Source-free domain adaptation for semantic image segmentation using internal representations.

Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic unsupervised domain adaptation (UDA) attempts to address a similar problem when there is target domain with no annotated data points through transferring knowledge from a source domain with annotated data. We develop an online UDA algorithm for semantic segmentation of images that improves model generalization on unannotated domains in scenarios where source data access is restricted during adaptation. We perform model adaptation by minimizing the distributional distance between the source latent features and the target features in a shared embedding space. Our solution promotes a shared domain-agnostic latent feature space between the two domains, which allows for classifier generalization on the target dataset. To alleviate the need of access to source samples during adaptation, we approximate the source latent feature distribution via an appropriate surrogate distribution, in this case a Gaussian mixture model (GMM).

An interpretable Bayesian clustering approach with feature selection for analyzing spatially resolved transcriptomics data.

Recent breakthroughs in spatially resolved transcriptomics (SRT) technologies have enabled comprehensive molecular characterization at the spot or cellular level while preserving spatial information. Cells are the fundamental building blocks of tissues, organized into distinct yet connected components. Although many non-spatial and spatial clustering approaches have been used to partition the entire region into mutually exclusive spatial domains based on the SRT high-dimensional molecular profile, most require an ad hoc selection of less interpretable dimensional-reduction techniques. To overcome this challenge, we propose a zero-inflated negative binomial mixture model to cluster spots or cells based on their molecular profiles. To increase interpretability, we employ a feature selection mechanism to provide a low-dimensional summary of the SRT molecular profile in terms of discriminating genes that shed light on the clustering result. We further incorporate the SRT geospatial profile via a Markov random field prior. We demonstrate how this joint modeling strategy improves clustering accuracy, compared with alternative state-of-the-art approaches, through simulation studies and 3 real data applications.

Disposable e-cigarette use: Factors, frequency and cigarette smoking among United States high school students.

BACKGROUND AND AIMS: Disposable e-cigarette use has increased among United States (US) high school students in recent years. However, there is limited research on the profile of these users, how often they use these products, and whether they displace cigarette smoking. This study aimed to measure how disposable e-cigarette use among US youth varies according to demographic characteristics and whether there is any association between e-cigarette use and reduced use of traditional cigarettes. DESIGN: We used cross-sectional data from the 2022 National Youth Tobacco Survey and conducted a multinomial logistic regression to examine factors associated with the types of e-cigarette devices used in the prior 30 days, adjusting for sex, sexual identity, grade level and race/ethnicity. We also used a finite mixture model to account for unobserved differences among users and identify e-cigarette use patterns in different subgroups of users. SETTING: United States. PARTICIPANTS: High school students in grades 9-12 (n = 14 389). MEASUREMENTS: Survey participants self-reported the type of e-cigarette device used, the frequency of e-cigarettes used and cigarettes smoked over the past 30 days. FINDINGS: Disposable e-cigarettes were the most popular e-cigarette type. Sex, sexual orientation, grade level and race/ethnicity were associated with disposable e-cigarette use. The odds of disposable e-cigarette use were lower in male students than in female students (odds ratio [OR] = 0.78, 95% confidence interval [CI] = [0.64-0.96]), and higher in students who identified as gay or lesbian (OR = 1.70, 95% CI = [1.11-2.61]) or bisexual (OR = 1.52, 95% CI = [1.16-1.99]) than in heterosexual students. The odds of disposable use were higher among students in higher grades (10th, 11th and 12th) than in 9th graders (OR = 1.71, 2.24 and 2.52, respectively). Disposable e-cigarette users had a lower frequency of traditional cigarette use than other e-cigarette users, both in the low-frequency class (incidence rate ratio [IRR] = 0.33, 95% CI = [0.12-0.92]) and the high-frequency class (IRR = 0.27, 95% CI = [0.08-0.92]). CONCLUSIONS: Disposable e-cigarette use appears to be higher among United States high school students who are female, older and/or identify as gay, lesbian or bisexual. Disposable e-cigarettes appear to be associated with reduced traditional cigarette use.

Model-based multifacet clustering with high-dimensional omics applications.

