共找到 20 条结果
Concept mapping (CM) is a widely used mixed method research approach for structuring and visualizing complex ideas across various fields, such as the health sciences. A critical bottleneck in the CM process is the idea synthesis phase, which remains labor-intensive, subjective, and consequently challenging to scale for large datasets. In this study, we propose IdeaDistiller, a semiautomated solution based on semantic clustering to optimize the idea synthesis step while maintaining methodological rigor through a human-in-the-loop approach. Using 9 health care-related datasets in English and Swedish, we systematically evaluated different embedding models, dimensionality reduction techniques, and clustering algorithms to identify robust and reproducible parameter settings for the proposed approach. IdeaDistiller clusters participant-generated ideas based on semantic similarity to identify similar ideas with different wording, suggests representative and unique ideas per cluster, and provides coherence scores and sorted outputs to aid manual validation. Our findings suggest that IdeaDistiller may substantially reduce the manual effort involved in idea synthesis while preserving quality and transparency. However, human expertise remains indispensable for validating and refining cluster outputs. Integrating semiautomated methods into the CM workflow offers significant potential for improving the efficiency, scalability, and rigor of the CM process. Building on our work will enable the exploration of larger multilingual datasets and integration into future CM studies.
Artificial intelligence (AI) is increasingly applied in colorectal and anorectal surgery, particularly for complex conditions such as anal fistula (AF). Conventional diagnostic and therapeutic approaches remain limited by intricate anatomy, high recurrence risk, and the need to preserve continence. This narrative review, evaluates the role of AI in AF and related anorectal disorders, with evidence mapped to the IDEAL (idea, development, exploration, assessment, and long-term follow-up) framework (stages 1-4, with stage 2 subdivided into 2a and 2b). Relevant literature was identified through targeted searches of PubMed, Embase, and Scopus. Studies investigating AI applications in AF or related anorectal conditions, including imaging, surgical planning, predictive modeling, and functional assessment, were included. Evidence was categorized according to IDEAL stages, ranging from proof-of-concept to long-term quality assurance. AI demonstrates potential across 4 key domains: (1) preoperative imaging (stages 1-2b); (2) intraoperative planning and assistance (stages 1-2a); (3) predictive modeling (stages 2a-2b); and (4) broader anorectal applications, including anorectal manometry and the EndoFLIP (endoluminal functional lumen imaging probe) procedure (stages 1-2b). Feasibility studies report high diagnostic performance, particularly for magnetic resonance imaging and computed tomography-based deep learning models; however, these findings are constrained by small sample sizes, limited external validation, and challenges related to workflow integration. Overall, AI has the potential to enhance diagnostic accuracy, surgical planning, and functional assessment in AF and related disorders. However, most studies remain within early IDEAL stages (1-2b), highlighting the need for multicenter validation, cost-effectiveness analyses, and robust ethical frameworks before widespread clinical implementation.
Clinical research involves complex, fragmented workflows across the clinical trial life cycle. We present a multi-agent system designed to support researchers across multiple stages of this life cycle, from trial preparation to translation. The proposed system uses a coordinated multi-agent architecture together with multiple large language models (LLMs) to provide task-dependent support across clinical research workflows. This work introduces a structured agentic AI approach and provides a foundation to manage the growing complexity of clinical trial workflows.
