Showing papers presented at "American Medical Informatics Association Annual Symposium in 2013"

Developing predictive models using electronic medical records: challenges and pitfalls.

Abstract: While Electronic Medical Records (EMR) contain detailed records of the patient-clinician encounter - vital signs, laboratory tests, symptoms, caregivers' notes, interventions prescribed and outcomes - developing predictive models from this data is not straightforward. These data contain systematic biases that violate assumptions made by off-the-shelf machine learning algorithms, commonly used in the literature to train predictive models. In this paper, we discuss key issues and subtle pitfalls specific to building predictive models from EMR. We highlight the importance of carefully considering both the special characteristics of EMR as well as the intended clinical use of the predictive model and show that failure to do so could lead to developing models that are less useful in practice. Finally, we describe approaches for training and evaluating models on EMR using early prediction of septic shock as our example application.

Sick patients have more data: the non-random completeness of electronic health records.

Abstract: As interest in the reuse of electronic health record (EHR) data for research purposes grows, so too does awareness of the significant data quality problems in these non-traditional datasets. In the past, however, little attention has been paid to whether poor data quality merely introduces noise into EHR-derived datasets, or if there is potential for the creation of spurious signals and bias. In this study we use EHR data to demonstrate a statistically significant relationship between EHR completeness and patient health status, indicating that records with more data are likely to be more representative of sick patients than healthy ones, and therefore may not reflect the broader population found within the EHR.

Crowdsourcing the verification of relationships in biomedical ontologies.

Abstract: Biomedical ontologies are often large and complex, making ontology development and maintenance a challenge. To address this challenge, scientists use automated techniques to alleviate the difficulty of ontology development. However, for many ontology-engineering tasks, human judgment is still necessary. Microtask crowdsourcing, wherein human workers receive remuneration to complete simple, short tasks, is one method to obtain contributions by humans at a large scale. Previously, we developed and refined an effective method to verify ontology hierarchy using microtask crowdsourcing. In this work, we report on applying this method to find errors in the SNOMED CT CORE subset. By using crowdsourcing via Amazon Mechanical Turk with a Bayesian inference model, we correctly verified 86% of the relations from the CORE subset of SNOMED CT in which Rector and colleagues previously identified errors via manual inspection. Our results demonstrate that an ontology developer could deploy this method in order to audit large-scale ontologies quickly and relatively cheaply.

Persuasive Performance Feedback: The Effect of Framing on Self-Efficacy

Abstract: Self-monitoring technologies have proliferated in recent years as they offer excellent potential for promoting healthy behaviors. Although these technologies have varied ways of providing real-time feedback on a user's current progress, we have a dearth of knowledge of the framing effects on the performance feedback these tools provide. With an aim to create influential, persuasive performance feedback that will nudge people toward healthy behaviors, we conducted an online experiment to investigate the effect of framing on an individual's self-efficacy. We identified 3 different types of framing that can be applicable in presenting performance feedback: (1) the valence of performance (remaining vs. achieved framing), (2) presentation type (text-only vs. text with visual), and (3) data unit (raw vs. percentage). Results show that the achieved framing could lead to an increased perception of individual's performance capabilities. This work provides empirical guidance for creating persuasive performance feedback, thereby helping people designing self-monitoring technologies to promote healthy behaviors.

Using natural language processing on the free text of clinical documents to screen for evidence of homelessness among US veterans.

Abstract: Information retrieval algorithms based on natural language processing (NLP) of the free text of medical records have been used to find documents of interest from databases. Homelessness is a high priority non-medical diagnosis that is noted in electronic medical records of Veterans in Veterans Affairs (VA) facilities. Using a human-reviewed reference standard corpus of clinical documents of Veterans with evidence of homelessness and those without, an open-source NLP tool (Automated Retrieval Console v2.0, ARC) was trained to classify documents. The best performing model based on document level work-flow performed well on a test set (Precision 94%, Recall 97%, F-Measure 96). Processing of a naive set of 10,000 randomly selected documents from the VA using this best performing model yielded 463 documents flagged as positive, indicating a 4.7% prevalence of homelessness. Human review noted a precision of 70% for these flags resulting in an adjusted prevalence of homelessness of 3.3% which matches current VA estimates. Further refinements are underway to improve the performance. We demonstrate an effective and rapid lifecycle of using an off-the-shelf NLP tool for screening targets of interest from medical records.

