Article

Auditing missingness and input-outcome circularity in unsupervised clinical phenotyping: an empirical case study in hospitalized traumatic brain injury

2026-08-10

Abstract excerpt

<title>Abstract</title> <p>**Background:** Routinely collected clinical scale data are increasingly used for unsupervised phenotyping, but two design choices are often under-audited: how missing scale values are handled, and whether variables later interpreted as outcomes were also used to define the clusters. We used a hospitalized traumatic brain injury (TBI) scale dataset as an empirical case study to audit mi...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: db4ab572-5ccb-539e-a51b-5fcc0b5292d9
DOI: 10.21203/rs.3.rs-10251325/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Auditing missingness and input-outcome circularity in unsupervised clinical phenotyping: an empirical case study in hospitalized traumatic brain injuryDOI 10.21203/rs.3.rs-10251325/v1Read

Multicohort development and validation of a machine learning model to predict six-month functional traumatic brain injury outcomes in a large national registrySemantic proximity Read

Phenotyping the Spectrum of Traumatic Brain Injury: A Review and Pathway to Standardization.Semantic proximity Read

Using machine learning to discover traumatic brain injury patient phenotypes: national concussion surveillance system Pilot.Semantic proximity Read

Unsupervised Machine Learning Reveals Novel Traumatic Brain Injury Patient Phenotypes with Distinct Acute Injury Profiles and Long-Term Outcomes.Semantic proximity Read

Development and internal validation of a machine learning–based prediction model and simplified screening score for in-hospital falls: a retrospective cohort studySemantic proximity Read

Imputation strategies for missing baseline neurological assessment covariates after traumatic brain injury: A CENTER-TBI studySemantic proximity Read

Age-Stratified ICU Mortality Is Systematically Miscalibrated in Published Clinical Estimates: Cross-Validated Evidence from 201,905 Encounters Across Two Independent DatasetsSemantic proximity Read

Large-scale automated phenotyping of cardiac arrest and withdrawal of life-sustaining therapy using electronic health record data.Semantic proximity Read

Phenotyping to predict 12-month health outcomes of older general medicine patientsSemantic proximity Read

Data-driven distillation and precision prognosis in traumatic brain injury with interpretable machine learning.Semantic proximity Read

Clinical phenotypes of patients with acute stroke: a secondary analysis.Semantic proximity Read

Predicting Traumatic Brain Injury Outcomes with Machine Learning: Development and External Validation in Two Indonesian Tertiary HospitalsSemantic proximity Read