How Health Care Data Analytics Improves Quality of Care

A doctor updates her patient’s electronic health record on a tablet.

Organizations across industries use data analytics (the process of analyzing large volumes of data to find value) to increase revenue, reduce costs, create operational efficiencies and improve overall performance. Data analytics used by hospitals, clinics and other health care providers can do all that and even more — it can also help save lives. Professionals interested in learning how to leverage the power of health care data analytics may consider pursuing an advanced degree such as an Executive Master of Health Administration.

How Data Analytics Is Used in the Health Care Industry

Health care data analytics can deliver better patient services and improve patient outcomes. This is especially true when it is used to analyze patient data in electronic health records (EHRs) and external health care sources such as disease registries and clinical trial studies. However, it is important to realize that analytics are only as good as the underlying health data, some of which can fall prey to the same structural biases that afflict other areas of society. According to the Healthcare Information and Management Systems Society (HIMSS), data diversity, as well as regulations and policy changes, will be necessary to ensure unbiased analytics.

That said, health care data analytics help health care organizations in the following ways.

Identify At-Risk Individuals

Data analytics can help identify at-risk individuals in need of chronic disease management services, resulting in better health outcomes and reduced costs. For example, health care providers can review data about a patient from health care records, such as an EHR. The data can include information about medications, reported symptoms, medical visits and hospitalizations, providing insights into a patient’s health journey and risk factors.

By identifying individuals at risk of chronic diseases early on, health care providers can prescribe preventative medicine and therapies. This helps minimize hospitalizations, reduce health care costs and maximize hospital resources for patients needing immediate critical care.

Skin cancer is one area in which machine learning algorithms can have a life-saving impact, although, as pointed out by HIMSS, it is also an area susceptible to bias as data sets focused primarily on light skin tones are less effective at skin cancer detection for those with darker skin.

Improve Patient Diagnosis and Treatment Methods

In addition to revealing patient risk for chronic conditions, health care data analytics can help improve diagnosis and treatment of those conditions. A study in the Journal of Clinical Oncology Clinical Cancer Informatics reveals how a tool called TransPRECISE can “guide pathway-based personalized medical decision making.” The tool analyzes data from 7,714 patient samples and 31 cancer types to help determine which medicines work best on different types of patients.

This type of data can help health care researchers evaluate the therapeutic efficiency of certain drugs on patients’ tumors. It also helps health care practitioners accelerate personalized, life-saving medicine to treat their patients.

Uncover and Combat Health Disparities

Through predictive analytics, (a type of analytics that uses models, statistics and machine learning algorithms), health care providers can uncover clusters of diseases and disorders among certain communities and groups.

For example, according to the Centers for Disease Control and Prevention (CDC), high blood pressure is 50% more likely among Black Americans between 35-64 years than whites in the same age group. Further review of historical and real-time data reveals that individuals’ social and economic conditions are primary factors behind this health disparity.

This information enables health care providers to identify individuals in high-risk groups. The objective is better disease management in the early stages of the disease and the creation of opportunities to develop programs that help address the factors that drive health disparities.

As noted earlier, however, it will be important to address data bias to prevent analytics from furthering health disparities. It is generally the very communities and groups we discuss here that are underrepresented in health care data to begin with. Fortunately, unlike biases in people, biases in data can be easily discovered, allowing health care providers, technology firms, regulators and policymakers to work together to combat this issue.

In a related context, data analytics can play a role in addressing public health issues such as mental health, which impacts 51.5 million people in the U.S., according to the National Institute of Mental Health. The Bloomberg Health Initiative provides case studies and tools to allow practitioners and health care providers to use data-centric approaches to solve public health challenges.

Identify Environmental Factors That Influence Disease Progression

According to the World Health Organization (WHO), 4.2 million people die from ambient air pollution-induced diseases such as chronic respiratory diseases, heart disease and lung cancer. Other environmental factors that influence disease progression include poor water supply and sanitation, lack of access to health care, and industrial pollution. HealthyPeople.gov reports that preventable environmental factors cause 23% of all deaths.

Data analytics can help predict how environmental factors such as air pollution, poor water supply and unhealthy sanitation trigger disease in certain regions. With this data, the health care industry can more accurately determine the demand for medicines to avoid shortages. Additionally, the data can help organizations develop clinical and informational strategies to prevent disease in the most affected communities.

How Data Analytics Helps Health Administrators

There is growing momentum for data analytics in health care. Some 60% of health care executives currently use health care data analytics in their organizations, according to a Society of Actuaries survey. Of those executives, 42% saw improved patient satisfaction and 39% reported cost savings. Value-based programs from the U.S. Centers for Medicare & Medicaid Services have contributed to increased data analytics in health care. For example, the Hospital Value-Based Purchasing (VBP) Program offers financial incentives to hospitals that improve health care provider performance.

Health care data analytics empowers health care leaders with essential data to identify operational practices that can improve health outcomes while reducing health care costs. It also helps health administrators analyze administrative and financial data, health care staff scheduling trends and patient satisfaction rates. From a business and service standpoint, data analytics helps health administrators uncover opportunities to improve operations and administration and lower health care costs.

Leverage Data Analytics to Lead in Health Care

Amid the COVID-19 pandemic, health care leaders face unprecedented challenges. These leaders — from the scientists responsible for developing the vaccines to health administrators running hospital operations — have used data to inform, innovate and help move society forward to a post-pandemic world.

But even after the pandemic, data analytics will continue to play a key role in addressing pressing issues such as inequities in health care access and quality of care. Tomorrow’s health leaders will need to be prepared to effectively use data analytics to find solutions to these and other challenges, while also recognizing and helping remedy the structural biases in data that can lead to subpar patient outcomes.

USC’s Executive MHA (EMHA) program offers individuals interested in improving health services the tools to advance their careers. The curriculum is geared toward health care administration professionals looking to expand their data analytics, business, policy and modern health management practice competencies.

Discover how the online EMHA program can help you utilize data analytics tools to lead the future of health care.


Recommended Readings

Telemedicine, COVID-19 and the Future of Healthcare

Healthcare in 2021

Day in the Life of Executive MHA student | Stacy Tarradath, MD



Centers for Disease Control and Prevention, National Center for Chronic Disease Prevention and Health Promotion

Centers for Medicare & Medicaid Services, "What Are the Value-based Programs?"

Datapine, "18 Examples of Big Data Analytics in Healthcare That Can Save People"

Deloitte Insights, "Predictive Analytics in Health Care"

Health IT Analytics, "3 Ways Predictive Analytics is Advancing the Healthcare Industry"

Health IT Analytics, "Big Data Analytics Tool Could Help Guide Cancer Precision Medicine"

Health IT Analytics, "Case Studies Apply Big Data Analytics to Public Health Research"

Health IT Analytics, "How Big Data Analytics Models Can Impact Healthcare Decision-Making"

Healthcare Information and Management Systems Society, “Uncovering and Removing Data Bias in Healthcare”

HealthyPeople.gov, Environmental Health

Journal of Clinical Oncology Clinical Cancer Informatics, "Personalized Network Modeling of the Pan-Cancer Patient and Cell Line Interactome"

National Institute of Mental Health, Mental Illness

Sisense, "What Is Healthcare Analytics?"

Society of Actuaries, "2019 Predictive Analytics in Health Care Trend Forecast"

World Health Organization, Ambient Air Pollution