Data science holds huge potential in healthcare, but many executives are unaware of the technology's many capabilities and applications.
There are four main analytics-based approaches in data science — predictive, prescriptive, descriptive and diagnostic — each is defined as follows.
- Predictive analytics uses statistical models and forecasting techniques to answer "What could happen?" These tools are often used to understand future events or predict possible patient outcomes.
- Prescriptive analytics uses optimization and simulation algorithms to answer "What should we do?" These approaches are often used to advise action based on potential outcomes.
- Descriptive analytics uses data aggregation and mining to answer "What happened?" These tools are often used to gain insight into the past.
- Diagnostic analytics uses data discovery, or mining, and correlations to answer "Why did it happen?" These approaches are often used to examine data or content.
Recently, a fifth approach — behavioral analytics — has grown in popularity, approaching "buzzword" status. In healthcare, behavioral analytics often answers the question "Will patients be engaged?" But it can also be turned back on hospitals for insight into how providers can improve their workflow and patient relationship.
Robert Lord, co-founder and president of cybersecurity firm Protenus, recently spoke with Becker's Hospital Review to clear up the confusion surrounding these emerging technology trends in the healthcare sector.
Here are seven things to know about behavioral analytics and how hospitals can apply these tools.
1. Behavioral analytics can use data from an organization's workflows to track employee behavior.
"It's the development of a comprehensive understanding of an individual's patterns of behavior traditionally in electronic systems ... and it uses data from an organization's workflows to better understand how employees, third parties [and] other individuals who have access to those types of systems are [using] those systems, whether appropriately or inappropriately," Mr. Lord says.
For example, these tools can extract information for a hospital's EHR to determine whether an employee was inappropriately accessing a patient's medical data.
2. These tools don't just identify bad behavior, though. They can help pinpoint things that are happening effectively and drive the best behavior and workflows for specific departments.
"You're really able to leverage the institutional knowledge on a user by user basis of all these types of systems," Mr. Lord says.
3. As with most analytics approaches, the more data organizations open the tool up to, the richer the insights become. Mr. Lord recommends looking to the EHR, human resources systems, medication systems and information from public sources, like social media, to create a more complete picture of that individual, which Mr. Lord likens to their fingerprints. With an analytics tool, those "fingerprints" can be tracked throughout an organization — from its computer systems to its doors that require key card access — in order to ensure each employee is doing what they should be doing, when they should be doing it.
4. It is crucial that organizations think about patient safety and data security when building their behavioral analytics solutions, Mr. Lord adds.
"You've got to have that transparency within your organization — that comfort with speaking up when you think something might be wrong — and that continuous desire to improve because obviously the threats out there are only getting more advanced," he says. "You've got to have continuous evolution of your own security posture … if you are using any types of sensitive data"
5. What's more, behavioral analytics can enhance patient engagement. Since it documents how a person does something, it can provide insight on how clinicians treat, interact or communicate with patients, Mr. Lord says. More specifically, behavioral analytics empowers trust by continuously ensuring the information in the EHR is accurate and not being exploited or accessed without authorization since it continuously monitors employees' patterns of use. It may even provide insight into ways the organization can elevate the patient experience.
"It gives patients confidence to know you are doing everything you can to give them the best possible experience that can lead to the best possible outcomes," Mr. Lords says. "More than anything, that trust that you are generating — there is nothing more effective to drive patient engagement."
6. However, some hospitals and health executives face challenges or unease when approaching these new horizons. They are often apprehensive when they see the upfront cost of behavioral analytics solutions. In the long run, these solutions can lend to cost savings. For example, the tools can replace some cybersecurity solutions.
7. Mr. Lord says healthcare leaders should embrace the deep, rich insights they can gain from behavioral analytics tools.
"Fundamentally, we need to have that culture change, and part of that culture change is for the leadership to say, 'We've go to put our money where our mouth is,'" Mr. Lord says.
More articles on data analytics & precision medicine:
Politico: Dr. Patrick Soon-Shiong's genetic test sales boosted by sales to physicians on his payroll