Implementing digital patient-doctor communications is great for healthcare providers, too. A study from Veroff and colleagues showed that chronic disease patients given “enhanced support” through phone, mail and digital communications with their healthcare teams had 5.3% lower medical costs, 12.5% fewer hospitalizations, and even 20.9% fewer preference-sensitive heart surgeries. Lower medical costs translate to healthier bottom lines for practices and healthcare systems both large and small, especially those engaging in resource-intensive collaborative care.
With the CDC reporting that 86% of U.S. healthcare costs go towards chronic disease management, technologies that improve doctor-patient communication are crucial. And because most chronic disease patients are affected by more than one condition—and many are supervised by multiple clinicians—tech that streamlines collaboration and efficiency is very important to CCM outcomes for each individual patient served.
Whether technology helps patients share the subjective or the objective—that is, whether a patient decides to communicate feelings and concerns about the treatment plan, or agrees to share biometric data furnished by modern wearables or other devices—it will lead to more confidence in health decisions on either side.
Compliant Sharing of Patient Data
In order for Health IT applications to exert their promised positive impact on chronic care management, medical data has to be shared in compliance with established privacy and security laws. The recent, rapid progress made in compliant sharing will yield unprecedented medical insights for disease treatment and prevention. Again, huge reductions in cost for all health stakeholders are in view.
In the U.S., ensuring HIPAA compliance from development to launch is a crucial step in future-proofing patient empowerment technologies. Creators of new digital applications endeavoring to use PHI must abide by HIPAA rules, which can be ensured in part by running through a thorough checklist in the ideation and early development stages.
The new HITECH standards for protection of PHI anticipate the importance of new, patient-facing technologies to common healthcare scenarios—all while ensuring PHI is safe and handled ethically. And the Final Rule modification to HIPAA, published in 2013, paves the way for even more data collected from patients at one point in time to be used at some future point.
Some exciting developments are underway because of the necessary flexibility of the new rules. A review of privacy and security in mHealth research for Alcohol Research: Current Reviews suggests that by adhering to HIPAA and HHS’ protection of human research subjects via the Common Rule; by ensuring patients can access their own EMRs and personally authorize others to use the records, and by employing security best practices like 128-bit key encryption, two-factor authentication, remote data wiping and biometric verification (for example, fingerprinting), mHealth research can move forward and deliver on its promise.
The Future: Machine Learning and Public Health Policy
Machine learning makes possible what was never possible before, with huge implications for both health research and clinical recommendations at the point of care. Using the vast swaths of data that can be compliantly shared through health IT applications, predictive analytics and machine learning can be used to make better, more accurate, cost-saving medical decisions.
Programs that analyze data with less help from explicit instructions and rely more on self-learning—the fundamental capability of machine learning applications—will prove invaluable as research leads to approved treatments and changes in public health policy. But even before epidemiological studies and large-scale policy changes happen, which will inevitably take time, health systems of various sizes can use health IT platforms today to generate usable data for engaged patients and their care teams.
Both “supervised” and “unsupervised” machine learning will add to medical knowledge that improves quality of life and saves lives. That can play out in many ways. For example, a certain technology could elucidate a heart disease patient’s risk for hospitalizations, and thus, what steps should be taken to avoid those costly events. Or, the same technology could reveal certain patterns in both patient EMRs and social and behavioral survey data (crucial factors that used to be less-accounted for in the clinic or ER), leading to new ways of predicting risk.
Flahault and colleagues suggest that the “precision global health” ideal will yield enormous achievements such as better allocation of healthcare resources via humanitarian aid to specific countries, preventive genomic medicine, or signals of a spreading viral illness based on locally-popular search engine terms. All of these public health advances will be made possible and streamlined by machine learning, applied to compliantly-shared data in our digital age.
What does the future of chronic care management look like?
It starts with data that’s collected using comprehensive health IT platforms such as OrbHealth, that patients understand and can learn to enjoy using every day. The data is then shared back and forth between patients and their doctors, to create more comprehensive, sustainable day-to-day health management.
Then, aggregate data, and insights arising from it, can be compliantly shared among health system executives, physicians, epidemiologists and researchers of various specialties. Machine learning will likely be involved at every step to unearth disease risk factors and helpful interventions.
With all of this bringing the most useful medical discoveries to the forefront, clinics and health systems will see financial and human resource burdens lifted. And patients will be more engaged and better-served at the point of care.