Important Correlates Research Articles

Analysis of Molding Defection in IC Packaging and Testing Process

Molding injects a molding compound into a mold to form a protective shell around the wafer. During the injection process, overflow may occur, leading to mold flash, which reduces yield and causes significant manufacturing cost losses. This paper proposes a deep-learning-based method for detecting and predicting the occurrence of mold flash probability to address this issue. First, the paper conducts random forest importance analysis and correlation analysis to identify the key parameters that significantly impact mold flash. This paper uses these key parameters as input signals for the prediction model. The paper introduces an HLGA Transformer to construct an ensemble meta-learning model that predicts the probability of molding defects, achieving a prediction accuracy of 98.16%. The ensemble meta-learning approach proposed in this paper outperforms other methods in terms of performance. The model predictions can be communicated to the system in real time, allowing it to promptly adjust critical machine operation parameters, thereby significantly improving the molding process yield and reducing substantial manufacturing cost losses.

Prediction and clustering of Alzheimer’s disease by race and sex: a multi-head deep-learning approach to analyze irregular and heterogeneous data

Early detection of Alzheimer’s disease (AD) is crucial to maximize clinical outcomes. Most disease progression analyses include people with diagnoses of cognitive impairment, limiting understanding of AD risk among those with normal cognition. The objective was to establish AD progression models through a deep learning approach to analyze heterogeneous, multi-modal datasets, including clustering analyses of population subsets. A multi-head deep-learning architecture was built to process and learn from biomedical and imaging data from the National Alzheimer’s Coordinating Center. Shapley additive explanation algorithms for feature importance ranking and pairwise correlation analysis were used to identify predictors of disease progression. Four primary disease progression clusters (slow, moderate and rapid converters or non-converters) were subdivided into groups by race and sex, yielding 16 sub-clusters of participants with distinct progression patterns. A multi-head and early-fusion convolutional neural network achieved the most competitive performance and demonstrated superiority over a single-head deep learning architecture and conventional tree-based machine-learning methods, with 97% test accuracy, 96% F1 score and 0.19 root mean square error. From 447 features, 2 sets of 100 predictors of disease progression were extracted. Feature importance ranking, correlation analysis and descriptive statistics further enriched cluster analysis and validation of the heterogeneity of risk factors.

Machine-learning-based diabetes classification method using blood flow oscillations and Pearson correlation analysis of feature importance

Abstract Diabetes is a global health issue affecting millions of people and is related to high morbidity and mortality rates. Current diagnostic methods are primarily invasive, involving blood sampling, which can lead to infection and increased patient stress. As a result, there is a growing need for noninvasive diabetes diagnostic methods that are both accurate and fast. High measurement accuracy and fast measurement time are essential for effective noninvasive diabetes diagnosis; these can be achieved using diffuse speckle contrast analysis (DSCA) systems and artificial intelligence algorithms. In this study, we use a machine learning algorithm to analyze rat blood flow signals measured using a DSCA system with simple operation, easy fabrication, and fast measurement for helping diagnose diabetes. The results confirmed that the machine learning algorithm for analyzing blood flow oscillation data shows good potential for diabetes classification. Furthermore, analyzing the blood flow reactivity test revealed that blood flow signals can be quickly measured for diabetes classification. Finally, we evaluated the influence of each blood flow oscillation data on diabetes classification through feature importance and Pearson correlation analysis. The results of this study should provide a basis for the future development of hemodynamic-based disease diagnostic methods.

Microstructure and properties of Cu-3Ti-0.3Cr-0.15Mg alloy designed via machine learning

With the development of information technology, machine learning (ML) has been widely applied in materials science. ML can avoid a multitude of trial and error experiments and improve the efficiency of discovering new materials. Hence, screening the alloys with excellent properties by machine learning is time-saving and effective. In this work, the major element descriptors were screened by importance analysis and correlation analysis as input features, and common ML algorithms were considered to establish ML model. The final ‘composition-process-property’ alloy design strategy was proposed and applied to guide the selection of alloy systems and composition. As a result, the Cu-3Ti-0.3Cr-0.15 Mg alloy was screened based on the extreme gradient boosting (XGBoost) model. The ultimate tensile strength and electrical conductivity of 1018 MPa and 20.1 % IACS were achieved for the designed alloy, respectively, which is well consistent with the predicted values. The ultra-high strength for the designed alloy can be mainly attributed to the precipitation strengthening. Specifically, the formation of nanoscale β′-Cu4Ti and Cr precipitates during the heat treatment plays a significant role in enhancing the strength of the alloy. This work offers new insights into the design of Cu-Ti alloys with excellent comprehensive properties by employing a machine learning model trained on small data sets, which also provides a potential to be applied to other materials systems.

