Latent class analysis identification of syndromes in Alzheimer's disease

2006 ◽  
Vol 3 (1) ◽  
Author(s):  
Cathal Walsh
Keyword(s):  
Social Sciences ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Latent Class Analysis ◽  
Posterior Distribution ◽  
Latent Variable ◽  
Latent Class ◽  
Bayesian Framework ◽  
Class Analysis ◽  
The Social

Latent variable models have been used extensively in the social sciences. In this work a latent class analysis is used to identify syndromes within Alzheimer's disease. The fitting of the model is done in a Bayesian framework, and this is examined in detail here. In particular, the label switching problem is identified, and solutions presented. Graphical summaries of the posterior distribution are included.

scholarly journals Identifying and predicting heterogeneity in cognitive decline among individuals with prodromal Alzheimer's disease using a latent class analysis

2020 ◽  
Vol 16 (S6) ◽  
Author(s):  
Roos J. Jutten ◽  
Sietske A.M. Sikkes ◽  
Kathryn V. Papp ◽  
Bart N.M. Van Berckel ◽  
Charlotte E. Teunissen ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Decline ◽  
Latent Class Analysis ◽  
Latent Class ◽  
Class Analysis ◽  
Prodromal Alzheimer’S Disease

O2-07-04: COGNITIVE SUBTYPES IN DEMENTIA DUE TO ALZHEIMER'S DISEASE IDENTIFIED BY LATENT CLASS ANALYSIS

2014 ◽  
Vol 10 ◽  
pp. P178-P179
Author(s):  
Nienke Scheltens ◽  
Francisca Galindo Garre ◽  
Yolande A.L. Pijnenburg ◽  
Annelies E. van der Vlies ◽  
Lieke L. Smits ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Latent Class Analysis ◽  
Latent Class ◽  
Class Analysis

scholarly journals O3-11-02: LATENT CLASS ANALYSIS IDENTIFIES FUNCTIONAL DECLINE WITH AMSTERDAM IADL IN PRE-CLINICAL ALZHEIMER'S DISEASE

2019 ◽  
Vol 15 ◽  
pp. P911-P912
Author(s):  
Sarah-Christine Villeneuve ◽  
Marion Houot ◽  
Merike Verrijp ◽  
Marie-Odile Habert ◽  
Bruno Dubois ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Latent Class Analysis ◽  
Latent Class ◽  
Functional Decline ◽  
Class Analysis

scholarly journals Identifying and evaluating clinical subtypes of Alzheimer’s disease in care electronic health records using unsupervised machine learning

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Nonie Alexander ◽  
Daniel C. Alexander ◽  
Frederik Barkhof ◽  
Spiros Denaxas
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Electronic Health Records ◽  
Latent Class Analysis ◽  
Latent Class ◽  
Affinity Propagation ◽  
Class Analysis ◽  
Clustering Methods ◽  
Health Records ◽  
Electronic Health

Abstract Background Alzheimer’s disease (AD) is a highly heterogeneous disease with diverse trajectories and outcomes observed in clinical populations. Understanding this heterogeneity can enable better treatment, prognosis and disease management. Studies to date have mainly used imaging or cognition data and have been limited in terms of data breadth and sample size. Here we examine the clinical heterogeneity of Alzheimer's disease patients using electronic health records (EHR) to identify and characterise disease subgroups using multiple clustering methods, identifying clusters which are clinically actionable. Methods We identified AD patients in primary care EHR from the Clinical Practice Research Datalink (CPRD) using a previously validated rule-based phenotyping algorithm. We extracted and included a range of comorbidities, symptoms and demographic features as patient features. We evaluated four different clustering methods (k-means, kernel k-means, affinity propagation and latent class analysis) to cluster Alzheimer’s disease patients. We compared clusters on clinically relevant outcomes and evaluated each method using measures of cluster structure, stability, efficiency of outcome prediction and replicability in external data sets. Results We identified 7,913 AD patients, with a mean age of 82 and 66.2% female. We included 21 features in our analysis. We observed 5, 2, 5 and 6 clusters in k-means, kernel k-means, affinity propagation and latent class analysis respectively. K-means was found to produce the most consistent results based on four evaluative measures. We discovered a consistent cluster found in three of the four methods composed of predominantly female, younger disease onset (43% between ages 42–73) diagnosed with depression and anxiety, with a quicker rate of progression compared to the average across other clusters. Conclusion Each clustering approach produced substantially different clusters and K-Means performed the best out of the four methods based on the four evaluative criteria. However, the consistent appearance of one particular cluster across three of the four methods potentially suggests the presence of a distinct disease subtype that merits further exploration. Our study underlines the variability of the results obtained from different clustering approaches and the importance of systematically evaluating different approaches for identifying disease subtypes in complex EHR.

