Personal Tasks Research Articles

Joint reaction and simulated muscle forces during squatting and walking in persons with hemophilia

BackgroundPersons with hemophilia experience joint bleeding that can lead to debilitating arthropathy, most commonly seen in ankles, knees, and elbows. Arthropathy can hinder participation in daily and athletic activities. We explored how hemophilic arthropathy impacts movement patterns in walking and bilateral squatting tasks in persons with hemophilia compared to healthy controls. MethodsPersons with hemophilia and healthy controls completed walking and squatting tasks while kinematic and kinetic motion capture data were collected. The Hemophilia Joint Health Score exam was performed to measure hemophiliac arthropathy. OpenSim was used to model muscle and joint reaction forces and calculate moments and angles. Peak values were compared using Cohen's d to estimate effect sizes of hemophilia on movement parameters. FindingsNine persons with hemophilia and eight age-matched controls were analyzed. Temporal-spatial metrics were similar between hemophilia and control groups in both tasks. In walking, persons with hemophilia had higher peak ankle dorsiflexion angles, vertical ground reaction force weight acceptance peaks, and hip extension and flexion moments compared to controls. In squatting, persons with hemophilia had lower knee extension moments, ankle joint reaction force, and knee extensor forces, but had higher hip extension moments. InterpretationTemporal-spatial metric similarity between hemophilia and controls suggests that kinetic and kinematic analyses are needed to identify movement pattern differences. These data identify potential compensatory strategies at the hip that may be used by persons with hemophilia to mitigate impact on the knee and ankle. Future work will confirm these data in a larger sample size and be used to develop physical therapy strategies.

Exploration of digital health literacy in the deep south.

385 Background: As technological advances are implemented in healthcare, cancer patients with low digital health literacy are at risk for inequities. Understanding the community’s comfort with using and teaching technology skills can be foundational for the application of digital healthcare tools. Methods: A cross-sectional survey was administered prior to community conversations about digital health literacy to understand community comfort with technology. Surveys measured self-reported personal comfort performing, personal comfort teaching, and perceived county-comfort completing technology-based tasks. Participants rated their comfort level on a 5-point Likert scale (1= not at all, 2 = slightly, 3 = somewhat, 4 = moderately, 5 = completely). Mean scores were calculated and mean comfort levels were compared across healthcare providers, lay navigators, community health advisors (CHAs), and community members using one-way ANOVA tests. Tukey's HSD post-hoc tests were used to explore group differences. Results: Between 8/2023-4/2024, 164 participants across Alabama and Mississippi completed the pre-survey, including 32 healthcare providers, 17 lay navigators, 31 community health advisors (CHAs), and 84 community members. The sample was primarily female (90%), Black (74%), and from Alabama (84%). ANOVA tests revealed significant group differences between personal comfort levels (p<0.001) comfort teaching (p<0.001), and perception of county-level comfort in technology-based tasks (p=0.043) with lay navigators and healthcare providers reporting higher personal comfort and comfort teaching others technology-based tasks compared to community members (post-hoc Tukey’s HSD). Conclusions: Digital health literacy gaps remain, with lay and clinical providers potentially overestimating comfort with technology. Baseline technology skills must be addressed as healthcare increases reliance on technology. Personal Comfort p-value Comfort Teaching Others p-value Perception of County Comfort p-value Using Search Engines 3.61 4.72 4.76 4.23 <.0001 2.95 4.19 4.88 3.48 <.0001 2.52 3.16 3.82 3.13 0.043 Searching Online for Health-Related Information 3.49 4.66 4.71 4.06 2.90 4.03 4.71 3.35 2.46 2.69 3.29 2.97 Scanning QR codes 2.80 4.47 4.65 3.77 2.55 3.84 4.76 3.13 2.38 2.44 2.71 2.81 Logging into their Patient Portal 3.27 4.44 4.59 3.87 2.75 3.94 4.76 3.03 2.44 2.59 3.00 2.65 Sending their Care-Team a Message 3.05 4.38 4.65 3.74 2.63 3.91 4.82 3.03 2.37 2.44 2.71 2.58 Personal comfort, comfort teaching, perception of community comfort with technology; 7/17 tasks shown; C = community, H = hospital, L = lay navigator, CHAs = community health advisors.

