Dealing with multiple local modalities in latent class profile analysis

Earlier age of drinking is a well-known predictor for a variety of adverse public health consequences in the United States and worldwide. In longitudinal research on early-onset drinkers, a great deal of attention has been paid to the identification of subgroups of individuals who follow similar sequential patterns of drinking behaviours. However, research on the sequential development of drinking behaviour can be challenging in part because it may not be possible to directly observe the particular drinking behaviour stage at a given point in time. To address this difficulty, one can use a latent class analysis (LCA) approach, which provides a set of principles for the systematic identification of homogeneous subgroups of individuals. We apply an LCA approach in an investigation of stage-sequential patterns of drinking behaviours among early-onset drinkers from early to late adolescence, using data from the 'National Longitudinal Survey of Youth 1997.' In this work, an identification procedure is used to sort different patterns of drinking behaviours into a small number of classes, based on responses to questions about drinking at each measurement occasion; with class assignment, next the class sequencing of early-onset drinkers over the entire set of time points is evaluated in order to identify two or more homogeneous subgroups. A condition to be satisfied is that all early-onset drinkers in a subgroup should exhibit a similar sequence of class memberships over time. This approach uncovers four common drinking behaviours in early-onset drinkers over three measurements from 1997 through 2003. The sequences of drinking behaviours can be grouped into three groups of sequential patterns representing the most probable progression of early-onset drinking behaviours.

PurposeResearch on symptom clusters in oncology is progressing, but knowledge gaps remain. One question is whether the number and types of symptom subgroups (i.e., latent classes) differ based on cancer diagnosis. The purpose of this study was to: (1) identify and compare latent class subgroups based on four highly prevalent symptoms (pain, fatigue, sleep disturbance, and depression), and (2) examine the differences in sociodemographic and clinical factors in the identified latent classes across the seven cancer types (i.e., prostate, non-small cell lung, non-Hodgkin’s lymphoma, breast, uterine, cervical, and colorectal cancer).MethodsThis study is a cross-sectional secondary analysis of data obtained from the My-Health study in partnership with four Surveillance, Epidemiology, and End Results (SEER) cancer registries located in California (two), Louisiana, and New Jersey. The sample included 4,762 cancer survivors 6-13 months following diagnosis of one of the seven cancer types mentioned. Latent class profile analysis was used.ResultsSubjects were primarily young (59% age 21-64 years), Caucasian (41%), married/cohabitating (58%) and unemployed (55%). The number and types of symptom subgroups varied across these seven cancer populations: four-subgroups were the common in prostate, lung, non-Hodgkin’s lymphoma, and breast cancer survivors. Unmarried, low education, and unemployment status were associated with high risk of symptom burden across the cancer types.ConclusionIdentifying symptom subgroups by cancer diagnosis has the potential to develop innovative and effective targeted interventions in cancer survivors. Further research is needed to establish extensive knowledge in symptom clustering between treatment regimens, and short-term and long-term cancer survivors.

OBJECTIVES: Derive latent profiles of accelerometry-measured moderate-vigorous physical activity (MVPA) for Hispanic/Latino adults, examine associations between latent MVPA profiles and neurocognition, and describe profiles via self-reported MVPA. METHODS: Complex survey design methods were applied to cross-sectional data from 7,672 adults ages 45-74 years in the Hispanic Community Health Study/Study of Latinos (HCHS/SOL; 2008-2011). MVPA was measured via hip-worn accelerometers. Latent profile analysis was applied to derive latent MVPA profiles (minutes/day of week). Neurocognition was assessed with the Brief-Spanish English Verbal Learning Test (B-SEVLT) Sum, B-SEVLT Recall, Controlled Oral Word Association Test (word fluency), and Digit Symbol Substitution (DSS) test. All tests were z-scored, and a global neurocognition score was generated by averaging across scores. Survey linear regression models were used to examine associations between latent MVPA profiles and neurocognitive measures. Self-reported MVPA domains were estimated (occupational, transportation, and recreational) for each latent profile. RESULTS: Four latent MVPA profiles from the overall adult target population (18-74 years) were derived and putatively labeled: No MVPA, low, moderate, and high. Only the high MVPA profile (compared to moderate) was associated with lower global neurocognition. Sensitivity analyses using latent MVPA profiles with only participants aged 45-74 years showed similar profiles, but no associations between latent MVPA profiles and neurocognition. The occupational MVPA domain led in all latent MVPA profiles. DISCUSSION: We found no consistent evidence to link accelerometry-measured MVPA profiles to neurocognitive function. Research to better characterize the role of high occupational MVPA in relation to neurocognition among Hispanic/Latino adults are needed.