Background The Older Women's Health Strategy for England highlighted the systemic under-representation of older women in healthcare. Over half of women over 80 are estimated to have osteoporosis, contributing to 180,000 fractures annually in the UK, with substantial personal and economic costs, despite clinically effective treatments and national guidelines being available. Aim To use insights from the experiences of older women and primary healthcare professionals to develop strategies to improve osteoporosis care. Design/Setting A community-based study in England, UK. Method Interviews with 30 community-dwelling older women (aged 70+) diagnosed with osteoporosis, and 31 healthcare professionals including GPs, physiotherapists, pharmacists, practice nurses, a healthcare assistant, and a community matron. We reviewed findings iteratively with our co-production group using a Constructivist Grounded Theory approach. Results Healthcare professionals acknowledged osteoporosis as clinically important but described limited knowledge and understanding. However, older women assumed expertise and proactive engagement from clinicians. Older women normalised symptoms as part of ageing frequently prioritising other co-morbidities. Most were unclear about their diagnosis, prognosis, or treatment plans. Self-management was expected but inadequately supported. There was little routine engagement with the wider primary care team. Digital communication further limited older women's engagement/re-engagement. Conclusion Osteoporosis remains poorly understood and inadequately managed in older women who face barriers, including multimorbidity, digital exclusion, and low self-efficacy. Many older women accept care gaps due to limited awareness and lack of meaningful interaction with healthcare professionals. Improved care navigation and greater involvement of the wider primary care team could enhance engagement and support better self-management.
Across the world, many national sport systems make extensive strategic investments in talent promotion programs (TPPs). The most common TPPs include youth sport academies and sport federations' junior squads. The central idea of TPPs is (1) to select the most promising talents at young ages (around puberty or younger) and (2) to involve them in a long-term continuous nurturing process to facilitate their performance development, eventually leading to increased senior peak performance. This central idea implies that the population of TPP participants is highly stable across age categories. On the other hand, TPPs sometimes replace deselected athletes with new 'side-entry' athletes (athletes who enter a TPP after its initial age category). Hence, there is athlete turnover-fluctuation in the TPP population through exits of participants and entries of new athletes. This implies that the TPP population is unstable across age categories. The magnitude of annual athlete turnover is thus indicative of the operating principle of TPPs and whether it corresponds to their central idea. This meta-analysis aimed to provide robust and generalizable evidence on the magnitude of annual athlete turnover in TPPs. It also investigated whether athlete turnover varies between youth sport academies vs federations' junior squads and across ages and sexes. A systematic literature search was conducted in March 2025 in Web of Science, PubMed, APA PsycINFO, APA PsycARTICLES, and Google Scholar, complemented by snowball search. We searched for original studies that reported annual athlete turnover within TPPs or data needed to compute annual athlete turnover. The search yielded 37 samples, published 2010-25, including 44,287 athletes from all Olympic sports and 42 countries. For each TPP sample and each season-to-season transition, annual athlete turnover was calculated as (number of entries + number of exits) / 2 / total number of current athletes. The mean annual athlete turnover within TPPs is 36.3%. It is slightly higher in federations' junior squads than youth sport academies but does not differ across ages or sexes. Most talent selection decisions are revised within two years and, accordingly, more than half of the TPP population is exchanged every two years. Unlike their original idea, the operating principle of TPPs is characterized by frequent selection, deselection, and replacement of youth athletes, resulting in sizeable athlete turnover. We discuss implications regarding inaccurate talent identification and inefficient TPP nurture. The operating principle of TPPs can be described as follows: TPPs try out many youth athletes and expand that number through sizeable athlete turnover. Most talent-identified youth athletes are deselected again soon and replaced with others who are then tried out.
Norm, the formal theoretical linguist, and Claudette, the computational language scientist, have a lovely time discussing whether modern language models can inform important questions in the language sciences. Just as they are about to part ways until they meet again, 25 of their closest friends show up - from linguistics, neuroscience, cognitive science, psychology, philosophy, and computer science. We use this discussion to highlight what we see as some common underlying issues: the String Statistics Strawman (the mistaken idea that LMs can't be linguistically competent or interesting because they, like their Markov model predecessors, are statistical models that learn from strings) and the As Good As It Gets Assumption (the idea that LM research as it stands in 2026 is the limit of what it can tell us about linguistics). We clarify the role of LM-based work for scientific insights into human language and advocate for a more expansive research program for the language sciences in the AI age, one that takes on the commentators' concerns in order to produce a better and more robust science of both human language and of LMs.
