Predicting Intensive Care Unit Admission Using Machine and Deep Learning: COVID-19 Case Study

The COVID-19 pandemic has affected the entire world by causing widespread panic and disrupting normal life. Since the outbreak began in December 2019, the virus has killed thousands of people and infected millions more. Hospitals are struggling to keep up with large patient flows. In some situations, hospitals are lacking enough beds and ventilators to accommodate all of their patients or are running low on supplies such as masks and gloves. Predicting intensive care unit (ICU) admission of patients with COVID-19 could help clinicians better allocate scarce ICU resources. In this study, many machine and deep learning algorithms are tested over predicting ICU admission of patients with COVID-19. Most of the algorithms we studied are extremely accurate toward this goal. With the convolutional neural network (CNN), we reach the highest results on our metrics (90.09% accuracy and 93.08% ROC-AUC), which demonstrates the usability of these learning models to identify patients who are likely to require ICU admission and assist hospitals in optimizing their resource management and allocation during the COVID-19 pandemic or others. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Evaluating a Covid-19 Vaccine Centre in the UK Using a DES Model

Efficient management of a Covid-19 vaccine centre (VC) is necessary for proper-functioning of a mass vaccination programme. This study reports on an evaluation of the operational performance of a VC. There are two key considerations: the VC capacity (patients per hour) and the patient flow-time (total time patients spent in the centre). In this paper, Witness Horizon a simulation model tool that can be used to enhance the effectiveness of vaccination facilities is introduced. The model is developed using discrete event simulation. The model utilises animation whilst dynamically displaying key performance indicators. The uniqueness of this approach is the ability to simulate and analyse VC scenarios stochastically by varying hourly arrivals, walk-ins to drive-in ratios, staffing levels, registration, immunization, and observation capacities. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Measuring the Impact of COVID-19 on Hospital Care Pathways

Care pathways in hospitals around the world reported significant disruption during the recent COVID-19 pandemic but measuring the actual impact is more problematic. Process mining can be useful for hospital management to measure the conformance of real-life care to what might be considered normal operations. In this study, we aim to demonstrate that process mining can be used to investigate process changes associated with complex disruptive events. We studied perturbations to accident and emergency (A &E) and maternity pathways in a UK public hospital during the COVID-19 pandemic. Co-incidentally the hospital had implemented a Command Centre approach for patient-flow management affording an opportunity to study both the planned improvement and the disruption due to the pandemic. Our study proposes and demonstrates a method for measuring and investigating the impact of such planned and unplanned disruptions affecting hospital care pathways. We found that during the pandemic, both A &E and maternity pathways had measurable reductions in the mean length of stay and a measurable drop in the percentage of pathways conforming to normative models. There were no distinctive patterns of monthly mean values of length of stay nor conformance throughout the phases of the installation of the hospital's new Command Centre approach. Due to a deficit in the available A &E data, the findings for A &E pathways could not be interpreted. © 2023, The Author(s).

Simulation Model of a Multi-Hospital Critical Care Network

We develop a discrete event simulation model for a network of eight major intensive care units (ICUs) in British Columbia, Canada. The model also contains high acuity units (HAUs) that provide critical care to patients that cannot be cared for in a general medical ward, but do not require the full spectrum of care available in an ICU. We model patient flow within the ICU and HAU for each of the hospitals, as well as patient transfers to address ICU capacity. Included in the model is early discharge from ICU to HAU, sometimes called 'bumping', when the ICU is full, as well as ICU overflow beds. The simulation model, which is calibrated using the British Columbia Critical Care Database, will be used to support planning for critical care capacity under endemic and seasonal COVID-19. © 2022 IEEE.

Effects of process changes on emergency department crowding in a changing world: an interrupted time-series analysis.

