Guided or factual computer support for kidney patients with different experience levels and medical health situations: preferences and usage

Abstract

Background Personalization of eHealth systems is a promising technique for improving patients' adherence. This paper explores the possibility of personalisation based on the patients' medical health situation and on their health literacy. The study is set within the context of a self-management support system (SMSS) for renal transplant patients. Methods A SMSS is designed with layering, nudging, emphaticizing, and focusing principles. It has two communication styles: (1) a guided style that provided more interpretation support and addressed emotional needs; and (2) a factual style that showed only measurement history, medical information, and recommendations. To evaluate the design, 49 renal transplant patients with three different experience levels participated in a lab study, in which they used the system in imaginary scenarios to deal with three medical health situations (alright, mild concern, and concern). Results A 96% understanding and 87% adherence rate was observed, with a significant interaction effect on adherence between patient group and health situation. Furthermore, compared to recently transplanted patients, not recently transplanted patients were relatively more positive towards the factual than the guided communication style in the "alright" condition. Furthermore, additional medical information was searched more often in health situations that causes mild concern and a majority of patients did not change the communication style to their preferred styles. Conclusion By attuning the communication style to patient's experience and medical health situation according to the applied principles and acquired insights, SMSSs are expected to be better used.

Feasibility of generating structured motivational messages for tailored physical activity coaching

“…Thirdly, we only considered messages represented in text form. However, other types of representation such as images ( 61 ), videos ( 62 ), or even emoticons ( 63 ) are possible. For example, auditory feedback was used in a study by Singh et al ( 64 ) to motivate people with chronic pain to be more physically active, and audio, visual, and haptic representations of motivational messages were proposed by Op den Akker et al ( 27 ).…”

Addressing people’s current and future states in a reinforcement learning algorithm for persuading to quit smoking and to be physically active

“…Especially when persuasive attempts are made over a long time, might it be beneficial to give a lower weight to samples collected at the beginning of the interaction with the system. Furthermore, since people’s preferences can also change over time [ 97 ], the weights for later samples need to be chosen carefully as well.…”

“…Given the so far limited impact of persuasive messages, an alternative may be to strategically persuade people through an entire dialog (e.g., [98,102]). In addition, one could aim to further increase the processing of the persuasion by using multi-modal forms of persuasion (e.g., [97,103,104]). This choice of modalities can also be learned [105].…”