Background: Dysphagia affects more than half of older adults with dementia and is associated with a 10-fold increase in mortality. The development of accessible, objective, and reliable screening tools is crucial for early detection and management. Objective: This systematic scoping review aimed to (1) examine the current state of the art in artificial intelligence (AI) and sensor-based technologies for dysphagia screening, (2) evaluate the performance of these AI-based screening tools, and (3) assess the methodological quality and rigor of studies on AI-based dysphagia screening tools. Methods: We conducted a systematic literature search across CINAHL, Embase, PubMed, and Web of Science from inception to July 4, 2024, following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) framework. In total, 2 independent researchers conducted the search, screening, and data extraction. Eligibility criteria included original studies using sensor-based instruments with AI to identify individuals with dysphagia or unsafe swallow events. We excluded studies on pediatric, infant, or postextubation dysphagia, as well as those using non–sensor-based assessments or diagnostic tools. We used a modified Quality Assessment of Diagnostic Accuracy Studies–2 tool to assess methodological quality, adding a “model” domain for AI-specific evaluation. Data were synthesized narratively. Results: This review included 24 studies involving 2979 participants (1717 with dysphagia and 1262 controls). In total, 75% (18/24) of the studies focused solely on per-individual classification rather than per–swallow event classification. Acoustic (13/24, 54%) and vibratory (9/24, 38%) signals were the primary modality sources. In total, 25% (6/24) of the studies used multimodal approaches, whereas 75% (18/24) used a single modality. Support vector machine was the most common AI model (15/24, 62%), with deep learning approaches emerging in recent years (3/24, 12%). Performance varied widely—accuracy ranged from 71.2% to 99%, area under the receiver operating characteristic curve ranged from 0.77 to 0.977, and sensitivity ranged from 63.6% to 100%. Multimodal systems generally outperformed unimodal systems. The methodological quality assessment revealed a risk of bias, particularly in patient selection (unclear in 18/24, 75% of the studies), index test (unclear in 23/24, 96% of the studies), and modeling (high risk in 13/24, 54% of the studies). Notably, no studies conducted external validation or domain adaptation testing, raising concerns about real-world applicability. Conclusions: This review provides a comprehensive overview of technological advancements in AI and sensor-based dysphagia screening. While these developments show promise for continuous long-term tele-swallowing assessments, significant methodological limitations were identified. Future studies can explore how each modality can target specific anatomical regions and manifestations of dysphagia. This detailed understanding of how different modalities address various aspects of dysphagia can significantly benefit multimodal systems, enabling them to better handle the multifaceted nature of dysphagia conditions.

This study aimed to investigate clinical effectiveness of a structured eight-week mindfulness-based music therapy (MBMT) program on improving mood regulation in older women with blindness. This investigation compared a MBMT group with a mindfulness intervention (MI) group and a control group. Ninety-two older females with blindness from a residential setting in Hong Kong were recruited and randomly allocated to a MBMT (n = 31), MI (n = 30), or control (n = 31) group. Psychological measurements regarding mood regulation and general mood states (namely, Difficulties in Emotion Regulation Scale [DERS], Geriatric Depression Scale [GDS], and Depression Anxiety Stress Scales-21), were taken at pretest and posttest. Outcome assessors were blinded to group assignment. Data was analyzed based on intention-to-treat basis. At posttest, DERS scores in the MBMT group (mean differences and 95% confidence interval: 12.1, 5.5 to 18.8) and the MI group (7.2, 0.5 to 13.8) were lower than that in the control group. GDS scores in the MBMT group (2.9, 1.7 to 4.0) and the MI group (1.7, 0.6 to 2.9) were lower than those in the control group. Compared with the MI group, the MBMT group improved emotional awareness sub-scores in DERS (2.1, 0.2 to 4.1) and appeared to lower depression in GDS scores (1.1, -0.0 to 2.3; p = 0.053). MBMT seems more beneficial than MI alone for improving emotional regulation in older women with blindness. The combination of mindfulness and music can generate a synergetic effect by enhancing both attention and appraisal components within the emotional-regulation process. ClinicalTrials.gov, NCT05583695.

Dementia causes disorders in multiple higher cortical functions. Visual impairment could further impact cognition in those with dementia. This study reports the results of a computerized attention training program in a patient with dementia and visual impairment. The case involves a 98-year-old woman with bilateral maculopathy and moderate dementia. The program consisted of pre- and post-assessments and training sessions. Assessments included the Cantonese version of the Mini-Mental State Examination, the digit span forward test, the Chinese version of the Verbal Learning Test (CVVLT), and the Test of Attentional Performance (TAP). Training sessions were conducted once to twice a week for a total of 8 45-minute sessions. The participant showed a decrease in the CVVLT score and improvements in TAP parameters. The results indicated that, in visually impaired older adults with dementia, attention and processing speed (measured by a sensitive test such as TAP) could potentially be improved with appropriate computerized training.

BACKGROUND Dysphagia affects more than half of older adults with dementia and is associated with a 10-fold increase in mortality. The development of accessible, objective, and reliable screening tools is crucial for early detection and management. OBJECTIVE This systematic scoping review aimed to (1) examine the current state of the art in artificial intelligence (AI) and sensor-based technologies for dysphagia screening, (2) evaluate the performance of these AI-based screening tools, and (3) assess the methodological quality and rigor of studies on AI-based dysphagia screening tools. METHODS We conducted a systematic literature search across CINAHL, Embase, PubMed, and Web of Science from inception to July 4, 2024, following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) framework. In total, 2 independent researchers conducted the search, screening, and data extraction. Eligibility criteria included original studies using sensor-based instruments with AI to identify individuals with dysphagia or unsafe swallow events. We excluded studies on pediatric, infant, or postextubation dysphagia, as well as those using non–sensor-based assessments or diagnostic tools. We used a modified Quality Assessment of Diagnostic Accuracy Studies–2 tool to assess methodological quality, adding a “model” domain for AI-specific evaluation. Data were synthesized narratively. RESULTS This review included 24 studies involving 2979 participants (1717 with dysphagia and 1262 controls). In total, 75% (18/24) of the studies focused solely on per-individual classification rather than per–swallow event classification. Acoustic (13/24, 54%) and vibratory (9/24, 38%) signals were the primary modality sources. In total, 25% (6/24) of the studies used multimodal approaches, whereas 75% (18/24) used a single modality. Support vector machine was the most common AI model (15/24, 62%), with deep learning approaches emerging in recent years (3/24, 12%). Performance varied widely—accuracy ranged from 71.2% to 99%, area under the receiver operating characteristic curve ranged from 0.77 to 0.977, and sensitivity ranged from 63.6% to 100%. Multimodal systems generally outperformed unimodal systems. The methodological quality assessment revealed a risk of bias, particularly in patient selection (unclear in 18/24, 75% of the studies), index test (unclear in 23/24, 96% of the studies), and modeling (high risk in 13/24, 54% of the studies). Notably, no studies conducted external validation or domain adaptation testing, raising concerns about real-world applicability. CONCLUSIONS This review provides a comprehensive overview of technological advancements in AI and sensor-based dysphagia screening. While these developments show promise for continuous long-term tele-swallowing assessments, significant methodological limitations were identified. Future studies can explore how each modality can target specific anatomical regions and manifestations of dysphagia. This detailed understanding of how different modalities address various aspects of dysphagia can significantly benefit multimodal systems, enabling them to better handle the multifaceted nature of dysphagia conditions.

Studies have shown that visual impairment is associated with an increased risk of cognitive decline. Individuals with co-existing cognitive and visual impairments are also at a higher risk of having disability, which can further impact on one’s independence in everyday activities. Computerized Cognitive Training (CCT) is one of the non-pharmacological interventions in managing cognitive decline. Objective: This study investigated the effects of an auditory CTT program in a group of participants with both cognitive and visual impairment. Methods: Sixteen participants were recruited. Participants had cognitive complaints and visual impairment. They received eight sessions of auditory-based CCT once or twice a week for 45 minutes within a 6-week period for each participant. Pre- and post-assessments were conducted before and after the training. Neuropsychological assessments included the Cantonese version of the Mini-Mental State Examination (CMMSE), the digit span forward test, the Chinese version of the Verbal Learning Test (CVVLT), and memory subtest of Neurobehavioral Cognitive Status Examination (NCSE). Pre- and post- mean assessment scores were compared. Results: Mean CMMSE score for this group of participants was 18.1. Significant differences were found in four assessments (digit span forward, CVVLT-Total: CVVLT-first trial, and NCSE-memory). No significant differences were found in the other tests. Additional repeated measures analysis showed age might play a role in CVVLT first trial and CVVLT total scores. Conclusion: The study is limited by its one-group design. The results provide preliminary evidence that auditory-based CCT may be beneficial to attention and memory in people with both cognitive and visual impairment.