Clusters of multiple long-term conditions in three UK datasets: a latent class analysis
Steell, L.; Krauth, S. J.; Ahmed, S.; Dibben, G. O.; Hanlon, P.; Nicholl, B. I.; McAllister, D.; Lewsey, J.; McIntosh, E.; Singh, S. J.; Taylor, R. S.; Mair, F. S.; Jani, B. D.
Show abstract
IntroductionLatent class analysis (LCA) can be used to identify subgroups within populations based on unobserved variables. LCA can be used to explore whether certain long-term conditions (LTC) occur together more frequently than others in patients with multiple-long term conditions. In this manuscript we present findings from applying LCA in three large-scale UK databanks. MethodsWe applied LCA to three different UK databanks: Secure Anonymised Information Linkage databank [SAIL], UK Biobank, and Understanding Society: the UK Household Longitudinal Study [UKHLS] and four different age groups: 18-36, 37-54, 55-73, and 74+ years. The optimal number of classes in each LCA was determined using maximum likelihood. Sample size adjusted Bayesian Information Criterion (aBIC) was used to assess model fit and elbow plots and model entropy were used to assess the best number of latent classes in each model. ResultsBetween three to six clusters were identified in the different datasets and age groups. Although different in detail, similar types of clusters were identified between datasets and age groups which combine disorders around similar systems incl. Cardiometabolic clusters, Pulmonary clusters, Mental health clusters, Painful conditions clusters, and cancer clusters.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Patterns of rates of mortality in the Clinical Practice Research Datalink 95%
- Latent class regression improves the predictive acuity and clinical utility of survival prognostication amongst chronic heart failure patients. 94%
- Wellbeing Impact Study of High-Speed 2 (WISH2): Protocol for a mixed-methods examination of the impact of major transport infrastructure development on mental health and wellbeing 93%
Similar papers in this journal
- Tracking Persistent Symptoms in Scotland (TraPSS): A Longitudinal Prospective Cohort Study of COVID-19 Recovery After Mild Acute Infection 94%
- Replicating a COVID-19 study in a national England database to assess the generalisability of research with regional electronic health record data 93%
- Predictors of adverse outcome in patients with suspected COVID-19 managed in a ‘virtual hospital’ setting: a cohort study 93%
Similar papers in this journal
- Patient symptoms and experience following COVID-19: results from a UK wide survey 92%
- Psychometric analysis of the modified Covid-19 Yorkshire Rehabilitation Scale (C19-YRSm) in a prospective multicentre study 92%
- Post-COVID assessment in a specialist clinical service: a 12-month, single-centre analysis of symptoms and healthcare needs in 1325 individuals 92%
Similar papers in this journal
- Development and validation of a modified Cambridge Multimorbidity Score for use with internationally recognized electronic health record clinical terms (SNOMED CT) 94%
- OpenSAFELY NHS Service Restoration Observatory 1: describing trends and variation in primary care clinical activity for 23.3 million patients in England during the first wave of COVID-19 93%
- Changes in General Practice use and costs with COVID-19 and telehealth initiatives 92%
Similar papers in this journal
- Patient characteristics associated with clinically coded long COVID: an OpenSAFELY study using electronic health records 92%
- A mixed-methods evaluation of patients’ views on primary care multi-disciplinary teams in Scotland 91%
- Home monitoring of HbA1c in diabetes mellitus: A protocol for systematic review and narrative synthesis on reliability, accuracy, and patient acceptability 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.