Using Latent Class Analysis to Identify Different Risk Patterns for Patients With Masked Hypertension
Ontology highlight
ABSTRACT:
SUBMITTER: Fu M
PROVIDER: S-EPMC8424076 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Objective: This study aimed to develop machine learning-based prediction models to predict masked hypertension and masked uncontrolled hypertension using the clinical characteristics of patients at a single outpatient visit. Methods: Data were derived from two cohorts in Taiwan. The first cohort included 970 hypertensive patients recruited from six medical centers between 2004 and 2005, which were split into a training set (n = 679), a validation set (n = 146), and a test set (n = 145) for model development and internal validation. The second cohort included 416 hypertensive patients recruited from a single medical center between 2012 and 2020, which was used for external validation. We used 33 clinical characteristics as candidate variables to develop models based on logistic regression (LR), random forest (RF), eXtreme Gradient Boosting (XGboost), and artificial neural network (ANN). Results: The four models featured high sensitivity and high negative predictive value (NPV) in internal validation (sensitivity = 0.914-1.000; NPV = 0.853-1.000) and external validation (sensitivity = 0.950-1.000; NPV = 0.875-1.000). The RF, XGboost, and ANN models showed much higher area under the receiver operating characteristic curve (AUC) (0.799-0.851 in internal validation, 0.672-0.837 in external validation) than the LR model. Among the models, the RF model, composed of 6 predictor variables, had the best overall performance in both internal and external validation (AUC = 0.851 and 0.837; sensitivity = 1.000 and 1.000; specificity = 0.609 and 0.580; NPV = 1.000 and 1.000; accuracy = 0.766 and 0.721, respectively). Conclusion: An effective machine learning-based predictive model that requires data from a single clinic visit may help to identify masked hypertension and masked uncontrolled hypertension.
| S-EPMC8639874 | biostudies-literature
Project description:BackgroundThe heterogeneity of tinnitus is a major challenge for tinnitus research. Even if a complex interaction of many factors is involved in the etiology of tinnitus, hearing loss (HL) has been identified as the most relevant etiologic factor. Here, we used a data-driven approach to identify patterns of hearing function in a large sample of tinnitus patients presenting in a tinnitus clinic.MethodsData from 2,838 patients presenting at the Tinnitus Center of the University Regensburg between 2007 and 2014 have been analyzed. Standard audiometric data were frequency-wise categorized in four categories [a: normal hearing (0-20 dB HL); b: moderate HL (25-50 dB HL; representing outer hair cell loss); c: severe HL (>50 dB HL; representing outer and inner hair cell loss); d: no data available] and entered in a latent class analysis, a statistical method to find subtypes of cases in multivariate categorical data. To validate the clinical relevance of the identified latent classes, they were compared with respect to clinical and demographic characteristics of their members.ResultsThe classification algorithm identified eight distinct latent classes with an excellent separation. Patient classes differed with respect to demographic (e.g., age, gender) and clinical characteristics (e.g., tinnitus location, tinnitus severity, gradual, or abrupt onset, etc.).DiscussionOur results demonstrate that data-driven categorization of hearing function seems to be a promising approach for profiling tinnitus patients, as it revealed distinct subtypes that reflect prototypic forms of HL and that differ in several relevant clinical characteristics.
| S-EPMC5316929 | biostudies-literature
Project description:ObjectivesResearch suggests that abuser risk factors differ across elder mistreatment types, but abuse interventions are not individualized. To move away from assumptions of perpetrator homogeneity and to inform intervention approaches, this study classifies abusers into subtypes according to their behavior profiles.MethodData are from the Older Adult Mistreatment Assessment administered to victims by Adult Protective Service (APS) in Illinois. Latent class analysis was used to categorize abusers (N = 336) using victim and caseworker reports on abusers' harmful and supportive behaviors and characteristics. Multinomial logistic regression was then used to determine which abuser profiles are associated with 4 types of mistreatment-neglect, physical, emotional, and financial-and other sociodemographic characteristics.ResultsAbusers fall into 4 profiles descriptively labeled "Caregiver," "Temperamental," "Dependent Caregiver," and "Dangerous." Dangerous abusers have the highest levels of aggression, financial dependency, substance abuse, and irresponsibility. Caregivers are lowest in harmful characteristics and highest in providing emotional and instrumental support to victims. The 4 profiles significantly differ in the average age and gender of the abuser, the relationship to victims, and types of mistreatment committed.DiscussionThis is the first quantitative study to identify and characterize abuser subtypes. Tailored interventions are needed to reduce problem behaviors and enhance strengths specific to each abuser profile.