Semantic MEDLINE for discovery browsing: using semantic predications and the literature-based discovery paradigm to elucidate a mechanism for the obesity paradox.

Abstract: Applying the principles of literature-based discovery (LBD), we elucidate the paradox that obesity is beneficial in critical care despite contributing to disease generally. Our approach enhances a previous extension to LBD, called "discovery browsing," and is implemented using Semantic MEDLINE, which summarizes the results of a PubMed search into an interactive graph of semantic predications. The methodology allows a user to construct argumentation underpinning an answer to a biomedical question by engaging the user in an iterative process between system output and user knowledge. Components of the Semantic MEDLINE output graph identified as "interesting" by the user both contribute to subsequent searches and are constructed into a logical chain of relationships constituting an explanatory network in answer to the initial question. Based on this methodology we suggest that phthalates leached from plastic in critical care interventions activate PPAR gamma, which is anti-inflammatory and abundant in obese patients.

Patient moderator interaction in online health communities.

Abstract: An increasing number of people visit online health communities to share experiences and seek health information. Although studies have enumerated reasons for patients' visits to online communities for health information from peers, we know little about how patients gain health information from the moderators in these communities. We qualitatively analyze 480 patient and moderator posts from six communities to understand how moderators fulfill patients' information needs. Our findings show that patients use the community as an integral part of their health management practices. Based on our results, we suggest enhancements to moderated online health communities for their unique role to support patient care.

Using animation as an information tool to advance health research literacy among minority participants.

Abstract: Lack of adequate consumer health information about clinical research contributes to health disparities among low health literate minority multicultural populations and requires appropriate methods for making information accessible. Enhancing understanding of health research can enable such minority multicultural consumers to make informed, active decisions about their own health and research participation. This qualitative study examines the effectiveness and acceptability of an animated video to enhance what we call health research literacy among minority multicultural populations. A team analyzed the transcripts of 58 focus groups of African Americans, Latinos, Native Hawaiians, and Filipinos in Los Angeles/Hawaii. Participants were accepting of animation and the video’s cultural appropriateness. Communicating information about health research via animation improved participants’ ability to identify personal information-gaps, engage in meaningful community-level dialogue, and ask questions about health research.

Evaluation of intravenous medication errors with smart infusion pumps in an academic medical center.

Abstract: While some published research indicates a fairly high frequency of Intravenous (IV) medication errors associated with the use of smart infusion pumps, the generalizability of these results are uncertain. Additionally, the lack of a standardized methodology for measuring these errors is an issue. In this study we iteratively developed a web-based data collection tool to capture IV medication errors using a participatory design approach with interdisciplinary experts. Using the developed tool, a prevalence study was then conducted in an academic medical center. The results showed that the tool was easy to use and effectively captured all IV medication errors. Through the prevalence study, violation errors of hospital policy were found that could potentially place patients at risk, but no critical errors known to contribute to patient harm were noted.

Identifying synonymy between SNOMED clinical terms of varying length using distributional analysis of electronic health records.

Abstract: Medical terminologies and ontologies are important tools for natural language processing of health record narratives. To account for the variability of language use, synonyms need to be stored in a semantic resource as textual instantiations of a concept. Developing such resources manually is, however, prohibitively expensive and likely to result in low coverage. To facilitate and expedite the process of lexical resource development, distributional analysis of large corpora provides a powerful data-driven means of (semi-)automatically identifying semantic relations, including synonymy, between terms. In this paper, we demonstrate how distributional analysis of a large corpus of electronic health records - the MIMIC-II database - can be employed to extract synonyms of SNOMED CT preferred terms. A distinctive feature of our method is its ability to identify synonymous relations between terms of varying length.

Comparison and combination of several MeSH indexing approaches.

Abstract: MeSH indexing of MEDLINE is becoming a more difficult task for the group of highly qualified indexing staff at the US National Library of Medicine, due to the large yearly growth of MEDLINE and the increasing size of MeSH. Since 2002, this task has been assisted by the Medical Text Indexer or MTI program. We extend previous machine learning analysis by adding a more diverse set of MeSH headings targeting examples where MTI has been shown to perform poorly. Machine learning algorithms exceed MTI's performance on MeSH headings that are used very frequently and headings for which the indexing frequency is very low. We find that when we combine the MTI suggestions and the prediction of the learning algorithms, the performance improves compared to any single method for most of the evaluated MeSH headings.

