Explore the vast range of titles available.

Background Determining extubation readiness in pediatric intensive care units (PICU) is challenging. We used expert-augmented machine learning (EAML), a method that combines machine learning with human expert knowledge, to predict successful extubation. Methods We extracted electronic health record data from patients in two PICUs. Data from patients in one unit was split into 80% training and 20% test, while patients in the other served as an external test set. EAML begins by training RuleFit, which converts gradient-boosted trees into decision rules. Then, expert clinicians were asked to assess the relative probability of successful extubation of the subgroup defined by each rule compared with the entire sample. The rules were ranked in order of increasing chance of successful extubation according to (1) the RuleFit model and (2) clinician assessment, and differences between the two rankings were calculated. The initial RuleFit model was then regularized based on these differences, producing the EAML model. Results The RuleFit model selected 46 rules; we surveyed 25 clinician experts to provide feedback on them. All clinicians worked in a PICU setting and were from multiple disciplines; over half (56%) had > 5 years of PICU experience. As expected, the added regularization slightly lowered performance of EAML compared with RuleFit in the internal test set, although the difference was not statistically significant (RuleFit AUC = 0.817 vs. best-performing EAML model AUC = 0.814, difference = 0.003, 95% CI of difference = -0.009, 0.003). EAML had superior performance in the external test set (RuleFit AUC = 0.791 vs. best-performing EAML model AUC = 0.799, difference = 0.007, 95% CI of difference = 0.002, 0.013). Conclusions When creating a model to predict successful extubation in PICU patients, incorporating expert knowledge directly into the model construction process via EAML produced a model more generalizable to an external test set.

Missing data are a common challenge in electronic health record (EHR)-based prediction modeling. Traditional imputation methods may not suit prediction or machine learning models, and real-world use requires workflows that are implementable for both model development and real-time prediction. We evaluated methods for handling missing data when using EHR data to build clinical prediction models for patients admitted to the pediatric intensive care unit (PICU). Using EHR data containing missing values from an academic medical center PICU, we generated a synthetic complete dataset. From this, we created 300 datasets with missing data under varying mechanisms and proportions of missingness for the outcomes of (1) successful extubation (binary) and (2) blood pressure (continuous). We assessed strategies to address missing data including simple methods (eg, last observation carried forward [LOCF]), complex methods (eg, random forest multiple imputation), and native support for missing values in outcome prediction models. Across 886 patients and 1220 intubation events, 18.2% of original data were missing. LOCF had the lowest imputation error, followed by random forest imputation (average mean squared error [MSE] improvement over mean imputation: 0.41 [range: 0.30, 0.50] and 0.33 [0.21, 0.43], respectively). LOCF generally outperformed other imputation methods across outcome metrics and models (mean improvement: 1.28% [range: -0.07%, 7.2%]). Imputation methods showed more performance variability for the binary outcome (balanced accuracy coefficient of variation: 0.042) than the continuous outcome (mean squared error coefficient of variation: 0.001). Traditional imputation methods for inferential statistics, such as multiple imputation, may not be optimal for prediction models. The amount of missingness influenced performance more than the missingness mechanism. In datasets with frequent measurements, LOCF and native support for missing values in machine learning models offer reasonable performance for handling missingness at minimal computational cost in predictive analyses.

Background Interprofessional simulation-based team training (ISBTT) is commonly used to optimize interprofessional teamwork in healthcare. The literature documents the benefits of ISBTT, yet effective interprofessional collaboration continues to be challenged by complex hierarchies and power dynamics. Explicitly addressing these issues during ISBTT may help participants acquire skills to navigate such challenges, but guidelines on how to do this are limited. Methods We applied an educational design research approach to develop and pilot structured facilitator guidelines that explicitly address power and hierarchy with interprofessional teams. We conducted this work in a previously established ISBTT program at our institution, between September 2020 and December 2021. We first reviewed the literature to identify relevant educational theories and developed design principles. We subsequently designed, revised, and tested guidelines. We used qualitative thematic and content analysis of facilitator interviews and video-recording of IBSTT sessions to evaluate the effects of the guidelines on the pre- and debriefs. Results Qualitative content analysis showed that structured guidelines shifted debriefing participation and content. Debriefings changed from physician-led discussions with a strong focus on medical content to conversations with more equal participation by nurses and physicians and more emphasis on teamwork and communication. The thematic analysis further showed how the conversation during debriefing changed and how interprofessional learning improved after the implementation of the guidelines. While power and hierarchy were more frequently discussed, for many facilitators these topics remained challenging to address. Conclusion We successfully created and implemented guidelines for ISBTT facilitators to explicitly address hierarchy and power. Future work will explore how this approach to ISBTT impacts interprofessional collaboration in clinical practice.

