Chatbot vs Checklist: Which format do you like the best?

When we have new symptoms, we all begin with self-triage in one form or another. Symptom checkers offer an easy, digital way to sift through symptoms and receive healthcare advice. They connect users to appropriate level of care. In this post, we explain how the chatbot symptom checker format offers different strengths that the original checklist format.

For severe symptoms, both formats quickly instruct the user to call 911 or go to the emergency room. But, most people aren’t using symptom checkers when symptoms are clearly severe and emergent. After assessing how serious the symptoms are, both types of symptoms checkers link to care options. These might be online scheduling, telehealth, and nearby care locations.

Let’s start with the chatbot:

Users are asked a series of questions about their symptoms in a conversational format. It flows like a text conversation.  At the end, there is a summary which suggests the next steps for getting the right level of care. “When done well, the questions walk the user through grouped concerns about their symptom: appearance, behavior, duration, related symptoms, etc. The chatbot symptom checker may not reveal which of the user’s answers drove the final outcome. It will reach the right result, but may not transfer knowledge. Chat is a ‘black box’ (no transparency) as to how the result was reached,” says Sue Riffel, CEO of Self Care Decisions.

Some bots go beyond triage and propose likely diagnoses. The ability to generate a list of likely diagnoses make these AI chatbots good for medical teaching. However, it increases the number of questions asked. Especially if more than one symptom is entered. It can be difficult for the user to know where they are in the process. This can lead to higher rate of abandonment.

Now let’s examine the checklist format:

The checklist format presents a list of symptom scenarios starting for the user to scan. It starts with the most serious at the top, moving down to the least.  The user reads each phrase and selects the first scenario that matches their situation. Their selection displays a recommended action (level of care needed and in what time frame) and links to the related care options. It might be to find a facility, schedule a visit (online or in-person) or to call during office hours.

As users read the symptom list in order of severity, they learn which scenarios are more serious. They also learn what signs they need to keep an eye on. In many cases, they are reassured when they reach the lower end of the list. They learn they can focus on care at home, for now.

Many pediatric settings (practices, Children’s Hospitals) prefer to checklist symptom checkers. Their audience, parents – especially new parents, learn with each symptom check. The care advice has been shown to build self-care skills. So, the transparency of how the decision is made is helpful in developing parents’ assessment skills. The checklist offers new knowledge which they will build upon with each use.

Why not offer both?

It is clear more patients are looking for digital solutions and the pandemic escalated that pursuit. There may be an advantage to offer both chatbot and checklist formats so patients can choose what they prefer. Though chatbots are popular, it is worth noting where they shine best and how that aligns with the needs of your audience. The solution ‘fit’ should align with the needs and preferences of the primary audience. Self Care Decisions supports both formats for this reason.

Author: Bonnie Offit, MD is a general pediatrician trained at Children’s Hospital of Philadelphia (CHOP). For over 30 years she has provided care for children in both primary and urgent care settings. She recently served as clinical director for telehealth in the Office of Digital Health at CHOP prior to her current role of Chief of Health Innovation at Self Care Decisions. Her interests focus on using technology to improve the patient experience and ultimately improve outcomes by getting the right care at the right time.

General references:

1. Palanica1 A, Flaschner2 P, Thommandram1 A, et al. Physicians’ perceptions of Chatbots in health care: Cross-sectional web-based survey. Journal of Medical Internet Research.https://www.jmir.org/2019/4/e12887/. Accessed October 26, 2021.
2. Philipson B. Chatbots in Healthcare: A more humanized, patient-oriented approach. Healthcare IT News. https://hitconsultant.net/2021/09/10/chatbots-healthcare-humanized-patient-oriented-approach/#.YXhbFNnMKbg. Published September 10, 2021. AccessedOctober 26, 2021.
3. Lerman R. The robot will see you now: Health-care chatbots boom but still can’t replace doctors. The Washington Post. https://www.washingtonpost.com/technology/2021/07/26/healthcare-chatbots-pandemic-rise/. Published August 13, 2021. Accessed October 26, 2021.