“Unlike wearable digital activity-trackers, digital phenotyping harnesses data from smartphone sensors (e.g., global positioning systems, accelerometer, gyroscope, etc.) and logs (e.g., communication logs, screen-activity logs) without additional active participation from the user. This effectively capitalizes on hardware already in the hands of patients rather than introducing additional devices. By coupling digital phenotyping with high-frequency, digitally collected PROMs, this method can be used to analyze behavioral patterns, social interactions, physical mobility, gross motor activity, and cognitive function, all of which may inform patient quality of life.
[..] In this study, Beiwe prospectively and passively collected raw smartphone accelerometer data continuously preoperatively and for 6 months postoperatively. [..] Accelerometer data were sampled identically for each patient, alternating between a 10-second on-cycle and a 10-second off-cycle. During on-cycles, the smartphone’s triaxial accelerometers were sampled, capturing acceleration in a 3-dimensional orthogonal coordinate system. This sampling design yielded dense temporal data without causing extensive phone battery drainage, an issue that the research team has studied.
[..] Of the 139 patients contacted preoperatively, 9 were unable to be reached, and 18 were ineligible because they lacked a smartphone or had technical issues using a smartphone. Of the 112 eligible patients, 64 patients (57.1%) downloaded the Beiwe application, and accelerometer data were available for 62 patients for final analysis [..]
[..] Among the 62 patients included, 45 patients (73%) experienced no clinically significant postoperative events, while 17 (27%) experienced 1 or more event [..]
Proportion of Patients With 60 or More Minutes of Daily Exertional Activity in the First 6 Weeks of Study Period. No differences existed at baseline (patients with a postoperative event, 0.63 [95% CI, 0.53-0.73] vs patients without a postoperative event, 0.71 [95% CI, 0.65-0.77]). Fewer patients with a postoperative event achieved 60 minutes of daily exertional activity than those without a postoperative event (week 1, 0.65 [95% CI, 0.58-0.70] vs 0.40 [95% CI, 0.31-0.49]; week 2, 0.69 [95% CI, 0.63-0.74] vs 0.49 [95% CI, 0.40-0.58]; week 3, 0.67 [95% CI, 0.61-0.73] vs 0.39 [95% CI, 0.30-0.48]; week 4, 0.70 [95% CI, 0.65-0.76] vs 0.47 [95% CI, 0.38-0.57]; week 5, 0.76 [95% CI, 0.71-0.81] vs 0.51 [95% CI, 0.42-0.60]; week 6, 0.73 [95% CI, 0.68-0.79] vs 0.43 [95% CI, 0.33-0.52]).
There were no differences between cohorts at baseline (proportion: 0.71 [95% CI, 0.65-0.77] vs 0.63 [95% CI, 0.53-0.73]; P = .15). However, in each subsequent week after surgery, there was a lower proportion of patients with a postoperative event who were able to achieve a minimal daily exertional activity of 60 minutes [see Figure above]”
*From the accompanying editorial: “Achieving clinical value, the ultimate goal, will occur when smartphone data are used to empower patients and clinicians to track recovery trajectories in real time and potentially identify postoperative complications at a point when they may be more easily treated. For a complete recovery picture beyond activity tracking, smartphones should also be used to collect patient-reported outcome data concerning other relevant aspects of postoperative recovery (e.g., pain, energy, emotional function). Using artificial intelligence techniques to process recovery data may support surgical decision-making by filling a need of patients, caregivers, and payers who commonly seek information about recovery expectations (e.g., can usual activities be resumed after surgery and how long it will take). Integrating patient-centered recovery data in electronic health records may provide an opportunity for recovery auditing and database-driven research aimed at quality improvement.
Using smartphones to capture patient-generated data regarding surgical recovery has a tremendous potential to transform postoperative care. The study by Panda et al. contributes proof-of-concept evidence that adds to this rapidly growing field of research.”
“Ubiquitous computing is still a fantasy, but not because the technology isn’t ready. It is. The fantasy is that any system mediating someone’s personal experience of the physical world that uses a modern corporation’s digital infrastructure would be objective or neutral. Humans are data and data is money, and this is the business model of many of the technology firms up to the task of ubiquitous computing.
[..] Players give Wizards Unite permission to track their movement using a combination of GPS, Wi-Fi, and mobile cell tower triangulation. To understand the extent of this location data, Kotaku asked for data from European players who had all filed personal information requests to Niantic under the GDPR, the European digital privacy legislation designed to give EU citizens more control over their personal data. Niantic sent these players all the data it had on them, which the players then shared with Kotaku.
The files we received contained detailed information about the lives of these players: the number of calories they likely burned during a given session, the distance they traveled, the promotions they engaged with. Crucially, each request also contained a large file of timestamped location data, as latitudes and longitudes.
[..] On average, we found that Niantic kept about three location records per minute of gameplay of Wizards Unite, nearly twice as many as it did with Pokémon Go. For one player, Niantic had at least one location record taken during nearly every hour of the day, suggesting that the game was collecting data and sharing it with Niantic even when the player was not playing.
[..] Foursquare, once a social app for telling friends what restaurants or museums you’ve been to, is now leveraging its 13 billion check-ins into its new business model: “a location data and technology platform” that pairs “location tech with other data points, like transaction history.” 150,000 business partners, including Apple and Uber, receive audience profiles and granular location data, which they can tailor into, for example, a curated, personalized itinerary for a hotel guest that also drives foot traffic.
“Clare Garvie demands the United States government hit pause on face recognition. She argues that while this convenient technology may seem benign to those who feel they have nothing to hide, face recognition is something we should all fear. Police databases now feature the faces of nearly half of Americans — most of whom have no idea their image is there. The invasive technology violates citizens’ constitutional rights and is subject to an alarming level of manipulation and bias.
Our privacy, our right to anonymity in public and our right to free speech are in danger. Congress must declare a national moratorium on the use of face-recognition technology until legal restrictions limiting its use and scope can be developed. Without restrictions on face recognition, America’s future is closer to a Chinese-style surveillance state than we’d like to think.”
You’re in a Police Lineup, Right Now (2019.10.15)