Classification of hospital admissions into emergency and elective care: a machine learning approach

A retrospective analysis of the incidence and risk factors of perioperative urinary tract infections after total hysterectomy

INTRODUCTION

Perioperative urinary tract infections (PUTIs) are common in the United States and are a significant contributor to high healthcare costs. There is a lack of large studies on the risk factors for PUTIs after total hysterectomy (TH).

METHODS

We conducted a retrospective study using a national inpatient sample (NIS) of 445,380 patients from 2010 to 2019 to analyze the risk factors and annual incidence of PUTIs associated with TH perioperatively.

RESULTS

PUTIs were found in 9087 patients overall, showing a 2.0% incidence. There were substantial differences in the incidence of PUTIs based on age group (P < 0.001). Between the two groups, there was consistently a significant difference in the type of insurance, hospital location, hospital bed size, and hospital type (P < 0.001). Patients with PUTIs exhibited a significantly higher number of comorbidities (P < 0.001). Unsurprisingly, patients with PUTIs had a longer median length of stay (5 days vs. 2 days; P < 0.001) and a higher in-hospital death rate (from 0.1 to 1.1%; P < 0.001). Thus, the overall hospitalization expenditures increased by $27,500 in the median ($60,426 vs. $32,926, P < 0.001) as PUTIs increased medical costs. Elective hospitalizations are less common in patients with PUTIs (66.8% vs. 87.6%; P < 0.001). According to multivariate logistic regression study, the following were risk variables for PUTIs following TH: over 45 years old; number of comorbidities (≥ 1); bed size of hospital (medium, large); teaching hospital; region of hospital(south, west); preoperative comorbidities (alcohol abuse, deficiency anemia, chronic blood loss anemia, congestive heart failure, diabetes, drug abuse, hypertension, hypothyroidism, lymphoma, fluid and electrolyte disorders, metastatic cancer, other neurological disorders, paralysis, peripheral vascular disorders, psychoses, pulmonary circulation disorders, renal failure, solid tumor without metastasis, valvular disease, weight loss); and complications (sepsis, acute myocardial infarction, deep vein thrombosis, gastrointestinal hemorrhage, pneumonia, stroke, wound infection, wound rupture, hemorrhage, pulmonary embolism, blood transfusion, postoperative delirium).

CONCLUSIONS

The findings suggest that identifying these risk factors can lead to improved preventive strategies and management of PUTIs in TH patients. Counseling should be done prior to surgery to reduce the incidence of PUTIs.

THE MANUSCRIPT ADDS TO CURRENT KNOWLEDGE

In medical practice, the identification of risk factors can lead to improved patient prevention and treatment strategies. We conducted a retrospective study using a national inpatient sample (NIS) of 445,380 patients from 2010 to 2019 to analyze the risk factors and annual incidence of PUTIs associated with TH perioperatively. PUTIs were found in 9087 patients overall, showing a 2.0% incidence. We found that noted increased length of hospital stay, medical cost, number of pre-existing comorbidities, size of the hospital, teaching hospitals, and region to also a play a role in the risk of UTI's.

CLINICAL TOPICS

Urogynecology.

A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis

Proactive analysis of patient pathways helps healthcare providers anticipate treatment-related risks, identify outcomes, and allocate resources. Machine learning (ML) can leverage a patient's complete health history to make informed decisions about future events. However, previous work has mostly relied on so-called black-box models, which are unintelligible to humans, making it difficult for clinicians to apply such models. Our work introduces PatWay-Net, an ML framework designed for interpretable predictions of admission to the intensive care unit (ICU) for patients with symptoms of sepsis. We propose a novel type of recurrent neural network and combine it with multi-layer perceptrons to process the patient pathways and produce predictive yet interpretable results. We demonstrate its utility through a comprehensive dashboard that visualizes patient health trajectories, predictive outcomes, and associated risks. Our evaluation includes both predictive performance - where PatWay-Net outperforms standard models such as decision trees, random forests, and gradient-boosted decision trees - and clinical utility, validated through structured interviews with clinicians. By providing improved predictive accuracy along with interpretable and actionable insights, PatWay-Net serves as a valuable tool for healthcare decision support in the critical case of patients with symptoms of sepsis.

