The integration of high-dimensional and multi-modal biomarker data remains a central challenge in precision medicine, hindered by noise, weak individual signals, and heterogeneous data structures. We propose AdaMixNet, an adaptive mixed-effects deep learning framework that unifies nonlinear fixed-effects modeling with kernel-based random-effects estimation to robustly and accurately predict complex disease outcomes. By leveraging feature screening to distinguish sparse, high-impact biomarkers from dense, low-signal features, AdaMixNet captures both strong and subtle biological effects across diverse data modalities. Through comprehensive simulations and applications to two large-scale real cohorts, i.e., METABRIC (breast cancer) and ADNI (Alzheimer’s disease), AdaMixNet shows robust overall performance, often outperforming strong machine-learning and statistical baselines in simulation and achieving competitive or best results for several real-data outcomes while maintaining good performance across sample sizes from 1000 to 20,000. AdaMixNet offers a generalizable and interpretable framework for integrating high-dimensional and multi-modal omics profiles with low-dimensional clinical data, accelerating the translation of molecular insights into clinical applications. Modern medicine collects large amounts of biological data, such as gene-expression profiles, genetic variants, and medical test results. However, combining these different types of data to better predict disease remains difficult. The data are often noisy, and important signals can be weak or hidden among many measurements. In this study, we developed a method called AdaMixNet. It is a computer-based tool that learns from both strong and subtle biological signals while also using standard clinical information. This helps improve the accuracy of predicting disease outcomes. We tested AdaMixNet using simulated data and two large real-world studies of breast cancer and Alzheimer’s disease. Our method reduced prediction errors compared to existing approaches. This work may help researchers and doctors better use complex biological data to support more personalized healthcare decisions in the future. Dai et al. develop AdaMixNet, an adaptive mixed-effects deep learning framework that integrates high-dimensional omics data with clinical variables for disease outcome prediction. Across simulations and the METABRIC and ADNI cohorts, AdaMixNet reduces prediction error by up to 25% and outperforms existing approaches.

Lung transplantation programs must decide when bilateral lung transplantation (BLT) offers meaningful functional benefit over single lung transplantation (SLT). Because donor and recipient characteristics jointly shape outcomes, the BLT-SLT contrast may differ across patients. However, analyzing observational registries poses a statistical challenge: apparent subgroup differences can be artifacts of complex confounding, while true heterogeneity can be missed or poorly quantified. Using a large national registry, we investigate whether the BLT effect varies across recipients and identify clinically relevant profiles of benefit using post-transplant lung function measured by forced expiratory volume in 1 second (FEV1). We develop deepHTL, a framework that tests for treatment effect heterogeneity and estimates how the BLT-SLT effect varies with patient features. In extensive simulations designed to resemble registry-like confounding, deepHTL controls false positives for detecting heterogeneity and yields more accurate individualized effect estimates than common machine learning methods. In the lung transplant cohort, we find strong evidence of heterogeneity in the BLT-SLT effect on FEV1: younger, lower risk recipients with better baseline status show the largest FEV1 gains from BLT, whereas older, higher risk candidates exhibit diminished marginal benefit. These findings provide statistically grounded guidance for patient selection and allocation of scarce donor organs.

INTRODUCTION:Disasters, including the recent COVID-19 pandemic, have disproportionately impacted nursing homes (NHs). NH residents experienced higher mortality during the pandemic, but not all NH were affected equally. Appalachia has a history of reduced health compared to the general United States. Therefore, this study is focused on NHs in Appalachia during the COVID-19 pandemic. PURPOSE:This study aimed to investigate how the neighborhood and NH characteristics are associated with mortality in Appalachian NHs during the COVID-19 pandemic. METHODS:Using publicly available datasets, including NH, patient, and county-level characteristics, the authors' investigated how the these factors impacted COVID-19 death, COVID-19 death rate, and total NH deaths by adopting negative binomial regression outcomes and multiple linear regression models. RESULTS:A total of 1259 NHs in Appalachia were included in the analysis. Deaths from COVID-19 were positively associated with the number of NH beds, share of White residents, and resident age. Centers for Medicare & Medicaid Services 5-star quality rating was negatively associated with COVID-19 deaths. On the other hand, although number of beds, acuity index, share of White residents, average age, and share of White residents in the community were positively associated with total deaths, lower county education levels and county income were negatively associated with total deaths. DISCUSSION AND IMPLICATIONS:NH and county characteristics associated with NH deaths varied from prior literature that included the general United States. Policymakers and NH leaders responsible for NHs in Appalachia should be sensitive to regional differences when making decisions and resource allocations.

