Using a manifold-based approach to extract clinical codes associated with winter respiratory viruses at an emergency department

Every winter, respiratory viruses put most Emergency Departments (ED) around the world under intense pressure. To reduce the consequent stress for hospitals, anticipation of the massive increase of intakes for illness-based symptoms is essential. As the Covid-19 2020 pandemic clearly illustrates, patients are not systematically tested. The ED staff therefore has no real-time knowledge of the presence of the virus in the patients flow. To address this issue, we propose here to use the hospital's laboratory-confirmed database as an attractor for the manifold-based approach for clustering the clinical codes associated with respiratory viruses. We propose a new framework based on the embedding of time series onto the Stiefel manifold, coupled with a density-based clustering algorithm (HDBSCAN) enhanced by a reduction of dimension (UMAP) for the clustering on that manifold. In particular, we show, based on real data sets of two academic hospitals in France, the significant benefits of using geometrical approaches for time series clustering as compared to traditional methods.

A New Model for a Sustainable Healthcare Supply Chain Prioritizes Patient Safety: Using the Fuzzy Delphi Method to Identify Healthcare Workers' Perspectives

The pandemic crisis and the resulting global uncertainties have obviously had a severe impact on the healthcare supply chain (HSC), leading scholars, healthcare executives, and policymakers to focus on the sustainability of the HSC. Technologies have emerged and developed rapidly in recent years, especially in the healthcare industry, for coping with the pandemic crisis and supporting the "new normal" for humankind. Within this context, various new technologies have been implemented to maximize the supply chain process, ensure patient and healthcare worker safety, and improve the quality of care. Hence, the integration of a technological dimension with the traditional three pillars of sustainability may aid in attempts to define the potential attributes of these dimensions of sustainability. Therefore, this study aimed to identify the key attributes of a sustainable healthcare supply chain (SHSC), and this paper presents a new, four-dimensional model for SHSCs, consisting of social, environmental, economic, and technological dimensions. A systematic literature review was conducted, resulting in the identification of 35 potential SHSC attributes. The Fuzzy Delphi Method (FDM) was then applied to determine the appropriateness of these potential attributes according to the consensus of 13 experts, including healthcare workers in a variety of medical specialties, who profoundly understand HSC sustainability. The results yielded 22 appropriate attributes, which were then categorized across the four dimensions. Consequently, a new model of an SHSC, which prioritizes patient safety, was constructed and is proposed here. This SHSC model can be applied strategically to the healthcare industry to enhance the safety of both medical personnel and patients in a sustainable manner.

A simulation model for predicting hospital occupancy for Covid-19 using archetype analysis.

COVID-19 pandemic has sent millions of people to hospitals worldwide, exhausting on many occasions the capacity of healthcare systems to provide care patients required to survive. Although several epidemiological research works have contributed a variety of models and approaches to anticipate the pandemic spread, very few have tried to translate the output of these models into hospital service requirements, particularly in terms of bed occupancy, a key question for hospital managers. This paper proposes a tool for predicting the current and future occupancy associated with COVID-19 patients of a hospital to help managers make informed decisions to maximize the availability of hospitalization and intensive care unit (ICU) beds and ensure adequate access to services for confirmed COVID-19 patients. The proposed tool uses a discrete event simulation approach that uses archetypes (i.e., empirical models of trajectories) extracted from empirical analysis of actual patient trajectories. Archetypes can be fitted to trajectories observed in different regions or to the particularities of current and forthcoming variants using a rather small amount of data. Numerical experiments on realistic instances demonstrate the accuracy of the tool's predictions and illustrate how it can support managers in their daily decisions concerning the system's capacity and ensure patients the access the resources they require.

Forecasting ICU Census by Combining Time Series and Survival Models.