| S-EPMC6283306 | biostudies-literature
Project description:Masked hypertension (MHT) is characterized by normal clinic and above normal 24-hour ambulatory blood pressure (BP) levels. We evaluated clinical characteristics and CV outcomes of different nocturnal patterns of MHT. We analyzed data derived from a large cohort of adult individuals, who consecutively underwent home, clinic, and ambulatory BP monitoring at our Hypertension Unit between January 2007 and December 2016. MHT was defined as clinic BP <140/90 mm Hg and 24-hour BP ≥ 130/80 mm Hg, and stratified into three groups according to dipping status: (a) dippers, (b) nondippers, and (c) reverse dippers. From an overall sample of 6695 individuals, we selected 2628 (46.2%) adult untreated individuals, among whom 153 (5.0%) had MHT. In this group, 67 (43.8%) were nondippers, 65 (42.5%) dippers, and 21 (13.7%) reverse dippers. No significant differences were found among groups regarding demographics, clinical characteristics, and prevalence of risk factors, excluding older age in reverse dippers compared to other groups (P < 0.001). Systolic BP levels were significantly higher in reverse dippers than in other groups at both 24-hour (135.6 ± 8.5 vs 130.4 ± 6.0 vs 128.2 ± 6.8 mm Hg, respectively; P < 0.001) and nighttime periods (138.2 ± 9.1 vs 125.0 ± 6.3 vs 114.5 ± 7.7 mm Hg; P < 0.001). Reverse dipping was associated with a significantly higher risk of stroke, even after correction for age, gender, BMI, dyslipidemia, and diabetes (OR 18.660; 95% IC [1.056-33.813]; P = 0.046). MHT with reverse dipping status was associated with higher burden of BP and relatively high risk of stroke compared to both dipping and nondipping profiles, although a limited number of CV outcomes have been recorded during the follow-up.
| S-EPMC8030919 | biostudies-literature
Project description:Youth involved with the juvenile justice system have higher rates of unmet social and psychological service needs than the general population. Yet, scant research has addressed the potentially complex needs of youth on probation. This study is thus a first step in improving our ability to promote positive youth development and improved outcomes from youth on probation. It uses administrative data on probation youth from FY2011-2013 in a mid-Atlantic state. We estimated latent class models based on the ordinal scoring (high, moderate, none/low) of the 25 subscales from a standardized assessment administered at intake. In order to test whether groups were distinct, we examined a range of variables, including the official risk classification and recidivism rates measured by officieal rearrests and reconvictions. We report the demographic differences between the estimated groups, as well as adverse childhood experiences, school and employment status, previous legal history, and substance use history. Ultimately, the seven-class model produced four groups that others have noted: a relatively low needs (lowest need), relatively high needs (complex needs), substance use service needs, and mental health service needs. The other three groups that emerged include two gender specific groups (one for male and one for female high-need groups) and a group with skills needs that lacks supportive and protective skills. The analyses will facilitate a better appreciation for the service needs of moderate risk youth. Youth on probation are not a uniform population; they reflect tremendous heterogeneity, and probation systems should embrace systemic responsivity to provide appropriate services to improve youth outcomes. Advancing efforts to provide a broader spectrum of services that address multi-morbid conditions can ensure that youth have opportunities to improve their quality of life during the period of supervision.
