Construct a mathematical model for optimizing the glucocorticoid replacement in patients with adrenocortical insufficiency

2015 Fiscal Year Final Research Report

• Project/Area Number: 25730179
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Life / Health / Medical informatics
• Research Institution: Tohoku Pharmaceutical University
• Principal Investigator: AOKI Sorama 東北薬科大学, 薬学部, 助手 (40584462)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: ステロイド補充療法 / データマイニング / クッシング症候群 / 副腎不全 / 基本的検査 / ステロイド / パターン認識 / インフォマティクス

Outline of Final Research Achievements

Using the self-organizing map which is one of the pattern recognition methods, we successfully constructed the model that can predict the lack of and the excess of the internal glucocorticoids, making use of a set of 13 routine tests ( γ-glutamyl trans peptitase [γ - GTP], lactate dehydrogenase [LDH], serum sodium [Na], serum potassium [K], serum chlorine [Cl], high density lipoprotein cholesterol [HDL-C], neutrophil count [Neut#], eosinophil count [Eosi#], lymphocyte counts [Lymp#], monocyte count [Mono#], red blood cell count [RBC], hemoglobin [Hg], hematocrit [HCT].
Furthermore, we quantitatively represented the effects of the internal glucocorticoids against the each of the routine tests by a simultaneous differential equation.

Free Research Field

医療情報学