Healthcare chatbots: The “Alexa” of medicine
What is a health chatbot ?
At the most basic level, a chatbot is a computer program/smart algorithm that simulates and processes human conversation (either written or spoken), allowing humans to interact with digital devices as if they were communicating with a real person. In other words instead of having a conversation with another person, the user talks with a (ro)bot that’s either powered by basic rules or machine learning. Health bots are the ones designed to help with health-related issues. Chatbot can be as simple as rudimentary program that answer a simple query with a single-line response, or as sophisticated as digital assistant that can (machine)learn and evolve to deliver increasing levels of personalization as it gathers and processes information.
Driven by artificial intelligence (AI), automated rules, natural-language processing (NLP) 4), and machine learning (ML), chatbots process data to deliver responses to requests of all kinds.
There are two main types of chatbots:
- Task-oriented (declarative) chatbots are single-purpose programs that focus on performing one function. They use automated rules and are enabled with NLP but use very little ML. Thus they are good to generate automated but conversational responses to user inquiries. They are good to handle FAQs, such as queries about opening times/locations of OPD or simple transactions that don’t involve a variety of variables. Since they do use NLP, end users can experience them in a conversational way although their capabilities are fairly basic. Currently, they are the most commonly used chatbots.
- Data-driven and predictive (conversational) chatbots are often referred to as virtual assistants / digital assistants, and they are much more sophisticated, interactive, and personalized than task-oriented chatbots. They are chatbots with some artificial awareness (AI) and use not only c NLP but can leverage natural-language understanding (NLU), and learning as they go (ML). They are able to apply predictive intelligence and analytics to enable personalization based on user profiles and past user behavior. Digital assistants can learn a user’s preferences over time, provide recommendations, and even anticipate needs. In addition to monitoring data and intent, they can even initiate conversations. Apple’s Siri and Amazon’s Alexa are examples of non-health, data-driven, predictive chatbots.
While chatbots have become almost commonplace in e-commerce, they have recently started to emerge in the healthcare sector, as well. They could potentially provide many different services; user health-related information, help set up appointments, set up reminders for appointments/intake of drugs. Based on symptoms they may even predict probable diagnosis but more importantly sort out non-important symptoms from important ones asserting if a patient requires immediate attention or if they are going to be okay. Thus, while they can certainly not ape a human doctor they may provide convenience of quick response. What they can indeed do well:
- Can schedule appointments
- Can answer general user queries related to hospitals/doctors
- Can be useful for sending reminders to patients
- Help self-triage patient’s disease based upon symptoms they enter
- Can be used for patient’s engagement
