Do health systems effectively leverage clinical analytics to drive real outcomes improvement? Holly Rimmasch, Chief Clinical Officer and Senior Vice President and General Manager of Clinical Quality Analytics at Health Catalyst, posed this thought-provoking question at the beginning of her Q&A interview podcast. Although leveraging clinical analytics that result in better care is a complex process, Rimmasch says it is possible, especially with the increased availability of healthcare data.
As healthcare organizations use data from increasing sources, organizations are still learning the best way to collect, organize, and distribute the most relevant data to end users. According to Rimmasch, the proliferation of healthcare data and clinical analytics has paved the way for better decision making across the industry.
Drawing from nearly three decades of healthcare experience—from direct patient care to clinical and operational healthcare strategy and various management and executive roles—Rimmasch shared four key aspects of clinical analytics that organizations should carefully consider if they want to achieve sustainable improvement:
The inception of the EHR made previously unseen clinical data widely accessible to healthcare organizations. While helpful in understanding a patient’s hospital experience, the EHR doesn’t provide a complete picture of an individual’s health. Organizations should also focus on acquiring other clinical data, including imaging, lab, and ambulatory data, because these data sets also contribute to understanding other valuable data points with health implications, such as prescriptions fills and refills.
Healthcare leaders should consider all data sources along the entire care continuum. EHR data is valuable but often doesn’t include specific information about a patient’s other routine care, such as filling a prescription. However, if a patient fills or refills a prescription, a claim is submitted with information about the drug, the dose, and the date. This information is significant and useful for the patient’s care team to know, but they can’t access it without claims data in addition to their EHR or clinical data. Therefore, organizations should consider multiple data sources beyond the traditional EHR.
Rimmasch said over her career, she has seen organizations leverage clinical analytics to improve preventive care, end-of-life care, and everything in between. She emphasized two specific ways she has seen organizations use data to advance care:
Target Individual Patients: When patients go to the clinician’s office, the care team uses data to identify at-risk areas they need to address. For example, if the patient has high blood glucose levels, the clinician might put him on a pre-diabetes care plan.
Target Groups: Early in her career, Rimmasch oversaw the care management program at a large healthcare provider and noticed that patients with heart failure would continue to readmit within a few weeks of discharge. When she looked at the heart failure data, she learned that in-person appointments within seven days of discharge, versus the routine phone call, allowed the care team to better assess how patients were faring after discharge and meet their specific needs. Rimmasch applied this analytic insight to the larger population of patients with heart failure to prevent unnecessary readmissions and accelerate healing in the home, if advised by the medical staff.
Data-driven improvement is a buzzword in healthcare, but there is truth to using data to drive long-lasting improvements, said Rimmasch. She provided a few key areas in which organizations can improve their clinical analytics use to inform better care:
EHR Alerts: To guide better care delivery, organizations can create custom alerts in the EHR-based on their own criteria. To avoid EHR alert fatigue and help the alerts catch provider attention, Rimmasch said that organizational leaders should prioritize the type and number of alerts each day based on the system’s high-priority areas.
Artificial Intelligence (AI) and Machine Learning (ML): Rimmasch said that leaders need to develop AI and ML with a deep understanding of the patient and clinician workflow. If leaders create AI and ML in a silo and then implement it in a clinical setting, these advanced tools will become a burden—rather than a benefit—for clinicians.
Among the unlimited types of data, the voice of the patient includes some of the most important information. According to Rimmasch, organizations’ clinical analytics should reflect the voice of the patient. Patient engagement tools (e.g., Twistle™ by Health Catalyst) allow health systems to communicate with patients and engage them throughout the care process. The opportunity to reach out to patients for appointment reminders and care updates keeps the patient aware and involves the patient as part of the care team.
As healthcare data becomes more widely available, clinical analytics will become increasing vital to delivering better care. Analytic insight from varied data sets helps providers understand what is actually happening compared to what they think is happening and informs clinicians when there is a better way to deliver care.
Rimmasch closed by emphasizing how critical adaptability is throughout the clinical analytics journey. Integrating analytics throughout the entire care process will open leaders’ minds to new opportunities for improvement.
View the full podcast or download the audio only version here.
Would you like to learn more about this topic? Here are some articles we suggest:
Would you like to use or share these concepts? Download presentation highlighting the key main points.