Integration of Machine Learning Algorithms and Discrete-Event Simulation for the Cost of Healthcare Resources.

A healthcare resource allocation generally plays a vital role in the number of patients treated (pnt) and the patient waiting time (wt) in healthcare institutions. This study aimed to estimate pnt and wt as output variables by considering the number of healthcare resources employed and analyze the cost of health resources to the hospital depending on the cost coefficient (δi) in an emergency department (ED). The integration of the discrete-event simulation (DES) model and machine learning (ML) algorithms, namely random forest (RF), gradient boosting (GB), and AdaBoost (AB), was used to calculate the estimation of the output variables depending on the δi of resources cost. The AB algorithm performed best in almost all scenarios based on the results of the analysis. According to the AB algorithm based on the δ0.0, δ0.1, δ0.2, and δ0.3, the accuracy data were calculated as 0.9838, 0.9843, 0.9838, and 0.9846 for pnt; 0.9514, 0.9517, 0.9514, and 0.9514 for wt, respectively in the training stage. The GB algorithm had the best performance value, except for the results of the δ0.2 (AB had a better accuracy at 0.8709 based on the value of δ0.2 for pnt) in the test stage. According to the AB algorithm based on the δ0.0, δ0.1, δ0.2, and δ0.3, the accuracy data were calculated as 0.7956, 0.9298, 0.8288, and 0.7394 for pnt; 0.8820, 0.8821, 0.8819, and 0.8818 for wt in the training phase, respectively. All scenarios created by the δi coefficient should be preferred for ED since the income provided by the pnt value to the hospital was more than the cost of healthcare resources. On the contrary, the wt estimation results of ML algorithms based on the δi coefficient differed. Although wt values in all ML algorithms with δ0.0 and δ0.1 coefficients reduced the cost of the hospital, wt values based on δ0.2 and δ0.3 increased the cost of the hospital.

A cost analysis with the discrete-event simulation application in nurse and doctor employment management.

AIM: This study aimed to analyse the treatment cost of a patient, depending on the number of patients treated, patient waiting times, and the number of nurses and doctors employed in an emergency department of a private hospital. BACKGROUND: Within health systems, changes in health care resources can be very costly, especially if these changes are long-term. The discrete-event simulation method described in this paper allows for the monitoring and analysis of complicated changes in real systems by using computer-based modelling. METHOD: The discrete event simulation model was derived from nine scenarios according to the number of nurses and doctors, and a comparison was made between the results of the scenarios and the actual results. RESULTS: Among the scenarios, scenario 6 provided the lowest treatment cost for a patient by employing three doctors and two nurses with the best performance. The cost of treatment for a patient varies between t9.00 and t11.00 depending on the value of δ, and the daily cost of these resources to the hospital is t1300.77. CONCLUSIONS: This study provides a clear picture of a cost analysis comparison based on changes made about the actual health system in the computer-based simulated environment. IMPLICATIONS FOR NURSING MANAGEMENT: The workforce data of nurses and doctors offers enough detail for cost analysis in health care settings to calculate the cost of treatment for a patient.

Erratum to "Is the lockdown important to prevent the COVID-19 pandemic? Effects on psychology, environment and economy-perspective" [Ann. Med. Surg. 56 (2020) 38-42].

[This corrects the article DOI: 10.1016/j.amsu.2020.06.010.].

Desirability Optimization Models to Create the Global Healthcare Competitiveness Index.

The aim of this research is to enhance desirability optimization models to create a global healthcare competitiveness index (GHCI) covering 53 countries with gross domestic product per capita (GDP PC) of over $10,000. The GHCI is defined as an index that reveals the progress and quality of the healthcare systems in countries providing their patients with easier access opportunities to healthcare services within the scope of this work. Methods of statistical analysis have been adopted together with optimization models and techniques in this research. The optimum and feasible values of the factors considered influential on objective functions have been determined as the basis of healthcare expenditure (HE) and GHCI in those relevant countries. Those released optimum outcomes are displayed between 0.64 and 0.66 in terms of desirability value. The GHCI values of those aforementioned countries range from 0 to 6. The computed average of the GHCI values of those countries is estimated as 2.4758. Finally, GHCI values of 53 countries have been calculated to set the current basis of desirability optimization models. These findings will be deemed as the basic essence of those prospective theories to be established for the future researches to constitute a new index to measure the competitiveness of healthcare systems in various countries all over the world.

Is the lockdown important to prevent the COVID-19 pandemic? Effects on psychology, environment and economy-perspective.

COVID-19's daily increasing cases and deaths have led to worldwide lockdown, quarantine and some restrictions. This study aims to analyze the effect of lockdown days on the spread of coronavirus in countries. COVID-19 cases and lockdown days data were collected for 49 countries that implemented the lockdown between certain dates (without interruption). The correlation tests were used for data analysis based on unconstrained (normal) and constrained (Tukey-lambda). The lockdown days was significantly correlated with COVID-19 pandemic based on unconstrained (r = -0.9126, F-ratio = 6.1654; t-ratio = 2.40; prob > .0203 with 49 observations) and based on Tukey-lambda (r = 0.7402, λ = 0.14). The lockdown, one of the social isolation restrictions, has been observed to prevent the COVID-19 pandemic, and showed that the spread of the virus can be significantly reduced by this preventive restriction in this study. This study offers initial evidence that the COVID-19 pandemic can be suppressed by a lockdown. The application of lockdown by governments is also thought to be effective on psychology, environment and economy besides having impact on Covid-19.