Estimation of the epidemiology of dementia and associated neuropsychiatric symptoms by applying machine learning to real-world data

INTRODUCTION

Incidence rates of dementia-related neuropsychiatric symptoms (NPS) are not known and this hampers the assessment of their population burden. The objective of this study was to obtain an approximate estimate of the population incidence and prevalence of both dementia and NPS.

METHODS

Given the dynamic nature of the population with dementia, a retrospective study was conducted within the database of the Basque Health Service (real-world data) at the beginning and end of 2019. Validated random forest models were used to identify separately depressive and psychotic clusters according to their presence in the electronic health records of all patients diagnosed with dementia.

RESULTS

Among the 631,949 individuals over 60 years registered, 28,563 were diagnosed with dementia, of whom 15,828 (55.4%) showed psychotic symptoms and 19,461 (68.1%) depressive symptoms. The incidence of dementia in 2019 was 6.8/1000 person-years. Most incident cases of depressive (72.3%) and psychotic (51.9%) NPS occurred in cases of incident dementia. The risk of depressive-type NPS grows with years since dementia diagnosis, living in a nursing home, and female sex, but falls with older age. In the psychotic cluster model, the effects of male sex, and older age are inverted, both increasing the probability of this type of symptoms.

CONCLUSIONS

The stigmatization factor conditions the social and attitudinal environment, delaying the diagnosis of dementia, preventing patients from receiving adequate care and exacerbating families' suffering. This study evidences the synergy between big data and real-world data for psychiatric epidemiological research.

Estimation of the epidemiology of dementia and associated neuropsychiatric symptoms by applying machine learning to real-world data

INTRODUCTION

Incidence rates of dementia-related neuropsychiatric symptoms (NPS) are not known and this hampers the assessment of their population burden. The objective of this study was to obtain an approximate estimate of the population incidence and prevalence of both dementia and NPS.

METHODS

Given the dynamic nature of the population with dementia, a retrospective study was conducted within the database of the Basque Health Service (real-world data) at the beginning and end of 2019. Validated random forest models were used to identify separately depressive and psychotic clusters according to their presence in the electronic health records of all patients diagnosed with dementia.

RESULTS

Among the 631,949 individuals over 60 years registered, 28,563 were diagnosed with dementia, of whom 15,828 (55.4%) showed psychotic symptoms and 19,461 (68.1%) depressive symptoms. The incidence of dementia in 2019 was 6.8/1000 person-years. Most incident cases of depressive (72.3%) and psychotic (51.9%) NPS occurred in cases of incident dementia. The risk of depressive-type NPS grows with years since dementia diagnosis, living in a nursing home, and female sex, but falls with older age. In the psychotic cluster model, the effects of male sex, and older age are inverted, both increasing the probability of this type of symptoms.

CONCLUSIONS

The stigmatization factor conditions the social and attitudinal environment, delaying the diagnosis of dementia, preventing patients from receiving adequate care and exacerbating families' suffering. This study evidences the synergy between big data and real-world data for psychiatric epidemiological research.

Validation of Random Forest Machine Learning Models to Predict Dementia-Related Neuropsychiatric Symptoms in Real-World Data

BACKGROUND

Neuropsychiatric symptoms (NPS) are the leading cause of the social burden of dementia but their role is underestimated.

OBJECTIVE

The objective of the study was to validate predictive models to separately identify psychotic and depressive symptoms in patients diagnosed with dementia using clinical databases representing the whole population to inform decision-makers.

METHODS

First, we searched the electronic health records of 4,003 patients with dementia to identify NPS. Second, machine learning (random forest) algorithms were applied to build separate predictive models for psychotic and depressive symptom clusters in the training set (N = 3,003). Third, calibration and discrimination were assessed in the test set (N = 1,000) to assess the performance of the models.

RESULTS

Neuropsychiatric symptoms were noted in the electronic health record of 58% of patients. The area under the receiver operating curve reached 0.80 for the psychotic cluster model and 0.74 for the depressive cluster model. The Kappa index and accuracy also showed better discrimination in the psychotic model. Calibration plots indicated that both types of model had less predictive accuracy when the probability of neuropsychiatric symptoms was <25%. The most important variables in the psychotic cluster model were use of risperidone, level of sedation, use of quetiapine and haloperidol and the number of antipsychotics prescribed. In the depressive cluster model, the most important variables were number of antidepressants prescribed, escitalopram use, level of sedation, and age.

CONCLUSION

Given their relatively good performance, the predictive models can be used to estimate prevalence of NPS in population databases.