High-dimensional omics data often contain intricate and multifaceted information, resulting in the coexistence of multiple plausible sample partitions based on different subsets of selected features. Conventional clustering methods typically yield only one clustering solution, limiting their capacity to fully capture all facets of cluster structures in high-dimensional data. To address this challenge, we propose a model-based multifacet clustering (MFClust) method based on a mixture of Gaussian mixture models, where the former mixture achieves facet assignment for gene features and the latter mixture determines cluster assignment of samples. We demonstrate superior facet and cluster assignment accuracy of MFClust through simulation studies. The proposed method is applied to three transcriptomic applications from postmortem brain and lung disease studies. The result captures multifacet clustering structures associated with critical clinical variables and provides intriguing biological insights for further hypothesis generation and discovery.

Directly selecting cell-type marker genes for single-cell clustering analyses.

In single-cell RNA sequencing (scRNA-seq) studies, cell types and their marker genes are often identified by clustering and differentially expressed gene (DEG) analysis. A common practice is to select genes using surrogate criteria such as variance and deviance, then cluster them using selected genes and detect markers by DEG analysis assuming known cell types. The surrogate criteria can miss important genes or select unimportant genes, while DEG analysis has the selection-bias problem. We present Festem, a statistical method for the direct selection of cell-type markers for downstream clustering. Festem distinguishes marker genes with heterogeneous distribution across cells that are cluster informative. Simulation and scRNA-seq applications demonstrate that Festem can sensitively select markers with high precision and enables the identification of cell types often missed by other methods. In a large intrahepatic cholangiocarcinoma dataset, we identify diverse CD8+ T cell types and potential prognostic marker genes.

Ornaments for efficient allele-specific expression estimation with bias correction.

Allele-specific expression plays a crucial role in unraveling various biological mechanisms, including genomic imprinting and gene expression controlled by cis-regulatory variants. However, existing methods for quantification from RNA-sequencing (RNA-seq) reads do not adequately and efficiently remove various allele-specific read mapping biases, such as reference bias arising from reads containing the alternative allele that do not map to the reference transcriptome or ambiguous mapping bias caused by reads containing the reference allele that map differently from reads containing the alternative allele. We present Ornaments, a computational tool for rapid and accurate estimation of allele-specific transcript expression at unphased heterozygous loci from RNA-seq reads while correcting for allele-specific read mapping biases. Ornaments removes reference bias by mapping reads to a personalized transcriptome and ambiguous mapping bias by probabilistically assigning reads to multiple transcripts and variant loci they map to. Ornaments is a lightweight extension of kallisto, a popular tool for fast RNA-seq quantification, that improves the efficiency and accuracy of WASP, a popular tool for bias correction in allele-specific read mapping. In experiments with simulated and human lymphoblastoid cell-line RNA-seq reads with the genomes of the 1000 Genomes Project, we demonstrate that Ornaments improves the accuracy of WASP and kallisto, is nearly as efficient as kallisto, and is an order of magnitude faster than WASP per sample, with the additional cost of constructing a personalized index for multiple samples. Additionally, we show that Ornaments finds imprinted transcripts with higher sensitivity than WASP, which detects imprinted signals only at gene level.

BPT-PLR: A Balanced Partitioning and Training Framework with Pseudo-Label Relaxed Contrastive Loss for Noisy Label Learning.

While collecting training data, even with the manual verification of experts from crowdsourcing platforms, eliminating incorrect annotations (noisy labels) completely is difficult and expensive. In dealing with datasets that contain noisy labels, over-parameterized deep neural networks (DNNs) tend to overfit, leading to poor generalization and classification performance. As a result, noisy label learning (NLL) has received significant attention in recent years. Existing research shows that although DNNs eventually fit all training data, they first prioritize fitting clean samples, then gradually overfit to noisy samples. Mainstream methods utilize this characteristic to divide training data but face two issues: class imbalance in the segmented data subsets and the optimization conflict between unsupervised contrastive representation learning and supervised learning. To address these issues, we propose a Balanced Partitioning and Training framework with Pseudo-Label Relaxed contrastive loss called BPT-PLR, which includes two crucial processes: a balanced partitioning process with a two-dimensional Gaussian mixture model (BP-GMM) and a semi-supervised oversampling training process with a pseudo-label relaxed contrastive loss (SSO-PLR). The former utilizes both semantic feature information and model prediction results to identify noisy labels, introducing a balancing strategy to maintain class balance in the divided subsets as much as possible. The latter adopts the latest pseudo-label relaxed contrastive loss to replace unsupervised contrastive loss, reducing optimization conflicts between semi-supervised and unsupervised contrastive losses to improve performance. We validate the effectiveness of BPT-PLR on four benchmark datasets in the NLL field: CIFAR-10/100, Animal-10N, and Clothing1M. Extensive experiments comparing with state-of-the-art methods demonstrate that BPT-PLR can achieve optimal or near-optimal performance.

