Luz Saúde

Bruno Campos

Electronic Health Records (EHRs) adoption has increased in the last decade.There were many improvements in healthcare with the introduction of EHRs, like decrease of errors and misinterpretations, with improved healthcare quality and patient safety with the implementation and enforcement of safety guidelines and with the application of effective alerts in some uses cases. However, physicians are challenged daily with the inability to access relevant information using interfaces that are not user-friendly, the lack of interoperability and access among systems, the lack of ongoing, contextual training that keeps many in healthcare from optimizing the use of available systems, too many hours spent documenting care, less face-to-face interactions with the patient and burnout.

The growing data volumes and differences in terminology, language, abbreviations, and even spelling in clinical documents make it challenging for physicians to have a full picture of patients for clinical decision support. 

A recent study demonstrates that 36 percent of clinicians spend more than half of their day on administrative tasks in the EHR. And what’s more, 72 percent of clinicians expect the time they spend on administrative tasks to increase over the next 12 months. Other study by American Medical Association (AMA), reveals that high volumes of data entry and poor usability are a main cause of physician burnout.

It is imperative to eliminate some of the redundancy and focus on what is meaningful. If the physicians cognitive bandwidth is used up just trying to get situational awareness, like, “Who is this patient, what are their meds, what are their problems, what are their care gaps?” then physicians are not able to be the diagnostician and to generate trust with patients.

Several emerging technologies are attempting to address the challenges of clinical documentation, optimization is an integral part of leveraging the technology to improve clinical workflow. Simply because a practice has adopted and implemented an EHR doesn´t mean the hospital will automatically function more effectively. Understanding how to improve is key.

The speech recognition service enables physicians to easily and quickly dictate their clinical notes and see their speech converted to accurate text in real time without any human intervention. Artificial intelligence innovations marry data points, such as lab results, vital signs and clinical words in the patient record and provide clinical documentation suggestions to the provider. Computer-assisted analyses of physician documentation provide real-time feedback and attempt to resolve inaccuracies.  

Tech giants like Amazon, Microsoft, Google are reaching deeper into healthcare with a new speech recognition service for clinical documentation. 

One example is nuance’s integrations into such EHR systems as Epic and Cerner allow providers to dictate notes, use their voice to navigate EHR systems, and ultimately reduce the time it takes to provide reports to patients. By using automatic transcription in telehealth visits, providers can worry less about note-taking and focus more on the patient, while picking up on small cues that might otherwise be difficult to detect. 

"There is not a single silver bullet or a magic key for the documentation burden problem, there are complementary strategies than can improve both goals, improve documentation and time for the patient."

While Microsoft Azure Cognitive Services for Language, under the Cognitive Services umbrella, is a set of machine learning and AI algorithms for developing intelligent applications that involve natural language processing. Text Analytics for Health extracts and labels relevant medical information from unstructured texts such as physician notes, discharge recommendations, clinical documents, and electronic health records.