Latent profile analysis (LPA) has become a popular statistical method for modeling unobserved population heterogeneity in cross-sectionally sampled data, but very few empirical studies have examined the question of how well enumeration indexes accurately identify the correct number of latent profiles present. This Monte Carlo simulation study examined the ability of several classes of enumeration indexes to correctly identify the number of latent population profiles present under 3 different research design conditions: sample size, the number of observed variables used for LPA, and the separation distance among the latent profiles measured in Mahalanobis D units. Results showed that, for the homogeneous population (i.e., the population has k = 1 latent profile) conditions, many of the enumeration indexes used in LPA were able to correctly identify the single latent profile if variances and covariances were freely estimated. However, for a heterogeneous population (i.e., the population has k = 3 distinct latent profiles), the correct identification rate for the enumeration indexes in the k = 3 latent profile conditions was typically very low. These results are compared with the previous cross-sectional mixture modeling studies, and the limitations of this study, as well as future cross-sectional mixture modeling and enumeration index research possibilities, are discussed.

Identification of Distinct Symptom Profiles in Cancer Patients Using a Pre-Specified Symptom Cluster.

Identifying the heterogeneity of self-advocacy in patients with gynecological cancer: a latent class profile analysis.

BackgroundThe ability to thrive at work has been demonstrated to be closely linked to the development of nurses.Effective utilization of strengths and maintaining hope are essential elements for clinical nurses’ ability to flourish in their roles. Nevertheless, the relationship between strengths use, hope, and thriving at work remains underexplored. This study aimed to identify distinct subgroups of clinical nurses based on their strengths use and to examine the mediating effect of hope between strengths use and thriving at work. The findings are intended to inform clinical managers on strategies to enhance nurses’ work performance and care quality.MethodsA convenience sample of 568 clinical nurses from two tertiary hospitals in Guangzhou City, Guangdong Province, China, was recruited between January and March 2024. The survey collected sociodemographic data and included the Adult Dispositional Hope Scale, Strengths Use Scale, and Thriving at Work Scale. Potential categories of nurse strengths use characteristics were identified using potential profile analysis, and potential relationships between variables were determined using Pearson correlation analysis, Bayesian factor robustness analyses, and Mediation analysis.ResultsLPA identified three distinct groups based on strengths use: low (30.8%), moderate (64.9%), and high (13.2%).The significant mediating effect of hope in the relationship between strengths use based on latent profile analysis and thriving at work was observed (SE = 0.61,95%CI = -10.01, -7.62; SE = 0.76,95%CI = -18.91, -15.91, respectively).ConclusionsThere exists heterogeneity in nurses’ strengths use. Hope plays a significant role in mediating the relationship between strengths use and thriving at work. It is recommended that nursing administrators or leaders pay attention to differences in individual levels of strengths use, encourage strengths-based practices and design interventions that foster hope, thereby promoting greater thriving in their professional roles.

