Background: Artificial intelligence (AI)–based chatbots can offer personalized, engaging, and on-demand health promotion interventions. Objective: The aim of this systematic review was to evaluate the feasibility, efficacy, and intervention characteristics of AI chatbots for promoting health behavior change. Methods: A comprehensive search was conducted in 7 bibliographic databases (PubMed, IEEE Xplore, ACM Digital Library, PsycINFO, Web of Science, Embase, and JMIR publications) for empirical articles published from 1980 to 2022 that evaluated the feasibility or efficacy of AI chatbots for behavior change. The screening, extraction, and analysis of the identified articles were performed by following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Results: Of the 15 included studies, several demonstrated the high efficacy of AI chatbots in promoting healthy lifestyles (n=6, 40%), smoking cessation (n=4, 27%), treatment or medication adherence (n=2, 13%), and reduction in substance misuse (n=1, 7%). However, there were mixed results regarding feasibility, acceptability, and usability. Selected behavior change theories and expert consultation were used to develop the behavior change strategies of AI chatbots, including goal setting, monitoring, real-time reinforcement or feedback, and on-demand support. Real-time user-chatbot interaction data, such as user preferences and behavioral performance, were collected on the chatbot platform to identify ways of providing personalized services. The AI chatbots demonstrated potential for scalability by deployment through accessible devices and platforms (eg, smartphones and Facebook Messenger). The participants also reported that AI chatbots offered a nonjudgmental space for communicating sensitive information. However, the reported results need to be interpreted with caution because of the moderate to high risk of internal validity, insufficient description of AI techniques, and limitation for generalizability. Conclusions: AI chatbots have demonstrated the efficacy of health behavior change interventions among large and diverse populations; however, future studies need to adopt robust randomized control trials to establish definitive conclusions.

Background: The ultimate goal of any prescribed medical therapy is to achieve desired outcomes of patient care. However, patient nonadherence has long been a major problem detrimental to patient health, and thus is a concern for all health care providers. Moreover, nonadherence is extremely costly for global medical systems because of unnecessary complications and expenses. Traditional patient education programs often serve as an intervention tool to increase patients’ self-care awareness, disease knowledge, and motivation to change patient behaviors for better adherence. Patient trust in physicians, patient-physician relationships, and quality of communication have also been identified as critical factors influencing patient adherence. However, little is known about how mobile patient education technologies help foster patient adherence. Objective: This study aimed to empirically investigate whether and how a mobile patient education system (MPES) juxtaposed with patient trust can increase patient adherence to prescribed medical therapies. Methods: This study was conducted based on a field survey of 125 patients in multiple states in the United States who have used an innovative mobile health care system for their health care education and information seeking. Partial least squares techniques were used to analyze the collected data. Results: The results revealed that patient-physician communication and the use of an MPES significantly increase patients’ trust in their physicians. Furthermore, patient trust has a prominent effect on patient attitude toward treatment adherence, which in turn influences patients’ behavioral intention and actual adherence behavior. Based on the theory of planned behavior, the results also indicated that behavioral intention, response efficacy, and self-efficacy positively influenced patients’ actual treatment adherence behavior, whereas descriptive norms and subjective norms do not play a role in this process. Conclusions: Our study is one of the first that examines the relationship between patients who actively use an MPES and their trust in their physicians. This study contributes to this context by enriching the trust literature, addressing the call to identify key patient-centered technology determinants of trust, advancing the understanding of patient adherence mechanisms, adding a new explanation of the influence of education mechanisms delivered via mobile devices on patient adherence, and confirming that the theory of planned behavior holds in this patient adherence context.

Background: Low birthweight (LBW) is a leading cause of neonatal mortality in the United States and a major causative factor of adverse health effects in newborns. Identifying high-risk patients early in prenatal care is crucial to preventing adverse outcomes. Previous studies have proposed various machine learning (ML) models for LBW prediction task, but they were limited by small and imbalanced data sets. Some authors attempted to address this through different data rebalancing methods. However, most of their reported performances did not reflect the models’ actual performance in real-life scenarios. To date, few studies have successfully benchmarked the performance of ML models in maternal health; thus, it is critical to establish benchmarks to advance ML use to subsequently improve birth outcomes.Objective: This study aimed to establish several key benchmarking ML models to predict LBW and systematically apply different rebalancing optimization methods to a large-scale and extremely imbalanced all-payer hospital record data set that connects mother and baby data at a state level in the United States. We also performed feature importance analysis to identify the most contributing features in the LBW classification task, which can aid in targeted intervention.Methods: Our large data set consisted of 266,687 birth records across 6 years, and 8.63% (n=23,019) of records were labeled as LBW. To set up benchmarking ML models to predict LBW, we applied 7 classic ML models (ie, logistic regression, naive Bayes, random forest, extreme gradient boosting, adaptive boosting, multilayer perceptron, and sequential artificial neural network) while using 4 different data rebalancing methods: random undersampling, random oversampling, synthetic minority oversampling technique, and weight rebalancing. Owing to ethical considerations, in addition to ML evaluation metrics, we primarily used recall to evaluate model performance, indicating the number of correctly predicted LBW cases out of all actual LBW cases, as false negative health care outcomes could be fatal. We further analyzed feature importance to explore the degree to which each feature contributed to ML model prediction among our best-performing models.Results: We found that extreme gradient boosting achieved the highest recall score—0.70—using the weight rebalancing method. Our results showed that various data rebalancing methods improved the prediction performance of the LBW group substantially. From the feature importance analysis, maternal race, age, payment source, sum of predelivery emergency department and inpatient hospitalizations, predelivery disease profile, and different social vulnerability index components were important risk factors associated with LBW.Conclusions: Our findings establish useful ML benchmarks to improve birth outcomes in the maternal health domain. They are informative to identify the minority class (ie, LBW) based on an extremely imbalanced data set, which may guide the development of personalized LBW early prevention, clinical interventions, and statewide maternal and infant health policy changes.

Live streaming shopping platforms are increasingly gaining momentum. However, how live streaming engages its viewers and induces purchase is poorly understood. Viewing a shopping process as fulfilling both utilitarian and hedonic values and based on social information foraging theory , we identify a unique characteristic of live streaming platforms, namely, live interactivity , and conceptualize its main components. We also hypothesize the impact of live interactivity from a utilitarian value view (i.e., product diagnosticity , product serendipity, and sensory appeal ) and a hedonic value view (i.e., entertainingness ). We argue that viewers will experience enhanced utilitarian and hedonic values when using the live streaming shopping platform, which in turn leads them to exhibit heightened purchase intention . Based on the survey data of 200 individuals, we find that live interactivity is positively related to product diagnosticity, serendipity, sensory appeal, and entertainingness. Except for product serendipity, the other three significantly lead to viewers’ purchase intention on a live streaming platform. Our findings add to the live streaming literature by conceptualizing and dimensionalizing live interactivity, theorizing its impacts, and exploring its underlying processes associated with product features and viewer engagement in their decision-making.