Bed Allocation Research Articles

The economics of deep and machine learning-based algorithms for COVID-19 prediction, detection, and diagnosis shaping the organizational management of hospitals

Research background: Deep and machine learning-based algorithms can assist in COVID-19 image-based medical diagnosis and symptom tracing, optimize intensive care unit admission, and use clinical data to determine patient prioritization and mortality risk, being pivotal in qualitative care provision, reducing medical errors, and increasing patient survival rates, thus diminishing the massive healthcare system burden in relation to severe COVID-19 inpatient stay duration, while increasing operational costs throughout the organizational management of hospitals. Data-driven financial and scenario-based contingency planning, predictive modelling tools, and risk pooling mechanisms should be deployed for additional medical equipment and unforeseen healthcare demand expenses. Purpose of the article: We show that deep and machine learning-based and clinical decision making systems can optimize patient survival likelihood and treatment outcomes with regard to susceptible, infected, and recovered individuals, performing accurate analyses by data modeling based on vital and clinical signs, surveillance data, and infection-related biomarkers, and furthering hospital facility optimization in terms of intensive care unit bed allocation. Methods: The review software systems employed for article screening and quality evaluation were: AMSTAR, AXIS, DistillerSR, Eppi-Reviewer, MMAT, PICO Portal, Rayyan, ROBIS, and SRDR. Findings & value added: Deep and machine learning-based clinical decision support tools can forecast COVID-19 spread, confirmed cases, and infection and mortality rates for data-driven appropriate treatment and resource allocations in effective therapeutic and diagnosis protocol development, by determining suitable measures and regulations and by using symptoms and comorbidities, vital signs, clinical and laboratory data and medical records across intensive care units, impacting the healthcare financing infrastructure. As a result of heightened use of personal protective equipment, hospital pharmacy and medication, outpatient treatment, and medical supplies, revenue loss and financial vulnerability occur, also due to expenses related to hiring additional staff and to critical resource expenditures. Hospital costs for COVID-19 medical care, screening, treatment capacity expansion, and personal protective equipment can lead to further financial losses while affecting COVID-19 frontline hospital workers and patients.

Safety and cost of performing laparoscopic sleeve gastrectomy with same day discharge at a large academic hospital.

Laparoscopic sleeve gastrectomy (LSG) is the most common surgical treatment for morbid obesity. While certain specialized ambulatory surgery centers offer LSG on an outpatient basis, patients undergoing LSG at most academic centers are admitted to hospital for initial postoperative convalescence and monitoring. Our institution has begun to offer LSG with same-day discharge (SDD) in select patients. We aimed to compare the perioperative outcomes and costs for patients undergoing LSG with inpatient admission versus SDD. All patients enrolled in the SDD program from December 2020 through July 2022 were identified from a prospectively maintained database. Patients enrolled in this pathway were analyzed on an intention-to-treat basis even if ultimately admitted postoperatively. Propensity scoring was used to match these patients 1:1 to those with planned inpatient recovery based on age, BMI, and ASA classification. Seventy-five patients were enrolled in the LSG with SDD program during the study period. Among these, 62 patients (82.7%) had successful immediate postoperative discharge. Reasons for cancelation of planned SDD included anxiety (n = 5), pain (n = 3), nausea (n = 2), and one patient each with hypotension, urinary retention, and bleeding. After matching, there were no differences in age, BMI, or ASA classification in a comparison group of patients with planned inpatient recovery. There were no differences in perioperative complications. There were no readmissions or requirements for outpatient intravenous fluids among patients with SDD, compared to n = 3 (4.0%) and n = 2 (2.7%) in the inpatient cohort, respectively. The total perioperative cost for patients undergoing LSG with planned SDD was 6.8% less than those with inpatient recovery. With appropriate protocols, LSG with same-day discharge can safely be performed at large academic surgery centers without increased morbidity or need for additional services in the perioperative period. SDD may be associated with decreased costs and allows for more efficient hospital bed allocation.

