Deep learning algorithms to identify documentation of serious illness conversations during intensive care unit admissions

SAGE Palliative Medicine & Chronic Care

This episode features Dr Alex Chan (Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, MA). Routine assessment of many established quality indicators is nearly impossible because the information is embedded as unstructured free text within electronic clinical notes. A key example of this is timely documentation of patient care preferences in critically ill older adults. The paper demonstrates that deep learning algorithms can be applied to assess a palliative care quality measure endorsed by the National Quality Forum. The deep learning algorithm analyzed clinical notes >18,000 times faster than clinician coders (0.022 s/note vs 402 s/note). The algorithms can analyze electronic clinical notes in a tiny fraction of the time needed for manual review, offering a practical option for rapid audit and feedback regarding care preference documentation at the system and clinician level. Full paper available from: https://journals.sagepub.com/doi/full/10.1177/0269216318810421

If you would like to record a podcast about your published (or accepted) Palliative Medicine paper, please contact Dr Amara Nwosu: [e-mail]