Identifying incident dementia by applying machine learning to a very large administrative claims dataset

PLoS One. 2019 Jul 5;14(7):e0203246. doi: 10.1371/journal.pone.0203246. eCollection 2019.

Abstract

Alzheimer's disease and related dementias (ADRD) are highly prevalent conditions, and prior efforts to develop predictive models have relied on demographic and clinical risk factors using traditional logistical regression methods. We hypothesized that machine-learning algorithms using administrative claims data may represent a novel approach to predicting ADRD. Using a national de-identified dataset of more than 125 million patients including over 10,000 clinical, pharmaceutical, and demographic variables, we developed a cohort to train a machine learning model to predict ADRD 4-5 years in advance. The Lasso algorithm selected a 50-variable model with an area under the curve (AUC) of 0.693. Top diagnosis codes in the model were memory loss (780.93), Parkinson's disease (332.0), mild cognitive impairment (331.83) and bipolar disorder (296.80), and top pharmacy codes were psychoactive drugs. Machine learning algorithms can rapidly develop predictive models for ADRD with massive datasets, without requiring hypothesis-driven feature engineering.

MeSH terms

  • Adult
  • Aged
  • Aged, 80 and over
  • Algorithms
  • Cognitive Dysfunction / diagnosis*
  • Cognitive Dysfunction / epidemiology
  • Datasets as Topic
  • Dementia / diagnosis*
  • Dementia / epidemiology
  • Female
  • Humans
  • Incidence
  • Machine Learning*
  • Male
  • Middle Aged

Grants and funding

Optum provided support in the form of salaries for authors [VSN, CAH, DCM, ADK, DMS], but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific roles of these authors are articulated in the ‘author contributions’ section.