What Causes Delays in Admission to Rehabilitation Care? A Structural Estimation Approach

Problem definition: Delays in admission to rehabilitation care can adversely impact patient outcomes. In addition, delayed patients keep occupying their acute care beds, making them unavailable for incoming patients. Admission delays are mainly caused by a lack of rehabilitation bed capacity and the time required to plan for rehabilitation activities, which we refer to as processing times. Because of non-standard bed allocation decisions and data limitations in practice, quantifying the magnitude of the two sources of delays can be technically challenging yet critical to the design of evidence-based interventions to reduce delays. We propose an empirical approach to understanding the contributions of the two sources of delays when only a single (combined) measure of admission delay is available. Methodology/results: We propose a hidden Markov model (HMM) to estimate the unobserved processing times and the status-quo bed allocation policy. Our estimation results quantify the magnitude of processing times versus capacity-driven delays and provide insights into factors impacting the bed allocation decision. We validate our estimated policy using a queueing model of patient flow and find that ignoring processing times or using simple bed allocation policies can lead to highly inaccurate delay estimates. In contrast, our estimated policy allows for accurate evaluation of different operational interventions. We find that reducing processing times can be highly effective in reducing admission delays and bed-blocking costs. In addition, allowing early transfer—whereby patients can complete some of their processing requirements in the rehabilitation unit—can significantly reduce admission delays, with only a small increase in rehab LOS. Managerial implications: Our study demonstrates the importance of quantifying different sources of delays in the design of effective operational interventions for reducing delays in admission to rehabilitation care. The proposed estimation framework can be applied in other transition-of-care settings with personalized capacity allocation decisions and hidden processing delays. History: This paper was selected for Fast Track in the M&SOM journal from the 2022 MSOM Healthcare SIG Conference. Funding: J. Dong was supported in part by the National Science Foundation [Grant CMMI-1762544]. V. Sarhangian was supported in part by the Natural Sciences and Engineering Research Council of Canada [Grant RGPIN-2018-04518] and the Connaught Fund. Supplemental Material: The e-companion is available at https://doi.org/10.1287/msom.2022.0377 .

Nonprofit vs. For-Profit: Allocation of Beds and Access to Care in U.S. Nursing Homes

Nonprofit vs. For-Profit: Allocation of Beds and Access to Care in U.S. Nursing Homes

Assessing the spatial equity of the aged care institutions based on the improved potential model: a case study in Shanghai, China.

With the spread of an aging society, the demand for aged care institutions among older adults is increasing. The inadequate supply and distribution of aged care institutions have led to an increasing concern about spatial equity in aged care institutions. Most studies have utilized accessibility to assess spatial equity from the supply perspective, while the demand perspective has received little attention. In addition, few studies have evaluated the spatial equity of aged care institutions at grid resolution. Therefore, this study takes Shanghai as an example to analyze aged care institutions from both the supply and demand perspectives. By proposing an improved potential model, at a network resolution of 500 × 500, the spatial equity of aged care institutions is more refined. The results show that aged care institutions and the older population in Shanghai are predominantly concentrated in the downtown area and surrounding regions. However, the results obtained from the Lorenz curve and Gini coefficient indicate the allocation of pension beds based on population size is proportional across different districts of Shanghai. When considering the quality indicators of aged care institutions and introducing the improved potential energy model to calculate spatial accessibility, an imbalance between regions in Shanghai still exists and needs further optimization.

