Clinical phenotyping in selected national networks: demonstrating the need for high-throughput, portable, and computational methods

Abstract

Objective The combination of phenomic data from electronic health records (EHR) and clinical data repositories with dense biological data has enabled genomic and pharmacogenomic discovery, a first step toward precision medicine. Computational methods for the identification of clinical phenotypes from EHR data will advance our understanding of disease risk and drug response, and support the practice of precision medicine on a national scale. Methods Based on our experience within three national research networks, we summarize the broad approaches to clinical phenotyping and highlight the important role of these networks in the progression of high-throughput phenotyping and precision medicine. We provide supporting literature in the form of a non-systematic review. Results The practice of clinical phenotyping is evolving to meet the growing demand for scalable, portable, and data driven methods and tools. The resources required for traditional phenotyping algorithms from expert defined rules are significant. In contrast, machine learning approaches that rely on data patterns will require fewer clinical domain experts and resources. Conclusions Machine learning approaches that generate phenotype definitions from patient features and clinical profiles will result in truly computational phenotypes, derived from data rather than experts. Research networks and phenotype developers should cooperate to develop methods, collaboration platforms, and data standards that will enable computational phenotyping and truly modernize biomedical research and precision medicine.

Genomic characterization and computational phenotyping of nitrogen-fixing bacteria isolated from Colombian sugarcane fields

“…A computational phenotyping approach was developed for the screening of plant growth promoting bacteria for their potential to serve as biofertilizers. Computational phenotyping entails the implementation of a variety of bioinformatic and statistical methods to predict phenotypes of interest based on whole genome sequence analysis (45, 46). This approach has been used for a variety of applications in the biomedical sciences: prediction of clinically relevant phenotypes, study of infectious diseases, identification of opportunistic pathogenic bacteria in the human microbiome, and cancer treatment decisions (47, 48).…”

A Roadmap for Foundational Research on Artificial Intelligence in Medical Imaging: From the 2018 NIH/RSNA/ACR/The Academy Workshop

“…Rule-based natural language EMR can provide labels for diagnostic images. Methods to extract labels from the EMR are often called "electronic phenotyping" because they identify patients with a defined disease, clinical condition, or outcome based on the contents of the EMR (49)(50)(51).…”

Evaluation of Patient-Level Retrieval from Electronic Health Record Data for a Cohort Discovery Task

“…Again, topics 22 and 25 did not return any relevant patients. Three topics had 100% precision (29,34,46).…”

“…Other approaches focus on normalizing semantic representation of patient data within the EHR itself [26] and applying deep learning to non-topical characteristics of studies and researchers [27]. A related area to cohort discovery is patient phenotyping, one of the goals of which is to identify patients for clinical studies [28][29][30]. However, the cohort discovery use case has some differences, as some studies have criteria beyond phenotypic attributes, such as age, past treatments, diagnostic criteria, and temporal considerations.…”