Purpose of review

Younger generations of physicians are using technology more fluently than previous generations. This has significant implications for healthcare as these digital natives become a majority of the population's patients, clinicians, and healthcare leaders.

Recent findings

Historically, healthcare has been slow to adopt new technology. Many physicians have attributed burnout symptoms to technology-related causes like the EMR. This is partly due to policies and practices led by those who were less familiar and comfortable with using new technologies. Younger physicians will drive technological advancement and integration faster than previous generations, allowing technology to adapt more quickly to serve the needs of clinicians and patients. These changes will improve efficiency, allow more flexible working arrangements, and increase convenience for patients and physicians. The next generation of physicians will use technology to support their work and lifestyle preferences, making them more resilient to burnout than previous generations.

COVID-19 highlighted the challenge of connecting patients with accurate information regarding the COVID-19 vaccine. Upon seeing large disparities in vaccination rates among different populations in Sacramento, we began incorporating behavioral nudges into our digital messages to deliver information on the vaccine. To evaluate if these nudges could reduce vaccine disparities in our community, we leveraged UCD EMR data from Epic to identify populations with low vaccination rates, developed tailored messaging trees to those populations, and deployed messaging campaigns that were constantly iterated with A/B testing.

Total-body PET/CT images can be rendered to produce images of a subject's face and body. In response to privacy and identifiability concerns when sharing data, we have developed and validated a workflow that obscures (defaces) a subject's face in 3-dimensional volumetric data. Methods: To validate our method, we measured facial identifiability before and after defacing images from 30 healthy subjects who were imaged with both [¹⁸F]FDG PET and CT at either 3 or 6 time points. Briefly, facial embeddings were calculated using Google's FaceNet, and an analysis of clustering was used to estimate identifiability. Results: Faces rendered from CT images were correctly matched to CT scans at other time points at a rate of 93%, which decreased to 6% after defacing. Faces rendered from PET images were correctly matched to PET images at other time points at a maximum rate of 64% and to CT images at a maximum rate of 50%, both of which decreased to 7% after defacing. We further demonstrated that defaced CT images can be used for attenuation correction during PET reconstruction, introducing a maximum bias of -3.3% in regions of the cerebral cortex nearest the face. Conclusion: We believe that the proposed method provides a baseline of anonymity and discretion when sharing image data online or between institutions and will help to facilitate collaboration and future regulatory compliance.