The hidden factor in COVID-19 rehabilitation: how does the microenvironment in mobile cabin hospitals impact patient recovery? An observational study

Backgrounds: Existing studies on the treatment of emergency infectious diseases have primarily focused on the pathogen and the human immune system. However, human health is intricately connected to environmental factors, and this interaction becomes particularly during large-scale public health emergencies. Few studies have examined the impact of spatial differences in the microenvironment on the rehabilitation rate of patients with the Omicron variant infection. Objective: This study employs causal inference statistical methods and spatial analysis to investigate how the hospital microenvironment affects the rehabilitation of COVID-19 patients in a mobile cabin hospital, so as to provide a scientific basis for the spatial arrangement of patients in mobile cabin hospitals. Design: Observational study. Methods: This study used the clinical information of 6291 patients admitted in a mobile cabin hospital in Shanghai, from April 9 to May 9, 2022, during the pandemic. Exploratory spatial data analysis and fixed-effects regression analysis were conducted to understand whether the microenvironment around the patients’ beds in the cabin impacted their rehabilitation. Results: The results indicate that the rehabilitation condition of patients is affected by spatial differences of microenvironment. Both the mean and minimum CT values of the surrounding patients show a significant positive correlation with the rehabilitation of patients. The further the distance from the vent is, the more the rehabilitation speed of the patients is affected by the CT values of the surrounding patients. Conclusion: These findings offer valuable insights for bed allocation, patients’ stratification and management, and ventilation management in the mobile cabin hospitals during public health emergencies.

Smart ICU Bed Allocation System - SMARTS Predictive Analytics for Risk Profiling and Triaging COVID-19 Patients

Smart ICU Bed Allocation System - SMARTS Predictive Analytics for Risk Profiling and Triaging COVID-19 Patients

Effectiveness of Machine Learning for COVID-19 Patient Mortality Prediction Using WEKA

Timely detection of patients with a high mortality risk in coronavirus disease 2019 (COVID-19) can substantially improve triage, bed allocation, time reduction, and potential outcomes. A potential solution is using machine learning (ML) algorithms to predict mortality in COVID-19 hospitalized patients. The study's objective was to create and verify individual risk assessments for mortality using anonymous demographic, clinical, and laboratory findings at admission, as well as to assess the possibility of death using machine learning. We used a standardized format and electronic medical records. Data from 2,313 patients were collected from two Muhammadiyah hospitals from January 2020 to July 2022. Utilizing each patient's clinical manifestation state at admission and laboratory parameters, 24 demographic, clinical, and laboratory results were studied. The algorithms analyzed were AdaBoost, logistic regression, random forest, support vector machine, naïve Bayes, and decision tree, which were applied through WEKA version 3.8.6. Random forest performed better than the other machine learning techniques, with precision, sensitivity, receiver operating characteristic (ROC), and accuracy of 78.6%, 78.7%, 85%, and 78.65%, respectively. The three top predictors were septic shock (OR=21.518, 95% CI=4.933–93.853), respiratory failure (OR=15.503, 95% CI=8.507–28.254), and D-dimer (OR=3.288, 95% CI=2.510–4.306). Machine learning–based predictive models, especially the random forest algorithm, may make it easier to identify patients at high risk of death and guide physicians' appropriate interventions.

Multidrug-resistant organisms may be associated with bed allocation and utilization efficiency in healthcare institutions, based on national monitoring data from China (2014–2020)