Kinetoplastids are one of two groups of euglenozoans that have compartmentalized the enzymes of metabolic pathways, including glycolysis, into a peroxisome-derived organelle called a glycosome. Several ideas have emerged regarding the evolutionary pressures that drove and are maintaining compartmentalization of these typically cytosolic enzymes. For example, their compartmentalization might result in superior efficiency in remodeling enzyme relative abundances in response to changing environmental conditions. We wished to empirically test the merits of this explanation. We began with the presumption that the abundances of glycosome-compartmentalized enzymes are broadly affected by changes in extracellular environment, similar to how they vary between life stages of the model kinetoplastid Trypanosoma brucei. Our hypothesis was that abundances of glycosome-localized enzymes in multiple kinetoplastids would alter as a result of their extracellular environment. Six different kinetoplastid species, including both dixenous and monoxenous parasites, were evaluated in culture for their response to extracellular nutrient and oxygen availability in terms of their expression of glycosome-localized enzymes. We analyzed their growth rates and utilized immunoblotting to measure abundances of glycosome-localized or partially-localized enzymes and cytosolic enolase in the different culture conditions. We found the tested enzyme abundances to be largely consistent. Oxygen availability and slow removal of nutrients from the extracellular environment resulted in only minor changes in enzyme abundance. Only abrupt replenishment of culture nutrients resulted in enzyme abundance responses - typically a modest decrease in both cytosolic enolase and the glycosome-localized enzymes. Results suggest that there is little evidence that parasites respond to external nutrient or oxygen availability through alterations in relevant enzyme abundances, at least absent life cycle transitions. Thus, our study does not provide support for the idea that efficient and coordinated remodeling of ratios of metabolic enzymes was an evolutionary driver of metabolic enzymes' compartmentalization in the glycosome. Further, it suggests that it may be relevant to test whether posttranslational modifications and/or changes to enzyme localization are mechanisms trypanosome utilize to adjust specific metabolic activity when needed.
As Bard, Keller, and Leavens show, attachment theory does not account for the diversity of child-rearing practices around the world. However, the entrenched commitment to Bowlby's idea that the attachment system is a biological adaptation prevents attachment researchers from fully understanding the import of such diversity. I argue that this idea relies on a static and flawed view of evolution.
Despite significant organizational investment in innovation programs, hierarchical structures and high power-distance cultures systematically constrain employee creative expression in ways that dominant innovation theories have not adequately theorized. Existing frameworks, rooted predominantly in Western, low-hierarchy contexts, treat environmental components as interchangeable and additive - an assumption this study interrogates. Drawing on Amabile's Componential Theory as both an analytical lens and a target for theoretical extension, this investigation employs a dual-source qualitative design combining 204 internally generated employee comments with 29 semi-structured interviews conducted across three large organizations in Saudi Arabia's hospitality and tourism sector. Reflexive thematic analysis was applied to examine how employees perceive, interpret, and navigate the organizational conditions shaping their innovative behavior. Analysis produced five interconnected themes - organizational culture barriers, leadership dynamics and power structures, recognition and reward system deficits, structural and process impediments, and individual and collaborative factors - revealing a landscape in which creative capacity is widely distributed but systematically blocked from reaching implementation. Three theoretical extensions to Componential Theory emerge from these findings. Psychological safety appears to function not merely as one facilitating factor among many, but as a preconditional requirement whose absence substantially constrains the contribution of all other environmental factors in hierarchical, high-power-distance contexts. Leadership influence appears amplified beyond its theorized role through three structural and cultural mechanisms. Environmental components exhibit phase-specific effects that systematically widen the gap between idea generation and implementation. These findings challenge the additive logic embedded in Componential Theory, proposing instead a configurational model in which certain environmental conditions may be more foundational than others, rather than merely interchangeable. Practically, organizations operating within hierarchical structures should reconceptualize psychological safety as a foundational infrastructure investment rather than a cultural enhancement, redesign leadership accountability frameworks to address innovation bottlenecks rather than individual encouragement, and architect dual-track innovation systems that formally separate and protect ideation from authority-dependent implementation processes. These propositions are advanced as theoretically informed interpretations grounded in abductive reasoning and intended to invite future empirical testing.