Abstract Introduction: This qualitative descriptive study explored the communal processes (i.e., dyadic communication and collaborative action) through which prostate cancer (PCa) survivors and their partners shaped each other’s diets. Methods: Dyads of PCa survivors and their partners (n=18 dyads, 36 individuals) were recruited through clinics and Research For Me, an online registry of active clinical studies. A 50-minute dyadic interview and two optional 5-minute individual interviews were conducted with each dyad. Interview guides were developed using the Communal Coping Model. Interviews were audio recorded, transcribed verbatim, and de-identified. Thematic analysis was applied to each transcript by two investigators independently. Results: Most enrolled couples were married (n=17) and heterosexual (n=17). Fifteen survivors were diagnosed with PCa within 5 years, and thirteen received at least one type of treatment. Eight themes emerged; six fell within the communication and action constructs of the Communal Coping Model. Themes for communication included: (1) established communication patterns and (2) couple dialogues about PCa and diet beliefs. Couples who have established effective communication patterns are better equipped to engage in dialogues about diet and health, which facilitates healthy dietary changes. Themes for action included: (1) information seeking, (2) partner support, (3) cooking and shopping, and (4) strategies for sustaining changes. Couples collaborated on these actions, delegated them to one partner, or acted individually. Couples who did not engage in collaborative actions reported greater conflict over dietary choices and a heavier burden of managing healthy diets. Two additional themes emerged: (1) PCa-induced dietary changes and (2) variations in dietary change timing. Conclusions: Through effective communication, couples can align their awareness of healthy diets and PCa, which facilitates joint dietary changes. Collaborative actions (e.g., shared cooking and shopping), rather than individual efforts, ease the burden of dietary changes. Overall, this study highlights the need for interventions that foster communication and collaborative action to help couples adopt and maintain healthy diets throughout the PCa trajectory. Citation Format: Jingle Xu, Lisa H. Ranzinger, Stephanie Sperry, Hung-jui Tan, Lixin Song, Jennifer Leeman, Baiming Zou, Rachel Hirschey. The communal process through which prostate cancer survivors and their partners affect each other's diets: A qualitative descriptive study [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(8_Suppl):Abstract nr LB131.

Perturbational transcriptomics links therapeutic compounds to cellular mechanisms and provides a powerful framework for drug discovery, but experimentally profiling transcriptional responses across diverse cell states, doses and durations is costly and often infeasible. Here we present DEPICT (Drug rEsponse Prediction in transCriptomics with Transformers), a deep learning framework that predicts condition-matched drug-induced transcriptional responses from baseline gene expression, perturbation settings and complementary drug representations. Using the LINCS L1000 dataset, DEPICT generalized to unseen drugs and cell types and outperformed five baseline strategies and two recent deep learning models. In the most challenging unseen-cell evaluation, DEPICT was the only model to surpass all baselines, improving differential-expression prediction accuracy and reducing perturbed-expression prediction error by 30.3% and 36.8%, respectively, relative to the next-best deep model. In a non-small cell lung cancer (NSCLC) case study, DEPICT-enabled virtual screening prioritized compounds predicted to reverse disease-associated transcriptional signatures. Notably, 13 of the top 20 prioritized compounds had either previously entered NSCLC-related clinical trials or been validated in NSCLC studies, supporting the translational relevance of the predicted perturbational profiles. DEPICT further enabled condition-matched drug synergy prediction and mechanistic exploration when experimentally matched profiles were unavailable. Together, these results show that accurate, condition-matched in silico perturbation profiling can scale transcriptomics-driven hypothesis generation for drug repurposing and combination discovery.

A significant proportion of intensive care unit (ICU) patients undergo surgical procedures, and some may develop postoperative infections. Accurately predicting postoperative infection risk and identifying key contributing factors is crucial for improving postoperative management and understanding infection mechanisms. However, this task is challenging due to the complex interplay of multiple risk factors. While machine learning models can model these intricate associations to predict postoperative infection risk, their lack of interpretability - failing to uncover each factor's impact-hinders their adoption in clinical settings. To address this difficulty, we introduced an interpretable deep neural network (DNN) model that integrates a permutation feature importance test (PermFIT). PermFIT rigorously evaluates the impact of each feature on postoperative infection risk through a rigorous statistical inference. By using only the identified important features as inputs, the DNN's predictive performance can be further enhanced. We conducted an extensive study using electronic health records (EHRs) from the Medical Information Mart for Intensive Care (MIMIC-III), a large-scale ICU EHR database. Under the PermFIT framework, our DNN model effectively identifies significant factors associated with postoperative infections while delivering the most accurate postoperative infection risk predictions. These findings highlight the clinical utility of our proposed DNN framework in managing postoperative care for ICU surgical patients, ultimately improving their health outcomes.

