Combining machine learning and optimization for the operational patient-bed assignment problem.

Assigning inpatients to hospital beds impacts patient satisfaction and the workload of nurses and doctors. The assignment is subject to unknown inpatient arrivals, in particular for emergency patients. Hospitals, therefore, need to deal with uncertainty on actual bed requirements and potential shortage situations as bed capacities are limited. This paper develops a model and solution approach for solving the patient bed-assignment problem that is based on a machine learning (ML) approach to forecasting emergency patients. First, it contributes by improving the anticipation of emergency patients using ML approaches, incorporating weather data, time and dates, important local and regional events, as well as current and historical occupancy levels. Drawing on real-life data from a large case hospital, we were able to improve forecasting accuracy for emergency inpatient arrivals. We achieved up to 17% better root mean square error (RMSE) when using ML methods compared to a baseline approach relying on averages for historical arrival rates. We further show that the ML methods outperform time series forecasts. Second, we develop a new hyper-heuristic for solving real-life problem instances based on the pilot method and a specialized greedy look-ahead (GLA) heuristic. When applying the hyper-heuristic in test sets we were able to increase the objective function by up to 5.3% in comparison to the benchmark approach in [40]. A benchmark with a Genetic Algorithm shows also the superiority of the hyper-heuristic. Third, the combination of ML for emergency patient admission forecasting with advanced optimization through the hyper-heuristic allowed us to obtain an improvement of up to 3.3% on a real-life problem.

[Initial preclinical assessment on-site]. / Präklinische Ersteinschätzung am Einsatzort.

Emergency personnel assess their patients as an essential part of their daily work in emergency settings. The clinical assessment can help differentiate between immediately life-threatening conditions and milder diseases in patients. This assessment is the basis for an adequate preclinical treatment and for a rational referral to the hospital providing further care. Carried out in a thoughtful manner it allows reasonable allocation of resources for inpatient care.Well-founded training, clinical experience, scores, and tools in the form of acronyms for assessing the patient lead to successful assessments according to quality standards.The preclinical initial assessment is crucial for ensuring appropriate care for patients on site with life-threatening conditions as well as those with minor problems. Prioritization of a treatment depends on the severity of the condition or injury.

Factors Associated with Pre-Hospital Delay and Intravenous Thrombolysis in China.

BACKGROUND: Pre-hospital delay was a critical factor affecting stroke patients receiving intravenous thrombolytic therapy. The aim of this study was to explore the factors associated with pre-hospital delay and thrombolysis in China. METHODS: Patient data were obtained from emergency department (ED), and the factors of patient pre-hospital delay were recorded through a well-designed form. RESULTS: A total of 630 patients were eventually included in the study. 317 patients were admitted to the ED during the thrombolysis time window, and only 105 patients received intravenous thrombolytic therapy. In the univariate analysis, transportation (OR: 0.15; 95% CI: 0.44 - 0.518; p = 0.001), atrial fibrillation (OR: 0.555; 95% CI: 0.372-0.828; p = 0.004) and response of symptoms (OR: 0.002; 95% CI: 0.000-0.013; p = 0.000) were associated with early arrival. Speech disturbances (OR: 2.095; 95% CI: 1.294-3.391; p = 0.002), smoking (OR: 2.563; 95% CI: 1.527-4.304; p = 0.000), alcohol consumption (OR: 2.155; 95% CI: 1.159-4.005; p = 0.014) and referral presentation (OR: 2.837; 95% CI: 1.584-5.082; p = 0.000) were associated with thrombolysis. In the logistic regression analysis, direct visiting to the hospital after onset and rushing to emergency after onset were independent predictor of early arrival of AIS and intravenous thrombolytic. CONCLUSIONS: The pre-hospital delay of acute ischemic stroke in China was still serious. Strengthening the ability to identify stroke-related symptoms and establishing a mutual referral medical support service model between lower and upper hospitals may effectively shorten the pre-hospital delay of stroke patients.

Advanced nurse practitioner scheduled return clinic: a clinical audit of a quality initiative.

Emergency care settings in Ireland have struggled with a high volume of service users in recent years. This nationwide crisis led to the establishment of the National Emergency Medicine Programme Strategy in 2012, which identified two key performance indicators for efficiency in emergency care: the patient experience time, which should not exceed six hours from the time of registration to the time of discharge; and patients who do not wait for treatment (DNW) should make up less than 5% of those attending emergency care services. This article explores a quality initiative to improve DNW rates using scheduled return clinics, implemented by a group of advanced nurse practitioners in an emergency department in a Dublin hospital. It reviews the literature on scheduled return clinics and discusses the rationale for the initiative, its implementation, barriers to its introduction and an audit of its effectiveness.

