A machine-learning approach for decision support and risk stratification of pediatric perioperative patients based on the APRICOT dataset.

BACKGROUND: Pediatric anesthesia has evolved to a high level of patient safety, yet a small chance remains for serious perioperative complications, even in those traditionally considered at low risk. In practice, prediction of at-risk patients currently relies on the American Society of Anesthesiologists Physical Status (ASA-PS) score, despite reported inconsistencies with this method. AIMS: The goal of this study was to develop predictive models that can classify children as low risk for anesthesia at the time of surgical booking and after anesthetic assessment on the procedure day. METHODS: Our dataset was derived from APRICOT, a prospective observational cohort study conducted by 261 European institutions in 2014 and 2015. We included only the first procedure, ASA-PS classification I to III, and perioperative adverse events not classified as drug errors, reducing the total number of records to 30 325 with an adverse event rate of 4.43%. From this dataset, a stratified train:test split of 70:30 was used to develop predictive machine learning algorithms that could identify children in ASA-PS class I to III at low risk for severe perioperative critical events that included respiratory, cardiac, allergic, and neurological complications. RESULTS: Our selected models achieved accuracies of >0.9, areas under the receiver operating curve of 0.6-0.7, and negative predictive values >95%. Gradient boosting models were the best performing for both the booking phase and the day-of-surgery phase. CONCLUSIONS: This work demonstrates that prediction of patients at low risk of critical PAEs can be made on an individual, rather than population-based, level by using machine learning. Our approach yielded two models that accommodate wide clinical variability and, with further development, are potentially generalizable to many surgical centers.

Examining Diurnal Differences in Multidisciplinary Care Teams at a Pediatric Trauma Center Using Electronic Health Record Data: Social Network Analysis.

BACKGROUND: The care of pediatric trauma patients is delivered by multidisciplinary care teams with high fluidity that may vary in composition and organization depending on the time of day. OBJECTIVE: This study aims to identify and describe diurnal variations in multidisciplinary care teams taking care of pediatric trauma patients using social network analysis on electronic health record (EHR) data. METHODS: Metadata of clinical activities were extracted from the EHR and processed into an event log, which was divided into 6 different event logs based on shift (day or night) and location (emergency department, pediatric intensive care unit, and floor). Social networks were constructed from each event log by creating an edge among the functional roles captured within a similar time interval during a shift. Overlapping communities were identified from the social networks. Day and night network structures for each care location were compared and validated via comparison with secondary analysis of qualitatively derived care team data, obtained through semistructured interviews; and member-checking interviews with clinicians. RESULTS: There were 413 encounters in the 1-year study period, with 65.9% (272/413) and 34.1% (141/413) beginning during day and night shifts, respectively. A single community was identified at all locations during the day and in the pediatric intensive care unit at night, whereas multiple communities corresponding to individual specialty services were identified in the emergency department and on the floor at night. Members of the trauma service belonged to all communities, suggesting that they were responsible for care coordination. Health care professionals found the networks to be largely accurate representations of the composition of the care teams and the interactions among them. CONCLUSIONS: Social network analysis was successfully used on EHR data to identify and describe diurnal differences in the composition and organization of multidisciplinary care teams at a pediatric trauma center.

Machine Learning Applied to Registry Data: Development of a Patient-Specific Prediction Model for Blood Transfusion Requirements During Craniofacial Surgery Using the Pediatric Craniofacial Perioperative Registry Dataset.