| S-EPMC7236694 | biostudies-literature
Project description:BackgroundResearch on elder abuse has defined it as a multidimensional construct that encompasses a set of different abusive behaviours, victims, perpetrators and settings. The array of possible elder abuse configurations is difficult to capture. This study sought to identify victimization patterns that represent distinct elder abuse configurations based on specific abusive behaviours and on the relationship with the perpetrator; it also sought to determine the association between these latent classes with victims' characteristics.MethodData comes from two elder abuse surveys: a representative sample of community-dwelling adults and a convenience sample of older adults reporting elder abuse to four state and NGOs institutions. Latent Class Analysis (LCA) was used to categorize victimization in the population-based (N?=?245) and in the victims' sample (N?=?510) using 7 items measuring physical, psychological and financial abuse, and appointed perpetrators. Association tests were conducted to determine differences and similarities of victims' characteristics between the different obtained classes.ResultsThe LCA procedure identified six different latent classes of victimization experiences in each of the samples, which were statistically and plausibly distinct. In the population-based survey: verbal abuse by others (29%); psychological abuse from children/grandchildren (18%); overlooked by others (18%); stolen by others (15%); verbal Intimate Partner Violence (IPV) (14%) and physical and psychological IPV (6%). In the victims' survey: physical abuse by children/grandchildren (29%); physical IPV (26%); psychological abuse by children/grandchildren (18%); polyvictimization by others (16%); physical abuse by others (6%) and physical and psychological IPV (4%). In the victims survey the 6 groups significantly differ in age, gender, civil status, living arrangements, perceived social support and functional status.ConclusionsThe results support the possibility of the multidimensionality of elder abuse not being accounted by the "classical" abuse typologies. Elder abuse victims seeking help may represent a distinct group from that included in population-based prevalence studies. The appointed perpetrators may be the most meaningful and relevant aspect in distinguishing victimization experiences. Further research is needed to develop tailored interventions to specific elder abuse cases and enhance successful outcomes.
| S-EPMC6480599 | biostudies-literature
Project description:BackgroundSystemic lupus erythematosus (SLE) is a heterogeneous systemic autoimmune condition for which there are limited licensed therapies. Clinical trial design is challenging in SLE due at least in part to imperfect outcome measures. Improved understanding of how disease activity changes over time could inform future trial design. The aim of this study was to determine whether distinct trajectories of disease activity over time occur in patients with active SLE within a clinical trial setting and to identify factors associated with these trajectories.MethodsLatent class trajectory models were fitted to a clinical trial dataset of a monoclonal antibody targeting CD22 (Epratuzumab) in patients with active SLE using the numerical BILAG-2004 score (nBILAG). The baseline characteristics of patients in each class and changes in prednisolone over time were identified. Exploratory PK-PD modelling was used to examine cumulative drug exposure in relation to latent class membership.ResultsFive trajectories of disease activity were identified, with 3 principal classes: non-responders (NR), slow responders (SR) and rapid-responders (RR). In both the SR and RR groups, significant changes in disease activity were evident within the first 90 days of the trial. The SR and RR patients had significantly higher baseline disease activity, exposure to epratuzumab and activity in specific BILAG domains, whilst NR had lower steroid use at baseline and less change in steroid dose early in the trial.ConclusionsLongitudinal nBILAG scores reveal different trajectories of disease activity and may offer advantages over fixed endpoints. Corticosteroid use however remains an important confounder in lupus trials and can influence early response. Changes in disease activity and steroid dose early in the trial were associated with the overall disease activity trajectory, supporting the feasibility of performing adaptive trial designs in SLE.