Using machine learning to classify the immunosuppressive activity of per- and polyfluoroalkyl substances

Per- and polyfluoroalkyl substances (PFASs), one of the persistent organic pollutants, have immunosuppressive effects. The evaluation of this effect has been the focus of regulatory toxicology. In this investigation, 146 PFASs (immunosuppressive or nonimmunosuppressive) and corresponding concentration gradients were collected from literature, and their structures were characterized by using Dragon descriptors. Feature importance analysis and stepwise feature elimination are used for feature selection. Three machine learning (ML) methods, namely Random Forest (RF), Extreme Gradient Boosting Machine (XGB), and Categorical Boosting Machine (CB), were utilized for model development. The model interpretability was explored by feature importance analysis and correlation analysis. The findings indicated that the three models developed have exhibited excellent performance. Among them, the best-performing RF model has an average AUC score of 0.9720 for the testing set. The results of the feature importance analysis demonstrated that concentration, SpPosA_X, IVDE, R2s, and SIC2 were the crucial molecular features. Applicability domain analysis was also performed to determine reliable prediction boundaries for the model. In conclusion, this study is the first application of ML models to investigate the immunosuppressive activity of PFASs. The variables used in the models can help understand the mechanism of the immunosuppressive activity of PFASs, allow researchers to more effectively assess the immunosuppressive potential of a large number of PFASs, and thus better guide environmental and health risk assessment efforts.

Development and validation of an artificial intelligence model for predicting de novo distant bone metastasis in breast cancer: a dual-center study

ObjectiveBreast cancer has become the most prevalent malignant tumor in women, and the occurrence of distant metastasis signifies a poor prognosis. Utilizing predictive models to forecast distant metastasis in breast cancer presents a novel approach. This study aims to utilize readily available clinical data and advanced machine learning algorithms to establish an accurate clinical prediction model. The overall objective is to provide effective decision support for clinicians.MethodsData from 239 patients from two centers were analyzed, focusing on clinical blood biomarkers (tumor markers, liver and kidney function, lipid profile, cardiovascular markers). Spearman correlation and the least absolute shrinkage and selection operator regression were employed for feature dimension reduction. A predictive model was built using LightGBM and validated in training, testing, and external validation cohorts. Feature importance correlation analysis was conducted on the clinical model and the comprehensive model, followed by univariate and multivariate regression analysis of these features.ResultsThrough internal and external validation, we constructed a LightGBM model to predict de novo bone metastasis in newly diagnosed breast cancer patients. The area under the receiver operating characteristic curve values of this model in the training, internal validation test, and external validation test1 cohorts were 0.945, 0.892, and 0.908, respectively. Our validation results indicate that the model exhibits high sensitivity, specificity, and accuracy, making it the most accurate model for predicting bone metastasis in breast cancer patients. Carcinoembryonic Antigen, creatine kinase, albumin-globulin ratio, Apolipoprotein B, and Cancer Antigen 153 (CA153) play crucial roles in the model’s predictions. Lipoprotein a, CA153, gamma-glutamyl transferase, α-Hydroxybutyrate dehydrogenase, alkaline phosphatase, and creatine kinase are positively correlated with breast cancer bone metastasis, while white blood cell ratio and total cholesterol are negatively correlated.ConclusionThis study successfully utilized clinical blood biomarkers to construct an artificial intelligence model for predicting distant metastasis in breast cancer, demonstrating high accuracy. This suggests potential clinical utility in predicting and identifying distant metastasis in breast cancer. These findings underscore the potential prospect of developing economically efficient and readily accessible predictive tools in clinical oncology.

Machine learning approaches for predicting mechanical properties in additive manufactured lattice structures

This study examines the mechanical performance of various lattice structures, highlighting the roles of geometric configurations, material properties, and processing conditions. Through advance feature importance analysis and correlation heatmaps, key determinants of mechanical behaviour such as lattice volume, surface roughness, micro-Vickers hardness, and lattice dimensions are identified. The findings reveal that lattice volume and surface roughness are the most significant predictors of displacement, accounting for 24.29 % and 23.71 % of the predictive power, respectively. An inverse relationship between micro-Vickers hardness and displacement emphasizes the need for material hardness optimization in design processes. Scatterplot analyses show complex interactions between surface roughness and micro-Vickers hardness across different conditions. Gyroid and BCC lattices exhibit inverse linear trends, while honeycomb and diamond display distinct linear and horizontal patterns, respectively. These complexities necessitate advanced analytical techniques like machine learning to capture and predict the mechanical behaviours of lattice structures effectively. Machine learning’s ability to handle high-dimensional data and identify non-linear relationships is crucial for accurate predictive models. The study also assesses the impact of post-processing conditions, indicating that stress relief and heat treatment enhances structural integrity and optimizes the material microstructure. This research provides a framework for designing and optimizing lattice structures, guiding informed decisions to meet performance standards.

