首页 文献索引 SCI期刊 AI助手
登录 注册
首页 正文

Computers in biology and medicine. 2025 Apr 11:191:110179. doi: 10.1016/j.compbiomed.2025.110179 Q17.02024

A machine learning approach to differentiate stage IV from stage I colorectal cancer

机器学习在区分IV期和I期结直肠癌中的应用 翻译改进

Naim Abu-Freha  1, Zaid Afawi  2, Miar Yousef  3, Walid Alamor  4, Noor Sanalla  4, Simon Esbit  5, Malik Yousef  6

作者单位 +展开

作者单位

  • 1 Institute of Gastroenterology and Hepatology, Soroka University Medical Center, Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva, Israel. Electronic address: abufreha@yahoo.de.
  • 2 Clalit Health Services, Southern District, Beer-Sheva, Israel.
  • 3 Lady Davis Carmel Medical Center, Haifa, Israel.
  • 4 Internal Medicine Department, Soroka University Medical Center, Beer-Sheva, Israel.
  • 5 Medical School for International Health, Ben-Gurion University of the Negev, Beer-Sheva, Israel.
  • 6 Department of Information Systems, Zefat Academic College, Zefat, Israel; Galilee Digital Health Research Center, Zefat Academic College, Zefat, Israel.
  • DOI: 10.1016/j.compbiomed.2025.110179 PMID: 40220595

    摘要 中英对照阅读

    Background and aim: The stage at which Colorectal cancer (CRC) diagnosed is a crucial prognostic factor. Our study proposed a novel approach to aid in the diagnosis of stage IV CRC by utilizing supervised machine learning, analyzing clinical history, and laboratory values, comparing them with those of stage I CRC.

    Methods: We conducted a respective study using patients diagnosed with stage I (n = 433) and stage IV CRC (n = 457). We employed supervised machine learning using random forest. The decision tree is used to visualize the model to identify key clinical and laboratory factors that differentiate between stage IV and stage I CRC.

    Results: The decision tree classifier revealed that symptoms combined with laboratory values were critical predictors of stage IV CRC. Change in bowel habits was predictive for stage IV CRC among 14 of 22 patients (63 %). Weight loss, constipation, and abdominal pain in combination with different levels of carcinoembryonic antigen (CEA) were predictors for stage IV CRC. A CEA level higher than 260 was indicative for stage IV CRC in all observed patients (61 out of 61 patients). Additionally, a lower CEA level, in combination with hemoglobin, white blood cell count, and platelet count, also predicted stage IV CRC.

    Conclusions: By applying a machine learning based approach, we identified symptoms and laboratory values (CEA, hemoglobin, white blood cell count, and platelet count), as crucial predictors for stage IV CRC diagnosis. This method holds potential for facilitating the diagnosis of stage IV CRC in clinical practice, even before imaging tests are conducted.

    Keywords: Colorectal cancer; Machine learning; Stage IV.

    Keywords:machine learning; stage iv cancer; stage i cancer

    背景和目的: 结直肠癌(CRC)的诊断分期是重要的预后因素。我们的研究提出了一种利用监督机器学习分析临床病史和实验室值,将其与一期CRC进行比较的新方法,以辅助四期CRC的诊断。

    方法: 我们使用433名一期CRC患者和457名四期CRC患者的资料进行了回顾性研究。我们采用了随机森林监督机器学习,并利用决策树可视化模型来识别区分四期和一期CRC的关键临床及实验室因素。

    结果: 决策树分类器显示,症状结合实验室值是四期CRC的重要预测因子。在22名患者中有14人(63%)的排便习惯改变被预测为四期CRC。体重下降、便秘和腹痛与不同水平的癌胚抗原(CEA)结合可以预测四期CRC。所有观察到的61名患者的CEA水平高于260,表明是四期CRC。此外,在CEA水平较低且结合血红蛋白、白细胞计数和血小板计数的情况下也能预测四期CRC。

    结论: 通过应用基于机器学习的方法,我们确定了症状及实验室值(如CEA、血红蛋白、白细胞计数和血小板计数)是四期CRC诊断的重要预测因子。该方法在临床实践中具有潜在价值,甚至可以在进行影像学检查之前辅助诊断四期CRC。

    关键词: 结直肠癌;机器学习;四期

    关键词:机器学习; 四期癌症; 一期癌症; 结直肠癌鉴别诊断

    翻译效果不满意? 用Ai改进或 寻求AI助手帮助 ,对摘要进行重点提炼
    Copyright © Computers in biology and medicine. 中文内容为AI机器翻译,仅供参考!

    相关内容

    期刊名:Computers in biology and medicine

    缩写:COMPUT BIOL MED

    ISSN:0010-4825

    e-ISSN:1879-0534

    IF/分区:7.0/Q1

    文章目录 更多期刊信息

    全文链接
    引文链接
    复制
    已复制!
    推荐内容
    A machine learning approach to differentiate stage IV from stage I colorectal cancer