IPerFEX-2023: Indonesian personal financial entity extraction using indoBERT-BiGRU-CRF model

There is minimal research focusing on applications of Indonesian named entity recognition (NER) in a specific domain. This study proposes an Indonesian personal financial entity extraction task that can be utilized in a financial assistant chatbot system to interpret user’s financial situation for personalization. Due to the simplicity that a chatbot has, it can promote financial management practices to youth as early as possible in their career. However, the challenge in financial NER is numerical entity extraction that relies heavily on contextual information and suffers the out-of-vocabulary (OOV) problem. Therefore, to extract 15 personal financial entities in daily Indonesian discussions (expense-type, expense-amount, income-type, income-amount, asset-type, asset-amount, saving-type, saving-amount, liability-type, liability-amount, family, time, financial-goal, age, and occupation), this research proposes a dataset, IPerFEX-2023, trained using the Bidirectional Gated Recurrent Unit BiGRU and Conditional Random Field (CRF) with Indonesian Bidirectional Encoder Representations from Transformers (IndoBERT) pre-trained model for feature embeddings (IndoBERT-BiGRU-CRF). It is compared with the corresponding Bidirectional Long Short-Term Memory (BiLSTM) (IndoBERT-BiLSTM-CRF) as baseline. Not only the IndoBERT-BiGRU-CRF model achieves the best performance with a 0.73 F1-score, but it is also 14% faster on average compared to the corresponding baseline model due to its simpler unit structure. This paper also discusses future directions covering model enhancement strategy based on the error analysis result and complementary tasks needed to complete personalization

Value of Engagement in Digital Health Technology Research: Evidence Across 6 Unique Cohort Studies.

Wearable digital health technologies and mobile apps (personal digital health technologies [DHTs]) hold great promise for transforming health research and care. However, engagement in personal DHT research is poor. The objective of this paper is to describe how participant engagement techniques and different study designs affect participant adherence, retention, and overall engagement in research involving personal DHTs. Quantitative and qualitative analysis of engagement factors are reported across 6 unique personal DHT research studies that adopted aspects of a participant-centric design. Study populations included (1) frontline health care workers; (2) a conception, pregnant, and postpartum population; (3) individuals with Crohn disease; (4) individuals with pancreatic cancer; (5) individuals with central nervous system tumors; and (6) families with a Li-Fraumeni syndrome affected member. All included studies involved the use of a study smartphone app that collected both daily and intermittent passive and active tasks, as well as using multiple wearable devices including smartwatches, smart rings, and smart scales. All studies included a variety of participant-centric engagement strategies centered on working with participants as co-designers and regular check-in phone calls to provide support over study participation. Overall retention, probability of staying in the study, and median adherence to study activities are reported. The median proportion of participants retained in the study across the 6 studies was 77.2% (IQR 72.6%-88%). The probability of staying in the study stayed above 80% for all studies during the first month of study participation and stayed above 50% for the entire active study period across all studies. Median adherence to study activities varied by study population. Severely ill cancer populations and postpartum mothers showed the lowest adherence to personal DHT research tasks, largely the result of physical, mental, and situational barriers. Except for the cancer and postpartum populations, median adherences for the Oura smart ring, Garmin, and Apple smartwatches were over 80% and 90%, respectively. Median adherence to the scheduled check-in calls was high across all but one cohort (50%, IQR 20%-75%: low-engagement cohort). Median adherence to study-related activities in this low-engagement cohort was lower than in all other included studies. Participant-centric engagement strategies aid in participant retention and maintain good adherence in some populations. Primary barriers to engagement were participant burden (task fatigue and inconvenience), physical, mental, and situational barriers (unable to complete tasks), and low perceived benefit (lack of understanding of the value of personal DHTs). More population-specific tailoring of personal DHT designs is needed so that these new tools can be perceived as personally valuable to the end user.

Cultural bias and cultural alignment of large language models.

Culture fundamentally shapes people's reasoning, behavior, and communication. As people increasingly use generative artificial intelligence (AI) to expedite and automate personal and professional tasks, cultural values embedded in AI models may bias people's authentic expression and contribute to the dominance of certain cultures. We conduct a disaggregated evaluation of cultural bias for five widely used large language models (OpenAI's GPT-4o/4-turbo/4/3.5-turbo/3) by comparing the models' responses to nationally representative survey data. All models exhibit cultural values resembling English-speaking and Protestant European countries. We test cultural prompting as a control strategy to increase cultural alignment for each country/territory. For later models (GPT-4, 4-turbo, 4o), this improves the cultural alignment of the models' output for 71-81% of countries and territories. We suggest using cultural prompting and ongoing evaluation to reduce cultural bias in the output of generative AI.