Forecasting ward-level bed requirements to aid pandemic resource planning: Lessons learned and future directions

During the COVID-19 pandemic, there has been considerable research on how regional and country-level forecasting can be used to anticipate required hospital resources. We add to and build on this work by focusing on ward-level forecasting and planning tools for hospital staff during the pandemic. We present an assessment, validation, and deployment of a working prototype forecasting tool used within a modified Traffic Control Bundling (TCB) protocol for resource planning during the pandemic. We compare statistical and machine learning forecasting methods and their accuracy at one of the largest hospitals (Vancouver General Hospital) in Canada against a medium-sized hospital (St. Paul's Hospital) in Vancouver, Canada through the first three waves of the COVID-19 pandemic in the province of British Columbia. Our results confirm that traditional statistical and machine learning (ML) forecasting methods can provide valuable ward-level forecasting to aid in decision-making for pandemic resource planning. Using point forecasts with upper 95% prediction intervals, such forecasting methods would have provided better accuracy in anticipating required beds on COVID-19 hospital units than ward-level capacity decisions made by hospital staff. We have integrated our methodology into a publicly available online tool that operationalizes ward-level forecasting to aid with capacity planning decisions. Importantly, hospital staff can use this tool to translate forecasts into better patient care, less burnout, and improved planning for all hospital resources during pandemics.

A Machine Learning Approach for Monitoring and Classifying Healthcare Data-A Case of Emergency Department of KSA Hospitals

The Emergency Departments (EDs), in hospitals located in a few important areas in Saudi Arabia, experience a heavy inflow of patients due to viral illnesses, pandemics, and even on a few special occasions events such as Hajj or Umrah, when pilgrims travel from one region to another with severe disease conditions. Apart from the EDs, it is critical to monitor the movements of patients from EDs to other wards inside the hospital or in the region. This is to track the spread of viral illnesses that require more attention. In this scenario, Machine Learning (ML) algorithms can be used to classify the data into many classes and track the target audience. The current research article presents a Machine Learning-based Medical Data Monitoring and Classification Model for the EDs of the KSA hospitals and is named MLMDMC-ED technique. The most important aim of the proposed MLMDMC-ED technique is to monitor and track the patient's visits to the EDs, the treatment given to them based on the Canadian Emergency Department Triage and Acuity Scale (CTAS), and their Length Of Stay (LOS) in the hospital, based on their treatment requirements. A patient's clinical history is crucial in terms of making decisions during health emergencies or pandemics. So, the data should be processed so that it can be classified and visualized in different formats using the ML technique. The current research work aims at extracting the textual features from the patients' data using the metaheuristic Non-Defeatable Genetic Algorithm II (NSGA II). The data, collected from the hospitals, are classified using the Graph Convolutional Network (GCN) model. Grey Wolf Optimizer (GWO) is exploited for fine-tuning the parameters to optimize the performance of the GCN model. The proposed MLMDMC-ED technique was experimentally validated on the healthcare data and the outcomes indicated the improvements of the MLMDMC-ED technique over other models with a maximum accuracy of 91.87%.

Big Data Analytics to Reduce Preventable Hospitalizations-Using Real-World Data to Predict Ambulatory Care-Sensitive Conditions