Background/Objectives: Head and neck cancer (HNC) represents the seventh most common cancer diagnosis globally, yet current treatments, including surgery, radiation, and immunotherapy, have shown limited improvement in outcomes. Drug repurposing offers a cost-effective strategy to identify new therapeutic options by leveraging existing medications with known safety profiles. Within this study, we developed the GARD pipeline (Genomic Alteration-based Repurposing for Drugs), designed to uncover repurposing candidates for HNC using genomic and network-based approaches. Methods: GARD integrates multi-omics data from The Cancer Genome Atlas (TCGA), including copy number variation (CNV) and somatic mutations (SOM). The cohort was stratified by human papillomavirus (HPV) status. Risk-associated genes were identified and then expanded via high-confidence protein-protein interaction (PPI) networks. Top candidate genes were filtered through comprehensive analysis of publicly available literature data in PubMed using LLMs to validate the relationship between the identified genes and HNC. The top risk genes and their network-expanded neighbors were mapped against DrugBank, and through statistical significance testing and literature validation, established significant drug-gene associations. Results: Significant genes associated with HNC, inferred by genomics alteration, were identified across HPV-positive and HPV-negative subgroups, such as PIK3CA, SOX2, TP53, EIF4G1, TLR7, CLDN1, PRKCI, and EPHA2. Further expansion through the PPI network identified other targetable genes such as EGFR, ERBB2, and the FGFRs. Literature-based validation efforts ensured confidence in the gene-disease association. Drug-gene mapping revealed candidates spanning those already in clinical trials for HNC (e.g., Afatinib, Cabozantinib, Dasatinib, Brigatinib, Lenvatinib, Capivasertib, and Erdafitinib) and emerging or repurposing candidates (Amuvatinib, XL765 (Voxtalisib), Golotimod, Artenimol, Quercetin, and Acetylsalicylic Acid), offering opportunities for precision repurposing. Conclusions: The GARD pipeline demonstrates a genomics-driven, network-informed framework for systematic drug repurposing in HNC. HPV stratification enhances precision, literature-based validation strengthens confidence, and integrated drug mapping enables refinement of existing therapies and discovery of novel candidates for personalized treatment strategies. Code Availability: The full implementation of the GARD pipeline, including preprocessing scripts, statistical analysis modules, and visualization tools, is publicly available on GitHub.

Identification of important biomarkers associated with complex disease survival outcomes is fundamental for gaining an in-depth understanding of disease mechanisms and advancing precision medicine in conditions such as cancer and cardiovascular disorders. However, these tasks are complicated by the unique nature of time-to-event data, which captures both the occurrence and timing of clinical events. Notably, complex associations such as the non-linear and non-additive biomarker interactions and the high-dimensionality challenge conventional survival data modeling approaches. To address these difficulties, we propose SurvDNN, an enhanced deep neural network framework specifically designed for survival outcomes modeling. SurvDNN incorporates a bootstrapping-based regularization strategy to mitigate overfitting and a novel stability-driven filtering algorithm to improve model robustness. To enable interpretable biomarker discovery, we extend the Permutation-based Feature Importance Test (PermFIT) to survival settings, allowing rigorous quantification of individual biomarker contributions under complex biomarker-outcome associations. Through extensive simulations and applications to real-world datasets, SurvDNN consistently outperforms existing machine learning approaches in both biomarker identification and predictive accuracy. Our results demonstrate the potential of SurvDNN coupled with PermFIT as an interpretable, robust, and powerful tool for biomarker-driven survival modeling in complex diseases. An open-source R package implementing SurvDNN is publicly available on GitHub (https://github.com/BZou-lab/SurvDNN).

