深入分析使用人工智能方法用于癌症预测的非侵入性技术的最新创新
Hari Mohan Rai1, Joon Yoo2, Abdul Razaque3
1School of Computing, Gachon University, 1342 Seongnam-daero, Sujeong-Gu, Seongnam-Si, 13120, Gyeonggi-Do, Republic of Korea. drhmrai@gachon.ac.kr.
Medical & biological engineering & computing
|July 16, 2024
概括
本综述比较了常规机器学习 (CML) 和深度神经网络 (DNN) 的非侵入性癌症检测. 最优的模型达到100%的准确性,但性能差异很大,结直肠癌的检测率最低.
科学领域:
- 在瘤学瘤学.
- 生物医学工程 生物医学工程
- 数据科学数据科学数据科学
背景情况:
- 癌症仍然是一个关键的全球健康挑战,需要先进的早期检测.
- 非侵入性方法对于改善患者的治疗结果和减少医疗负担至关重要.
- 自动检测系统对于有效和可扩展的癌症查至关重要.
研究的目的:
- 综合审查和比较传统的机器学习 (CML) 和深度神经网络 (DNN) 以进行非侵入性癌症预测.
- 分析CML和DNN模型在七种主要癌症类型的表现,使用检测准确度作为主要指标.
- 确定研究缺口,并提出未来的方向,以加强自动化癌症检测技术.
主要方法:
- 从2018-2024年对310篇出版物的系统审查,重点关注非侵入性癌症检测.
- 对CML和DNN方法进行比较分析,评估数据集,特征和模式等因素.
- 基于检测准确度的性能评估,将模型分为高性能 (>=99%) 和低性能 (65.83-85.8%).
主要成果:
- 功能,数据集和模型的最佳组合可以实现CML和DNN的100%准确性.
- 观察到显著的精度差异 (高达35%),特别是在未经优化模型中.
- 结肠直肠癌的准确性最低 (DNN 69%,CML 65.83%),而其他癌症的性能更高.
- DNN的研究正在增加,但CML仍然具有竞争力,有时表现优于DNN.
结论:
- 无论是CML还是DNN都显示出高精度非侵入性癌症检测的潜力.
- 模型优化,功能选择和数据集质量对于实现可靠的性能至关重要.
- 需要进一步的研究来解决性能差异,特别是对于诸如结直肠癌等具有挑战性的癌症,以及完善自动检测工具.
相关概念视频
Issues And Trends In Healthcare Delivery System
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cancer Survival Analysis
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...