The purpose of this study was to develop a prediction model to identify individuals and populations with a high risk of being hospitalized due to an ambulatory care-sensitive condition who might benefit from preventative actions or tailored treatment options to avoid subsequent hospital admission. A rate of 4.8% of all individuals observed had an ambulatory care-sensitive hospitalization in 2019 and 6389.3 hospital cases per 100,000 individuals could be observed. Based on real-world claims data, the predictive performance was compared between a machine learning model (Random Forest) and a statistical logistic regression model. One result was that both models achieve a generally comparable performance with c-values above 0.75, whereas the Random Forest model reached slightly higher c-values. The prediction models developed in this study reached c-values comparable to existing study results of prediction models for (avoidable) hospitalization from the literature. The prediction models were designed in such a way that they can support integrated care or public and population health interventions with little effort with an additional risk assessment tool in the case of availability of claims data. For the regions analyzed, the logistic regression revealed that switching to a higher age class or to a higher level of long-term care and unit from prior hospitalizations (all-cause and due to an ambulatory care-sensitive condition) increases the odds of having an ambulatory care-sensitive hospitalization in the upcoming year. This is also true for patients with prior diagnoses from the diagnosis groups of maternal disorders related to pregnancy, mental disorders due to alcohol/opioids, alcoholic liver disease and certain diseases of the circulatory system. Further model refinement activities and the integration of additional data, such as behavioral, social or environmental data would improve both model performance and the individual risk scores. The implementation of risk scores identifying populations potentially benefitting from public health and population health activities would be the next step to enable an evaluation of whether ambulatory care-sensitive hospitalizations can be prevented.

Does What Happens in the ED Stay in the ED? The Effects of Emergency Department Physician Workload on Post-ED Care Use

PROBLEM DEFINITION

Emergency department (ED) crowding has been a pressing concern in healthcare systems in the U.S. and other developed countries. As such, many researchers have studied its effects on outcomes within the ED. In contrast, we study the effects of ED crowding on system performance outside the ED-specifically, on post-ED care utilization. Further, we explore the mediating effects of care intensity in the ED on post-ED care use.

METHODOLOGY/RESULTS

We utilize a dataset assembled from more than four years of microdata from a large U.S. hospital and exhaustive billing data in an integrated health system. By using count models and instrumental variable analyses to answer the proposed research questions, we find that there is an increasing concave relationship between ED physician workload and post-ED care use. When ED workload increases from its 5th percentile to the median, the number of post-discharge care events (i.e., medical services) for patients who are discharged home from the ED increases by 5% and it is stable afterwards. Further, we identify physician test-ordering behavior as a mechanism for this effect: when the physician is busier, she responds by ordering more tests for less severe patients. We document that this "extra" testing generates "extra" post-ED care utilization for these patients.

MANAGERIAL IMPLICATIONS

This paper contributes new insights on how physician and patient behaviors under ED crowding impact a previously unstudied system performance measure: post-ED care utilization. Our findings suggest that prior studies estimating the cost of ED crowding underestimate the true effect, as they do not consider the "extra" post-ED care utilization.

Finding good alternatives to hospitalisation: a data register study in five municipal acute wards in Norway

BACKGROUND

In Norway, municipal acute wards (MAWs) have been implemented in primary healthcare since 2012. The MAWs were intended to offer decentralised acute medical care 24/7 for patients who otherwise would be admitted to hospital. The aim of this study was to assess whether the MAW represents the alternative to hospitalisation as intended, through 1) describing the characteristics of patients intended as candidates for MAWs by primary care physicians, 2) exploring the need for extended diagnostics prior to admission in MAWs, and 3) exploring factors associated with patients being transferred from the MAWs to hospital.

METHODS

The study was based on register data from five MAWs in Norway in the period 2014-2020.

RESULTS

In total, 16 786 admissions were included. The median age of the patients was 78 years, 60% were women, and the median length of stay was three days. Receiving oral medication (OR 1.23, 95% CI 1.09-1.40), and the MAW being located nearby the hospital (OR 2.29, 95% CI 1.92-2.72) were factors associated with patients admitted to MAW after extended diagnostics. Patients needing advanced treatment, such as oxygen therapy (OR 2.13, 95% CI 1.81-2.51), intravenous medication (OR 1.60, 95% CI 1.45-1.81), intravenous fluid therapy (OR 1.32, 95% CI 1.19-1.47) and MAWs with long travel distance from the MAW to the hospital (OR 1.46, 95% CI 1.22-1.74) had an increased odds for being transferred to hospital.

CONCLUSIONS

Our findings indicate that MAWs do not represent the alternative to hospitalisation as intended. The results show that patients receiving extended diagnostics before admission to MAW got basic treatment, while patients in need of advanced medical treatment were transferred to hospital from a MAW. This indicates that there is still a potential to develop MAWs in order to fulfil the intended health service level.