BACKGROUND: Craniosynostosis is the premature fusion of ≥1 cranial sutures and often requires surgical intervention. Surgery may involve extensive osteotomies, which can lead to substantial blood loss. Currently, there are no consensus recommendations for guiding blood conservation or transfusion in this patient population. The aim of this study is to develop a machine-learning model to predict blood product transfusion requirements for individual pediatric patients undergoing craniofacial surgery. METHODS: Using data from 2143 patients in the Pediatric Craniofacial Surgery Perioperative Registry, we assessed 6 machine-learning classification and regression models based on random forest, adaptive boosting (AdaBoost), neural network, gradient boosting machine (GBM), support vector machine, and elastic net methods with inputs from 22 demographic and preoperative features. We developed classification models to predict an individual's overall need for transfusion and regression models to predict the number of blood product units to be ordered preoperatively. The study is reported according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist for prediction model development. RESULTS: The GBM performed best in both domains, with an area under receiver operating characteristic curve of 0.87 ± 0.03 (95% confidence interval) and F-score of 0.91 ± 0.04 for classification, and a mean squared error of 1.15 ± 0.12, R-squared (R) of 0.73 ± 0.02, and root mean squared error of 1.05 ± 0.06 for regression. GBM feature ranking determined that the following variables held the most information for prediction: platelet count, weight, preoperative hematocrit, surgical volume per institution, age, and preoperative hemoglobin. We then produced a calculator to show the number of units of blood that should be ordered preoperatively for an individual patient. CONCLUSIONS: Anesthesiologists and surgeons can use this continually evolving predictive model to improve clinical care of patients presenting for craniosynostosis surgery.

Diagnostic Errors in Pediatric Critical Care: A Systematic Review.

OBJECTIVES: To summarize the literature on prevalence, impact, and contributing factors related to diagnostic error in the PICU. DATA SOURCES: Search of PubMed, EMBASE, and the Cochrane Library up to December 2019. STUDY SELECTION: Studies on diagnostic error and the diagnostic process in pediatric critical care were included. Non-English studies with no translation, case reports/series, studies providing no information on diagnostic error, studies focused on non-PICU populations, and studies focused on a single condition/disease or a single diagnostic test/tool were excluded. DATA EXTRACTION: Data on research design, objectives, study sample, and results pertaining to the prevalence, impact, and factors associated with diagnostic error were abstracted from each study. DATA SYNTHESIS: Using independent tiered review, 396 abstracts were screened, and 17 studies (14 full-text, 3 abstracts) were ultimately included. Fifteen of 17 studies (88%) had an observational research design. Autopsy studies (autopsy rates were 20-47%) showed a 10-23% rate of missed major diagnoses; 5-16% of autopsy-discovered diagnostic errors had a potential adverse impact on survival and would have changed management. Retrospective record reviews reported varying rates of diagnostic error from 8% in a general PICU population to 12% among unexpected critical admissions and 21-25% of patients discussed at PICU morbidity and mortality conferences. Cardiovascular, infectious, congenital, and neurologic conditions were most commonly misdiagnosed. Systems factors (40-67%), cognitive factors (20-3%), and both systems and cognitive factors (40%) were associated with diagnostic error. Limited information was available on the impact of misdiagnosis. CONCLUSIONS: Knowledge of diagnostic errors in the PICU is limited. Future work to understand diagnostic errors should involve a balanced focus between studying the diagnosis of individual diseases and uncovering common system- and process-related determinants of diagnostic error.

Consensus Recommendations for Blood Culture Use in Critically Ill Children Using a Modified Delphi Approach.

OBJECTIVES: Blood cultures are fundamental in evaluating for sepsis, but excessive cultures can lead to false-positive results and unnecessary antibiotics. Our objective was to create consensus recommendations focusing on when to safely avoid blood cultures in PICU patients. DESIGN: A panel of 29 multidisciplinary experts engaged in a two-part modified Delphi process. Round 1 consisted of a literature summary and an electronic survey sent to invited participants. In the survey, participants rated a series of recommendations about when to avoid blood cultures on five-point Likert scale. Consensus was achieved for the recommendation(s) if 75% of respondents chose a score of 4 or 5, and these were included in the final recommendations. Any recommendations that did not meet these a priori criteria for consensus were discussed during the in-person expert panel review (Round 2). Round 2 was facilitated by an independent expert in consensus methodology. After a review of the survey results, comments from round 1, and group discussion, the panelists voted on these recommendations in real-time. SETTING: Experts' institutions; in-person discussion in Baltimore, MD. SUBJECTS: Experts in pediatric critical care, infectious diseases, nephrology, oncology, and laboratory medicine. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Of the 27 original recommendations, 18 met criteria for achieving consensus in Round 1; some were modified for clarity or condensed from multiple into single recommendations during Round 2. The remaining nine recommendations were discussed and modified until consensus was achieved during Round 2, which had 26 real-time voting participants. The final document contains 19 recommendations. CONCLUSIONS: Using a modified Delphi process, we created consensus recommendations on when to avoid blood cultures and prevent overuse in the PICU. These recommendations are a critical step in disseminating diagnostic stewardship on a wider scale in critically ill children.

