Getting it right first time: what have we learnt?

Getting It Right First Time (GIRFT) is a national programme of improvement to identify and reduce unwarranted variation and non-evidence-based practice in healthcare. It aims to improve patient care, increase productivity and reduce costs. Professor Tim Briggs, an orthopaedic surgeon, began the programme with a pilot review visiting every orthopaedic surgery department in England. He used publicly available data to illuminate variation, and worked with the clinicians and management to develop improvements. The impressive initial report in 2015 led to NHS Improvement investing £60m to expand the programme to 40 medical and surgical specialties. The follow-up Orthopaedic report detailed savings of £696m to the NHS. GIRFT is now sharing its data with the CQC and leading the charge with elective recovery following COVID-19. GIRFT differs from previous programmes of improvement through its peer led, supportive approach to promoting change with early engagement of both clinicians and management. Common themes run through the almost 40 specialty reports published to date: variation in procurement and litigation costs, huge variations in patient treatment options (often with a lack of evidence base) and poor data quality. Successfully applied in orthopaedic surgery, it has been taken on enthusiastically by other specialties. Whether it can deliver its objective of £1.4bn savings whilst improving patient outcomes is yet to be seen, but its approach is changing the culture of the NHS.

Covid Wave Prediction using SARIMA Machine Learning Algorithm

A speedy and accurate diagnosis of COVID-19 is made possible by effective SARS-Co V -2 screening, which can also lessen the strain on health care systems. There have been built prediction models that assess the likelihood of infection by combining a number of parameters. These are intended to help medical professionals worldwide prioritize patients, particularly when there are few healthcare resources available. From a dataset of 51,831 tested people, out of which 4,769 were confirmed to have COVID-19 virus, a machine learning method was developed and trained. Records of the following week with 47,401 tested people, of which 3,624 were tested positive was also considered. Our method accurately predicted the COVID-19 test results using eight binary characteristics, including gender, age 60, known contact with an infected person, and the presence of five early clinical signs. © 2023 IEEE.

COVID-19 Detection Using Deep Learning Based Medical Image Segmentation

COVID-19 is a rapidly spreading illness around the globe, yet healthcare resources are limited. Timely screening of people who may have had COVID-19 is critical in reducing the virus's spread considering the lack of an effective treatment or medication. COVID-19 patients should be diagnosed as well as isolated as early as possible to avoid the infection from spreading and levelling the pandemic arc. To detect COVID-19, chest ultrasound tomography seems to be an option to the RT-PCR assay. The Ultrasound of the lung is a very precise, quick, relatively reliable surgical assay that can be used in conjunction with the RT PCR (Reverse Transcription Polymerase Chain Reaction) assay. Differential diagnosis is difficult due to large differences in structure, shape, and position of illnesses. The efficiency of conventional neural learning-based Computed tomography scans feature extraction is limited by discontinuous ground-glass and acquisitions, as well as clinical alterations. Deep learning-based techniques, primarily Convolutional Neural Networks (CNN), had successfully proved remarkable therapeutic outcomes. Moreover, CNNs are unable to capture complex features amongst images examples, necessitating the use of huge databases. In this paper semantic segmentation method is used. The semantic segmentation architecture U-Net is applied on COVID-19 CT images as well as another method is suggested based on prior semantic segmentation. The accuracy of U-Net is 87% and by using pre-trained U-Net with convolution layers gives accuracy of 89.07%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Predisposing factors for admission to intensive care units of patients with COVID-19 infection-Results of the German nationwide inpatient sample.