A cross-omics data analysis strategy for metabolite-microbe pair identification.

Given the pivotal roles of metabolomics and microbiomics, numerous data mining approaches aim to uncover their intricate connections. However, the complex many-to-many associations between metabolome-microbiome profiles yield numerous statistically significant but biologically unvalidated candidates. To address these challenges, we introduce BiOFI, a strategic framework for identifying metabolome-microbiome correlation pairs (Bi-Omics). BiOFI employs a comprehensive scoring system, incorporating intergroup differences, effects on feature correlation networks, and organism abundance. Meanwhile, it establishes a built-in database of metabolite-microbe-KEGG functional pathway linking relationships. Furthermore, BiOFI can rank related feature pairs by combining importance scores and correlation strength. Validation on a dataset of cesarean-section infants confirms the strategy's validity and interpretability. The BiOFI R package is freely accessible at https://github.com/chentianlu/BiOFI.

Integration of the balanced scorecard and FAO SAFA for assessing the sustainability of horticultural production in Jawa Barat

Abstract The agricultural sector is a vital component of Indonesia’s economy. However, agricultural production in Jawa Barat, particularly in horticulture, is facing various sustainability challenges. It is crucial to adopt a sustainable approach to agricultural production. This study aims to develop the Balanced Scorecard (BSC) framework to enhance the sustainability of horticultural production in Jawa Barat, using the FAO Sustainability Assessment of Food and Agriculture (SAFA) Framework. A focus group discussion (FGD) was conducted with 68 horticultural farmers representing different regions and horticultural commodities in Jawa Barat. During the FGD, participants rated their familiarity with SAFA Framework indicators and assessed their importance. Frequency analysis was performed on the collected data to determine familiarity and importance levels and correlation analysis using the R method. This research reveals that indicators related to community investment, biodiversity, and renewable energy received lower recognition, suggesting a need for increased emphasis in these areas. The correlation analysis revealed a positive link between Finance and Customer dimensions, highlighting the importance of financial management for customer satisfaction. Addressing these findings will help enhance sustainability and bridge gaps in horticultural practices in Jawa Barat. The findings will support sustainable agricultural practices, enhance decision-making, and promote the long-term viability of the horticultural sector

The Influence of Climate Change on the Distribution of Hibiscus mutabilis in China: MaxEnt Model-Based Prediction.

Our study utilized 374 geographical distribution records of H. mutabilis and 19 bioclimatic factors, employing the MaxEnt model and the Geographic Information System (ArcGIS). The key environmental variables influencing the suitable distribution areas of H. mutabilis were analyzed through the comprehensive contribution rate, permutation importance, and Pearson correlation coefficient. Based on this analysis, the contemporary and future suitable distribution areas and their extents were predicted. The results indicate that the key limiting factor affecting the suitable distribution areas of H. mutabilis is the precipitation of the driest month (bio14), with secondary factors being annual precipitation (bio12), annual mean temperature (bio1), and annual temperature range (bio7). Under contemporary climate conditions, the total suitable area for H. mutabilis is approximately 2,076,600 km2, primarily concentrated in the tropical and subtropical regions of southeastern China. Under low-to-medium-emission scenarios (SSP1-2.6, SSP2-4.5), the total suitable area of H. mutabilis shows a trend of first decreasing and then increasing compared to the current scenario. In contrast, under high-emission scenarios (SSP5-8.5), it exhibits a trend of first increasing and then decreasing. The spatial pattern changes indicate that the retention rate of suitable areas for H. mutabilis ranges from 95.28% to 99.28%, with the distribution centers primarily located in Hunan and Guizhou provinces, showing an overall migration trend towards the west and north. These findings suggest that H. mutabilis possesses a certain level of adaptability to climate change. However, it is crucial to consider regional drought and sudden drought events in practical cultivation and introduction processes. The results of our study provide a scientific basis for the rational cultivation management, conservation, and utilization of germplasm resources of H. mutabilis.