Characterization of domain formation in complex membranes.

A widely known property of lipid membranes is their tendency to undergo a separation into disordered (Ld) and ordered (Lo) domains. This impacts the local structure of the membrane relevant for the physical (e.g., enhanced electroporation) and biological (e.g., protein sorting) significance of these regions. The increase in computing power, advancements in simulation software, and more detailed information about the composition of biological membranes shifts the study of these domains into the focus of classical molecular dynamics simulations. In this chapter, we present a versatile yet robust analysis pipeline that can be easily implemented and adapted for a wide range of lipid compositions. It employs Gaussian-based Hidden Markov Models to predict the hidden order states of individual lipids by describing their structure through the area per lipid and the average SCC order parameters per acyl chain. Regions of the membrane with a high correlation between ordered lipids are identified by employing the Getis-Ord local spatial autocorrelation statistic on a Voronoi tessellation of the lipids. As an example, the approach is applied to two distinct systems at a coarse-grained resolution, demonstrating either a strong tendency towards phase separation (1,2-dipalmitoyl-sn-glycero-3-phosphocholine (DPPC), 1,2-dilinoleoyl-sn-glycero-3-phosphocholine (DIPC), cholesterol) or a weak tendency toward phase separation (1-palmitoyl-2-oleoyl-sn-glycero-3-phosphocholine (POPC), 1-palmitoyl-2-docosahexaenoyl-sn-glycero-3-phosphocholine (PUPC), cholesterol). Explanations of the steps are complemented by coding examples written in Python, providing both a comprehensive understanding and practical guidance for a seamless integration of the workflow into individual projects.

Intergenerational educational mobility and cognitive trajectories among middle-aged and older Chinese people: An application of growth mixture and mobility contrast models in longitudinal analysis.

OBJECTIVES: Due to statistical challenges in disentangling the mobility effect (i.e., intergenerational educational mobility) from the position effect (i.e., parental and person's own education), the impact of intergenerational educational mobility on cognitive function remains unclear. We employed a novel approach to identify the mobility effect and investigate the net impact of intergenerational educational mobility on heterogeneous patterns of cognition among middle-aged and older adults in China. METHODS: Participants aged 45 and older were recruited from the China Health and Retirement Longitudinal Study, a population-based prospective cohort study between 2011 and 2018. We identified cognitive trajectories using the growth mixture model (GMM) and subsequently employed the mobility contrast model (MCM) to examine the effects of intergenerational educational mobility on cognitive patterns stratified by gender. RESULTS: Almost two-thirds of respondents experienced intergenerational educational mobility, and 55% experienced upward mobility. Men had a higher rate of upward mobility than women. Three population-based cognitive patterns were identified: the low cognitive function with decline group (28%), the moderate cognitive function group (47%), and the high cognitive function group (26%). MCM analysis revealed that both upward and downward intergenerational educational mobility negatively impacted cognitive trajectory patterns, extending beyond the influence of individuals' current and parental education. DISCUSSION: In future research, the impact of mobility can be studied in longitudinal datasets by combining the GMM and MCM approaches. The net negative effect of intergenerational educational mobility on cognitive trajectory patterns indicates that it should be recognized as an independent predictor of cognitive decline.

Boosting cuckoo optimization algorithm via Gaussian mixture model for optimal power flow problem in a hybrid power system with solar and wind renewable energies.

This paper presents a novel approach, the Gaussian Mixture Method-enhanced Cuckoo Optimization Algorithm (GMMCOA), designed to optimize power flow decision parameters, with a specific focus on minimizing fuel cost, emissions, network loss, and voltage deviation. GMMCOA integrates the strengths of COA and GMM while mitigating their individual limitations. While COA offers robust search capabilities, it suffers from initial parameter dependency and the risk of getting trapped in local optima. Conversely, GMM delivers high-speed performance but requires guidance to identify the best solution. By combining these methods, GMMCOA achieves an intelligent approach characterized by reduced parameter dependence and enhanced convergence speed. The effectiveness of GMMCOA is demonstrated through extensive testing on both the IEEE 30-bus and the large-scale 118-bus test systems. Notably, for the 118-bus test system, GMMCOA achieved a minimum cost of $129,534.7529 per hour and $103,382.9225 per hour in cases with and without the consideration of renewable energies, respectively, surpassing outcomes produced by alternative algorithms. Furthermore, the proposed method is benchmarked against the CEC 2017 test functions. Comparative analysis with state-of-the-art algorithms, under consistent conditions, highlights the superior performance of GMMCOA across various optimization functions. Remarkably, GMMCOA consistently outperforms its competitors, as evidenced by simulation results and Friedman examination outcomes. With its remarkable performance across diverse functions, GMMCOA emerges as the preferred choice for solving optimization problems, emphasizing its potential for real-world applications.

