Admission Risk Assessment Research Articles

NICU Admission for Term Neonates in a Large Single-Center Population: A Comprehensive Assessment of Risk Factors Using a Tandem Analysis Approach.

Objective: Neonatal intensive care unit (NICU) admission among term neonates is associated with significant morbidity and mortality, as well as high healthcare costs. A comprehensive NICU admission risk assessment using an integrated statistical approach for this rare admission event may be used to build a risk calculation algorithm for this group of neonates prior to delivery. Methods: A single-center case–control retrospective study was conducted between August 2005 and December 2019, including in-hospital singleton live born neonates, born at ≥37 weeks’ gestation. Analyses included univariate and multivariable models combined with the machine learning gradient-boosting model (GBM). The primary aim of the study was to identify and quantify risk factors and causes of NICU admission of term neonates. Results: During the study period, 206,509 births were registered at the Shaare Zedek Medical Center. After applying the study exclusion criteria, 192,527 term neonates were included in the study; 5292 (2.75%) were admitted to the NICU. The NICU admission risk was significantly higher (ORs [95%CIs]) for offspring of nulliparous women (1.19 [1.07, 1.33]), those with diabetes mellitus or hypertensive complications of pregnancy (2.52 [2.09, 3.03] and 1.28 [1.02, 1.60] respectively), and for those born during the 37th week of gestation (2.99 [2.63, 3.41]; p < 0.001 for all), adjusted for congenital malformations and genetic syndromes. A GBM to predict NICU admission applied to data prior to delivery showed an area under the receiver operating characteristic curve of 0.750 (95%CI 0.743–0.757) and classified 27% as high risk and 73% as low risk. This risk stratification was significantly associated with adverse maternal and neonatal outcomes. Conclusion: The present study identified NICU admission risk factors for term neonates; along with the machine learning ranking of the risk factors, the highly predictive model may serve as a basis for individual risk calculation algorithm prior to delivery. We suggest that in the future, this type of planning of the delivery will serve different health systems, in both high- and low-resource environments, along with the NICU admission or transfer policy.

Validation of Postpartum Hemorrhage Admission Risk Factor Stratification in a Large Obstetrics Population.

This study aimed to evaluate the performance of the California Maternal Quality Care Collaborative (CMQCC) admission risk criteria for stratifying postpartum hemorrhage risk in a large obstetrics population. Using detailed electronic health record data, we classified 261,964 delivery hospitalizations from Kaiser Permanente Northern California hospitals between 2010 and 2017 into high-, medium-, and low-risk groups based on CMQCC criteria. We used logistic regression to assess associations between CMQCC risk groups and postpartum hemorrhage using two different postpartum hemorrhage definitions, standard postpartum hemorrhage (blood loss ≥1,000 mL) and severe postpartum hemorrhage (based on transfusion, laboratory, and blood loss data). Among the low-risk group, we also evaluated associations between additional present-on-admission factors and severe postpartum hemorrhage. Using the standard definition, postpartum hemorrhage occurred in approximately 5% of hospitalizations (n = 13,479), with a rate of 3.2, 10.5, and 10.2% in the low-, medium-, and high-risk groups. Severe postpartum hemorrhage occurred in 824 hospitalizations (0.3%), with a rate of 0.2, 0.5, and 1.3% in the low-, medium-, and high-risk groups. For either definition, the odds of postpartum hemorrhage were significantly higher in medium- and high-risk groups compared with the low-risk group. Over 40% of postpartum hemorrhages occurred in hospitalizations that were classified as low risk. Among the low-risk group, risk factors including hypertension and diabetes were associated with higher odds of severe postpartum hemorrhage. We found that the CMQCC admission risk assessment criteria stratified women by increasing rates of severe postpartum hemorrhage in our sample, which enables early preparation for many postpartum hemorrhages. However, the CMQCC risk factors missed a substantial proportion of postpartum hemorrhages. Efforts to improve postpartum hemorrhage risk assessment using present-on-admission risk factors should consider inclusion of other nonobstetrical factors.

