The power of voice in the healthcare industry

(Source: Computer Weekly)
“We’re right on the edge of a new era of conversational computing, where in certain circumstances your primary mode of interaction with a machine will be talking to it and having it talk back”. — Paul Saffo

For years, people have dreamed about talking to computers like we talk to each other. In recent years, we have been able to make it happen. Speech recognition gives us the opportunity to communicate with the technology around us and it has become a normal part of many people’s lives, as we can see voice-interfaces showing up in mobile phones, automobiles, and TVs. We now talk to our devices, ask them to check the weather, send an email or call a friend, but have we ever thought about the impact it has made on the healthcare industry? Well, if you are interested to know more about it, keep reading!

In this article, we are going to talk about what is speech recognition technology, how is it used in the healthcare industry and the benefits that this technology has to offer, as this particular technology has had a significant impact on the ability of healthcare providers to operate more cost-effectively and provide a better level of patient care.

What is Speech Recognition Technology (SRT)?

Speech recognition is the ability of a machine or a program to identify and capture words and phrases in spoken language through devices such as microphones, and transform them into digital format, with the use of specially designed speech recognition software. In other words, is the ability to create written text from speech. Instead of using the keyboard and mouse, users use their voice, and the program types what they are saying. Siri and Alexa are examples of SRT in use today. (Ref: TechTarget)

Speech recognition might seem “fresh” to consumers, but it actually took many decades for its development. The first speech recognition system was designed by Bell Laboratories in 1952, known as the “Audrey” system, which could understand only digits spoken by a single voice. But it was not until 1972, where engineer William C. Dersch created the IBM Shoebox, a device able to recognize ten digits and six control words spoken to it through a microphone, giving a great step in the development of this technology. Not so new, right?

The Shoebox (1962) (Source: IBM)

The concept of speech recognition technology is frequently confused with the concept “Voice Recognition Technology (VRT). Even though both utilise recordings of the human voice, they are different. Voice recognition is the process by which a system recognizes the individual characteristics of one’s voice, while SRT helps recognize patterns and turns those patterns into something else (such as written language). In other words, voice recognition tries to capture the “Who”, while speech recognition is the technology that captures the “What”. (Ref: Quora)

How is SRT used in the medical field?

According to the National Institutes of Health, the healthcare industry first started implementing speech-recognition systems for medical reporting around 1994. However, the first use of SRT systems was not that well adopted because of two main reasons:

First, doctors didn’t want to abandon the traditional way to perform their work and didn’t want to change. Second, the initial SRT systems were far from user-friendly. The early technology required doctors to “learn” how to “talk” to the computer, rather than the computer learning to listen to the doctor. Doctors would be forced to adapt to the technology by changing their ways of speaking and besides that, the system was not capable of understanding medical terminology because of a small vocabulary.

Source: (Clinical-innovation)

In recent years, the quality of computer speech recognition has improved considerably, as the technology has been able to understand medical terminology and medication names, becoming one of the best solutions that allow doctors and nurses to dictate reports and make transcriptions with a minimum of errors at lower cost, as the traditional process of typing long reports is tiresome and time consuming, not to mention that medical transcription services are often very expensive.

“The introduction of speech-recognition technology for nurses is significant because they typically spend as much or more time on documentation as they do on direct patient care.” — Joseph Conn (Modern Healthcare)

The implementation of the SRT brings a lot of benefits to the healthcare industry, from time-saving to cost reducing. First of all, doctors have been able to become more efficient in the process of transcripts by using a speech recognition software, since the process of dictating is way much faster than typing long reports, not to mention the great accuracy the technology has reached over the past years. Secondly, it increases the productivity in the healthcare industry, as doctors are able to see more patients over the course of the day when using SRT compared to the traditional way. Another benefit is that it also reduces the amount of time it takes for a doctor to get the information readily available for use, making it possible to get information between departments quickly. (Ref: Health management)

(Source: Flickr)

Less paperwork and more time to focus on helping a patient — isn’t that what we want?

The usage of speech recognition software in hospitals can be a crucial method of helping doctors to make decisions and save lives, as it allows them to see more patients, finish and share documentation immediately, and increase the overall quality of the patient experience.

Speech recognition technology is revolutionizing the way healthcare professionals work in various types of medical environments as it creates a more user-friendly environment for doctors and nurses to operate efficiently and it is a great solution to the medical transcription process. More hospitals are implementing SRT to their system because of the benefits it offers. Thanks to this technology, many doctors can spend less time on the screen and finally focus on what matters the most, helping their patients.

If you want to learn more about speech recognition technology and how to design for speech-enabled interfaces, come and join us on the upcoming Talk UX in Taipei! (Check out the speakers and secure your seat for Talk UX here!)

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.