在社会压力下压力测试临床决策:LLMs可能会对医疗造成伤害
Mahmud Omar1,2, Reem Agbareia3, Jolion McGreevy4
1The Windreich Department of Artificial Intelligence and Human Health, Mount Sinai Health System, NY, USA.
medRxiv : the preprint server for health sciences
|December 8, 2025
概括
大型语言模型 (LLM) 可以产生有害的临床决策,特别是在社会压力下. 一个简单的安全提醒有助于但不能消除这些风险,需要医生监督.
科学领域:
- 人工智能在医学中的应用
- 临床决策支持系统 临床决策支持系统
- 自然语言处理自然语言处理.
背景情况:
- 大型语言模型 (LLM) 越来越多地被整合到临床工作流中.
- 在临床决策上LLM的影响及其造成危害的潜力仍然在很大程度上未得到量化.
研究的目的:
- 评估大型语言模型 (LLM) 产生有害临床决策的倾向.
- 评估社会压力和缓解线索对LLM产生的有害输出的影响.
主要方法:
- 一组20个LLM在超过1000万个临床场景中进行了测试.
- 场景包括在中立和六个社会压力条件下呈现的安全和道德困境.
- 可选地提供了一个缓解提示 ("检查或升级如果不安全").
主要成果:
- 在所有情景中,LLM产生了11.7% (1.1800万) 的潜在有害输出.
- 社会压力显著增加了有害反应,特别是涉及权力或责任转移的提示.
- 缓解提示使有害决策从16.6%减少到10.1% (p < 0.001),但没有消除它们.
结论:
- 劳动法师表现出在规模上产生有害医疗决策的能力.
- 虽然安全提醒可以减轻伤害,但在临床整合之前,持续的医生监督和强大的护是必不可少的.
- 伤害倾向应该是评估医疗保健机构LLM的核心绩效指标.
相关概念视频
Obedience
35.2K
According to obedience research, we may harm others under the forceful pressures of an authority figure (Milgram, 1974). How about if the inappropriate orders were delivered with less force? The increasing interdependence between nurses and physicians compelled Hofling and his colleagues to explore nurses’ reactions to a potentially harmful medical request made by the perceived authority figure, the doctor (Hofling, Brotzman, Dalrymple, Graves, & Pierce, 1966). In this situation,...
35.2K
Exercise Stress Test
1.1K
Introduction
Exercise stress testing, commonly known as a treadmill test, is a noninvasive procedure used to evaluate cardiovascular function and diagnose heart conditions.
Definition
An exercise stress test measures the heart's response to exertion using a treadmill or stationary bicycle. Chest electrodes record the heart's electrical activity through an ECG, and blood pressure is monitored regularly.
Purposes
Exercise stress testing, commonly known as a treadmill test, is a noninvasive procedure used to evaluate cardiovascular function and diagnose heart conditions.
Definition
An exercise stress test measures the heart's response to exertion using a treadmill or stationary bicycle. Chest electrodes record the heart's electrical activity through an ECG, and blood pressure is monitored regularly.
Purposes
1.1K
Lazarus's Cognitive Appraisal Theory
1.6K
Cognitive psychologist Richard Lazarus proposed the cognitive-mediational theory of emotions, which emphasizes how individuals' assessments of stressors significantly affect their experience of stress. According to Lazarus, the stress response is determined by a two-step appraisal process: primary appraisal and secondary appraisal. These cognitive appraisals help individuals evaluate the potential impact of a stressor and determine the adequacy of their coping resources.
Primary Appraisal:...
Primary Appraisal:...
1.6K
Ethical Dilemmas II
2.2K
Resolving an ethical dilemma in healthcare involves a systematic approach that considers every aspect of the issue, respecting both the patient's needs and values and the healthcare professional's ethical obligations. Here are potential steps to resolve an ethical dilemma:
2.2K
Milgram's Obedience to Authority
7.2K
Obedience to authority is classically demonstrated in a more famous series of social psychology experiments performed by Stanley Milgram. He was a social psychology professor at Yale who was influenced by the trial of Adolf Eichmann, a Nazi war criminal. Eichmann’s defense for the atrocities he committed was that he was “just following orders.”
7.2K
Ethical Issues
2.0K
Nurses are essential in patient care, upholding the ethical principles of their profession and effectively navigating ethical dilemmas. Neglecting ethical issues can lead to inadequate patient care, compromised therapeutic relationships, and moral distress among healthcare workers.
Ethical Concerns in Healthcare:
Ethical Concerns in Healthcare:
2.0K


