Trends and opportunities in computable clinical phenotyping: A scoping review

He, Ting; Belouali, Anas; Patricoski, Jessica; Lehmann, Harold P.; Ball, Robert; Anagnostou, Valsamo; Kreimeyer, Kory; Botsis, Taxiarchis

doi:10.1016/j.jbi.2023.104335

Cited by 13 publications

(5 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although previously studies have highlighted the limitations in using EMR for phenotyping such as complex, inaccurate, and missing data problems [ 27 , 28 ], our approach uses a wide range of clinical features from EMR data and has been shown to work efficiently in both derivation and validation datasets. Our study phenotypes show results consistent with the corresponding MODs.…”

Section: Discussionmentioning

confidence: 99%

Derivation and Validation of Generalized Sepsis-induced Acute Respiratory Failure Phenotypes Among Critically Ill Patients: A Retrospective Study

Choudhary,

Upadhyaya,

Davis

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Septic patients who develop acute respiratory failure (ARF) requiring mechanical ventilation represent a heterogenous subgroup of critically ill patients with widely variable clinical characteristics. Identifying distinct phenotypes of these patients may reveal insights about the broader heterogeneity in the clinical course of sepsis. We aimed to derive novel phenotypes of sepsis-induced ARF using observational clinical data and investigate their generalizability across multi-ICU specialties, considering multi-organ dynamics. Methods: We performed a multi-center retrospective study of ICU patients with sepsis who required mechanical ventilation for ≥24 hours. Data from two different high-volume academic hospital systems were used as a derivation set with N=3,225 medical ICU (MICU) patients and a validation set with N=848 MICU patients. For the multi-ICU validation, we utilized retrospective data from two surgical ICUs at the same hospitals (N=1,577). Clinical data from 24 hours preceding intubation was used to derive distinct phenotypes using an explainable machine learning-based clustering model interpreted by clinical experts. Results: Four distinct ARF phenotypes were identified: A (severe multi-organ dysfunction (MOD) with a high likelihood of kidney injury and heart failure), B (severe hypoxemic respiratory failure [median P/F=123]), C (mild hypoxia [median P/F=240]), and D (severe MOD with a high likelihood of hepatic injury, coagulopathy, and lactic acidosis). Patients in each phenotype showed differences in clinical course and mortality rates despite similarities in demographics and admission co-morbidities. The phenotypes were reproduced in external validation utilizing an external MICU from second hospital and SICUs from both centers. Kaplan-Meier analysis showed significant difference in 28-day mortality across the phenotypes (p<0.01) and consistent across both centers. The phenotypes demonstrated differences in treatment effects associated with high positive end-expiratory pressure (PEEP) strategy. Conclusion: The phenotypes demonstrated unique patterns of organ injury and differences in clinical outcomes, which may help inform future research and clinical trial design for tailored management strategies.

show abstract

Section: Discussionmentioning

confidence: 99%

Derivation and Validation of Generalized Sepsis-induced Acute Respiratory Failure Phenotypes Among Critically Ill Patients: A Retrospective Study

Choudhary,

Upadhyaya,

Davis

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Even forward-looking and innovative enterprise-wide query approaches, such as the Duke University Enterprise Data Unified Content Explorer (DEDUCE), struggled to provide service and data at scale (17). Two recent reviews described the challenges associated with the preliminary step of leveraging data to identify “computable clinical” (15) or “digital” (11) phenotypes and concluded that new, more efficient, and automated approaches are needed to accelerate research.…”

Section: Discussionmentioning

confidence: 99%

Automated self-service cohort selection for large-scale population sciences and observational research: The California Teachers Study Researcher Platform