Background Epinephrine is provided during cardiopulmonary resuscitation (CPR) to increase systemic vascular resistance and generate higher diastolic blood pressure (DBP) to improve coronary perfusion and attain return of spontaneous circulation (ROSC). The DBP response to epinephrine during pediatric CPR and its association with outcomes have not been well described. Thus, the objective of this study was to measure the association between change in DBP after epinephrine administration during CPR and ROSC. Methods This was a prospective multicenter study of children receiving ≥ 1 min of CPR with ≥ 1 dose of epinephrine and evaluable invasive arterial BP data in the 18 ICUs of the ICU-RESUS trial (NCT02837497). Blood pressure waveforms underwent compression-by-compression quantitative analysis. The mean DBP before first epinephrine dose was compared to mean DBP two minutes post-epinephrine. Patients with ≥ 5 mmHg increase in DBP were characterized as “responders.” Results Among 147 patients meeting inclusion criteria, 66 (45%) were characterized as responders and 81 (55%) were non-responders. The mean increase in DBP with epinephrine was 4.4 [− 1.9, 11.5] mmHg (responders: 13.6 [7.5, 29.3] mmHg versus non-responders: − 1.5 [− 5.0, 1.5] mmHg; p  < 0.001). After controlling for a priori selected covariates, epinephrine response was associated with ROSC (aRR 1.60 [1.21, 2.12]; p  = 0.001). Sensitivity analyses identified similar associations between DBP response thresholds of ≥ 10, 15, and 20 mmHg and ROSC; DBP responses of ≥ 10 and ≥ 15 mmHg were associated with higher aRR of survival to hospital discharge and survival with favorable neurologic outcome (Pediatric Cerebral Performance Category score of 1–3 or no worsening from baseline). Conclusions The change in DBP following epinephrine administration during pediatric in-hospital CPR was associated with return of spontaneous circulation.

Background Quality of cardiopulmonary resuscitation (CPR) is associated with survival, but recommended guidelines are often not met, and less than half the children with an in-hospital arrest will survive to discharge. A single-center before-and-after study demonstrated that outcomes may be improved with a novel training program in which all pediatric intensive care unit staff are encouraged to participate in frequent CPR refresher training and regular, structured resuscitation debriefings focused on patient-centric physiology. Methods/design This ongoing trial will assess whether a program of structured debriefings and point-of-care bedside practice that emphasizes physiologic resuscitation targets improves the rate of survival to hospital discharge with favorable neurologic outcome in children receiving CPR in the intensive care unit. This study is designed as a hybrid stepped-wedge trial in which two of ten participating hospitals are randomly assigned to enroll in the intervention group and two are assigned to enroll in the control group for the duration of the trial. The remaining six hospitals enroll initially in the control group but will transition to enrolling in the intervention group at randomly assigned staggered times during the enrollment period. Discussion To our knowledge, this is the first implementation of a hybrid stepped-wedge design. It was chosen over a traditional stepped-wedge design because the resulting improvement in statistical power reduces the required enrollment by 9 months (14%). However, this design comes with additional challenges, including logistics of implementing an intervention prior to the start of enrollment. Nevertheless, if results from the single-center pilot are confirmed in this trial, it will have a profound effect on CPR training and quality improvement initiatives. Trial registration ClinicalTrials.gov, NCT02837497 . Registered on July 19, 2016.

IntroductionStigma and discrimination among healthcare workers can hinder diagnosis and the provision of appropriate care in dementia. This study is aimed at developing, delivering and evaluating the feasibility of a group antistigma intervention to improve knowledge, attitudes and behaviours in relation to people living with dementia among community health workers (CHWs).Methods and analysisThis will be a randomised controlled feasibility trial conducted with 150 CHWs from 14 primary care units (PCUs) in São Paulo, Brazil. PCUs will be randomly allocated (1:1) in two parallel groups—experimental group or control group. Participants from PCUs allocated to the experimental group will receive a 3-day group intervention involving audio-visual and printed materials as well as elements of social contact. The control group will keep their usual routine. Knowledge, attitude and intended behaviour stigma-based outcomes will be assessed at baseline and at follow-up (30 days after intervention) to both groups, with additional questions on feasibility for the experimental group at follow-up. Around 10–15 participants will take part in follow-up semistructured interviews to further explore feasibility. Quantitative analyses will follow an ‘intention to treat’ approach. Qualitative data will be analysed using content analysis.Ethics and disseminationThis study was approved by the National Commission for Ethics in Research in Brazil (n. 5.510.113). Every participant will sign a consent form. Results will be disseminated through academic journals and events related to dementia. The intervention materials will be made available online.