BackgroundBlack individuals are more likely to die from colorectal cancer (CRC) and experience more treatment-related side effects compared to White individuals. Physical activity (PA) has been associated with decreased side effects, improved CRC treatment completion rates and responses, and survival. However, Black survivors of CRC are 60% less likely to engage in PA than White survivors. The Physical Activity Centers Empowerment (PACE) study is testing an intervention specifically designed to increase PA among Black individuals diagnosed with CRC. ObjectiveThis study outlines the protocol for a randomized controlled trial. The study aims to test the feasibility of PACE and will use the reach, effectiveness, adoption, implementation, and maintenance (RE-AIM) framework. MethodsThe PACE study was developed in partnership with a community advisory board consisting of Black cancer advocates and survivors of cancer. The study aims to recruit 72 participants aged >18 years from North Carolina who have been diagnosed with CRC. These participants will be randomized in a 1:1 ratio to an intervention or control group. During the 12-week intervention, all participants will receive a wearable activity tracker and informational materials from the American College of Sports Medicine’s “Moving through Cancer” program. The intervention group will also receive additional PACE theory–guided intervention components, including personalized daily adaptive step goals, access to the PACE video library, and optional video chat meetings for PA support. Data will be collected at 3 time points: baseline, after the intervention (3 months), and 6 months after the intervention (9 months). Using the RE-AIM framework, the study aims to evaluate the intervention’s reach, effectiveness, acceptability, implementation, and maintenance. ResultsThe National Institute on Minority Health and Health Disparities funded this study in 2021. Study enrollment began in August 2024 and is anticipated to conclude in December 2024. ConclusionsThis study will advance our understanding of effective behavioral strategies to increase PA and help advance the use of PA as a form of complementary cancer treatment, with the aim of improving health outcomes for Black survivors of CRC. Trial RegistrationClinicalTrials.gov NCT06411756; https://clinicaltrials.gov/study/NCT06411756 International Registered Report Identifier (IRRID)DERR1-10.2196/65804

MOTIVATION:Omics features, often measured by high-throughput technologies, combined with clinical features, significantly impact the understanding of many complex human diseases. Integrating key omics biomarkers with clinical risk factors is essential for elucidating disease mechanisms, advancing early diagnosis, and enhancing precision medicine. However, the high dimensionality and intricate associations between disease outcomes and omics profiles present substantial analytical challenges. RESULTS:We propose a high-dimensional feature importance test (HiFIT) framework to address these challenges. Specifically, we develop an ensemble data-driven biomarker identification tool, Hybrid Feature Screening (HFS), to construct a candidate feature set for downstream machine learning models. The pre-screened candidate features from HFS are further refined using a computationally efficient permutation-based feature importance test employing machine learning methods to flexibly model the potential complex associations between disease outcomes and molecular biomarkers. Through extensive numerical simulation studies and practical applications to microbiome-associated weight changes following bariatric surgery, as well as the examination of gene-expression-associated kidney pan-cancer survival data, we demonstrate HiFIT's superior performance in both outcome prediction and feature importance identification. AVAILABILITY AND IMPLEMENTATION:An R package implementing the HiFIT algorithm is available on GitHub (https://github.com/BZou-lab/HiFIT).

The integration of drug molecular representations into predictive models for Drug Response Prediction (DRP) is a standard procedure in pharmaceutical research and development. However, the comparative effectiveness of combining these representations with genetic profiles for DRP remains unclear. This study conducts a comprehensive evaluation of the efficacy of various drug molecular representations employing cutting-edge machine learning models under various experimental settings. Our findings reveal that the inclusion of molecular representations from either PubChem fingerprints or SMILES can significantly enhance the performance of DRPs when used in conjunction with deep learning models. However, the optimal choice of drug molecular representation can vary depending on the predictive model and the specific DRP task. The insights derived from our study offer useful guidance on selecting the most suitable drug molecular representations for constructing efficient predictive models for DRPs, aiding for drug repurposing, personalized medicine, and new drug discovery.