Analyzing the influence of the bed allocation and utilization efficiency in healthcare institutions on the isolation proportion of Multidrug-resistant organisms (MDROs) to provide data to support prevention and control of MDROs. In this study, the provincial panel data from 2014 to 2020 in China on health resource indicators, including the number of beds per 1,000 population, hospital bed utilization rate, and average hospital stay from 2014 to 2020 in China were used to analyze the relationship between bed allocation or utilization efficiency and MDROs by the panel data quantile regression model. It was shown that the number of beds per 1,000 population had a negative effect on the isolation proportion of methicillin-resistant Staphylococcus aureus, vancomycin-resistant Enterococcus faecalis, vancomycin-resistant Enterococcus faecium, penicillin-resistant Streptococcus pneumoniae, methicillin-resistant coagulase-negative Staphylococcus, and cefotaxime or ceftriaxone resistant Escherichia coli (regression coefficient < 0, P < 0.05). The utilization rate of hospital bed had a positive effect on the isolation proportion of methicillin-resistant Staphylococcus aureus, methicillin-resistant coagulase-negative Staphylococcus, vancomycin-resistant Enterococcus faecium, penicillin-resistant Streptococcus pneumoniae, cefotaxime or ceftriaxone resistant Escherichia coli, carbapenem-resistant Escherichia coli, cefotaxime or ceftriaxone resistant Klebsiella pneumoniae, carbapenem-resistant Klebsiella pneumoniae, carbapenem-resistant Pseudomonas aeruginosa, and carbapenem-resistant Acinetobacter baumannii (regression coefficient > 0, P < 0.05). The average hospital stay had a positive effect on the isolation proportion for several antibiotic-resistant organisms, including methicillin-resistant Staphylococcus aureus, methicillin-resistant coagulase-negative Staphylococcus, vancomycin-resistant Enterococcus faecalis, vancomycin-resistant Enterococcus faecium, penicillin-resistant Streptococcus pneumoniae, cefotaxime or ceftriaxone resistant Escherichia coli, carbapenem-resistant Escherichia coli, quinolone-resistant Escherichia coli, cefotaxime or ceftriaxone resistant Klebsiella pneumoniae, carbapenem-resistant Pseudomonas aeruginosa, and carbapenem-resistant Acinetobacter baumannii (regression coefficient > 0, P < 0.05). Bed allocation and utilization efficiency in healthcare institutions may affect the isolation proportion of MDROs in varying degrees.

Application of TTC and TTAS Mechanisms in Bed Allocation Problem in Chinese Universities

Dormitory beds are assigned to students at random in China each year. However, a big majority of students are dissatisfied with their results, which will have an impact on their academic performance. The goal of this paper is to help students choose a suitable bed by using an algorithm after the initial allocation. This research constructs a bed allocation model and firstly employ the top trading cycles algorithm, which fulfills individual rationality, Pareto-efficiency, and strategy-proofness. Notwithstanding, this paper finds that the chance of indifferences cannot be precluded, despite the fact that this article let students rank beds as indicated by their inclinations for rooms and beds. Subsequently, the top trading cycles algorithm is ineffectual for this issue. The top trading absorbing sets algorithm is then applied to the general domain to create individual rationally, Pareto-efficient, and strategy-proof matching. This paper finds that the top trading absorbing sets algorithm is a suitable solution for bed allocation problem in Chinese universities and suggests universities to apply this algorithm after randomly allocating beds to freshmen to enhance the satisfaction of students.

Disparity in hospital beds’ allocation at the county level in China: an analysis based on a Health Resource Density Index (HRDI) model

BackgroundAs approximately 3/4 of the population lives in county-level divisions in China, the allocation of health resources at the county level will affect the realization of health equity. This study aims to evaluate the disparity in hospital beds at the county level in China, analyze its causes, and discuss measures to optimize the allocation.MethodsData were drawn from the Chinese County/City Statistical Yearbook (2001–2020). The health resource density index (HRDI) was applied to mediate between the influence of demographic and geographical factors on the allocation of hospital beds. The trends of HRDI allocation were evaluated through the growth incidence curve and the probability density function. The regional disparity in the HRDI was examined through the Lorenz curve, and Dagum Gini coefficient. The contribution of the Gini coefficient and its change were assessed by using the Dagum Gini decomposition method.ResultsFrom 2000 to 2019, the number of hospital beds per thousand people at the county level in China increased dramatically by 1.49 times. From the aspect of the HRDI, there were large regional disparities at the national level, with a Gini coefficient of 0.367 in 2019 and in the three subregions. In 2019, the Gini coefficient of the HRDI exhibited regional variations, with the highest value observed in the western region, followed by the central region and the eastern region. Decomposition reveals that the contribution of interregional disparity changed from the dominant factor to the least important factor, accounting for 29.79% of the overall disparity and the contribution of trans-variation intensity increased from 29.19% to 39.75%, whereas the intraregional disparity remained stable at approximately 31% and became the second most important factor.ConclusionThe regional disparity in hospital beds allocation at the county level in China was large and has not improved substantially. Trans-variation intensity was the main reason for the overall disparity and changes, and the intraregional disparity was more important than the interregional disparity for the overall disparity.

