A cost sensitive inpatient bed reservation approach to reduce emergency department boarding times

Medical capacity investment for epidemic disease: The effects of policymaker's confidence and public trust

Due to the server bed shortage, which has raised ethical dilemmas in the earliest days of the COVID-19 crisis, medical capacity investment has become a vital decision-making issue in the attempt to contain the epidemic. Furthermore, economic strength has failed to explain the significant performance difference across countries in combatting COVID-19. Unlike common diseases, epidemic diseases add substantial unpredictability, complexity, and uncertainty to decision-making. Knowledge miscalibration on epidemiological uncertainties by policymaker's over- and underconfidence can seriously impact policymaking. Ineffective risk communication may lead to conflicting and incoherent information transmission. As a result, public reactions and attitudes could be influenced by policymakers' confidence due to the level of public trust, which eventually affects the degree to which an epidemic spreads. To uncover the impacts of policymakers' confidence and public trust on the medical capacity investment, we establish epidemic diffusion models to characterize how transmission evolves with (and without) vaccination and frame the capacity investment problem as a newsvendor problem. Our results show that if the public fully trusts the public health experts, the policymaker's behavioral bias is always harmful, but its effect on cost increment is marginal. If a policymaker's behavior induces public reactions due to public trust, both the spread of the epidemic and the overall performance will be significantly affected, but such impacts are not always harmful. Decision bias may be beneficial when policymakers are pessimistic or highly overconfident. Having an opportunity to amend initially biased decisions can debias a particular topic but has a limited cost-saving effect.

Managing inpatient bed setup: an action-research approach using lean technical practices and lean social practices

PURPOSE

This article aims to introduce a guide to improving hospital bed setup by combining lean technical practices (LTPs), such as kaizen and value stream mapping (VSM) and lean social practices (LSPs), such as employee empowerment.

DESIGN/METHODOLOGY/APPROACH

Action research approach was employed to analyze the process of reconfiguration of bed setup management in a Brazilian public hospital.

FINDINGS

The study introduces three contributions: (1) presents the use of VSM focused specifically on bed setup, while the current literature presents studies mainly focused on patient flow management, (2) combines the use of LSPs and LTPs in the context of bed management, expanding current studies that are focused either on mathematical models or on social and human aspects of work, (3) introduces a practical guide based on six steps that combine LSPs and LSPs to improve bed setup management.

RESEARCH LIMITATIONS/IMPLICATIONS

The research focused on the analysis of patient beds. Surgical beds, delivery, emergency care and intensive care unit (ICU) were not considered in this study. In addition, the process indicators analyzed after the implementation of the improvements did not contemplate the moment of the COVID-19 pandemic. Finally, this research focused on the implementation of the improvement in the context of only one Brazilian public hospital.

PRACTICAL IMPLICATIONS

The combined use of LSPs and LTPs can generate considerable gains in bed setup efficiency and consequently increase the capacity of a hospital to admit new patients, without the ampliation of the physical space and workforce.

SOCIAL IMPLICATIONS

The improvement of bed setup has an important social character, whereas it can generate important social benefits such as the improvement of the admission service to patients, reducing the waiting time, reducing hospitalization costs and improving the hospital capacity without additional physical resources. All these results are crucial for populations, their countries and regions.

ORIGINALITY/VALUE

While the current literature on bed management is more focused on formal models or pure human and social perspectives, this article brings these two perspectives together in a single, holistic framework. As a result, this article points out that the complex bed management problem can be efficiently solved by combining LSPs and LTPs to present theoretical and practical contributions to the important social problem of hospital bed management.

Prospective External Validation of a Commercial Model Predicting the Likelihood of Inpatient Admission From the Emergency Department

STUDY OBJECTIVE

Early notification of admissions from the emergency department (ED) may allow hospitals to plan for inpatient bed demand. This study aimed to assess Epic's ED Likelihood to Occupy an Inpatient Bed predictive model and its application in improving hospital bed planning workflows.