Background: Intensive care units (ICU) capacities are one of the most critical determinants in health-care management of the COVID-19 pandemic. Therefore, we aimed to analyze the ICU-admission and case-fatality rate as well as characteristics and outcomes of patient admitted to ICU in order to identify predictors and associated conditions for worsening and case-fatality in this critical ill patient-group. Methods: We used the German nationwide inpatient sample to analyze all hospitalized patients with confirmed COVID-19 diagnosis in Germany between January and December 2020. All hospitalized patients with confirmed COVID-19 infection during the year 2020 were included in the present study and were stratified according ICU-admission. Results: Overall, 176,137 hospitalizations of patients with COVID-19-infection (52.3% males; 53.6% aged ≥70 years) were reported in Germany during 2020. Among them, 27,053 (15.4%) were treated in ICU. COVID-19-patients treated on ICU were younger [70.0 (interquartile range (IQR) 59.0-79.0) vs. 72.0 (IQR 55.0-82.0) years, P < 0.001], more often males (66.3 vs. 48.8%, P < 0.001), had more frequently cardiovascular diseases (CVD) and cardiovascular risk-factors with increased in-hospital case-fatality (38.4 vs. 14.2%, P < 0.001). ICU-admission was independently associated with in-hospital death [OR 5.49 (95% CI 5.30-5.68), P < 0.001]. Male sex [OR 1.96 (95% CI 1.90-2.01), P < 0.001], obesity [OR 2.20 (95% CI 2.10-2.31), P < 0.001], diabetes mellitus [OR 1.48 (95% CI 1.44-1.53), P < 0.001], atrial fibrillation/flutter [OR 1.57 (95% CI 1.51-1.62), P < 0.001], and heart failure [OR 1.72 (95% CI 1.66-1.78), P < 0.001] were independently associated with ICU-admission. Conclusion: During 2020, 15.4% of the hospitalized COVID-19-patients were treated on ICUs with high case-fatality. Male sex, CVD and cardiovascular risk-factors were independent risk-factors for ICU admission.

Daily changes in spatial accessibility to ICU beds and their relationship with the case-fatality ratio of COVID-19 in the state of Texas, USA.

During the COVID-19 pandemic, many patients could not receive timely healthcare services due to limited availability and access to healthcare resources and services. Previous studies found that access to intensive care unit (ICU) beds saves lives, but they overlooked the temporal dynamics in the availability of healthcare resources and COVID-19 cases. To fill this gap, our study investigated daily changes in ICU bed accessibility with an enhanced two-step floating catchment area (E2SFCA) method in the state of Texas. Along with the increased temporal granularity of measurements, we uncovered two phenomena: 1) aggravated spatial inequality of access during the pandemic, and 2) the retrospective relationship between insufficient ICU bed accessibility and the high case-fatality ratio of COVID-19 in rural areas. Our findings suggest that those locations should be supplemented with additional healthcare resources to save lives in future pandemic scenarios.

Analysis and Prediction of COVID-19 Spread in Ernakulam District, Kerala

The world is witnessing a pandemic of SARS-CoV2 infection since the first quarter of the twenty-first century. Ever since the first case was reported in Wuhan city of China in December 2019, the virus has spread over 223 countries. Understanding and predicting the dynamics of COVID-19 spread through data analysis will empower our administrations with insights for better planning and response against the burden inflicted on our health care infrastructure and economy. The aim of the study was to analyze and predict COVID-19 spread in Ernakulam district of Kerala. Data was extracted from lab data management system (LDMS), a government portal to enter all the COVID-19 testing details. Using the EpiModel package of R-mathematical modeling of infectious disease dynamics, the predictive analysis for hospitalization rate, percentage of patients requiring oxygen and ICU admission, percentage of patients getting admitted, duration of hospital stay, case fatality rate, age group and gender-wise fatality rate, and hospitalization rate were computed. While calculating the above-said variables, the percentage of vaccinated population, breakthrough infections, and percentage of hospitalization among the vaccinated was also taken into consideration. The time trend of patients in ICU showed men outnumbered women. Positive cases were more among 20–30 years, while 61–70 years age group had more risk for ICU admission. An increase in CFR with advancing age and also a higher CFR among males were seen. Conclusions: Analyzing and predicting the trend of COVID-19 would help the governments to better utilize their limited healthcare resources and adopt timely measures to contain the virus. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Development of a Covid-19 Information Dashboard to Access the Health Care Resources and Requirements Online