Predictive / Reactive Planning and Scheduling of a Surgical Suite with Emergency Patient Arrival.

This paper surveys the problem of predictive / reactive scheduling of an integrated operating theatre with two types of demand for surgery: 1) elective or known demand; 2) emergency or uncertain demand. The stochastic arrival of emergency patients with uncertain surgery time enforces the scheduler to react to disruption and modify scheduling plan of elective patients. We focus on this predictive / reactive scheduling problem which has not been investigated in such way before. As in hospitals, at the time of occurrence a disruption in a surgical suite, the scheduler has not enough time to make the best decision; we propose a new approach based on two-stage stochastic programming model with recourse which determines the best recourse strategy in advance of any disruption occurrence. Using the proposed approach, the primary schedule is generated in such a way that it can absorb disruption with minimum effect on planned elective surgeries. For the first time in operating theatre planning, two new significant sets of performance measures comprising "robustness" and "stability" measures are considered in generation of primary schedule which will be shown to be of great importance in efficiency of surgical suite planning. Computational experiments performed on sets of generated problem based on the data obtained from a non-profit hospital. In order to demonstrate efficiency of the proposed method, computational results of the proposed approach are compared with classic approach.

[Impact of the COVID-19 pandemic on the care of major trauma patients: analysis from the TraumaRegister DGU®]. / Auswirkung der COVID-19-Pandemie auf die Versorgung von Schwerverletzten: Analyse aus dem TraumaRegister DGU®.

BACKGROUND: The treatment of major trauma patients requires intensive care capacity, which is a critical resource particularly during the coronavirus disease 2019 (COVID-19) pandemic. Therefore, the aim of this study was to analyze the impact on major trauma care considering the intensive care treatment of COVID-19 positive patients. METHODS: Demographic, prehospital, and intensive care treatment data from the TraumaRegister DGU® of the German Trauma Society (DGU) in 2019 and 2020 were analyzed. Only major trauma patients from the state of Bavaria were included. Inpatient treatment data of COVID-19 patients in Bavaria in 2020 were obtained using IVENA eHealth. RESULTS: In total, 8307 major trauma patients were treated in the state of Bavaria in the time period investigated. The number of patients in 2020 (n = 4032) compared to 2019 (n = 4275) was not significantly decreased (p = 0.4). Regarding COVID-19 case numbers, maximum values were reached in the months of April and December with more than 800 intensive care unit (ICU) patients per day. In the critical period (> 100 patients with COVID-19 on ICU), a prolonged rescue time was evident (64.8 ± 32.5 vs. 67.4 ± 30.6 min; p = 0.003). The length of stay and ICU treatment of major trauma patients were not negatively affected by the COVID-19 pandemic. CONCLUSION: The intensive medical care of major trauma patients could be ensured during the high-incidence phases of the COVID-19 pandemic. The prolonged prehospital rescue times show possible optimization potential of the horizontal integration of prehospital and hospital.

[The potential role of improvisation training to optimize communication in emergency care]. / Az improvizációs tréningek lehetséges szerepe a kommunikáció optimalizálására a sürgosségi ellátásban.

INTRODUCTION: One of the most common challenges in acute care is the time- and space-limited communication with patients, relatives and colleagues. There is ample evidence, however, that the quality of care, patient and staff satisfaction can be improved, measured and researched using simple communication tools (e.g., training). OBJECTIVE: This improvement was what we focused on when carrying out voluntary participation surveys with the staff of the Department of Emergency Medicine of the Clinical Centre of the University of Pécs. METHOD: With the help of a trained psychologist-actor and a senior specialist in medical communication, we investigated the potential impact of applied improvisation on medical communication by testing the participants in various situations simulating communication challenges after having completed an improv-based communication training full of exercises, games and tasks. After warm-up games taken from improv, the participants completed pre-defined tasks and finished every session with discussion and self-reflective feedback. Questionnaire (Interpersonal Confidence Questionnaire - ICQ) was used to check the potentially positive impact of improvisation on emergency communication. RESULTS: Our studies confirmed that the applied elements of medical improvisation, developing communication skills through play not only make participants more assertive and empathic, but also - after preparation - lead to a smoother and more effective exchange of information. Positive feedback from participants in the training sessions also confirms this. DISCUSSION: Our aim is to develop an improvisation-based communication training focused specifically on acute care providers, which, based on our initial experience, could optimize communication with patients, relatives and also between professionals. CONCLUSION: Application of improvisational techniques in this segment of acute care studied by us might open new perspectives to improve communication. Orv Hetil. 2023; 164(19): 739-746.