Capacity planning of ICUs is essential for effective management of health safety, quality of patient care, and the allocation of ICU resources. Whereas ICU length of stay (LOS) may be estimated using patient information such as severity of illness scoring systems, ICU census is impacted by both patient LOS and arrival patterns. We set out to develop and evaluate an ICU census forecasting algorithm using the Multiple Organ Dysfunction Score (MODS) and the Nine Equivalents of Nursing Manpower Use Score (NEMS) for capacity planning purposes. DESIGN: Retrospective observational study. SETTING: We developed the algorithm using data from the Medical-Surgical ICU (MSICU) at University Hospital, London, Canada and validated using data from the Critical Care Trauma Centre (CCTC) at Victoria Hospital, London, Canada. PATIENTS: Adult patient admissions (7,434) to the MSICU and (9,075) to the CCTC from 2015 to 2021. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We developed an Autoregressive integrated moving average time series model that forecasts patients arriving in the ICU and a survival model using MODS, NEMS, and other factors to estimate patient LOS. The models were combined to create an algorithm that forecasts ICU census for planning horizons ranging from 1 to 7 days. We evaluated the algorithm quality using several fit metrics. The root mean squared error ranged from 2.055 to 2.890 beds/d and the mean absolute percentage error from 9.4% to 13.2%. We show that this forecasting algorithm provides a better fit when compared with a moving average or a time series model that directly forecasts ICU census. Additionally, we evaluated the performance of the algorithm using data during the global COVID-19 pandemic and found that the error of the forecasts increased proportionally with the number of COVID-19 patients in the ICU. CONCLUSIONS: It is possible to develop accurate tools to forecast ICU census. This type of algorithm may be important to clinicians and managers when planning ICU capacity as well as staffing and surgical demand planning over a short time horizon.

Performance analysis of English hospitals during the first and second waves of the coronavirus pandemic.

The coronavirus infection COVID-19 killed millions of people around the world in 2019-2022. Hospitals were in the forefront in the battle against the pandemic. This paper proposes a novel approach to assess the effectiveness of hospitals in saving lives. We empirically estimate the production function of COVID-19 deaths among hospital inpatients, applying Heckman's two-stage approach to correct for the bias caused by a large number of zero-valued observations. We subsequently assess performance of hospitals based on regression residuals, incorporating contextual variables to convex quantile regression. Data of 187 hospitals in England over a 35-week period from April to December 2020 is divided in two sub-periods to compare the structural differences between the first and second waves of the pandemic. The results indicate significant performance improvement during the first wave, however, learning by doing was offset by the new mutated virus straits during the second wave. While the elderly patients were at significantly higher risk during the first wave, their expected mortality rate did not significantly differ from that of the general population during the second wave. Our most important empirical finding concerns large and systematic performance differences between individual hospitals: larger units proved more effective in saving lives, and hospitals in London had a lower mortality rate than the national average.

Machine Learning in ASD: An Intensive Study of Automated Disease Prediction System

Of late, due to drastic climate change and excessive pollution, people live in such an atmosphere where they have to combat continuously several deadly diseases. To get the proper treatment of such diseases, people must rely on appropriate diagnoses. There are a lot of signs or symptoms that bear the existence of a particular condition. Generally, almost all the people who suffer from viral infections, dengue, and COVID-19 get a common sign of high fever. Therefore, it is challenging for doctors to determine the exact disease with this particular symptom. Accordingly, a technically equipped medical system should be developed to get a more error-free diagnosis. In this context, a case study uses the Random Forest Algorithm to combine diagnostic prediction and technology, which will help medical practitioners detect diseases. Agile Software can be used here. One of the essential advantages of agile methodology is speed to market and risk reduction. This paper showcases a module developed with the help of Machine Learning. Here, Agile Software is designed to become very effective in detecting a particular disease more efficiently. In this specific system preventing errors and malfunctions has been proven to be 95% effective in the medical field. © 2023 Scrivener Publishing LLC.

'Social' media? How Swiss hospitals used social media platforms during the early months of the COVID-19 pandemic crisis.