Examining First- and Second-Level Digital Divide at the Intersection of Race/Ethnicity, Gender, and Socioeconomic Status: An Analysis of the National Health and Aging Trends Study.

Significant societal and technological changes in the 2010s called for an up-to-date understanding of the digital divide among older adults in the United States. This trend study aimed to examine the effects of race/ethnicity and the intersecting effects of race/ethnicity with other marginalized identities related to gender, income, education, and occupation on the first- and second-level digital divide. Utilizing a nationally representative sample of older community dwellers from the National Health and Aging Trends Study, we conducted weighted logistic regressions at 3 time points (2011/2013, 2015, and 2019). The first-level digital divide was measured by access to working phones or computers/laptops; the second-level divide was measured by 7 activities in personal task, social, and health-related Internet use. The first-level racial/ethnic digital divide became nonsignificant in 2019, whereas the disparities in all second-level measures persisted. The intersecting effects of race/ethnicity with low education and/or low income became nonsignificant in 2019 for personal-task use. However, the interactions with low education and/or low income became significant for social and health-related use in 2015 and/or 2019. This study highlights the persistence of the second-level racial/ethnic digital divide among older community dwellers in the United States, especially the exacerbated social and health-related digital divide for people of color with low socioeconomic status. By considering intersections of marginalized social identities, policymakers and stakeholders should develop targeted strategies to bridge the digital divide, promote health outcomes, and reduce health disparities.

SQL Injection Attack Detection Based on Similarity Matching Between Vectors Extracted From Design Time and Run-Time Queries

Everyone uses web-based applications to carry out daily business and personal tasks. These programmes are vulnerable to attack by hackers, who may also misuse the data. The most serious attack with the greatest damaging potential on digital platforms is the structured query language injection attack (SQLiA). The backend databases could be corrupted or destroyed by SQLiA if it manages to breach security protections. Using SQLiA tactics, hackers can get unauthorized access, steal important data, and take over the network completely or partially. An automatic SQL injection prevention and detection technique is needed to safeguard web-based applications from SQLiA. This research suggests a novel similarity-matching algorithm of vectors extracted from design time and run-time queries. This technique allocates the weights of different SQL keywords used in design time and run-time queries and further design time and run-time vectors have been created from respective queries. The similarity between the design time and run time vector is determined by calculating the angle between these two vectors. The angle of deviation between the design time vector and run time vector is calculated and if the angle of deviation is zero, then it is concluded as no SQL injection otherwise, it indicates the existence of SQLiA vulnerability. The proposed algorithm is validated against the GitHub dataset. In the first dataset, out of 1300 injected queries, the proposed method identifies 1219 injected queries; out of 300 normal queries, it identifies 290 normal queries with 93.76% and 96.66% detection accuracy, respectively. Similarly, for the second dataset, out of 10489 injected queries, it identifies 10280 injected queries and out of 301 normal queries, it identifies 280 normal queries with 98.01% and 93.02% detection accuracy, respectively.

Supplemental Material for Judging Beauty and Liking: The Effects of Personal Intuitions and Task Instructions

Supplemental Material for Judging Beauty and Liking: The Effects of Personal Intuitions and Task Instructions

Enhanced functional brain network integration in mild cognitive impairment during cognitive task performance: A compensatory mechanism or a result of neural disinhibition?

Although previous studies have observed increased global network integration during tasks in persons with mild cognitive impairment (MCI), the association between this integration and actual task performance has remained unexplored. Understanding this link is crucial for uncovering the underlying mechanism behind these changes in network integration and their potential role in MCI. Here, to find such a link, we investigated brain network integration derived from electroencephalography recordings during a visual motion discrimination task in older adults with MCI and those with normal cognition. We focused on a critical period just before stimulus presentation, which is known to be important for task performance. Our results revealed that during this period, MCI patients exhibited increased network integration compared to controls. Interestingly, increased integration was associated with worse task performance in the MCI group, suggesting it was not beneficial. No such association was found in the control group. Notably, this difference existed despite similar overall task performance between the groups. This suboptimal integration pattern during the cognitive task might reflect network de-differentiation due to disinhibition in MCI patients. Collectively, our study highlights the potential of analysing network integration during tasks to identify cognitive impairment and suggest a distinct role for network integration in MCI patients compared with healthy controls.