BackgroundThe widespread use of digital technologies has raised growing concerns about their impact on mental health. While self-regulation has been proposed as a protective factor, little is known about how distinct psychological profiles based on self-regulatory and technology use patterns relate to psychological distress. Person-centered approaches, such as latent profile analysis, may offer deeper insights, particularly in underrepresented populations.ObjectiveThis study aimed to identify latent psychological profiles based on self-regulation, nomophobia (fear of being without a phone), and problematic use of the internet and social media (defined by behavioral symptoms), to examine their associations with general psychological distress and the presence of emotional symptoms in a Colombian sample. Additionally, the predictive roles of age and gender in class membership were explored.MethodsParticipants were recruited through a convenience sampling strategy aimed at ensuring heterogeneity of the sample in terms of age and gender. A total of 453 participants aged 12 to 57 years (mean 21.03, SD 8.41 years; 257/453, 56.7% female) completed validated measures of self-regulation (Abbreviated Self-Regulation Questionnaire), nomophobia (Nomophobia Questionnaire), internet and social media use (MULTICAGE-TIC, a multidomain screening questionnaire based on the CAGE framework), and psychological distress (General Health Questionnaire-12). Latent profile analysis was conducted using standardized scores of continuous variables. Model fit was assessed using the Bayesian information criterion, entropy, and bootstrapped likelihood ratio test. Differences in psychological distress scores across latent classes were examined through variance analysis (ANOVA) and regression models. A multinomial logistic regression tested the predictive value of age and gender for class membership.ResultsThe optimal solution revealed 4 distinct latent profiles (entropy=0.85). Class 1 showed high self-regulation and low problematic technology use, displaying the lowest psychological distress scores. Class 2 presented moderate levels across all indicators but the highest level of psychological distress. Classes 3 and 4 showed mixed patterns. Class 3 (higher information and communication technology [ICT] use and lower self-regulation) exhibited lower distress than class 2, whereas class 4 (younger individuals with low self-regulation and moderately high ICT use) showed higher distress than class 3. Psychological distress differed significantly across profiles (ANOVA, P<.001). Age and gender predicted class membership. Older males were more likely to belong to class 1, and younger females were more likely to be classified into classes 3 and 4.ConclusionsLatent profile analysis identified distinct configurations of digital behavior, self-regulation, and psychological distress. Self-regulation consistently differentiated profiles with lower distress scores, suggesting its relevance for understanding how individuals manage ICT use. These findings support the value of person-centered approaches to characterize heterogeneous patterns of technology-related behaviors. The study provides evidence from a Spanish-speaking sample, offering a novel perspective on psychological distress and problematic technology use in contexts that remain underrepresented in the literature.

Latent profile and network analysis of anxiety and depressive symptoms among teachers.

Nomophobia (NMP) is a contemporary digital ailment referring to the improper utilization of smartphones which can have significant impacts on the physical and mental health of college students. However, as a result of unclear cutoff points, the proportion of people with NMP may be exaggerated. This study therefore aimed to determine the critical value of NMP and assess the extentto which Chinese college students are impacted by NMP using the Nomophobia Questionnaire (NMP-Q). Latent profile analysis (LPA) and the receiver operating characteristic curve (ROC) were combined to determine the critical value based on NMP-Q scores using a large sample of 3,998 college students (Mage = 20.58; SD = 1.87). Based on latent profile (i.e., at-risk NMP group), ROC revealed an optimal cut-off point of 73 (Sensitivity = 0.965, Specificity = 0.970, Accuracy = 0.968, AUC = 99.60%, Youden's index = 0.935), and the percentage of NMP students being 28.04%, with 1,121 participants identified as positive cases (probable cases). Positive cases were found to exhibit more severe depression and anxiety symptoms, with a higher proportion of females were observed in the positive group (N = 829; 73.95%). These findings provide evidence that the proportion of NMP individuals may have been overestimated in the past. Furthermore, this study helps to validate the NMP-Q as a valid tool to identify NMP in college-aged individuals.

