Deep neural network models for identifying incident dementia using claims and EHR datasets

PLoS One. 2020 Sep 24;15(9):e0236400. doi: 10.1371/journal.pone.0236400. eCollection 2020.

Abstract

This study investigates the use of deep learning methods to improve the accuracy of a predictive model for dementia, and compares the performance to a traditional machine learning model. With sufficient accuracy the model can be deployed as a first round screening tool for clinical follow-up including neurological examination, neuropsychological testing, imaging and recruitment to clinical trials. Seven cohorts with two years of data, three to eight years prior to index date, and an incident cohort were created. Four trained models for each cohort, boosted trees, feed forward network, recurrent neural network and recurrent neural network with pre-trained weights, were constructed and their performance compared using validation and test data. The incident model had an AUC of 94.4% and F1 score of 54.1%. Eight years removed from index date the AUC and F1 scores were 80.7% and 25.6%, respectively. The results for the remaining cohorts were between these ranges. Deep learning models can result in significant improvement in performance but come at a cost in terms of run times and hardware requirements. The results of the model at index date indicate that this modeling can be effective at stratifying patients at risk of dementia. At this time, the inability to sustain this quality at longer lead times is more an issue of data availability and quality rather than one of algorithm choices.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Aged
  • Aged, 80 and over
  • Cohort Studies
  • Deep Learning
  • Dementia / diagnosis*
  • Dementia / epidemiology
  • Electronic Health Records
  • Female
  • Humans
  • Male
  • Neural Networks, Computer
  • Risk Factors

Grants and funding

The project was sponsored by OptumLabs, Global CEO Initiative, Biogen, Janssen Pharmaceutical, and Merck. A donation of computer hardware by Dell was graciously received, which allowed the project to fit large models efficiently. OptumLabs provided support in the form of salaries for authors [VSN, CAH, YS, WHC, PAB], 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.