Narrow Results

This chapter addresses the key issues impacting the adoption of information technology (IT) in healthcare organizations. Four case studies were developed from different hospitals through a series of in-depth interviews to determine the factors affecting their IT adoption. The findings reveal that, at the organization level, these hospitals primarily make decisions to adopt new technologies based on project-related costs. At the individual level, the complications in the implementation process play a major role as they are influenced by human-related issues. Apart from the identification of key factors from the case studies, the latter part of this chapter also presents the mental framework of IT adoption for healthcare organizations developed based on the technology acceptance model.

Increasingly large electronic health records (EHRs) provide an opportunity to algorithmically learn medical knowledge. In one prominent example, a causal health knowledge graph could learn relationships between diseases and symptoms and then serve as a diagnostic tool to be refined with additional clinical input. Prior research has demonstrated the ability to construct such a graph from over 270,000 emergency department patient visits. In this work, we describe methods to evaluate a health knowledge graph for robustness. Moving beyond precision and recall, we analyze for which diseases and for which patients the graph is most accurate. We identify sample size and unmeasured confounders as major sources of error in the health knowledge graph. We introduce a method to leverage non-linear functions in building the causal graph to better understand existing model assumptions. Finally, to assess model generalizability, we extend to a larger set of complete patient visits within a hospital system. We conclude with a discussion on how to robustly extract medical knowledge from EHRs.

A national healthcare system involves multiple stakeholders including care providers and consumers, governments, professionals, industries, etc. This study reviews the national healthcare system of China, and identifies 5 major challenges to the system. E-health solutions (products or services) play an important role in addressing many issues of the challenges. A market research in this study identifies 25 types of e-health solutions on current Chinese market. The solutions are developed by local competitors based on their technical strengths. Many of them are not widely accepted and used. An online survey is conducted to investigate the usefulness of the solutions in the perspective of the users. Based on the survey feedback, the solutions are ranked according to their degree of need by the Chinese consumers. The ranking provides the Chinese governments with some insights for their decision making to improve the healthcare system; and industry players with information for business opportunities. The Chinese experience would be references for e-health endeavours of other countries.

This study explores digitalization in the healthcare sector, and presents insights on the use of data for developing and organizing preventive healthcare services for young people, which has been identified as one of the most crucial issues to be tackled by public decision-makers. Conducted as a qualitative case study with municipal decision-makers, this study highlights the needs and implications of data as a complex, systemic issue with far reaching long-term impact, where the right kind of data could improve the health and well-being of the society far beyond healthcare domain.

The healthcare industry in India provides an essential service to everyone in society yet the costs involved have deterred access to the public. This is driven by the incompetent use of healthcare technology, an incomplete system of payments, additional medical services, and limited involvement by patients in the decision-making process of the healthcare system. The spread of COVID-19 vividly demonstrated these weaknesses associated with India’s healthcare system. Given this situation, this chapter identifies the causes of unsustainable healthcare expenditure in India and discusses how to curtail healthcare costs while contributing toward improving the environmental and social impacts of this sector. We conducted research by exploring how the healthcare companies can curtail costs by implementing new practices such as improving the efficiency of utilizing technology. In doing so, this study reveals that only limited efforts in research and development are taking place. The findings of this chapter signify that India’s healthcare is in a weak shape and requires massive transformation. Other developing countries should take India as an example of how to progress and improve their own healthcare sector.

In this chapter, we refine and extend the conceptualization of institutional work when it is linked to entrepreneurial agency engendering institutional change. This extension is conducted employing the method of collaborative autoethnography as we studied the formation of the James C. Kennedy Wellness Center. This Center was instituted through the entrepreneurial agency of outside actors who built and organized it in an impoverished and rural community in Charleston, Mississippi. We examine how the concept of institutional work is extended when linked through entrepreneurial agency. Based on our collaborative autoethnographic examination and analysis of the data collected through observations, interviews, site visits, electronic searches, and photographs, as well as the crucial dialogue conducted by researchers possessing both emic and etic perspectives, we identify a new fourth dimension, assessment, of institutional work linked to entrepreneurial agency. The work of assessment complements the previously identified dimensions of institutional work — creating, maintaining, and disrupting.

