Implementation and validation of a new method to model voluntary departures from emergency departments. Running Title: Modeling Voluntary departures from emergency departments

Combining simulation models and machine learning in healthcare management: strategies and applications

Simulation models and artificial intelligence (AI) are largely used to address healthcare and biomedical engineering problems. Both approaches showed promising results in the analysis and optimization of healthcare processes. Therefore, the combination of simulation models and AI could provide a strategy to further boost the quality of health services. In this work, a systematic review of studies applying a hybrid simulation models and AI approach to address healthcare management challenges was carried out. Scopus, Web of Science, and PubMed databases were screened by independent reviewers. The main strategies to combine simulation and AI as well as the major healthcare application scenarios were identified and discussed. Moreover, tools and algorithms to implement the proposed approaches were described. Results showed that machine learning appears to be the most employed AI strategy in combination with simulation models, which mainly rely on agent-based and discrete-event systems. The scarcity and heterogeneity of the included studies suggested that a standardized framework to implement hybrid machine learning-simulation approaches in healthcare management is yet to be defined. Future efforts should aim to use these approaches to design novel intelligentin-silicomodels of healthcare processes and to provide effective translation to the clinics.

A Hybrid Analytic Hierarchy Process and Likert Scale Approach for the Quality Assessment of Medical Education Programs

The quality assessment of training courses is of utmost importance in the medical education field to improve the quality of the training. This work proposes a hybrid multicriteria decision-making approach based on two methodologies, a Likert scale (LS) and the analytic hierarchy process (AHP), for the quality assessment of medical education programs. On one hand, the qualitative LS method was adopted to estimate the degree of consensus on specific topics; on the other hand, the quantitative AHP technique was employed to prioritize parameters involved in complex decision-making problems. The approach was validated in a real scenario for evaluating healthcare training activities carried out at the Centre of Biotechnology of the National Hospital A.O.R.N. “A. Cardarelli” of Naples (Italy). The rational combination of the two methodologies proved to be a promising decision-making tool for decision makers to identify those aspects of a medical education program characterized by a lower user satisfaction degree (revealed by the LS) and a higher priority degree (revealed by the AHP), potentially suggesting strategies to increase the quality of the service provided and to reduce the waste of resources. The results show how this hybrid approach can provide decision makers with helpful information to select the most important characteristics of the delivered education program and to possibly improve the weakest ones, thus enhancing the whole quality of the training courses.

Machine Learning and Regression Analysis to Model the Length of Hospital Stay in Patients with Femur Fracture

Fractures of the femur are a frequent problem in elderly people, and it has been demonstrated that treating them with a diagnostic–therapeutic–assistance path within 48 h of admission to the hospital reduces complications and shortens the length of the hospital stay (LOS). In this paper, the preoperative data of 1082 patients were used to further extend the previous research and to generate several models that are capable of predicting the overall LOS: First, the LOS, measured in days, was predicted through a regression analysis; then, it was grouped by weeks and was predicted with a classification analysis. The KNIME analytics platform was applied to divide the dataset for a hold-out cross-validation, perform a multiple linear regression and implement machine learning algorithms. The best coefficient of determination (R²) was achieved by the support vector machine (R² = 0.617), while the mean absolute error was similar for all the algorithms, ranging between 2.00 and 2.11 days. With regard to the classification analysis, all the algorithms surpassed 80% accuracy, and the most accurate algorithm was the radial basis function network, at 83.5%. The use of these techniques could be a valuable support tool for doctors to better manage orthopaedic departments and all their resources, which would reduce both waste and costs in the context of healthcare.

Efficiency measures of emergency departments: an Italian systematic literature review

Life expectancy globally increased in the last decades: the number of people aged 65 or older is consequently projected to grow, and healthcare demand will increase as well. In the recent years, the number of patients visiting the hospital emergency departments (EDs) rocked in almost all countries of the world. These departments are crucial in all healthcare systems and play a critical role in providing an efficient assistance to all patients. A systematic literature review covering PubMed, Scopus and the Cochrane Library was performed from 2009 to 2019. Of the 718 references found in the literature research, more than 25 studies were included in the current review. Different predictors were associated with the quality of EDs care, which may help to define and implement preventive strategies in the near future. There is no harmonisation in efficiency measurements reflecting the performance in the ED setting. The identification of consistent measures of efficiency is crucial to build an evidence base for future initiatives. The aim of this study is to review the literature on the problems encountered in the efficiency of EDs around the world in order to identify an organisational model or guidelines that can be implemented in EDs to fill inefficiencies and ensure access optimal treatment both in terms of resources and timing. This review will support policy makers to improve the quality of health facilities, and, consequently of the entire healthcare systems.

