Becker's Hospital Review

26 INNOVATION Algorithm can improve end-of-life care for cancer patients By Mariah Taylor P hiladelphia-based Penn Medicine researchers recently found that a machine-learning algorithm that predicts mortality risk in cancer patients quadrupled the rates of end-of-life care conversations with patients. e study, published in JAMA Oncology on Jan. 12, included 20,506 patients with cancer. e algorithm identified high-risk patients and sent email or text "nudges" to physicians to start serious illness conversations. e nudges resulted in more than 40,000 patient encounters, making it the largest study of machine learning-based interventions focused on serious illness care in oncology, according to a Jan. 12 Penn Medicine news release. Aer a 24-week follow-up period, researchers found the following: 1. Conversation rates increased from 3.4 percent to 13.5 percent among high-risk patients. 2. e use of chemotherapy or targeted therapy in the final two weeks of life decreased from 10.4 percent to 7.5 percent. 3. e intervention had no effect on other end-of-life metrics, including hospice enrollment or length of stay, inpatient death or intensive care unit use. 4. ere was an increase in conversations about goals of care among patients who were not flagged as high-risk by the algorithm. e increase was observed in all patient demographics but was larger among Medicare beneficiaries, suggesting the intervention could help close disparity gaps. "Communicating with cancer patients about their goals and wishes is a key part of care and can reduce unnecessary or unwanted treatment at the end of life. e problem is that we don't do it enough, and it can be hard to identify when it's time to have that conversation with a given patient," study senior author Ravi Parikh, MD, an oncologist and associate director of the Penn Center for Cancer Care Innovation at Philadelphia-based Abramson Cancer Center, said in the release. n UC Davis Health aims to reduce 'pajama time' through AI documentation By Giles Bruce S acramento, Calif.-based UC Davis Health will document medical conversations via artificial intelligence to cut down on "pajama time" for providers. The health system is partnering with virtual practice management platform LiveCare Corp. to automate documentation as part of the UC Davis Digital Collaborative for Innovation and Validation, or Digital CoLab. "Documentation burden is one of the major drivers of provider burnout, and, historically, technologies such as EHRs have led to increased burden and provider 'pajama time' on after-hours administrative work," said Ashish Atreja, MD, CIO and chief digital health officer of UC Davis Health, in a Jan. 8 LiveCare news release. "We're excited to explore how LiveCare's technology can reduce this burden." The technology aims to garner insights to improve patient care, clinician experience and billing accuracy by interpreting conversations between patients, nurses and physicians in real time. n Ardent Health launches innovation studio By Noah Schwartz N ashville, Tenn.-based Ardent Health Services partnered with SwitchPoint Ventures to launch an innovation studio focused on healthcare delivery and administration. The partnership is building off of Ardent and SwitchPoint's previous collaborations on artificial intelligence. The studio will work to develop data-focused healthcare tools that can be spun off as independent ventures, according to a Jan. 11 Ardent news release. "Ardent and SwitchPoint share a commitment to addressing the root problems that burden healthcare delivery," Ardent President and CEO Marty Bonick said. "Making healthcare work better demands more than status quo thinking. SwitchPoint's team listens, breaks down assumptions, attacks the salient issues, and iterates until there's a breakthrough." n

• Cover