Many diseases show dichotomous phenotypic variation but do not follow a simple Mendelian pattern of inheritance. Variances of these binary diseases are presumably controlled by multiple loci and environmental variants. A least-squares method has been developed for mapping such complex disease loci by treating the binary phenotypes (0 and 1) as if they were continuous. However, the least-squares method is not recommended because of its ad hoc nature. Maximum Likelihood (ML) and Bayesian methods have also been developed for binary disease mapping by incorporating the discrete nature of the phenotypic distribution. In the ML analysis, the likelihood function is usually maximized using some complicated maximization algorithms (e.g. the Newton-Raphson or the simplex algorithm). Under the threshold model of binary disease, we develop an Expectation Maximization (EM) algorithm to solve for the maximum likelihood estimates (MLEs). The new EM algorithm is developed by treating both the unobserved genotype and the disease liability as missing values. As a result, the EM iteration equations have the same form as the normal equation system in linear regression. The EM algorithm is further modified to take into account sexual dimorphism in the linkage maps. Applying the EM-implemented ML method to a four-way-cross mouse family, we detected two regions on the fourth chromosome that have evidence of QTLs controlling the segregation of fibrosarcoma, a form of connective tissue cancer. The two QTLs explain 50-60% of the variance in the disease liability. We also applied a Bayesian method previously developed (modified to take into account sex-specific maps) to this data set and detected one additional QTL on chromosome 13 that explains another 26% of the variance of the disease liability. All the QTLs detected primarily show dominance effects.

IntroductionConsistently predicting adverse outcomes of long-distance running, such as running-related injuries (RRIs) and chronic fatigue, has proven to be a complicated matter. However, research suggests that a stronger focus on psychological factors of runners might provide further insights. Consequently, in this study, we explored the interplay between self-regulatory coping strategies and motivational aspects. Using a person-centered approach, we investigated whether latent psychological profiles of runners were associated with RRIs and chronic fatigue. MethodsQuestionnaire data were gathered from Dutch recreational long-distance runners (N = 425) using a cross-sectional design. We determined whether specific psychological combinations (i.e., latent profiles) based on coping strategies (i.e., running-related resources and recovery) and motivational aspects (i.e., harmonious and obsessive passion) could be distinguished using latent profile analysis (LPA). The resulting profiles were tested for their associations with RRIs and chronic fatigue. ResultsLPA revealed three different psychological risk profiles, termed the ‘low-risk’, ‘medium-risk’, and ‘high-risk’ profile. The low-risk profile showed low scores on obsessive passion and high scores on all recovery dimensions, whereas the high-risk profile resembled the opposite pattern. Furthermore, the low-risk profile showed significantly fewer RRIs and lower chronic fatigue scores than the high-risk profile. DiscussionThe results reveal that (1) patterns of passion and coping strategies interact in defining different profiles and (2) that such profiles are indeed linked to RRIs and chronic fatigue. Utilizing profiles might enable targeted intervention and more effective preventative measures by pinpointing at-risk runners. Specific combinations of psychological aspects, as reflected by our profiles, thus appear a worthwhile direction to consider in understanding RRIs and chronic fatigue in long-distance running.

BACKGROUND The widespread use of digital technologies—especially the internet and social media—has raised growing concerns about their impact on mental health. While self-regulation has been proposed as a protective factor, little is known about how distinct psychological profiles based on self-regulatory and technology use patterns relate to well-being. Person-centered approaches such as Latent Profile Analysis (LPA) may offer deeper insights, particularly in underrepresented populations. OBJECTIVE This study aimed to identify latent psychological profiles based on self-regulation, nomophobia, and problematic use of the internet and social media and to examine their association with mental health outcomes in a Colombian sample. Additionally, the predictive roles of age and gender on class membership were explored. Methods METHODS 453 participants aged 12 to 57 years (M = 21.03, SD = 8.41; 57% female) completed validated measures of self-regulation, nomophobia, internet use, social media use, and psychological health (GHQ-12). Latent Profile Analysis was conducted using standardized scores of continuous variables. Model fit was assessed using BIC, entropy, and BLRT. Differences in psychological health across latent classes were examined through ANOVA and regression models. A multinomial logistic regression tested the predictive value of age and gender on class membership. RESULTS The optimal solution revealed four distinct latent profiles (entropy = 0.85): Class 1 (adaptive): high self-regulation, low nomophobia, and low ICT use; presented the best psychological health. Class 4 (vulnerable): low self-regulation, high nomophobia, and high ICT use; reported the poorest health outcomes. Classes 2 and 3 displayed intermediate profiles, with Class 3 showing slightly better health than Class 4. Differences in psychological health across classes were statistically significant (ANOVA, p &lt; .001). Age and gender were significant predictors of class membership: younger females were more likely to belong to Class 1, whereas older males were more likely to be classified into Classes 3 and 4. CONCLUSIONS LPA enabled the identification of distinct psychological profiles that vary in mental health outcomes and digital vulnerability. Self-regulation emerged as a central protective factor, suggesting the importance of tailored digital interventions to enhance regulatory capacities. These findings reinforce the value of person-centered approaches and highlight the need for scalable strategies to mitigate the mental health risks associated with problematic ICT use in Spanish-speaking populations.

