注意你的流行率!
Sébastien J J Guesné1, Thierry Hanser2, Stéphane Werner2
1Lhasa Limited, Granary Wharf House, 2 Canal Wharf, Leeds, West Yorkshire, LS11 5PS, UK. sebastien.guesne@lhasalimited.org.
Journal of cheminformatics
|April 15, 2024
概括
本研究介绍了评估定量结构-活动关系 (QSAR) 模型的平衡指标,提供了一个统一的框架,以克服二进制分类中依赖于流行率的性能指标问题. 均衡的指标确保在各种数据集之间进行公平的模型比较.
科学领域:
- 计算化学和化学信息学
- 机器学习模型验证的验证
- 定量结构-活动关系 (QSAR) 研究研究.
背景情况:
- 像准确度这样的标准性能指标在二进制分类中可能会因为不平衡的数据集而导致误导.
- 平衡精度和马修斯相关系数 (MCC) 用于减轻不平衡,但有局限性.
- 现有的文献缺乏理解和扩展平衡指标超出平衡准确性的正式框架.
研究的目的:
- 在QSAR模型验证的背景下,正式定义混矩阵,灵敏度和特异性.
- 为了证明在非恒定的流行率下比较绩效指标的局限性.
- 将均衡指标的概念扩展到马修斯相关系数 (MCC) 和其他绩效指标.
主要方法:
- 混矩阵,灵敏度和特异性的正式定义.
- 使用合成数据对流行程度依赖性的分析.
- 作为灵敏度,特异性和流行度的函数,平衡度表达式的导数.
主要成果:
- 平衡精度相当于对50%的流行率 (平衡测试集) 校准的精度.
- 马修斯相关系数 (MCC) 已被证明是患病率依赖的,在极端患病率下潜在的低估.
- 为平衡指标提出了一个新的框架,包括一个平衡的MCC,通过灵敏度和特异性来表达.
结论:
- 拟议的平衡指标为QSAR模型验证提供了强大的和统一的方法,使不同流行率的数据集能够进行可靠的比较.
- 这项工作将平衡评估的概念扩展到平衡准确度之外,为模型性能提供了更全面的理解.
- 衍生出的混矩阵和平衡的度量表达式促进了化学信息学中的QSAR模型的准确解释和比较.
相关概念视频
Prevalence and Incidence
478
In statistical epidemiology and health sciences, two essential metrics—prevalence and incidence—are fundamental for understanding disease dynamics within a population. These measures enable public health officials, epidemiologists, and researchers to assess the burden of diseases, allocate resources effectively, and design impactful public health policies and interventions.
Prevalence indicates the proportion of individuals in a population who have a specific disease or health...
Prevalence indicates the proportion of individuals in a population who have a specific disease or health...
478
Preventive Healthcare Services
1.0K
Preventive healthcare services keep people healthy via frequent check-ups, screening, and counseling. They primarily aid in disease prevention rather than treating an acute or chronic illness. Preventive treatment also keeps individuals productive and energetic, allowing them to work well into their retirement years. Examples of preventive care services include:
1.0K
Relative Risk
162
Relative risk (RR) is a statistical measure commonly used in epidemiology to compare the likelihood of a particular event occurring between two groups. This metric is important for evaluating the relationship between exposure to a specific risk factor and the probability of a particular outcome. It plays a crucial role in medical research, public health studies, and risk assessment. Relative risk quantifies how much more (or less) likely an event is to occur in an exposed group compared to an...
162
Transmission-based Precautions I: Contact, Enteric, and Droplets
3.6K
Transmission-based precautions are for patients known to be infected or suspected to be infected or colonized with organisms that pose a significant risk to others. Some transmission-based precautions include contact, enteric, and droplet.
Contact Precautions:
Contact precautions are the measures taken to prevent the transmission of infectious agents, especially epidemiologically important microorganisms such as MRSA or influenza, primarily transmitted through direct or indirect contact with an...
Contact Precautions:
Contact precautions are the measures taken to prevent the transmission of infectious agents, especially epidemiologically important microorganisms such as MRSA or influenza, primarily transmitted through direct or indirect contact with an...
3.6K
Standard Precaution
1.9K
Standard precautions are the minimum infection control safeguards used while caring for all patients, irrespective of their disease condition. They help prevent the spread of common infectious microorganisms to healthcare workers, patients, and visitors in all healthcare settings.
Hand hygiene is the most crucial means to prevent the transmission of disease. Employers are legally required to provide their workers with personal protective equipment (PPE) to minimize exposure or contact with...
Hand hygiene is the most crucial means to prevent the transmission of disease. Employers are legally required to provide their workers with personal protective equipment (PPE) to minimize exposure or contact with...
1.9K
Survey Safety
26
Surveying near highways, rough terrain, or power lines involves significant risks. Working along highways is particularly dangerous and requires the use of warning signs and flagmen. It is safest to avoid working directly on roads and use offsets whenever possible. When highway work is unavoidable, it must follow all safety guidelines. Surveyors should wear bright clothing, such as orange reflective vests, to ensure visibility to motorists, coworkers, and hunters. In construction zones, wearing...
26