Task Type Effects on EFL Oral Production, Perception, and Proficiency

This study investigates the oral production and perceptions of 38 EFL learners using two task types: personal information and narrative picture tasks. It also examines whether proficiency level moderates the impact of task type on EFL speech. Results from two-way ANOVAs and thematic analysis revealed that the personal information task was less demanding for EFL learners than the narrative picture task. The data also indicated that EFL learners achieved higher levels of accuracy and syntactic complexity during the personal information task, diverging from theoretical underpinnings and existing research findings in this area. Furthermore, the data showed that while proficiency affected the accuracy and fluency of speech production, it did not moderate task performance, suggesting that EFL learners' performance on the two tasks remained consistent across different proficiency levels. These findings have significant implications for research, pedagogy, and assessment in EFL contexts.

Perceptions and Use of AI Chatbots among Students in Higher Education: A Scoping Review of Empirical Studies

With the recent arrival of publicly available AI chatbots like ChatGPT, Copilot, Gemini, and Claude follows a need for knowledge about how students in higher education perceive and use these tools, and what this might mean for their learning processes. This scoping review analyzes 24 empirical articles published between 1 January 2022 and 5 September 2023 on students’ perceptions and use of AI chatbots in higher education. The articles were reviewed using a five-stage scoping review methodology. The findings underscore a global research interest in how students engage with AI chatbots, which is especially pronounced in Asia. The studies span diverse disciplines, with a predominance in science, technology, engineering, and mathematics disciplines. The empirical findings reveal that students perceive AI chatbots as highly useful and motivating as personal task assistants and for getting immediate feedback and help with writing, coding, and academic tasks. However, students are concerned about the accuracy and reliability of the responses from the chatbots, as well as potential negative impacts on their learning processes, critical thinking, discipline, and creativity. The purpose-driven use of AI chatbots among students and their potentially positive influence on motivation and learning processes offer insights for educators and policymakers. Our research concludes that while positive attitudes, perceptions, and critical use prevail, addressing students’ concerns is crucial for responsible AI integration in higher education.

Technostress and time spent online. A cross-cultural comparison for teachers and students.

Research shows that ICT is beneficial for academics and students, aiding in overcoming distance barriers, streamlining administration, and improving teaching and learning processes. However, the negative impact of technology, particularly technostress, are garnering attention. In the context of the concerns about technostress among higher education institutions (HEI), the aim of the study is to analyze the technostress creators and inhibitors for university teachers and students in different European countries. The topical concept of digital well-being is seen as "a subjective individual experience of optimal balance between the benefits and drawbacks obtained from mobile connectivity, focusing on the personal perception of what amount of time spent using technology is optimal so that well-being is preserved". To explore specific aspects related to use of technology, two - parallel online surveys for academics (N = 446) and students (N = 660) from four European countries (Romania, Germany, Norway, and Finland) were conducted between November 2022 - January 2023. The surveys included the Technostress scale and the Technostress Inhibitors Scale, the Technology self-efficacy Scale, and a questionnaire focusing on socio-demographic aspects, work experience, academic field, dimensions related to the actual use of technology and participants perception on the optimal use of technology for work, learning or personal tasks, in terms of the period of day/week and amount of time spent. We also inquired about the social support given and received when using technology and the formal and informal rules, expectations, policies, punishments, and rewards regarding the use of technology. The findings suggest that the perceived optimal use of technology is significantly lower than the actual use for all the contexts. Overuse of technology was associated with technostress. Our results also showed that technology self-efficacy and social support from colleagues and teachers are negatively associated with technostress. Country differences regarding technostress and time spent online were also observed. Despite the needed caution in interpreting the results because of the unbalanced sample size across countries, the results could be used to develop research and support interventions within European countries to promote digital well-being, a better work-life balance with further positive effects on academic satisfaction and work/learning productivity.

Data-efficient comfort modeling: Active transfer learning for predicting personal thermal comfort using limited data

Personal comfort models are used to predict thermal comfort responses at the individual level rather than predicting the average thermal comfort responses for large populations. These models, data-driven in nature, need to be trained on large amounts of occupant comfort feedback and sensor data to achieve accurate predictions. However, collecting such data is often expensive and labor-intensive in reality. To address this, we proposed a data-efficient active transfer learning (ATL) framework to improve the performance of personal comfort models under limited data. To demonstrate the validity of this framework, we developed a base Convolutional Neural Network-Long Short-term Memory (CNNLSTM) model alongside two transfer learning models utilizing feature extraction (TL-CNNLSTM-FE) and fine-tuning (TL-CNNLSTM-FE) approaches, enhanced by a novel active learning strategy. Using these models, three comfort prediction tasks (i.e., thermal preference, thermal acceptability, and air movement preference) were performed by transferring the knowledge from the ASHRAE Global Thermal Comfort Database II to a limited dataset collected in the tropics. Empirical results indicate that the active transfer learning framework proposed was able to consistently outperform the base and transfer learning models using only less than 10% of the training data for all personal comfort tasks, highlighting the effectiveness of this strategy. The implications of this work are especially useful for the research community working on the practical applications of data-efficient machine learning approaches for personal thermal comfort predictions.