Leveraging Various Feature Selection Methods for Churn Prediction Using Various Machine Learning Algorithms

This study aims to examine the effect of customer experience on customer retention at DQLab Telco, using machine learning techniques to predict customer churn. The study uses a dataset of 6590 customers of DQLab Telco, which contains various features related to their service usage and satisfaction. The data includes various features such as gender, tenure, phone service, internet service, monthly charges, and total charges. These features represent the demographic and service usage information of the customers. The study applies several feature selection methods, such as ANOVA, Recursive Feature Elimination, Feature Importance, and Pearson Correlation, to select the most relevant features for churn prediction. The study also compares three machine learning algorithms, namely Logistic Regression, Random Forest, and Gradient Boosting, to build and evaluate the prediction models. This study finds that Logistic Regression without feature selection achieves the highest accuracy of 79.47%, while Random Forest with Feature Importance and Gradient Boosting with Recursive Feature Elimination achieve accuracy of 77.60% and 79.86%, respectively. The study also identifies the features influencing customer churn most, such as monthly charges, tenure, partner, senior citizen, internet service, paperless billing, and TV streaming. The study provides valuable insights for DQLab Telco in developing customer churn reduction strategies based on predictive models and influential features. The study also suggests that feature selection and machine learning algorithms play a vital role in improving the accuracy of churn prediction and should be customized according to the data context.

Contribution of Atmospheric Factors in Predicting Sea Surface Temperature in the East China Sea Using the Random Forest and SA-ConvLSTM Model

Atmospheric forcings are significant physical factors that influence the variation of sea surface temperature (SST) and are often used as essential input variables for ocean numerical models. However, their contribution to the prediction of SST based on machine-learning methods still needs to be tested. This study presents a prediction model for SST in the East China Sea (ECS) using two machine-learning methods: Random Forest and SA-ConvLSTM algorithms. According to the Random Forest feature importance scores and correlation coefficients R, 2 m air temperature and longwave radiation were selected as the two most important key atmospheric factors that can affect the SST prediction performance of machine-learning methods. Four datasets were constructed as input to SA-ConvLSTM: SST-only, SST-T2m, SST-LWR, and SST-T2m-LWR. Using the SST-T2m and SST-LWR, the prediction skill of the model can be improved by about 9.9% and 9.43% for the RMSE and by about 8.97% and 8.21% for the MAE, respectively. Using the SST-T2m-LWR dataset, the model’s prediction skill can be improved by 10.75% for RMSE and 9.06% for MAE. The SA-ConvLSTM can represent the SST in ECS well, but with the highest RMSE and AE in summer. The findings of the presented study requires much more exploration in future studies.

Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in Critically Ill Elderly Patients During Hospitalization: Internet-Based and Interpretable Model Study.

Acute kidney disease (AKD) affects more than half of critically ill elderly patients with acute kidney injury (AKI), which leads to worse short-term outcomes. We aimed to establish 2 machine learning models to predict the risk and prognosis of AKD in the elderly and to deploy the models as online apps. Data on elderly patients with AKI (n=3542) and AKD (n=2661) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were used to develop 2 models for predicting the AKD risk and in-hospital mortality, respectively. Data collected from Xiangya Hospital of Central South University were for external validation. A bootstrap method was used for internal validation to obtain relatively stable results. We extracted the indicators within 24 hours of the first diagnosis of AKI and the fluctuation range of some indicators, namely delta (day 3 after AKI minus day 1), as features. Six machine learning algorithms were used for modeling; the area under the receiver operating characteristic curve (AUROC), decision curve analysis, and calibration curve for evaluating; Shapley additive explanation (SHAP) analysis for visually interpreting; and the Heroku platform for deploying the best-performing models as web-based apps. For the model of predicting the risk of AKD in elderly patients with AKI during hospitalization, the Light Gradient Boosting Machine (LightGBM) showed the best overall performance in the training (AUROC=0.844, 95% CI 0.831-0.857), internal validation (AUROC=0.853, 95% CI 0.841-0.865), and external (AUROC=0.755, 95% CI 0.699-0.811) cohorts. In addition, LightGBM performed well for the AKD prognostic prediction in the training (AUROC=0.861, 95% CI 0.843-0.878), internal validation (AUROC=0.868, 95% CI 0.851-0.885), and external (AUROC=0.746, 95% CI 0.673-0.820) cohorts. The models deployed as online prediction apps allowed users to predict and provide feedback to submit new data for model iteration. In the importance ranking and correlation visualization of the model's top 10 influencing factors conducted based on the SHAP value, partial dependence plots revealed the optimal cutoff of some interventionable indicators. The top 5 factors predicting the risk of AKD were creatinine on day 3, sepsis, delta blood urea nitrogen (BUN), diastolic blood pressure (DBP), and heart rate, while the top 5 factors determining in-hospital mortality were age, BUN on day 1, vasopressor use, BUN on day 3, and partial pressure of carbon dioxide (PaCO2). We developed and validated 2 online apps for predicting the risk of AKD and its prognostic mortality in elderly patients, respectively. The top 10 factors that influenced the AKD risk and mortality during hospitalization were identified and explained visually, which might provide useful applications for intelligent management and suggestions for future prospective research.

