International journal of nursing sciences · 2025
Increasing breastfeeding literacy: A preliminary study to develop an AI-based chatbot.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Kantovitz Kamila Rosamilia, Mattoso Maria Eduarda, Meyer Maria Davoli, de Araújo Marcella Armbruster, Giovani Priscila Alves, Martinez Valentin, Dubey Nileshkumar, Nociti Francisco Humberto, Motta Rogério Heládio Lopes
Аннотация
OBJECTIVES: Breastfeeding plays a critical role in the healthy development of infants, yet exclusive breastfeeding (EBF) rates remain low, particularly among low-income mothers. This study aimed to develop and validate an AI-based educational innovative solution to increase breastfeeding literacy across caregivers and mothers.
METHODS: The BabyChat (AI-based) was developed through two phases. In phase I, the content was created using the Canvas application, with the idea tree structured through MindMeister, and delivered via the ManyChat tool on Facebook. The focus was on the benefits of EBF during the initial 6 months of life, as recommended by the WHO, and continued breastfeeding until 1,000 days of life. In Phase II, functionality tests were performed using UserTesting and subsequently validated by the Content Validity Index (CVI). Healthcare professionals reviewed the clarity and relevance of the information on a four-point scale. Intra-examiner concordance was assessed by percentage of agreement and the median for each CVI-I point.
RESULTS: The contents of BabyChat included 8 topics and 18 subtopics (based on relevant contents including nutritional and anatomical aspects, weaning strategies among others) aimed to educate mothers and caregivers. Five mothers participated in evaluation of the BabyChat. Overall, most participants found the chatbot's question-and-answer functionality clear and helpful, with accurate command execution and timely response speeds, etc. However, two participants noted occasional issues such as misinterpreted questions, delayed command responses, and unclear or hard-to-find interface buttons. A total of four experts in psychology, dentistry, and medicine validated the framework. The agreement rate between experts ranged from 25 % to 100 %, with median values between 3 and 4, indicating excellent content relevance.
CONCLUSION: The BabyChat was developed and validated for use in increasing breastfeeding literacy among caregivers and mothers. Future studies should be considered to expand the BabyChat validation to other healthcare professionals, including nursing staff, to comprehensively capture the impact of BabyChat on mothers, as well as to incorporate population-specific topics that depend on cultural and geographical aspects.
METHODS: The BabyChat (AI-based) was developed through two phases. In phase I, the content was created using the Canvas application, with the idea tree structured through MindMeister, and delivered via the ManyChat tool on Facebook. The focus was on the benefits of EBF during the initial 6 months of life, as recommended by the WHO, and continued breastfeeding until 1,000 days of life. In Phase II, functionality tests were performed using UserTesting and subsequently validated by the Content Validity Index (CVI). Healthcare professionals reviewed the clarity and relevance of the information on a four-point scale. Intra-examiner concordance was assessed by percentage of agreement and the median for each CVI-I point.
RESULTS: The contents of BabyChat included 8 topics and 18 subtopics (based on relevant contents including nutritional and anatomical aspects, weaning strategies among others) aimed to educate mothers and caregivers. Five mothers participated in evaluation of the BabyChat. Overall, most participants found the chatbot's question-and-answer functionality clear and helpful, with accurate command execution and timely response speeds, etc. However, two participants noted occasional issues such as misinterpreted questions, delayed command responses, and unclear or hard-to-find interface buttons. A total of four experts in psychology, dentistry, and medicine validated the framework. The agreement rate between experts ranged from 25 % to 100 %, with median values between 3 and 4, indicating excellent content relevance.
CONCLUSION: The BabyChat was developed and validated for use in increasing breastfeeding literacy among caregivers and mothers. Future studies should be considered to expand the BabyChat validation to other healthcare professionals, including nursing staff, to comprehensively capture the impact of BabyChat on mothers, as well as to incorporate population-specific topics that depend on cultural and geographical aspects.