Background: Pressure injury (PI) is a common and preventable problem, yet it is a challenge for at least two reasons. First, the nurse shortage is a worldwide phenomenon. Second, the majority of nurses have insufficient PI-related knowledge. Machine learning (ML) technologies can contribute to lessening the burden on medical staff by improving the prognosis and diagnostic accuracy of PI. To the best of our knowledge, there is no existing systematic review that evaluates how the current ML technologies are being used in PI management. Objective: The objective of this review was to synthesize and evaluate the literature regarding the use of ML technologies in PI management, and identify their strengths and weaknesses, as well as to identify improvement opportunities for future research and practice. Methods: We conducted an extensive search on PubMed, EMBASE, Web of Science, Cumulative Index to Nursing and Allied Health Literature (CINAHL), Cochrane Library, China National Knowledge Infrastructure (CNKI), the Wanfang database, the VIP database, and the China Biomedical Literature Database (CBM) to identify relevant articles. Searches were performed in June 2020. Two independent investigators conducted study selection, data extraction, and quality appraisal. Risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). Results: A total of 32 articles met the inclusion criteria. Twelve of those articles (38%) reported using ML technologies to develop predictive models to identify risk factors, 11 (34%) reported using them in posture detection and recognition, and 9 (28%) reported using them in image analysis for tissue classification and measurement of PI wounds. These articles presented various algorithms and measured outcomes. The overall risk of bias was judged as high. Conclusions: There is an array of emerging ML technologies being used in PI management, and their results in the laboratory show great promise. Future research should apply these technologies on a large scale with clinical data to further verify and improve their effectiveness, as well as to improve the methodological quality.

Background: Storytelling interventions have demonstrated substantial potential in improving emotional well-being, cognitive function, and quality of life for older adults. However, its effectiveness is often limited by the challenges of processing disorganized and redundant life stories, which impose substantial cognitive demands on caregivers. Although storytelling interventions are a well-established therapeutic approach, current practices depend heavily on manual narrative organization, restricting both the scalability and consistency of treatment delivery. Prior research has primarily focused on validating the clinical outcomes of storytelling interventions, with insufficient attention given to technological solutions that could enhance narrative processing while preserving therapeutic integrity. Digital approaches to life story structuring remain underexplored, despite their potential to amplify storytelling benefits by reducing cognitive load and improving recall accuracy. Objective: This study aims to design an event timeline generation algorithm to optimize the prior work of the Story Mosaic system. The optimized system enables (1) the automatic extraction of event elements from life narratives, (2) the automatic organization of fragmented life stories into structured timelines, and (3) the preservation of clinically relevant contextual details during compression. The goal is to reduce manual intervention costs while increasing treatment efficacy through artificial intelligence–driven narrative structuring. Methods: We have designed a novel method, CARE event timeline (CARE-ET), which combines a temporal attention mechanism with graph-based event relationship modeling. Furthermore, we used the CARE-ET algorithm to optimize existing story collage systems. The system uses multifeature extraction technology to capture event clues from oral histories, prioritizes the 6 elements of events through a hierarchical attention mechanism, and uses adaptive compression algorithms to reduce redundancy while maintaining narrative continuity. To verify the effectiveness of the CARE-ET method, this paper adopts a multidimensional evaluation framework, which encompasses event summary assessment, timeline quality evaluation, and usability testing of the optimized system. Results: The proposed CARE-ET algorithm outperforms the baseline in both narrative flow and temporal accuracy. The Story Mosaic system, optimized by the CARE-ET algorithm, underwent usability evaluation by 10 caregivers recruited for this study. Based on standardized assessment metrics, the system received an A rating for usability. The comprehensive experimental results demonstrate that the CARE-ET method can effectively structure fragmented narratives from older adults, enhancing the usability of the Story Mosaic system. Conclusions: The proposed method enables the structured extraction of representative event summaries, transforming disorganized life stories into an event timeline for caregiver-supported older adult well-being interventions. Future research should investigate longitudinal effects on cognitive preservation and explore integration with existing dementia care protocols. This work establishes a critical foundation for intelligent assistive technologies in geriatric mental health interventions.

