Does regional belonging explain the similarities in the expenditure determinants of Italian healthcare deliveries? An approach based on Artificial Neural Networks (original) (raw)
Related papers
Economic Analysis and Policy, 2017
The investigation of the determinants of public health expenditure is the focus of a vivid debate among health economists whereas the actual crisis of the welfare systems calls for the adoption of innovative tools to inform rational decisions, in the light of stringent budget constraints. The purpose of this paper is to show the potentialities of Artificial Neural Networks (ANNs) in investigating whether healthcare providers belonging to the same jurisdiction show similarities in their health care expenditure determinants. Similarities are reproduced in terms of fuzzy dependencies between health budgetary data of the healthcare providers belonging to five Italian regions. The analysis carried out sees the application of Auto Contractive Maps (AutoCM) model. The methodology is effective in illustrating regional patterns of expenditure and similarities across Local Health Units (Aziende Sanitarie Locali-ASLs). The results give interesting insights on the presence of notable regional models for health expenditure.
Since 1992 the Italian local health units (LHU) gained financial independence and became responsible to provide and deliver health care at the local level. Management and financial accounting represent the tool utilized to monitor their net income and the working capital every year. From 2001 on, LHU budget data have being summarized by means of the ''income statement''. The income statement is considered the most relevant form for the monitoring of healthcare expenditures. A big amount of data have been collected after that obligation of publishing the income statement. The application of new methods for a better understanding of relationships among variables would be worthwhile. The development of artificial neural networks (ANNs) can represent a useful tool to analyze the relationships among these variables. The purpose of this paper is showing the potentialities of ANNs and especially of artificial neural networks what-if theory (AWIT) model when applied to health budgetary data. This innovative methodology has been employed, in the present paper, to analyze data from five Italian Regions, carrying out some comparison among them. In short, using one dataset that is defined as being the ideal standard containing the relationships necessary to measure desired outcomes, another dataset can be compared to determine its degree of closeness. We can determine the degree of closeness of the second or treated dataset with the original standard. This is the key concept of the method called AWIT. The descriptive analysis carried out outlines the areas of waste LHU and suggests to develop strategies to contrast an inefficient use of resources.
BMC Health Services Research
Background: After 2008 global economic crisis, Italian governments progressively reduced public healthcare financing. Describing the time trend of health outcomes and health expenditure may be helpful for policy makers during the resources' allocation decision making process. The aim of this paper is to analyze the trend of mortality and health spending in Italy and to investigate their correlation in consideration of the funding constraints experienced by the Italian national health system (SSN). Methods: We conducted a 20-year time-series study. Secondary data has been extracted from a national, institution based and publicly accessible retrospective database periodically released by the Italian Institute of Statistics. Age standardized all-cause mortality rate (MR) and health spending (Directly Provided Services-DPS, Agreed-Upon Services-TAUS, and private expenditure) were reviewed. Time trend analysis (1995-2014) through OLS and Multilayer Feed-forward Neural Networks (MFNN) models to forecast mortality and spending trend was performed. The association between healthcare expenditure and MR was analyzed through a fixed effect regression model. We then repeated MFNN time trend forecasting analyses on mortality by adding the spending item resulted significantly related with MR in the fixed effect analyses. Results: DPS and TAUS decreased since 2011. There was a mismatch in mortality rates between real and predicted values. DPS resulted significantly associated to mortality (p < 0.05). In repeated mortality forecasting analysis, predicted MR was found to be lower when considering the pre-constraints health spending trend. Conclusions: Between 2011 and 2014, Italian public health spending items showed a reduction when compared to prior years. Spending on services directly provided free of charge appears to be the financial driving force of the Italian public health system. The overall mortality was found to be higher than the predicted trend and this scenario may be partially attributable to the healthcare funding constraints experienced by the SSN.
Modeling Public Health Care Expenditure Using Patient Level Data: Empirical Evidence from Italy
SSRN Electronic Journal, 2016
In this work we present some results obtained with a unique database of patient level data collected through GPs. The availability of such data opens new scenarios and paradigms for the planning and management of the health care system and for policy impact evaluation studies. The dataset, representative of the Italian population, contains detailed information on prescribed drugs, laboratory tests, outpatient visits and hospitalizations of more than 2 millions patients, managed by 900 GPs overtime. This pool of registers has produced a stock of information on about 25 millions of medical diagnosis, 100 millions of laboratory and diagnostic tests, 10 millions of blood pressure measurements and 50 millions of drug prescriptions. Using this novel dataset we analyze the expenditures of the Italian NHS over time, across age and geographical areas for the period from 2004 to 2011.