Stochastic characterization of navigation strategies in an automated variant of the Barnes maze.

Animals can use a repertoire of strategies to navigate in an environment, and it remains an intriguing question how these strategies are selected based on the nature and familiarity of environments. To investigate this question, we developed a fully automated variant of the Barnes maze, characterized by 24 vestibules distributed along the periphery of a circular arena, and monitored the trajectories of mice over 15 days as they learned to navigate towards a goal vestibule from a random start vestibule. We show that the patterns of vestibule visits can be reproduced by the combination of three stochastic processes reminiscent of random, serial, and spatial strategies. The processes randomly selected vestibules based on either uniform (random) or biased (serial and spatial) probability distributions. They closely matched experimental data across a range of statistical distributions characterizing the length, distribution, step size, direction, and stereotypy of vestibule sequences, revealing a shift from random to spatial and serial strategies over time, with a strategy switch occurring approximately every six vestibule visits. Our study provides a novel apparatus and analysis toolset for tracking the repertoire of navigation strategies and demonstrates that a set of stochastic processes can largely account for exploration patterns in the Barnes maze.

Functional Biscuits, a Healthy Addition to Your Coffee Break-Evaluating Consumer Acceptability and Willingness to Pay.

An increasing number of individuals are eating out due to work and study commitments. This trend directly influences people's food choices, especially those who frequently rely on snacks and pre-packaged foods. Consuming these foods can lead to long-term health consequences. Adding functional foods to vending machines could lead to healthier choices. Our aim is to evaluate the acceptability and willingness to pay (WTP) of workers and students for a snack pack of novel functional biscuits (FBs) made with high amylose contents. We found that the experimental flour used is effective in preventing various non-communicable diseases; two phases of analysis were carried out on 209 participants. The participants blindly tested the products and only after the sensory evaluation were they informed about the biscuits' health contents. Firstly, the blind investigation highlighted the acceptability of the FBs compared to the conventional biscuits. Secondly, the finite mixture model on WTP revealed that some consumers are interested in the health benefits associated with high-amylose test blends and others are focused on hedonistic taste. The design of a communication strategy and industry approach should aim to assist consumers in comprehending the health benefits and sensory aspects of novel functional foods available on the market.

A novel Gaussian sum quaternion constrained cubature Kalman filter algorithm for GNSS/SINS integrated attitude determination and positioning system.

The quaternion cubature Kalman filter (QCKF) algorithm has emerged as a prominent nonlinear filter algorithm and has found extensive applications in the field of GNSS/SINS integrated attitude determination and positioning system (GNSS/SINS-IADPS) data processing for unmanned aerial vehicles (UAV). However, on one hand, the QCKF algorithm is predicated on the assumption that the random model of filter algorithm, which follows a white Gaussian noise distribution. The noise in actual GNSS/SINS-IADPS is not the white Gaussian noise but rather a ubiquitous non-Gaussian noise. On the other hand, the use of quaternions as state variables is bound by normalization constraints. When applied directly in nonlinear non-Gaussian system without considering normalization constraints, the QCKF algorithm may result in a mismatch phenomenon in the filtering random model, potentially resulting in a decline in estimation accuracy. To address this issue, we propose a novel Gaussian sum quaternion constrained cubature Kalman filter (GSQCCKF) algorithm. This algorithm refines the random model of the QCKF by approximating non-Gaussian noise with a Gaussian mixture model. Meanwhile, to account for quaternion normalization in attitude determination, a two-step projection method is employed to constrain the quaternion, which consequently enhances the filtering estimation accuracy. Simulation and experimental analyses demonstrate that the proposed GSQCCKF algorithm significantly improves accuracy and adaptability in GNSS/SINS-IADPS data processing under non-Gaussian noise conditions for Unmanned Aerial Vehicles (UAVs).

A sparse factor model for clustering high-dimensional longitudinal data.