Introduction:Disasters have disproportionately impacted nursing home (NH) residents. COVID-19 impacted NH more so than the community-dwelling population, but there was much variation in mortality rates among NH residents. These disparities have been studied, but place-based disparities have received less attention. Place-based disparities are differences in health due to physical location, including factors like rurality, local socioeconomic conditions, and the physical environment. Methods:We searched three databases for peer-reviewed studies of place-based factors associated with mortality in U.S. NHs during the COVID-19 pandemic, ending in January 2024. Data were organized using the National Institute on Minority Health and Health Disparities research framework. Results:We identified 27 articles that included individual, interpersonal, community, and societal place-based factors associated with mortality during the pandemic. Differences in mortality were related to local community socioeconomic factors, staff neighborhood socioeconomic factors, urbanity, community viral spread, and state-level factors, including political leaning and social distancing policies. Rurality was associated with lower mortality but was also associated with racial disparities. Discussion:Place-based disparities at the individual, organizational, community, and societal levels were identified. Rurality and local COVID-19 spread were the most commonly studied place-based factors associated with NH deaths during the pandemic. Neighborhood factors may be most impactful through the impact on NH staff. Racial disparities were linked with location, highlighting the effects of historical systemic racism on NHs. Policies to protect NH residents during disasters must be sensitive to local characteristics.

What factors influence pelvic floor muscle exercise (PFME) intention and engagement among men post-radical prostatectomy (RP), and how do demographic and medical characteristics moderate these relationships? Post-RP urinary incontinence (UI) affects up to 69% of patients, significantly impacting their quality of life. PFME is recommended to manage UI, but many patients fail to achieve the required frequency and intensity, leading to suboptimal outcomes. This study seeks to identify factors influencing PFME intention and engagement, using the Reasoned Action Approach (RAA), to fill the gaps in PFME research and practice. The literature highlights that experiential attitude, instrumental attitude, injunctive norm, autonomy, capacity and perceived UI influence PFME engagement. Previous studies have not fully explored the role of these determinants specifically among men post-RP. Additionally, the moderating effects of demographic and medical factors, such as education level and time since surgery, on these relationships remain underexamined. This gap underscores the need for targeted, evidence-based interventions to optimise UI management post-RP. This study utilised a correlational design with data collected at two points: baseline and a four-week follow-up. A total of 108 men with prostate cancer (PC) post-RP from two large hospitals in Amman, Jordan, participated. After obtaining IRB approval, we recruited patients during their follow-up visits, achieving a recruitment rate of 93.1%. Written informed consent was obtained from all participants. Data were collected through anonymous, printed questionnaires administered in private rooms at the hospitals. PFME engagement, RAA determinants and demographics were measured. A follow-up survey was completed by 107 participants, yielding a retention rate of 99.1%. Statistical analysis included hierarchical regression and moderation analyses. In the final model, PFME intention (beta = 0.33, p < 0.001) and perceived UI (beta = -0.08, p < 0.001) were significant predictors of PFME engagement. Follow-up regression showed that PFME intention predicted engagement less effectively (B = 0.51, p < 0.001), and perceived UI predicted engagement more strongly (B = -0.22, p < 0.001) when participants were 6 months or longer post-RP. Interactions between months since RP and intention (B = -0.60, p < 0.001) and perceived UI (B = -0.11, p < 0.017) significantly impacted PFME engagement. The study suggests that the RAA framework can effectively predict PFME engagement in men post-RP, guiding the development of tailored interventions to enhance PFME engagement, ultimately improving urinary incontinence outcomes. This research also has the potential to impact the research community by offering insights into behavioural determinants and enhancing the effectiveness of post-radical prostatectomy rehabilitation strategies.

Objectives Safety concerns in assisted living (AL) communities are critical, yet understudied from the perspectives of residents, family caregivers, and staff. This study aimed to explore and compare safety concerns across these 3 groups. Design This qualitative study conducted structured interviews to identify safety concerns from the perspectives of residents, family caregivers, and staff. Setting and Participants Data were collected from 104 participants in AL communities across the United States, comprising 32 residents, 34 family caregivers, and 38 staff members. Methods We conducted summative content analysis of interview transcripts, identifying distinct safety concerns and comparing the commonality and discrepancies in safety concerns across the 3 participant groups. Results We identified 29 safety concerns in AL communities. For the top common safety concern, resident condition-related falls were the most frequently reported concern across all groups. Regarding the discrepancies among the 3 groups, resident and/or family groups expressed concerns about prompt use of assistive devices and technology, communication/relationships, and self-care/independence, whereas staff frequently reported concern with environmental issues causing falls. Conclusions and Implications Safety concerns in AL communities are multifaceted and shared across residents, family caregivers, and staff, with falls and unmet care needs being primary concerns. However, differences identified in this study suggest the need for tailored interventions that address the unique concerns of each group. Improving communication among staff, residents, and families may reduce safety concern mismatches and potentially contribute to a safer AL environment.

