Interest in the field of performance assessment of health care structures has grown in recent decades. In fact, the possibility of determining overall performances of health care structures plays a key role in the optimization of resource allocation and investment planning, as it contributes to reducing the uncertainty of future performance. In this context, key performance indicator (KPI) tools have been developed to assess the performance of health care structures from process, organizational, cost, financial, and output points of view. In practice, they are periodically calculated, and the effect of several KPIs on the overall performance of health care structures is determined by management through human judgment or software that provides synthetic dashboards. Given their non-stationary nature, performance assessment and forecasting are generally tackled by employing adaptive models, but these approaches cannot reflect the holistic nature of performance itself, nor take into account the impact of KPIs on the overall performances. In order to overcome these shortcomings, this study presents an expert system whose engine relies on fuzzy sets, in which the input-output relations and correlations have been modeled through inference rules based on time-series trends. The focus is on the financial performance assessment of a health care structure, such as a hospital. The approach is of an interdisciplinary kind, as several indicators were taken as inputs that relate to output, process, and cost KPIs, and their impact on the output measure, which is of a financial kind (namely the total reimbursement). The output measure calculated by the expert system was then compared with that predicted using only adaptive forecasting models, and the error with respect to the actual value was determined. Results showed that measures determined by fuzzy inference, able to effectively model actual input-output relations, outperform those of adaptive models.

Interest in the field of performance assessment of health care structures has grown in recent decades. In fact, the possibility of determining overall performances of health care structures plays a key role in the optimization of resource allocation and investment planning, as it contributes to reducing the uncertainty of future performance. In this context, key performance indicator (KPI) tools have been developed to assess the performance of health care structures from process, organizational, cost, financial, and output points of view. In practice, they are periodically calculated, and the effect of several KPIs on the overall performance of health care structures is determined by management through human judgment or software that provides synthetic dashboards. Given their non-stationary nature, performance assessment and forecasting are generally tackled by employing adaptive models, but these approaches cannot reflect the holistic nature of performance itself, nor take into account the impact of KPIs on the overall performances. In order to overcome these shortcomings, this study presents an expert system whose engine relies on fuzzy sets, in which the input-output relations and correlations have been modeled through inference rules based on time-series trends. The focus is on the financial performance assessment of a health care structure, such as a hospital. The approach is of an interdisciplinary kind, as several indicators were taken as inputs that relate to output, process, and cost KPIs, and their impact on the output measure, which is of a financial kind (namely the total reimbursement). The output measure calculated by the expert system was then compared with that predicted using only adaptive forecasting models, and the error with respect to the actual value was determined. Results showed that measures determined by fuzzy inference, able to effectively model actual input-output relations, outperform those of adaptive models. (C) 2016 Elsevier B.V. All rights reserved.

An expert system for financial performance assessment of health care structures based on fuzzy sets and KPIs

Piazza, Tommaso;
2016-01-01

Abstract

Interest in the field of performance assessment of health care structures has grown in recent decades. In fact, the possibility of determining overall performances of health care structures plays a key role in the optimization of resource allocation and investment planning, as it contributes to reducing the uncertainty of future performance. In this context, key performance indicator (KPI) tools have been developed to assess the performance of health care structures from process, organizational, cost, financial, and output points of view. In practice, they are periodically calculated, and the effect of several KPIs on the overall performance of health care structures is determined by management through human judgment or software that provides synthetic dashboards. Given their non-stationary nature, performance assessment and forecasting are generally tackled by employing adaptive models, but these approaches cannot reflect the holistic nature of performance itself, nor take into account the impact of KPIs on the overall performances. In order to overcome these shortcomings, this study presents an expert system whose engine relies on fuzzy sets, in which the input-output relations and correlations have been modeled through inference rules based on time-series trends. The focus is on the financial performance assessment of a health care structure, such as a hospital. The approach is of an interdisciplinary kind, as several indicators were taken as inputs that relate to output, process, and cost KPIs, and their impact on the output measure, which is of a financial kind (namely the total reimbursement). The output measure calculated by the expert system was then compared with that predicted using only adaptive forecasting models, and the error with respect to the actual value was determined. Results showed that measures determined by fuzzy inference, able to effectively model actual input-output relations, outperform those of adaptive models.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10278/3707962
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 19
  • ???jsp.display-item.citation.isi??? 15
social impact