Dynamic multi-label feature selection algorithm based on label importance and label correlation

Multi-label distribution is a popular direction in current machine learning research and is relevant to many practical problems. In multi-label learning, samples are usually described by high-dimensional features, many of which are redundant or invalid. This paper proposes a multi-label static feature selection algorithm to solve the problems caused by high-dimensional features of multi-label learning samples. This algorithm is based on label importance and label relevance, and improves the neighborhood rough set model. One reason for using neighborhood rough sets is that feature selection using neighborhood rough sets does not require any prior knowledge of the feature space structure. Another reason is that it does not destroy the neighborhood and order structure of the data when processing multi-label data. The method of mutual information is used to achieve the extension from single labels to multiple labels in the multi-label neighborhood; through this method, the label importance and label relevance of multi-label data are connected. In addition, in the multi-label task scenario, features may be interdependent and interrelated, and features often arrive incrementally or can be extracted continuously; we call these flow features. Traditional static feature selection algorithms do not handle flow features well. Therefore, this paper proposes a dynamic feature selection algorithm for flow features, which is based on previous static feature selection algorithms. The proposed static and dynamic algorithms have been tested on a multi-label learning task set and the experimental results show the effectiveness of both algorithms.

Patterns of Socioeconomic Marginalization among People Who Use Drugs: A Gender-Stratified Repeated Measures Latent Class Analysis.

Socioeconomic factors are important correlates of drug use behaviors and health-related outcomes in people who use drugs (PWUD) residing in urban areas. However, less is known about the complex overlapping nature of socioeconomic conditions and their association with a range of individual, drug use, and health-related factors in men and women who use drugs. Data were obtained from two community-recruited prospective cohorts of PWUD. Using a gender-stratified approach, we conducted repeated measures latent class analyses (RMLCA) to identify discrete latent socioeconomic subgroups. Multivariable generalized estimating equations were then used to identify correlates of class membership. Between June 2014 and December 2018, RMLCA of 9844 observations from 1654 participants revealed five distinct patterns of socioeconomic status for both men and women. These patterns were primarily distinguished by variations in income, material and housing security, income generation activity, exposure to violence, criminal justice involvement, and police contact. Across gender, progressive increases in exposure to multiple dimensions of socioeconomic disadvantage were found to be associated with frequent use of opioids and stimulants, accessing social services, and being hepatitis C virus antibody-positive. Similar but less congruent trends across gender were observed for age, binge drug use, engagement with opioid agonist therapy, and living with HIV. Gendered patterns of multiple and overlapping dimensions of socioeconomic adversity aligned with patterns of frequent drug use and health-related concerns, highlighting priority areas for gender-inclusive, multilevel responses to mitigate health disparities and meet the diverse socioeconomic needs of urban-dwelling men and women who use drugs.

Perceptions of bias in HIV prevention services, happiness with social support, and anticipated PrEP stigma among Black and Latine/x sexual and gender diverse individuals

ABSTRACT Although pre-exposure prophylaxis (PrEP) is a highly effective preventive treatment for HIV, anticipated PrEP stigma can hinder uptake. Perceptions of bias in HIV prevention and evaluations (e.g., happiness) tied to social support among Black and Latine/x sexual and gender diverse (SGD) individuals could be important correlates of anticipated PrEP stigma. To further this line of inquiry, a national sample of 872 Black and Latine/x SGD individuals who had and had never taken PrEP (Mage = 25.1, SD = 2.8) reported how they perceived HIV prevention and how happy they were with their social support. Multivariable linear regressions revealed that greater perceptions of bias in HIV prevention services were associated with higher anticipated PrEP stigma among Black and Latine/x SGD individuals who have never taken PrEP. Greater happiness with friend support was associated with lower PrEP stigma, whereas greater happiness with family support was associated with higher PrEP stigma among individuals who have taken PrEP. Findings highlight the need for PrEP and HIV interventions to address the intersectional stigma attached to prevention and for researchers to understand how evaluations of social support may contribute to stigma among Black and Latine/x SGD individuals.