With the emergence of coronavirus and the rapidly increasing number of cases, we observed that people were suffering from a lack of information about where to source critical requirements such as oxygen cylinders, beds, ambulance service, and ventilators. In this research paper and project, the authors have designed and developed an interactive information dashboard to access the availability of these resources and requirements at different locations across India from myriad sources. The information dashboard will show information for all the states across India. The dashboard visualizes the number of corona cases, hospital beds, blood bank, etc. The end-users and the COVID-19 support team can imagine all the requirements in the dashboard that is factual and credible within their vicinity from multiple information sources. The user need not search various information sites to search for different conditions. The project collates the data of other requirements from primary sources of information like Twitter and government websites and lists them on the dashboard. The authors used open-source programming and database technologies to display the data per user requirements. The dashboard was helpful to the end-users during COVID-19 times in terms of convenient accessibility and efficiency. © 2022 IEEE.

Identification of an Optimal COVID-19 Booster Allocation Strategy to Minimize Hospital Bed-Days with a Fixed Healthcare Budget.

Healthcare decision-makers face difficult decisions regarding COVID-19 booster selection given limited budgets and the need to maximize healthcare gain. A constrained optimization (CO) model was developed to identify booster allocation strategies that minimize bed-days by varying the proportion of the eligible population receiving different boosters, stratified by age, and given limited healthcare expenditure. Three booster options were included: B1, costing US $1 per dose, B2, costing US $2, and no booster (NB), costing US $0. B1 and B2 were assumed to be 55%/75% effective against mild/moderate COVID-19, respectively, and 90% effective against severe/critical COVID-19. Healthcare expenditure was limited to US$2.10 per person; the minimum expected expense using B1, B2, or NB for all. Brazil was the base-case country. The model demonstrated that B1 for those aged <70 years and B2 for those ≥70 years were optimal for minimizing bed-days. Compared with NB, bed-days were reduced by 75%, hospital admissions by 68%, and intensive care unit admissions by 90%. Total costs were reduced by 60% with medical resource use reduced by 81%. This illustrates that the CO model can be used by healthcare decision-makers to implement vaccine booster allocation strategies that provide the best healthcare outcomes in a broad range of contexts.

Do wildfires exacerbate COVID-19 infections and deaths in vulnerable communities? Evidence from California.

Understanding whether and how wildfires exacerbate COVID-19 outcomes is important for assessing the efficacy and design of public sector responses in an age of more frequent and simultaneous natural disasters and extreme events. Drawing on environmental and emergency management literatures, we investigate how wildfire smoke (PM2.5) impacted COVID-19 infections and deaths during California's 2020 wildfire season and how public housing resources and hospital capacity moderated wildfires' effects on COVID-19 outcomes. We also hypothesize and empirically assess the differential impact of wildfire smoke on COVID-19 infections and deaths in counties exhibiting high and low social vulnerability. To test our hypotheses concerning wildfire severity and its disproportionate impact on COVID-19 outcomes in socially vulnerable communities, we construct a county-by-day panel dataset for the period April 1 to November 30, 2020, in California, drawing on publicly available state and federal data sources. This study's empirical results, based on panel fixed effects models, show that wildfire smoke is significantly associated with increases in COVID-19 infections and deaths. Moreover, wildfires exacerbated COVID-19 outcomes by depleting the already scarce hospital and public housing resources in local communities. Conversely, when wildfire smoke doubled, a one percent increase in the availability of hospital and public housing resources was associated with a 2 to 7 percent decline in COVID-19 infections and deaths. For California communities exhibiting high social vulnerability, the occurrence of wildfires worsened COVID-19 outcomes. Sensitivity analyses based on an alternative sample size and different measures of social vulnerability validate this study's main findings. An implication of this study for policymakers is that communities exhibiting high social vulnerability will greatly benefit from local government policies that promote social equity in housing and healthcare before, during, and after disasters.

