Usability, Satisfaction, and Post-use Health Problems of a Medical Chatbot Service Providing Medicine Use Recommendations for Women during Pregnancy and Lactation in Japan (Preprint)

Abstract

Many pregnant and lactating women are concerned about medication. Most women of reproductive age use medicines before, during, and after pregnancy, and they are aware that not all medicines are safe for them and their babies. While women face such concerns daily, they usually have few opportunities to communicate with healthcare professionals about safe medication use because of the limited availability of services and difficulty in making appointments.

This study evaluated the user experience of a medical chatbot service that provides medicine use information to pregnant and lactating women by investigating users’ consultation categories, satisfaction levels, and post-use health problems.

We collected the user data of a medical chatbot service providing medicine use information for pregnant and lactating women in Japan (Kusuribo) between December 13, 2021, and August 10, 2022. The satisfaction-related question was placed below the recommendation statements of the chatbot. An additional survey was distributed to collect post-health problem data from residents within one of the municipalities. The user status of this service (number of weeks of pregnancy, number of postpartum months, breastfeeding method, consultation categories, and preexisting conditions/complications) was presented, and the average level of satisfaction was calculated for all users and for each consultation category. The proportion of post-use problems was evaluated using the survey responses. χ2 and Fisher’s exact tests were conducted to assess the differences in user status and satisfaction levels.

The study included 1,000 records comprising 419 (41.9%) cases by pregnant women and 581 (58.1%) cases by lactating women. The response rate for the satisfaction question was 32.7%. The most frequently consulted categories in both groups were headache, cold symptoms, and hay fever symptoms. Of all users, 11.8% reported having preexisting medical or chronic complications, with bronchial asthma being the most prevalent (35.6%). The overall satisfaction rate was 93.9%, and the satisfaction levels of the two user groups showed no significant difference (P = .866). High satisfaction levels were observed across the consultation categories. An additional questionnaire was sent to 70 users, of whom 28 (40%) responded. None of the users indicated that they experienced health problems after using the service.

A medical chatbot service that provides medicine use information to women during pregnancy and lactation can achieve high satisfaction and safety.