概念验证:使用背向传播神经网络 (BPNN) 预测癌症患者的痛苦
Schulze Jan Ben1, Marc Dörner1, Moritz Philipp Günther1
1Department of Consultation-Liaison-Psychiatry and Psychosomatic Medicine, University Hospital Zurich, University of Zurich, Zurich, Switzerland.
Heliyon
|August 14, 2023
概括
使用反向传播神经网络 (BPNN) 的新型人工智能模型可以预测癌症患者的痛苦. 这种人工智能方法改进了传统的方法来识别需要精神瘤支持的个体.
科学领域:
- 在瘤学瘤学.
- 人工智能的人工智能
- 心理医学 心理医学
- 机器学习 机器学习
背景情况:
- 很大比例的癌症患者 (25-60%) 经历心理困扰,需要精神瘤服务.
- 像逻辑回归这样的传统方法在准确预测癌症患者的痛苦预测因子方面存在局限性.
- 需要先进的方法来提高在瘤学中的个人危险预测的准确性.
研究的目的:
- 开发和验证癌症患者心理痛苦的预测模型.
- 使用反向传播神经网络 (BPNN) 来提高个人预测准确度.
- 在瘤病患者队列中确定痛苦的关键预测因素.
主要方法:
- 追溯分析了2011-2019年间诊断和治疗的3063名癌症患者的数据.
- 应急温度计 (DT) 被用作患者应急的查仪器.
- 开发了一个后传神经网络 (BPNN) 来预测困境,用于初始预测器识别的后勤回归.
主要成果:
- 后勤回归确定了13个重要的痛苦预测因素,包括情绪,身体和实际问题.
- 有8个隐藏神经元的3层BPNN实现了最高的准确性,显示了75.9%的整体巧合率.
- BPNN模型实现了79.0%的灵敏度,71.8%的特异性,78.9%的PPV和71.9%的NPV.
结论:
- 开发的BPNN模型作为人工智能应用的概念验证,用于预测癌症患者的痛苦.
- 人工智能模型展示了强大的歧视和确定有心理困扰风险的患者的可行性.
- 这种方法有可能在癌症治疗中进行主动干预和个性化精神瘤护理.
相关概念视频
01:21Cancer Survival Analysis
384
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...
384
01:19Psychoneuroimmunology: Diabetes and Cancer
47
Chronic stress has been linked to both the onset and progression of serious health conditions, including Type 2 diabetes and cancer. Type 2 diabetes, a widespread chronic illness, is closely associated with obesity and insulin resistance, both of which often worsen under stress. Studies indicate that men experiencing high levels of chronic stress face a 45% higher risk of developing diabetes compared to those with minimal stress. Stress triggers physiological responses that elevate blood...
47