Development of Risk Score for Predicting 3-Year Incidence of Type 2 Diabetes: Japan Epidemiology Collaboration on Occupational Health Study

Abstract

ObjectiveRisk models and scores have been developed to predict incidence of type 2 diabetes in Western populations, but their performance may differ when applied to non-Western populations. We developed and validated a risk score for predicting 3-year incidence of type 2 diabetes in a Japanese population.MethodsParticipants were 37,416 men and women, aged 30 or older, who received periodic health checkup in 2008–2009 in eight companies. Diabetes was defined as fasting plasma glucose (FPG) ≥126 mg/dl, random plasma glucose ≥200 mg/dl, glycated hemoglobin (HbA1c) ≥6.5%, or receiving medical treatment for diabetes. Risk scores on non-invasive and invasive models including FPG and HbA1c were developed using logistic regression in a derivation cohort and validated in the remaining cohort.ResultsThe area under the curve (AUC) for the non-invasive model including age, sex, body mass index, waist circumference, hypertension, and smoking status was 0.717 (95% CI, 0.703–0.731). In the invasive model in which both FPG and HbA1c were added to the non-invasive model, AUC was increased to 0.893 (95% CI, 0.883–0.902). When the risk scores were applied to the validation cohort, AUCs (95% CI) for the non-invasive and invasive model were 0.734 (0.715–0.753) and 0.882 (0.868–0.895), respectively. Participants with a non-invasive score of ≥15 and invasive score of ≥19 were projected to have >20% and >50% risk, respectively, of developing type 2 diabetes within 3 years.ConclusionsThe simple risk score of the non-invasive model might be useful for predicting incident type 2 diabetes, and its predictive performance may be markedly improved by incorporating FPG and HbA1c.

Prediction of Glucose Metabolism Disorder Risk Using a Machine Learning Algorithm: Pilot Study (Preprint)

“…However, in comparable reports on the risk assessment of diabetes, the area under the curves was 0.67 to 0.882. [5][6][7]16] A similar trend was seen in our study. The highest area under the curve was 0.77 for pre-diabetes risk assessment, while the highest area under the curve for diabetes risk assessment was 0.93.…”

“…[22] As far as we know, all previous diabetes risk assessment tools were based on information obtained from questionnaires, such as family history and lifestyle habits. [4][5][6][7]16] Because of this, our results could not be easily compared with previous reports. A previous study showed that combining the results of blood tests and questionnaire information improved the prediction accuracy of diabetes risk assessment.…”

“…A previous study showed that combining the results of blood tests and questionnaire information improved the prediction accuracy of diabetes risk assessment. [16] We will attempt to improve the prediction accuracy of diabetes risk by integrating information obtained from blood tests and information obtained from questionnaires. Second, subjects who underwent multiple examinations were judged to have glucose metabolism disorder if they were diagnosed even once.…”

Development of new diabetes risk scores on the basis of the current definition of diabetes in Japanese subjects [Rapid Communication]

“…Takahiro Miyakoshi 1) , Rie Oka 2) , Yasuto Nakasone 1), 3) , Yuka Sato 1) , Keishi Yamauchi 1) , Rie Hashikura 4) , Masayuki Takayama 5) , Yudai Hirayama 6) , Kazuko Hirabayashi 4) , Hideo Koike 4) and Toru Aizawa However, glycated hemoglobin (HbA1c) criteria was recently added to the definition of DM, so that the currently recommended definition of DM is based on three kinds of laboratory measures such as fasting plasma glucose (FPG), 2-hour plasma glucose (2hPG) during a 75 g oral glucose tolerance test (OGTT) and HbA1c [11][12][13]. Japan Diabetes Society's proposal is somewhat reserved on HbA1c so that it stated "If HbA1c is used at initial examination, another method of determination is required for diagnosis at re-examination.…”

“…Nonetheless, the selection of a high-risk population is a prerequisite to make an early intervention efficacious. To this end, measuring the future risk of DM in non-diabetic subjects is mandatory for which many types of DM risk score (RS) have already been developed [3][4][5][6][7][8][9][10].…”