BACKGROUND: During a 6-year period, several process changes were introduced at the emergency department (ED) to decrease crowding, such as the implementation of a general practitioner cooperative (GPC) and additional medical staff during peak hours. In this study, we assessed the effects of these process changes on three crowding measures: patients' length of stay (LOS), the modified National ED OverCrowding Score (mNEDOCS), and exit block while taking into account changing external circumstances, such as the COVID-19 pandemic and centralization of acute care. METHODS: We determined time points of the various interventions and external circumstances and built an interrupted time-series (ITS) model per outcome measure. We analyzed changes in level and trend before and after the selected time points using ARIMA modeling, to account for autocorrelation in the outcome measures. RESULTS: Longer patients' ED LOS was associated with more inpatient admissions and more urgent patients. The mNEDOCS decreased with the integration of the GPC and the expansion of the ED to 34 beds and increased with the closure of a neighboring ED and ICU. More exit blocks occurred when more patients with shortness of breath and more patients > 70 years of age presented to the ED. During the severe influenza wave of 2018-2019, patients' ED LOS and the number of exit blocks increased. CONCLUSIONS: In the ongoing battle against ED crowding, it is pivotal to understand the effect of interventions, corrected for changing circumstances and patient and visit characteristics. In our ED, interventions which were associated with decreased crowding measures included the expansion of the ED with more beds and the integration of the GPC on the ED.

Impact of the Covid-19 pandemic on dental practices in Denmark.

OBJECTIVE: To investigate the impact of the Covid-19 pandemic on the patient flow and economy as experienced by dental practices in Denmark. MATERIAL AND METHODS: A survey regarding experience of patient flow, economical turnover, financial strain and willingness to pay for large treatments during the first year of the Covid-19 pandemic (March 2020 to March 2021), along with information on the characteristics of the practice (specialist practice, ownership, practice operation and size) was distributed to all dental practices in Denmark in March 2021. RESULTS: Of the 1728 practices, 581 (33.6%) answered the survey. A decline in patient flow and a decline in economical turnover were reported by 79% and 84.4% of the practices, respectively. Financial strain was reported by 15.8% and an increased willingness to pay for large treatments was reported by 32.1%. A large decline in turnover and financial strain were associated with non-specialized practices, practices with a single owner and small practices. Logistic regressions showed that practices not receiving referrals had an odds ratio of 2.34 (CI: 1.32-4.14) for having a large decline in economic turnover compared with practices receiving referrals and that small practices had an odds ratio of 1.92 (CI: 1.16-3.19) for reporting financial strain compared with large practices. CONCLUSIONS: Reportedly, the Covid-19 pandemic resulted in a decline in both patient flow and economical turnover in Danish dental practices. Large and more specialized practices seem to have managed the economic crisis better.

The Patient Flow Effect of Pandemic Policies: A Hybrid Simulation Study in a Norwegian Emergency Department.

The COVID-19 pandemic required several interventions within emergency departments, complicating the patient flow. This study explores the effect of intervention policies on patient flow in emergency departments under pandemic conditions. The patient flow interventions under evaluation here are the addition of extra treatment rooms and the addition of a waiting zone. A predeveloped hybrid simulation model was used to conduct five scenarios: (1) pre-pandemic patient flow, (2) patient flow with a 20% contamination rate, (3) adding extra treatment rooms to patient flow, (4) adding a waiting zone to the patient flow, (5) adding extra treatment rooms and a waiting zone to the patient flow. Experiments were examined based on multiple patient flow metrics incorporated into the model. Running the scenarios showed that introducing the extra treatment rooms improved all the patient flow parameters. Adding the waiting zone further improved only the contaminated patient flow parameters. Still, the benefit of achieving this must be weighed against the disadvantage for ordinary patients. Introducing the waiting zone in addition to the extra treatment room has one positive effect, decreasing time that the treatment rooms are blocked for contaminated patients entering the treatment room.

"Toy" Paediatric Critical Care Unit (Pccu): Building a Computer Simulation to Improve Patient Flow in a Scottish Pccu