Comparison of Diagnostic and Triage Accuracy of Ada Health and WebMD Symptom Checkers, ChatGPT, and Physicians for Patients in an Emergency Department: Clinical Data Analysis Study.

BACKGROUND: Diagnosis is a core component of effective health care, but misdiagnosis is common and can put patients at risk. Diagnostic decision support systems can play a role in improving diagnosis by physicians and other health care workers. Symptom checkers (SCs) have been designed to improve diagnosis and triage (ie, which level of care to seek) by patients. OBJECTIVE: The aim of this study was to evaluate the performance of the new large language model ChatGPT (versions 3.5 and 4.0), the widely used WebMD SC, and an SC developed by Ada Health in the diagnosis and triage of patients with urgent or emergent clinical problems compared with the final emergency department (ED) diagnoses and physician reviews. METHODS: We used previously collected, deidentified, self-report data from 40 patients presenting to an ED for care who used the Ada SC to record their symptoms prior to seeing the ED physician. Deidentified data were entered into ChatGPT versions 3.5 and 4.0 and WebMD by a research assistant blinded to diagnoses and triage. Diagnoses from all 4 systems were compared with the previously abstracted final diagnoses in the ED as well as with diagnoses and triage recommendations from three independent board-certified ED physicians who had blindly reviewed the self-report clinical data from Ada. Diagnostic accuracy was calculated as the proportion of the diagnoses from ChatGPT, Ada SC, WebMD SC, and the independent physicians that matched at least one ED diagnosis (stratified as top 1 or top 3). Triage accuracy was calculated as the number of recommendations from ChatGPT, WebMD, or Ada that agreed with at least 2 of the independent physicians or were rated "unsafe" or "too cautious." RESULTS: Overall, 30 and 37 cases had sufficient data for diagnostic and triage analysis, respectively. The rate of top-1 diagnosis matches for Ada, ChatGPT 3.5, ChatGPT 4.0, and WebMD was 9 (30%), 12 (40%), 10 (33%), and 12 (40%), respectively, with a mean rate of 47% for the physicians. The rate of top-3 diagnostic matches for Ada, ChatGPT 3.5, ChatGPT 4.0, and WebMD was 19 (63%), 19 (63%), 15 (50%), and 17 (57%), respectively, with a mean rate of 69% for physicians. The distribution of triage results for Ada was 62% (n=23) agree, 14% unsafe (n=5), and 24% (n=9) too cautious; that for ChatGPT 3.5 was 59% (n=22) agree, 41% (n=15) unsafe, and 0% (n=0) too cautious; that for ChatGPT 4.0 was 76% (n=28) agree, 22% (n=8) unsafe, and 3% (n=1) too cautious; and that for WebMD was 70% (n=26) agree, 19% (n=7) unsafe, and 11% (n=4) too cautious. The unsafe triage rate for ChatGPT 3.5 (41%) was significantly higher (P=.009) than that of Ada (14%). CONCLUSIONS: ChatGPT 3.5 had high diagnostic accuracy but a high unsafe triage rate. ChatGPT 4.0 had the poorest diagnostic accuracy, but a lower unsafe triage rate and the highest triage agreement with the physicians. The Ada and WebMD SCs performed better overall than ChatGPT. Unsupervised patient use of ChatGPT for diagnosis and triage is not recommended without improvements to triage accuracy and extensive clinical evaluation.

Emergency patient flow forecasting in the radiology department.

The accurate forecast of radiology emergency patient flow is of great importance to optimize appointment scheduling decisions. This study used a multi-model approach to forecast daily radiology emergency patient flow with consideration of different patient sources. We constructed six linear and nonlinear models by considering the lag effects and corresponding time factors. The autoregressive integrated moving average and least absolute shrinkage and selection operator (Lasso) were selected from the category of linear models, whereas linear-and-radial support vector regression models, random forests and adaptive boosting were chosen from the category of nonlinear models. The models were applied to 4-year daily emergency visits data in the radiology department of West China Hospital in Chengdu, China. The mean absolute percentage error of six models ranged from 8.56 to 9.36 percent for emergency department patients, whereas it varied from 10.90 to 14.39 percent for ward patients. The best-performing model for total radiology visits was Lasso, which yielded a mean absolute percentage error of 7.06 percent. The arrival patterns of emergency department and total radiology emergency patient flows could be modeled by linear processes. By contrast, the nonlinear model performed best for ward patient flow. These findings will benefit hospital managers in managing efficient patient flow, thus improving service quality and increasing patient satisfaction.