The Children's Hospital-Acquired Thrombosis (CHAT) Consortium Admission Risk-Assessment Models from Traditional Biostatistics and Machine Learning

Introduction Incidence of pediatric hospital-acquired venous thromboembolism (HA-VTE) is increasing raising concern for acute and chronic sequelae and impact on the health care system. This has prompted many pediatric centers to implement prophylaxis programs despite the lack of a validated risk-assessment model (RAM) or evidence of a favorable risk/benefit ratio for pharmacologic prophylaxis. The multi-center Children's Hospital-Acquired Thrombosis (CHAT) Consortium was created in 2014 to derive RAMs with subsequent prospective validation (i.e. CHAT 1901, the second study from the CHAT Consortium). We present the CHAT RAMs using traditional biostatistical (CHAT-TB) and machine learning (CHAT-ML) methods. Methods The first project of the CHAT Consortium was an eight-center, retrospective, case-control study of subjects aged 0-21 years diagnosed with a radiographic-confirmed, symptomatic HA-VTE and frequency-matched controls (by year and hospital) from January 1, 2012 through December 31, 2016. Controls were randomly sampled from the complete list of children without HA-VTE hospitalized and the sampling proportion of controls with hospital stay &amp;lt; 48 hours was 20%. CHAT-TB: Weighted logistic regression examined univariate effects of variables known at baseline (prior to and on day of admission) on incidence of symptomatic HA-VTE. Key predictors with sufficient frequency and significance in univariate analyses progressed as candidates in the multivariable RAM developed via the Lasso method. Clinically important interaction effects were tested separately and considered a candidate predictor when the p-value of the interaction term was &amp;lt; 0.10. Five approximately equal-sized samples were used for internal validation. The RAM was built independently in each sub-sample and the model fit was tested in the n - sub-sample cohort. Receiver operating characteristic (ROC) curves were used to assess performance in both a model re-substitution and average of the 5-sample internal validation subsets. CHAT-ML: We developed and evaluated four machine learning (ML) models (adaptive boosting, random forest, gradient boosting, and logistic regression), and the most accurate RAM was selected by comparing the relationship of model specificity and sensitivity in ROC curves. ML modelling consists of: pre-processing and feature extraction, data profiling and exploration, model selection, training, and testing, model re-calibration in partnership with subject-matter experts. With more than 250 variables for each patient, lasso regression was utilized to reduce the number of features to have only those with non-zero weight in the regression. We then divided the dataset into training (n=1250) and test (n=540) groups and report the F1 score, i.e. the harmonic mean of precision (i.e. positive predictive value) and recall (i.e. sensitivity) which is used to measure accuracy of a ML classifier. Results Demographics are summarized in Table 1. CHAT-TB: Significant predictors from the weighted logistic regression model are shown in Table 2 and ROC curves from the model re-substitution and 5-sample internal validation demonstrate precision with AUC of 79.9% (CI: 77.7-82.1%) and 77.9% (75.6-80.2%), respectively. CHAT-ML: Significant clinical variables included: change in mobility as assessed by BradenQ scoring, CVC, congenital heart disease, presence of a complex chronic condition (Feudtner 2014), contraindication to VTE prophylaxis (Table 3), ICU admission, infection, and change in platelet count. Figure 1 shows that gradient boosting outperformed other models via area under the ROC curve (AUC=0.95) and F1-score (0.89). Adaptive boosting also performed well with AUC=0.93 and F1-score (0.87). Discussion We present two novel RAMs from the CHAT Consortium. The CHAT RAM-TB and RAM-ML demonstrate sufficient performance for prospective validation and RAM-ML shows a stronger AUC. CHAT 1901 is designed to validate the RAMs, assess performance individually and comparatively, and develop risk-assessment calculators for clinical use and/or integration into the electronic health record (specific to the CHAT-ML, a visual analytics application will provide an interface for clinicians to enter information on significant predictors and receive a calculated risk score). Disclosures Mahajerin: Spark: Speakers Bureau; Genentech: Consultancy, Speakers Bureau; Kedrion: Membership on an entity's Board of Directors or advisory committees; Alexion: Speakers Bureau. Jaffray:CSL Behring: Research Funding. Croteau:Bayer: Consultancy, Honoraria; CSL Behring: Consultancy, Honoraria; Shire: Consultancy, Honoraria; Novo Nordisk: Consultancy, Honoraria, Research Funding; Spark Therapeutics: Research Funding; Pfizer: Research Funding; Genentech: Consultancy, Honoraria; Octapharma: Honoraria; Genentech: Consultancy, Honoraria; Octapharma: Honoraria. Silvey:Genentech: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau; Bayer: Membership on an entity's Board of Directors or advisory committees. Goldenberg:NIH: Other: research support and salary support. Young:Kedrion: Consultancy, Honoraria; Novo Nordisk: Consultancy, Honoraria; Spark: Consultancy, Honoraria; Shire/Takeda: Consultancy, Honoraria; Uniqure: Consultancy, Honoraria; CSL Behring: Consultancy, Honoraria; Freeline: Consultancy, Honoraria; Genentech/Roche: Consultancy, Honoraria, Research Funding; Bioverativ/Sanofi: Consultancy, Honoraria; Grifols: Consultancy, Honoraria.