Exploring the relationship between drug side-effects and therapeutic indications.

Abstract: Therapeutic indications and drug side-effects are both measureable human behavioral or physiological changes in response to the treatment. In modern drug development, both inferring potential therapeutic indications and identifying clinically important drug side-effects are challenging tasks. Previous studies have utilized either chemical structures or protein targets to predict indications and side-effects. In this study, we compared indication prediction using side-effect information and side-effect prediction using indication information against models using only chemical structures and protein targets. Experimental results based on 10-fold cross-validation, show that drug side-effects and therapeutic indications are the most predictive features for each other. In addition, we extracted 6,706 statistically highly correlated disease-side-effect pairs from all known drug-disease and drug-side-effect relationships. Many relationship pairs provide explicit repositioning hypotheses (e.g., drugs causing postural hypotension are potential candidates for hypertension) and clear adverse-reaction watch lists (e.g., drugs for heart failure possibly cause impotence). All data sets and highly correlated disease-side-effect relationships are available at http://astro.temple.edu/~tua87106/druganalysis.html.

Method for the development of data visualizations for community members with varying levels of health literacy.

Abstract: Many Americans are challenged by the tasks of understanding and acting upon their own health data. Low levels of health literacy contribute to poor comprehension and undermine the confidence necessary for health self-management. Visualizations are useful for minimizing comprehension gaps when communicating complex quantitative information. The process of developing visualizations that accommodate the needs of individuals with varying levels of health literacy remains undefined. In this paper we provide detailed descriptions of a) an iterative methodological approach to the development of visualizations, b) the resulting types of visualizations and examples thereof, and c) the types of data the visualizations will be used to convey. We briefly describe subsequent phases in which the visualizations will be tested and refined. Web deployment of the final visualizations will support the ethical obligation to return the data to the research participants and community that contributed it.

Teleretinal screening for diabetic retinopathy in six Los Angeles urban safety-net clinics: final study results.

Abstract: In a previous paper, we presented initial findings from a study on the feasibility and challenges of implementing teleretinal screening for diabetic retinopathy in an urban safety net setting facing eyecare specialist shortages. This paper presents some final results from that study, which involved six South Los Angeles safety net clinics. A total of 2,732 unique patients were screened for diabetic retinopathy by three ophthalmologist readers, with 1035 receiving a recommendation for referral to specialty care. Referrals included 48 for proliferative diabetic retinopathy, 115 for severe non-proliferative diabetic retinopathy (NPDR), 247 for moderate NPDR, 246 for mild NPDR, 97 for clinically significant macular edema, and 282 for a non-diabetic condition, such as glaucoma. Image quality was also assessed, with ophthalmologist readers grading 4% to 13% of retinal images taken at the different clinics as being inadequate for any diagnostic interpretation.

Desiderata for healthcare integrated data repositories based on architectural comparison of three public repositories.

Abstract: Integrated data repositories (IDRs) are indispensable tools for numerous biomedical research studies. We compare three large IDRs (Informatics for Integrating Biology and the Bedside (i2b2), HMO Research Network’s Virtual Data Warehouse (VDW) and Observational Medical Outcomes Partnership (OMOP) repository) in order to identify common architectural features that enable efficient storage and organization of large amounts of clinical data. We define three high-level classes of underlying data storage models and we analyze each repository using this classification. We look at how a set of sample facts is represented in each repository and conclude with a list of desiderata for IDRs that deal with the information storage model, terminology model, data integration and value-sets management.

Survival association rule mining towards type 2 diabetes risk assessment.

Abstract: Type-2 Diabetes Mellitus is a growing epidemic that often leads to severe complications. Effective preventive measures exist and identifying patients at high risk of diabetes is a major health-care need. The use of association rule mining (ARM) is advantageous, as it was specifically developed to identify associations between risk factors in an interpretable form. Unfortunately, traditional ARM is not directly applicable to survival outcomes and it lacks the ability to compensate for confounders and to incorporate dosage effects. In this work, we propose Survival Association Rule (SAR) Mining, which addresses these shortcomings. We demonstrate on a real diabetes data set that SARs are naturally more interpretable than the traditional association rules, and predictive models built on top of these rules are very competitive relative to state of the art survival models and substantially outperform the most widely used diabetes index, the Framingham score.