Provider reported value and use of virtual resources in extended primary care prior to and during COVID-19.

BACKGROUND: A proactive approach to delivering care using virtual resources, while reducing in-person contact, is needed during the COVID-19 pandemic. OBJECTIVE: In the current study we describe pre- to post- COVID-19 pandemic onset related changes in electronic delivery of primary care. METHODS: A longitudinal, pre-post within-subjects design was used. Patient-aligned care team providers from one VA medical center, a primary care annex, and four affiliated community-based outpatient clinics completed both a baseline and follow up survey (N = 62) or the follow-up survey only (N = 85). The follow-up survey contained questions about COVID-19. RESULTS: The majority of providers (88%) reported they would continue virtual care once pandemic restrictions were lifted. Most (83%) felt prepared to transition to virtual care when pandemic restrictions began. Use of My HealtheVet, Telehealth, and mobile apps showed a significant increase (22.7%; 31.1%; 48.5%). Barriers to virtual care included (1) internet connectivity; (2) patients' lack of technology comfort and skills; and (3) technical issues. Main supports to provide virtual care to patients were (1) peers/ colleagues; (2) technology support through help desk; (3) equipment such as laptops and dual screens; (4) being able to use doximety and virtual care manager, and (5) training. CONCLUSIONS: Overall, provider-use and perceptions related to using virtual care improved over time. Providers adapted quickly to providing virtual care during COVID-19 and planned to provide virtual care long-term.

Evolution of Anxiety and Depression in Men during the First Six Months of the COVID-19 Pandemic and Factors Associated with Worsening of Mental Health: Retrospective Longitudinal Study

Background: The Coronavirus disease (COVID-19) pandemic has had a huge impact on the psychological wellbeing of the population, however, few studies have analysed the psychological consequences for the most vulnerable groups, particularly those suffering from depression and anxiety, and specifically in men. The objective of this study is to analyse the changes in a population of men undergoing active treatment for depression or anxiety and factors associated with these changes. Methods: Retrospective, longitudinal and observational study of a population of 28,294 men in northern Spain. The study variables were sociodemographic variables, chronic comorbidities, COVID-19 infection, anxiolytic and antidepressant drug consumption, and use of healthcare resources. These variables were collected from the Primary Health Care electronic records for the two distinct periods (6 months before and 6 months following the end of the lockdown). To compare drug patterns and the use of healthcare resources a paired Student's T-test was used. To analyse associated factors related to a deterioration of mental disorders, a multivariate logistic regression was performed. Results: In relation to changes in drug patterns, 40% of men saw an increase in at least one Defined Daily Dose (DDD) of their prescribed drugs during the 6 months following lockdown and the number of appointments at health centres and home visits significantly decreased. Factors associated with a deterioration of mental disorders are being under 60 years old, having an income of less than 18,000 euros/year and suffering from more than one comorbidity. Conclusions: The pandemic had a significant impact on men with a previous diagnosis of depression and/or anxiety.

Estimating the spatial correlation and convergence of China's healthcare resources allocation: evidence from the Yangtze River Delta Region.

BACKGROUND: China's imbalanced allocation of healthcare resources mainly arises from urban-rural and intercity differences, the solution of which has been the goal of reforms during the past decades. Estimating the spatial correlation and convergence could help to understand the impact of China's fast-evolving medical market and the latest healthcare reforms. METHODS: The entropy weight method was used to construct a healthcare resource supply index (HRS) by using data of 41cities in a cluster in the Yangtze River Delta (YRD) from 2007 to 2019. The Dagum Gini coefficient, kernel density estimation, Moran's I, and LISA cluster map were used to characterize the spatiotemporal evolution and agglomeration of healthcare resources, and then a spatial panel model was used to perform ß convergence estimation by incorporating the spatial effect, city heterogeneity, and healthcare reforms. RESULTS: Healthcare resources supply in the YRD region increases significantly and converges rapidly. There is a significant spatial correlation and agglomeration between provinces and cities, and a significant spatial spillover effect is also found in ß convergence. No evidence is found that the latest healthcare reforms have an impact on the balanced allocation and convergence of healthcare resources. CONCLUSION: China's long-term investment in past decades has yielded a more balanced allocation and intercity convergence of healthcare resources. However, the latest healthcare reforms do not contribute to the balanced allocation of healthcare resources from the supply-side, and demand-side analysis is needed in the future studies.