BACKGROUND AND AIM: Paediatric Critical Care Units (PCCU) in the UK are experiencing a bed crisis due to increasing demand for PCCU care, more complex patient characteristics, and significant staffing issues exacerbated by the global COVID-19 pandemic. No prior study has attempted to use advanced data science methodologies to improve patient flow and capacities in PCCU. This innovative project aims to develop a novel data-driven computer simulation to examine the feasibility of using data science to understand and improve patient flow through a single PCCU in Scotland. METHOD(S): A PCCU computer simulation was built for the Edinburgh Sick Children's Hospital using routinely collected resource data and PCCU domain expertise. This prototype or 'toy' PCCU consists of a hybrid Agent Based (AB) / Discrete Event (DE) computer simulation to examine the high-level operation of the unit (DE) and human behaviour (AB). Routinely collected bed management data is used to parameterise the simulation. RESULT(S): Our 'toy' PCCU was successfully built using our existing unit structures (PICU/HDU bed distributions and staffing model) and allows computer simulation of patient arrival patterns, resource availability and usage. Preliminary findings have identified potential PCCU bottle-neck points affecting patient flow such as under-staffing, poorly planned elective admissions and inadequate staff skill set mixture. The simulation takes around 20 minutes to run on an average desktop computer. CONCLUSION(S): 'Toy' PCCU offers a promising and novel computational simulation technique for understanding and improving patient flow through PCCU. Validation studies are required to ascertain its usefulness in improving patient flow locally in Edinburgh and in multi-centre settings.

A Comparative Machine Learning Approaches for Patient Flow Forecasting in an Emergency Department during the COVID-19

The Corona Virus Disease 2019 (COVID-19) has impacted numerous areas of the health system. In fact, it made the world work remotely during several months and created an assorted uncertainty for medical service recipients. Thus, anticipating novel everyday patient income in relation to the COVID-19 has become pivotal for clinical, political, and different authorities who handle on a daily basis, COVID-19 related planned operations. Current machine learning draws near, in an attempt to get dynamic results. This work intends to demonstrate the wayan Emergency Department (ED) is able to use machine-learning approaches during the daily patient flow forecasting for better management in an emergency department. Thus, it is essential to test five different supervised machine-learning approaches by evaluating their coefficient of determination (R2) to figure the everyday patient flow income for better management. © 2022 IEEE.

Impact of COVID-19 pandemic on orthodontic patient’s inflow in daily orthodontic practice: A cross-sectional study

Aim: To evaluate the effects of the COVID-19 pandemic and lockdown on orthodontic patients’ apprehension and inflow and to investigate the treatment-related problems encountered during the pandemic. Materials and Methods: A cross-sectional study was carried out in Saudi Arabia, and patients with active orthodontic treatment were reached via an online questionnaire. A total of 260 orthodontic patients agreed to participate in the study. The sample size calculation was performed using the Raosoft sample size calculator based on the estimation of 75% of the population need orthodontic treatment. The questionnaire included three sections: demographic data, patient fear, and troubles encountered during the lockdown. A link was sent to the participants via different social media platforms and applications. The chi-square goodness-of-fit test was used to assess differences between the variables. Pearson correlation, binomial logistic regression, and multiple logistic regression tests were used to assess the extent of the relationship between patient apprehension and safety measures of COVID-19, as well as between patient orthodontic-related problems. Results: About half of the participants (52.3%) were not afraid of COVID-19 or panicked;however, 54% of them felt depressed during the lockdown. More than 80% were not afraid of visiting the orthodontists or thinking of changing their orthodontists for safety measures and did not want to postpone their treatment. The participants felt that excellent disinfection was the most important measure of infection control followed by wearing masks, face shields, and protective clothing. Conclusion: COVID-19 and the lockdown have a noticeable impact on the patients’ apprehension and dejection. A very high percentage of patients in this study showed no hesitation to visit their orthodontists, and they did not want to stop their treatment during the pandemic. The most common treatment-related problem reported was cheek injury, followed by bracket breakage.

Application of job shop scheduling approach in green patient flow optimization using a hybrid swarm intelligence.

With the increasing demand for hospital services amidst the COVID-19 pandemic, allocation of limited public resources and management of healthcare services are of paramount importance. In the field of patient flow scheduling, previous research primarily focused on classical-based objective functions, while ignoring environmental-based objective functions. This study presents a flexible job shop scheduling problem to optimize patient flow and, thereby, minimize the total carbon footprint, as the sustainability-based objective function. Since flexible job shop scheduling is an NP-hard problem, a metaheuristic optimization algorithm, called Chaotic Salp Swarm Algorithm Enhanced with Opposition-Based Learning and Sine Cosine (CSSAOS), was developed. The proposed algorithm integrates the Salp Swarm Algorithm (SSA) with chaotic maps to update the position of followers, the sine cosine algorithm to update the leader position, and opposition-based learning for a better exploration of the search space. generating more accurate solutions. The proposed method was successfully applied in a real-world case study and demonstrated better performance than other well-known metaheuristic algorithms, including differential evolution, genetic algorithm, grasshopper optimization algorithm, SSA based on opposition-based learning, quantum evolutionary SSA, and whale optimization algorithm. In addition, it was found that the proposed method is scalable to different sizes and complexities.