OBJECTIVES: This paper about social media platforms of Swiss hospitals refers to the period between 10 February 2020 and 6 July 2020. The study included in-depth insights into the use of platforms, content analyses of posts and resonance of the posts. The study's objective was to get insights into social media post creation by and corresponding resonance in pandemic crisis. STUDY DESIGN: This study included collection and analyses of posts created by a selection of Swiss hospitals during the period of study. All university hospitals and a variety of private and regional hospitals in all regions of Switzerland are represented. The data collection started before the official shutdown in Switzerland. METHODS: This study used mixed method approach and content analysis to evaluate 2,326 posts during the study period related to the COVID-19 pandemic. RESULTS: During the first phase of the pandemic, hospitals used social media platforms more frequently than normal. Especially in the first month, the number of posts rose disproportionally. The numbers dropped back to the initial situation after only 4 months into the COVID-19 pandemic. Most hospitals used Facebook and Twitter, whereas Instagram and YouTube's use were marginal. University hospitals used social media platforms differently than regional hospitals. CONCLUSION: Most posts generated only a very low response with a median of 2. Hospitals were therefore not able to create engagement of their followers. However, hospitals that publish actively were able to build a more active community. Only a small number of posts led to heated discussions in the comments. These viral posts shared information on the illness, the vaccination, children and COVID-19.

Healthcare management and COVID-19: data-driven bibliometric analytics

Healthcare management and COVID-19 has been broadly studied during the recent few days, especially after declaration of the COVID-19 outbreak in almost all countries in the world. Therefore, the present research article aims to provide an extensive overview of the scientific literature about the study of healthcare management and COVID-19 for choosing the new topic of related research. It conducts four types of analyses where the first analysis is a trend analysis and other three analyses are related to network and density maps. The second analysis is analyzed decisively in order to produce all keywords, author keywords and index keywords co-occurrence network map and country co-authorship network map and tables summarizing the significant scientific trends under the present topics. The third analysis is analyzed purposefully in order to produce all documents, journals, authors and countries bibliographic coupling network maps and tables summarizing the significant scientific trends. The last analysis provides valuable approaching of the most significant used keywords on the research topic and the links among them using keyword co-occurrence network and density maps respectively.

Mediating Effects of Attitudes, Risk Perceptions, and Negative Emotions on Coping Behaviors: Evidence From a Survey of Older Chinese Adults

Based on the perspectives of social risk amplification and the knowledge-attitudes-practice model, this study aimed to test how the level of knowledge about COVID-19 and information sources can predict people's behavioral changes and to examine the effect mechanisms through the mediating roles of attitude, risk perception, and negative emotions in a survey of 498 older Chinese adults. The results showed that (1) older people had a lower level of factual knowledge regarding the variant strains and vaccines;(2) in the information sources-behavior, information sources had a critical influence on elderly individuals' coping behaviors;and (3) in the knowledge-behavior, factual knowledge had a significant effect on elderly individuals' coping behaviors. Specifically, for prevention behaviors, both risk perception and negative emotions played full mediating roles. The findings have significant implications for the development of an effective COVID-19 prevention program to older adults coping with pandemic conditions.

Influential Factors for Hospital Management Maturity Models in a post-Covid-19 scenario - Systematic Literature Review

The importance of Maturity Models in healthcare is proven to support, monitor and direct healthcare organizations to better plan and execute their investments, developments and processes. In this work, two literature reviews were collected: one of them focuses on the identification of the main maturity models developed in the health area, the similarities and gaps between them, identifying what are the Influencing Factors for each model studied, and the other is the identification lessons learned for hospital management during the Covid-19 pandemic. Combining these two lines of investigation, it can be concluded that, in order to better prepare, adapt and make health systems more resilient, it is fundamental that future Maturity Models begin to map agility in diagnosing diseases, scale of exams, process of hospital disinfection and technological infrastructure, focusing on ICTs such as ML, LMS, DL, Robot Assistance, Actuators, Big Data, Blockchain, Smart Wearables, Delivery Drones, Artificial Intelligence, Internet of Things, Augmented Reality, Virtual Reality, Sensors and Cloud Technology. These IFs are identified as gaps for existing MMs in the sector. Allied to this, it is indicated that the future MMs consider expanding their focus in supply chain, services and applications, monitoring and, mainly, patient safety and care, given the importance that these IFs demonstrated in coping with the pandemic. Copyright © 2023 by Author/s and Licensed by IADiTI.

