RISK EVALUATION METHOD, RISK EVALUATION DEVICE, AND RISK EVALUATION PROGRAM

• Main Authors: NAKAMURA SHINICHIRO, TAKADA MASATO, ISADA KATSUYA
• Format: Patent
• Language: English; Japanese
• Published: 09.01.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

To provide a technique for improving accuracy in evaluating magnitudes of risks related to health conditions of subjects.SOLUTION: A risk evaluation method causes a computer to execute: a step of obtaining, from a storage unit, medical examination information including measured values of physical examinations for a predetermined period of a plurality of subjects and receipt information including medical expenses and injury/illness names for the predetermined period of the plurality of subjects; a model creation step of creating a model including interaction terms formed by the products of explanatory variables, with the measured values of predetermined measurement items included in the medical examination information and the number of consultations with the predetermined injury/illness names obtained by summing up the receipt information as the explanatory variables, the model representing a probability that the medical expenses are equal to or more than a predetermined threshold with the predetermined injury/illness names in the receipt information; and a risk evaluation step of reading the medical examination information of the subjects after the predetermined period from the storage unit and calculating risk evaluation values using the values based on the medical examination information and the model.SELECTED DRAWING: Figure 1 【課題】対象者の健康状態に関するリスクの大きさを評価する際の精度を向上させるための技術を提供する。【解決手段】リスク評価方法は、複数の対象者の所定期間における健康診断の測定値を含む健診情報と、複数の対象者の所定期間における医療費及び傷病名を含むレセプト情報とを記憶部から取得するステップと、健診情報に含まれる所定の測定項目の測定値、及びレセプト情報を集計して求められる所定の傷病名での受診回数を説明変数として、当該説明変数の積によって形成される交互作用項を含み、レセプト情報において所定の傷病名で且つ医療費が所定の閾値以上となる確率を表すモデルを作成するモデル作成ステップと、対象者の所定期間以降における健診情報を記憶部から読み出し、当該健診情報に基づく値とモデルとを用いてリスクの評価値を算出するリスク評価ステップとをコンピュータが実行する。【選択図】図１