Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 3, 2026

Phenotypic Profiling of Human Stem Cell-Derived Midbrain Dopaminergic Neurons
09:21

Phenotypic Profiling of Human Stem Cell-Derived Midbrain Dopaminergic Neurons

Published on: July 7, 2023

Evaluating unsupervised and rule-based phenotyping methods versus administrative code counts for systemic sclerosis

Yiming Luo1, Gongbo Zhang2, Aradhna Agarwal1

  • 1Division of Rheumatology and Clinical Immunology, Department of Medicine, Vagelos College of Physicians and Surgeons, Columbia University Irving Medical Center, New York, New York, USA.

Seminars in Arthritis and Rheumatism
|July 1, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

RankVar: machine learning-based variant ranking and reinterpretation for rare genetic diseases.

Genome medicine·2026
Same authorSame journal

Autoantibody associations in patients with early diffuse cutaneous systemic sclerosis: the prospective registry of early systemic sclerosis.

Seminars in arthritis and rheumatism·2026
Same author

Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization.

Proceedings of the conference. Association for Computational Linguistics. Meeting·2026
Same author

Hard to Halt: Automation Bias in Agent-Driven Sequencing Prior Authorization Workflows.

medRxiv : the preprint server for health sciences·2026
Same author

Unsupervised characterization of 100,272 EHR patients identifies high-risk groups and comorbidities linked to premature aging.

NPJ digital medicine·2026
Same author

TimeX: Phenotype Onset Extraction from Clinical Narratives.

npj health systems·2026
This summary is machine-generated.

Linear combinations of principal components (LPC) and phenotype risk score (PheRS) show improved mortality prediction for systemic sclerosis (SSc) patients compared to ICD M34 code counts. Both methods offer comparable SSc identification performance.

Area of Science:

  • Rheumatology
  • Medical Informatics
  • Machine Learning

Background:

  • Systemic sclerosis (SSc) diagnosis and mortality prediction are critical challenges in clinical practice.
  • Electronic health records (EHR) offer a rich data source for developing predictive models.
  • Current methods for SSc identification using EHR data have limitations.

Purpose of the Study:

  • To evaluate unsupervised machine learning (linear combinations of principal components - LPC) and rule-based (phenotype risk score - PheRS) approaches for SSc identification and mortality prediction.
  • To compare the performance of LPC, PheRS, and International Classification of Disease (ICD) M34 code counts using EHR data.

Main Methods:

  • A retrospective single-center study was conducted.
  • SSc-specific PheRS and LPC scores were developed using 17 clinical features from EHR data.
Keywords:
Electronic health recordPhenotype identificationSystemic sclerosis

Related Experiment Videos

Last Updated: Jul 3, 2026

Phenotypic Profiling of Human Stem Cell-Derived Midbrain Dopaminergic Neurons
09:21

Phenotypic Profiling of Human Stem Cell-Derived Midbrain Dopaminergic Neurons

Published on: July 7, 2023

  • The performance of LPC, PheRS, and M34 code counts was assessed for SSc identification and mortality prediction.

    • Main Results:

    • LPC demonstrated superior performance over PheRS in identifying rheumatologist-diagnosed SSc when compared to matched controls (AUROC 0.90 vs 0.87).
    • In a three-method comparison, LPC, PheRS, and M34 code counts showed marginal differences in distinguishing SSc from non-SSc controls (AUROC 0.72, 0.70, 0.70, respectively).
    • LPC and PheRS significantly outperformed M34 code counts in predicting mortality among SSc patients (AUROC 0.74, 0.72 vs 0.63).

    Conclusions:

    • M34 code counts provide reasonable performance for SSc identification, comparable to LPC and PheRS.
    • LPC and PheRS exhibit superior performance in predicting mortality in SSc patients compared to M34 code counts.
    • These findings highlight the potential of advanced analytical methods for improving SSc patient outcomes.