Lacey,

Spielfogel,

Benbow

et al. 2023

Preprint

View full text Add to dashboard Cite

ObjectiveCohort selection is ubiquitous and essential, but manual and ad hoc approaches are time-consuming, labor-intense, and difficult to scale. We sought to automate the task of cohort selection by building self-service tools that enable researchers to independently generate datasets for population sciences research.Materials and MethodsThe California Teachers Study (CTS) is a prospective observational study of 133,477 women who have been followed continuously since 1995. The CTS includes extensive survey-based and real-world data from cancer, hospitalization, and mortality linkages. We curated data from our data warehouse into a column-oriented database and developed a researcher-facing web application that guides researchers through the project lifecycle; captures researchers’ inputs; and automatically generates custom and analysis-ready data, code, dictionaries, and documentation.ResultsResearchers can register, access data, and propose projects on the CTS Researcher Platform via our CTS website. The Platform supports cohort and cross-sectional study designs for cancer, mortality, and any other ICD-based phenotypes or endpoints. User-friendly prompts and menus capture analytic design, inclusion/exclusion criteria, endpoint definitions, censoring rules, and covariate selection. Our platform empowers researchers everywhere to query, choose, review, and automatically and quickly receive custom data, analytic scripts, and documentation for their research projects. Research teams can review, revise, and update their choices anytime.DiscussionWe replaced inefficient traditional cohort-selection processes with an integrated self-service approach that simplifies and improves cohort selection for all stakeholders. Compared with manual methods, our solution is faster and more scalable, user-friendly, and collaborative. Other studies could re-configure our individual database, project-tracking, website, and data-delivery components for their own specific needs, or they could utilize other widely available solutions (e.g., alternative database or project-tracking tools) to enable similarly automated cohort-selection in their own settings. Our comprehensive and flexible framework could be adopted to improve cohort selection in other population sciences and observational research settings.

show abstract

“…Manually selecting or creating the relevant medical features for computable phenotypes from thousands of EHR features is time intensive and requires extensive domain knowledge. For poorly understood diseases, feature selection is even more difficult [23,24]. This has opened another area of EHR clinical research into medical feature extraction and concept representations [25,26], such as knowledge graphs.…”

Section: Introductionmentioning

confidence: 99%

Multi-Source Graph Synthesis (MUGS) for Pediatric Knowledge Graphs from Electronic Health Records

Li,

Pan

et al. 2024

Preprint

View full text Add to dashboard Cite

The wealth of valuable real-world medical data found within Electronic Health Record (EHR) systems is particularly significant in the field of pediatrics, where conventional clinical studies face notably high barriers. However, constructing accurate knowledge graphs from pediatric EHR data is challenging due to its limited content density compared to EHR data for the general population. Additionally, knowledge graphs built from EHR data primarily covering adult patients may not suit the unique biomedical characteristics of pediatric patients. In this research, we introduce a graph transfer learning approach aimed at constructing precise pediatric knowledge graphs. We present MUlti-source Graph Synthesis (MUGS), an algorithm designed to create embeddings for pediatric EHR codes by leveraging information from three distinct sources: (1) pediatric EHR data, (2) EHR data from the general population, and (3) existing hierarchical medical ontology knowledge shared across different patient populations. We break down these code embeddings into shared and unshared components, facilitating the adaptive and robust capture of varying levels of heterogeneity across different medical sites through meticulous hyperparameter tuning. We assessed the quality of these code embeddings in recognizing established relationships among pediatric codes, as curated from credible online sources, pediatric physicians, or GPT. Furthermore, we developed a web API for visualizing pediatric knowledge graphs generated using MUGS embeddings and devised a phenotyping algorithm to identify patients with characteristics similar to a given profile, with a specific focus on pediatric pulmonary hypertension (PH). The MUGS-generated embeddings demonstrated resilience against negative transfer and exhibited superior performance across all three tasks when compared to pediatric-only approaches, multi-site pooling, and semantic-based methods. MUGS embeddings open up new avenues for evidence-based pediatric research utilizing EHR data.

show abstract

Trends and opportunities in computable clinical phenotyping: A scoping review

Cited by 13 publications

References 81 publications

Derivation and Validation of Generalized Sepsis-induced Acute Respiratory Failure Phenotypes Among Critically Ill Patients: A Retrospective Study

Derivation and Validation of Generalized Sepsis-induced Acute Respiratory Failure Phenotypes Among Critically Ill Patients: A Retrospective Study

Automated self-service cohort selection for large-scale population sciences and observational research: The California Teachers Study Researcher Platform

Multi-Source Graph Synthesis (MUGS) for Pediatric Knowledge Graphs from Electronic Health Records

Contact Info

Product

Resources

About