sureLDA: A multidisease automated phenotyping method for the electronic health record

Abstract

Objective A major bottleneck hindering utilization of electronic health record data for translational research is the lack of precise phenotype labels. Chart review as well as rule-based and supervised phenotyping approaches require laborious expert input, hampering applicability to studies that require many phenotypes to be defined and labeled de novo. Though International Classification of Diseases codes are often used as surrogates for true labels in this setting, these sometimes suffer from poor specificity. We propose a fully automated topic modeling algorithm to simultaneously annotate multiple phenotypes. Materials and Methods Surrogate-guided ensemble latent Dirichlet allocation (sureLDA) is a label-free multidimensional phenotyping method. It first uses the PheNorm algorithm to initialize probabilities based on 2 surrogate features for each target phenotype, and then leverages these probabilities to constrain the LDA topic model to generate phenotype-specific topics. Finally, it combines phenotype-feature counts with surrogates via clustering ensemble to yield final phenotype probabilities. Results sureLDA achieves reliably high accuracy and precision across a range of simulated and real-world phenotypes. Its performance is robust to phenotype prevalence and relative informativeness of surogate vs nonsurrogate features. It also exhibits powerful feature selection properties. Discussion sureLDA combines attractive properties of PheNorm and LDA to achieve high accuracy and precision robust to diverse phenotype characteristics. It offers particular improvement for phenotypes insufficiently captured by a few surrogate features. Moreover, sureLDA’s feature selection ability enables it to handle high feature dimensions and produce interpretable computational phenotypes. Conclusions sureLDA is well suited toward large-scale electronic health record phenotyping for highly multiphenotype applications such as phenome-wide association studies .

Classifying Pseudogout Using Machine Learning Approaches With Electronic Health Record Data

“…Topic modeling provides a method for identifying discussion of pseudogout in the EHR by combining information from a wide variety of features, including symptoms (e.g., joint swelling), laboratory tests (e.g., synovial fluid crystal analysis), and medications. We employed a novel topic modeling method, called sureLDA, because this method has recently been shown to work well for phenotyping a host of both acute and chronic diseases from EHR data (14). This method predicts a pseudogout propensity score (sureLDA score) for each of the 30,089 patients.…”

Quantitative disease risk scores from EHR with applications to clinical risk stratification and genetic studies

“…Then z PHECODE is predicted with by ordinary least squares regression to obtain the regression coefficient vector β . The final PheNorm score of subject i can be obtained by the weighted linear combination of health care utilization and candidate feature sets, with feature vector z i , The actual implementation follows the scripts in R package sureLDA 50 , where random sampling with replacement of observations in each training set is used to form a bootstrap of size 10 5 .…”

The Digital Analytic Patient Reviewer (DAPR) for COVID-19 Data Mart Validation

“…Large portions of them were healthy prior to admission so they had no rich data to mine. Large volume of missing data raises concerns about the reliability of our phenotyping algorithms [16][17][18][19][20][21][22][23][24][25][26][27][28]. In addition, during the surge, many seriously ill patients did not get coded as having an ICU visit (i.e., a major severity indicator) due to the bed shortage.…”