A Systems Approach to Optimizing Patient Flow During the COVID-19 Pandemic

In 2020, health systems have been affected by the novel coronavirus (COVID-19) pandemic, causing an influx of COVID-19 related visits and a sharp decline in non-emergency and elective visits. To mitigate the spread of COVID-19, healthcare systems - including the University of Virginia Health System - reduced ambulatory visits and implemented various social distancing measures, resulting in a drastic change in the patient admittance process. The focus of this work is to accurately characterize the effect of COVID-19 on one of the UVA Internal Medicine, Primary Care clinics, and where possible, to refine and optimize patient flow through the appointment process while accommodating public health restrictions. To achieve these goals, the team adopted a systems approach, which involves the iterative process of problem identification, analysis, and testing recommendations. The first phase of the project focused primarily on establishment of the current state and problem identification. The appointment process contains six major elements: scheduling, sign-in/remote registration, check-in, rooming, check-out, and telemedicine. Through extensive discussions with the clients, surveys of clinic staff, in-person observation, and data collection and analysis, the capstone team was able to understand the pandemic's impact on the clinic's patient flow and identify key problem areas at each stage in the appointment process. The team then used these insights to develop informed recommendations for these pain points. The second phase of the project consisted of formulating trials within UVA health restrictions and guidelines to test the impact of our recommendations. Through a pilot of a new remote registration process, on-time patients increased from 68% to 75%, nurse perceived workload decreased significantly, and the arrival process became more predictable. From this work, the team was able to develop a more generic framework for how health systems might assess and address patient flow issues under normal circumstances as well as during future pandemics.

Optimization of Patient Flow and Process for a Primary Care Clinic during the COVID-19 Pandemic

Many patient throughput inefficiencies result from poor communication practices, inadequate understanding of optimizing healthcare systems to maximize efficiency, and longterm complications caused by the COVID-19 pandemic. The challenges precipitated by the pandemic, combined with the need to provide safe, high-quality care to patients, have further exacerbated existing patient flow and throughput issues. The overarching goal of this project is to improve the patient experience in primary care clinics and reduce the stress placed on providers, nurses, and staff. The authors implemented a two-phased approach that combined qualitative observations with quantitative data analysis, developed a robust methodology for understanding the University Physicians of Charlottesville (UPC) Clinic's processes, and produced structured insights for stakeholders. We established what components comprised a typical patient's journey through system intake through qualitative clinic observations: pre-registration, check-in, and rooming. In contrast to the qualitative observations, the quantitative analysis encompassed the complete patient experience, outs coping to include appointment durations and check-out. All quantitative analyses relied on data from the University of Virginia (UVA) Health's electronic medical record (EMR) system, Epic. In addition to the qualitative analyses, the authors utilized Cadence reports and appointment scheduling data to understand patient flow through the UPC Clinic. Primarily, the data are utilized to understand the distributions between the different patient flow milestones of registration, clinic check-in, rooming, and check-out and what factors, if any, were statistically significant. This approach enabled us to model the distribution of patient arrival times, wait times between arrival and rooming, and other relevant bottlenecks in the flow process. © 2022 IEEE.

Examining patient flow in a tertiary hospital's emergency department at a low coronavirus prevalence region.