Non-coronary predictors of elevated high-sensitive cardiac troponin T (hs-cTnT) levels in an unselected emergency patient cohort.

BACKGROUND: Aim of this study was to evaluate the predictors of hs-cTnT in a non-ACS patient cohort admitted to the emergency department. HYPOTHESIS: Atrial fibrillation and hypertension may not always be sufficient for elevation for hs-cTnT. METHODS: We performed a retrospective, single center study encompassing in total 1003 patients. Individuals were retrospectively divided in ACS- and non-ACS patients by two independent investigators reviewing the medical records. In order to identify predictors of hs-cTnT elevation hazard ratios were calculated for age, gender, vital signs, cardiovascular risk factors, LVEF, serum levels of CRP, hemoglobin, and creatinine. Elevation of hs-cTnT was defined by exceeding 14 ng/L (upper reference limit [URL]). RESULTS: About 987 patients were included while 25 patients were excluded because of missing data. 307 patients (31.4%) met the current guideline requirements of diagnosing an ACS, whereas 671 patients (68.6%) were hospitalized with excluded ACS. In the multivariate analysis age, anemia, CRP, creatinine, and reduced systolic left ventricular ejection fraction were independent predictors of elevated troponin T levels in the non-ACS group. However, hypertensive systolic blood pressure, atrial fibrillation and tachycardia were not predictive for Troponin T elevation in non-ACS patients in this multivariate analysis. CONCLUSIONS: In an unselected, non-ACS patient cohort age, chronic renal failure, inflammatory state, and reduced left ventricular systolic function were associated with hs-cTnT levels above the upper reference limit. Rather, often supposed predictors as atrial fibrillation, hypertension, and tachycardia cannot sufficiently explain increased hs-cTnT in our study. Hence, further studies are needed to assess whether isolated hypertension, tachycardia, or atrial fibrillation sufficiently explain elevated hs-cTnT.

Scheduling terminology for oral and maxillofacial surgery. Are we speaking a universal language?

Use of a universal vocabulary to assist with the scheduling of operations has been shown to considerably reduce delays and improve the use of theatre resources. Within the UK the National Confidential Enquiry into Patient Outcome and Death (NCEPOD) has established a classification to assist with the triage of both emergency and non-emergency operating lists. We completed a survey to assess the uptake and understanding of this classification when scheduling maxillofacial operations. From a list of eight scheduling terms, respondents had to choose one each for 20 different clinical situations (that represented equally) immediate, urgent, expedited, and elective operations as defined by them. A total of 50 surveys were collated. Only 65% of answers selected represented NCPOD terms. 25% of answers represented a term higher and 18% a term lower, on the scale of intervention for the same category of situation. Current NCEPOD terms do not seem to be used universally and are poorly understood. Considerable variation in terminology exists when scheduling maxillofacial operations.

[Medications in Emergency Medicine - an Update]. / Notfallmedikamente - ein Update.

Every doctor, whether responsible for a hospital or a clinic, should have a solid foundation in the care of the emergent patient. Nearly all specialties require some medications to be administered by in section - a reanimation or an anaphylactic shock must be correctly treated and promptly, before further help arrives. Medications are an essential onerstone in the care of emerge nices. Varying medications are in demand based on specialty, ED structure, and location in which care is provided. This must be synchronised with the eventual likely emergencies, as well as with personal knowledge and experience of the ED staff.

A Clinical Study on the Emergency Patients of Oral and Maxillofacial Surgery Visiting Sang-Gye Paik Hospital Emergency Room

Development and Experimental Application of an Emergency Patient Information Delivery System Using a PDA / 대한의료정보학회지

This study developed, and applied, a portable emergency medical information system, enabling patient-related information to be efficiently shared with the hospital information system, via a PDA, while an emergency patient was being taken to the emergency room. The system consisted of an emergency patient`s server for monitoring the condition of the emergency patients registered in an emergency room, in real time, and a PDA terminal that delivers patient and emergency ac tivity information to a se rver through a wireless connection. Within the emergency room of G hospital a DB server was in charge of the stored information to de liver information the patients' conditions, emergency treatments, and activities, with 119 emergency medical system personnel being responsible for the information storage space, via a PDA. In addition, the member of personnel in charge of an emergency room can check the registrations of the 119 EMS personnel through a user's application, that enablings real-time checks of the fir st-aid patients being registerted in the information storage space. In conclusion, the development and experimental application of the emergency patient information delivery system demonstrated that a PDA can be used in an emergency medical environment. Modification to the interface, for a convenient input into a PDA, and an increase in its usability, through the training and continuous studies of the users, will help to make qualitative improvements to this emergency medical service.