Digital Scribes May Soon Change How Doctors Take Notes, But There Are Still Hurdles to Overcome: New Paper

From electronic health records to more advanced forms of testing and beyond, new technologies are increasingly reshaping the practice of medicine. Among the tools on the horizon are “digital scribes”, which will have the capacity to automatically generate medical notes based on a patient-clinician conversation.

In “Challenges of developing a digital scribe to reduce clinical documentation burden”, a new paper published in NJP Digital Medicine, researchers at the Australian Institute of Health Innovation, including PCHSS investigator Professor Enrico Coiera, lay out the vision of digital scribes in medicine as well as the challenges to their development and implementation.

The authors point to five technical challenges that still hinder the development of effective digital scribes. For instance, current technologies lack the ability to record and transcribe human conversations, which are filled with cross-talk, repetitions, and an array of errors as well as technical medical jargon, with sufficient accuracy. Even if they were able to automatically generate a perfect transcript, there would remain shortcomings in the capacities of artificial intelligence and machine learning technologies to restructure and extract useful information and summaries from conversations that may jump from topic to topic.

Beyond these challenges, there is also the issue of the lack of the large quantities of available medical data necessary for training deep learning systems to work as digital scribes.

There are also non-technical challenges to the implementation of digital scribes. The authors point to concerns that they will detract from doctors’ engagement with important aspects of care: “The main concern raised is that manual documentation allows clinicians to structure their thoughts, think critically, reflect, and practice medicine effectively, such that removing it would adversely affect the way clinicians practice medicine.”

However, the authors argue, if intelligently balanced with tried-and-true practice, digital scribes primarily hold promise to enhance the clinical experience.

Rather than replacement of clinicians as depicted in many dystopic AI futures, the goal of digital scribes is the formation of a “human–AI symbiosis” that augments the clinician–patient experience and improves quality of care. Digital scribes could well transform clinician–patient communication, bringing the focus back to the patient and clinical reasoning. The more seamless the digital scribe solution, the greater the support for the clinician engagement with patients.

Subscribe to our newsletter