Academic publishing in surgery has undergone profound change during the past several decades. Expansion of medical schools, residency programs, international academic centers, and digital publishing platforms has produced unprecedented growth in manuscript submissions and intensified competition for professional attention. Journals are judged both by readership, as measured by article downloads, and by scientific influence, as reflected in scholarly citation. At The American Surgeon, these changes prompted development of editorial frameworks designed to identify contributions most likely to matter to practicing surgeons and subsequent investigators. Many manuscripts contained observations whose significance was underrecognized by their authors. This observation led to the Hidden Publishable Idea (HPI), a framework for identifying contributions most useful to readers. Once identified, the HPI often revealed methodological limitations that imposed an evidentiary ceiling, preventing definitive conclusions while suggesting new hypotheses for future investigation. Analysis of downloads and citations suggested that readership and scholarly adoption are related but distinct outcomes. This observation led to development of the CitDL matrix, a two-by-two framework based on high and low download and citation performance. The editorial objective was not simply manuscript acceptance, but identification and development of contributions that could move manuscripts toward greater readership, greater scholarly engagement, or both. These concepts represent adaptive responses to the contemporary challenge of helping useful ideas find their audience and contribute to the advancement of surgical practice and science.
Eating disorders are a global health concern, yet research in this field has historically been underfunded and sometimes perceived as "niche". To attempt to address these challenges, the international charity Consortium for Research in Eating Disorders (CoRe-ED) was launched in September 2024. CoRe-ED aims to promote innovations in eating disorders research by empowering all voices and supporting the development of new therapies. The present study examined the characteristics of individuals who joined CoRe-ED over the first ~ 15 months, their engagement with consortium initiatives and their expected benefits and experiences. Between 25 September 2024 and 31 December 2025, CoRe-ED registrants completed an online registration form and consented to the use of deidentified, aggregated data for research. Data were analysed for registrant characteristics, including primary country of residence and role(s) (e.g., researcher, health professional, lived experience), and for perceived expectations and experiences, using inductive thematic analysis. Survey feedback from ten CoRe-ED events, engagement with collaborative CoRe-ED initiatives, and an overarching survey capturing overall registrant experiences were also analysed. A total of 960 individuals from 37 countries across five continents registered with CoRe-ED, representing researchers, health professionals, individuals with lived experience, advocates, not-for-profit representatives and industry professionals. Registrants' expectations included networking and community building, research contribution and collaboration, learning and professional development, advocacy, facilitation of innovation, integration of lived experience into research, global collaboration and mentorship. CoRe-ED also implemented a structured "Next Big Research Idea" initiative, which involved 18 internationally distributed multidisciplinary teams across 20 countries in collaborative research proposal development. Event-specific and overall feedback indicated high satisfaction with CoRe-ED activities, particularly valuing the diversity of presenters, global perspectives, inclusive environment and opportunities to learn and connect. Over the first ~ 15 months, CoRe-ED engaged a diverse, international registrant group and developed activities consistent with early registrant expectations. The consortium implemented initiatives intended to support cross-disciplinary research collaboration, knowledge exchange and innovation, while expanding international representation. Future research should examine longer-term experiences, including impacts on research outputs, mentorship, co-design and policy translation, to better understand how the consortium evolves in response to the needs of its international community. Eating disorders are a global health concern, but research and support in this area are limited. To attempt to address this, the international charity Consortium for Research in Eating Disorders (CoRe-ED) was launched in September 2024 to bring together people from different countries, professions and experiences. Over the first ~ 15 months, 960 individuals from 37 countries joined, including researchers, health professionals, people with lived experience, advocates, not-for-profit workers and industry representatives. Registrants reported wanting to build networks, contribute to research, access learning and professional development, engage in advocacy, support innovation, integrate lived experience into research, participate in global collaborations and receive mentorship. CoRe-ED also launched a “Next Big Research Idea” initiative, which brought together 18 multidisciplinary teams across 20 countries to develop collaborative eating disorders research proposals. Feedback on events and the overall consortium was very positive, with registrants highlighting the diversity of presenters, inclusive environment, global perspectives and learning opportunities. These findings potentially suggest CoRe-ED engaged a diverse, international group and implemented initiatives aligned with registrants’ expectations. Future research should examine longer-term experiences to better understand how the consortium responds to the needs of its international community.