Scalability of Abstraction-Network-Based Quality Assurance to Large SNOMED Hierarchies

Abstract: ion networks are compact summarizations of terminologies used to support orientation and terminology quality assurance (TQA). Area taxonomies and partial-area taxonomies are abstraction networks that have been successfully employed in support of TQA of small SNOMED CT hierarchies. However, nearly half of SNOMED CT’s concepts are in the large Procedure and Clinical Finding hierarchies. ion network derivation methodologies applied to those hierarchies resulted in taxonomies that were too large to effectively support TQA. A methodology for deriving sub-taxonomies from large taxonomies is presented, and the resultant smaller abstraction networks are shown to facilitate TQA, allowing for the scaling of our taxonomy-based TQA regimen to large hierarchies. Specifically, sub-taxonomies are derived for the Procedure hierarchy and a review for errors and inconsistencies is performed. Concepts are divided into groups within the sub-taxonomy framework, and it is shown that small groups are statistically more likely to harbor erroneous and inconsistent concepts than large groups.

Cloudwave: distributed processing of "big data" from electrophysiological recordings for epilepsy clinical research using Hadoop.

Abstract: Epilepsy is the most common serious neurological disorder affecting 50-60 million persons worldwide. Multi-modal electrophysiological data, such as electroencephalography (EEG) and electrocardiography (EKG), are central to effective patient care and clinical research in epilepsy. Electrophysiological data is an example of clinical "big data" consisting of more than 100 multi-channel signals with recordings from each patient generating 5-10GB of data. Current approaches to store and analyze signal data using standalone tools, such as Nihon Kohden neurology software, are inadequate to meet the growing volume of data and the need for supporting multi-center collaborative studies with real time and interactive access. We introduce the Cloudwave platform in this paper that features a Web-based intuitive signal analysis interface integrated with a Hadoop-based data processing module implemented on clinical data stored in a "private cloud". Cloudwave has been developed as part of the National Institute of Neurological Disorders and Strokes (NINDS) funded multi-center Prevention and Risk Identification of SUDEP Mortality (PRISM) project. The Cloudwave visualization interface provides real-time rendering of multi-modal signals with "montages" for EEG feature characterization over 2TB of patient data generated at the Case University Hospital Epilepsy Monitoring Unit. Results from performance evaluation of the Cloudwave Hadoop data processing module demonstrate one order of magnitude improvement in performance over 77GB of patient data. (Cloudwave project: http://prism.case.edu/prism/index.php/Cloudwave).

Understanding adoption of a personal health record in rural health care clinics: revealing barriers and facilitators of adoption including attributions about potential patient portal users and self-reported characteristics of early adopting users.

Abstract: Personal health records (PHRs) are important for improving patient care. An important prerequisite to realize benefits of PHR use is patient recruitment. To understand clinic barriers to adoption, we used Rogers' Diffusion of Innovations theory to frame an examination of clinic staff perceptions of a new PHR and perceptions of likely patient portal users. Clinic staff reported many relative advantages and observable benefits of the PHR but also some distinct problems. Attributions about potential patient users included demographic, computer use, and personality characteristics staff expected in likely users. Analysis of patient survey data of early adopters compared to non-users revealed discrepancies between clinic staff expectations and early adopters' self-reports. Implications for improving adoption of PHRs include ensuring compatibility with existing systems and avoiding recruitment biases.

A family-based framework for supporting quality assurance of biomedical ontologies in BioPortal.

Abstract: BioPortal contains over 300 ontologies, for which quality assurance (QA) is critical. Abstraction networks (ANs), compact summarizations of ontology structure and content, have been used in such QA efforts, typically in a "one-off" manner for a single ontology. Ontologies can be characterized-independently of knowledge-content focus-from a structural standpoint leading to the formulation of ontology families. A family is defined as a set of ontologies satisfying some overarching condition regarding their structural features. Seven such families, comprising 186 ontologies, are identified. To increase efficiency, a new family-based QA framework is introduced in which an automated, uniform AN derivation technique and accompanying semi-automated, uniform QA regimen are applicable to the ontologies of a given family. Specifically, across an entire family, the QA efforts exploit family-wide AN features in the characterization of sets of classes that are more likely to harbor errors. The approach is demonstrated on the Cancer Chemoprevention BioPortal ontology.