BACKGROUND:Research has shown that late fatigue post-stroke is associated with poorer long-term outcomes, but the association between early fatigue with concurrent outcomes like physical function within six months is underexplored. AIM:To explore the interrelationship between stroke survivors' adaptation to fatigue and physical function changes during hospitalization and at one, three, and six months post-stroke. DESIGN:A prospective longitudinal cohort study with a convergent mixed-methods design. METHODS:Adults (≥18 years) with first-ever ischemic stroke were included. Fatigue, physical function, and data from semi-structured interviews were collected at four time points. A mixed-effect model was used to explore the quantitative relationship, with physical function as the dependent outcome and fatigue as the fixed-effect variable. Directed content analysis was used for qualitative data. A side-by-side display was used to present mixed-methods findings. RESULTS:Thirty-two survivors were in the quantitative arm; nine of those were in the qualitative arm. Quantitative analysis showed that each unit increase in fatigue decreased physical function by 0.27, adjusting for age, depression, and time. Qualitative findings confirmed that fatigue hindered recovery and pre-stroke activity resumption. Survivors described a vicious cycle between fatigue and function, with varying fatigue patterns and exacerbating factors within six months. CONCLUSIONS:Fatigue and physical function were interrelated within six months after stroke. Given the small, single-center sample, these results should be interpreted cautiously. Still, our findings highlight the value of early, systematic fatigue assessment and collaborative discussions between survivors and health professionals to guide individualized management strategies. CLINICAL REHABILITATION IMPACT:Managing post-stroke fatigue requires both survivor-led strategies (e.g., self-monitoring, rest, pacing) and professional support to address contributing conditions. Routine follow-up should include systematic fatigue assessment, collaborative discussion of management options, and periodic re-evaluation to optimize recovery.

Respiratory viral infections pose a global health burden, yet the cellular immune mechanisms underlying protection and pathology remain unclear. Natural infection cohorts often lack pre-exposure baselines and time-controlled sampling, whereas inoculation and vaccination trials generate well-structured longitudinal transcriptomic data. However, these datasets are scattered across repositories and processed inconsistently, hindering integrative and AI-driven analyses. To address these challenges, we developed the Human Respiratory Viral Immunization LongitudinAl Gene Expression (HR-VILAGE-3K3M) repository: an AI-ready resource integrating bulk and single-cell transcriptomic profiles from 3,178 subjects across 66 studies. The dataset spans vaccination, inoculation, and mixed exposures, with samples from blood and nasal swabs collected from public repositories including GEO, ImmPort, and ArrayExpress. We curated and harmonized subject-level metadata, standardized outcome measures, and applied unified preprocessing with rigorous quality control. We further provide benchmark analyses illustrating its utility. This resource supports discovery of biomarkers, immune mechanisms, and methodological development. As one of the largest longitudinal transcriptomic resources for human respiratory viral immunization, HR-VILAGE-3K3M enables reproducible and scalable analyses to accelerate vaccine and antiviral research.

Poststroke fatigue severely affects stroke survivors (SSs) physically and mentally. Although the literature acknowledges the critical role of care partners (CPs) in survivors' fatigue adaptation, this topic remains under-explored. This study, guided by the Adaptive Leadership Framework for Chronic Illness, explored how SSs and CPs managed fatigue collaboratively within 6 months poststroke. This longitudinal qualitative analysis included nine first-time ischemic SSs and their CPs who consented to interviews. Semistructured interviews were conducted during the index hospitalization (or within 10 days postdischarge) and at 1, 3, and 6 months poststroke. Directed content analysis was used to analyze the data. Four themes were identified. First, SSs and CPs engaged in collaborative work by achieving a mutual understanding of fatigue levels but misalignment was found during 3-6 months poststroke. Second, CPs provided emotional and practical support, exercising adaptive leadership to help survivors adapt to fatigue. The support squad, including informal and formal helpers beyond the primary CPs, also undertook adaptive leadership behaviors to facilitate the post-stroke adaptation to fatigue for both SSs and CPs. Third, the day-to-day realities of post-stroke fatigue presented persistent challenges for SSs. Fourth, SSs managed fatigue (adaptive work) by using self-awareness, resting, and pacing activities. Results suggested the need for SSs and CPs to develop a shared understanding of fatigue. Healthcare professionals should treat SSs and CPs as an adaptive unit, ensuring access to support resources at discharge to facilitate post-stroke adaptation to fatigue.