| S-EPMC8320218 | biostudies-literature
Project description:In this study, using latent class analysis (LCA), we investigated whether there are any homogeneous subclasses of individuals exhibiting different profiles of metabolic syndrome (MetS) components. The current study was conducted within the framework of the Tehran Lipid and Glucose Study (TLGS), a population-based cohort including 6448 subjects, aged 20-50 years. We carried out a LCA on MetS components and assessed the association of some demographic and behavioral variables with membership of latent subclasses using multinomial logistic regression. Four latent classes were identified:(1) Low riskclass, with the lowest probabilities for all MetS components (its prevalence rate in men: 29%, women: 64.7%), (2) MetS with diabetes medication (men: 1%, women: 2.3%), (3) Mets without diabetes medication (men: 32%, women: 13.4%), (4) dyslipidemia (men: 38%, women: 19.6%). In men the forth subclass was more significantly associated with being smoker (odds ratio: 4.49; 95% CI: 1.89-9.97). Our study showed that subjects with MetS could be classified in sub-classes with different origins for their metabolic disorders including drug treated diabetes, those with central obesity and dyslipidemia associated with smoking.
| S-EPMC6367385 | biostudies-other
Project description:BackgroundTo advance asthma cohort research, we need a method that can use longitudinal data, including when collected at irregular intervals, to model multiple phenotypes of wheeze and identify both time-invariant (eg, sex) and time-varying (eg, environmental exposure) risk factors.ObjectiveTo demonstrate the use of latent class growth analysis (LCGA) in defining phenotypes of wheeze and examining the effects of causative factors, using repeated questionnaires in an urban birth cohort study.MethodsWe gathered repeat questionnaire data on wheeze from 689 children ages 3 through 108 months (n = 7,048 questionnaires) and used LCGA to identify wheeze phenotypes and model the effects of time-invariant (maternal asthma, ethnicity, prenatal environmental tobacco smoke, and child sex) and time-varying (cold/influenza [flu] season) risk factors on prevalence of wheeze in each phenotype.ResultsLCGA identified four wheezing phenotypes: never/infrequent (47.1%), early-transient (37.5%), early-persistent (7.6%), and late-onset (7.8%). Compared with children in the never/infrequent phenotype, maternal asthma was a risk factor for the other 3 phenotypes; Dominican versus African American ethnicity was a risk factor for the early-transient phenotype; and male sex was a risk factor for the early-persistent phenotype. The prevalence of wheeze was higher during the cold/flu season than otherwise among children in the early-persistent phenotype (P = .08).ConclusionThis is the first application of LCGA to identify wheeze phenotypes in asthma research. Unlike other methods, this modeling technique can accommodate questionnaire data collected at irregularly spaced age intervals and can simultaneously identify multiple trajectories of health outcomes and associations with time-invariant and time-varying causative factors.
| S-EPMC3371648 | biostudies-literature
Project description:Over the past three decades, obesity-related diseases have increased tremendously in China, and are now the leading causes of morbidity and mortality. Patterns of weight change can be used to predict risk of obesity-related diseases, increase understanding of etiology of disease risk, identify groups at particularly high risk, and shape prevention strategies.Latent class trajectory modeling was used to compute weight change trajectories for adults aged 18 to 66 using the China Health and Nutrition Survey (CHNS) data (n = 12,611). Weight change trajectories were computed separately for males and females by age group at baseline due to differential age-related patterns of weight gain in China with urbanization. Generalized linear mixed effects models examined the association between weight change trajectories and baseline characteristics including urbanicity, BMI category, age, and year of study entry.Trajectory classes were identified for each of six age-sex subgroups corresponding to various degrees of weight loss, maintenance and weight gain. Baseline BMI status was a significant predictor of trajectory membership for all age-sex subgroups. Baseline overweight/obesity increased odds of following 'initial loss with maintenance' trajectories. We found no significant association between baseline urbanization and trajectory membership after controlling for other covariates.Trajectory analysis identified patterns of weight change for age by gender groups. Lack of association between baseline urbanization status and trajectory membership suggests that living in a rural environment at baseline was not protective. Analyses identified age-specific nuances in weight change patterns, pointing to the importance of subgroup analyses in future research.
| S-EPMC4336139 | biostudies-literature