Abstract--COVID-19 is a respiratory disease that caused a global pandemic in 2019. It is highly infectious and has the following symptoms: fever or chills, cough, shortness of breath, fatigue, muscle or body aches, headache, the new loss of taste or smell, sore throat, congestion or runny nose, nausea or vomiting, and diarrhea. These symptoms vary in severity; some people with many risk factors have been known to have lengthy hospital stays or die from the disease. In this paper, we analyze patients' electronic health records (EHR) to predict the severity of their COVID-19 infection using the length of stay (LOS) as our measurement of severity. This is an imbalanced classification problem, as many people have a shorter LOS rather than a longer one. T o combat this problem, we synthetically create alternate oversampled training data sets. Once we have this oversampled data, we run it through an Artificial Neural Network (ANN), which during training has its hyperparameters tuned by using bayesian optimization. We select the model with the best F1 score and then evaluate it and discuss it. COVID-19 is defined by the Centers for Disease Control and Prevention (CDC) as "a respiratory disease caused by SARS-CoV -2, a coronavirus discovered in 2019. The virus spreads mainly from person to person through respiratory droplets produced when an infected person coughs, sneezes, or talks" [1]. Furthermore, they add, "For people who have symptoms, illness can range from mild to severe. Adults 65 years and older and people of any age with underlying medical conditions are at higher risk for severe illness" [1].In 2019 this novel coronavirus was first detected. The highly infectious nature of this disease, combined with the respiratory nature of the infection, caused a pandemic. Along with being highly contagious, COVID-19 also has an extensive range of symptoms such as fever or chills, cough, shortness of breath, fatigue, muscle or body aches, headache, the new loss of taste or smell, sore throat, congestion or runny nose, nausea or vomiting, and diarrhea [2]. Along with a long list of symptoms, COVID-19 has many risk factors, which may increase the severity of the infection.

Background: Emergency department (ED) overcrowding remains a major challenge, causing delays in care and increased operational strain. Hospital management often reacts to congestion after it occurs. Machine learning predictive modeling offers a proactive approach by forecasting patient flow metrics, such as waiting count, to improve resource planning and hospital efficiency. Objective: This study develops machine learning models to predict ED waiting room occupancy at two time scales. The hourly model forecasts the waiting count six hours ahead (e.g., a 1 PM prediction for 7 PM), while the daily model estimates the average waiting count for the next 24 hours (e.g., a 5 PM prediction for the following day's average). These tools support staffing decisions and enable earlier interventions to reduce overcrowding. Methods: Data from a partner hospital's ED in the southeastern United States were used, integrating internal metrics and external features. Eleven machine learning algorithms, including traditional and deep learning models, were trained and evaluated. Feature combinations were optimized, and performance was assessed across varying patient volumes and hours. Results: TSiTPlus achieved the best hourly prediction (MAE: 4.19, MSE: 29.32). The mean hourly waiting count was 18.11, with a standard deviation of 9.77. Accuracy varied by hour, with MAEs ranging from 2.45 (11 PM) to 5.45 (8 PM). Extreme case analysis at one, two, and three standard deviations above the mean showed MAEs of 6.16, 10.16, and 15.59, respectively. For daily predictions, XCMPlus performed best (MAE: 2.00, MSE: 6.64), with a daily mean of 18.11 and standard deviation of 4.51. Conclusions: These models accurately forecast ED waiting room occupancy and support proactive resource allocation. Their implementation has the potential to improve patient flow and reduce overcrowding in emergency care settings.

Patient length of stay (LoS) is a critical metric for evaluating the efficacy of hospital management. The primary objectives encompass to improve efficiency and reduce costs while enhancing patient outcomes and hospital capacity within the patient journey. By seamlessly merging data-driven techniques with simulation methodologies, the study proposes an all-encompassing framework for the optimization of patient flow. Using a comprehensive dataset of 2.3 million de-identified patient records, we analyzed demographics, diagnoses, treatments, services, costs, and charges with machine learning models (Decision Tree, Logistic Regression, Random Forest, Adaboost, LightGBM) and Python tools (Spark, AWS clusters, dimensionality reduction). Our model predicts patient length of stay (LoS) upon admission using supervised learning algorithms. This hybrid approach enables the identification of key factors influencing LoS, offering a robust framework for hospitals to streamline patient flow and resource utilization. The research focuses on patient flow, corroborating the efficacy of the approach, illustrating decreased patient length of stay within a real healthcare environment. The findings underscore the potential of hybrid data-driven models in transforming hospital management practices. This innovative methodology provides generally flexible decision-making, training, and patient flow enhancement; such a system could have huge implications for healthcare administration and overall satisfaction with healthcare.