INVESTIGATION INTO THE ORGANIZATION OF MEDICAL CARE PROVISION IN CARDIOVASCULAR SURGERY DURING MARTIAL LAW

The aim of this study is to examine the organization of cardio-surgical medical care during martial law for offering qualified medical assistance to servicemen classified as temporary casualties, through bed allocation planning and bed-day calculation. Materials and methods: This research encompassed military personnel actively engaged in combat operations (n=473), with an average age of 44.1±2.2. The primary data source for analysis was the foundational medical records, including medical histories and initial medical records. Results. The article presents the results of the analysis of the needs aimed at providing a cardiac surgery hospital with an adequate number of inpatient beds and substantiates the duration of treatment - inpatient stay (bed days). Determining these factors holds exceptional importance as it facilitates the delivery of high-quality specialized treatment to the ill and/or injured, ensuring their timely rehabilitation and return to active duty within the Armed Forces of Ukraine. It was observed that the study groups exhibited no significant distinctions in terms of nosological categories of circulatory system diseases, average age, and the number of bed-days, with no statistical significance identified. The analysis revealed that during the full-scale invasion of the Russian Federation into Ukraine's territory in 2022, the demand for cardiac surgery hospital beds surged by 266.3% when compared to the 2014 bed capacity. Notably, the number of bed-days saw only a modest 6.3% increase during inpatient treatment for servicemen. Conclusions. The study has shown that the number of bed days did not increase significantly in the inpatient treatment of military personnel, only by 6.3%. Due to the increase in the number of patients/wounded, the State Institution "Amosov National Institute of Cardiovascular Surgery of the National Academy of Medical Sciences of Ukraine" opened a Military Cardiac and Major Vessel Surgery Department. This department specializes in providing highly specialized medical care to servicemen with combat-related heart injuries, major vessel wounds, and chest trauma.

Two-stage multi-objective optimization for ICU bed allocation under multiple sources of uncertainty

Due to the impact of COVID-19, a significant influx of emergency patients inundated the intensive care unit (ICU), and as a result, the treatment of elective patients was postponed or even cancelled. This paper studies ICU bed allocation for three categories of patients (emergency, elective, and current ICU patients). A two-stage model and an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II) are used to obtain ICU bed allocation. In the first stage, bed allocation is examined under uncertainties regarding the number of emergency patients and their length of stay (LOS). In the second stage, in addition to including the emergency patients with uncertainties in the first stage, it also considers uncertainty in the LOS of elective and current ICU patients. The two-stage model aims to minimize the number of required ICU beds and maximize resource utilization while ensuring the admission of the maximum number of patients. To evaluate the effectiveness of the model and algorithm, the improved NSGA-II was compared with two other methods: multi-objective simulated annealing (MOSA) and multi-objective Tabu search (MOTS). Drawing on data from real cases at a hospital in Lyon, France, the NSGA-II, while catering to patient requirements, saves 9.8% and 5.1% of ICU beds compared to MOSA and MOTS. In five different scenarios, comparing these two algorithms, NSGA-II achieved average improvements of 0%, 49%, 11.4%, 9.5%, and 17.1% across the five objectives.

