This post is the first in our two-part natural language processing series, which will delve into Doctor.com’s proprietary NLP software used to help track and analyze the language throughout all of an organization’s patient comments.

The future of patient experience may well involve machine learning — but don’t let that scare you. Natural language processing (NLP) is a core component of artificial intelligence (AI) and has been gaining traction in healthcare in recent years. Why healthcare? Because of the opportunity that presents itself with all the data healthcare organizations collect, specifically with regards to patient feedback.

With NLP, all of the thousands of comments and reviews you’ve spent time and money collecting and curating can be analyzed and categorized so that more useful information can be extracted from them.

At Doctor.com, we’ve built a proprietary NLP engine to make sense of all this unstructured data to provide deep insight into what patients are telling you, because the more you know what patients are experiencing and what they need, the quicker and more efficiently you can respond and improve.

The dinner party analogy

An analogy we like to use to help people understand how NLP can change the way they approach reviews involves meeting people at a dinner party. You could go around to every person and ask a series of sterile “yes or no” or even multiple-choice questions and learn facts about them, but it wouldn’t truly help you know them because your questions constrain how much they’re able to share. Indeed, you may not have even asked the most important questions and so don’t even know what you’re missing.

On the other hand, if you spoke with each person and asked only open-ended questions, you would get a much more in-depth understanding of their world. These types of queries prompt the person to share their feelings and thoughts without the arbitrary constraints of a more structured question, and they’re not easily answered leading questions.

Think about it. If you asked someone “Do you have kids?” their response wouldn’t tell you all that much. But if you said to the same individual “Tell me about your family,” you’d get a much more holistic response with real-world application.

What is natural language processing?

Natural language processing is a branch of computer science used to analyze, understand, and derive meaning from human language in a useful way. In particular, it’s concerned with programming computers to successfully process incredible amounts of natural language data in a way that is similar to how a human processes conversations.

NLP allows the computer to do the hard work of processing literally thousands of conversations and understand them well enough to identify patterns and sentiment trends — so you can then use this information to improve where needed. Sure, a human could process every one of the thousands of comments you have, but with NLP, a computer can do it in a fraction of the time.

Through natural language processing, developers can organize and structure knowledge to perform tasks such as automatic summarization, translation, named entity recognition, relationship extraction, sentiment analysis, speech recognition, topic segmentation, and more.

Our NLP was developed specifically for the healthcare industry with regards to patient comments, with all of the nuance, quirks, and privacy concerns of that field.

Stay tuned for our next installment in the natural language processing series, where we’ll discuss our unique approach and how it works.