TY - JOUR
T1 - Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning
AU - Makino, Masaki
AU - Yoshimoto, Ryo
AU - Ono, Masaki
AU - Itoko, Toshinari
AU - Katsuki, Takayuki
AU - Koseki, Akira
AU - Kudo, Michiharu
AU - Haida, Kyoichi
AU - Kuroda, Jun
AU - Yanagiya, Ryosuke
AU - Saitoh, Eiichi
AU - Hoshinaga, Kiyotaka
AU - Yuzawa, Yukio
AU - Suzuki, Atsushi
N1 - Publisher Copyright:
© 2019, The Author(s).
PY - 2019/12/1
Y1 - 2019/12/1
N2 - Artificial intelligence (AI) is expected to support clinical judgement in medicine. We constructed a new predictive model for diabetic kidney diseases (DKD) using AI, processing natural language and longitudinal data with big data machine learning, based on the electronic medical records (EMR) of 64,059 diabetes patients. AI extracted raw features from the previous 6 months as the reference period and selected 24 factors to find time series patterns relating to 6-month DKD aggravation, using a convolutional autoencoder. AI constructed the predictive model with 3,073 features, including time series data using logistic regression analysis. AI could predict DKD aggravation with 71% accuracy. Furthermore, the group with DKD aggravation had a significantly higher incidence of hemodialysis than the non-aggravation group, over 10 years (N = 2,900). The new predictive model by AI could detect progression of DKD and may contribute to more effective and accurate intervention to reduce hemodialysis.
AB - Artificial intelligence (AI) is expected to support clinical judgement in medicine. We constructed a new predictive model for diabetic kidney diseases (DKD) using AI, processing natural language and longitudinal data with big data machine learning, based on the electronic medical records (EMR) of 64,059 diabetes patients. AI extracted raw features from the previous 6 months as the reference period and selected 24 factors to find time series patterns relating to 6-month DKD aggravation, using a convolutional autoencoder. AI constructed the predictive model with 3,073 features, including time series data using logistic regression analysis. AI could predict DKD aggravation with 71% accuracy. Furthermore, the group with DKD aggravation had a significantly higher incidence of hemodialysis than the non-aggravation group, over 10 years (N = 2,900). The new predictive model by AI could detect progression of DKD and may contribute to more effective and accurate intervention to reduce hemodialysis.
UR - https://www.scopus.com/pages/publications/85070786171
UR - https://www.scopus.com/pages/publications/85070786171#tab=citedBy
U2 - 10.1038/s41598-019-48263-5
DO - 10.1038/s41598-019-48263-5
M3 - Article
C2 - 31413285
AN - SCOPUS:85070786171
SN - 2045-2322
VL - 9
JO - Scientific reports
JF - Scientific reports
IS - 1
M1 - 11862
ER -
