Sleep-wake monitoring of people with intellectual disability: Examining the agreement of EMFIT QS and actigraphy.

BACKGROUND: Gaining insight into sleep-wake patterns of persons with intellectual disabilities is commonly done using wrist actigraphy. For some people, contactless alternatives are needed. This study compares a contactless bed sensor with wrist actigraphy to monitor sleep-wake patterns of people with moderate to profound intellectual disabilities. METHOD: Data were collected with EMFIT QS (activity and presence) and MotionWatch 8/Actiwatch 2 (activity, ambient light, and event marker/sleep diary) for 14 nights in 13 adults with moderate-profound intellectual disabilities residing in intramural care. RESULTS: In a care-as-usual setting, EMFIT QS and actigraphy assessment show little agreement on sleep-wake variables. CONCLUSION: Currently, EMFIT QS should not be considered an alternative to wrist actigraphy for sleep-wake monitoring. Further research is needed into assessing sleep-wake variables using (contactless) technological devices and how the data should be interpreted within the care context to achieve reliable and valid information on sleep-wake patterns of people with intellectual disabilities.

Toward Responsible Artificial Intelligence in Long-Term Care: A Scoping Review on Practical Approaches.

BACKGROUND AND OBJECTIVES: Artificial intelligence (AI) is widely positioned to become a key element of intelligent technologies used in the long-term care (LTC) for older adults. The increasing relevance and adoption of AI has encouraged debate over the societal and ethical implications of introducing and scaling AI. This scoping review investigates how the design and implementation of AI technologies in LTC is addressed responsibly: so-called responsible innovation (RI). RESEARCH DESIGN AND METHODS: We conducted a systematic literature search in 5 electronic databases using concepts related to LTC, AI, and RI. We then performed a descriptive and thematic analysis to map the key concepts, types of evidence, and gaps in the literature. RESULTS: After reviewing 3,339 papers, 25 papers were identified that met our inclusion criteria. From this literature, we extracted 3 overarching themes: user-oriented AI innovation; framing AI as a solution to RI issues; and context-sensitivity. Our results provide an overview of measures taken and recommendations provided to address responsible AI innovation in LTC. DISCUSSION AND IMPLICATIONS: The review underlines the importance of the context of use when addressing responsible AI innovation in LTC. However, limited empirical evidence actually details how responsible AI innovation is addressed in context. Therefore, we recommend expanding empirical studies on RI at the level of specific AI technologies and their local contexts of use. Also, we call for more specific frameworks for responsible AI innovation in LTC to flexibly guide researchers and innovators. Future frameworks should clearly distinguish between RI processes and outcomes.

Cognitive map formation supported by auditory, haptic, and multimodal information in persons with blindness.

For efficient navigation, the brain needs to adequately represent the environment in a cognitive map. In this review, we sought to give an overview of literature about cognitive map formation based on non-visual modalities in persons with blindness (PWBs) and sighted persons. The review is focused on the auditory and haptic modalities, including research that combines multiple modalities and real-world navigation. Furthermore, we addressed implications of route and survey representations. Taking together, PWBs as well as sighted persons can build up cognitive maps based on non-visual modalities, although the accuracy sometime somewhat differs between PWBs and sighted persons. We provide some speculations on how to deploy information from different modalities to support cognitive map formation. Furthermore, PWBs and sighted persons seem to be able to construct route as well as survey representations. PWBs can experience difficulties building up a survey representation, but this is not always the case, and research suggests that they can acquire this ability with sufficient spatial information or training. We discuss possible explanations of these inconsistencies.

Opportunities and Pitfalls in Applying Emotion Recognition Software for Persons With a Visual Impairment: Simulated Real Life Conversations.