Exploring characteristics of specialization as moderators of the link between specialization and patient experience of care

BACKGROUND

Hospitals are increasingly pursuing specialization as a strategy to operate efficiently while delivering high-quality care. To date, however, evidence is lacking on whether hospital specialization has a consistent effect on patients' experience of care or whether different specialization characteristics influence how specialization works.

PURPOSE

This study investigates whether specialization characteristics, that is, the within-specialty concentration and the within-specialty urgency score, moderate the link between hospital specialization and patient experience of care.

METHODOLOGY

We use patient-reported and administrative data from German hospitals between 2014 and 2017, with orthopedic and trauma care as the research setting. Our sample consists of 157,458 patient observations nested within 483 hospitals. We apply random-intercept multilevel modeling.

RESULTS

Our results indicate that the effect of specialization on patient experience of care (a) decreases as the within-specialty concentration increases and (b) increases as the within-specialty urgency score increases.

CONCLUSION

This study provides novel insights into the specialization characteristics that make hospital specialization in orthopedic and trauma care particularly effective at improving patient experiences.

PRACTICE IMPLICATIONS

Although specialization is gaining popularity as a strategy for pooling scarce resources and facilitating high-quality health care, hospital managers and policymakers should consider that certain characteristics of specialization can influence the way that specialization works and how effective it is in improving patient experiences. Within the scope of orthopedic and trauma care, our study suggests that a low concentration of diagnoses within a service area and a high average level of medical urgency make specialization particularly effective at improving patient experiences.

The path from big data analytics capabilities to value in hospitals: a scoping review

BACKGROUND

As the uptake of health information technologies increased, most healthcare organizations have become producers of big data. A growing number of hospitals are investing in the development of big data analytics (BDA) capabilities. If the promises associated with these capabilities are high, how hospitals create value from it remains unclear. The present study undertakes a scoping review of existing research on BDA use in hospitals to describe the path from BDA capabilities (BDAC) to value and its associated challenges.

METHODS

This scoping review was conducted following Arksey and O'Malley's 5 stages framework. A systematic search strategy was adopted to identify relevant articles in Scopus and Web of Science. Data charting and extraction were performed following an analytical framework that builds on the resource-based view of the firm to describe the path from BDA capabilities to value in hospitals.

RESULTS

Of 1,478 articles identified, 94 were included. Most of them are experimental research (n=69) published in medical (n=66) or computer science journals (n=28). The main value targets associated with the use of BDA are improving the quality of decision-making (n=56) and driving innovation (n=52) which apply mainly to care (n=67) and administrative (n=48) activities. To reach these targets, hospitals need to adequately combine BDA capabilities and value creation mechanisms (VCM) to enable knowledge generation and drive its assimilation. Benefits are endpoints of the value creation process. They are expected in all articles but realized in a few instances only (n=19).

CONCLUSIONS

This review confirms the value creation potential of BDA solutions in hospitals. It also shows the organizational challenges that prevent hospitals from generating actual benefits from BDAC-building efforts. The configuring of strategies, technologies and organizational capabilities underlying the development of value-creating BDA solutions should become a priority area for research, with focus on the mechanisms that can drive the alignment of BDA and organizational strategies, and the development of organizational capabilities to support knowledge generation and assimilation.

Risk Factors for Pulmonary Embolism in ICU Patients: A Retrospective Cohort Study from the MIMIC-III Database