METHODS

All ED adult (18 years and older) visits from September 2021 to August 2022 at a large regional health care system were included. The primary outcome was inpatient admission. The predictive model is a random forest algorithm that uses demographic and clinical features. The model was implemented prospectively, with scores generated every 15 minutes. The area under the receiver operator curves (AUROC) and precision-recall curves (AUPRC) were calculated using the maximum score prior to the outcome and for each prediction independently. Test characteristics and lead time were calculated over a range of model score thresholds.

RESULTS

Over 11 months, 329,194 encounters were evaluated, with an incidence of inpatient admission of 25.4%. The encounter-level AUROC was 0.849 (95% confidence interval [CI], 0.848 to 0.851), and the AUPRC was 0.643 (95% CI, 0.640 to 0.647). With a prediction horizon of 6 hours, the AUROC was 0.758 (95% CI, 0.758 to 0.759,) and the AUPRC was 0.470 (95% CI, 0.469 to 0.471). At a predictive model threshold of 40, the sensitivity was 0.49, the positive predictive value was 0.65, and the median lead-time warning was 127 minutes before the inpatient bed request.

CONCLUSION

The Epic ED Likelihood to Occupy an Inpatient Bed model may improve hospital bed planning workflows. Further study is needed to determine its operational effect.

Machine learning methods applied to triage in emergency services: A systematic review

BACKGROUND

In emergency services is important to accurately assess and classify symptoms, which may be improved with the help of technology. One mechanism that could help and improve predictions from health records or patient flow is machine learning (ML).

AIM

To analyse the effectiveness of ML systems in triage for making predictions at the emergency department in comparison with other triage scales/scores.

METHODS

Following the PRISMA recommendations, a systematic review was conducted using CINAHL, Cochrane, Cuiden, Medline and Scopus databases with the search equation "Machine learning AND triage AND emergency".

RESULTS

Eleven studies were identified. The studies show that the use of ML methods consistently predict important outcomes like mortality, critical care outcomes and admission, and the need for hospitalization in comparison with scales like Emergency Severity Index or others. Among the ML models considered, XGBoost and Deep Neural Networks obtained the highest levels of prediction accuracy, while Logistic Regression performed obtained the worst values.

CONCLUSIONS

Machine learning methods can be a good instrument for helping triage process with the prediction of important emergency variables like mortality or the need for critical care or hospitalization.

Leveraging electronic health record data to inform hospital resource management : A systematic data mining approach

Early identification of resource needs is instrumental in promoting efficient hospital resource management. Hospital information systems, and electronic health records (EHR) in particular, collect valuable demographic and clinical patient data from the moment patients are admitted, which can help predict expected resource needs in early stages of patient episodes. To this end, this article proposes a data mining methodology to systematically obtain predictions for relevant managerial variables by leveraging structured EHR data. Specifically, these managerial variables are: i) Diagnosis categories, ii) procedure codes, iii) diagnosis-related groups (DRGs), iv) outlier episodes and v) length of stay (LOS). The proposed methodology approaches the problem in four stages: Feature set construction, feature selection, prediction model development, and model performance evaluation. We tested this approach with an EHR dataset of 5,089 inpatient episodes and compared different classification and regression models (for categorical and continuous variables, respectively), performed temporal analysis of model performance, analyzed the impact of training set homogeneity on performance and assessed the contribution of different EHR data elements for model predictive power. Overall, our results indicate that inpatient EHR data can effectively be leveraged to inform resource management on multiple perspectives. Logistic regression (combined with minimal redundancy maximum relevance feature selection) and bagged decision trees yielded best results for predicting categorical and numerical managerial variables, respectively. Furthermore, our temporal analysis indicated that, while DRG classes are more difficult to predict, several diagnosis categories, procedure codes and LOS amongst shorter-stay patients can be predicted with higher confidence in early stages of patient stay. Lastly, value of information analysis indicated that diagnoses, medication and structured assessment forms were the most valuable EHR data elements in predicting managerial variables of interest through a data mining approach.