A case-mix classification system for explaining healthcare costs using administrative data in Italy
European journal of internal medicine, 2018
The Italian National Health Service (NHS) provides universal coverage to all citizens, granting primary and hospital care with a copayment system for outpatient and drug services. Financing of Local Health Trusts (LHTs) is based on a capitation system adjusted only for age, gender and area of residence. We applied a risk-adjustment system (Johns Hopkins Adjusted Clinical Groups System, ACG® System) in order to explain health care costs using routinely collected administrative data in the Veneto Region (North-eastern Italy). All residents in the Veneto Region were included in the study. The ACG system was applied to classify the regional population based on the following information sources for the year 2015: Hospital Discharges, Emergency Room visits, Chronic disease registry for copayment exemptions, ambulatory visits, medications, the Home care database, and drug prescriptions. Simple linear regressions were used to contrast an age-gender model to models incorporating more compreh...
Health Care in Italy: Expenditure Determinants and Regional Differentials
2010
The aim of this work is to identify the determinants of health spending differentials among Italian regions, which could highlight the existence of potential margins for savings. The analysis exploits a dataset for the panel of the 21 Italian regions starting in the early 1990s and ending in 2006. After having controlled for standard healthcare demand indicators, spending differentials appear to be associated with differences in the degree of appropriateness of the treatments, supply structure and social capital indicators. These results suggest that savings could be achieved without reducing the amount of services supplied to citizens. This is particularly important in view of the expected rise in health spending associated with the forecast demographic developments.
Spatial effects in hospital expenditures: A district level analysis
Health Economics, 2017
Geographical clusters in health expenditures are well documented and accounting for spatial interactions may contribute to properly identify the factors affecting the use of health services the most. As for hospital care, spillovers may derive from strategic behaviour of hospitals and from patients' preferences that may induce mobility across jurisdictions, as well as from geographically-concentrated risk factors, knowledge transfer and interactions between different layers of care. Our paper focuses on a largely overlooked potential source of spillovers in hospital expenditure: the heterogeneity of primary care providers' behaviour. To do so, we analyse expenditures associated to avoidable hospitalisations separately from expenditures for highly complex treatments, as the former are most likely affected by General Practitioners, while the latter are not. We use administrative data for Italy's Region Emilia Romagna between 2007 and 2010. Since neighbouring districts may belong to different Local Health Authorities (LHAs), we employ a spatial contiguity matrix that allows to investigate the effects of geographical and institutional proximity and use it to estimate Spatial Autoregressive and Spatial Durbin Models.
The Socio-Economic Determinants of the Number of Physicians in Italian Regions
SSRN Electronic Journal
In the following article, we analyse the determinants of the number of physicians in the context of ISTAT BES-Benessere Equo Sostenibile data among twenty Italian regions in the period 2004-2022. We apply Panel Data with Random Effects, Panel Data with Fixed Effects, and Pooled OLS-Ordinary Least Squares. We found that the number of Physicians among Italian regions is positively associated, among others, to "Trust in the Police and Firefighters", "Net Income Inequality", and negatively associated, among others, to "Research and Development Intensity" and "Soil waterproofing by artificial cover". Furthermore, we apply the k-Means algorithm optimized with the Silhouette Coefficient and we find the presence of two clusters. Finally, we confront eight different machinelearning algorithms to predict the future value of physicians and we find that the PNN-Probabilistic Neural Network is the best predictive algorithm.
Use of artificial neural networks in applying methodology for allocating health resources
Revista de saúde pública, 2013
To describe the construction of a factor of allocation of financial resources, based on the population's health needs. Quantitative study with data collected from public databases referring to the state of Pernambuco, Northeastern Brazil, between 2000 and 2010. Variables which reflected epidemiological, demographic, socio-economic and educational processes were selected in order to create a factor of allocation which highlighted the health needs of the population. The data sources were: SUS (Brazilian Unified Health System) Department of Computer Science, Atlas of Human Development in Brazil, IBGE (Brazilian Institute of Geography and Statistics), Information System on Public Health Budgets, National Treasury and data from the Pernambuco Health Secretariat between 2000 and 2010. Pearson's coefficient was used to assess linear correlation and the factor of allocation was calculated using analysis by artificial neural networks. The quartiles of the municipalities were defined ...