A chatbot app to quit smoking
Researchers in Seattle, Wash. have now developed an artificial intelligence (AI) -powered chatbot app called QuitBot to help more people successfully quit smoking cigarettes. The app is available for free on Apple and Android devices and is a comprehensive app that provides users personalized support.
Developed using scientifically backed answers vetted by scientists and experienced smoking cessation clinicians, QuitBot combines evidence-based structured conversations to guide users through the process of quitting. The app differs from other smoking cessation tools by offering personalized support via mobile device whenever and wherever a user has a craving to smoke.
“QuitBot goes a step further than other currently available smoking cessation tools by offering users the ability to ask specific questions and receive tailored, scientifically backed responses,” said Dr. Jonathan Bricker, a professor and behavioral science researcher in the Public Health Sciences Division at Fred Hutch in Seattle. “It’s capable of understanding user’s questions about quitting smoking and responding with clinically proven answers. This feature helps make the experience more engaging and meaningful for the user.”
QuitBot is a smoking cessation program of 3- to 5-minute focused conversations over two phases: 14 days pre-quit date and 28 days post-quit date. The conversations cover topics such things as “why to quit” and setting a quit date. The conversations also help for identifying and coping with a wide range of triggers and recovering from lapses or relapses. Users can ask QuitBot any question they have about quitting smoking and it will respond with the researchers’ trained AI-based natural language technology.
“We know that quitting smoking has significant health benefits, including preventing many types of cancer, but it is incredibly difficult for people to realize those health benefits because smoking is highly addictive,” said Dr. Bricker.
Developed by Fred Hutch’s Health and Behavioral Innovations in Technology (HABIT) research group, the tool took six years of iteration, collaboration and testing. “Releasing QuitBot now and making it completely free is highly intentional,” said Dr. Bricker. “We wanted to get the app out to the public as quickly and easily as possible to help make a significant impact on smoking and to ensure that this new technology is available openly and non-commercially.”
Initial funding to develop QuitBot was provided by the National Cancer Institute. The Fred Hutch researchers then collaborated with Microsoft AI for Good Lab, using their AI expertise to refine the conversational chat function.
AI changing the practice of medicine
AI involves the simulation of human intelligence by computer systems and machines. It is now transforming how we receive healthcare. Using AI and machine learning it is now possible to quickly analyze huge datasets, such as electronic medical records. Other datasets include results of lab tests and medical imaging such as x-rays, MRIs and CT scans. This information can uncover new insights on how best to treat individuals for a host of illnesses.
It is hoped that AI may have the ability to diagnose diseases much earlier than has ever been possible. Utilizing AI for common diagnostic tests, such as electrocardiograms and echocardiograms, could help diagnose diseases much more accurately. This could help save peoples’ lives by preventing delays in care. Conversely, AI can help individuals avoid therapies that may not provide any benefit but significantly affect their quality of life.
AI algorithms can be applied to digital images of biopsies to identify subtle differences between tumors. This type of information may point to the presence of genetic mutations and open up a new avenue for developing personalized medicines for treating cancer. AI offers the promise of improving and diversity clinical trials. AI can provide locations where diverse patients are more likely to be treated. Further, AI can help better prioritize eligible patients.
Recently, clinicians used AI to accelerate the design of diabetes prevention software. In a study published online in the Journal of Medical Internet Research, researchers examined the capabilities of a form of AI called generative AI or GenAI. It predicts likely options for the next word in any sentence based on how billions of people used words in context on the internet. A side effect of this next-word prediction is that the generative AI "chatbots" like chatGPT can generate replies to questions in realistic language, and produce clear summaries of complex texts.
Led by researchers at NYU Langone Health, the current paper explores the application of ChatGPT to the design of a software program that uses text messages to counter diabetes by encouraging patients to eat healthier and get exercise. The team tested whether AI-enabled interchanges between doctors and software engineers could hasten the development of such a personalized automatic messaging system.
“The chatbot drove rapid progress throughout the software development life cycle, from capturing original ideas, to deciding which features to include, to generating the computer code,” said study corresponding author Danissa Rodriguez, assistant professor in the Dept. of Population Health at NYU Langone. “If this proves to be effective at scale it could revolutionize healthcare software design.”
John Schieszer is an award-winning national journalist and radio and podcast broadcaster of The Medical Minute. He can be reached at medicalminutes@gmail.com.
John Schieszer is an award-winning national journalist and radio and podcast broadcaster of The Medical Minute.
