Dataset Information

Integrating expert knowledge for dementia risk prediction in individuals with mild cognitive impairment (MCI): a study protocol

ABSTRACT:

Introduction

To date, there is no broadly accepted dementia risk score for use in individuals with mild cognitive impairment (MCI), partly because there are few large datasets available for model development. When evidence is limited, the knowledge and experience of experts becomes more crucial for risk stratification and providing MCI patients with prognosis. Structured expert elicitation (SEE) includes formal methods to quantify experts’ beliefs and help experts to express their beliefs in a quantitative form, reducing biases in the process. This study proposes to (1) assess experts’ beliefs about important predictors for 3-year dementia risk in persons with MCI through SEE methodology and (2) to integrate expert knowledge and patient data to derive dementia risk scores in persons with MCI using a Bayesian approach.

Methods and analysis

This study will use a combination of SEE methodology, prospectively collected clinical data, and statistical modelling to derive a dementia risk score in persons with MCI. Clinical expert knowledge will be quantified using SEE methodology that involves the selection and training of the experts, administration of questionnaire for eliciting expert knowledge, discussion meetings and results aggregation. Patient data from the Prospective Registry for Persons with Memory Symptoms of the Cognitive Neurosciences Clinic at the University of Calgary; the Alzheimer’s Disease Neuroimaging Initiative; and the National Alzheimer’s Coordinating Center’s Uniform Data Set will be used for model training and validation. Bayesian Cox models will be used to incorporate patient data and elicited data to predict 3-year dementia risk.

Discussion

This study will develop a robust dementia risk score that incorporates clinician expert knowledge with patient data for accurate risk stratification, prognosis and management of dementia.

SUBMITTER: Wang M

PROVIDER: S-EPMC8587594 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundCox proportional hazards regression models and machine learning models are widely used for predicting the risk of dementia. Existing comparisons of these models have mostly been based on empirical datasets and have yielded mixed results. This study examines the accuracy of various machine learning and of the Cox regression models for predicting time-to-event outcomes using Monte Carlo simulation in people with mild cognitive impairment (MCI).MethodsThe predictive accuracy of nine time-to-event regression and machine learning models were investigated. These models include Cox regression, penalized Cox regression (with Ridge, LASSO, and elastic net penalties), survival trees, random survival forests, survival support vector machines, artificial neural networks, and extreme gradient boosting. Simulation data were generated using study design and data characteristics of a clinical registry and a large community-based registry of patients with MCI. The predictive performance of these models was evaluated based on three-fold cross-validation via Harrell's concordance index (c-index), integrated calibration index (ICI), and integrated brier score (IBS).ResultsCox regression and machine learning model had comparable predictive accuracy across three different performance metrics and data-analytic conditions. The estimated c-index values for Cox regression, random survival forests, and extreme gradient boosting were 0.70, 0.69 and 0.70, respectively, when the data were generated from a Cox regression model in a large sample-size conditions. In contrast, the estimated c-index values for these models were 0.64, 0.64, and 0.65 when the data were generated from a random survival forest in a large sample size conditions. Both Cox regression and random survival forest had the lowest ICI values (0.12 for a large sample size and 0.18 for a small sample size) among all the investigated models regardless of sample size and data generating model.ConclusionCox regression models have comparable, and sometimes better predictive performance, than more complex machine learning models. We recommend that the choice among these models should be guided by important considerations for research hypotheses, model interpretability, and type of data.

Project description:BackgroundMild cognitive impairment and cognitive impairment, no dementia, are emerging terms that encompass the clinical state between normal cognition and dementia in elderly people. Controversy surrounds their characterization, definition and application in clinical practice. In this article, we provide physicians with practical guidance on the definition, diagnosis and treatment of mild cognitive impairment and cognitive impairment, no dementia, based on recommendations from the Third Canadian Consensus Conference on the Diagnosis and Treatment of Dementia, held in March 2006.MethodsWe developed evidence-based guidelines using systematic literature searches, with specific criteria for study selection and quality assessment, and a clear and transparent decision-making process. We selected studies published from January 1996 to December 2005 that had mild cognitive impairment or cognitive impairment, no dementia, as the outcome. Subsequent to the conference, we searched for additional articles published between January 2006 and January 2008. We graded the strength of evidence using the criteria of the Canadian Task Force on Preventive Health Care.ResultsWe identified 2483 articles, of which 314 were considered to be relevant and of good or fair quality. From a synthesis of the evidence in these studies, we made 16 recommendations. In brief, family physicians should be aware that most types of dementia are preceded by a recognizable phase of mild cognitive decline. They should be familiar with the concepts of mild cognitive impairment and of cognitive impairment, no dementia. Patients with these conditions should be closely monitored because of their increased risk for dementia. Leisure activities, cognitive stimulation and physical activity could be promoted as part of a healthy lifestyle in elderly people and those with mild cognitive impairment. Vascular risk factors should be treated optimally. No other specific therapies can yet be recommended.InterpretationPhysicians will increasingly see elderly patients with mild memory loss, and learning an approach to diagnosing states such as mild cognitive impairment is now warranted. Close monitoring for progression to dementia, promotion of a healthy lifestyle and treatment of vascular risk factors are recommended for the management of patients with mild cognitive impairment.

Project description:IntroductionAlzheimer's disease patients are reported to have higher survival rate compared to patients with vascular dementia or dementia with Lewy bodies. There is a paucity of studies investigating survival including persons with cognitive decline and dementia of various aetiologies.ObjectivesWe aimed to compare survival for patients with subjective cognitive decline, mild cognitive impairment, Alzheimer's disease, vascular dementia, mixed Alzheimer's/vascular dementia, dementia with Lewy bodies/Parkinson's disease, and other dementias compared to the general Norwegian population, taking into account the role of gender, cognitive function, function in everyday activities, comorbidity and education.MethodsPatients (N = 4682), ≥65 years, in the The Norwegian register of persons assessed for cognitive symptoms (NorCog) during 2009-2017 were followed for mortality in the National Registry until January 2018. Flexible parametric survival models were applied to estimate relative survival, life expectancy and years of life lost for diagnostic groups compared with the general population.ResultsPatients with vascular dementia or dementia with Lewy bodies/Parkinson's had the shortest survival, followed by mixed dementia, Alzheimer's disease, unspecified dementia, mild cognitive impairment and subjective cognitive decline. At age 70 years, men with vascular dementia or dementia with Lewy bodies/Parkinson's had life expectancy of 4.7 years, which corresponded to 10.3 years of life lost compared to the general population. Years of life lost for other diagnoses were 10.0 years for mixed dementia, 9.2 years for Alzheimer's disease, 9.3 years for other dementias, 5.2 years for mild cognitive impairment and 2.2 years for subjective cognitive decline. Corresponding years of life lost in women were: 12.7 years, 10.5 years, 9.8 years, 10.6 years, 7.8 years, and 2.6 years. Poor relative survival among dementia patients was associated with male gender, comorbidity, low cognitive function, and low function in activities of daily living.ConclusionsCompared with the general population, patients with subjective cognitive decline had no significant loss in life expectancy, while patients with mild cognitive impairment and all dementia subtypes had large losses, especially those with a diagnosis of vascular dementia or dementia with Lewy bodies/Parkinson's.