Rare Diseases Symptoms Automatic Extraction

A Temporal Pattern Mining Approach for Classifying Electronic Health Record Data.

[heparin-induced thrombocytopenia]

We study the problem of learning classification models from complex multivariate temporal data encountered in electronic health record systems. The challenge is to define a good set of features that are able to represent well the temporal aspect of the data. Our method relies on temporal abstractions and temporal pattern mining to extract the classification features. Temporal pattern mining usually returns a large number of temporal patterns, most of which may be irrelevant to the classification task. To address this problem, we present the Minimal Predictive Temporal Patterns framework to generate a small set of predictive and non-spurious patterns. We apply our approach to the real-world clinical task of predicting patients who are at risk of developing heparin induced thrombocytopenia. The results demonstrate the benefit of our approach in efficiently learning accurate classifiers, which is a key step for developing intelligent clinical monitoring systems.

Diseases presenting "large number" symptom

  • acute rheumatic fever
  • adrenal incidentaloma
  • allergic bronchopulmonary aspergillosis
  • canavan disease
  • coats disease
  • cowden syndrome
  • dedifferentiated liposarcoma
  • dracunculiasis
  • epidermolysis bullosa simplex
  • fabry disease
  • familial mediterranean fever
  • gm1 gangliosidosis
  • heparin-induced thrombocytopenia
  • hereditary cerebral hemorrhage with amyloidosis
  • hirschsprung disease
  • kindler syndrome
  • legionellosis
  • malignant atrophic papulosis
  • neuralgic amyotrophy
  • phenylketonuria
  • pleomorphic liposarcoma
  • primary effusion lymphoma
  • scrub typhus
  • severe combined immunodeficiency
  • triple a syndrome
  • waldenström macroglobulinemia
  • well-differentiated liposarcoma
  • wiskott-aldrich syndrome
  • wolf-hirschhorn syndrome
  • x-linked adrenoleukodystrophy
  • zellweger syndrome

You can validate or delete this automatically detected symptom