BACKGROUND: Taiwan's successful containment of the COVID-19 outbreak prior to 2021 provided a unique environment for the surveillance of unnecessary emergency medical use. The aim of the study is to examine the impact of the coronavirus disease (COVID-19) pandemic on the patient flow in the emergency department (ED) of a tertiary hospital over 1 year in southern Taiwan, a region with low COVID-19 prevalence. METHODS: Cross-sectional observational study was conducted from January to December 2020. Essential parameters of patient flow in the ED between January and February 2020 and the subsequent 11-month period were compared to data from 2019. Data were analyzed with descriptive statistics, using an independent sample t-test or Mann-Whitney U test, as applicable. RESULTS: The ED census showed an acute decline (- 30.8%) from January to February 2020, reaching its nadir (- 40.5%) in April 2020. From February to December 2020, there was an average decrease of 20.3% in ED attendance (p < 0.001). The impact was most significant in ambulatory visits, lower-urgency acuity (level III) visits, and pediatric visits, without change in the acuity proportion. The length of stay shortened mainly in the adult division, which typically had an overcrowding problem (median, 5.7-4.4 hours in discharge; 24.8-16.9 hours in hospitalization; p < 0.001). The incidence of 72-hour unscheduled return visits was also reduced (4.1-3.5%, p = 0.002). CONCLUSIONS: In contrast to devastated regions, the impact on the ED patient flow in regions having low COVID-19 prevalence highlights a remodeling process of emergency medical care that would improve overcrowding.

AI-Based Chest CT Analysis for Rapid COVID-19 Diagnosis and Prognosis: A Practical Tool to Flag High-Risk Patients and Lower Healthcare Costs.

Early diagnosis of COVID-19 is required to provide the best treatment to our patients, to prevent the epidemic from spreading in the community, and to reduce costs associated with the aggravation of the disease. We developed a decision tree model to evaluate the impact of using an artificial intelligence-based chest computed tomography (CT) analysis software (icolung, icometrix) to analyze CT scans for the detection and prognosis of COVID-19 cases. The model compared routine practice where patients receiving a chest CT scan were not screened for COVID-19, with a scenario where icolung was introduced to enable COVID-19 diagnosis. The primary outcome was to evaluate the impact of icolung on the transmission of COVID-19 infection, and the secondary outcome was the in-hospital length of stay. Using EUR 20000 as a willingness-to-pay threshold, icolung is cost-effective in reducing the risk of transmission, with a low prevalence of COVID-19 infections. Concerning the hospitalization cost, icolung is cost-effective at a higher value of COVID-19 prevalence and risk of hospitalization. This model provides a framework for the evaluation of AI-based tools for the early detection of COVID-19 cases. It allows for making decisions regarding their implementation in routine practice, considering both costs and effects.

Clinical analysis on diagnostic accuracy of Bosch Vivalytic SARS-CoV-2 point-of-care test and evaluation of cycle threshold at admission for COVID-19 risk assessment.

BACKGROUND: Point-of-care (POC) polymerase chain reaction (PCR) tests have the ability to improve testing efficiency in the Coronavirus disease 2019 (COVID-19) pandemic. However, real-world data on POC tests is scarce. OBJECTIVE: To evaluate the efficiency of a novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) POC test in a clinical setting and examine the prognostic value of cycle threshold (CT) on admission on the length of hospital stay (LOS) in COVID-19 patients. METHODS: Patients hospitalised between January and May 2021 were included in this prospective cohort study. Patients' nasopharyngeal swabs were tested for SARS-CoV-2 with Allplex™2019-nCoV (Seegene Inc.) real-time (RT) PCR assay as gold standard as well as a novel POC test (Bosch Vivalytic SARS-CoV-2 [Bosch]) and the SARS-CoV-2 Rapid Antigen Test (Roche) accordingly. Clinical sensitivity and specificity as well as inter- and intra-assay variability were analyzed. RESULTS: 120 patients met the inclusion criteria with 46 (38%) having a definite COVID-19 diagnosis by RT-PCR. Bosch Vivalytic SARS-CoV-2 POC had a sensitivity of 88% and specificity of 96%. The inter- and intra- assay variability was below 15%. The CT value at baseline was lower in patients with LOS ≥ 10 days when compared to patients with LOS < 10 days (27.82 (± 4.648) vs. 36.2 (25.9-39.18); p = 0.0191). There was a negative correlation of CT at admission and LOS (r[44]s = - 0.31; p = 0.038) but only age was associated with the probability of an increased LOS in a multiple logistic regression analysis (OR 1.105 [95% CI, 1.03-1.19]; p = 0.006). CONCLUSION: Our data indicate that POC testing with Bosch Vivalytic SARS-CoV-2 is a valid strategy to identify COVID-19 patients and decrease turnaround time to definite COVID-19 diagnosis. Also, our data suggest that age at admission possibly with CT value as a combined parameter could be a promising tool for risk assessment of increased length of hospital stay and severity of disease in COVID-19 patients.

