Ethically Building Business Intelligence in Healthcare

This chapter advocates the use of a value-sensitive design (VSD) approach toward deriving patient intelligence by illustrating that the insights provided by the healthcare data that captures patients' concerns, needs, and desires—known as values—provide more sustainable care. Authors examine three cases extracted from top information systems (IS) peer-reviewed journals in which medical data is collected and analyzed and in which intelligence is derived through a VSD framework. VSD is a three-part methodology that comprises conceptual, empirical, and technical investigations. This chapter investigates the value sensitivity of the following key activities and tasks that result in intelligence from data: data collection, data analysis, and data reporting.

Patient Empowerment and Analytics

The healthcare system is focusing more on patient empowerment leading to patients with active health management. In this process, although some mechanisms exist, there is a need for patient empowerment to move to a new realm where the empowerment process is activated remotely from the patient's side. With the increasing importance of Internet and e-health, it is believed that patient empowerment can be facilitated in the online setting and can be more effective than traditional face-to-face setting. Facilitating patient empowerment online also paves way to data analytics as various online activities can be tracked and the emerging analytic techniques can be utilized to gain insight into the data. This chapter provides knowledge on patient empowerment, data analytics, and their relationship including the role of patient empowerment in data analytics.

A Proposed Architecture to Sustain Public-Private Partnership

Information technology has enabled tertiary health care providers to improve patient access to preventive and post-discharge care transition services. When such services are supported by facilities that are under the control of the hospital, hospitals can still influence the delivery and overall quality of patient care services. However, for a variety of reasons, many hospitals rely on external care providers who operate relatively independently from the hospital to deliver these services. As such, service delivery intended to create efficiency and value to patients can become complex, challenging to deliver, and resource intensive—especially if the service delivery spans a prolonged time horizon. This chapter discusses one case of an intermediary who helps hospitals address the smoking cessation needs of patients. Using service dominant logic research, the service exchanges among three different ecosystems (healthcare providers, intermediary, and patients) are modeled and intelligence needed to align their goals using blockchain architecture is highlighted.

Integration of BI in Healthcare

In the digital age, the healthcare industry is generating a huge amount of data and information. Although there are structured data such as EHRs, the major data type is unstructured data such as clinical text. The sources of health data are also diversified, including medical data, clinical data, patient-generated data, and social media data. Different methods are applied to analyze the variety of data and obtain health information. When the various types of information are generated, information retrieval and extraction techniques can be used for further decision-making. Data and information-enabled decision-making is a complex process. Many tools and methods are developed to support decision-making in healthcare. Along with the benefits of integrating business intelligence in healthcare, issues and challenges exist. This chapter discusses the health data and information and how they support decision-making in healthcare.

Data to Analytics to Insight

Continual feedback to adapt to external regulatory and competitive environment is essential in today's complex healthcare landscape, and hospital leadership needs to transform its strategic planning process to reflect the market dynamic. Digital artifacts such as performance dashboard track operational data and transform these into key performance indicators (KPIs) to set organizational goals and align unit level operations. However, the velocity of change occurring in the marketplace needs a dynamic approach: a real-time aggregation of operational data into KPIs for a daily or weekly review to gain insights and respond quickly to evolving market expectations. This chapter discusses how an rtDashboard (real time dashboard) has evolved to become a key artifact that transformed the way a hospital in SE Michigan engaged in its strategic planning process.

Generation and Management of Data for Healthcare and Health Diagnostics

Healthcare Analytics deals with patient records, effective management of hospitals, and clinical care. But the big data available is still not enough for focused research as it is complicated to find insights from complex, noisy, heterogeneous, and voluminous data, which takes time and effort, while a small clinical data will be more effective for decision making. The health care data also varies in data collection methods and their processing methods. Data generated through patient records is structured, wearable technologies generate semi structured data, and X rays and images provide unstructured data. Storing and extracting information from the structured, semi-structured, and unstructured data is a challenging task. Different machine learning techniques can simplify the process. The chapter discusses the data characteristics, identifying critical attributes, various classification and optimization algorithms for decision making purposes. The purpose of the discussion is to create a basis for selection of algorithms based on size, temporal validity, and outcomes expected.

Deep Learning of Data Analytics in Healthcare

The importance of data as the fuel of artificial intelligence is self-evident. As the degree of informatization in various industries deepens, the amount of accumulated data continues to increase; however, data processing capability lags far behind the exponential growth of data volume. To gather accurate results, more and more data should be collected. However, the more data collected, the slower the processing and analyzing of that data. The emergence of deep learning solves the problem of how to process large amounts of data quickly and precisely. With the advancement of technology, the healthcare industry has achieved a promising level of needed data. Moreover, if deep learning can be used to aid disease diagnosis, patient data can be processed efficiently, useful information can be screened, valuable diagnostic rules can be mined, and disease diagnosis results can be better formulated and treated. It is foreseeable that deep learning has the potential to improve the effectiveness and the efficiency of healthcare and relevant industries.

Operations-Intelligence-Strategy (OIS) Process in Healthcare

The healthcare industry has generated a huge amount of data in diverse formats. The big data in healthcare is leading the revolution in healthcare. Collecting data at the operational level is the starting point for the big data-driven healthcare revolution. By analyzing the operational level big data, healthcare organizations can gain the business intelligence for further strategy development, for example how to improve the healthcare quality, how to provide better long-term care, and how to empower the patients. This chapter discusses this process as operations-intelligence-strategy (OIS) process in healthcare. Objectives are understanding how to gain business intelligence from sensor data mining in healthcare, biomedical signal analysis, and biomedical image analysis, and exploring the applications and impacts of the OIS process, with a focus on the sensor data mining in healthcare.

Leveraging Intelligence in Value Creation Across Provider Patient Ecosystems

Value creation in healthcare calls for the design of care plans that integrate the activities of clinical and non-clinical actors of both the provider and patient ecosystems as they work towards the shared goal: ensure patient adherence outside the provider ecosystem. Given the differing institutional mechanisms that influence actor behavior, intelligence gathered through digital services has two objectives. The first objective is to use digital services to track patient adherence to care plans, so that these care plans can be adapted as needed. The second objective is to learn about the characteristics of the patient ecosystem, so that incentives can be designed to ensure that all actors are working towards the same shared goal. This chapter uses a service modeling approach to explicate the interconnected role of actors across ecosystems and develop strategies to address these two objects. Several use cases are used to illustrate this approach.

Billing and Review Perspectives in Healthcare

The relatively recent and more pervasive retention of electronic healthcare data has provided new opportunities for the advancement of analytics and business intelligence tools within healthcare. The tasks comprising the delivery process for healthcare provide numerous points for data capture, and associated analyses to improve efficiencies and quality of care. In general, healthcare data is extracted from transaction-based systems designed for billing, scheduling, and workflow. However, data characterizing medical events can be further leveraged to assist in the diagnosis and treatment of patients. In fact, healthcare information technology (HIT) to improve patient diagnosis and treatment is remarkably neglected. This chapter outlines the process flow for healthcare delivery, describes the data extracted during this process flow, details the enablers and inhibitors of HIT and accompanying analytics, presents concerns about data integrity and quality, and provides some methods for data cleansing and staging.