Analysis of the socioeconomic barriers in implementing public health measures to contain COVID-19 transmission in Pakistan: a DELPHI–DEMATEL-based approach

PurposeThe present study aims to identify and evaluate the socioeconomic barriers to effective COVID-19 pandemic transmission control in Pakistan.Design/methodology/approachThe study identifies multiple socio-economic barriers through an extensive literature review. The preliminary analysis unveiled 15 socio-economic barriers. Nine experts were contacted to collect data and finalize the most prominent barriers to COVID-19 transmission control using the DELPHI method. The Decision-Making Trial and Evaluation Laboratory (DEMATEL) method was used to process and interpret the data collected and a cause–effect relationship was established among the barriers.FindingsThe finalized barriers to effective COVID-19 pandemic transmission control were evaluated using DEMATEL which grouped criteria into two grouped criteria – cause and effect. The DEMATEL analysis shows that poor safety culture, lack of strategy and goal setting, lack of resources, late realization and recognition of the pandemic problem and lack of expertise and capacity in disaster and risk management fall into the cause group. These factors are critical as they directly affect the remaining barriers identified in the study.Originality/valueDespite the collective global efforts, the national economies have been struggling to completely control COVID-19 transmission control. Pakistan's economy has been facing the third wave of the pandemic. It is mandatory to identify the barriers and evaluate them to develop a comprehensive strategy ensuring that there would be no fourth wave. The study identifies and evaluates the barriers to COVID-19 transmission control in Pakistan using the integrated DELPHI-DEMATEL framework. The findings would help the government, experts and strategists to develop a comprehensive disaster and risk management strategy.

Healthcare waste hazards assessment using EWGM-FMEA: Case study in Oman

In the last years, particularly after Covid-19, Health care waste (HCW) has increased significantly due to the increasing population and number of healthcare organizations. HCW produces a significant risk of infectious contamination and injury. Accordingly, healthcare waste management plays a vital role in creating waste management strategies, and policies and implementing waste management plans. To build robust healthcare management systems, the risk assessment process is a key step. This paper assesses the top hazards of healthcare waste at Sultan Qaboos University Hospital (SQUH) in Oman using the Exponential Weighted Geometric Mean-Failure Mode and Effect Analysis (EWGM-FMEA). Fifteen healthcare waste hazards were selected to apply the tool. These hazards are ranked to prioritize the top hazards wastes. This assessment helps in identifying the most crucial hazards,whiche the policymakers should pay attention thus, the main countermeasures could be conducted. These hazards were proposed based on the conducted survey questionnaire and interviews accordingly, and analyses of the data have been carried out. The applied tool examined the importance of quantifying healthcare waste to apply the appropriate corrective actions which can be applied to mitigate the harm and the negative effects of healthcare waste. The results of the assessment tool will help policymakers in developing clear plans for management, disposal of wastes, and segregation. Furthermore, prioritizing healthcare waste explored the importance of integrating tthe raining plans of workers with the healthcare waste management policy. Although the prospective managerial and policy implications of this research, some limitations could be studied by future researchers. Firstly, the sample covered one hospital that may be representative of only one hospital in Oman which constrains the generalization of results. Secondly, the number of identified waste hazards is fifteen so, increased the number of hazards may help policymakers in building a more effective healthcare waste management plan which will reflect in improving the healthcare management system in the organization, mitigating the harmful effects on human health and the negative effects on the environment. © 2023 The Author(s). This open access article is distributed under a Creative Commons Attribution (CC-BY) 4.0 license.

Mitigation Measures to Control the Expected Mpox Outbreak in a Developing Country-Pakistani Scenario.