Prediction of emergency department patient disposition decision for proactive resource allocation for admission

We investigate the capability of information from electronic health records of an emergency department (ED) to predict patient disposition decisions for reducing "boarding" delays through the proactive initiation of admission processes (e.g., inpatient bed requests, transport, etc.). We model the process of ED disposition decision prediction as a hierarchical multiclass classification while dealing with the progressive accrual of clinical information throughout the ED caregiving process. Multinomial logistic regression as well as machine learning models are built for carrying out the predictions. Utilizing results from just the first set of ED laboratory tests along with other prior information gathered for each patient (2.5 h ahead of the actual disposition decision on average), our model predicts disposition decisions with positive predictive values of 55.4%, 45.1%, 56.9%, and 47.5%, while controlling false positive rates (1.4%, 1.0%, 4.3%, and 1.4%), with AUC values of 0.97, 0.95, 0.89, and 0.84 for the four admission (minor) classes, i.e., intensive care unit (3.6% of the testing samples), telemetry unit (2.2%), general practice unit (11.9%), and observation unit (6.6%) classes, respectively. Moreover, patients destined to intensive care unit present a more drastic increment in prediction quality at triage than others. Disposition decision classification models can provide more actionable information than a binary admission vs. discharge prediction model for the proactive initiation of admission processes for ED patients. Observing the distinct trajectories of information accrual and prediction quality evolvement for ED patients destined to different types of units, proactive coordination strategies should be tailored accordingly for each destination unit.

Multistate model of the patient flow process in the pediatric emergency department

Objectives

The main purpose of this paper was to model the process by which patients enter the ED, are seen by physicians, and discharged from the Emergency Department at Nationwide Children’s Hospital, as well as identify modifiable factors that are associated with ED lengths of stay through use of multistate modeling.

Methods

In this study, 75,591 patients admitted to the ED from March 1^st, 2016 to February 28^th, 2017 were analyzed using a multistate model of the ED process. Cox proportional hazards models with transition-specific covariates were used to model each transition in the multistate model and the Aalen-Johansen estimator was used to obtain transition probabilities and state occupation probabilities in the ED process.

Results

Acuity level, season, time of day and number of ED physicians had significant and varying associations with the six transitions in the multistate model. Race and ethnicity were significantly associated with transition to left without being seen, but not with the other transitions. Conversely, age and gender were significantly associated with registration to room and subsequent transitions in the model, though the magnitude of association was not strong.

Conclusions

The multistate model presented in this paper decomposes the overall ED length of stay into constituent transitions for modeling covariate-specific effects on each transition. This allows physicians to understand the ED process and identify which potentially modifiable covariates would have the greatest impact on reducing the waiting times in each state in the model.

Overflow models for the admission of intensive care patients

An earlier article, inspired by overflow models in telecommunication systems with multiple streams of telephone calls, proposed a new analytical model for a network of intensive care units (ICUs), and a new patient referral policy for such networks to reduce the blocking probability of external emergency patients without degrading the quality of service (QoS) of canceled elective operations, due to the more efficient use of ICU capacity overall. In this work, we use additional concepts and insights from traditional teletraffic theory, including resource sharing, trunk reservation, and mutual overflow, to design a new patient referral policy to further improve ICU network efficiency. Numerical results based on the analytical model demonstrate that our proposed policy can achieve a higher acceptance level than the original policy with a smaller number of beds, resulting in improved service for all patients. In particular, our proposed policy can always achieve much lower blocking probabilities for external emergency patients while still providing sufficient service for internal emergency and elective patients. In addition, we provide new accurate and computationally efficient analytical approximations for QoS evaluation of ICU networks using our proposed policy. We demonstrate numerically that our new approximation method yields more accurate, robust and conservative results overall than the traditional approximation. Finally, we demonstrate how our proposed approximation method can be applied to solve resource planning and optimization problems for ICU networks in a scalable and computationally efficient manner.

Predicting hospital admission at the emergency department triage: A novel prediction model

BACKGROUND

Emergency department (ED) overcrowding is a growing international patient safety issue. A major contributor to overcrowding is long wait times for inpatient hospital admission. The objective of this study is to create a model that can predict a patient's need for hospital admission at the time of triage.

