1,721,148 research outputs found
Towards a real-time prediction of waiting times in emergency departments: A comparative analysis of machine learning techniques
No full textEmergency Departments (EDs) can better manage activities and resources and anticipate overcrowding through accurate estimations of waiting times. However, the complex nature of EDs imposes a challenge on waiting time prediction. In this paper, we test various machine learning techniques, using predictive analytics, applied to two large datasets from real EDs. We evaluate the predictive ability of Lasso, Random Forest, Support Vector Regression, Artificial Neural Network, and the Ensemble Method, using different error metrics and computational times. To improve the prediction accuracy, new queue-based variables, that capture the current state of the ED, are defined as additional predictors. The results show that the Ensemble Method is the most effective at predicting waiting times. In terms of both accuracy and computational efficiency, Random Forest is a reasonable trade-off. The results have significant practical implications for EDs and hospitals, suggesting that a real-time performance monitoring system that supports operational decision-making is possible
Organizzazione e cura Convegno Internazionale "L'Arco di Traiano a Benevento e gli archi trionfali romani: tra ideologia e propaganda - Benevento, 21-22 Febbraio 2020
No full textIl Convegno Internazionale "L'Arco di Traiano a Benevento e gli archi trionfali romani: tra ideologia e propaganda" ha inteso fare lo status quaestionis relativamente agli studi e alle ricerche sull'Arco di Benevento e sugli archi trionfali romani, che ebbero una grande importanza sul piano ideologico e propagandistico
How to Make Innovation With External Partners? The Conceptual Design of an ICT Platform Supporting the Inbound Open Innovation
No full textOver time, Open Innovation (OI) strategy was considered a “must” for many firms. While focusing specifically on the inbound OI process, the literature has put in evidence that ICT has much to contribute; in fact, it can foster activities, such as communication, cooperation, knowledge sharing and creation among different actors. The empirical evidence shows that platforms have exponentially grown during the last years. However, on closer view, existing platforms support only specific OI phases or sub-processes, but not the process in its own entirety.
Conversely, the scientific debate, although recognizing that ICTs can enable the entire inbound process and although analyzing the existing platforms, has rather disregarded the way firms can support the whole OI inbound process by means of ICT. Also, to our best knowledge, literature does not offer any contribution regarding a systematic design (specifically a conceptual design) of such an ICT platform.
Hence, the objective of this paper is to develop the conceptual design of an ICT platform supporting the inbound Open Innovation process within the Technological Developments business unit of Leonardo Defense Systems Division.
After a preliminary phase concerning the context analysis, methodology includes three main steps: (i) conceptualization of functions; (ii) preliminary design; (iii) conceptual design of the System/SW architecture. In each of these phases, we tried to merge evidence from the scientific literature with empirical insight emerging from the field
Queue-based features for dynamic waiting time prediction in emergency department
No full textPurpose: The purpose of this study is twofold: exploring new queue-based variables enabled by process mining and evaluating their impact on the accuracy of waiting time prediction. Such queue-based predictors that capture the current state of the emergency department (ED) may lead to a significant improvement in the accuracy of the prediction models. Design/methodology/approach: Alongside the traditional variables influencing ED waiting time, the authors developed new queue-based predictors exploiting process mining. Process mining techniques allowed the authors to discover the actual patient-flow and derive information about the crowding level of the activities. The proposed predictors were evaluated using linear and nonlinear learning techniques. The authors used real data from an ED. Findings: As expected, the main results show that integrating the set of predictors with queue-based variables significantly improves the accuracy of waiting time prediction. Specifically, mean square error values were reduced by about 22 and 23 per cent by applying linear and nonlinear learning techniques, respectively. Practical implications: Accurate estimates of waiting time can enable the ED systems to prevent overcrowding e.g. improving the routing of patients in EDs and managing more efficiently the resources. Providing accurate waiting time information also can lead to decreased patients’ dissatisfaction and elopement. Originality/value: The novelty of the study relies on the attempt to derive queue-based variables reporting the crowding level of the activities within the ED through process mining techniques. Such information is often unavailable or particularly difficult to extract automatically, due to the characteristics of ED processes
Scientific Communities and Decentralized Orchestration: A Social Network Analysis of the CINet Conference
Full text linkA process mining methodology for modeling unstructured processes
No full textThe effective representation of business processes is widely recognized as a critical task in Business Process Management (BPM). Unfortunately, the complexity of unstructured processes makes process modeling extremely challenging and limits the suitability of traditional model-driven approaches, which appear considerably less effective and efficient. Nevertheless, most of the recent and promising data-driven approaches dealing with unstructured processes are not yet completely developed and typically fail to provide an adequate procedural process model. This study proposes a novel process mining-based methodology to achieve a significant process model when unstructured processes occur. Specifically, the method assesses and combines the outcomes of different process mining algorithms by evaluating the process model through appropriate quality parameters (i.e., accuracy and comprehensibility). The final output of the method corresponds to a unitary procedural process model that is mathematically computable, evaluable through objective quality metrics, comparable with other process models, convertible to other model languages, and usable for supporting BPM activities. Finally, a real case study of an Italian hospital is presented to verify the applicability of the proposed methodology
Transforming healthcare ecosystems through blockchain: Opportunities and capabilities for business process innovation
No full textBlockchain is an unprecedented enabler and booster of business process innovation, especially in the healthcare sector. Nonetheless, its transformational potential has yet to be fully harnessed because of the challenges that digitalization has posed to Business Process Management (BPM) and the inherent complexity of the healthcare processes. Accordingly, through the ambidextrous BPM theoretical lenses, this paper investigates what are the main opportunities for Blockchain-driven healthcare process innovation and which BPM capabilities may unleash them. Two exploratory case studies were conducted to probe the Blockchain-driven process redesign: a case of exploitative BPM, focusing on drug logistics, and a case of explorative BPM, focusing on integrated home care. Our findings suggest that Blockchain may enable Healthcare innovation opportunities, such as the redesign of the information flow and the development of new forms of collaboration in the health ecosystem. In addition, the most relevant BPM capabilities to pursue such innovations were identified. These results integrate the BPM research stream and enhance the understanding of Blockchain-driven healthcare process innovation
- …