Modeling Patient Flow in an Emergency Department under COVID-19 Pandemic Conditions: A Hybrid Modeling Approach.

Emergency departments (EDs) had to considerably change their patient flow policies in the wake of the COVID-19 pandemic. Such changes affect patient crowding, waiting time, and other qualities related to patient care and experience. Field experiments, surveys, and simulation models can generally offer insights into patient flow under pandemic conditions. This paper provides a thorough and transparent account of the development of a multi-method simulation model that emulates actual patient flow in the emergency department under COVID-19 pandemic conditions. Additionally, a number of performance measures useful to practitioners are introduced. A conceptual model was extracted from the main stakeholders at the case hospital through incremental elaboration and turned into a computational model. Two agent types were mainly modeled: patient and rooms. The simulated behavior of patient flow was validated with real-world data (Smart Crowding) and was able to replicate actual behavior in terms of patient occupancy. In order to further the validity, the study recommends several phenomena to be studied and included in future simulation models such as more agents (medical doctors, nurses, beds), delays due to interactions with other departments in the hospital and treatment time changes at higher occupancies.

Towards A Fuzzy Rule-Based Approach for Patient Flow Management in Emergency Department during the COVID-19: Sahloul Hospital Case Study, Tunisia

The Corona Virus Disease 2019 (COVID-19) epidemic has touched many sectors of the health system. It was remote around the world during months and generated a diverse doubt for healthcare beneficiaries. Most hospitals have been opposing constraints in the treatment of the COVID-19 patients, and there is a need to improve patients flow waiting time so that the health staff is less menaced, and more patients can be handled. In this paper, we present a new fuzzy rule-based system for patient flow management in the emergency department, in the case of Sahloul University Hospital one of a big Tunisian Hospitals, in order to contribute reducing the patient flow waiting time and presenting a better management of patient flow during the COVID-19 epidemic phase. © 2021 IEEE.

Emergency Department Overcrowding: Understanding the Factors to Find Corresponding Solutions.

It is certain and established that overcrowding represents one of the main problems that has been affecting global health and the functioning of the healthcare system in the last decades, and this is especially true for the emergency department (ED). Since 1980, overcrowding has been identified as one of the main factors limiting correct, timely, and efficient hospital care. The more recent COVID-19 pandemic contributed to the accentuation of this phenomenon, which was already well known and of international interest. Considering what would appear to be a trivial definition of overcrowding, it may seem simple for the reader to hypothesize solutions for what seems to be one of the most avoidable problems affecting the hospital system. However, proposing solutions to overcrowding, as well as their implementation, cannot be separated from a correct and precise definition of the issue, which must consider the main causes and aggravating factors. In light of the need of finding solutions that can put an end to hospital overcrowding, this review aims, through a review of the literature, to summarize the triggering factors, as well as the possible solutions that can be proposed.

Simulation of the COVID-19 patient flow and investigation of the future patient arrival using a time-series prediction model: a real-case study.

COVID-19 looks to be the worst pandemic disease in the last decades due to its number of infected people, deaths, and the staggering demand for healthcare services, especially hospitals. The first and most important step is to identify the patient flow through a certain process. For the second step, there is a crucial need for predicting the future patient arrivals for planning especially at the administrative level of a hospital. This study aims to first simulate the patient flow process and then predict the future entry of patients in a hospital as the case study. Also, according to the system status, this study suggests some policies based on different probable scenarios and assesses the outcome of each decision to improve the policies. The simulation model is conducted by Arena.15 software. The seasonal auto-regressive integrated moving average (SARIMA) model is used for patient's arrival prediction within 30 days. Different scenarios are evaluated through a data envelopment analysis (DEA) method. The simulation model runs for predicted patient's arrival for the least efficient scenario and the outputs compare the base run scenario. Results show that the system collapses after 14 days according to the predictions and simulation and the bottleneck of the ICU and CCU departments becomes problematic. Hospitals can use simulation and also prediction tools to avoid the crisis to plan for the future in the pandemic.