Decreased rates of shoulder dystocia and brachial plexus injury via an evidence-based practice bundle.

To evaluate whether a standardized approach to identify pregnant women at risk for shoulder dystocia (SD) is associated with reduced incidence of SD and brachial plexus injury (BPI). Between 2011 and 2015, prospective data were collected from 29 community-based hospitals in the USA during implementation of an evidence-based practice bundle, including an admission risk assessment, required "timeout" before operative vaginal delivery (OVD), and low-fidelity SD drills. All women with singleton vertex pregnancies admitted for vaginal delivery were included. Rates of SD, BPI, OVD, and cesarean delivery were compared between a baseline period (January 2011-September 2013) and an intervention period (October 2013-June 2015), during which there was a system-wide average bundle compliance of 90%. There was a significant reduction in the incidence of SD (17.6%; P=0.028), BPI (28.6%; P=0.018), and OVD (18.0%; P<0.001) after implementation of the evidence-based practice bundle. There was a nonsignificant reduction in primary (P=0.823) and total (P=0.396) cesarean rates, but no association between SD drills and incidence of BPI. Implementation of a standard evidence-based practice bundle was found to be associated with a significant reduction in the incidence of SD and BPI. Utilization of low-fidelity drills was not associated with a reduction in BPI.

P-832 - Are inpatients routinely assessed for venous-thrombo-embolism on admission?

Introduction Venous Thrombo-embolism (VTE) can be fatal, and therefore forms a key part of the admission risk assessment. NICE guidelines give a framework for assessment and management of VTE risk, and this has recently been introduced to Oxford Health NHS Foundation Trust. Aims To investigate whether VTE risk is routinely assessed on admission, with the aim of developing plans around the prevention and management of VTE in inpatients. Standards All in-patients should have a physical health assessment on admission which should be clearly documented within patient notes and should include documentation of VTE risk. Methods A cross-sectional audit of all adult and older-adult wards in Oxfordshire and Buckinghamshire, September 2011. Results The sample included 133 adult inpatients and 77 older-adult inpatients, across 12 wards. The admission physical health assessment was completed for 90% of general adult patients and 92% of older-adult patients. There was excellent documentation of VTE risk, 59% in general adult wards and 99% in older adult wards. Conclusions Rates of completion of VTE risk were good, particularly on older adult wards. The vast majority of patients scored as low risk for VTE. Risk assessments were completed separately to the admission physical health assessment and there needs to be greater consistency of documentation within electronic patient records. New guidelines regarding completion of physical health assessment and VTE risk have now been issued within the Trust; re-audit in 6 months will review whether good practice is maintained and that improvements occur where necessary.

Risk assessment of self- and other-directed aggression in adolescent psychiatric inpatient units

To examine the predictive validity of unstructured clinical risk assessment and associated risk factors for aggression in predicting self- and other-directed aggression in the first 4 weeks of admission for patients admitted to an Australian adolescent psychiatric inpatient facility. A retrospective review of patient records was conducted at the Marian Drummond Adolescent Unit during late 2009 for the period of September 2006 to July 2009. Information collected included admission risk assessment ratings, aggressive incident reports, patient diagnoses, sex and history of aggression and self-harming behaviour. A total of 193 adolescents (aged 13-18 years old) were included in retrospective analyses. The hypothesis that unstructured clinical risk assessment would be predictive of self- and other-directed aggression was partially supported. High risk assessment scores were predictive of engagement in other-directed aggression. A history of physical aggression was also found to be predictive of engagement in other-directed aggression; however, it was not as predictive as the risk assessment rating. High risk assessment scores were not predictive of self-directed aggression. A history of engaging in one or more acts of self-harm or suicide was the most predictive of engagement in self-directed aggression during inpatient stay. Female sex also predicted engagement in self-directed aggression. Based on professional expertise, prior experience and intuition, clinicians are relatively good predictors of other-directed aggression in adolescent inpatient units; however, they are less successful at predicting self-directed aggression in this population. It is possible that, unlike other-directed aggression, self-harming behaviour is heavily dependent on environmental factors and that admission to the inpatient unit removes these triggers from the individual's environment.