Objectives The purpose of this study was to classify latent profiles based on parenting characteristics perceived by 7th-grade students and to examine the influence of parental attachment as a predictive factor. Additionally, the study aimed to identify differences in reading habits and learning factors, such as academic understanding, academic stress, and self-regulated learning, across the latent profiles. Methods This study utilized data from 1,328 adolescents who participated in the 14th wave of the Korean Children and Youth Panel Survey (KCYPS). Using SPSS 25.0 and Mplus 8.11, latent profile analysis (LPA) was conducted based on adolescents' perceptions of parenting characteristics. The study then examined whether there were significant differences in the average levels of reading habits, academic understanding, academic stress, and self-regulated learning among the identified latent profiles. Additionally, the study tested whether the parental attachment factors—communication, alienation, and trust—affect the parenting characteristics of achievement pressure, rational explanation, and parental monitoring in 7th-grade students. Results The results of the study indicated that, first, the latent profiles of parenting characteristics perceived by adolescents were classified into three distinct groups. Second, parental attachment was found to have a significant influence on the classification of these profiles based on adolescents' perceptions of parenting characteristics. Third, significant differences were observed in learning factors according to the perceived parenting characteristics, with the ‘high parental monitoring group’ scoring the highest. Conclusions This study classified adolescents' perceived parenting characteristics using a person-centered approach through latent profile analysis and revealed parental attachment types that could serve as risk or protective factors. Additionally, it validated the differences in academic understanding, academic stress, and self-regulated learning across the latent profiles. The findings provide implications for interventions in adolescent counseling, parent education, and family counseling.

Traditional approaches to assessing sleep quality in clinical nurses often overlook population heterogeneity and the complex interplay of influencing factors. This study employs Latent Profile Analysis (LPA) and Association Rule Mining (ARM) to identify distinct sleep quality subgroups and uncover key factor combinations, thereby informing targeted intervention strategies. A total of 1,686 nurses from 123 hospitals in Shandong Province were recruited through multistage stratified sampling. LPA was used to classify participants based on seven sleep dimensions from the Pittsburgh Sleep Quality Index (PSQI), while ARM was applied to identify frequent itemsets of sleep disorder triggers. Key influencing factors were further examined using univariate analysis and multivariate logistic regression. Three latent sleep profiles were identified: high (63.11%), moderate (34.10%), and low (2.79%) sleep quality. The low-sleep subgroup was characterized by higher proportions of being unmarried/divorced (42.55%), low monthly income (≤ 3,000 CNY, 42.55%), non-permanent employment (76.60%), and severe psychological distress (44.68%). In contrast, the high-sleep subgroup featured higher rates of being married (85.62%), moderate income (3,001–7,000 CNY, 73.03%), and low psychological distress (51.32%). Key determinants included marital status (OR = 2.153/2.252), income (OR = 9.098), employment type (OR = 1.475), and psychological state (OR = 0.060–0.555). ARM revealed distinct risk combinations: “low income + non-permanent employment” (lift = 3.895) for the low-sleep group; “married + moderate income + non-permanent employment + patient conflict” for the moderate group; and “high income + low psychological distress” buffering night-shift effects in the high-sleep group. By integrating LPA and ARM, this study reveals the multidimensional heterogeneity and interactive mechanisms underlying clinical nurses’ sleep quality. The findings support a stratified intervention framework combining institutional safeguards with precision strategies to enhance sleep health management in nursing populations.