Back

Development of an algorithm for the Charlson Comorbidity Index using the National Database Study in the Japan Kanto 7 Prefectures

Sekine, A.; Nakajima, K.

2025-04-11 epidemiology
10.1101/2025.04.10.25325568 medRxiv
Show abstract

The Charlson Comorbidity Index (CCI) contains 19 diseases, is weighted according to their potential influence on mortality, and has been widely used as a valid predictor for all-cause mortality. In this study, we aimed to develop an algorithm to define the CCI using information about diagnosed diseases and prescribed medication from the Japan National Database of Health Insurance Claims and Specific Health Checkups (NDB). The present study included 10,183,619 individuals who underwent health checkups from April 2018 to March 2019. We identified diagnosed diseases using Japans disease codes, which correspond to a more detailed disease classification than the International Classification of Diseases 10th edition codes, and Japans medication codes, which detail medication classifications. The mean CCI scores of men, women, and all subjects were 0.67 {+/-} 1.20, 0.68 {+/-} 1.14, and 0.68 {+/-} 1.17, respectively. For all patients, chronic pulmonary disease was the most prevalent condition out of the 19 Charlson comorbidities. Although further validation studies are needed to assess the association between our CCI and actual mortality in NDB, this index can be useful for epidemiological studies using a real-world database to adjust for patient comorbid conditions.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.