Resources Allocation and Utilization Efficiency in China's Healthcare Sector

The reasonable allocation of healthcare resources across different levels of healthcare facilities is the key to promoting the tiered diagnosis and treatment approach. The sudden outbreak of COVID-19 underscores the shortage of resources and service capability of China's primary healthcare facilities. From the perspective of the vertical division of labor in the healthcare service system and based on the quality adjustment and quantitative correction of healthcare workers, this paper comprehensively calculates and analyzes the evenness of resources allocation between hospitals and primary healthcare facilities;and then, combining the theoretical model derivation with China's empirical data test, this paper demonstrates how the misallocation of healthcare resources affects their utilization efficiency. The results are as below. (1) There are varying degrees of quantity and quality imbalance in various healthcare resources between hospitals and primary healthcare facilities. (2) When other conditions remain unchanged, the more misallocated healthcare resources are, the lower the "actual"utilization efficiency after quality adjustment is. (3) Compared with the absence of price regulation, government price regulation has led to a relative "overtreatment equilibrium"in the healthcare service market. Therefore, measures should be taken to optimize the structure of healthcare resources allocation and improve the efficiency of resources utilization, such as strengthening the government's healthcare financing function, formulating policies that favor primary healthcare facilities, and encouraging social capital to invest at the community level. © 2021 Junhao Wang and Jia Wanwen, published by De Gruyter.

Ethical values and principles to guide the fair allocation of resources in response to a pandemic: a rapid systematic review.

BACKGROUND: The coronavirus 2019 pandemic placed unprecedented pressures on healthcare services and magnified ethical dilemmas related to how resources should be allocated. These resources include, among others, personal protective equipment, personnel, life-saving equipment, and vaccines. Decision-makers have therefore sought ethical decision-making tools so that resources are distributed both swiftly and equitably. To support the development of such a decision-making tool, a systematic review of the literature on relevant ethical values and principles was undertaken. The aim of this review was to identify ethical values and principles in the literature which relate to the equitable allocation of resources in response to an acute public health threat, such as a pandemic. METHODS: A rapid systematic review was conducted using MEDLINE, EMBASE, Google Scholar, LitCOVID and relevant reference lists. The time period of the search was January 2000 to 6th April 2020, and the search was restricted to human studies. January 2000 was selected as a start date as the aim was to capture ethical values and principles within acute public health threat situations. No restrictions were made with regard to language. Ethical values and principles were extracted and examined thematically. RESULTS: A total of 1,618 articles were identified. After screening and application of eligibility criteria, 169 papers were included in the thematic synthesis. The most commonly mentioned ethical values and principles were: Equity, reciprocity, transparency, justice, duty to care, liberty, utility, stewardship, trust and proportionality. In some cases, ethical principles were conflicting, for example, Protection of the Public from Harm and Liberty. CONCLUSIONS: Allocation of resources in response to acute public health threats is challenging and must be simultaneously guided by many ethical principles and values. Ethical decision-making strategies and the prioritisation of different principles and values needs to be discussed with the public in order to prepare for future public health threats. An evidence-based tool to guide decision-makers in making difficult decisions is required. The equitable allocation of resources in response to an acute public health threat is challenging, and many ethical principles may be applied simultaneously. An evidence-based tool to support difficult decisions would be helpful to guide decision-makers.