Social Empowerment and Its Effect on Poverty Alleviation for Sustainable Development among Women Entrepreneurs in the Nigerian Agricultural Sector

Despite the fact that the issue of female poverty is widespread, continuous attempts are made to combat it and advance women’s empowerment. To achieve the goals of sustainable development, such as eradicating poverty, attaining gender equality, promoting good jobs and economic growth, and eliminating inequities, creative strategies must be developed. This study focused on the Nigerian Youth and Women Farmers Association in order to examine the effect of social empowerment on alleviating poverty in Nigeria’s agricultural sector. Out of the 353 issued questionnaires, 335 were returned and used in this study’s investigation. The structural equation model with partial least squares (SEM-PLS) was used to analyse the acquired data. The results showed an important correlation between social empowerment and reductions in poverty among women working in the agricultural sector. This highlights how crucial it is to work together, provide resources, and extend support in order to empower women socially and foster an atmosphere that supports their social and economic advancement. This research recommends that lawmakers, organisations, and governmental entities actively support the empowerment of women in the agricultural sector in order to encourage sustainable farming practices among female entrepreneurs.

Educational proposal to strengthen social motor skills in primary school students

School coexistence is a relevant topic of research and intervention in educational institutions as it is a component of measuring the levels of student learning achievement. The objective of this research was to determine the impact of socio-motor skills in school coexistence in primary school students. The type of research is non-experimental, correlational, causal, and quantitative, and cross-sectional. The population consisted of primary school students and the sample consisted of 185 students. The results indicated that there is an important correlation between children's socio-motor skills and their school coexistence. These elements highlight the importance of integrating programs and activities into the school curriculum that encourage the development of socio-motor skills from an early age.

Linkages between atmospheric rivers and humid heat across the United States

Abstract. The global increase in atmospheric water vapor due to climate change tends to heighten the dangers associated with both humid heat and heavy precipitation. Process-linked connections between these two extremes, particularly those which cause them to occur close together in space or time, are of special concern for impacts. Here we investigate how atmospheric rivers relate to the risk of summertime humid heat in the United States. We find that the hazards of atmospheric rivers and humid heat often occur in close proximity, most notably across the northern third of the United States. In this region, high levels of water vapor – resulting from the spatially organized horizontal moisture plumes that characterize atmospheric rivers – act to amplify humid heat, generally during the transition from dry high-pressure ridge conditions to wet low-pressure trough conditions. In contrast, the US Southeast, Southwest, and Northwest tend to experience atmospheric rivers and humid heat separately, representing an important negative correlation of joint risk.

Psychosocial correlates of physical activity in cancer survivors: a systematic review and meta-analysis.

Physical activity (PA) is a non-pharmacological approach to optimize health benefits in cancer survivors and is recommended as part of care. However, most cancer survivors fail to meet PA recommendations. The current systematic review and meta-analysis aimed to identify psychosocial correlates of free-living PA in cancer survivors. Three electronic databases were searched (PubMed, PsycINFO, and SportDiscus). Meta-analyses were conducted for psychosocial correlates tested ≥ 3 times. Sixty-four articles were included. Eighty-eight different free-living PA correlates were identified. Meta-analyses (n = 32 studies) tested 23 PA correlates, of which 16 were significant (p < 0.05). Larger effect sizes (0.30 < ES > 0.45) were found for exercise self-efficacy, perceived behavioral control, intention, lower perceived barriers for exercise, enjoyment, perceived PA benefits, and attitudes. Small-to-moderate effects (0.18 < ES < 0.22) were found for subjective norms, physical functioning, quality of life, depression, and mental health. These findings were generally in line with narrative results. This systematic review highlights important psychosocial correlates of free-living PA that can be targeted in future PA promotion interventions for cancer survivors. Constructs mainly from SCT and TPB were the most studied and appear to be associated with free-living PA in this population. However, we cannot currently assert which frameworks might be more effective. Further studies of better methodological quality, per correlate and theory, exploring longer-term associations and across different types of cancer, are needed. Having higher exercise self-efficacy, perceived behavioral control, intention, enjoyment and perceived PA benefits, more positive attitudes towards PA, and lower perceived barriers for exercise, can help increase PA in cancer survivors.