Mpox (previously named Monkeypox) is one of the neglected viral infectious diseases that remained silent for a long period before finally emerging as a threat to the healthcare system in endemic regions of the world in recent years. It has been mostly centered in African countries but has now been reported in other non-endemic regions as well. While keeping a strict eye on COVID pandemic handling, there is a need to remain concerned and alert about viral threats such as Mpox infections in the future. This situation has altered the healthcare system of endemic regions, including Pakistan, to stay vigilant against the expected Mpox outbreaks in the coming months. Though no specific cases have been reported in Pakistan, the healthcare system needs to take mitigation measures to tackle an expected threat before it arrives. This is important in order to avoid another major shock to the health care system of Pakistan. Moreover, since no specific treatment is available for Mpox, we can only rely upon mitigation measures, involving preventive and treatment strategies devised around some already in-use antiviral agents against Mpox viruses. Moreover, there is an imperative need to proactively prepare the healthcare system against Mpox outbreaks, spread awareness, and involve the public in a participatory approach to stay well prepared against any such infection. Moreover, there is a need to utilize financial sources, aids, and funds wisely, to create awareness in the public about such expected healthcare outbreaks in the future.

The COVID crisis impact on open education in the field of healthcare management.

This paper aims to explore how the Hellenic Open University managed to adapt to the new normal of the pandemic and particularly what methods it deployed in its postgraduate Healthcare Management program. The first part introduces the key features of the Hellenic Open University and analyzes the strategic policy deployed by the University during the pandemic through the pillars of academic integrity, openness and excellence. The second part presents the research method and findings regarding both instructors and students of the Healthcare Management postgraduate program. The third part concludes that the policy introduced by University had a positive effect overall both to academic staff and healthcare practitioners. The importance and innovation of this study lies in the fact that it emphasizes on adult students who are in their crashing majority healthcare practitioners and thus have already a saying regarding the pandemic's management. The scope of the research was to demonstrate that this student audience had a significant input in the teaching procedure, since they were at the forefront of the pandemic crisis. In this regard, the instructor-student relationship was more than ever reciprocal based on the knowledge of the first and the experience of the latter.

Electronic consultation (e-consultation) between primary care and the neurology department: One-year experience in a healthcare area in Andalusia, Spain

Introduction: The COVID-19 pandemic has prompted the implementation of telemedicine programmes to facilitate healthcare. In November 2020 we initiated an e-consultation programme between primary care and the neurology department, with asynchronous response, through a platform integrated into the corporate computer system of the Andalusian Public Health System. We present the results of the first year of operation. Methods: We present a descriptive study of the e-consultations received in 2021 from a health area of approximately 300,000 inhabitants aged ≥ 14 years. The reasons for consultation were pre-established: "primary headache” (PH), "new-onset cognitive impairment” (CI), "complications of dementia” (DEM), and "epilepsy” (EPI). We defined inclusion criteria and the clinical information/tests that had to be provided. General practitioners could choose between e-consultation or face-to-face referral. Results: A total of 1,806 e-consultations were received (approximately 6/1,000 population/year). By reasons for consultation: CI 34.3%, PH 32%, DEM 14.4%, EPI 11.7%, unspecified 7.6%. Responses were sent after an average of 2.25 days and were classified as: "refer for in-person consultation” (47.12%), "resolved” (39.98%), "criteria not met” (12.57%), or "follow-up by e-consultation” (0.33%). As expected, a high proportion of face-to-face referrals were required for CI (73.46%);the main value of the system for these patients was to prioritise appointments and select the most appropriate form of care. For the rest of the reasons for consultation, the proportion of "resolved” e-consultations reached 52.61%. Conclusions: Asynchronous e-consultation between primary care and the neurology department is a useful tool in the indicated conditions, offering a rapid, "one-stop” response to a significant proportion of clinical or therapeutic uncertainties, as well as optimising face-to-face appointments. © 2023

A Markovian model for the spread of the SARS-CoV-2 virus.

We propose a Markovian stochastic approach to model the spread of a SARS-CoV-2-like infection within a closed group of humans. The model takes the form of a Partially Observable Markov Decision Process (POMDP), whose states are given by the number of subjects in different health conditions. The model also exposes the different parameters that have an impact on the spread of the disease and the various decision variables that can be used to control it (e.g, social distancing, number of tests administered to single out infected subjects). The model describes the stochastic phenomena that underlie the spread of the epidemic and captures, in the form of deterministic parameters, some fundamental limitations in the availability of resources (hospital beds and test swabs). The model lends itself to different uses. For a given control policy, it is possible to verify if it satisfies an analytical property on the stochastic evolution of the state (e.g., to compute probability that the hospital beds will reach a fill level, or that a specified percentage of the population will die). If the control policy is not given, it is possible to apply POMDP techniques to identify an optimal control policy that fulfils some specified probabilistic goals. Whilst the paper primarily aims at the model description, we show with numeric examples some of its potential applications.