Design of Virtual Reality Scenes on Horticultural Therapy Treatment

The prevalence of depression and anxiety disorders has increased dramatically in the last two years due to the global COVID-19 epidemic, which leads to a shortage of traditional mental health care resources. To address these issues, we propose to use the digital, immersive, and private features of virtual reality technology to assist in the treatment of mental illness. We designed and completed a garden scene for virtual reality horticultural therapy based on the basic principles of traditional horticultural therapy. In order to study the effectiveness of the gardening scenario, we recruited 30 subjects to explore the effectiveness of mood regulation. A survey of a PANAS scale was conducted before and after the garden scene, and a user experience scale was presented to the subjects after the experiment. The ANOVA results showed that there were significant differences between anxious, distressed and self-loathing before and after the experiment. This demonstrates that virtual reality horticulture therapy has a mood-improving effect. In future works, we will improve the design of VR gardening scenarios and conduct more in-depth research on virtual reality horticulture therapy. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Covid-19 Detection by Wavelet Entropy and Self-adaptive PSO

The rapid global spread of COVID-19 disease poses a huge threat to human health and the global economy. The rapid increase in the number of patients diagnosed has strained already scarce healthcare resources to track and treat Covid-19 patients in a timely and effective manner. The search for a fast and accurate way to diagnose Covid-19 has attracted the attention of many researchers. In our study, a deep learning framework for the Covid-19 diagnosis task was constructed using wavelet entropy as a feature extraction method and a feedforward neural network classifier, which was trained using an adaptive particle swarm algorithm. The model achieved an average sensitivity of 85.14% ± 2.74%, specificity of 86.76% ± 1.75%, precision of 86.57% ± 1.36%, accuracy of 85.95% ± 1.14%, and F1 score of 85.82% ± 1.30%, Matthews correlation coefficient of 71.95 ± 2.26%, and Fowlkes-Mallows Index of 85.83% ± 1.30%. Our experiments validate the usability of wavelet entropy-based feature extraction methods in the medical image domain and show the non-negligible impact of different optimisation algorithms on the models by comparing them with other models. © 2022, Springer Nature Switzerland AG.

Ukraine war refugees - threats and new challenges for healthcare in Poland.

BACKGROUND: Between February 2022, when the war in Ukraine began, and April 1, 2022, the number of refugees to neighboring countries reached 4,137,842 people. The majority have fled to Poland. The main challenge for the health system in Poland in this situation is how to develop effective adaptation measures. AIM: The aim of this study is to describe threats and challenges to public health related in particular to infectious diseases and to identify the resources of the healthcare system that are necessary to meet the needs of the recent war refugees and the Polish population. METHODS: Scientific publications, statistical data from national and international organizations, information obtained from public institutions in Poland and Ukraine, and reliable sources of up-to-date information on the Internet were used. Key data on threats and challenges to public health were collected and presented. FINDINGS: Differences were observed between Poland and Ukraine in terms of immunization programmes and their implementation as well as in relation to the prevalence of selected infectious diseases. The increase in demand for healthcare resources in Poland was estimated on the basis of current indicators. Both the possibilities of counteracting epidemic threats related to the current situation and possible consequences for the availability of services and the health condition of all people currently staying in Poland were presented. CONCLUSION: European countries may experience public health threats due to the influx of war refugees. The data presented could be useful for European countries while developing effective strategies to mitigate public health issues.

