Clinicians favor small data over big data for healthcare assessments and predictions. Here’s why
The healthcare sector is fragmented, complex, and hyper-local. There are over 100 healthcare systems in the US, 280 health information exchanges, and over 5500 hospitals. One million physicians are addressing the healthcare requirements of 320M Americans. While all these channels spit out data, leading to what is popularly known as big data for healthcare, there is another quiet and continuous flow of data from individuals or in this case patients, called `small data’.
Deborah Estrin, Computer Science at Cornell Tech and Healthcare Policy and Research at Weill Cornell Medicine puts it succinctly when she says, “Small data is being generated continuously on our mobile phones and through our online activities: walking and location patterns, as well as shopping, communicating, and web surfing. It is the various data traces we each generate every day, just by living our day-to-day routine: checking email, taking the bus to work, going grocery shopping, walking home, and more.”
Why clinicians prefer Small Data to Big Data for healthcare prediction models
The big difference between big and small data is in big data large volumes of data are analyzed for patterns while small data looks at an individual’s historical data to develop models for predictions and futuristic treatment.
While big data has been at the forefront in healthcare technology for some time now, clinicians are often turning to small data to efficiently manage patient care. Small data helps them by providing quick input on allergies, times for blood cultures, missed appointments, and so forth, which are tactical in nature but extremely important inefficient patient care. Big data for example can say, X number of patients were admitted in the ER during a certain period of time. Can big data quickly identify how often or why Mr. or Mrs. John was admitted to the ER last month?
Small data is providing big insights for the individual. An app for managing pain for example quietly collects data about the individual, such as a fitness tracker, and can be presented to the individual and his clinician. In similar ways, smartphones can track heartbeats, eating habits, fitness quotient and you name it, to empower the clinician with insights into a person’s physical well-being.
The rising importance of Small Data in healthcare technology
Technology companies see the potential of smartphones in healthcare and innovative solutions are being unleashed. For healthcare ISVs, the challenge is to connect small data to big data, to improve individual healthcare, even as solutions are uncovered which can have a far greater impact on a larger target group. Not stopping there, the hidden challenge is to ensure privacy even as data that is collected is assessed and answers are uncovered.
Healthcare systems that have implemented electronic health records (EHR) can extend this to patients. If the systems can integrate individual health information, then both physicians and patients are maximizing digital health technologies.
|Big Data Model||Small Data Model|
|What can be the effect of immunization programs?||Is my child’s immunity to diseases taken care of?|
|Where do some of the healthiest people in the world live||Is my diabetes medication working as expected|
|Are there any generic factors to identify a disease||Am I susceptible to X disease?|
Some suggested systems include:
- Health information exchange
- Point-of-care decision support systems
- Workflow tools to track and report on patient health
- Smartphone and online appointment setting and registration.
Trigent Software understands the healthcare space having served a large number of clients over the last 20 years. Our commitment to patient healthcare has resulted in our focus on small data to improve the quality of patient care, reduce healthcare costs, and enhance patient loyalty.