Pulmonary embolism (PE) is a common and potentially lethal form of venous thromboembolic disease in ICU patients. A limited number of risk factors have been associated with PE in ICU patients. In this study, we aimed to screen the independent risk factors of PE in ICU patients that can be used to evaluate the patient's condition and provide targeted treatment. We performed a retrospective cohort study using a freely accessible critical care database Medical Information Mart for Intensive Care (MIMIC)-III. The ICU patients were divided into two groups based on the incidence of PE. Finally, 9871 ICU patients were included, among which 204 patients (2.1%) had pulmonary embolism. During the multivariate logistic regression analysis, sepsis, hospital_LOS (the length of stay in hospital), type of admission, tumor, APTT (activated partial thromboplastin time) and platelet were independent risk factors for patients for PE in ICU, with OR values of 1.471 (95%CI 1.001-2.162), 1.001 (95%CI 1.001-1.001), 3.745 (95%CI 2.187-6.414), 1.709 (95%CI 1.247-2.341), 1.014 (95%CI 1.010-1.017) and 1.002 (95%CI 1.001-1.003) (P_s < 0.05). ROC curve analysis showed that the composite indicator had a higher predictive value for ICU patients with PE, with a ROC area under the curve (AUC) of 0.743 (95%CI 0.710 -0.776, p < 0.001). Finally, sepsis, tumor, platelet count, length of stay in the hospital, emergency admission and APTT were independent predictors of PE in ICU patients.

Multilevel Zero-One Inflated Beta Regression Model for the Analysis of the Relationship between Exogenous Health Variables and Technical Efficiency in the Spanish National Health System Hospitals

Background: This article proposes a methodological innovation in health economics for the second stage analysis of technical efficiency in hospitals. It investigates the relationship between the installed capacity in regions and hospitals and their ownership structure. Methods: A multilevel zero-one inflated beta regression model is employed to model pure technical efficiency more adequately than other models frequently used in econometrics. Results: Compared to publicly managed hospitals, the mean efficiency index of hospitals with public-private partnership (PPP) formulas was 4.27-fold. This figure was 1.90-fold for private hospitals. Concerning the efficiency frontier, the odds ratio (OR) of PPP models vs. public hospitals was 42.06. The OR of private hospitals vs. public hospitals was 8.17. A one standard deviation increase in the percentage of beds in intensive care units increases the odds of being situated on the efficiency frontier by 50%. Conclusions: The proportion of hospital beds in intensive care units relates to a higher chance of being on the efficiency frontier. Hospital ownership structure is related to the mean efficiency index of Spanish National Health Service hospitals, as well as the odds of being situated on the efficiency frontier.

Machine Learning in Medical Emergencies: a Systematic Review and Analysis

Despite the increasing demand for artificial intelligence research in medicine, the functionalities of his methods in health emergency remain unclear. Therefore, the authors have conducted this systematic review and a global overview study which aims to identify, analyse, and evaluate the research available on different platforms, and its implementations in healthcare emergencies. The methodology applied for the identification and selection of the scientific studies and the different applications consist of two methods. On the one hand, the PRISMA methodology was carried out in Google Scholar, IEEE Xplore, PubMed ScienceDirect, and Scopus. On the other hand, a review of commercial applications found in the best-known commercial platforms (Android and iOS). A total of 20 studies were included in this review. Most of the included studies were of clinical decisions (n = 4, 20%) or medical services or emergency services (n = 4, 20%). Only 2 were focused on m-health (n = 2, 10%). On the other hand, 12 apps were chosen for full testing on different devices. These apps dealt with pre-hospital medical care (n = 3, 25%) or clinical decision support (n = 3, 25%). In total, half of these apps are based on machine learning based on natural language processing. Machine learning is increasingly applicable to healthcare and offers solutions to improve the efficiency and quality of healthcare. With the emergence of mobile health devices and applications that can use data and assess a patient's real-time health, machine learning is a growing trend in the healthcare industry.

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.

Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes: The 2019 Literature Year in Review

Data science continues to be recognized and used within healthcare due to the increased availability of large data sets and advanced analytics. It can be challenging for nurse leaders to remain apprised of this rapidly changing landscape. In this article, we describe our findings from a scoping literature review of papers published in 2019 that use data science to explore, explain, and/or predict 15 phenomena of interest to nurses. Fourteen of the 15 phenomena were associated with at least one paper published in 2019. We identified the use of many contemporary data science methods (eg, natural language processing, neural networks) for many of the outcomes. We found many studies exploring Readmissions and Pressure Injuries. The topics of Artificial Intelligence/Machine Learning Acceptance, Burnout, Patient Safety, and Unit Culture were poorly represented. We hope that the studies described in this article help readers: (1) understand the breadth and depth of data science's ability to improve clinical processes and patient outcomes that are relevant to nurses and (2) identify gaps in the literature that are in need of exploration.