Increased healthcare demand is significantly straining European services. Digital solutions including advanced modelling techniques offer a promising solution to optimising patient flow without impacting day-to-day healthcare provision. In this work we outline an ongoing project that aims to optimise healthcare resources using agent-based simulations.

Every day, hospital staff do the best they can to navigate the daily chaos of bed management by making educated guesses as to what is going to happen over the course of the day. Relying on team huddles throughout the day, staff pore over Excel or paper spreadsheets to predict how many beds will open up and when. They try to estimate demand for those beds by the time of day, unsure when to deploy "surge capacity." On some days, this method works out well. However, more often than not, the staff's best efforts result in long patient waits, unwanted staff overtime, and ultimately lower access to care.

Accurately forecasting patient arrivals at Urgent Care Clinics (UCCs) and Emergency Departments (EDs) is important for effective resourcing and patient care. However, correctly estimating patient flows is not straightforward since it depends on many drivers. The predictability of patient arrivals has recently been further complicated by the COVID-19 pandemic conditions and the resulting lockdowns. This study investigates how a suite of novel quasi-real-time variables like Google search terms, pedestrian traffic, the prevailing incidence levels of influenza, as well as the COVID-19 Alert Level indicators can both generally improve the forecasting models of patient flows and effectively adapt the models to the unfolding disruptions of pandemic conditions. This research also uniquely contributes to the body of work in this domain by employing tools from the eXplainable AI field to investigate more deeply the internal mechanics of the models than has previously been done. The Voting ensemble-based method combining machine learning and statistical techniques was the most reliable in our experiments. Our study showed that the prevailing COVID-19 Alert Level feature together with Google search terms and pedestrian traffic were effective at producing generalisable forecasts. The implications of this study are that proxy variables can effectively augment standard autoregressive features to ensure accurate forecasting of patient flows. The experiments showed that the proposed features are potentially effective model inputs for preserving forecast accuracies in the event of future pandemic outbreaks.

Have you ever found yourself sitting for hours in a busy waiting room at the ER? It's stressful, you're in physical pain and everyone is rushing around you, focused on the massive number of other patients waiting, too. Luckily, hospitals are beginning to use machine learning solutions to streamline the waiting room process. The healthcare industry is introducing AI to combat many issues in the field. AI in hospitals can not only ease hospital patient flow, but it can also help develop pharmaceutical drugs, keep and analyze data and patient records, and even help diagnose illnesses like cancer. When people spend less time in the ER waiting room, more people can be treated in a timely manner.

Terence Mills, CEO of AI.io, a data science & engineering company that is building AI solutions that solve business problems. Have you ever found yourself sitting for hours in a busy waiting room at the ER? It's stressful, you're in physical pain and everyone is rushing around you, focused on the massive number of other patients waiting, too. Luckily, hospitals are beginning to use machine learning solutions to streamline the waiting room process. The healthcare industry is introducing AI to combat many issues in the field. AI in hospitals can not only ease hospital patient flow, but it can also help develop pharmaceutical drugs, keep and analyze data and patient records, and even help diagnose illnesses like cancer. When people spend less time in the ER waiting room, more people can be treated in a timely manner.

Technology is fighting death with data – including machine learning and artificial intelligence. Last week marked the annual Health Informatics New Zealand conference, in which local and global innovators spoke about how their work is changing local healthcare models. Amongst the New Zealand companies leading the way are Umbrellar and Auckland's Mercy Radiology and Clinics. "If we want healthcare service delivery to be consistent across the country, and we want to provide the best value to patients, we need to embrace digital technology," comments Mercy Radiology and Clinics CEO Lloyd McCann. "We need to address cultural barriers to change in the sector. Data, information and intelligence will help us drive this cultural transformation."

Back in September 2017, NHS England chief executive Simon Stevens told the NHS Health and Care Innovation Expo that major artificial intelligence (AI) innovations were in the pipeline in the NHS. He said that AI and machine learning is being, and will be, used in areas such as dermatology and pathology to improve clinical care. Efficiencies have never been more necessary. However, according to some, the sector has been slow to catch up with AI's benefits. Dr Panos Constantinides, associate professor of information systems at Warwick Business School and a digital technology researcher, says: "Unlike in other sectors, where companies such as Amazon and Google have been able to use AI in combination with data on online user behaviour to make recommendations on future user choices, the highly regulated healthcare industry does not grant easy access to patient data. Maintaining the security and confidentiality of patient data is a key priority in most countries."