It might be a bit of a leap to associate quality data with improving the patient experience. But the pathway is apparent when you consider that physicians need data to track patient diagnoses, treatments, progress, and outcomes. The data must be high quality (easily accessible, standardized, comprehensive) so it simplifies, rather than complicates, the physician’s job. This becomes even more important in the pursuit of population health, as care teams need to easily identify at-risk patients in need of preventive or follow-up care. Patients engaged in their own care via portals and personal peripherals contribute to the volume and quality of data and feel empowered in the process. This physician and patient engagement leads to improved care and outcomes, and, ultimately, an improved patient experience.
Learn more about Dr. Ed Corbett
Edward Corbett, M.D. joined Health Catalyst in June 2014 as a medical officer. He earned his medical degree at the University of Texas Health Science Center in San Antonio where he also completed his residency in Internal Medicine. He is board certified in Internal Medicine. He started his career as a physician at the Cooper Clinic in Dallas, Texas specializing in preventive medicine. Prior to joining Health Catalyst he was a physician partner at Central Utah Clinic, a large multispecialty clinic which was the first Medicare ACO in the state of Utah. He has a special interest in improving patient care through the better use of technology and has been actively involved in clinical IT throughout his career.
Read articles by Dr. Ed Corbett
Machine learning in healthcare is already proving its worth in clinical applications. From identifying tumors in mammograms, to diagnosing skin cancer and diabetic retinopathy from images, algorithms can perform certain duties more quickly and reliably than humans. While only used for specialized medicine now, the time will come where every practitioner and patient will benefit from cyber-assisted bedside care. This won’t develop without ethical implications, but the advantages that machine learning will bring to healthcare in terms of lower costs, improved quality of care, and greater provider and patient satisfaction, will easily outweigh those concerns.
In this article, Dr. Ed Corbett explores the intricacies of machine learning from two perspectives: as a physician and as a family caregiver with a personal story about how this data science could benefit patient lives today.
Perceptions of standardization and personalization vary widely by healthcare industry role. Advocates of standardized care say it improves efficiency, outcomes, and patient safety. Advocates of personalization, however, don’t want to see a one-size-fits-all approach become the norm. They want to see a healthcare system in which physicians treat patients like unique individuals.
But what if standardization and personalization didn’t have to be mutually exclusive? What if these historically competitive approaches to care improvement could work together to improve care?
Dr. Corbett describes how health systems can prioritize standardization and personalization using data to bridge the gap. Data enables informed decision making, customized treatment plans, and patient engagement. It supports both standardization and personalization approaches in the ultimate quest for care delivery improvement.
Optimize physician workflow and you’ll contribute to optimizing patient care. But what is it physicians look for to improve diagnoses, decision-making, patient care, and ultimately, outcomes? To answer this, consider what constitutes ideal working conditions in any industry: the right tools, training, and information to maximize productivity and deliver results. Physicians need analytics integrated into the EHR to maximize their efficiency, a common quest among the chronically overworked. And by flowing the universe of global, local, and individual data back into an enterprise data warehouse, a healthcare system can close the analytics loop, and begin to realize true precision medicine.
While working as an internist at an outpatient clinic, I would see physician performance reports that would tell me little more than if I was doing “good” or “bad.” There was no way to know how I compared to others. My colleagues, who also received these reports, and I didn’t trust the numbers either. In short, the reports were useless. Then, I discovered creating reports with a data warehouse. This addresses issues in six ways: 1. There is a cleaner data set and physicians don’t need to worry about fixing the data. 2. It addresses the “but my patients are different” argument. 3. The information is up-to-date. 4. The data is granular and detailed. 5. Physicians take ownership of the data because they are involved in the process. 6. Finally, it saves valuable time. When reports are created this way, physicians can make real change in their behavior and improve patient outcomes.
The Clinical Integration Hierarchy: A Primer on the Backbone of Data-driven Quality and Cost Improvement
Healthcare delivery is typically siloed into departments and care settings. But accountable care and value-based payment models require organizations to coordinate care across the continuum. To accomplish this, the Clinical Integration Hierarchy groups healthcare into work process that reflect how care is actually delivered. At the most granular level are care processes such as AMI and Cardiac Rehab (some of which are further divided into sub-care processes such as when AMI is divided into PCI and CABG). Next, care process families form the link between care processes through common pathologic conditions. Finally, the care process families comprise clinical programs such as Cardiovascular and Behavioral Health. The Clinical Integration Hierarchy forms the foundation for systematically tackling quality and cost improvement.