Machine learning in patient flow: a review

This work is a review of the ways in which machine learning has been used in order to plan, improve or aid the problem of moving patients through healthcare services. We decompose the patient flow problem into four subcategories: prediction of demand on a healthcare institution, prediction of the demand and resource required to transfer patients from the emergency department to the hospital, prediction of potential resource required for the treatment and movement of inpatients and prediction of length-of-stay and discharge timing. We argue that there are benefits to both approaches of considering the healthcare institution as a whole as well as the patient by patient case and that ideally a combination of these would be best for improving patient flow through hospitals. We also argue that it is essential for there to be a shared dataset that will allow researchers to benchmark their algorithms on and thereby allow future researchers to build on that which has already been done. We conclude that machine learning for the improvement of patient flow is still a young field with very few papers tailor-making machine learning methods for the problem being considered. Future works should consider the need to transfer algorithms trained on a dataset to multiple hospitals and allowing for dynamic algorithms which will allow real-time decision-making to help clinical staff on the shop floor.

Statistical learning methodologies and admission prediction in an emergency department

BACKGROUND

The quality of an emergency department (ED) is highly dependent on its ability to supply efficient, as well as high-quality treatment for all patients. Key performance indicators are important when measuring the performance of an emergency department. This study aimed to perform an exploratory data analysis and to develop an admission prediction model based on a dataset that was constructed from key performance indicators selected by a panel of expert physicians, nurses and hospital administrators.

METHODS

A dataset of 172,695 records was retrospectively collected from an Emergency Department. The relationships within the dataset were analyzed and three machine learning algorithms were compared for an admission predictive model based on the initial patient information.

RESULTS

The dataset showed that mean length of stay was similar in the different weekdays, there was a positive linear relationship between the length of stay and patient age and the admission predictive model yielded an AUC of 0.79.

CONCLUSIONS

The selected indicators can be used to study whether emergency department allocates its resources properly to cope with overcrowding and the predictive model may be employed by Hospital and ED administrates to fill information gaps and support decision making for the improvement of the key performance indicators.

Investigating the link between medical urgency and hospital efficiency - Insights from the German hospital market

With hospital budgets remaining tight and healthcare expenditure rising due to demographic change and advances in technology, hospitals continue to face calls to contain costs and allocate their resources more efficiently. In this context, efficiency has emerged as an increasingly important way for hospitals to withstand competitive pressures in the hospital market. Doing so, however, can be challenging given unpredictable fluctuations in demand, a prime example of which are emergencies, i.e. urgent medical cases. The link between medical urgency and hospitals' efficiency, however, has been neglected in the literature to date. This study therefore aims to investigate the relationship between hospitals' urgency characteristics and their efficiency. Our analyses are based on 4094 observations from 1428 hospitals throughout Germany for the years 2015, 2016, and 2017. We calculate an average urgency score for each hospital based on all cases treated in that hospital per year and also investigate the within-hospital dispersion of medical urgency. To analyze the association of these urgency measures with hospitals' efficiency we use a two-stage double bootstrap data envelopment analysis approach with truncated regression. We find a negative relationship between the urgency score and hospital efficiency. When testing for non-linear effects, the results reveal a u-shaped association, indicating that having either a high or low overall urgency score is beneficial in terms of efficiency. Finally, our results reveal that higher within-hospital urgency dispersion is negatively related to efficiency.

Severity of illness and the weekend mortality effect: a retrospective cohort study

Background

Weekend admission to the hospital has been found to be associated with higher in-hospital mortality rates, but the cause for this phenomenon remains controversial. US based studies have been limited in their characterization of the weekend patient population, making it difficult to draw conclusions about the implications of this effect.

Methods

A retrospective cohort study, examining de-identified, patient level data from 2015 to 2017 at US academic medical centers submitting data to the Vizient database, comparing demographic and clinical risk profiles, as well as mortality, cost and length of stay, between weekend and weekday patient populations. Between-group differences in mortality were assessed using the chi-square test for categorical measures and Wilcoxon rank-sum test for continuous measures. Logistic regression models were used to test the multivariate association of weekend admission and other patient-level factors with death, LOS, etc.

