Machine learning characterization of a rare neurologic disease via electronic health records: a proof-of-principle study on stiff person syndrome.

Journal: BMC neurology
PMID: 39097681

Abstract

BACKGROUND: Despite the frequent diagnostic delays of rare neurologic diseases (RND), it remains difficult to study RNDs and their comorbidities due to their rarity and hence the statistical underpowering. Affecting one to two in a million annually, stiff person syndrome (SPS) is an RND characterized by painful muscle spasms and rigidity. Leveraging underutilized electronic health records (EHR), this study showcased a machine-learning-based framework to identify clinical features that optimally characterize the diagnosis of SPS.

Authors

  • Soo Hwan Park
    Geisel School of Medicine at Dartmouth, Hanover, NH, USA.
  • Seo Ho Song
    Department of Psychiatry, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA.
  • Frederick Burton
    Department of Psychiatry, University of California Los Angeles Health, Los Angeles, CA, USA.
  • Cybèle Arsan
    Department of Psychiatry, Oakland Medical Center, Kaiser Permanente, Oakland, CA, USA.
  • Barbara Jobst
    Geisel School of Medicine at Dartmouth, Hanover, NH, USA.
  • Mary Feldman
    Geisel School of Medicine at Dartmouth, Hanover, NH, USA. Mary.S.Feldman@hitchcock.org.

Keywords

External Resources

Popular Topics
Recent Journals