A methodology of phenotyping ICU patients from EHR data: high-fidelity, personalized, and interpretable phenotypes estimation

Abstract

Phenotyping methods aiming to produce high-fidelity time-dependent phenotypes in a specific context with personalized interpretation are challenging, especially given the complexity of physiological systems and data quality. We present a three-stage methodological phenotyping pipeline based on a mechanistic physiological model framework applied to the glucose-insulin system of ICU patients from electronic health record data. Balancing flexibility and biological fidelity, the pipeline within the data assimilation (DA) framework is used to compute physiologically-anchored phenotypes that are high-fidelity, personalized, time-sensitive, and interpretable using data present in real-time ICU settings. We construct the computational phenotyping pipeline such that it is generalizable and we demonstrate the pipeline's accuracy and reliability through external data evaluation using electronic health record data and clinical face validation.

Competing Interest Statement

The authors have declared no competing interest.

Funding Statement

The work is supported by US National Institutes of Health (NIH)/National Library of Medicine \# 5R01LM012734.

Author Declarations

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Colorado Multiple Institutional Review Board gave ethical approval for this work

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

Data Availability

All data produced in the present work are PHI ruled by HIPPA and unavailable for sharing.

留言 (0)

沒有登入
gif