The company can reduce the time required per appointment by 80%

Even before COVID, doctors felt burned out; In January 2019, the Harvard School of Public Health and other institutions viewed doctor burnout as “Public Health Crisis. ”N.Now the problem is worse: A Medscape poll in September found that 64% of US doctors said burnout worsened during the crisis. As a result, 25% said they were retiring earlier than planned, “while 12% said they were planning a career change away from medicine.

That burnout has impacted the patient-doctor relationship, said Matthew Ko, co-founder of DeepScribe, an AI-powered medical transcription startup that announced a $ 5.2 million launch Thursday. The company specifically seeks to alleviate doctor burnout by reducing the time spent on paperwork.

“Doctors routinely cite paperwork as one of their biggest problems. They spend more than a third of their time documenting, resulting in rushed appointments, doctors burned out, and, in the worst case, errors and omissions. Patients who see a distracted doctor cling to his or your computer, you feel unheard and uninformed, “he told me.

There are general ways for doctors to address this problem: medical human writer or dictation apps. The apps are cheap, but also imprecise and awkward to use. Human scribes give better results, but they are expensive and require hiring and training. DeepScribe’s solution is to provide what is known as the “World’s First Ambient AI Medical Recorder,” which takes the burden off the doctor by automatically transcribing appointments and uploading them to electronic health records (EHRs).

DeepScribe was launched in 2019 and offers Doctors with an iPhone and iPad app that listens in the background, takes notes and automatically summarizes the entire patient conversation into a compliant note in the doctor’s EHR system. It In addition, doctors can create precisely tailored notes and choose between long sentences or short, conversational or official notes, a summary of all discussed or only medically relevant points.

There are a number of other startups that also offer medical transcription services, including Abridge and Medcorder. Amazon even launched its own service in 2019. DeepScribe excels in a crowded room because it “The first AI solution to offer both the affordability and convenience of an automated recorder with out-of-the-box accuracy comparable to that of human assistants, “said Ko.

The company uses an AI model that was developed in the AI ​​Research Lab at UC Berkeley and combines classic classic rule-based processing of natural language (NLP) with modern deep learning techniques. It combines the output of three different speech recognition engines: one of its own, which identifies doctor / patient specific jargon; IBMs who are good at identifying drugs and diseases; and googles for conversational speeches.

“My co-founder Akilesh Bapu and I used an approach to DeepScribe that is similar to the ingenious ‘Centaur’ AI that recently won the American Crossword Puzzle Tournament. This approach limits the problem area and makes the deep learning algorithms both more effective as well as more predictable. “said Ko.

“The resulting output is commendable enough to make DeepScribe the only AI universally accepted by medical professionals that can take patient notes from natural conversation.”

DeepScribe offers 16% more accuracy and saves money at the same time Doctors three hours a day, which reduces the time required per appointment by 80% and eliminates work after work. In each appointment, users spend twice as much time talking to their patient instead of using the computer.

DeepScribe is growing rapidly, especially last year, with 66% new customer acquisition per month. During this time, 400 providers have taken over DeepScribe technology and generated around 500,000 banknotes. The company documents appointments with 10,000 patients per week and supports 18 different specialties and 40 states, 99% of which have introduced DeepScribe in the last 12 months alone. Much of this growth is due to increased demand thanks to COVID.

“As the pandemic made the work of front-line providers difficult and it became unsanitary and a point of friction to have personal writers in the face of the spread of COVID, we saw increased demand. 99% of our current users have DeepScribe in the past 12 months introduced alone, “said Ko to me.

At the beginning of the pandemic, DeepScribe built a telemedicine platform from the ground up so doctors could build in transcription and distributed this tool to over 300 doctors for free.

The new financing round was led by Bee Partners with the participation of Industry Ventures and Stage II Capital together with the existing investors Tsingyuan Ventures, 1984 Ventures, Wavemaker 360, Supernode Ventures, Skydeck, Plug & Play and Sequoia Scout Fund.

The company plans to expand his team increasing the number of ML and product engineers as well as his Sales and implementation teams to catch up with product demand. It will also be eExpansion of the range of EHR integrations eExpansion of the product range and functionality for all types of doctors or specialties.

What DeepScribe really addresses is a growing gap in the quality of patient care between those doctors who could afford a human scribe and therefore devote more time and attention to their patients, and those who couldn’t, leaving them less focused can their patients. The goal of DeepScribe is to make accurate medical recorders available to all doctors, from the highly paid specialist in an urban hospital system to the rural clinic.

Because of this, DeepScribe intends to create a “Jarvis” for doctors that will create more efficient patient visits and better informed patients as doctors and AI work in harmony.

For example, before the doctor sees the patient, the company gives them a summary of the patient’s medical history and the reason for the patient’s visit in a format that is optimized for the doctor to access information efficiently. The doctor receives data from patients with similar complaints and treatment patterns. In addition, the doctor can compare the effectiveness of his diagnoses with other patients with similar complaints and simulate the possible outcome of treatments.

“We won’t stop until every doctor has a sustainable, affordable, and accurate solution to the hours of paperwork they have to do and brings the joy of care back to medicine,” Ko said.


Please enter your comment!
Please enter your name here