A natural language processing algorithm to define a venous thromboembolism phenotype

Abstract: Deep venous thrombosis and pulmonary embolism are diseases associated with significant morbidity and mortality. Known risk factors are attributed for only slight majority of venous thromboembolic disease (VTE) with the remainder of risk presumably related to unidentified genetic factors. We designed a general purpose Natural Language (NLP) algorithm to retrospectively capture both acute and historical cases of thromboembolic disease in a de-identified electronic health record. Applying the NLP algorithm to a separate evaluation set found a positive predictive value of 84.7% and sensitivity of 95.3% for an F-measure of 0.897, which was similar to the training set of 0.925. Use of the same algorithm on problem lists only in patients without VTE ICD-9s was found to be the best means of capturing historical cases with a PPV of 83%. NLP of VTE ICD-9 positive cases and non-ICD-9 positive problem lists provides an effective means for capture of both acute and historical cases of venous thromboembolic disease.

Implementation of a computerized patient handoff application.

Abstract: For hospitalized patients, handoffs between providers affect continuity of care and increase the risk of medical errors. Most commercial electronic health record (EHR) systems lack dedicated tools to support patient handoff activities. We developed a collaborative application supporting patient handoff that is fully integrated with our commercial EHR. The application creates user-customizable printed reports with automatic inclusion of a variety of EHR data, including: allergies, medications, 24-hour vital signs, recent common laboratory test results, isolation requirements, and code status. It has achieved widespread voluntary use at our institution (6,100 monthly users; 700 daily reports generated), and we have distributed the application to several other institutions using the same EHR. Though originally designed for resident physicians, today about 50% of the application users are nurses, 40% are physicians/physician assistants/nurse practitioners, and 10% are pharmacists, social workers, and other allied health providers.

Towards collaborative filtering recommender systems for tailored health communications.

Abstract: The goal of computer tailored health communications (CTHC) is to promote healthy behaviors by sending messages tailored to individual patients. Current CTHC systems collect baseline patient "profiles" and then use expert-written, rule-based systems to target messages to subsets of patients. Our main interest in this work is the study of collaborative filtering-based CTHC systems that can learn to tailor future message selections to individual patients based explicit feedback about past message selections. This paper reports the results of a study designed to collect explicit feedback (ratings) regarding four aspects of messages from 100 subjects in the smoking cessation support domain. Our results show that most users have positive opinions of most messages and that the ratings for all four aspects of the messages are highly correlated with each other. Finally, we conduct a range of rating prediction experiments comparing several different model variations. Our results show that predicting future ratings based on each user's past ratings contributes the most to predictive accuracy.

A Large-Scale Analysis of the Reasons Given for Excluding Articles that are Retrieved by Literature Search During Systematic Review

Abstract: Objective A literature search to identify relevant studies is one of the first steps in performing a systematic review (SR) in support of evidence-based medicine. To maximize efficiency, the search must find practically all relevant studies and retrieve few that are irrelevant; however, this level of precision is seldom attained. Therefore, many articles must be manually examined for relevance. To better understand the limitations of current search tools as applied to SR, we characterized the most common reasons that papers retrieved by SR searches were excluded from the review. Methods The textual reasons given for retrieved but excluded articles were extracted from 6,743 SRs performed by 54 Cochrane Collaboration review groups. The frequencies of different exclusion reasons were analyzed, and we developed a taxonomy summarizing these reasons. Results Almost 65% of articles were excluded because the means of comparison were inappropriate. Of these, about 72% were due to the randomized controlled trial (RCT) design being required but not employed by the excluded study. Mismatching interventions and outcomes and incorrect population characteristics were also common reasons for exclusion. Conclusions Currently available search methods do not adequately address the most common exclusion reasons for systematic review, even those based primarily on study design.

Twinlist: novel user interface designs for medication reconciliation.

Abstract: Medication reconciliation is an important and complex task for which careful user interface design has the potential to help reduce errors and improve quality of care. In this paper we focus on the hospital discharge scenario and first describe a novel interface called Twinlist. Twinlist illustrates the novel use of spatial layout combined with multi-step animation, to help medical providers see what is different and what is similar between the lists (e.g., intake list and hospital list), and rapidly choose the drugs they want to include in the reconciled list. We then describe a series of variant designs and discuss their comparative advantages and disadvantages. Finally we report on a pilot study that suggests that animation might help users learn new spatial layouts such as the one used in Twinlist.