METHODS

Retrospective observational study of electronic clinical records of all ED visits over ten years to a large urban hospital in Singapore. The data was randomly divided into a derivation set and a validation set. We used the derivation set to develop a logistic regression model that predicts probability of hospital admission for patients presenting to the ED. We tested the model on the validation set and evaluated the performance with receiver operating characteristic (ROC) curve analysis.

RESULTS

A total of 1,232,016 visits were included for final analysis, of which 38.7% were admitted. Eight variables were included in the final model: age group, race, postal code, day of week, time of day, triage category, mode of arrival, and fever status. The model performed well on the validation set with an area under the curve of 0.825 (95% CI 0.824-0.827). Increasing age, increasing triage acuity, and mode of arrival via private patient transport were most predictive of the need for admission.

CONCLUSIONS

We developed a model that accurately predicts admission for patients presenting to the ED using demographic, administrative, and clinical data routinely collected at triage. Implementation of the model into the electronic health record could help reduce the burden of overcrowding.

Deconstructing the 4-h rule for access to emergency care and putting patients first

Evidence suggests improved outcomes for patients requiring emergency admission to hospital are associated with improved emergency department (ED) efficiency and lower transit times. Factors preventing timely transfers of emergency patients to in-patient beds across the ED-in-patient interface are major causes for ED crowding, for which several remedial strategies are possible, including parallel processing of probable admissions, direct-to-ward admissions and single-point medical registrars for receiving and processing all referrals directed at specific speciality units. Dynamic measures of ED overcrowding that focus on boarding time are more indicative of EDs with exit block involving the ED-in-patient interface than static proxy measures such as hospital bed occupancy and numbers of ED presentations. The ideal 4-h compliance rate for all ED presentations is around 80%, based on a large retrospective study of more than 18million presentations to EDs of 59 Australian hospitals over 4 years, which demonstrated a highly significant linear reduction in risk-adjusted in-patient mortality for admitted patients as the compliance rate for all patients rose to 83%, but was not confirmed beyond this rate. Closely monitoring patient outcomes for emergency admissions in addition to compliance with time-based access targets is strongly recommended in ensuring reforms aimed at decongesting EDs do not compromise the quality and safety of patient care.

Predicting admission at triage: are nurses better than a simple objective score?

AIM

We compared two methods of predicting hospital admission from ED triage: probabilities estimated by triage nurses and probabilities calculated by the Glasgow Admission Prediction Score (GAPS).

METHODS

In this single-centre prospective study, triage nurses estimated the probability of admission using a 100 mm visual analogue scale (VAS), and GAPS was generated automatically from triage data. We compared calibration using rank sum tests, discrimination using area under receiver operating characteristic curves (AUC) and accuracy with McNemar's test.

RESULTS

Of 1829 attendances, 745 (40.7%) were admitted, not significantly different from GAPS' prediction of 750 (41.0%, p=0.678). In contrast, the nurses' mean VAS predicted 865 admissions (47.3%), overestimating by 6.6% (p<0.0001). GAPS discriminated between admission and discharge as well as nurses, its AUC 0.876 compared with 0.875 for VAS (p=0.93). As a binary predictor, its accuracy was 80.6%, again comparable with VAS (79.0%), p=0.18. In the minority of attendances, when nurses felt at least 95% certain of the outcome, VAS' accuracy was excellent, at 92.4%. However, in the remaining majority, GAPS significantly outperformed VAS on calibration (+1.2% vs +9.2%, p<0.0001), discrimination (AUC 0.810 vs 0.759, p=0.001) and accuracy (75.1% vs 68.9%, p=0.0009). When we used GAPS, but 'over-ruled' it when clinical certainty was ≥95%, this significantly outperformed either method, with AUC 0.891 (0.877-0.907) and accuracy 82.5% (80.7%-84.2%).

CONCLUSIONS

GAPS, a simple clinical score, is a better predictor of admission than triage nurses, unless the nurse is sure about the outcome, in which case their clinical judgement should be respected.