To improve quality and safety and to contain costs, hospitals should optimize their processes. Therefore, they need to have a full understanding and visibility of their operations and supply chain flows. In this chapter, we combined a lean management approach using value stream mapping, with a data-driven approach using process mining applied to the surgery processes of a private hospital in Switzerland. As the sterilization process was identified as a major bottleneck, we developed a digital twin and artificial intelligence algorithms to optimize the hospital operations and supply chain management. As a result, the hospital increased the quality of its work environment, improved visibility in their processes, and developed a stronger communication channel with their teams. In addition, they could better plan schedules, which allowed the hospital to limit overtime of the operating room staff. Finally, they optimized costs and saved time in their overall sterilization process.

There has been a lot of interest in time series forecasting in recent years. Deep neural networks have shown their effectiveness and accuracy in various industries. It is currently one of the most extensively used machine-learning algorithms for dealing with massive volumes of data due to the reasons stated above. Statistical modeling includes forecasting, which is used for decision-making in various fields. Time-varying variables may be forecasted based on their past values, which is the goal of forecasting. Developing models and techniques for trustworthy forecasting is an important part of the forecasting process. As part of this study, a systematic mapping investigation and a literature review are used. Time series researchers have relied on ARIMA approaches for decades, notably the autoregressive integrated moving average model, but the need for it to be stationary makes this method somewhat rigid. Forecasting methods have improved and expanded with the introduction of computers, ranging from stochastic models to soft computers. Conventional approaches may not be as accurate as soft computing. In addition, the volume of data that can be analyzed and the efficiency of the process are two of the many benefits of using soft computing.

This paper analyzes data on approximately 30,000 women from a survey in Uttar Pradesh in 1995 together with the data from surveys of public and private providers of healthcare and family planning services. A framework was developed for analyzing the effects of quality of services on utilization, and for understanding the gradual evolution of the healthcare infrastructure. The empirical results from logistic regressions for use of female sterilization and IUD showed significant effects of quality of services in government and private hospitals, and of socioeconomic variables such as education, caste, and an index of household possessions. Secondly, models for infant mortality of children born in the preceding 3-year period showed significant effects of socioeconomic variables, quality of healthcare services and birth spacing. Lastly, analysis of data at a more aggregated (Primary Sampling Unit) level indicated differential effects of economic development on the quality of services available in the public and private facilities.

Healthcare supply chain management differs from other applications in terms of its key elements. The misalignment, high costs for healthcare providers and heavy dependence on third parties, distributors, and manufacturers are the main trouble making issues for the healthcare supply chain. At the same time, some of the supply chain components of the health sector have a different position compared to the other materials that are taking place in the other supply chains. In particular, the specific consumables used in the surgical operations bear a significant importance in terms of the usage and the costs. In some cases, the doctors may not have a strict opinion on the exact quantity of the consumables they will use during the operation before starting it. On the other hand, it is not always possible to have all these materials in the stock because of their high cost. Moreover, due to the inefficiencies in the social security system in Turkey, the social security institutions do not always accept to pay the price of the materials used. Worse still, the related information generally reaches with a significant delay to the hospital management.

A major challenge for business information systems (BIS) design and management within healthcare units is the need to accommodate the complexity and changeability in terms of their clinical protocols, technology, business and administrative processes. Interoperability is the response to these demands, but there are many ways to achieve an “interoperable” information system. In this chapter we address the requirements of a healthcare interoperability framework to enhance enterprise architecture interoperability of healthcare organizations, while maintaining the organization's technical and operational environments, and installed technology. The healthcare interoperability framework is grounded on the combination of model driven architecture (MDA) and service-oriented architecture (SOA) technologies.

The main argument in this chapter is to advocate the role of chief information officer (CIO) in dealing with challenges posed by the need to achieve BIS grounded on interoperability at the different layers, and in developing and executing an interoperability strategy, which must be aligned with the health organization's business, administrative, and clinical processes. A case study of the Hospital de São Sebastião is described demonstrating the critical role of the CIO for the development of an interoperable platform.

