Delivering Data-Driven Personalized Medicine at Scale
Despite all the information, data and technology available to us, hospitals still struggle to determine which treatments work best for their patients at the lowest cost. One of the most significant barriers to administering personalized treatments is time—at present, there's just too much data for healthcare professionals to handle.
Inevitably, our inability to access and understand patient healthcare data leads to high costs and poor outcomes in the U.S. The question is: How do we fix the problem? The key is in unlocking the power of the data itself.
Here, we’ll explore how data is changing the way we deliver personalized medicine and how data professionals will play a key role in the future of healthcare.
Challenges to Leveraging Data for Personalized Medicine
Although hospitals have made progress in leveraging big data in healthcare, most remain inefficient. Doctors are already strapped for time, and they are not equipped to handle the deluge of patient data they encounter day-to-day, much less use it to provide optimized patient care.
Data silos are also a continuing problem. The healthcare industry has always been fragmented, and despite some progress being made to unify it (such as with the standardized formatting of electronic medical records), there are still glaring inefficiencies.
For example, a study conducted on the efficacy of a particular treatment may yield promising results, but those results are disconnected from the various touchpoints throughout the industry. Every patient has unique health needs, so those variables must also be taken into account when determining the effectiveness of a treatment and how best to use it. Furthermore, the ability to deploy treatments depends on a long infrastructure of manufacturers, suppliers and distributors, all of which can have an impact on clinical outcomes.
The adoption of big data analysis in healthcare has also lagged behind other industries. According to one report, 80% of executives from financial services, insurance, media, entertainment, manufacturing and logistics companies say their investments in big data processing have been “successful.”1
To make on-the-spot decisions, healthcare professionals need real-time access to patient data as well as insights drawn from big data analytics that are understandable and actionable. Without a clear view of all the data that can affect their decision-making, they must focus on old and costly healthcare models such as “trial-and-error” treatments.
How Data Science Increasingly Impacts Personalized Medicine
In an ideal world, personalized medicine would follow the principles of “the uncannily accurate recommendations served up by online stores and streaming services,” as the University of Chicago Medical Center puts it.2
We aren’t there yet, but even though we aren’t as far along as we’d like to be in applying data to personalized medicine, there are some clear cases in which data has improved clinical outcomes. Here are just a few ways that data science can help deliver more effective personalized medicine.
Creating a Timeline of the Patient’s Journey
Patient journey mapping—also known as “healthcare process mapping”—has become an integral part of building a better patient experience at hospitals. As an exercise, it helps healthcare leaders understand how patients interact with their hospital and health system.
Patient journey maps can be created by collecting data at various touchpoints throughout the hospital and combining them with unique patient data. That data can then be analyzed and aggregated to a visualization platform, where leaders can see the patient journey in an easy-to-use format. This helps them identify opportunities for improvement in patient communications, create personalized patient experiences and maintain patient retention.
Shifting from Reactive Medicine to Preventive Medicine
One of the most significant promises of big data is the ability to shift from reactive medicine to preventive medicine. Big data can come from various sources, including medical suppliers, wearable devices, EMRs, pharmacies and healthcare providers themselves.
This enables health care professionals to provide more accurate diagnoses and assessments.
Predicting Patients’ Susceptibility to Disease
Similarly, healthcare providers can use big data to create a more holistic view of their patients and their susceptibility to certain diseases. Data acquired in healthcare settings can be combined with demographic information, local data and other sources to determine a patient’s vulnerability to certain types of diseases.
For example, healthcare providers and machine learning algorithms may determine a patient is at higher risk of diabetes if they have a history of poor nutrition, they fit a high-risk demographic, they live in an area where it’s difficult to get fresh food (a “food desert”) and their community is likely to have polluted air, soil or water.
Prescribing More Effective Drugs
Pharmacy practices is another area of the healthcare system that has been influenced by data. There are several steps before a drug can reach a patient’s hands. It must be manufactured, distributed, prescribed and sold, all of which generate data.
Traditionally, this data was used to ensure the right prescription reached the right patient. Now, that data can be used to manage healthcare plan expenditures and provide more effective treatments. Prescription plans can be tailored to the unique needs of each patient, and big data collected on how consumers use prescription drugs can help to reduce costs.
Eliminating “Trial-and-Error” Inefficiencies That Inflate Costs
In the past, treating illnesses usually began with a diagnosis, which then leads to treatment. But if the diagnosis was wrong or the treatment ineffective, doctors had to go back to the drawing board, wasting precious time and resources.
Moving forward, doctors can provide more precise health interventions by collecting and analyzing data from vast patient populations. Using AI and machine learning, they can leverage this data to provide more accurate diagnoses and treatment regimens based on a patient background and unique health identifiers.
The Healthcare Industry Needs Data Professionals
To deliver these outcomes, there is a growing need for data science professionals in healthcare.
According to a paper in BMC Medicine, part of Springer Nature, “There is a need for an interdisciplinary effort, including data scientists, physicians, patient advocates, regulatory agencies and health insurance organizations [concerning personalized medicine]. Partially unrealistic expectations and concerns about data science-based solutions need to be better managed. In parallel, computational methods must advance more to provide direct benefit to clinical practice.”3
If you’re interested in a healthcare-based data science career, you don’t need to be a doctor or nurse to pursue it. Start with EmergingEd’s online healthcare data courses. You’ll get the foundation you need to pursue a career in healthcare analytics, so you can start making a difference in patient outcomes.
- Retrieved on September 21, 2020, from catalyst.nejm.org/doi/full/10.1056/CAT.18.0290
- Retrieved on September 21, 2020, from uchicagomedicine.org/forefront/research-and-discoveries-articles/data-driven-medicine
- Retrieved on September 21, 2020, from bmcmedicine.biomedcentral.com/articles/10.1186/s12916-018-1122-7