Improving performance of the hospitalization process by applying the principles of Lean Thinking

Evaluation of different machine learning algorithms for predicting the length of stay in the emergency departments: a single-centre study

Background

Recently, crowding in emergency departments (EDs) has become a recognised critical factor impacting global public healthcare, resulting from both the rising supply/demand mismatch in medical services and the paucity of hospital beds available in inpatients units and EDs. The length of stay in the ED (ED-LOS) has been found to be a significant indicator of ED bottlenecks. The time a patient spends in the ED is quantified by measuring the ED-LOS, which can be influenced by inefficient care processes and results in increased mortality and health expenditure. Therefore, it is critical to understand the major factors influencing the ED-LOS through forecasting tools enabling early improvements.

Methods

The purpose of this work is to use a limited set of features impacting ED-LOS, both related to patient characteristics and to ED workflow, to predict it. Different factors were chosen (age, gender, triage level, time of admission, arrival mode) and analysed. Then, machine learning (ML) algorithms were employed to foresee ED-LOS. ML procedures were implemented taking into consideration a dataset of patients obtained from the ED database of the "San Giovanni di Dio e Ruggi d'Aragona" University Hospital (Salerno, Italy) from the period 2014-2019.

Results

For the years considered, 496,172 admissions were evaluated and 143,641 of them (28.9%) revealed a prolonged ED-LOS. Considering the complete data (48.1% female vs. 51.9% male), 51.7% patients with prolonged ED-LOS were male and 47.3% were female. Regarding the age groups, the patients that were most affected by prolonged ED-LOS were over 64 years. The evaluation metrics of Random Forest algorithm proved to be the best; indeed, it achieved the highest accuracy (74.8%), precision (72.8%), and recall (74.8%) in predicting ED-LOS.

Conclusions

Different variables, referring to patients' personal and clinical attributes and to the ED process, have a direct impact on the value of ED-LOS. The suggested prediction model has encouraging results; thus, it may be applied to anticipate and manage ED-LOS, preventing crowding and optimising effectiveness and efficiency of the ED.

A framework for lean implementation in preoperative assessment: Evidence from a high complexity hospital in Italy

Purpose: A routine preoperative assessment is considered both ineffective and inefficient. Despite the widespread application of lean thinking in healthcare, there is little evidence of successful experiences in preoperative admissions in order to reduce "No value added" activities. A conceptual framework reporting the drivers (clinic, tools, innovation, organization, and governance) and impacts (patient, efficiency, sustainability, time, learning and growth) was developed. Methodology: Drawing on the experience of an Italian high complexity hospital, this paper analyzes the case study by reporting evidence on how to implement lean in preoperative assessment and how to evaluate the positive results obtained. Results: Applying lean principles, the identification of value improved the appropriateness of care by creating 40 personalized pathways; the value stream resulted in a reduction of "No Value Added Time" from 37% to 28%, chest X-rays from 41% to 14% and cardiac visits from 49% to 37%; the pursuit of continuous flow through innovation contributed to increase the use of digitalization; the new pull organization helped to reduce the average time spent per year by 1.5 h; the continuous improvement was ensured through the governance of results. Conclusion: The proposed framework should be used to improve the quality of care in preoperative admissions by adopting the lean drivers for successful implementation and reporting the impacts.

Leanness assessment of a complex assembly line using integrated value stream mapping: a case study

Purpose

This paper proposes an integrated value stream mapping (VSM) for a complex assembly line to improve the leanness of a complex automotive component manufacturing organization.

Design/methodology/approach

This study depicts the application of VSM at the case organization, where top management is concerned about the challenges of higher cycle time and lower productivity. Gemba walks were conducted to establish the concept of “walk the flow, create the flow” along the assembly line. The multi-hierarchical cross-functional team developed the current value stream map to know the “as-is” state. Then, the team analysed the current VSM and proposed the future VSM for the “to-be” state.

Findings

The integrated VSM shows different processes and work cells, various wastes, non-value-added activities, cycle time, uptime and the material and information flows for both products of the assembly line on the same map. The integrated VSM reduced cycle time, non-value-added activities, work in process inventory and improved line efficiency and production per labour hour for both the products, simultaneously.

Research limitations/implications

The limitation of the study is that the study focussed only on the application of VSM for one complex assembly only. Future research may be conducted using the developed integrated VSM approach in other complex production environments.

Practical implications

Managers can identify and reduce system waste by incorporating the concept of integrated VSM in a complex production or assembly environment where two or more products are being manufactured/assembled with low similarity.

Originality/value

The application of VSM for assembly lines is highly challenging because of merging flows, a large number of child parts in the lines and assembly of more than one product on the same line.

Lean management practices perception and their influence on organizational performance in a public Higher Education Institution

Purpose

The purpose of this paper is to explore the perception of Lean management practices by public servants of a Higher Education Institution (HEI) and its influence on the organizational performance. The underlying assumption is that Lean management practices may have perceived even without a whole dissemination of the Lean Thinking way in the institution, and they exercise a positive influence on organizational performance.

Design/methodology/approach

A questionnaire of Lean management practices applicable to HEIs was developed and a survey was carried out in a public HEI in Brazil. A valid sample of 748 respondents was obtained.

Findings

The results demonstrate that some Lean management practices (leadership support and employee involvement, focus on the internal customers, long-term thinking, community services value, elimination of waste and continuous improvement) have a positive influence on the organizational performance of the studied HEI. These results extend the applicability and foster the initiation of Lean management practices in the public service scenario and HEIs.

Practical implications

This study supports HEI leaders and managers in developing and/or promoting better management practices to improve organizational performance. In addition, it promotes the advancement of Lean initiatives in the organizational environment of the HEI, allowing for a better quality to the “beneficiaries” of the services provided.

Originality/value

Despite the broad evidence of Lean in the manufacturing and industrial sectors, this study advances by exploring the perception of Lean management practices in the HEIs context and their influence on organizational performance. This paper also initiates and fosters the discussion of internal costumers and community services value as basic practices of an HEI.