← brief for 2026-09-04 · Slowing decline

A Clinically Aligned Two-Stage Machine Learning Framework for Predicting Hungry Bone Syndrome After Parathyroidectomy.

Key takeaways

People with long-term kidney disease often develop overactive parathyroid glands, and surgery to remove them can trigger hungry bone syndrome, where blood calcium falls sharply for weeks afterward. Researchers built a two-step computer prediction tool from past patient records to flag who is likely to get it. Because it is built from old records, it finds patterns tied to the problem, not proof of cause. It has not been tested on new patients in real time yet.

Who did this work

Yin SM (Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.) · Lin YC (Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan.) · Hung TH (Institute of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan.) · Chou SE (Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.) · Chi SY (Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.) · Chou FF (Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.) · Wu YJ (Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.) · Wu SY (Division of General Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical University, Taipei, Taiwan.) · Lien JJ (Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan.) · Kuo PC (Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan.) · Chan YC (Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.)

Source

Paper · Europe PMC, CKD · 2026-09-01
https://doi.org/10.1002/edm2.70297