Patient notes and the patient record has been a large part of Medmin’s history and it would be fair to say that some consultants are considerably more verbose than others. That said, our team of med-secs have transitioned from the dictaphone to iphone audio files and for the last eighteen months, they have been using Dragon which is a speech to text transcription programme.

Medical Secretaries often have training in medical terminology and, indeed AMSPAR (The Association of Medical Secretaries, Practice Managers, Administrators and Receptionists) offers professional qualifications in the subject area.

But entry into the patient record is just one part of the story. Patients sometimes see multiple consultants during their treatment and that can also mean time spent, looking back through pages of notes, either online or as paper records. It’s time-consuming and with time in short supply a number of organisations have seen an opportunity to get involved.

For every hour doctors spend with patients, they spend two hours on paperwork and note taking.

Healthcare is big business and not surprisingly, some of the biggest players in tech have thrown their hats into the ring in a bid to offer solutions that don't involve typing.

Amazon, Microsoft, and Google have all created software to this effect.

Just like in any sector, productivity is important and if doctors can reduce time in note-taking they can see more cases and, with better access to that data, provide better outcomes for their patients.

In November 2020, Google launched open source machine learning software to help doctors make sense of patient medical records. The platform is composed of two programs. One, an API for healthcare-related natural language processing, scans medical documents for key information about a patient’s journey, puts it into a standard format, and summarizes it for the doctor. It can pull from multiple sources of information like medical records as well as transcribed doctors’ notes. The goal is to create an easy way for doctors to review a patient’s past care. 

The second, called AutoML Entity Extraction for Healthcare, is a low-code tool kit that helps doctors to pull out specific data from a patient’s record, like information about a genetic mutation.

Microsoft has Project EmpowerMD. EmpowerMD listens to clinical conversations between doctors and patients. It integrates this content with information from the patient's EHR and automatically generates a medical summary. This allows physicians to spend more face-to-face time with patients. EmpowerMD is a learning system built on Azure. It uses a rich set of machine learning (ML) algorithms to tackle complex natural language understanding challenges.

The system is highly customizable. Doctors can easily edit the summaries generated by the system to suit their own individual style. The system learns from all such interactions to achieve the best medical outcomes.

Amazon, the company that brought us Alexa, has also entered the fray. Amazon Transcribe Medical is an automatic speech recognition (ASR) service that makes it easy for doctors to add medical speech-to-text capabilities to voice-enabled applications. 

Conversations between health care providers and patients provide the foundation of a patient’s diagnosis and treatment plan and clinical documentation workflow. It’s critically important that this information is accurate. 

Driven by state-of-the-art machine learning, Amazon Transcribe Medical accurately transcribes medical terminologies such as medicine names, procedures, and even conditions or diseases. Amazon Transcribe Medical can serve a diverse range of use cases such as transcribing physician-patient conversations for clinical documentation, capturing phone calls in pharmacovigilance, or subtitling telehealth consultations.

Amazon Transcribe Medical is available as a set of public APIs that can address both batch workloads and real-time speech-to-text applications. The service prioritizes patient data privacy and security. 

Amazon Transcribe Medical provides transcription expertise for primary care and specialty care areas such as cardiology, neurology, obstetrics-gynecology, pediatrics, oncology, radiology and urology.

Finally Nvidia, which has done a lot of work with AI and imaging, has started offering medical transcription. In 2020, Nvidia launched a service called BioMegatron, which is built to recognize conversational speech. The data set is trained on over six billion medical terms and is 92% accurate.

Good though these systems are - sometimes it still needs an experienced Med-Sec to ensure that the final record is accurate - fortunately Medmin has it covered...