Becker's Hospital Review

40 CIO / HEALTH IT Penn Medicine researchers predict depression diagnoses from Facebook posts By Jessica Kim Cohen A Facebook user's language ticks may tip off a clinician to their likelihood of developing depression, accord- ing to a study published in the Proceedings of the National Academy of Sciences. Researchers from Philadelphia-based Penn Medicine and Stony Brook (N.Y.) University parsed through the Facebook statuses of more than 500,000 consenting patients, some of whom had been diagnosed with depression and some of whom had not, to determine what they called "depression-associated language markers." Armed with these findings, the researchers created an algorithm they hoped would accurately predict a patient's likelihood of being diag- nosed with depression, based only on language used in their Facebook statuses. e algorithm flagged Facebook statuses for language that referenced symptoms like sadness, loneliness and hostility, such as with words like "tears" or "feelings." e algorithm also considered frequency of various words and phras- es, such as how commonly a user posted a self-referential status with first-person pronouns like "I" and "me" — these users were likely to be diagnosed with depression. "Social media data contain markers akin to the genome," Johannes Eichstaedt, PhD, founding research scientist of the World Well-Being Project at Penn and Stony Brook and a postdoctoral psychology fel- low at the University of Pennsylvania, said in a statement. "Depression appears to be something quite detectable in this way; it really changes people's use of social media." To evaluate the algorithm, the researchers applied it to the Facebook sta- tuses of nearly 700 consenting patients who had visited an emergency department at a large urban academic medical center, 114 of whom had a diagnosis of depression in their medical records — and the algorithm proved accurate, even when only looking at a limited time frame. In fact, the algorithm could accurately predict a patient's likelihood of being diagnosed with depression when only analyzing Facebook sta- tuses from three months before the first documentation of depression in their medical record, according to the researchers. Based on these findings, the researchers suggested social media net- works, such as Facebook, could one day be used by clinicians to screen consenting patients for depression. "e hope is that one day, these screening systems can be integrated into systems of care," Dr. Eichstaedt said. "is tool raises yellow flags; eventually the hope is that you could directly funnel people it identifies into scalable treatment modalities." n Apple Heart Study hits 400K participants & 4 more updates By Jessica Kim Cohen A pple and Stanford (Calif.) University School of Medicine released an update on their joint heart rhythm study, dubbed the Apple Heart Study, on Nov. 1 — roughly one year after its launch. Researchers at Apple and Stanford opened enrollment for the clinical trial in November 2017. Together, the re- search team planned to investigate whether the Apple Watch's heart rate sensor could detect irregular heart rhythms suggestive of atrial fibrillation, a disorder that the CDC estimates results in 130,000 deaths each year. Here are five updates on the Apple Heart Study: 1. The Apple Heart Study has enrolled more than 400,000 participants. To enroll, participants at least 22 years of age with an Apple Watch and an iPhone could download the free Apple Heart Study app in the Apple App Store. Once downloaded, the app tracks the participant's heart- rate pulse sensor and delivers alerts on irregular heart rhythms to the user's Apple Watch and iPhone. 2. Researchers from Apple, Stanford and collaborating research organizations published a paper on the study's design in the American Heart Journal. The paper speci- fies participants who receive an alert regarding an irreg- ular heart rhythm are asked to schedule a telehealth visit with a physician. Participants are also sent electrocardi- ography patches, which record the electrical rhythm of their hearts for up to one week. 3. The study, which closed enrollment in August, is now in its final phase of data collection. Apple and Stan- ford anticipate the study will be completed in 2019, as early as January. 4. Apple used a subset of the study data as part of its reg- ulatory submission for FDA clearance of its Apple Watch app that analyzes pulse-rate data to alert users to signs of atrial fibrillation, which the company announced in Sep- tember. Researchers with the Apple Heart Study were aware of the submission to the FDA, but have not seen the submission data. 5. Physicians who spoke with Wired questioned wheth- er Apple's new FDA-cleared feature, which it plans to release in the Apple Watch Series 4 by the end of 2018, would lead to more misdiagnoses, unnecessary tests and overtreatment. While one of the Apple Heart Study's goals is to learn how patients respond to the app's alerts, Wired points out these results won't be finalized until 2019. n

• Cover