Inter-observer reliability assessments in time motion studies: the foundation for meaningful clinical workflow analysis.

Abstract: Understanding clinical workflow is critical for researchers and healthcare decision makers. Current workflow studies tend to oversimplify and underrepresent the complexity of clinical workflow. Continuous observation time motion studies (TMS) could enhance clinical workflow studies by providing rich quantitative data required for in-depth workflow analyses. However, methodological inconsistencies have been reported in continuous observation TMS, potentially reducing the validity of TMS' data and limiting their contribution to the general state of knowledge. We believe that a cornerstone in standardizing TMS is to ensure the reliability of the human observers. In this manuscript we review the approaches for inter-observer reliability assessment (IORA) in a representative sample of TMS focusing on clinical workflow. We found that IORA is an uncommon practice, inconsistently reported, and often uses methods that provide partial and overestimated measures of agreement. Since a comprehensive approach to IORA is yet to be proposed and validated, we provide initial recommendations for IORA reporting in continuous observation TMS.

The current capabilities of health information technology to support care transitions

Abstract: To determine whether HIT currently supports care transitions we interviewed clinicians from several healthcare settings. We learned about HIT tools to help nurses facilitate transitions, but discovered that there are few tools to promote high quality, safe transitions of care. We also found that HIT is rarely employed for patient-centered care coordination mechanisms. In conclusion, HIT tools are typically used within one healthcare setting to prepare for a transition, rather than across healthcare settings.

Time-motion analysis of clinical nursing documentation during implementation of an electronic operating room management system for ophthalmic surgery.

Abstract: Efficiency and quality of documentation are critical in surgical settings because operating rooms are a major source of revenue, and because adverse events may have enormous consequences. Electronic health records (EHRs) have potential to impact surgical volume, quality, and documentation time. Ophthalmology is an ideal domain to examine these issues because procedures are high-throughput and demand efficient documentation. This time-motion study examines nursing documentation during implementation of an EHR operating room management system in an ophthalmology department. Key findings are: (1) EHR nursing documentation time was significantly worse during early implementation, but improved to a level near but slightly worse than paper baseline, (2) Mean documentation time varied significantly among nurses during early implementation, and (3) There was no decrease in operating room turnover time or surgical volume after implementation. These findings have important implications for ambulatory surgery departments planning EHR implementation, and for research in system design.

Supporting Shared Decision Making within the MobiGuide Project

Abstract: This paper describes our approach for fostering and facilitating communication among patients and caregivers in the context of shared decision making, i.e., when decisions must be taken not only on the basis of scientific evidence but also of the patient’s preferences and context. This happens because clinical practice guidelines cannot provide recommendations for every possible situation, and cannot foresee every change in a patient’s context, which might imply the deviation from a previously acknowledged recommendation. Within the EU-funded project MobiGuide (www.mobiguide-project.eu), supporting remote patient management, we propose decision theory as a methodological framework for a tool that, during face to face encounters, is used to tailor pre-defined, generic decision models to the individual patient, by involving the patient himself in the customization of the model parameters. Although this approach is not appropriate for all patients, it leads, in well-chosen cases, to a more informed choice, with potentially better treatment compliance.

Priority Queuing Models for Hospital Intensive Care Units and Impacts to Severe Case Patients

Abstract: This paper examines several different queuing models for intensive care units (ICU) and the effects on wait times, utilization, return rates, mortalities, and number of patients served. Five separate intensive care units at an urban hospital are analyzed and distributions are fitted for arrivals and service durations. A system-based simulation model is built to capture all possible cases of patient flow after ICU admission. These include mortalities and returns before and after hospital exits. Patients are grouped into 9 different classes that are categorized by severity and length of stay (LOS). Each queuing model varies by the policies that are permitted and by the order the patients are admitted. The first set of models does not prioritize patients, but examines the advantages of smoothing the operating schedule for elective surgeries. The second set analyzes the differences between prioritizing admissions by expected LOS or patient severity. The last set permits early ICU discharges and conservative and aggressive bumping policies are contrasted. It was found that prioritizing patients by severity considerably reduced delays for critical cases, but also increased the average waiting time for all patients. Aggressive bumping significantly raised the return and mortality rates, but more conservative methods balance quality and efficiency with lowered wait times without serious consequences.