Application of DMAIC Cycle and Modeling as Tools for Health Technology Assessment in a University Hospital

Background

The Health Technology Assessment (HTA) is used to evaluate health services, manage healthcare processes more efficiently, and compare medical technologies. The aim of this paper is to carry out an HTA study that compares two pharmacological therapies and provides the clinicians with two models to predict the length of hospital stay (LOS) of patients undergoing oral cavity cancer surgery on the bone tissue.

Methods

The six Sigma method was used as a tool of HTA; it is a technique of quality management and process improvement that combines the use of statistics with a five-step procedure: “Define, Measure, Analyze, Improve, Control” referred to in the acronym DMAIC. Subsequently, multiple linear regression has been used to create two models. Two groups of patients were analyzed: 45 were treated with ceftriaxone while 48 were treated with the combination of cefazolin and clindamycin.

Results

A reduction of the overall mean LOS of patients undergoing oral cavity cancer surgery on bone was observed of 40.9% in the group treated with ceftriaxone. Its reduction was observed in all the variables of the ceftriaxone group. The best results are obtained in younger patients (−54.1%) and in patients with low oral hygiene (−52.4%) treated. The regression results showed that the best LOS predictors for cefazolin/clindamycin are ASA score and flap while for ceftriaxone, in addition to these two, oral hygiene and lymphadenectomy are the best predictors. In addition, the adjusted R squared showed that the variables considered explain most of the variance of LOS.

Conclusion

SS methodology, used as an HTA tool, allowed us to understand the performance of the antibiotics and provided variables that mostly influence postoperative LOS. The obtained models can improve the outcome of patients, reducing the postoperative LOS and the relative costs, consequently increasing patient safety, and improving the quality of care provided.

A Hybrid Genetic Algorithm for Nurse Scheduling Problem considering the Fatigue Factor

Nowadays and due to the pandemic of COVID-19, nurses are working under the highest pressure benevolently all over the world. This urgent situation can cause more fatigue for nurses who are responsible for taking care of COVID-19 patients 24 hours a day. Therefore, nurse scheduling should be modified with respect to this new situation. The purpose of the present research is to propose a new mathematical model for Nurse Scheduling Problem (NSP) considering the fatigue factor. To solve the proposed model, a hybrid Genetic Algorithm (GA) has been developed to provide a nurse schedule for all three shifts of a day. To validate the proposed approach, a randomly generated problem has been solved. In addition, to show the applicability of the proposed approach in real situations, the model has been solved for a real case study, a department in one of the hospitals in Esfahan, Iran, where COVID-19 patients are hospitalized. Consequently, a nurse schedule for May has been provided applying the proposed model, and the results approve its superiority in comparison with the manual schedule that is currently used in the department. To the best of our knowledge, it is the first study in which the proposed model takes the fatigue of nurses into account and provides a schedule based on it.

Lean Six Sigma Approach for Reducing Length of Hospital Stay for Patients with Femur Fracture in a University Hospital

Surgical intervention within 48 h of hospital admission is the gold standard procedure for the management of elderly patients with femur fractures, since the increase in preoperative waiting time is correlated with the onset of complications and longer overall length of stay (LOS) in the hospital. However, national evidence demonstrates that there is still the need to provide timely intervention for this type of patient, especially in some regions of central southern Italy. Here we discuss the introduction of a diagnostic–therapeutic assistance pathway (DTAP) to reduce the preoperative LOS for patients undergoing femur fracture surgery in a university hospital. A Lean Six Sigma methodology, based on the DMAIC cycle (Define, Measure, Analyze, Improve, Control), is implemented to evaluate the effectiveness of the DTAP. Data were retrospectively collected and analyzed from two groups of patients before and after the implementation of DTAP over a period of 10 years. The statistics of the process measured before the DTAP showed an average preoperative LOS of 5.6 days (standard deviation of 3.2), thus confirming the need for corrective actions to reduce the LOS in compliance with the national guidelines. The influence of demographic and anamnestic variables on the LOS was evaluated, and the impact of the DTAP was measured and discussed, demonstrating the effectiveness of the improvement actions implemented over the years and leading to a significant reduction in the preoperative LOS, which decreased to an average of 3.5 days (standard deviation of 3.60). The obtained reduction of 39% in the average LOS proved to be in good agreement with previously developed DTAPs for femur fracture available in the literature.