Practices, Perceptions, and Attitudes in the Evaluation of Critically Ill Children for Bacteremia: A National Survey.

OBJECTIVES: Sending blood cultures in children at low risk of bacteremia can contribute to a cascade of unnecessary antibiotic exposure, adverse effects, and increased costs. We aimed to describe practice variation, clinician beliefs, and attitudes about blood culture testing in critically ill children. DESIGN: Cross-sectional electronic survey. SETTING: Fifteen PICUs enrolled in the Blood Culture Improvement Guidelines and Diagnostic Stewardship for Antibiotic Reduction in Critically Ill Children collaborative, an investigation of blood culture use in critically ill children in the United States. SUBJECTS: PICU clinicians (bedside nurses, resident physicians, fellow physicians, nurse practitioners, physician assistants, and attending physicians). INTERVENTIONS: None. MEASUREMENT AND MAIN RESULTS: Survey items explored typical blood culture practices, attitudes and beliefs about cultures, and potential barriers to changing culture use in a PICU setting. Fifteen of 15 sites participated, with 347 total responses, 15-45 responses per site, and an overall median response rate of 57%. We summarized median proportions and interquartile ranges of respondents who reported certain practices or beliefs: 86% (73-91%) report that cultures are ordered reflexively; 71% (61-77%) do not examine patients before ordering cultures; 90% (86-94%) obtain cultures for any new fever in PICU patients; 33% (19-61%) do not obtain peripheral cultures when an indwelling catheter is in place; and 64% (36-81%) sample multiple (vs single) lumens of central venous catheters for new fever. When asked about barriers to reducing unnecessary cultures, 80% (73-90%) noted fear of missing sepsis. Certain practices (culture source and indication) varied by clinician type. Obtaining surveillance cultures and routinely culturing all possible sources (each lumen of indwelling catheters and peripheral specimens) are positively correlated with baseline blood culture rates. CONCLUSIONS: There is variation in blood culture practices in the PICU. Fear and reflexive habits are common drivers of cultures. These practices may contribute to over-testing for bacteremia. Further investigation of how to optimize blood culture use is warranted.

How good is our diagnostic intuition? Clinician prediction of bacteremia in critically ill children.

BACKGROUND: Clinical intuition and nonanalytic reasoning play a major role in clinical hypothesis generation; however, clinicians' intuition about whether a critically ill child is bacteremic has not been explored. We endeavored to assess pediatric critical care clinicians' ability to predict bacteremia and to evaluate what affected the accuracy of those predictions. METHODS: We conducted a retrospective review of clinicians' responses to a sepsis screening tool ("Early Sepsis Detection Tool" or "ESDT") over 6 months. The ESDT was completed during the initial evaluation of a possible sepsis episode. If a culture was ordered, they were asked to predict if the culture would be positive or negative. Culture results were compared to predictions for each episode as well as vital signs and laboratory data from the preceding 24 h. RESULTS: From January to July 2017, 266 ESDTs were completed. Of the 135 blood culture episodes, 15% of cultures were positive. Clinicians correctly predicted patients with bacteremia in 82% of cases, but the positive predictive value was just 28% as there was a tendency to overestimate the presence of bacteremia. The negative predictive value was 96%. The presence of bandemia, thrombocytopenia, and abnormal CRP were associated with increased likelihood of correct positive prediction. CONCLUSIONS: Clinicians are accurate in predicting critically ill children whose blood cultures, obtained for symptoms of sepsis, will be negative. Clinicians frequently overestimate the presence of bacteremia. The combination of evidence-based practice guidelines and bedside judgment should be leveraged to optimize diagnosis of bacteremia.

