Kickstarted in the 1990s, big data continues to alter everything healthcare. To date, most big data software investments in healthcare come from the insurers’ side. Public and private payers drive the shift to the value-based care realm by introducing care delivery quality measures for their provider networks and testing them with claims and service delivery analytics.
These measures then spread around and create certain benchmarks for performance evaluation among providers, also top-down affecting factors that hinder healthcare processes: fraud, unregulated costs, poor asset management and more.
With the transforming requirements and anticipations about care delivery, big data stands at the core of technology evolution, demanding more advanced healthcare software to generate, store, process, and analyze clinical information. In this article, we will explore the current use of big data in healthcare across the whole care cycle, touching upon the most recent technological know-hows.
The first of many benefits that big data brings into healthcare is supporting the proactive approach by offering various prevention options based on aggregation of patient data. At the patient level, smartphones and smart wearables, such as Jawbone, Fitbit, and Samsung Gear Fit help track basic vitals, including blood pressure, weight, temperature, and blood glucose.
A range of apps and smart devices support both healthy individuals that want to track their general wellbeing and patients with chronic conditions that need to balance their health status and prevent complications.
On a larger scale, Alphabet’s life sciences company Verily aims to improve current population health management efforts by tracking all biometric values from 10,000 volunteers and composing the baseline of human health.
The same population health improvement goal drives the Pittsburgh Health Data Alliance’s activities, who aim to aggregate the data from multiple sources—medical and insurance records, genetic data, wearable sensors, and social media use. This collected data will be then used to create cohesive patient profiles and offer patients customized healthcare packages.
Looking into heart disease prevention measures, Apple and Stanford Medicine partnered up for the Apple Heart Study. The study’s goal is to elicit and analyze irregular heart rhythms, like atrial fibrillation, and help patients avoid more serious cardiac health issues, such as heart failure and stroke.
When it comes to diagnosis, patients are eager to get more information about their possible conditions, treatment options, and anticipated outcomes. The self-awareness wave, emerged with the first wearable sensors, expands to genome sequencing.
Patients turn to various genetic test kits, such as 23andMe and Color Genomics, to get on the informed side of their specific genetic susceptibilities. To get the result, they need to spit into a special tube, register this saliva collection tube via the barcode, and mail the specimen back to the lab. Currently, genetic test results can gauge the risk of developing certain hereditary disorders and chronic diseases, including Alzheimer’s and cancer.
However, patients are not the only ones wanting to get more valuable information. Providers collect huge amounts of data, but it is fragmentized across individual PCP’s offices, hospitals, and clinics. The demand for unifying and connecting this data with the information from wearable sensors to extract diagnosis suggestions stays poignant in 2018 and in upcoming years as well.
The good thing is there are already some successful cases of handling big data in medicine to admire and explore. The Johns Hopkins Hospital in Baltimore spots an AI-powered “data command center” that pulls in data from dozens of streams in real time, accessing EHR, emergency dispatch service updates, and lab results, while simultaneously checking hospital beds availability.
Based on acquired data and using human-trained algorithms, the center makes immediate decisions on triaging patients and transferring them into a proper facility, also notifying the care team on site. This approach is highly successful with medical emergencies because every minute is critical in such situations. Of course, the financial benefit of big data in healthcare within this case is undeniable.
According to Jeff Terry, the GE Healthcare overseer for the Hopkins command center project, “there’s been about a 60% increase in the ability to accept complex cancer patients, an over 25% reduction in emergency room boarding, and a 60% reduction in operating room holds with the command center since its launch in February 2016.” In 2018, GE also plans to announce 10 new command centers for 30 different providers. As Terry claims, the centers should yield a roughly 4 to 1 ROI.
Another state-of-the-art example of big data in medicine comprises software capable of recognizing patterns in patient data (for example, IBM Watson). Currently, machine learning allows these programs to identify and localize malignancies in test results. Further technology evolution will hopefully bring in a wider range of early diagnosis possibilities for more conditions, allowing physicians to achieve better patient health outcomes.
When a patient’s journey continues to the treatment stage, big data can substantially expand the clinical expertise of health specialists. With deep learning algorithms, providers can access the summary of existing medical knowledge and research on a particular condition or medication option. Practically, big data in the healthcare industry is similar to Sherlock Holmes in criminology, finding more clues and turning educated guesses into informed decisions.
As a result, providers can tune the treatment plan to a particular patient and lower the risk of severe side effects or exacerbations, which is crucial for cancers and other chronic conditions.
Big data also helps to fight the medication nonadherence problem, costing about $100—$300 billion a year due to complications developing when patients struggle with following the recommendations for prescribed treatment.
Express Scripts, the Missouri-based PBM, has defined 300 different factors and created a custom algorithm that identifies whether a patient will follow prescriptions. The factors include basic demographic data with income level and zip code, behavioral data, even genders of the prescriber and the patient.
Express Scripts states that their proprietary algorithm performs with 94% accuracy assigning risk scores to patients. The company then reaches out to high-risk patients via various channels, and it seems to work out well for everybody. Express Scripts reports reducing nonadherence rate by 37% and saving more than $180 million for their clients.
Blue Cross Blue Shield, in their turn, aim at preventing opioid abuse cases. Teamed up with Fuzzy Logix, the company worked their way through years of insurance and pharmacy data. As a result, they came up with whopping 742 risk factors and an algorithm to sift through groups of patients and identify those at risk of misusing opioids.
Of course, it is challenging to prevent at-risk individuals from developing an addiction to opioids, but the companies strive for at least reducing the number of abuse-related deaths with timely interventions.
A patient’s rehabilitation from an acute episode doesn’t stop when they leave the hospital, that’s why providers have the 30-day readmission rate as one of the crucial benchmarks for clinical performance evaluation. Big data bonds with deep learning to assist patients in need of follow-ups and long-term care, providing them with a better understanding of their current health status, and helping them avoid complications or medical emergencies.
Smartphones and wearable sensors are prevailing tools to handle patient data at this care point.
For example, GPS-enabled inhalers for asthmatics can record information about a patient’s physical location, sleep patterns, and physical activity to recognize if he or she may be feeling unwell.
In such a case, the inhaler will alert all authorized care team members and family about possible anxiety episodes or panic attacks.
As another example, apps for diabetes patients can provide them with daily nutrition and activity suggestions, offer therapeutic education and record blood glucose entries to keep everyone involved in the care cycle aware of the patient’s diabetes management progress.
As the tendency goes, patients gradually evolve into full-fledged customers similarly to their roles in other industries. Yes, “care consumers” sounds a bit off for now, but the whole ecosystem moves towards consumerism. One of the indicators is that EHR vendors are putting their systems into the cloud and embellishing them with CRM-like functionality, allowing caregivers to create comprehensive patient profiles and initiate multichannel communication with them.
In patient-centered healthcare, big data brings forth an array of technologies that put the control over the care cycle in the hands of patients themselves.
Some providers embrace the changes and put extra effort to adopt emerging technologies as soon as possible because they plan to gain strategic advantages in the competition. Others stay on a more cautious side, waiting up until long-term trends will reveal themselves and separate from fads. Although only time can tell the winning approach, we think that you can’t really go wrong with the technologies that target using big data for more informed and connected care delivery.