Development and validation of a health literacy scale for family caregivers of older people with chronic illness

BackgroundFamily caregivers (FCs) encounter a variety of health problems in older people with chronic illness, necessitating a certain level of health literacy to access, understand, appraise and apply health information and services. This study aimed to develop and validate a scale for measuring health literacy among FCs of older people with chronic illness.MethodsConcept mapping was first employed to develop a conceptual model of health literacy of FCs. Scale domains were derived from the conceptual model, and item generation was performed using deductive and inductive methods. Quantitative methods, including merging scale dimensions and items, expert reviews, cognitive interviews, and item reduction analysis, were used to refine the scale. Confirmatory factor analysis was employed to validate the scale’s structure. Concurrent validity, internal consistency, and test-retest reliability were also examined.ResultsA 20-dimension conceptual model was developed, and 60 items were generated for the scale. Expert review (content validity index > 0.85) and cognitive interview with FCs confirmed the relevance and clarity of the majority of the generated scale items. Confirmatory factor analysis with 451 FCs of older people with chronic illness supported a 5-factor structure (symptom management, daily personal care and household tasks, care coordination, communication and relationship with the care recipient, and self-care of caregivers) with 42 finalized scale items, including four levels of health literacy skills (accessing, understanding, appraising and applying health information). Concurrent validity with the European Health Literacy Questionnaire (HLS-EU-Q47) was satisfactory (r = 0.67, p < 0.01). The Cronbach’s α coefficient of the scale was 0.96, with subscales ranging from 0.84 to 0.91. The two-week test-retest reliability was 0.77 (p < 0.01).ConclusionThis study developed a conceptual model explaining the concept and factors of health literacy among FCs of older people with chronic illness that could provide the groundwork for future studies in developing relevant evidence-based interventions. A new Health Literacy Scale-Family Caregiver (HLS-FC) with satisfactory psychometric properties was developed in this study, which can be utilized to identify caregivers with insufficient health literacy and facilitate timely interventions by healthcare professionals.

Talking sh**! – are we doing enough?

This paper is a discursive piece on whether clinical psychologists and psychological practitioners are taking the time to consider bowel, urine and toileting issues sufficiently in their work. It draws on the disgust literature and the links to compassion in care giving. It seeks to explore experiences in direct therapy, in caregiver work, within teams and aims to encourage greater reflection on our relationships to these issues. The hope is to draw attention to the extraordinary work of those completing personal care tasks and the impact it has, with an attempt to position ourselves alongside people tolerating incontinence in order to grasp the psychological impact on self.

Task organization of the psychologist’s professional activity

The paper provides a theoretical analysis and reveals the constructive potential of the task-based organization of a psychologist’s professional activity in his/her systematic counseling work with a client, in which the latter goes through a four-stage cyclic-actual path of personal definition of a traumatic life problem as his/her own internal task: first, awareness of its subject and requirements, then its redefinition and redefinition, and finally its independent formulation as a purely personal one. In particular, it is proved that from the standpoint of the task approach, any activity can be interpreted as a series of continuously solvable tasks that can be faced by a person in the form of some action (a simple task); a situation that requires searching for connections between previously known information and unknown information, and thus obtaining some new knowledge (a thinking task), or a situation that, although it contains certain initial data, the person who solves it still does not know how to achieve the desired result (a problem task). It is from the standpoint of the latter definition that the personal request made by a client to a professional psychologist is considered. It is argued that it is the complex internal mechanism of transforming a problematic situation into a problematic task that is the “starting point” that separates a simple feeling of internal discomfort about the difficult life situation experienced by the client from his or her action activity, which, as a result of his or her own efforts, leads him or her to the desired answer. It has been determined that the central stage of this complex path is the process of a person’s internal acceptance of an external task as an internal (self) task, which can either be independently realized by the person at a certain time or recognized and approved with outside help (from a partner, loved one, friend, colleague, etc.). Therefore, it is the professional psychological support of such transformational changes that a psychologist must cope with when providing assistance to a client. The study found that in the process of such problematic dialogic interaction, which is the main channel of counseling or therapeutic practice, the person in need redefines and redefines the previously set task. In addition, the following scientific fact has been established: in order for an externally formed problem situation to become an internally accepted task for a person and eventually find its solution, it must go through four main stages: awareness (of the subject and requirements), its redefinition and redefinition up to the independent formulation of a new, purely personal task, which already contains more additional initial data (causes, means, probable consequences, etc.) and a set of possible options for an acceptable solution.