Predicting COVID-19 Hospital Stays with Kolmogorov–Gabor Polynomials: Charting the Future of Care

Optimal allocation of ward beds is crucial given the respiratory nature of COVID-19, which necessitates urgent hospitalization for certain patients. Several governments have leveraged technology to mitigate the pandemic’s adverse impacts. Based on clinical and demographic variables assessed upon admission, this study predicts the length of stay (LOS) for COVID-19 patients in hospitals. The Kolmogorov–Gabor polynomial (a.k.a., Volterra functional series) was trained using regularized least squares and validated on a dataset of 1600 COVID-19 patients admitted to Khorshid Hospital in the central province of Iran, and the five-fold internal cross-validated results were presented. The Volterra method provides flexibility, interactions among variables, and robustness. The most important features of the LOS prediction system were inflammatory markers, bicarbonate (HCO3), and fever—the adj. R2 and Concordance Correlation Coefficients were 0.81 [95% CI: 0.79–0.84] and 0.94 [0.93–0.95], respectively. The estimation bias was not statistically significant (p-value = 0.777; paired-sample t-test). The system was further analyzed to predict “normal” LOS ≤ 7 days versus “prolonged” LOS &gt; 7 days groups. It showed excellent balanced diagnostic accuracy and agreement rate. However, temporal and spatial validation must be considered to generalize the model. This contribution is hoped to pave the way for hospitals and healthcare providers to manage their resources better.

Relative bed allocation for COVID-19 patients, EHR investments, and COVID-19 mortality outcomes.

Managing flexibility in the relative bed allocation for COVID-19 and non-COVID-19 patients was a key challenge for hospitals during the COVID-19 pandemic. Based on organizational information processing theory (OIPT), we propose that the local electronic health record (EHR) systems could improve patient outcomes through improved bed allocation in the local area. In an empirical analysis of county-level weekly hospital data in the US, relative capacity of beds in hospitals with higher EHR was associated with lower 7-, 14-, and 21-day forward-looking COVID-19 death rate at the county-level. Testing for cross-state variation in non-pharmaceutical interventions along contiguous county border-pair analysis to control for spatial correlation varying between state variations in non-pharmaceutical intervention policies, 2SLS analysis using quality ratings, and using foot-traffic data at the US hospitals our findings are generally supported. The findings have implications for policymakers and stakeholders of the local healthcare supply chains and EHR systems.

Hospital Bed Allocation using Three-Stage Weighted Optimization Method for Government Hospital in Pulau Pinang

Ineffective bed allocation across hospital departments leads to the imbalance between patients’ needs and resource capacity. This study aims to simulate patients’ arrivals, to measure the departments’ importance and to design a mathematical model for allocating beds which will be realized by the proposed three-stage weighted optimization model. The stages consist of data simulation in ARENA software, weight evaluation based on bed occupancy rate patients’ arrival rates, bed occupancy rate (BOR), patients’ average length of stay (ALOS) and bed operation cost (BOC), and weighted optimization using goal programming (GP) model. The goals to be achieved in this study consists of minimizing the idle beds in departments and the hospital and minimizing the total BOC. The result of the study shows that obstetrics and orthopaedics wards obtained the biggest number of beds while dengue and paediatrics surgery wards obtained the least number. The statistical analysis made to the results shows that patients’ arrival rate is the most influential factor in allocating the beds as its Pearson correlation value to the bed numbers is 0.789, which indicates strong correlation.

Allocation of hospital beds on the emergence of new infectious disease: A mathematical model.

This paper is concerned to a mathematical model for the management of hospital beds when a new infection emerges in the population with the existing infections. The study of this joint dynamics presents formidable mathematical challenges due to a limited number of hospital beds. We have derived the invasion reproduction number, which investigates the potential of a newly emerged infectious disease to persist when some infectious diseases are already invaded the host population. We have shown that the proposed system exhibits transcritical, saddle-node, Hopf, and Bogdanov-Takens bifurcations under certain conditions. We have also shown that the total number of infected individuals may increase if the fraction of the total number of hospital beds is not properly allotted to the existing and a newly emerged infectious disease. The analytically obtained results are verified with the help of numerical simulations.