With the development of computer and database technology, people have a multitude of ways to access information. However, the rapid increase of big data information has created new problems for people. Due to the vast amounts of monitoring data and ineffective extraction of intrinsic data, more and more information are ignored. There is demand for user-oriented growth in data analysis, which is a technology that presents data in a more graphical way for easier visualization. This data visualization technology will impact users greatly and aid them in making decisions in the future. By combining the D3 visualization library with practical applications in the field of health care, data visualization can be used to effectively explore health care research.

Healthcare is usually the first that comes to our minds when dealing with the consequence of major hazards to deal with the large numbers of casualties; however, this was not available due to the ineffective preparedness. Literature illustrates a significant number of publications covering the resilience of healthcare to major hazards; however these tend to be fragmented due to the complexity of this service which often gives an incomplete picture of the health service and thus leads to inadequate level of preparedness. This chapter addresses some of this fragmentation by shedding light on disaster-resilience in the healthcare sector with the view to enhance the understanding of this service and thus builds its capacity and ultimately mitigates disaster risks. The chapter covers the performance of healthcare post disasters; hospitals’ structural, non-structural and functional integrity; regulations and safety codes; and the integration of resilience and the sustainability agendas through an illustration of international case studies. This chapter also presents new dimensions for enhancing disaster-resilience in a healthcare setting. These dimensions are based on a new concept known as sustainable healthcare.

Recent research using Twitter as an information communication channel has shown how event organizers convey and disseminate their agenda across industries and disciplines. However, little research has been carried out on the user’s choice of information components when composing a tweet through the lens of information theory. This research employs a comparative case study to examine how medical-terminology hashtags and corresponding lay-language hashtags have been used to help to communicate healthcare messages on the Twitter platform. The main result of this case study revealed patterns that both retweeting behavior and the use of a variety of components to construct a tweet contribute to higher entropy values which imply that these are a more informative ways to communicate healthcare messages.

The research reported here is related to the impulse-radar technology when applied in care services for elderly persons. A method for estimation of impulse-radar signal parameters, based on the Bayes theorem and Markov-chain Monte-Carlo technique, is proposed. Initial results have shown that the proposed approach can be effectively used for estimation of the parameters of the echoes, and thus — for person localization.

The proliferation of healthcare data has brought the opportunities of applying data-driven approaches, such as machine learning methods, to assist diagnosis. Recently, many deep learning methods have been shown with impressive successes in predicting disease status with raw input data. However, the “black-box” nature of deep learning and the highreliability requirement of biomedical applications have created new challenges regarding the existence of confounding factors. In this paper, with a brief argument that inappropriate handling of confounding factors will lead to models’ sub-optimal performance in real-world applications, we present an efficient method that can remove the inuences of confounding factors such as age or gender to improve the across-cohort prediction accuracy of neural networks. One distinct advantage of our method is that it only requires minimal changes of the baseline model’s architecture so that it can be plugged into most of the existing neural networks. We conduct experiments across CT-scan, MRA, and EEG brain wave with convolutional neural networks and LSTM to verify the efficiency of our method.

Clinical decisions to treat and diagnose patients are affected by implicit biases formed by racism, ableism, sexism, and other stereotypes. These biases reflect broader systemic discrimination in healthcare and risk marginalizing already disadvantaged groups. Existing methods for measuring implicit biases require controlled randomized testing and only capture individual attitudes rather than outcomes. However, the ”big-data” revolution has led to the availability of large observational medical datasets, like EHRs and biobanks, that provide the opportunity to investigate discrepancies in patient health outcomes. In this work, we propose a causal inference approach to detect the effect of clinician implicit biases on patient outcomes in large-scale medical data. Specifically, our method uses proximal mediation to disentangle pathway-specific effects of a patient’s sociodemographic attribute on a clinician’s diagnosis decision. We test our method on real-world data from the UK Biobank. Our work can serve as a tool that initiates conversation and brings awareness to unequal health outcomes caused by implicit biases.