Back

From survey to support: Exploring hospitalized patients mental well-being and the opportunities for intelligent assistive devices

Meyer, A.; Rathmann, N.; Vetter, M.

2025-08-05 health systems and quality improvement
10.1101/2025.08.01.25332768 medRxiv
Show abstract

BackgroundIntelligent assistive technologies, including chatbots and wearable biosensors, hold considerable promise for transforming mental well-being support in healthcare settings. Hospital stays are often associated with emotional strain, influenced by environmental, procedural, and communication factors [1, 2]. Intelligent assistive technologies have the potential to provide real-time, personalized interventions. However, for a successful translation of these technologies into clinical practice, patient insights are imperative. [3-5] MethodsA 2023 cross-sectional survey at the Department of Radiology and Nuclear Medicine at the University Hospital Mannheim aimed to inform the development of intelligent assistive technologies for supporting the patients emotional well-being. The survey, which was designed to assess emotional states, psychological stressors, and care experiences, employed a mixed-methods approach, incorporating 39 questions. The data was analyzed using descriptive and inferential statistics, with qualitative responses coded for thematic patterns. ResultsThe survey revealed that prolonged waiting times (> 1 hour, 74% of participants) and communication problems significantly reduced mental well-being (mean score dropped from 4.45 to 3.57 out of 5, p = 0.027). Language barriers and organizational inefficiencies exacerbated distress, while staff empathy and social visits improved well-being. Prior to procedures, the most common stated emotions by participants were apprehension (68% therapeutic procedure and 58% diagnostic procedure) and anxiety (47% therapeutic, 21% diagnostic), with these emotions shifting to confidence (78% therapeutic, 57% diagnostic) and hope (62% therapeutic, 49% diagnostic) post-procedure. ConclusionThese findings highlight communication delays and procedural anxiety as key emotional stressors. The strategic implementation of intelligent assistive technologies, such as multilingual AI chatbots capable of providing real-time updates and biosensors monitoring physiological stress, has the potential to mitigate distress and enhance patient experiences, especially in situations with heightened emotional states (eg. pre-procedural phases, extended waiting periods, or limited information flow). Future development should prioritize co-design with patients and clinicians, with effectiveness validated through multi-center clinical trials.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.