When large language models meet personalization: perspectives of challenges and opportunities

The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large language models has been dramatically improved, leading to human-like performances in understanding, language synthesizing, common-sense reasoning, etc. Such a major leap forward in general AI capacity will fundamentally change the pattern of how personalization is conducted. For one thing, it will reform the way of interaction between humans and personalization systems. Instead of being a passive medium of information filtering, like conventional recommender systems and search engines, large language models present the foundation for active user engagement. On top of such a new foundation, users’ requests can be proactively explored, and users’ required information can be delivered in a natural, interactable, and explainable way. For another thing, it will also considerably expand the scope of personalization, making it grow from the sole function of collecting personalized information to the compound function of providing personalized services. By leveraging large language models as a general-purpose interface, the personalization systems may compile user’s requests into plans, calls the functions of external tools (e.g., search engines, calculators, service APIs, etc.) to execute the plans, and integrate the tools’ outputs to complete the end-to-end personalization tasks. Today, large language models are still being rapidly developed, whereas the application in personalization is largely unexplored. Therefore, we consider it to be right the time to review the challenges in personalization and the opportunities to address them with large language models. In particular, we dedicate this perspective paper to the discussion of the following aspects: the development and challenges for the existing personalization system, the newly emerged capabilities of large language models, and the potential ways of making use of large language models for personalization.

Workplace Bullying in Higher Education: A Case Study of an International Student in an Australian Public University

Workplace bullying is a significant issue affecting employees across various sectors, including higher education. This case study examines the experiences of a Chinese female international student employed part-time at a public university in Sydney, Australia. The study documents the specific bullying behaviors she encountered, explores the underlying causes and contributing factors within the organizational and cultural context, and assesses the impact on her psychological well-being and job performance. The findings reveal that the bullying behaviors were multifaceted and persistent, including excessive workload, verbal abuse, and coercion into personal tasks. These behaviors had profound psychological, academic, and physical impacts on the victim, exacerbated by cultural dynamics and inadequate organizational responses. The study highlights the need for comprehensive anti-bullying policies, effective organizational interventions, and tailored support systems for international students. By addressing these issues, universities can create a safer and more supportive work environment for all employees and students. The study also suggests avenues for future research, including comparative studies across different cultural contexts, longitudinal studies, and the evaluation of intervention strategies.

Emotional Experiences During Completion of Daily Occupations in Individuals With Anxiety

The present study examined the frequency with which individuals with anxiety experienced positive and negative emotions during the completion of daily occupations. Participants were 89 individuals with a self-reported diagnosis of anxiety who completed the Emotional Experiences in Activities of Daily Living Scale (EEADLs) and State-Trait Inventory for Cognitive and Somatic Anxiety (STICSA). Individuals with high anxiety demonstrated more negative emotions but no differences in positive emotions during completion of personal care and household tasks with high physical and cognitive demands. Assessing emotions experienced during occupations can help inform recommendations to improve occupational balance and engagement in individuals with anxiety.

Analysis of trust factors for AI-assisted diagnosis in intelligent Healthcare: Personalized management strategies in chronic disease management

By utilizing various techniques to integrate the Unified Theory of Acceptance and Use of Technology (UTAUT) model with the variables of personal innovation and task complexity, an initial trust mechanism is established. Based on the inherent motivation and demand of doctors to use AI-assisted diagnosis systems, a doctor adoption model for AI-assisted diagnosis systems is established. Using chronic disease management as an example, personalized management strategies based on reinforcement learning technology are discussed for a virtual management environment that provides intervention recommendations according to the medical condition. It is shown in experiments that the fitting goodness-of-fit value of the model for willingness to use, which excludes initial trust-related factors, is only 0.557, while the fitting goodness-of-fit value of the proposed model in this paper is 0.673. This indicates that the model that includes initial trust factors can more accurately explain the logic of the behavior evolution of doctors adopting AI-assisted diagnosis systems.