHR)–integrated clinical pathways (E-ICPs), which are easily understood care algorithms accessible at the point of care.

To describe our institution’s creation of E-ICPs to address the COVID-19 pandemic, and to assess the use and impact of these tools.

Urban academic medical center with adult and pediatric hospitals, emergency departments, and ambulatory practices.

Using the E-ICP processes and infrastructure established at our institution as a foundation, we developed a suite of COVID-19–specific E-ICPs along with a process for frequent reassessment and updating. We examined the development and use of our COVID-19–specific pathways for a 6-month period (March 1–September 1, 2020), and we have described their impact using case studies.

In total, 45 COVID-19–specific pathways were developed, pertaining to triage, diagnosis, and management of COVID-19 in diverse patient settings. Orders available in E-ICPs included those for isolation precautions, testing, treatments, admissions, and transfers. Pathways were accessed 86,400 times, with 99,081 individual orders were placed. Case studies demonstrate the impact of COVID-19 E-ICPs on stewardship of resources, testing optimization, and data reporting.

E-ICPs provide a flexible and unified mechanism to meet the evolving demands of the COVID-19 pandemic, and they continue to be a critical tool leveraged by clinicians and hospital administrators alike for the management of COVID-19. Lessons learned may be generalizable to other urgent and nonurgent clinical conditions.

The aim of this study was to assess the feasibility of the national electronic primary health care (PHC) database in Kyrgyzstan in producing information on the disease burden of the patient population and on the processes and quality of care of noncommunicable diseases (NCDs) in PHC.

Strengthening of the PHC is essential for low- and middle-income countries (LMICs) to tackle the increasing burden of NCDs. Capacity building and quality improvement require timely data on processes and quality of care.

A data extraction was carried out covering four PHC clinics in Bishkek in 2019 to pilot the use of the national data for quality assessment purposes. The data included patient-level information on all appointments in the clinics during the year 2018 and consisted of data of altogether 48 564 patients. Evaluation indicators of the WHO Package of Essential NCD Interventions framework were used to assess the process and outcome indicators of patients with hypertension or diabetes.

The extracted data enabled the identification of different patient populations and analyses of various process and outcome indicators. The legibility of data was good and the structured database enabled easy data extraction and variable formation on patient level. As an example of process and outcome indicators of those with hypertension, the blood pressure was measured at least on two occasions of 90% of women and 89% of men, and blood pressure control was achieved among 61% of women and 53% of men with hypertension. This study showed that a rather basic system gathering nationally patient-level data to an electronic database can serve as an excellent information source for national authorities. Investments should be made to develop electronic health records and national databases also in LMICs.

Paramedics received training in point-of-care ultrasound (POCUS) to assess for cardiac contractility during management of medical out-of-hospital cardiac arrest (OHCA). The primary outcome was the percentage of adequate POCUS video acquisition and accurate video interpretation during OHCA resuscitations. Secondary outcomes included POCUS impact on patient management and resuscitation protocol adherence.

A prospective, observational cohort study of paramedics was performed following a four-hour training session, which included a didactic lecture and hands-on POCUS instruction. The Prehospital Echocardiogram in Cardiac Arrest (PECA) protocol was developed and integrated into the resuscitation algorithm for medical non-shockable OHCA. The ultrasound (US) images were reviewed by a single POCUS expert investigator to determine the adequacy of the POCUS video acquisition and accuracy of the video interpretation. Change in patient management and resuscitation protocol adherence data, including end-tidal carbon dioxide (EtCO2) monitoring following advanced airway placement, adrenaline administration, and compression pauses under ten seconds, were queried from the prehospital electronic health record (EHR).

Captured images were deemed adequate in 42/49 (85.7%) scans and paramedic interpretation of sonography was accurate in 43/49 (87.7%) scans. The POCUS results altered patient management in 14/49 (28.6%) cases. Paramedics adhered to EtCO2 monitoring in 36/36 (100.0%) patients with an advanced airway, adrenaline administration for 38/38 (100.0%) patients, and compression pauses under ten seconds for 36/38 (94.7%) patients.

Paramedics were able to accurately obtain and interpret cardiac POCUS videos during medical OHCA while adhering to a resuscitation protocol. These findings suggest that POCUS can be effectively integrated into paramedic protocols for medical OHCA.

The SARS-CoV-2 pandemic has highlighted the need for rapid creation and management of ICU field hospitals with effective remote monitoring which is dependent on the rapid deployment and integration of an Electronic Health Record (EHR). We describe the use of simulation to evaluate a rapidly scalable hub-and-spoke model for EHR deployment and monitoring using asynchronous training.

We adapted existing commercial EHR products to serve as the point of entry from a simulated hospital and a separate system for tele-ICU support and monitoring of the interfaced data. To train our users we created a modular video-based curriculum to facilitate asynchronous training. Effectiveness of the curriculum was assessed through completion of common ICU documentation tasks in a high-fidelity simulation. Additional endpoints include assessment of EHR navigation, user satisfaction (Net Promoter), system usability (System Usability Scale-SUS), and cognitive load (NASA-TLX).

A total of 5 participants achieved a 100% task completion on all domains except ventilator data (91%). Systems demonstrated high degrees of satisfaction (Net Promoter = 65.2), acceptable usability (SUS = 66.5), and acceptable cognitive load (NASA-TLX = 41.5); with higher levels of cognitive load correlating with the number of screens employed.

Clinical usability of a comprehensive and rapidly deployable EHR was acceptable in an intensive care simulation which was preceded by < 1 hour of video education about the EHR. This model should be considered in plans for integrated clinical response with remote and accessory facilities.

Electronic health records (EHRs) are a significant contributor to physicians’ low satisfaction, reduced engagement and increased burnout. Yet the majority of evidence around EHR and physician harms is based on self-reported screen time, which may both over- and underreport actual exposure.

The purpose of this study was to examine how objective EHR use correlates with physician well-being and to develop preliminary recommendations for well-being-based EHR interventions.

Prior to the onset of COVID-19, psychiatry residents and attending physicians working in an out-patient clinic at an academic medical centre provided consent for access to EHR-usage logs and completed a well-being assessment made up of three scales: the Maslach Burnout Inventory, the Urecht Work Engagement Scale and the Professional Quality of Life Measure. Survey responses and objective EHR data were analysed with descriptive statistics.

Responses were obtained from 20 psychiatry residents (total eligible residents n = 27; 74% participation) and 16 clinical faculty members (total eligible faculty n = 24; 67% participation) with an overall response rate of 71% (total eligible residents and faculty n = 51 and total residents and faculty who completed survey n = 36). Moderate correlations for multiple well-being domains emerged in analysis for all participants, especially around the time spent per note and patient visits closed the same day.

EHR-usage logs represent an objective tool in the evaluation and enhancement of physician well-being. Results from our pilot study suggest that metrics for note writing efficiency and closing patient visits the same day are associated with physician well-being. These metrics will be important to study in ongoing efforts involving well-being-based EHR interventions.