Recent advances in engineering technologies have enabled the collection of a large number of longitudinal features. This wealth of information presents unique opportunities for researchers to investigate the complex nature of diseases and uncover underlying disease mechanisms. However, analyzing such kind of data can be difficult due to its high dimensionality, heterogeneity and computational challenges. In this article, we propose a Bayesian nonparametric mixture model for clustering high-dimensional mixed-type (eg, continuous, discrete and categorical) longitudinal features. We employ a sparse factor model on the joint distribution of random effects and the key idea is to induce clustering at the latent factor level instead of the original data to escape the curse of dimensionality. The number of clusters is estimated through a Dirichlet process prior. An efficient Gibbs sampler is developed to estimate the posterior distribution of the model parameters. Analysis of real and simulated data is presented and discussed. Our study demonstrates that the proposed model serves as a useful analytical tool for clustering high-dimensional longitudinal data.

Parenting practices and trajectories of proactive coping assets among emerging adult Black men.

Positive youth development (PYD) frameworks suggest that a critical response to investigating the challenges young Black men living in resource poor communities experience involves identifying contextual resources in young men's lives and personal assets that promote success. The following study examines heterogeneity in proactive coping assets trajectories, parental practices as predictors of developmental trajectories, and associated outcomes of each trajectory. The study sample consisted of Black emerging adult men living in rural Georgia (N = 504). At baseline, men were between the ages of 19 and 22 (Mage = 20.29; SD = 1.10). At wave four, the participants' mean age was 27.67 (SD = 1.39). Results of growth mixture modeling from waves 1 to 3 discerned three developmental trajectory classes of emerging adults' proactive coping assets: a high and increasing class (n = 247, 49%), a low and stable class (n = 212, 42%), and a moderate and decreasing class (n = 45, 9%). Trajectory classes were linked to baseline levels of parental support, coaching, and expectations. Analysis revealed that parental support and parental coaching predicted proactive coping asset trajectory class identification. Links were then investigated between emerging adults' proactive coping asset trajectory classes and wave four physical health, depression, and alcohol use. Results revealed significant associations between class identification, alcohol use, and physical health. Study findings provide evidence supporting the impact of parenting on emerging adult Black men, underscoring the need to expand resources that support parenting and emerging adult relationships.

A structural microsimulation model for demand-side cost-sharing in healthcare.

Demand-side cost-sharing reduces moral hazard in healthcare but increases exposure to out-of-pocket expenditure. We introduce a structural microsimulation model to evaluate both total and out-of-pocket expenditure for different cost-sharing schemes. We use a Bayesian mixture model to capture the healthcare expenditure distributions across different age-gender categories. We estimate the model using Dutch data and simulate outcomes for a number of policies. The model suggests that for a deductible of 300 euros shifting the starting point of the deductible away from zero to 400 euros leads to an average 4% reduction in healthcare expenditure and 47% lower out-of-pocket payments.

Optimizing Collaborative Crowdsensing: A Graph Theoretical Approach to Team Recruitment and Fair Incentive Distribution.

Collaborative crowdsensing is a team collaboration model that harnesses the intelligence of a large network of participants, primarily applied in areas such as intelligent computing, federated learning, and blockchain. Unlike traditional crowdsensing, user recruitment in collaborative crowdsensing not only considers the individual capabilities of users but also emphasizes their collaborative abilities. In this context, this paper takes a unique approach by modeling user interactions as a graph, transforming the recruitment challenge into a graph theory problem. The methodology employs an enhanced Prim algorithm to identify optimal team members by finding the maximum spanning tree within the user interaction graph. After the recruitment, the collaborative crowdsensing explored in this paper presents a challenge of unfair incentives due to users engaging in free-riding behavior. To address these challenges, the paper introduces the MR-SVIM mechanism. Initially, the process begins with a Gaussian mixture model predicting the quality of users' tasks, combined with historical reputation values to calculate their direct reputation. Subsequently, to assess users' significance within the team, aggregation functions and the improved PageRank algorithm are employed for local and global influence evaluation, respectively. Indirect reputation is determined based on users' importance and similarity with interacting peers. Considering the comprehensive reputation value derived from the combined assessment of direct and indirect reputations, and integrating the collaborative capabilities among users, we have formulated a feature function for contribution. This function is applied within an enhanced Shapley value method to assess the relative contributions of each user, achieving a more equitable distribution of earnings. Finally, experiments conducted on real datasets validate the fairness of this mechanism.

Trajectories and influencing factors of social anxiety in postoperative breast cancer patients.