Results

We analyzed 10,365,605 adult inpatient encounters. Within the weekend patient population, 30.6% of patients were categorized as having either a major or extreme risk of mortality on admission, as compared to 23.7% on weekdays (p < 0.001). We found a significantly increased unadjusted mortality rate associated with weekend admission (OR 1.46; 95% CI 1.45–1.47) which was substantially attenuated after adjusting for disease severity and other demographic covariates, though remained significant (OR 1.05; 95% CI 1.04–1.06). In the subgroup of non-elective admissions, the unadjusted OR for death was 1.14 (95% CI 1.13–1.15), and the adjusted OR was 1.04 (95% CI 1.03–1.05). Weekend admission was associated with a longer median LOS (4 vs 3 days in the weekday group; p < 0.01), but a lower median cost ($8224 vs $9999 dollars in the weekday group; p < 0.01).

Conclusion

The patient population admitted on weekends is proportionally higher risk than the population admitted on weekdays, and the observed weekend mortality effect is largely attributable to this risk imbalance.

[Routine Data from Emergency Departments: Varying Documentation Standards, Billing Modalities and Data Custodians at an Identical Unit of Care]

Hintergrund Nicht nur im Kontext der Neuordnung der Notfallversorgung in Deutschland besteht derzeit ein hoher Bedarf an Daten aus Notaufnahmen. Für die Versorgungsforschung bieten sich Daten an, welche auf gesetzlicher Grundlage generiert werden. Unterschiedliche Kostenträger und Abrechnungsmodi stellen eigene Anforderungen an die Dokumentation dieser Routinedaten.

Methodische Herausforderungen Aufgrund der sektoralen Trennung gibt es keinen Datensatz oder Datenhalter, der Auskunft über alle Notaufnahmebehandlungen geben kann. Aus administrativer Sicht gilt die gesamte Notaufnahmebehandlung als ambulant oder stationär, tatsächlich wird die Entscheidung darüber erst während der Versorgung getroffen. Für die stationäre Versorgung existiert ein administratives Notfallkennzeichen, allerdings kein direktes Merkmal für Notaufnahmebehandlungen. Bei Abrechnung ambulanter Fälle über die kassenärztlichen Vereinigungen ist mindestens eine Diagnose (ICD-10-Kode) zu erfassen, versehen mit einem Kennzeichen zur Diagnosesicherheit. Es können mehrere ICD-10-Kodes ohne Hierarchie angegeben werden. Bei stationär behandelten Patienten ist eine Aufnahmediagnose und nach Behandlungsende die Hauptdiagnose und ggf. Nebendiagose(n) an die zuständige Krankenkasse zu übermitteln. Die gesetzliche Unfallversicherung hat eigene Dokumentationsanforderungen.

Lösungsansätze Je nach Forschungsfrage und Studiendesign sind unterschiedliche Vorgehensweisen erforderlich. Stammen die Daten unmittelbar aus Notaufnahmen bzw. Kliniken ist eine Information über den Kostenträger und den Abrechnungsmodus hilfreich. Bei Nutzung von Krankenkassendaten muss die Identifikation von stationär behandelten Patienten in einer Notaufnahme aktuell indirekt erfolgen. Dazu können unter anderem die Parameter Aufnahmegrund und definierte „eindeutige“ Notfall-Diagnosen herangezogen werden. Die fallpauschalenbezogene Krankenhausstatistik hat eigene Limitationen, enthält dafür aber die stationären Fälle aller Kostenträger.

Diskussion Die divergierenden Anforderungen an die administrative Dokumentation verursachen einen hohen Aufwand in den Kliniken. Perspektivisch ist eine Vereinheitlichung der Leistungserfassung und Dokumentation von Notfallbehandlungen aller Kostenarten auch zur Generierung von validen, vergleichbaren und repräsentativen Daten für die Versorgungsforschung erstrebenswert. Die Einführung eines eigenen Fachabteilungsschlüssels würde zur Identifikation von Notaufnahmebehandlungen beitragen.