A Study Of Bed Occupancy Management In The Healthcare System Using The M/M/C Queue And Probability

Many diverse healthcare systems, including hospitals, laboratories, pharmaceutical business, radiology, organ transplant etc. have been modelled and studied using queuing models. Due to their analytical nature and capacity for speedy resolution, queueing models are well-liked by researchers and system designers and can offer reasonably accurate assessments of system performance. The problem of allocating the ideal number of beds to different wards, as well as assigning roles to doctors in various hospital wards and outside the hospital, is one that health care management is now dealing with. In this paper, we will use (M/M/C) queue to explore bed occupancy management, patient movement, and ideal bed counts in hospitals. Additionally, we will look for the probability that a patient will be chosen for a bed allocation and the expected occupancy rates for a specific time frame.

RV4JaCa—Towards Runtime Verification of Multi-Agent Systems and Robotic Applications

This paper presents a Runtime Verification (RV) approach for Multi-Agent Systems (MAS) using the JaCaMo framework. Our objective is to bring a layer of security to the MAS. This is achieved keeping in mind possible safety-critical uses of the MAS, such as robotic applications. This layer is capable of controlling events during the execution of the system without needing a specific implementation in the behaviour of each agent to recognise the events. In this paper, we mainly focus on MAS when used in the context of hybrid intelligence. This use requires communication between software agents and human beings. In some cases, communication takes place via natural language dialogues. However, this kind of communication brings us to a concern related to controlling the flow of dialogue so that agents can prevent any change in the topic of discussion that could impair their reasoning. The latter may be a problem and undermine the development of the software agents. In this paper, we tackle this problem by proposing and demonstrating the implementation of a framework that aims to control the dialogue flow in a MAS; especially when the MAS communicates with the user through natural language to aid decision-making in a hospital bed allocation scenario.

Health resource allocation in Western China from 2014 to 2018

BackgroundHealth equity has persistently been a global concern. How to fairly and appropriately allocate health resources is a research hotspot. While Western China is relatively backward economically and presents difficulties for the allocation of health resources, little attention has been given to the equity of resource allocation there. This study analysed the equity of allocation of beds, physicians and nurses in Western China from 2014-2018 to provide targeted guidance for improving the equity of health resource allocation.MethodsData for 2014-2018 obtained from the Statistical Yearbook (2015-2019) of provinces (autonomous regions and municipalities) were used to analyse health resource allocation in terms of beds, physicians and nurses in Western China. The Lorenz curve and Gini coefficient were calculated to evaluate equity in the population dimension and geographic dimension. The Theil index was used to measure the inequity of the three indicators between minority and nonminority areas.ResultsThe number of beds, physicians and nurses in Western China showed an increasing trend from 2014-2018. The Lorenz curve had a smaller curvature in the population dimension than in the geographic dimension. The Gini coefficients for health resources in the population dimension ranged from 0.044 to 0.079, and in the geographic dimension, the Gini coefficients ranged between 0.614 and 0.647. The above results showed that the equity of health resource allocation was better in the population dimension than in the geographic dimension. The Theil index ranged from 0.000 to 0.004 in the population dimension and from 0.095 to 0.326 in the geographic dimension, indicating that the inequity in health resource allocation was higher in the geographic dimension. The intergroup contribution ratios of the Theil index in both the population and geographic dimensions were greater than 60%, indicating that the inequity in resource allocation was mainly caused by intergroup differences, namely, the allocation of health resources within the province. Among them, the inequity of physicians and nurses allocation was the most obvious.ConclusionsFrom 2014 to 2018, the total amount of health resources have improved in Western China. However, health resource allocation in Western China was still inequitable in the population and geographic dimensions, and the inequity of health resource allocation in the geographic dimension showed a tendency to worsen. Meanwhile, although the inequity of human recourse allocation was alleviated in 2018 compare with 2014, the inequity of human resource distribution within provinces was still obvious. The government can increase the number of health resources and improve the accessibility of health resources by increasing financial investment, strengthening humanistic care for health workers, and establishing internet hospitals.