Ghanima Waleed, Cooper Nichola
Department of Research, Norway and Institute of Clinical Medicine, Østfold Hospital, University of Oslo, Oslo, Norway.
Department of Haemato-Oncology, Østfold Hospital, Norway and Institute of Clinical Medicine, Oslo, Norway.
Br J Haematol. 2024 Sep;205(3):770-771. doi: 10.1111/bjh.19684. Epub 2024 Aug 5.
The absence of reliable biomarkers in immune thrombocytopenia (ITP) complicates treatment choice, necessitating a trial-and-error approach. Machine learning (ML) holds promise for transforming ITP treatment by analysing complex data to identify predictive factors, as demonstrated by Xu et al.'s study which developed ML-based models to predict responses to corticosteroids, rituximab and thrombopoietin receptor agonists. However, these models require external validation before can be adopted in clinical practice. Commentary on: Xu et al. A novel scoring model for predicting efficacy and guiding individualised treatment in immune thrombocytopenia. Br J Haematol 2024; 205:1108-1120.
免疫性血小板减少症（ITP）缺乏可靠的生物标志物，这使得治疗选择变得复杂，需要采用反复试验的方法。机器学习（ML）有希望通过分析复杂数据来识别预测因素，从而改变ITP的治疗方式，正如Xu等人的研究所证明的那样，该研究开发了基于ML的模型来预测对皮质类固醇、利妥昔单抗和血小板生成素受体激动剂的反应。然而，这些模型在能够应用于临床实践之前需要进行外部验证。评论：Xu等人。一种预测免疫性血小板减少症疗效和指导个体化治疗的新型评分模型。《英国血液学杂志》2024年；205:1108 - 1120。