The identification of cognitive subtypes in Alzheimer's disease dementia using latent class analysis

2015 ◽  
Vol 87 (3) ◽  
pp. 235-243 ◽  
Author(s):  
Nienke M E Scheltens ◽  
Francisca Galindo-Garre ◽  
Yolande A L Pijnenburg ◽  
Annelies E van der Vlies ◽  
Lieke L Smits ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Latent Class Analysis ◽  
Latent Class ◽  
Class Analysis ◽  
Alzheimer’S Disease Dementia

scholarly journals Bourdieu in de buurt : Sociale klassendebat en de klassenstructuur van Rotterdam

Sociologie ◽  
2020 ◽  
Vol 15 (2) ◽  
pp. 117-147
Author(s):  
Gijs Custers ◽  
Godfried Engbersen
Keyword(s):  
Latent Class Analysis ◽  
Latent Class ◽  
Research Approach ◽  
Class Analysis ◽  
Social And Cultural Capital ◽  
New Class ◽  
Social Mix ◽  
The Social ◽  
New Research

Abstract Studies by Savage et al. (2013) and Vrooman, Gijsberts and Boelhouwer (2014) introduce new class typologies that combine Bourdieu’s work with latent class analysis. This paper identifies this new research approach as Bourdieusian latent class analysis. We discuss the role of these studies within the social class debate and we review the merits and limitations of this approach. In addition, we show how the class structure of Rotterdam can be empirically established by studying the distribution of economic, social and cultural capital. We use the Neighbourhood Profile data (N = 14,040; 71 neighbourhoods) to develop a class typology that includes eight social groups. This class typology complements conventional indicators of neighbourhood socioeconomic status and can be used to study ‘social mix’ and gentrification.

scholarly journals Hispanic/Latino Acculturation Profiles and Telomere Length: Latent Class Analysis on a Nationally Representative Sample

2021 ◽  
Vol 9 ◽  
Author(s):  
Francisco Alejandro Montiel Ishino ◽  
Philip McNab ◽  
Kevin Villalobos ◽  
Jeffrey H. Cohen ◽  
Anna M. Nápoles ◽  
...  
Keyword(s):  
Latent Class Analysis ◽  
Telomere Length ◽  
Representative Sample ◽  
Latent Variable ◽  
Latent Class ◽  
The United States ◽  
Public Health Research ◽  
Class Analysis ◽  
Foreign Born ◽  
The Us

Background: Acculturation profiles and their impact on telomere length among foreign-born Hispanics/Latinos living in the United States (US) are relatively unknown. The limited research available has linked acculturation with shortened telomere length.Objectives: To identify acculturation profiles among a US representative sample of Hispanics/Latinos and to then examine telomere length differences between profiles.Methods: We conducted a latent class analysis among a non-institutionalized US-representative sample of Hispanics/Latinos using the 1999–2002 National Health and Nutrition Examination Survey (N = 2,292). The latent variable of acculturation was assessed by length of time in the US and language used as a child, read and spoken, usually spoken at home, used to think, and used with friends (i.e., Spanish and/or English). Telomere length assessed from leukocytes was used as the distal continuous outcome.Results: We identified five profiles: (1) low acculturated [33.2% of sample]; (2) partially integrated [18.6% of sample]; (3) integrated [19.4% of sample]; (4) partially assimilated [15.1% of sample]; and (5) assimilated [13.7% of sample]. Acculturation profiles revealed nuanced differences in conditional probabilities with language use despite the length of time spent in the US. While telomere length did vary, there were no significant differences between profiles.Conclusion: Profiles identified revealed that possible life-course and generational effects may be at play in the partially assimilated and assimilated profiles. Our findings expand public health research using complex survey data to identify and assess the dynamic relationship of acculturation profiles and health biomarkers, while being among the first to examine this context using a person-centered approach.

Sign in / Sign up

Export Citation Format

Share Document