BACKGROUND: A large part of the communication cues exchanged between persons is nonverbal. Persons with a visual impairment are often unable to perceive these cues, such as gestures or facial expression of emotions. In a previous study, we have determined that visually impaired persons can increase their ability to recognize facial expressions of emotions from validated pictures and videos by using an emotion recognition system that signals vibrotactile cues associated with one of the six basic emotions. OBJECTIVE: The aim of this study was to determine whether the previously tested emotion recognition system worked equally well in realistic situations and under controlled laboratory conditions. METHODS: The emotion recognition system consists of a camera mounted on spectacles, a tablet running facial emotion recognition software, and a waist belt with vibrotactile stimulators to provide haptic feedback representing Ekman's six universal emotions. A total of 8 visually impaired persons (4 females and 4 males; mean age 46.75 years, age range 28-66 years) participated in two training sessions followed by one experimental session. During the experiment, participants engaged in two 15 minute conversations, in one of which they wore the emotion recognition system. To conclude the study, exit interviews were conducted to assess the experiences of the participants. Due to technical issues with the registration of the emotion recognition software, only 6 participants were included in the video analysis. RESULTS: We found that participants were quickly able to learn, distinguish, and remember vibrotactile signals associated with the six emotions. A total of 4 participants felt that they were able to use the vibrotactile signals in the conversation. Moreover, 5 out of the 6 participants had no difficulties in keeping the camera focused on the conversation partner. The emotion recognition was very accurate in detecting happiness but performed unsatisfactorily in recognizing the other five universal emotions. CONCLUSIONS: The system requires some essential improvements in performance and wearability before it is ready to support visually impaired persons in their daily life interactions. Nevertheless, the participants saw potential in the system as an assistive technology, assuming their user requirements can be met.

Conveying facial expressions to blind and visually impaired persons through a wearable vibrotactile device.

In face-to-face social interactions, blind and visually impaired persons (VIPs) lack access to nonverbal cues like facial expressions, body posture, and gestures, which may lead to impaired interpersonal communication. In this study, a wearable sensory substitution device (SSD) consisting of a head mounted camera and a haptic belt was evaluated to determine whether vibrotactile cues around the waist could be used to convey facial expressions to users and whether such a device is desired by VIPs for use in daily living situations. Ten VIPs (mean age: 38.8, SD: 14.4) and 10 sighted persons (SPs) (mean age: 44.5, SD: 19.6) participated in the study, in which validated sets of pictures, silent videos, and videos with audio of facial expressions were presented to the participant. A control measurement was first performed to determine how accurately participants could identify facial expressions while relying on their functional senses. After a short training, participants were asked to determine facial expressions while wearing the emotion feedback system. VIPs using the device showed significant improvements in their ability to determine which facial expressions were shown. A significant increase in accuracy of 44.4% was found across all types of stimuli when comparing the scores of the control (mean±SEM: 35.0±2.5%) and supported (mean±SEM: 79.4±2.1%) phases. The greatest improvements achieved with the support of the SSD were found for silent stimuli (68.3% for pictures and 50.8% for silent videos). SPs also showed consistent, though not statistically significant, improvements while supported. Overall, our study shows that vibrotactile cues are well suited to convey facial expressions to VIPs in real-time. Participants became skilled with the device after a short training session. Further testing and development of the SSD is required to improve its accuracy and aesthetics for potential daily use.

Exploring Determinants of Patient Adherence to a Portal-Supported Oncology Rehabilitation Program: Interview and Data Log Analyses.

BACKGROUND: Telemedicine applications often do not live up to their expectations and often fail once they have reached the operational phase. OBJECTIVE: The objective of this study was to explore the determinants of patient adherence to a blended care rehabilitation program, which includes a Web portal, from a patient's perspective. METHODS: Patients were enrolled in a 12-week oncology rehabilitation treatment supported by a Web portal that was developed in cooperation with patients and care professionals. Semistructured interviews were used to analyze thought processes and behavior concerning patient adherence and portal use. Interviews were conducted with patients close to the start and the end of the treatment. Besides, usage data from the portal were analyzed to gain insights into actual usage of the portal. RESULTS: A total of 12 patients participated in the first interview, whereas 10 participated in the second round of interviews. Furthermore, portal usage of 31 patients was monitored. On average, 11 persons used the portal each week, with a maximum of 20 in the seventh week and a drop toward just one person in the weeks in the follow-up period of the treatment. From the interviews, it was derived that patients' behavior in the treatment and use of the portal was primarily determined by extrinsic motivation cues (eg, stimulation by care professionals and patient group), perceived severity of the disease (eg, physical and mental condition), perceived ease of use (eg, accessibility of the portal and the ease with which information is found), and perceived usefulness (eg, fit with the treatment). CONCLUSIONS: The results emphasized the impact that care professionals and fellow patients have on patient adherence and portal usage. For this reason, the success of blended care telemedicine interventions seems highly dependent on the willingness of care professionals to include the technology in their treatment and stimulate usage among patients.