BACKGROUND: Social anxiety among postoperative breast cancer patients is a prevalent concern, with its intensity fluctuating throughout the course of treatment. The study aims to describe the trajectory of social anxiety in postoperative breast cancer patients, explore the influencing factors, and provide theoretical support for the construction of future intervention programs. METHODS: This study was conducted from June 2022 to January 2023, encompassing 213 breast cancer patients from three first-class hospitals in China. Data collection occurred at four distinct time points. A growth mixture model was employed to identify latent categories representing the trajectories of social anxiety changes among patients. A multiple regression analysis was utilized to explore predictive factors associated with different latent trajectory categories. RESULTS: The trajectory of social anxiety changes in postoperative breast cancer patients includes five potential categories: maintaining mild social anxiety group, changing from mild to moderate social anxiety group, maintaining moderate social anxiety group, changing from moderate to severe social anxiety group, and maintaining severe social anxiety group. Cluster analysis results indicated three types: positive, negative, and low. Logistic regression analysis revealed that younger age, spouses concerned about postoperative appearance, chemotherapy with taxol-based drugs, opting for modified radical surgery or radical mastectomy surgical approaches, and breast cancer patients with negative rumination were factors that influenced patients' social anxiety (P < 0.05). CONCLUSION: The trajectory of social anxiety in postoperative breast cancer patients comprises five potential categories. In clinical practice, it is essential to strengthen the management of high-risk populations susceptible to experiencing social anxiety emotions, including younger age, spouses concerned about postoperative appearance, chemotherapy with taxol-based drugs, opting for modified radical surgery or radical mastectomy surgical approaches, and breast cancer patients with negative rumination.

Bayesian hidden mark interaction model for detecting spatially variable genes in imaging-based spatially resolved transcriptomics data.

Recent technology breakthroughs in spatially resolved transcriptomics (SRT) have enabled the comprehensive molecular characterization of cells whilst preserving their spatial and gene expression contexts. One of the fundamental questions in analyzing SRT data is the identification of spatially variable genes whose expressions display spatially correlated patterns. Existing approaches are built upon either the Gaussian process-based model, which relies on ad hoc kernels, or the energy-based Ising model, which requires gene expression to be measured on a lattice grid. To overcome these potential limitations, we developed a generalized energy-based framework to model gene expression measured from imaging-based SRT platforms, accommodating the irregular spatial distribution of measured cells. Our Bayesian model applies a zero-inflated negative binomial mixture model to dichotomize the raw count data, reducing noise. Additionally, we incorporate a geostatistical mark interaction model with a generalized energy function, where the interaction parameter is used to identify the spatial pattern. Auxiliary variable MCMC algorithms were employed to sample from the posterior distribution with an intractable normalizing constant. We demonstrated the strength of our method on both simulated and real data. Our simulation study showed that our method captured various spatial patterns with high accuracy; moreover, analysis of a seqFISH dataset and a STARmap dataset established that our proposed method is able to identify genes with novel and strong spatial patterns.

Trajectory patterns and influencing factors of supportive care needs in stroke patients: A longitudinal study.

AIM: To investigate the trajectory patterns and influencing factors of supportive care needs in stroke patients. DESIGN: A longitudinal study. METHODS: In total, 207 stroke patients who received treatment at the Department of Neurology in a hospital in Xuzhou between July 2022 and July 2023 were recruited using convenience sampling. Questionnaires including supportive care needs, hospital anxiety and depression scale, and the Barthel index were investigated at baseline and at 1, 3, and 6 months. A latent class growth model was applied to identify the supportive care needs trajectories. Multiple logistic regression was used to determine the predictors for membership. This study adheres to STROBE reporting guidelines. RESULTS: Three patterns of supportive care needs trajectories were identified: A high needs slow decline group (20.8%), a medium needs stable group (56.5%) and a medium needs rapid decline group (22.7%). Based on further analysis, the findings indicated that age, education level, monthly income, comorbidity, activities of daily living, anxiety and depression were associated with the trajectory categories of supportive care needs with stroke patients. CONCLUSION: This study demonstrates heterogeneity in changes in supportive care needs among stroke patients. Healthcare providers need to consider these different categories of needs and develop individualized care measures based on the characteristics of different patients. IMPACT: Healthcare providers should be aware of the fluctuations in care needs of stroke patients at various stages. Additionally, the study aimed to identify patients' specific needs based on their circumstances, monitor the rehabilitation process and establish a more personalized and optimized care plan through multidisciplinary collaboration. The ultimate goal was to alleviate symptomatic distress and address the long-term care needs of patients. PATIENT OR PUBLIC CONTRIBUTION: No patient or public contribution.