为体重管理专家提供可解释的人工智能软件工具 (PRIMO):混合方法研究研究
Glenn J Fernandes1,2, Arthur Choi3, Jacob Michael Schauer2
1Department of Computer Science, Northwestern University, Evanston, IL, United States.
Journal of medical Internet research
|September 6, 2023
概括
机器学习模型可以预测早期的减肥成功. 一个可解释的AI工具PRIMO增加了体重管理专家对这些预测的信任和同意,提高了潜在的干预效率.
科学领域:
- 机器学习在医疗保健中的应用.
- 可解释的人工智能 (XAI)
- 行为科学和干预的有效性.
背景情况:
- 机器学习 (ML) 模型可以预测减肥干预的成功,从而实现个性化治疗调整.
- 然而,缺乏信任和理解阻碍了体重管理专家采用ML.
- 可解释的人工智能 (XAI) 为弥合这一差距提供了一个潜在的解决方案.
研究的目的:
- 根据早期干预数据,开发和评估一种ML模型,以预测基于早期干预数据的6个月减肥成功.
- 评估基于ML的解释是否改善了体重管理专家对模型预测的同意.
- 确定影响专家对ML模型的理解和信任的因素,以预测体重减轻.
主要方法:
- 一个随机森林 (RF) ML模型在6个月的减肥干预中受训了419名参与者的数据.
- 一个交互式XAI工具PRIMO被开发来解释RF模型的预测.
- 14名权重管理专家评估了使用PRIMO之前和之后的假设案例,并将其与其他可解释性方法进行了比较.
主要成果:
- 射频模型在预测减肥成功的准确率达到了81%.
- 专家在使用PRIMO时与其他方法相比,与ML预测的一致性显著更高 (P=.02).
- 面试显示了对多种解释类型,不确定性可视化和模型性能指标的偏好.
结论:
- 像PRIMO这样的可解释的ML模型可以增加体重管理专家对早期体重减轻成功预测的信任和同意.
- 这种增强的信任可以促进干预措施的动态修改,以提高有效性.
- 该研究提供了在体重管理环境中提高ML模型可理解性和可信度的方法.
相关概念视频
Regression Toward the Mean
6.3K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.3K
Obesity
534
The Body Mass Index (BMI) is a numerical value derived from a person's weight and height, used to categorize individuals into weight ranges. It is calculated using the formula: weight in kilograms divided by height in meters squared. Obesity is a health condition characterized by excessive accumulation of adipose tissue that poses health risks, often diagnosed with a BMI ≥ 30. This excess fat storage occurs when surplus dietary calories are converted into triglycerides and stored in...
534
Strategies for Assessing and Addressing Confounding
119
Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
119


