Cancer of unknown primary articles within Nature Medicine

Featured

• Article
  16 April 2024 | Open Access

  Prediction of tumor origin in cancers of unknown primary origin with cytology-based deep learning

  Developed on cytology images of hydrothorax and ascites from 57,220 cases at four hospitals, a deep-learning model shows high accuracy in tumor origin prediction and presents prognostic value when patient treatment is consistent with the cancer origin predicted by the model.

  • Fei Tian
  • , Dong Liu
  •  & Xiangchun Li

• Research Briefing | 10 August 2023

  Machine learning for improved clinical management of cancers of unknown primary

  OncoNPC, a machine learning classifier developed to predict the primary origin of tumors, made confident predictions for over 40% of cancers of unknown primary (CUP) cases analyzed. Patients with CUP who had received site-specific treatments that retrospectively matched the OncoNPC predictions had better outcomes than patients who had been treated with discordant site-specific therapies. OncoNPC predictions doubled the number of patients with CUP who would be eligible for genomically guided therapies.

• Article | 07 August 2023

  Machine learning for genetics-based classification and treatment response prediction in cancer of unknown primary

  A machine-learning classifier predicts the origin of cancer of unknown primary based on electronic health records and next-generation sequencing data, showing that patients treated accordingly to model predictions had significantly better outcomes.

  • Intae Moon
  • , Jaclyn LoPiccolo
  •  & Alexander Gusev