Testing hypotheses of phenotypic modularity involves assessing whether groups of traits covary more strongly with each other than with parts outside the group. Structural Equation Modelling (SEM) is a flexible statistical framework for interrogating complex relationships between sets of variables, making it ideally suited to studies of hierarchical modularity and integration. However, quantifying the modular organization of high-dimensional traits using SEM in a phylogenic context has only recently become possible through new methodological advances. Here, we applied SEM to investigate patterns and correlates of phenotypic modularity in the skull and brain of birds. Birds independently evolved relatively large brains multiple times, as well as a wide range of different skull and brain morphologies. While some have proposed the bird skull is composed of several functional or developmental modules, others have suggested the skull is highly integrated, with share allometric scaling structuring trait correlations. The data best supported a model in which brain shape is influenced by changes in shape of the neurocranium as well as a 'jaw' module consisting of the rostrum shape and jaw musculature. Rostrum shape itself does not strongly covary with other aspects of the skull and brain, suggesting decoupling of beak morphology from the rest of the avian cranium. All variables, with the exception of rostrum shape, are strongly influenced by size, supporting the idea that allometry is a major influence on craniofacial integration in birds. These results provide new insights into likely drivers shaping the evolution of the skull in birds and highlight the usefulness of phyloSEM testing hypotheses of evolutionary modularity and integration.
The synthetic ammonia (NH3) process based on the photoelectrochemical nitrate reduction reaction (PEC NIRR) represents a green pathway, but precisely controlling the interfacial reactions to suppress hydrogen evolution and promote nitrate reduction is a key challenge. In this study, a CuBi2O4/CuMOF for PEC NIRR has been successfully constructed. Owing to its intrinsic defect structure, CuMOF exhibits the excellent hydrophilicity, which effectively promotes the adsorption and cleavage of water molecules. Furthermore, the generation of active hydrogen radicals (H*) improves the catalytic reaction kinetics. CuBi2O4/CuMOF achieves an NH3 yield of 19.76 μg h-1 cm-2, which is approximately 3.12 times that of CuBi2O4, and the NH3 selectivity of CuBi2O4/CuMOF is 2.08 times than that of CuBi2O4. In summary, this study clarifies the key role of defect-induced hydrophilicity of CuMOF in the generation of H*, which provides a new idea for designing the efficient PEC NIRR systems.
Up to 75% of children treated for severe acute malnutrition (SAM) relapse within six months of recovery, yet evidence on post-discharge interventions remains limited. We conducted a formative assessment to understand how small-quantity lipid-based nutrient supplements (SQ-LNS) could be integrated in post-discharge care to prevent relapse. This study aimed to inform whether and how a program integrating SQ-LNS into post-discharge monitoring could be implemented in Mali. Specifically, we aimed to: 1) identify barriers and enablers to post-discharge monitoring, 2) develop one or more post-discharge models based on recommendations, 3) understand the feasibility of these model(s), 4) describe acceptability of the model(s) and product, and 5) propose a final model to be piloted at larger scale. This formative study comprised two iterative phases conducted between September 2024 and May 2025. In exploratory Phase One, we conducted semi-structured interviews with 12 caregivers of children with SAM and eight treatment providers, in triangulation with 13 focus groups among caregivers, health care workers (HCW's), and supervisors. Themes included current practices, anticipated challenges, and service delivery preferences. Findings informed a confirmatory Phase Two involving four direct observations of three delivery models implemented at four sites and 13 interviews with similar participants. Textual data were coded and thematically analyzed using Dedoose software. Although national guidelines recommend routine post-discharge monitoring for SAM children, it was rarely practiced due to limited awareness among HCW's. Both caregivers and HCW's supported the idea of post-SAM monitoring, preferring on-site over home visits for feasibility. Caregivers valued growth monitoring, interacting with HCW's, and nutritional supplementation. While unfamiliar with SQ-LNS, caregivers viewed it positively based on their experience with therapeutic foods. Three delivery models were tested: (1) weekly visits for one month transitioning to fortnightly thereafter, (2) fortnightly visits and program days, and (3) fortnightly visits for caregivers and weekly program days at the health site. Model three proved most feasible for caregivers and providers. This formative research informed a program design that aligns with caregiver preferences and health system capacity, requiring minimal external support. Fortnightly post-discharge monitoring paired with SQ-LNS supplementation at treatment sites is recommended.