Transforming the Morbidity and Mortality Conference to Promote Safety and Quality in a PICU.

OBJECTIVE: Determine the effectiveness of a structured systems-oriented morbidity and mortality conference in improving the process of reviewing and responding to adverse events in a PICU. DESIGN: Prospective time series analysis before and after implementation of a systems-oriented morbidity and mortality conference. SETTING: Single tertiary referral PICU in Baltimore, MD. PATIENTS: Thirty-three patients discussed before and 31 patients after implementation of a systems-oriented morbidity and mortality conference over a total of 20 morbidity and mortality conferences, from April 2013 to March 2014. INTERVENTIONS: Systems-oriented morbidity and mortality conference incorporating elements of medical incident analysis. MEASUREMENTS AND MAIN RESULTS: There was a significant increase in meeting attendance (mean, 12 vs 31 attendees per morbidity and mortality conference; p < 0.001) after the systems-oriented morbidity and mortality conference was instituted. There was no significant difference in the mean number of cases suggested (4.2 vs 4.6) or discussed (3.3 vs 3.1) per morbidity and mortality conference. There was also no significant difference in the mean number of adverse events identified per morbidity and mortality conference (3.4 vs 4.3). However, there was an increase in the proportion of cases discussed using a standard case review tool, but this did not reach statistical significance (27% vs 45%; p = 0.231). Nevertheless, we observed a significant increase in the mean number of quality improvement interventions suggested (2.4 vs 5.6; p < 0.001) and implemented (1.7 vs 4.4; p < 0.001) per morbidity and mortality conference. All adverse event categories identified had corresponding interventions suggested after the systems-oriented morbidity and mortality conference was instituted compared with before (80% vs 100%). Intervention-to-adverse event ratios per category were also higher (mean, 0.6 vs 1.5). CONCLUSIONS: A structured systems-oriented PICU morbidity and mortality conference incorporating elements of medical incident analysis improves the process of reviewing and responding to adverse events by significantly increasing quality improvement interventions suggested and implemented. Future work would involve testing locally adapted versions of the systems-oriented morbidity and mortality conference in multiple inpatient settings.

Hemoglobin thresholds for transfusion in pediatric patients at a large academic health center.

BACKGROUND: Although prior studies support the use of a hemoglobin (Hb) transfusion trigger of 7 to 8 g/dL for most hospitalized adults, there are few studies in pediatric populations. We therefore investigated transfusion practices and Hb triggers in hospitalized children. STUDY DESIGN AND METHODS: We performed a historical cohort study comparing transfusion practices in hospitalized children by service within a single academic institution. Blood utilization data from transfused patients (n = 3370) were obtained from electronic records over 4 years. Hb triggers and posttransfusion Hb levels were defined as the lowest and last Hb measured during hospital stay, respectively, in transfused patients. The mean and percentile distribution for Hb triggers were compared to the evidence-based restrictive transfusion threshold of 7 g/dL. RESULTS: Mean Hb triggers were above the restrictive trigger (7 g/dL) for eight of 12 pediatric services. Among all of the services, there were significant differences between the mean Hb triggers (>2.5 g/dL, p<0.0001) and between the posttransfusion Hb levels (>3 g/dL, p < 0.0001). The variation between the 10th and 90th percentiles for triggers (up to 4 g/dL, p < 0.0001) and posttransfusion Hb levels (up to 6 g/dL, p < 0.0001) were significant. Depending on the service, between 25 and 90% of transfused patients had Hb triggers higher than the restrictive range. CONCLUSIONS: Red blood cell (RBC) transfusion therapy varies significantly in hospitalized children with mean Hb triggers above a restrictive threshold for most services. Our findings suggest that transfusions may be overused and that implementing a restrictive transfusion strategy could decrease the use of RBC transfusions, thereby reducing the associated risks and costs.