A nurse versus a chatbot ‒ the effect of an empowerment program on chemotherapy-related side effects and the self-care behaviors of women living with breast Cancer: a randomized controlled trial

Abstract

Background The high levels of unmet needs in relation to provision of self-care information reported by women living with breast cancer suggests that pre-chemotherapy education is suboptimal. Chatbots are emerging as a promising platform to provide education to patients helping them self-manage their symptoms at home. However, evidence from empirical studies on the effect of chatbots education on women living with breast cancer self-care behaviors and symptoms management are scarce. Methods This three-arm randomized controlled trial was performed in a chemotherapy day care center within an oncology center in Egypt. A total of 150 women living with breast cancer were randomly selected and randomized into three groups: the ChemoFreeBot group (n = 50), the nurse-led education group (n = 50), and the routine care group (n = 50). In the ChemoFreeBot group, women were given a link to interact with ChemoFreeBot and ask questions about their symptoms and self-care interventions by typing questions or keywords at any time. On the same day as their first day of chemotherapy, the nurse-led education group received face to face teaching sessions from the researcher (nurse) about side effects and self-care interventions. The routine care group received general knowledge during their chemotherapy session about self-care interventions. The self-care behaviors effectiveness and the frequency, severity and distress of chemotherapy side effects were measured at baseline and postintervention for the three groups. The ChemoFreeBot’s usability was assessed. Results The mixed design repeated measures ANOVA analyses revealed a statistically significant both group effect and interaction effect of group*time, indicating a significant difference between the three groups in terms of the physical symptoms frequency (F = 76.075, p < .001, F = 147, p < .001, respectively), severity (F = 96.440, p < .001, F = 220.462, p < .001), and distress (F = 77.171, p < .001, F = 189.680, p < .001); the psychological symptoms frequency (F = 63.198, p < .001, F = 137.908, p < .001), severity (F = 62.137, p < .001), (F = 136.740, p < .001), and distress (F = 43.003, p < .001, F = 168.057, p < .001), and the effectiveness of self-care behaviors (F = 20.134, p < .001, F = 24.252, p < .001, respectively). The Post hoc analysis with Bonferroni adjustment in showed that women in the ChemoFreeBot group experienced a statistically significant less frequent, less severe and less distressing physical and psychological symptoms and higher effective self-care behaviors than those in the nurse-led education and routine care groups (p > .001). Conclusion ChemoFreeBot was a useful and cost-effective tool to improve increase self-care behavior and reduce chemotherapy side effects in women living with breast cancer through the provision of personalized education and the improvement of the accessibility to real-time and high-quality information compared to “one size fits all” approach used by nurses to provide the information. ChemoFreeBot can be an empowering tool to assist nurses to educate women with breast cancer and allow women to take an active role in managing their symptom. Trial registration This study was retrospectively registered in the University hospital Medical Information Network (UMIN) Center, Clinical Trials Registry on 26/09/2022; Registration No:R000055389,Trial ID:UMIN000048955.

A systematic review of artificial intelligence-powered (AI-powered) chatbot intervention for managing chronic illness

“…Out of the eight studies, five focused primarily on patients, providing support for education and self-care [ 27–31 ]. Three studies offered assistance to both patients and healthcare professionals in utilizing AI-powered chatbots for treatment and education [ 14 , 26 , 32 ].…”

“…Among the chronic illness investigated, cancer, including breast cancer, post-cancer treatment and geriatric oncology, was the subject of investigation in four studies [ 14 , 26 , 27 , 32 ]. One studying type 2 diabetes [ 29 ].…”

“…Among eight RCTs, only one [ 32 ] exhibited a low risk, two [ 29 , 30 ] exhibited a high-risk of missing outcome data, a significant portion of the data was not available, while five [ 14 , 26–28 , 31 ] raised some concerns regarding potential bias in outcome measurement. This was attributed to either the omission of blinding in the assessment process or the utilization of an unsuitable method to evaluate the intervention’s effects.…”

“…However, there was no statistically significant alteration in pain-related impairment observed in the intervention group compared to the control group [ 30 ]. Additionally, participants in the intervention group demonstrated improved treatment adherence, self-care management, heightened awareness of symptoms and triggers, fewer, milder and less distressing symptoms, and overall better self-care compared to the nurse-led education and routine care groups [ 32 ]. Some studies were not reported health related measures [ 26 , 27 ].…”

Managing chronic pain after breast cancer treatments: are web-based interventions the future?

“…Whilst pain was not a specific outcome, monitoring and acting on reported symptoms may reduce the risks from chemotherapy known to promote development of chronic pain. A chatbot was similarly reported as a useful and cost-effective intervention to improve self-management and reduce chemotherapy side effects in breast cancer by providing personalised education and improve the accessibility to real-time information [41▪].…”