Home | About | Events | Contact | Advisory Board | Writer’s Guidelines | Reprints | Organizations | Advertising
July/August 2018
Innovations: Analytics in Palliative Care Palliative medicine may be one of today's most misunderstood disciplines, both by patients and family members. Palliative medicine aims to improve the quality of life and provide comfort to patients living with chronic or terminal illness—at any stage of the illness—not just at the end of life. Hospice care is a subcategory of palliative care and focuses primarily on terminal illness and end of life. Approximately 90 million people in the United States are living with a serious illness,1 and nearly 90% of hospitals with 300 beds or more feature a palliative care program.2 Despite the prevalence of palliative care teams in hospitals, there are a number of challenges that hinder access, including poor hospital culture and awareness, a lack of education about the range of palliative care services, and an inability to identify patients who need care. Addressing these concerns greatly reduces suffering in the most effective manner. Toward that goal, some organizations have turned to analytics-enabled technology, which offers opportunities to improve palliative care delivery in several ways. Identifying Patients Requiring Care Clinical monitoring tools that use real-time predictive analytics offer great insights into a patient's current health. Clinicians can better identify those in need of palliative care when they have a clear picture of a patient's current and projected state of health. Moreover, clinical tools and analytics give care teams, patients, and their families objective data to help them make appropriate decisions regarding their palliative care treatment. Optimizing Quality of Life Life expectancy estimations for oncology patients have historically been inconsistent and don't always provide clinicians a complete picture from which to best address patients' care goals. However, using analytics within a palliative care program not only paints a more holistic picture of a patient's health but also provides prognostic tools and predictive models that help clinicians, patients, and their families decide on a realistic care plan. A recent study from Yale Cancer Center/Smilow Cancer Hospital resulted in the creation of the Imminent Mortality Predictor in Advanced Cancer (IMPAC), a predictive model that uses objective data from electronic health records to generate life expectancy probabilities in real time. To help determine what further aggressive treatments may or may not be warranted, IMPAC leverages clinical surveillance technology to measure hospitalized oncology patients' likelihood of death within 90 days. In this type of predictive model, clinicians and patients can better determine when patients' quality of life would benefit from choosing not to seek treatment as part of their palliative care. Minimizing Patient Length of Stay Yale New Haven Hospital recently conducted a pilot study that incorporated clinical surveillance tools into a trigger for palliative care. The study found the mean length of stay for patients receiving palliative intervention decreased from 26.3 days for all other groups to 13.9 days. Furthermore, the 30-day readmission rate was reduced from 35% in the nonpalliative care group to 4% in the intervention group. By improving the prevention of 30-day readmissions and reducing length of stay for Yale New Haven Hospital's palliative care patients, the results of this study demonstrate the benefits of clinical surveillance tools and triggers in palliative care. Providing Cost Savings In fact, the Yale New Haven Hospital study on length of stay found that costs were lowered by 54% for patients receiving palliative intervention. Additionally, a widely cited study on cost savings associated with US hospital palliative care found an average 400-bed hospital with palliative care consultation could realize net savings of $1.3 million per year.3 The findings of both studies illustrate how clinical technology and analytics in palliative care can help bend the cost curve. Analytics also can help reduce costs for patients not undergoing treatment. Because end-of-life care can be expensive, using clinical tools and predictive models to best determine whether treatment is appropriate can reduce costs for patients whose quality of life would not improve with treatment. In fact, Yale Cancer Center's IMPAC study estimated a potential cost savings of $15,413 per patient—the potential avoidable cost of $17,861 minus the cost of hospice ($2,448). Choosing not to seek treatment can be a difficult decision for patients and families. However, an informed decision can help improve a patient's quality of life and realize significant potentially avoidable costs. Spreading the Word Clinical technology and analytics have tremendous potential to overcome the obstacles to effective end-of-life care. Not only do these tools help physicians and patients determine whether treatment is the best course of action but they also help better identify appropriate patients for palliative intervention as part of their end-of-life care. Moreover, clinical tools and analytics can help reduce the length of stay for palliative care patients and decrease costs, whether or not treatment is sought. — LeAnne Hester is chief commercial officer at PeraHealth. References 2. Center to Advance Palliative Care. America's care of serious illness. https://reportcard.capc.org/ 3. Morrison RS, Penrod JD, Cassel JB, et al. Cost savings associated with US hospital palliative care consultation programs. Arch Intern Med. 2008;168(16):1783-1790. |