Existing behavioral and neural evidence suggests that people rely on mental simulation when predicting others' decisions. If true, making predictions with a biased decision system should result in biased predictions. We tested this idea directly by biasing participants' risk valuation through adaptation to either high- or low-probability contexts and then asking them to predict the choices of three distinct agents (risk-average, risk-averse, risk-seeking). The adaptation manipulation biased participants' predictions for the risk-average and risk-averse agents, suggesting simulation with their own (biased) decision process when predicting these agents. In contrast, there was no adaptation effect for the risk-seeking agent. Similarly, participants' own risk tendencies correlated with predictions for the risk-average and risk-averse, but not the risk-seeking agent. Drift diffusion modeling analyses showed that this adaptation bias was the result of changes in participants' risk valuation parameter. Overall, these findings support simulation-based prediction while suggesting a modulating role of the other person's characteristics.
This study used a descriptive phenomenological design to explore nurse educators' perceptions of leadership support and examine how such support influences their job satisfaction and intent to leave. Virtual interviews were conducted with 14 nurse educators representing seven US states. Findings indicated that leadership support plays a meaningful role in shaping both job satisfaction and intent to leave for nurse educators. The results align with existing literature and reinforce the idea that leadership support is not merely beneficial but essential for retaining qualified faculty in nursing education. Therefore, leadership support within nursing education programs warrants further investigation.
Due to the widespread use of generative artificial intelligence (GenAI) in undergraduate medical education (UGME), this study aimed to develop a set of consensus-based principles for the responsible and ethical use of GenAI, established by medical students and faculty and further validated by international medical and artificial intelligence (AI) experts. A four-round modified Delphi process, an in-person idea-generation round, two structured rating rounds, and an external expert validation round were conducted between May 2025 and February 2026. The panel included medical students (n = 13) and medical professors (n = 2) in the first three rounds, and international experts in medical education and AI (n = 9) in the final round. In Round 1, an open-ended question yielded 37 potential principles. In Rounds 2 and 3, these items were rated using a 7-point Likert scale (1 = Strongly Disagree, 7 = Strongly Agree) with space for written comments; median scores and interquartile ranges were used to assess the strength of agreement against predefined decision rules, and the principles were retained, reworded, consolidated, or excluded accordingly. In Round 4, the near-final principles were validated by 9 international experts in AI medical education, AI ethics, AI technology education, or senior medical educators involved with AI curricula. The process identified 14 consensus-based principles for the use of GenAI in UGME. Given the swift adoption of GenAI in medical education, students need explicit guidance for ethical and responsible use. We established an internationally informed, expert-validated set of principles for medical students' use of GenAI through a student-partner Delphi study with external validation by a multinational expert panel. Institutions developing GenAI guidelines may adapt this framework for implementation in local educational contexts.