Impact of Digitalization of the Healthcare Industry and Covid 19 Management: Case of the UAE

Technology has changed the face of almost every sphere of life including the healthcare system which was erstwhile considered a subject of pure clinical evaluation. The onset of the Covid 19 pandemic underscored adaptation to technology as the singular solution to address the banes of the huge number of people afflicted with it globally with limited healthcare workers and resources. The opening of a small healthcare centre in the Al Ras region marked the beginning of healthcare in Dubai. The healthcare system of the UAE has grown exponentially over the years, and it now offers a variety of specialized services that sets it apart from the others. The UAE healthcare industry is increasingly improving to meet the changing needs of its people as well as the country's goal to become a regional medical tourism hub. The government is implementing several long-term projects to achieve balanced growth and to incorporate sustainable growth in the industry while meeting the immediate needs of the population. Comprehensive health-care reforms have been enacted over the last ten years. This paper examines the development and results of Health-Care reforms in the UAE using primary data collected by conducting a survey in a prominent health organization in the UAE. The main aim of the survey was to study the impact of digitalization on the healthcare sector in the UAE. The case in point was the influence of digitalized measures including Big Data Analytics and Artificial Intelligence (AI) in handling the Covid-19 situation from the point of view of the healthcare sector employees. © 2021 IEEE.

Internet of Things for Managing Global Pandemics: Lessons from COVID-19 Pandemic

The Internet of Things, often known as IoT, is an innovative technology that connects digital devices all around us, allowing Machine to Machine (M2M) communication between digital devices all over the world, owing to the technological advancements in the 21st century. Due to the convenience, connectivity, and affordability, this IoT is being served in various domains including healthcare where it brings exceptional benefits to improve patient care, uplifting medical resources to the next level. As of now, the IoT is served in various aspects of healthcare making many of the medical processes much easier as opposed to the earlier times. One of the most important aspects that this IoT can be used is, managing various aspects of healthcare during global pandemics, as pandemics can bring an immense strain on healthcare resources. As there is no proper study is done with regards to the proper use of IoT for managing pandemics, in this regard, through our study we aim to provide a comprehensive analysis of various use cases of IoT towards managing pandemics especially in terms of COVID-19 owing to what we are currently going through, along with key challenges and future directions. In this regard, we are proposing a contextual framework synthesizing the current literature and resources, which can be adopted when managing global pandemics like COVID-19 at the national and global levels. © 2021 IEEE.

Predicting COVID-19-Related Health Care Resource Utilization Across a Statewide Patient Population: Model Development Study.

BACKGROUND: The COVID-19 pandemic has highlighted the inability of health systems to leverage existing system infrastructure in order to rapidly develop and apply broad analytical tools that could inform state- and national-level policymaking, as well as patient care delivery in hospital settings. The COVID-19 pandemic has also led to highlighted systemic disparities in health outcomes and access to care based on race or ethnicity, gender, income-level, and urban-rural divide. Although the United States seems to be recovering from the COVID-19 pandemic owing to widespread vaccination efforts and increased public awareness, there is an urgent need to address the aforementioned challenges. OBJECTIVE: This study aims to inform the feasibility of leveraging broad, statewide datasets for population health-driven decision-making by developing robust analytical models that predict COVID-19-related health care resource utilization across patients served by Indiana's statewide Health Information Exchange. METHODS: We leveraged comprehensive datasets obtained from the Indiana Network for Patient Care to train decision forest-based models that can predict patient-level need of health care resource utilization. To assess these models for potential biases, we tested model performance against subpopulations stratified by age, race or ethnicity, gender, and residence (urban vs rural). RESULTS: For model development, we identified a cohort of 96,026 patients from across 957 zip codes in Indiana, United States. We trained the decision models that predicted health care resource utilization by using approximately 100 of the most impactful features from a total of 1172 features created. Each model and stratified subpopulation under test reported precision scores >70%, accuracy and area under the receiver operating curve scores >80%, and sensitivity scores approximately >90%. We noted statistically significant variations in model performance across stratified subpopulations identified by age, race or ethnicity, gender, and residence (urban vs rural). CONCLUSIONS: This study presents the possibility of developing decision models capable of predicting patient-level health care resource utilization across a broad, statewide region with considerable predictive performance. However, our models present statistically significant variations in performance across stratified subpopulations of interest. Further efforts are necessary to identify root causes of these biases and to rectify them.