Dataset Information

Identifying undetected dementia in UK primary care patients: a retrospective case-control study comparing machine-learning and standard epidemiological approaches.

ABSTRACT:

Background

Identifying dementia early in time, using real world data, is a public health challenge. As only two-thirds of people with dementia now ultimately receive a formal diagnosis in United Kingdom health systems and many receive it late in the disease process, there is ample room for improvement. The policy of the UK government and National Health Service (NHS) is to increase rates of timely dementia diagnosis. We used data from general practice (GP) patient records to create a machine-learning model to identify patients who have or who are developing dementia, but are currently undetected as having the condition by the GP.

Methods

We used electronic patient records from Clinical Practice Research Datalink (CPRD). Using a case-control design, we selected patients aged >65y with a diagnosis of dementia (cases) and matched them 1:1 by sex and age to patients with no evidence of dementia (controls). We developed a list of 70 clinical entities related to the onset of dementia and recorded in the 5?years before diagnosis. After creating binary features, we trialled machine learning classifiers to discriminate between cases and controls (logistic regression, naïve Bayes, support vector machines, random forest and neural networks). We examined the most important features contributing to discrimination.

Results

The final analysis included data on 93,120 patients, with a median age of 82.6?years; 64.8% were female. The naïve Bayes model performed least well. The logistic regression, support vector machine, neural network and random forest performed very similarly with an AUROC of 0.74. The top features retained in the logistic regression model were disorientation and wandering, behaviour change, schizophrenia, self-neglect, and difficulty managing.

Conclusions

Our model could aid GPs or health service planners with the early detection of dementia. Future work could improve the model by exploring the longitudinal nature of patient data and modelling decline in function over time.

SUBMITTER: Ford E

PROVIDER: S-EPMC6889642 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying undetected dementia in UK primary care patients: a retrospective case-control study comparing machine-learning and standard epidemiological approaches.

Ford Elizabeth E Rooney Philip P Oliver Seb S Hoile Richard R Hurley Peter P Banerjee Sube S van Marwijk Harm H Cassell Jackie J

BMC medical informatics and decision making 20191202 1

<h4>Background</h4>Identifying dementia early in time, using real world data, is a public health challenge. As only two-thirds of people with dementia now ultimately receive a formal diagnosis in United Kingdom health systems and many receive it late in the disease process, there is ample room for improvement. The policy of the UK government and National Health Service (NHS) is to increase rates of timely dementia diagnosis. We used data from general practice (GP) patient records to create a mac ...[more]

PMID: 31791325

Similar Datasets

Project description:BACKGROUND:Prognostic modelling using standard methods is well-established, particularly for predicting risk of single diseases. Machine-learning may offer potential to explore outcomes of even greater complexity, such as premature death. This study aimed to develop novel prediction algorithms using machine-learning, in addition to standard survival modelling, to predict premature all-cause mortality. METHODS:A prospective population cohort of 502,628 participants aged 40-69 years were recruited to the UK Biobank from 2006-2010 and followed-up until 2016. Participants were assessed on a range of demographic, biometric, clinical and lifestyle factors. Mortality data by ICD-10 were obtained from linkage to Office of National Statistics. Models were developed using deep learning, random forest and Cox regression. Calibration was assessed by comparing observed to predicted risks; and discrimination by area under the 'receiver operating curve' (AUC). FINDINGS:14,418 deaths (2.9%) occurred over a total follow-up time of 3,508,454 person-years. A simple age and gender Cox model was the least predictive (AUC 0.689, 95% CI 0.681-0.699). A multivariate Cox regression model significantly improved discrimination by 6.2% (AUC 0.751, 95% CI 0.748-0.767). The application of machine-learning algorithms further improved discrimination by 3.2% using random forest (AUC 0.783, 95% CI 0.776-0.791) and 3.9% using deep learning (AUC 0.790, 95% CI 0.783-0.797). These ML algorithms improved discrimination by 9.4% and 10.1% respectively from a simple age and gender Cox regression model. Random forest and deep learning achieved similar levels of discrimination with no significant difference. Machine-learning algorithms were well-calibrated, while Cox regression models consistently over-predicted risk. CONCLUSIONS:Machine-learning significantly improved accuracy of prediction of premature all-cause mortality in this middle-aged population, compared to standard methods. This study illustrates the value of machine-learning for risk prediction within a traditional epidemiological study design, and how this approach might be reported to assist scientific verification.