Risk Assessment: Predicting Physical Aggression in Child Psychiatric Inpatient Units

The aim of this study was to examine the predictive validity of unstructured clinical risk assessment and associated risk factors for aggression in predicting physical aggression in children admitted to an Australian psychiatric inpatient facility. A retrospective review of patient records was conducted at the State Wide Child Inpatient Unit during late 2009 for the period September 2006-July 2009. Children between the ages of 8 and 13 were included in analyses. Information collected included admission risk assessment ratings, critical incident reports, patient diagnoses and history of aggression and trauma. A total of 127 children (aged 8-13 years) were included in retrospective analyses. Higher aggression risk rankings were predictive of the frequency but not the severity of aggression. A diagnosis of a disruptive behaviour disorder and a history of being a victim of trauma were also predictive of engagement in aggression; however, were not as predictive as the risk assessment. A high risk assessment rating for aggression was better able to predict engagement in aggressive behaviour than a history of physical aggression alone. Based on professional expertise, prior experience and intuition, clinicians were able to successfully predict engagement in aggressive behaviour during patient admission to a child psychiatric inpatient units.

Comprehensive maternal hemorrhage protocols improve patient safety and reduce utilization of blood products

The purpose of this study was to assess the effectiveness of instituting a comprehensive protocol for the treatment of maternal hemorrhage. The protocol was separated into 4 stages, designated 0-3, based on the degree of blood loss and the patient response to interventions. Key components included admission risk assessment, measurement of blood loss, early but limited use of uterotonic agents, early presence of obstetrical and anesthesia staff, and transfusion with fixed ratios of blood products. Data were collected retrospectively and prospectively relative to the start of the protocol. We noted a significant shift toward resolution of maternal bleeding at an earlier stage (P < .01), use of fewer blood products (P < .01), and a 64% reduction in the rate of disseminated intravascular coagulation. In addition, there were significant improvements in staff and physician perceptions of patient safety (P < .01). Comprehensive maternal hemorrhage treatment protocols improve patient safety and reduce utilization of blood products.

142: Comprehensive maternal hemorrhage protocols improve patient safety and reduce utilization of blood products

142: Comprehensive maternal hemorrhage protocols improve patient safety and reduce utilization of blood products

Admission risk assessment by cardiac troponin T in unstable coronary artery disease: Additional prognostic information from continuous ST segment monitoring: Nørgaard BL, Andersen K, Dellborg M, et al J Am Coll Cardiol 33: 1519–1527 May 1999

Admission risk assessment by cardiac troponin T in unstable coronary artery disease: Additional prognostic information from continuous ST segment monitoring: Nørgaard BL, Andersen K, Dellborg M, et al J Am Coll Cardiol 33: 1519–1527 May 1999

Admission risk assessment by cardiac troponin T in unstable coronary artery disease: additional prognostic information from continuous ST segment monitoring

OBJECTIVESWe investigated whether the addition of 24 h of continuous vectorcardiography ST segment monitoring (cVST) for an early (within 24 h of the latest episode of angina) determination of cardiac troponin T (cTnT) could provide additional prognostic information in patients with unstable coronary artery disease (UCAD), i.e., unstable angina and non–Q wave myocardial infarction.BACKGROUNDDetermination of cTnT at admission and cVST are individually reported to be valuable techniques for the risk assessment of patients with UCAD.METHODSTwo hundred and thirty-two patients suspected of UCAD were studied. Patients were followed for 30 days, and the occurrence of cardiac death or acute myocardial infarction (AMI) were registered.RESULTSOne ST segment episode or more (relative risk [RR] 7.43, p = 0.012), a cTnT level ≥0.20 μg/liter (RR 3.85, p = 0.036) or prestudy medication with calcium antagonists (RR 3.31, p = 0.041) were found to carry independent prognostic information after multivariate analysis of potential risk variables. By combining a cTnT determination and subsequent cVST for 24 h, subgroups of patients at high (25.8%) (n = 31), intermediate (3.1%) (n = 65) and low risk (1.7%) (n = 117) of death or AMI could be identified.CONCLUSIONSTwenty-four hours of cVST provides additional prognostic information to that of an early cTnT determination in patients suspected of having UCAD. The combination of biochemical and electrocardiographic methods provides powerful and accurate risk stratification in UCAD.