Deep learning analysis of clinical course of primary nephrotic syndrome: Japan Nephrotic Syndrome Cohort Study (JNSCS)

Tomonori Kimura, Ryohei Yamamoto, Mitsuaki Yoshino, Ryuichi Sakate, Enyu Imai, Shoichi Maruyama, Hitoshi Yokoyama, Hitoshi Sugiyama, Kosaku Nitta, Tatsuo Tsukamoto, Shunya Uchida, Asami Takeda, Toshinobu Sato, Takashi Wada, Hiroki Hayashi, Yasuhiro Akai, Megumu Fukunaga, Kazuhiko Tsuruya, Kosuke Masutani, Tsuneo KontaTatsuya Shoji, Takeyuki Hiramatsu, Shunsuke Goto, Hirofumi Tamai, Saori Nishio, Kojiro Nagai, Kunihiro Yamagata, Hideo Yasuda, Shizunori Ichida, Tomohiko Naruse, Tomoya Nishino, Hiroshi Sobajima, Toshiyuki Akahori, Takafumi Ito, Yoshio Terada, Ritsuko Katafuchi, Shouichi Fujimoto, Hirokazu Okada, Tetsushi Mimura, Satoshi Suzuki, Yosuke Saka, Tadashi Sofue, Kiyoki Kitagawa, Yoshiro Fujita, Makoto Mizutani, Naoki Kashihara, Hiroshi Sato, Ichiei Narita, Yoshitaka Isaka

Research output: Contribution to journalArticlepeer-review

Abstract

Background: Prognosis of nephrotic syndrome has been evaluated based on pathological diagnosis, whereas its clinical course is monitored using objective items and the treatment strategy is largely the same. We examined whether the entire natural history of nephrotic syndrome could be evaluated using objective common clinical items. Methods: Machine learning clustering was performed on 205 cases from the Japan Nephrotic Syndrome Cohort Study, whose clinical parameters, serum creatinine, serum albumin, dipstick hematuria, and proteinuria were traceable after kidney biopsy at 5 measured points up to 2 years. The clinical patterns of time-series data were learned using long short-term memory (LSTM)-encoder–decoder architecture, an unsupervised machine learning classifier. Clinical clusters were defined as Gaussian mixture distributions in a two-dimensional scatter plot based on the highest log-likelihood. Results: Time-series data of nephrotic syndrome were classified into four clusters. Patients in the fourth cluster showed the increase in serum creatinine in the later part of the follow-up period. Patients in both the third and fourth clusters were initially high in both hematuria and proteinuria, whereas a lack of decline in the urinary protein level preceded the worsening of kidney function in fourth cluster. The original diseases of fourth cluster included all the disease studied in this cohort. Conclusions: Four kinds of clinical courses were identified in nephrotic syndrome. This classified clinical course may help objectively grasp the actual condition or treatment resistance of individual patients with nephrotic syndrome.

Original languageEnglish
Pages (from-to)1170-1179
Number of pages10
JournalClinical and Experimental Nephrology
Volume26
Issue number12
DOIs
Publication statusPublished - 12-2022

All Science Journal Classification (ASJC) codes

  • Physiology
  • Nephrology
  • Physiology (medical)

Fingerprint

Dive into the research topics of 'Deep learning analysis of clinical course of primary nephrotic syndrome: Japan Nephrotic Syndrome Cohort Study (JNSCS)'. Together they form a unique fingerprint.

Cite this