Towards a Better and Smarter Healthcare and IoT

Towards a Better and Smarter Healthcare and IoT

Navin Kumar (Advisory Board Company, USA)
Copyright: © 2019 |Pages: 38
DOI: 10.4018/978-1-5225-6207-8.ch009
OnDemand PDF Download:
No Current Special Offers


The amount of healthcare data continues to exponentially grow everyday. The complexity of this data further limits the analytical capabilities of traditional healthcare systems. With value-based care, it is far more imminent for healthcare organizations to control the costs and to improve the quality of care in order to sustain their business. The purpose of the chapter is to gain insights into complexities and challenges that exist in current healthcare systems and how big data analytics and IoT can play a pivotal role to positively influence the quality of care and patient outcomes. The chapter also provides solutions and strategies for building cloud-based data asset that can deliver rich data analytics to both the healthcare systems and the patients.
Chapter Preview


Healthcare is complex and expensive. Healthcare expenses continue to steadily increase over time. In United States alone, healthcare spending has risen to $2.7 trillion or about 17.8% of Gross Domestic Product and costs $9,990 per person (CDC Health Expenditures, 2017). In other words, on a measurement plot defined by population and economy, the healthcare expense is already surpassing by more than $600 billion compared to a benchmark presented by (Kayyali, Knott, & Kuiken, 2013). In terms of general health globally, more than 95% of the world’s population currently suffers from one or more chronic health problems (cardiovascular diseases, diabetes, respiratory diseases), according to the Global Burden of Disease Study 2013 (Vos et al., 2015). The same study also states that health problems are also a result of patients living longer with modern medical science but with a greater number of expensive and weary health problems.

Market research suggests that 86% of United States healthcare expenses go into chronic disease treatments and it is the most expensive, intractable, and the rapidly growing health problem. As of 2012, about 50% of adults suffered from one or more chronic conditions. In a 2014 survey (CDC Morbidity, 2016), 70% of top 10 root causes for mortality were the chronic conditions. In fact, heart disease and cancer, the two chronic diseases, amounted to 46% of all deaths. Another chronic disease, that continues to spread rapidly, is the obesity and makes up of 36% of all adults with BMI ≥ 30 kg/m2. Diabetes accounts for $245 billion in medical costs annually and is already identified as the leading cause of kidney failure, non-injury lower-limb amputations, and even causing blindness among adults.

Besides being expensive, healthcare is also enormous in its data volume. Healthcare systems continue to accumulate exabytes and zettabytes of data (Raghupathi & Raghupathi, 2014). While other industries and businesses are already adapting to modern analytical and Big Data solutions, healthcare still lacks behind in such capabilities.

In terms of real issues and challenges, there are many non-trivial analytical problems to solve in healthcare. For instance, how could a provider have a single comprehensive view of the patient to make informed decisions? What if patients could share their IoT health monitoring data with healthcare organizations, which could help predict better patient outcomes? How could patients get access to personalized healthcare resources such as for aged or chronically ill population? What if patients could communicate with providers more frequently and effectively to seek their consultation? How could patients provide real time feedback that could feed into healthcare systems and show up in performance dashboards? Could patients be given a predictable wait time at medical facilities to reduce their anxiety and distress? These are just some of the pressing challenges that healthcare organizations continue to face everyday in their naturally complex and diverse healthcare data.

As the modern technologies continue to evolve, Big Data and Internet of Things (IoT) has enormous potentials to transform these challenges into opportunities to produce a better healthcare (Schneeweiss, 2014; Raghupathi & Raghupathi, 2014; Dey, Hassanien et al., 2018). Imagine the health and cost benefits if systems can auto-detect and prevent the onset of disease, or manage disease before it reaches the extremely costly treatments (Kamal, Dey et al., 2017). Improving patient outcome by utilizing IoT devices (Bhatt, Dey et al., 2017) can be a true incentive for providers. In current Value-based care model, reimbursements for care services tie to the quality of patient care. A high quality of care generates greater hospital revenue by receiving timely reimbursements and rewards from payers and insurance companies. Better outcomes further lead to healthier patients who are more willing to partner with providers than ever before.

Key Terms in this Chapter

Population Health: Emphasis on improving health outcomes of a group of patients such as diabetic or cardiovascular patients.

Quality of Care: The degree to which medical treatments and care services provided to patient yields to the increase in likelihood of positive results.

Patient Encounter: An interaction between patient and healthcare providers to receive the care and treatments.

EDW: A central repository of integrated data used for reporting, analytics and machine learning.

Chronic Disease: A disease that persists for a long time and cannot simply be cured with vaccines or medications such as diabetes, arthritis, hypertension.

Personalized Care: Custom medical treatment approach depending on individual patient’s health and medical history.

CDC: Centers for Disease Control and Prevention; a federal agency to conduct and support disease prevention and population health improvements.

Cloud Computing: Delivery mechanism of computing services (server, storage, database, networking, software) over the Internet.

EHR: Maintains electronic version of patient medical history and makes it easy to share across healthcare entities.

Complete Chapter List

Search this Book: