Article Text

Download PDFPDF

SAT0309 Can we foresee sle in itp patients? to distinguish itp patients with high risk of sle by a nationwide cohort study-based decision tree
  1. T-H Li1,
  2. Y-S Chang2,
  3. C-Y Tsai3
  1. 1Division of Allergy, Immunology and Rheumatology, Department of Internal Medicine, Chiayi Branch, Taichung Veteran General Hospital, Chiayi City
  2. 2Division of Allergy, Immunology and Rheumatology, Department of Internal Medicine, Taipei Hospital, Ministry of Health and Welfare, New Taipei City
  3. 3Division of Allergy, Immunology and Rheumatology, Department of Internal Medicine, Taipei Veteran General Hospital, Taipei City, Taiwan, Province of China


Background Immune thrombocytopenic purpura (ITP) is an autoimmune-associated thrombocytopenia which is occasionally the initial presentation of systemic lupus erythematosus (SLE), and thus periodical following up has been suggested. Whereas long-term surveillance on all ITP patients would be time and cost-consuming, and thus to distinguish those with high probability of SLE development among ITP patients should be more practical.

Objectives To distinguish ITP patients with high risk of SLE development by a decision tree model.

Methods We enrolled ITP patients without previous SLE diagnosis from the National Health Insurance research database between 1997 and 2012 and identified those certificated with catastrophic illness of SLE during follow up, by which the diagnosis was reconfirmed by another rheumatologists. We also analyzed the symptoms and comorbidities as well as the dose of average oral steroid to derive the decision trees, which classified the ITP patients with different probability of development of SLE.

Results A total of 10,265 ITP patients were enrolled, among whom 80 patients developed SLE while following-up. The whole ITP patients were allocated to training group (7,186 patients including 57 with SLE) and testing group (3,079 patients including 23 with SLE); the former was used for derivation of the decision-tree based model and the latter for validation of the previously mentioned model, and provided high sensitivity (78.2%), specificity (99.2%) and negative prediction value (99.8%, Fig.). To reduce the complexity, we also pruned our decision tree to propose less-complicated models.

Conclusions We derived classification decision tree suitable for various clinical scenarios of ITP patients, among whom those with high probability of development of SLE would be distinguished.


  1. Balsalobre Aznar J, Herráez Herrera P, Porta Etessam J, Torres Martín C, Bermell Serrano JC, Núñez Lόpez R, et al. Idiopathic thrombocytopenic purpura as first manifestation of systemic lupus erythematosus lupus. An Med Interna. 1999;16:611–4.

  2. Risk factors for future development of systemic lupus erythematosus in children with idiopathic thrombocytopenic purpura. Pediatr Blood Cancer. 2006;47(5 Suppl):657–9.


Disclosure of Interest None declared

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.