Dataset Information

Latent variable mixture modelling and individual treatment prediction.

ABSTRACT: Understanding which groups of patients are more or less likely to benefit from specific treatments has important implications for healthcare. Many personalised medicine approaches in mental health employ variable-centred approaches to predicting treatment response, yet person-centred approaches that identify clinical profiles of patients can provide information on the likelihood of a range of important outcomes. In this paper, we discuss the use of latent variable mixture modelling and demonstrate its use in the application of a patient profiling algorithm using routinely collected patient data to predict outcomes from psychological treatments. This validation study analysed data from two services, which included n?=?44,905 patients entering treatment. There were different patterns of reliable recovery, improvement and clinical deterioration from therapy, across the eight profiles which were consistent over time. Outcomes varied between different types of therapy within the profiles: there were significantly higher odds of reliable recovery with High Intensity therapies in two profiles (32.5% of patients) and of reliable improvement in three profiles (32.2% of patients) compared with Low Intensity treatments. In three profiles (37.4% of patients) reliable recovery was significantly more likely if patients had CBT vs Counselling. The developments and potential application of latent variable mixture approaches are further discussed.

SUBMITTER: Saunders R

PROVIDER: S-EPMC7417810 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Latent variable mixture modelling and individual treatment prediction.

Saunders Rob R Buckman Joshua E J JEJ Pilling Stephen S

Behaviour research and therapy 20191028

Understanding which groups of patients are more or less likely to benefit from specific treatments has important implications for healthcare. Many personalised medicine approaches in mental health employ variable-centred approaches to predicting treatment response, yet person-centred approaches that identify clinical profiles of patients can provide information on the likelihood of a range of important outcomes. In this paper, we discuss the use of latent variable mixture modelling and demonstra ...[more]

PMID: 31841709

Similar Datasets

Project description:BackgroundThe patterning of food intake at eating occasions is a poorly understood, albeit important, step towards achieving a healthy dietary pattern. However, to capture the many permutations of food combinations at eating occasions, novel analytic approaches are required. We applied a latent variable mixture modelling (LVMM) approach to understand how foods are consumed in relation to each other at breakfast.MethodsDietary intake at breakfast (n = 8145 occasions) was assessed via 24-h recall during the 2011-12 Australian National Nutrition and Physical Activity Survey (n = 3545 men and n = 4127 women, ⩾19 y). LVMM was used to determine breakfast food profiles based on 35 food group variables, reflecting compliance with Australian Dietary Guidelines. F and adjusted-chi2 tests assessed differences in timing of consumption and participant characteristics between the breakfast profiles. Regression models, adjusted for covariates, were used to examine associations between breakfast food profiles and objective adiposity measures (BMI and waist circumference).ResultsFive distinct profiles were found. Three were similar for men and women. These were labelled: "Wholegrain cereals and milks" (men: 16%, women: 17%), "Protein-foods" (men and women: 11%) and "Mixed cereals and milks" (men: 33%, women: 37%). Two "Breads and spreads" profiles were also found that were differentiated by their accompanying beverages (men) or type of grain (women). Profiles were found to vary by timing of consumption, participant characteristics and adiposity indicators. For example, the "Protein-foods" profile occurred more frequently on weekends and after 9 am. Men with a "Bread and spreads (plus tea/coffee)" profile were older (P < 0.001) and had lower income and education levels (P < 0.05), when compared to the other profiles. Women with a "Protein-foods" profile were younger (P < 0.001) and less likely to be married (P < 0.01). Both men and women with a "Wholegrain cereals and milks" profile had the most favourable adiposity estimates (P < 0.05).ConclusionsWe identified five breakfast food profiles in adults that varied by timing of consumption, participant characteristics and adiposity indicators. LVMM was a useful approach for capturing the complexity of food combinations at breakfast. Future research could collect contextual information about eating occasions to understand the complex factors that influence food choices.

Project description:BackgroundRecent advances in biotechnology enable the acquisition of high-dimensional data on individuals, posing challenges for prediction models which traditionally use covariates such as clinical patient characteristics. Alternative forms of covariate representations for the features derived from these modern data modalities should be considered that can utilize their intrinsic interconnection. The connectivity information between these features can be represented as an individual-specific network defined by a set of nodes and edges, the strength of which can vary from individual to individual. Global or local graph-theoretical features describing the network may constitute potential prognostic biomarkers instead of or in addition to traditional covariates and may replace the often unsuccessful search for individual biomarkers in a high-dimensional predictor space.MethodsWe conducted a scoping review to identify, collate and critically appraise the state-of-art in the use of individual-specific networks for prediction modelling in medicine and applied health research, published during 2000-2020 in the electronic databases PubMed, Scopus and Embase.ResultsOur scoping review revealed the main application areas namely neurology and pathopsychology, followed by cancer research, cardiology and pathology (N = 148). Network construction was mainly based on Pearson correlation coefficients of repeated measurements, but also alternative approaches (e.g. partial correlation, visibility graphs) were found. For covariates measured only once per individual, network construction was mostly based on quantifying an individual's contribution to the overall group-level structure. Despite the multitude of identified methodological approaches for individual-specific network inference, the number of studies that were intended to enable the prediction of clinical outcomes for future individuals was quite limited, and most of the models served as proof of concept that network characteristics can in principle be useful for prediction.ConclusionThe current body of research clearly demonstrates the value of individual-specific network analysis for prediction modelling, but it has not yet been considered as a general tool outside the current areas of application. More methodological research is still needed on well-founded strategies for network inference, especially on adequate network sparsification and outcome-guided graph-theoretical feature extraction and selection, and on how networks can be exploited efficiently for prediction modelling.

Dataset Information

Latent variable mixture modelling and individual treatment prediction.

Publications

Latent variable mixture modelling and individual treatment prediction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets