移植前和移植前的参数可以使用机器学习来预测血液细胞移植后的长期存活率
Panagiotis G Asteris1, Amir H Gandomi2, Danial J Armaghani3
1Computational Mechanics Laboratory, School of Pedagogical and Technological Education, Athens, Greece.
Transplant immunology
|February 28, 2025
概括
一个新的机器学习 (ML) 模型准确地预测了全源造血干细胞移植 (allo-HSCT) 后的长期存活率. 这种人工智能工具可以识别高风险患者,改善血液恶性瘤的精准医学.
科学领域:
- 血液学 血液学 血液学
- 在瘤学瘤学.
- 医疗信息学 医疗信息学
背景情况:
- 全基性造血干细胞移植 (allo-HSCT) 是血液性恶性瘤的治愈选择.
- -HSCT的并发症降低了疗效,增加了发病率,降低了生存率.
- 预测并发症和生存的现有评分系统在准确性方面存在局限性.
研究的目的:
- 开发一种机器学习 (ML) 模型,用于预测alo-HSCT接受者的长期存活率.
- 确定影响生存的关键移植前和移植后的临床和实验室变量.
- 为了提高接受allo-HSCT的患者的风险分层.
主要方法:
- 这是一项追溯性研究,涉及564名allo-HSCT接受者.
- 利用了16个临床和实验室变量和生存状况.
- 开发并测试了一个基于数据集精制贪算法 (DEGRA) 的ML模型.
主要成果:
- 实现了ML模型的92.02%的预测准确度.
- 确定了八个关键参数:注入的CD34+细胞,患者的年龄和性别,调节方案的毒性,疾病风险指数 (DRI),移植来源以及血小板和中性粒细胞的移植.
- 该模型有效地整合了移植前和移植后的数据.
结论:
- 这代表了第一个将移植后变量纳入人工智能模型,用于预测成年HSCT接受者的死亡率.
- 在精准医学时代,高精度算法对于识别高死亡和发病风险的患者至关重要.
- 开发的ML模型为个性化患者管理和allo-HSCT风险评估提供了一个有前途的工具.
相关概念视频
Bone Marrow Sampling and Transplants
270
Bone marrow transplant is a potential cure for several diseases, including cancer and specific genetic disorders. Notably, this procedure is applicable for patients suffering from aplastic anemia, certain types of leukemia, severe combined immunodeficiency disease (SCID), Hodgkin's disease, non-Hodgkin's lymphoma, multiple myeloma, thalassemia, sickle-cell disease, and certain cancers.
The transplant begins with high doses of chemotherapy and radiation treatment, which aim to destroy...
The transplant begins with high doses of chemotherapy and radiation treatment, which aim to destroy...
270
Cancer Survival Analysis
319
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
319


