Publications by authors named "Christine J Cliatt Brown"
Predicting the onset of Alzheimer's disease and related dementia using electronic health records: findings from the cache county study on memory in aging (1995-2008).
BMC Med Inform Decis Mak
October 2024
Article Synopsis
- This research explores whether structured clinical data can predict dementia diagnoses, using a machine learning model on a population-based cohort.
- The study linked healthcare data and sociodemographic information, finding that 12.4% of participants were diagnosed with dementia, with Random Forest models yielding an Area Under the Curve (AUC) of 0.67 for overall predictions.
- While structured clinical data showed some predictive capability, using ICD codes improved accuracy to 0.77, indicating a need for further research to ensure these models accurately identify true dementia cases.
Introduction: The C9orf72 mutation can manifest in diverse clinical ways, including rapid cognitive decline, parkinsonism, or late-life neuropsychiatric symptoms, sometimes mimicking autoimmune encephalitis.
Case Report: A 64-year-old female presented to the autoimmune neurology clinic with rapidly progressive dementia (RPD) associated with episodes of headache, confusion, auditory hallucinations, and abnormal electroencephalogram. She was treated empirically at an outside hospital for possible autoimmune encephalitis with intravenous methylprednisolone, but there was no improvement, and rapid cognitive decline continued.
Introduction: Clinical notes, biomarkers, and neuroimaging have been proven valuable in dementia prediction models. Whether commonly available structured clinical data can predict dementia is an emerging area of research. We aimed to predict Alzheimer's disease (AD) and Alzheimer's disease related dementias (ADRD) in a well-phenotyped, population-based cohort using a machine learning approach.
View Article and Find Full Text PDF