An investigation into managerial support for the psychological wellbeing of national health service doctors during the Covid-19 pandemic: A cross sectional study.

AIM: This study investigates the psychological wellbeing of United Kingdom National Health Service doctors during the Covid-19 pandemic and evaluates how they have been supported managerially. METHOD: A mixed-method sequential study design of online surveys and semi-structured interviews was employed between July-August 2020, with a response rate of 273/300 and 4/4 respectively. The Warwick-Edinburgh Mental Wellbeing Scale (WEMWBS) and Health and Safety Executive Management Standards (HSE MS) were used as measuring tools. The Jobs Demands Resource (JD-R) model and its relation to psychological wellbeing was determined. Survey findings informed semi-structured interviews, coded using thematic analysis. RESULTS: Overall mean WEMWBS, 43.2 (SD = 9.44), was low as was mean managerial support, 2.38 (SD = 0.78). Overall mean clinical demand score was high (2.6 on reverse scale). First year female trainee respondents from frontline specialties were found to have low psychological wellbeing scores. Key correlations were found between high managerial support, low clinical demands and low psychological wellbeing (r > 0.6). Core themes emerged: (1) breakdown of leadership, (2) vulnerability of wellbeing without support, (3) suboptimal navigation through change and (4) poor physical and human resource management. CONCLUSION: Maintaining the psychological wellbeing of doctors requires physical and psychological resources to meet clinical demands and the enhancement of fundamental managerial principles of control, communication, change management and leadership through adversity.

Artificial intelligence: the major role it played in the management of healthcare during COVID-19 pandemic

The sudden arrival of COVID-19 called for new technologies to manage the healthcare system and to reduce the burden of patients in the hospitals. Artificial intelligence (AI) which involved using computers to model intelligent behavior became an important choice. Various AI applications helped a lot in the management of healthcare and delivering quick medical consultations and various services to a wide variety of patients. These new technological developments had significant roles in detecting the COVID-19 cases, monitoring them, and forecasting for the future. Artificial intelligence is applied to mimic the functional system of human intelligence. AI techniques and applications are also applied in proper examinations, prediction, analyzing, and tracking of the whereabouts of patients and the projected results. It also played a significant role in recognizing and proposing the generation of vaccines to prevent COVID-19. This study is therefore an attempt to understand the major role and use of AI in healthcare institutions by providing urgent decision-making techniques that greatly helped to manage and control the spread of the COVID-19 disease.

COVID-19 management at one of the largest hospitals in Germany: Concept, evaluation and adaptation.

CONTEXT: The LMU University Hospital is among the largest healthcare facilities in Germany. The measures implemented prior to and during the first pandemic wave of COVID-19, were evaluated in preparation of a second pandemic wave. This paper presents the pandemic management concept, evaluation and adaptation of LMU University Hospital. METHODS: Between July and September 2020 the disaster management team of LMU University Hospital conducted a mixed-method evaluation of the hospital's pandemic management. A workshop series based on the After Action Review working group format was organized to examine the management structure, decision-making processes, documentation, and crisis preparedness response for a second COVID-19 wave. Further, the satisfaction of employees with the hospital's COVID-19 management was examined through an anonymous survey. RESULTS: The workshop series highlighted a need for structural and operational adaptation of the COVID-19 management at LMU University Hospital. The results of the employee survey (N = 2182) provided positive feedback for the measures taken during the first pandemic wave. Specific actions were derived concerning the availability of personal protective equipment and emergency childcare services. A key outcome of both evaluation activities was the identified need for further improvement in communication between stakeholders. All changes were adopted prior to the second pandemic wave.