Project description:OBJECTIVES:The aim of this study was to critically explore the views of the public about the acceptability and feasibility of proactive approaches to earlier dementia diagnosis and also identification of people at high risk of dementia. DESIGN:Qualitative study using task group methodology and thematic data analysis. SETTING:Task groups were held either at the university (n=5) or at a carers' centre (n=1). PARTICIPANTS:A convenience sample of 31 of 54 participants identified by local non-statutory agencies took part in a task group. All were aged between 40 years and 80 years, 21 were women and 10men participated. RESULTS:Despite the use of task group methodology, participants expressed limited understandings of dementia and confusion between proactive approaches. Nevertheless, they highlighted a range of potential benefits and limitations of proactive approaches and the ethical issues raised. There was a preference to embed risk assessment within routine health checks, which focused on achieving a healthier lifestyle, rather than specifically on dementia. Participants emphasised the need to ensure informed consent prior to use of proactive approaches and to provide appropriate support. They also suggested alternative approaches that could potentially facilitate the early detection of dementia or reduce risk at a population level. CONCLUSIONS:As international policy on dementia shifts towards a prevention agenda there is growing interest in identifying those at risk of developing dementia. This study provides useful insights into the acceptability of the use of such proactive approaches among the public. The introduction of proactive approaches to dementia identification raises complex practical and ethical issues, particularly in the context of low public understanding of dementia. The importance of better quality information about dementia (and the likelihood of developing dementia) and provision of psychological support for those undergoing risk assessment were highlighted.

Project description:BACKGROUND:Heparin is one of the most commonly used medications in intensive care units. In clinical practice, the use of a weight-based heparin dosing nomogram is standard practice for the treatment of thrombosis. Recently, machine learning techniques have dramatically improved the ability of computers to provide clinical decision support and have allowed for the possibility of computer generated, algorithm-based heparin dosing recommendations. OBJECTIVE:The objective of this study was to predict the effects of heparin treatment using machine learning methods to optimize heparin dosing in intensive care units based on the predictions. Patient state predictions were based upon activated partial thromboplastin time in 3 different ranges: subtherapeutic, normal therapeutic, and supratherapeutic, respectively. METHODS:Retrospective data from 2 intensive care unit research databases (Multiparameter Intelligent Monitoring in Intensive Care III, MIMIC-III; e-Intensive Care Unit Collaborative Research Database, eICU) were used for the analysis. Candidate machine learning models (random forest, support vector machine, adaptive boosting, extreme gradient boosting, and shallow neural network) were compared in 3 patient groups to evaluate the classification performance for predicting the subtherapeutic, normal therapeutic, and supratherapeutic patient states. The model results were evaluated using precision, recall, F1 score, and accuracy. RESULTS:Data from the MIMIC-III database (n=2789 patients) and from the eICU database (n=575 patients) were used. In 3-class classification, the shallow neural network algorithm performed the best (F1 scores of 87.26%, 85.98%, and 87.55% for data set 1, 2, and 3, respectively). The shallow neural network algorithm achieved the highest F1 scores within the patient therapeutic state groups: subtherapeutic (data set 1: 79.35%; data set 2: 83.67%; data set 3: 83.33%), normal therapeutic (data set 1: 93.15%; data set 2: 87.76%; data set 3: 84.62%), and supratherapeutic (data set 1: 88.00%; data set 2: 86.54%; data set 3: 95.45%) therapeutic ranges, respectively. CONCLUSIONS:The most appropriate model for predicting the effects of heparin treatment was found by comparing multiple machine learning models and can be used to further guide optimal heparin dosing. Using multicenter intensive care unit data, our study demonstrates the feasibility of predicting the outcomes of heparin treatment using data-driven methods, and thus, how machine learning-based models can be used to optimize and personalize heparin dosing to improve patient safety. Manual analysis and validation suggested that the model outperformed standard practice heparin treatment dosing.