Pressure injury (PI) is one of the major causes of short-term death. Early intervention for patients at risk plays an essential role in PI. However, many nurses may ignore risks. This paper aims to establish a model to predict interventions according to the patient's physical signs, which can help nurses develop care plans. We used data from 1,483 patients with 25 characteristics and 17 interventions. We use the Random Forest and Particle Swarm Optimization (PSO) to optimize model parameters. Then we compared it with KNN, SVM, and Decision Tree. The 10-fold cross-validation result showed that the Random Forest has better accuracy than other methods, with an f1 score of 0.84. This finding proved the feasibility of using machine learning to help formulate care plans according to the classification of index prediction results. Our model shows that hemoglobin, Braden PI score, and age are the three most influential risk factors.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Pressure injury (PI) is a common and preventable problem, yet it is a challenge for at least two reasons. First, the nurse shortage is a worldwide phenomenon. Second, the majority of nurses have insufficient PI-related knowledge. Machine learning (ML) technologies can contribute to lessening the burden on medical staff by improving the prognosis and diagnostic accuracy of PI. To the best of our knowledge, there is no existing systematic review that evaluates how the current ML technologies are being used in PI management. Objective: The objective of this review was to synthesize and evaluate the literature regarding the use of ML technologies in PI management, and identify their strengths and weaknesses, as well as to identify improvement opportunities for future research and practice. Methods: We conducted an extensive search on PubMed, EMBASE, Web of Science, Cumulative Index to Nursing and Allied Health Literature (CINAHL), Cochrane Library, China National Knowledge Infrastructure (CNKI), the Wanfang database, the VIP database, and the China Biomedical Literature Database (CBM) to identify relevant articles. Searches were performed in June 2020. Two independent investigators conducted study selection, data extraction, and quality appraisal. Risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). Results: A total of 32 articles met the inclusion criteria. Twelve of those articles (38%) reported using ML technologies to develop predictive models to identify risk factors, 11 (34%) reported using them in posture detection and recognition, and 9 (28%) reported using them in image analysis for tissue classification and measurement of PI wounds. These articles presented various algorithms and measured outcomes. The overall risk of bias was judged as high. Conclusions: There is an array of emerging ML technologies being used in PI management, and their results in the laboratory show great promise. Future research should apply these technologies on a large scale with clinical data to further verify and improve their effectiveness, as well as to improve the methodological quality.

BACKGROUND Storytelling intervention has demonstrated significant potential in improving emotional well-being, cognitive function, and quality of life for older adults. However, its effectiveness is often limited by the challenges of processing disorganized and redundant life stories, which impose substantial cognitive demands on caregivers. Although storytelling intervention is a well-established therapeutic approach, current practices depend heavily on manual narrative organization, restricting both the scalability and consistency of treatment delivery. Prior research has primarily focused on validating the clinical outcomes of storytelling intervention, with insufficient attention given to technological solutions that could enhance narrative processing while preserving therapeutic integrity. Digital approaches to life story structuring remain underexplored, despite their potential to amplify storytelling intervention benefits by reducing cognitive load and improving recall accuracy. OBJECTIVE This study aims to enhance cognitive reminiscence therapy (CRT) by developing Story Mosaic, a collaborative computing system designed to (1) automatically organize fragmented life stories into structured timelines, (2) retain clinically relevant contextual details during compression, and (3) optimize recall processes for improved therapeutic outcomes. The goal is to reduce manual intervention costs while increasing treatment efficacy through AI-driven narrative structuring. METHODS We have designed a novel method, CARE-ET, which combines a temporal attention mechanism with graph-based event relationship modeling, and developed the Story Mosaic system based on this method as its core algorithm. The system uses multi-feature extraction technology to capture event clues from oral histories; it prioritizes the six elements of events through a hierarchical attention mechanism; and it uses adaptive compression algorithms to reduce redundancy while maintaining narrative continuity. The system validation employed a comprehensive mixed-methods approach comprising: (1) quantitative performance evaluation of the CARE-ET algorithm, (2) qualitative assessment of cognitive load differences between AI-assisted and manual organization methods, and (3) usability evaluation of the Story Mosaic system - both conducted through qualitative interviews with 10 caregivers. RESULTS The proposed CARE-ET algorithm outperforms the baseline in both narrative flow and temporal accuracy. Caregiver interviews revealed that the structured life stories exhibited strong readability and comprehensibility, reducing work-related stress and cognitive load. System usability evaluations achieved an A- grade based on standardized metrics. Qualitative feedback from participants highlighted enhanced confidence in memory retrieval during therapy sessions. These findings collectively indicate that the Story Mosaic system based on the CART-ET method is helpful in enhancing CRT. Future research should investigate longitudinal effects on cognitive preservation and explore integration with existing dementia care protocols. This work establishes a critical foundation for intelligent assistive technologies in geriatric mental health interventions. CONCLUSIONS The proposed method enables structured extraction of representative event summaries, transforming disorganized life stories into actionable data for caregiver-supported elderly wellbeing interventions.