Deep learning-based prediction model for postoperative complications of cervical posterior longitudinal ligament ossification.
Sadayuki ItoHiroaki NakashimaToshitaka YoshiiSatoru EgawaKenichiro SakaiKazuo KusanoShinji TsutuiTakashi HiraiYu MatsukuraKanichiro WadaKeiichi KatsumiMasao KodaAtsushi KimuraTakeo FuruyaSatoshi MakiNarihito NagoshiNorihiro NishidaYukitaka NagamotoYasushi OshimaKei AndoMasahiko TakahataKanji MoriHideaki NakajimaKazuma MurataMasayuki MiyagiTakashi KaitoKei YamadaTomohiro BannoSatoshi KatoTetsuro OhbaSatoshi InamiShunsuke FujibayashiHiroyuki KatohHaruo KannoMasahiro OdaKensaku MoriHiroshi TaneichiYoshiharu KawaguchiKatsushi TakeshitaMorio MatsumotoMasashi YamazakiAtsushi OkawaShiro ImagamaPublished in: European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society (2023)
A new algorithm using deep learning was able to predict complications after cervical OPLL surgery. This model was well calibrated, with prediction accuracy comparable to that of regression models. The accuracy remained high even for predicting only neurological complications, for which the case number is limited compared to conventional statistical methods.