The Role of Artificial Intelligence in Early Cancer Diagnosis.
The Role of Artificial Intelligence in Early Cancer Diagnosis.
复制标题
DOI：
10.3390/cancers14061524
复制
发表时间：
2022-03-16
期刊：
影响因子：
5.2
通讯作者：
Lee RW
中科院分区：
文献类型：
--
作者：
Hunter B;Hindocha S;Lee RW
在早期阶段诊断癌症增加了在许多肿瘤组中进行有效治疗的机会。关键方法包括筛查有风险但没有症状的患者，并迅速适当地调查那些有症状的患者。机器学习，即计算机学习复杂的数据模式来做出预测，有可能彻底改变早期癌症诊断。在这里，我们概述了这些算法如何通过分析常规健康记录、医学图像、活检样本和血液检测来帮助医生改善风险分层和早期诊断。这些工具在未来几年将得到越来越多的使用。提高早期癌症患者的诊断比例是世界卫生组织的一个关键优先事项。在许多肿瘤组中，筛查计划改善了生存率，但患者选择和风险分层是关键挑战。此外，人们担心诊断工作人员有限，特别是在COVID-19大流行的情况下，这给病理学和放射学服务带来了压力。在这篇综述中，我们讨论了人工智能算法如何帮助临床医生（1）筛查有癌症风险的无症状患者，（2）调查和分诊有症状的患者，以及（3）更有效地诊断癌症复发。我们概述了主要的人工智能方法，包括历史模型，如逻辑回归，以及深度学习和神经网络，并强调了它们的早期诊断应用。许多数据类型都适用于计算分析，包括电子医疗记录、诊断图像、病理切片和外周血，我们提供了如何利用这些数据诊断癌症的示例。我们还讨论了人工智能算法的潜在临床意义，包括目前在临床实践中使用的模型的概述。最后，我们讨论了潜在的限制和陷阱，包括道德问题，资源需求，数据安全和报告标准。
Diagnosing cancer at an early stage increases the chance of performing effective treatment in many tumour groups. Key approaches include screening patients who are at risk but have no symptoms, and rapidly and appropriately investigating those who do. Machine learning, whereby computers learn complex data patterns to make predictions, has the potential to revolutionise early cancer diagnosis. Here, we provide an overview of how such algorithms can assist doctors through analyses of routine health records, medical images, biopsy samples and blood tests to improve risk stratification and early diagnosis. Such tools will be increasingly utilised in the coming years. Improving the proportion of patients diagnosed with early-stage cancer is a key priority of the World Health Organisation. In many tumour groups, screening programmes have led to improvements in survival, but patient selection and risk stratification are key challenges. In addition, there are concerns about limited diagnostic workforces, particularly in light of the COVID-19 pandemic, placing a strain on pathology and radiology services. In this review, we discuss how artificial intelligence algorithms could assist clinicians in (1) screening asymptomatic patients at risk of cancer, (2) investigating and triaging symptomatic patients, and (3) more effectively diagnosing cancer recurrence. We provide an overview of the main artificial intelligence approaches, including historical models such as logistic regression, as well as deep learning and neural networks, and highlight their early diagnosis applications. Many data types are suitable for computational analysis, including electronic healthcare records, diagnostic images, pathology slides and peripheral blood, and we provide examples of how these data can be utilised to diagnose cancer. We also discuss the potential clinical implications for artificial intelligence algorithms, including an overview of models currently used in clinical practice. Finally, we discuss the potential limitations and pitfalls, including ethical concerns, resource demands, data security and reporting standards.
登录
查看更多内容
影响因子：
5.9
作者：
Baccouche A;Garcia-Zapirain B;Castillo Olea C;Elmaghraby AS
通讯作者：
Elmaghraby AS
影响因子：
4.2
作者：
Beck, J. Thaddeus;Rammage, Melissa;Vinegra, Michael
通讯作者：
Vinegra, Michael
影响因子：
78.8
作者：
Bera, Kaustav;Schalper, Kurt A.;Madabhushi, Anant
通讯作者：
Madabhushi, Anant
影响因子：
3.4
作者：
Browning L;Colling R;Rakha E;Rajpoot N;Rittscher J;James JA;Salto-Tellez M;Snead DRJ;Verrill C
通讯作者：
Verrill C
获得可持续和适合的英国健康和护理人员。
影响因子：
168.9
作者：
Anderson, Michael;O'Neill, Ciaran;Clark, Jill Macleod;Street, Andrew;Woods, Michael;Johnston-Webber, Charlotte;Charlesworth, Anita;Whyte, Moira;Foster, Margaret;Majeed, Azeem;Pitchforth, Emma;Mossialos, Elias;Asaria, Miqdad;McGuire, Alistair
通讯作者：
McGuire, Alistair