Reinforcement learning has shown strong promise for strengthening the reasoning ability of large language models (LLMs), but sparse, delayed rewards over long chains make token-level credit assignment a central challenge. Actor-critic methods like PPO provide token-level credit but require training a value network alongside the policy, which introduces complexity and can encourage overfitting. Critic-free alternatives such as GRPO avoid this burden but rely on sequence-level outcomes, distributing a single reward uniformly across tokens and ignoring structural differences between responses. We propose Prefix-to-Tree (P2T), which organizes the sampled responses of a prompt into a prefix tree and computes nonparametric prefix values by aggregating descendant outcomes. Building on this idea, we develop TEMPO (Tree-Estimated Mean Prefix Value for Policy Optimization), a critic-free algorithm that enriches GRPO with branch-aware temporal-difference (TD) corrections. Across Qwen3-1.7B and Qwen3-4B, TEMPO consistently improves both convergence and final performance over PPO and GRPO on in-distribution benchmarks (MATH, MedQA) and out-of-distribution settings (GSM-HARD, AMC23, MedMCQA, MMLU-Medical), achieving higher validation accuracy within comparable wall-clock time.
Recent events involving war and terrorism have rekindled the debate about the meaning of such concepts and how people define those actions. Previous research from the perspective of social psychology has suggested that the main criterion for distinguishing acts of war from terrorist actions is the differentiation between military and civilian targets. However, a secondary criterion related to the ethnic-cultural identity of the aggressor has also been observed. This study aims to examine whether people still rely primarily on the distinction between military and civilian targets, or whether biased judgments based on the ethnic-cultural identity of the aggressor continue to influence their assessments. Specifically, 297 Italian citizens evaluated whether some actions perpetrated by four groups (i.e. Arab, Palestinian, Israeli, and US) were closer to their idea of war or terrorism. Results show that both criteria are present, although participants do not seem to perceive major differences between the different forms of aggression presented, in terms of war and terrorism, at least not as strongly as in research conducted a decade ago. However, similar to these prior research studies, some actors, particularly Arabs and Palestinians, are considered more terroristic, and this is especially true of those with high ethnocentrism scores.
Fatigue and sleep disturbances are highly prevalent in neurodegenerative diseases (NDDs) and immune-mediated inflammatory diseases (IMIDs). Conventional patient-reported outcomes (PROs) are subjective and prone to recall bias; Digital health technologies and wearable sleep trackers offer objective, continuous monitoring of sleep and physiology at home. This study evaluated the feasibility of using consumer- and research- grade sleep trackers to predict next-day physical and mental fatigue and daytime sleepiness in individuals with NDDs and IMIDs as an exploratory analysis, and examined whether machine-learning models could identify preliminary sleep features to inform future fatigue monitoring research in chronic disease populations. The IDEA-FAST feasibility study enrolled 134 participants (42 healthy adults, 39 NDD, 53 IMID) across four European centres. Over 3,062 nights, participants wore three sleep trackers (BedSensor, ZKONE, DREEM 2) and completed daily fatigue and sleepiness PROs at home. A polysomnography sub-study ( n = 28 ) validated tracker performance. Machine learning models using physiological and sleep-architecture features were evaluated with leave-one-subject-out cross-validation. Sleep trackers showed moderate PSG agreement. Models demonstrated preliminary discriminative capacity for next-day physical fatigue in healthy adults (AUC = 0.75), driven mainly by respiratory rate and REM sleep duration. In NDD, physical fatigue AUC reached 0.62 under enriched training, with REM latency and deep sleep as key features. Mental fatigue prediction reached AUC = 0.66 in healthy adults; daytime sleepiness AUC = 0.66 in NDD. Findings should be interpreted as exploratory, as outcome binarisation using a global threshold may conflate between-person disease-group differences with within-person symptom variation. Wearable sleep trackers show feasibility for objective home-based sleep monitoring, with preliminary evidence supporting sleep physiology as a candidate predictor of next-day physical fatigue in healthy adults. Predictive performance in chronic disease cohorts remains limited, underscoring the need for larger, multimodal studies to establish disease-specific digital fatigue endpoints.