Zocdoc launches patient-focused search engine that can understand natural human language

By Heather Mack
Share

Doctor appointment booking platform Zocdoc is launching a new, smarter search feature to its offering on both mobile and desktop. Now, the ability to find and schedule doctor visits will become more personalized and approachable with Zocdoc’s Patient Powered Search engine, which employs machine learning and natural language processing to make the experience more conversational.

The idea is to take the onus off patients to know exactly what they are looking for, including proper terminology to accurately describe a condition. The Patient Powered Search engine can recognize more everyday human language, including vague searches like “hurt wrist” or misspelled medical conditions. It even has a limited emoji vocabulary.

“Millions of patients come to Zocdoc each month to find and book appointments with healthcare providers across more than 50 specialties … This is no small feat, considering the healthcare industry uses academic terminology and alphabetized lists of hard-to-spell specialties to categorize and deliver care,” the company wrote in a blog post. “At the same time, according to the CDC, nine in ten Americans struggle to understand jargon-filled health information. This disconnect between medical speak and patients’ own colloquial language – think ‘gyno’ not ‘obstetrician-gynecologist’ – can frustrate, intimidate or even deter patients in their searches. This is especially concerning at the critical moment when patients are motivated to seek care.”

Zocdoc developed the beta version of the Patient Powered Search based on data they have gathered over the past 10 years since launching, and built a machine-learning algorithm using existing medical literature gathered online. Using aggregated data in a method knows as semantic search technology, the search engine has learned natural human communication and mapped commonly used terms to the appropriate corresponding medical term, visit reason or procedure. It is then paired with string-matching technology to retrieve relevant results.

“Additionally, during our beta period, some of the most common searches were simply-put symptoms, conditions or even body parts, such as ‘stomach,’ ‘TMJ’ and ‘tonsil.’ which, thanks to our algorithm, now successfully map to gastroenterologists, prosthodontists and ENTs,” the company wrote. “We are also using machine learning to aggregate intent, and prioritize and re-rank search results based on patient behaviors so the most popular search selections will appear at the top. This allows us to continually learn what patients are looking for, and adjust results based on trends or new needs.”

Zocdoc’s original service, which is available on iOS and Android devices, is targeted at consumers. The app asks for a user’s zip code and insurance provider and then lists nearby doctors and their availability. Users can then select a time to complete the appointment booking. Since October 2012, Zocdoc has also offered a check-in feature so that patients can also send over a basic medical history before they arrive instead of filling out the medical history clipboard. But Zocdoc has been moving beyond appointment booking for a while. In 2015, the company announced it had raised $130 million to do just that.

In June 2014, ZocDoc launched a premium service that employers can offer their employees, called Zocdoc for Business. This was Zocdoc’s first offering for employers. Zocdoc for Business launched with a handful of customers, including Foursquare, Gilt, IAC, Jefferies, NASDAQ OMX, and Quirky.

“Patient-Powered Search lays an important foundation for the future – it gives Zocdoc, our patients, and our partners an unmatched advantage when it comes to healthcare search, discovery and booking,” the company wrote.  “And, most importantly, it furthers our core mission to give power to the patient – putting patients’ needs at the center of our product innovation to remove friction throughout their healthcare journey.”Air Jordan II 2 Shoes