Project description:BACKGROUND:The ability to confidently predict health outcomes from gene expression would catalyze a revolution in molecular diagnostics. Yet, the goal of developing actionable, robust, and reproducible predictive signatures of phenotypes such as clinical outcome has not been attained in almost any disease area. Here, we report a comprehensive analysis spanning prediction tasks from ulcerative colitis, atopic dermatitis, diabetes, to many cancer subtypes for a total of 24 binary and multiclass prediction problems and 26 survival analysis tasks. We systematically investigate the influence of gene subsets, normalization methods and prediction algorithms. Crucially, we also explore the novel use of deep representation learning methods on large transcriptomics compendia, such as GTEx and TCGA, to boost the performance of state-of-the-art methods. The resources and findings in this work should serve as both an up-to-date reference on attainable performance, and as a benchmarking resource for further research. RESULTS:Approaches that combine large numbers of genes outperformed single gene methods consistently and with a significant margin, but neither unsupervised nor semi-supervised representation learning techniques yielded consistent improvements in out-of-sample performance across datasets. Our findings suggest that using l2-regularized regression methods applied to centered log-ratio transformed transcript abundances provide the best predictive analyses overall. CONCLUSIONS:Transcriptomics-based phenotype prediction benefits from proper normalization techniques and state-of-the-art regularized regression approaches. In our view, breakthrough performance is likely contingent on factors which are independent of normalization and general modeling techniques; these factors might include reduction of systematic errors in sequencing data, incorporation of other data types such as single-cell sequencing and proteomics, and improved use of prior knowledge.

Project description:IntroductionStudies of prevalence and the demographic profile of type 1 diabetes are challenging because of the relative rarity of the condition, however, these outcomes can be determined using routine healthcare data repositories. Understanding the epidemiology of type 1 diabetes allows for targeted interventions and care of this life-affecting condition.ObjectivesTo describe the prevalence, incidence and demographics of persons with type 1 diabetes diagnosed in Wales, UK, using the Secure Anonymised Information Linkage (SAIL) Databank.MethodsData derived from primary and secondary care throughout Wales available in the SAIL Databank were used to identify people with type 1 diabetes to determine the prevalence and incidence of type 1 diabetes over a 10 year period (2008-18) and describe the demographic and clinical characteristics of this population by age, socioeconomic deprivation and settlement type. The seasonal variation in incidence rates was also examined.ResultsThe prevalence of type 1 diabetes in 2018 was 0.32% in the whole population, being greater in men compared to women (0.35% vs 0.28% respectively); highest in those aged 15-29 years (0.52%) and living in the most socioeconomically deprived areas (0.38%). The incidence of type 1 diabetes over 10 years was 14.0 cases/100,000 people/year for the whole population of Wales. It was highest in children aged 0-14 years (33.6 cases/100,000 people/year) and areas of high socioeconomic deprivation (16.8 cases/100,000 people/year) and least in those aged 45-60 years (6.5 cases/100,000 people/year) and in areas of low socioeconomic deprivation (11.63 cases/100,000 people/year). A seasonal trend in the diagnoses of type 1 diabetes was observed with higher incidence in winter months.ConclusionThis nation-wide retrospective epidemiological study using routine data revealed that the incidence of type 1 diabetes in Wales was greatest in those aged 0-14 years with a higher incidence and prevalence in the most deprived areas. These findings illustrate the need for health-related policies targeted at high deprivation areas to include type 1 diabetes in their remit.

Dataset Information

Identifying undetected dementia in UK primary care patients: a retrospective case-control study comparing machine-learning and standard epidemiological approaches.

Background

Methods

Results

Conclusions

Publications

Identifying undetected dementia in UK primary care patients: a retrospective case-control study comparing machine-learning and standard epidemiological approaches.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets