An explainable machine learning model for prognosis prediction in sudden sensorineural hearing loss under integrated therapy - Takeaways - MDSpire

An explainable machine learning model for prognosis prediction in sudden sensorineural hearing loss under integrated therapy

  • By

  • Xiaoxiao Ye

  • Yuxin Deng

  • Binbin Xiong

  • Min Chen

  • Gang Chen

  • Chen Huang

  • June 1, 2026

  • 0 min

Share

  • 1

    A retrospective study of 227 SSNHL patients evaluated machine learning models for predicting treatment outcomes during integrated therapy.

  • 2

    The XGBoost model achieved an AUC of 0.718, demonstrating superior performance and clinical utility in predicting SSNHL outcomes.

  • 3

    Key prognostic predictors identified include APTT, disease duration, platelet count, and total protein levels.

  • 4

    Optimal recovery was linked to specific platelet counts and APTT values, highlighting critical intervention windows.

  • 5

    The study emphasizes the need for further multicenter studies to validate the model's generalizability and prognostic factors.

Original Source(s)

An explainable machine learning model for prognosis prediction in sudden sensorineural hearing loss under integrated therapy

  • by Xiaoxiao Ye, Yuxin Deng, Binbin Xiong, Min Chen, Gang Chen, Chen Huang

  • June 1, 2026

Related Content

Analysis of the quality and reliability of benign paroxysmal positional vertigo-related short videos on TikTok and Bilibili: A cross-sectional study

Diagnosis and treatment strategies for airway involvement in relapsing polychondritis: a comprehensive review

Case Report: A rare triad of neoplasms: navigating synchronous accessory breast cancer, papillary thyroid carcinoma, and inflammatory nasal papilloma