在植入前遗传测试中评估生成性AI聊天机器人的性能:对专家评估的比较研究
Belén Lledo1, Paola Carbone1, Jose A Ortiz1
1Instituto Bernabeu Biotech, Alicante, Spain.
Reproductive biomedicine online
|February 14, 2026
概括
生成型人工智能聊天机器人对植入前遗传测试 (PGT) 问题表现出中等可靠性. 聊天GPT和双子座的表现比Llama更好,但临床监督对人工智能在生殖医学中至关重要.
科学领域:
- 生殖医学 生殖医学
- 人工智能的人工智能
- 遗传学 是一个遗传学.
背景情况:
- 生成性AI聊天机器人越来越多地用于健康信息.
- 它们在诸如植入前遗传检测 (PGT) 等专业医疗领域的可靠性尚未得到充分证实.
- 与患者相关的问题需要准确而细致的答案.
研究的目的:
- 评估生成性AI聊天机器人的可靠性,以回答有关PGT的患者相关问题.
- 在这种情况下,比较不同的AI模型 (ChatGPT-3.5,Gemini-1.5,Llama-2) 的性能.
- 评估问题复杂度 (简单与有争议) 对AI答案准确性的影响.
主要方法:
- 对三个生成人工智能模型的前性评估:ChatGPT-3.5,Gemini-1.5,和Llama-2.
- 12名生殖医学专家对13个与PGT相关的问题进行了评分.
- 根据预先定义的标准,对简单和有争议的问题,对0-5的比例进行了评分.
主要成果:
- 在简单和有争议的PGT问题中,ChatGPT表现最高,其次是双子座,然后是Llama.
- 在ChatGPT和Llama之间,以及在有争议的问题上在Gemini和Llama之间观察到显著的性能差异.
- 与有争议的问题相比,对于简单的问题,人工智能的表现通常更高,这表明可靠性的变化.
结论:
- 生成性AI聊天机器人为PGT相关的查询提供了适度的可靠性,模型之间的性能有显著差异.
- 聊天GPT和双子座比Llama表现优越,这表明在处理复杂的医疗信息方面具有不同的能力.
- 在将人工智能工具整合到生殖医学实践之前,临床验证和监督至关重要,以确保患者安全和信息准确性.
相关概念视频
What is Population Genetics?
65.0K
A population is composed of members of the same species that simultaneously live and interact in the same area. When individuals in a population breed, they pass down their genes to their offspring. Many of these genes are polymorphic, meaning that they occur in multiple variants. Such variations of a gene are referred to as alleles. The collective set of all the alleles within a population is known as the gene pool.
65.0K
Animal Mitochondrial Genetics
9.3K
Among all the organelles in an animal cell, only mitochondria have their own independent genomes. Animal mitochondrial DNA is a double-stranded, closed-circular molecule with around 20,000 base pairs. Mitochondrial DNA is unique in that one of its two strands, the heavy, or H, -strand is guanine rich, whereas the complementary strand is cytosine rich and called the light, or L, -strand. Compared to nuclear DNA, mitochondrial DNA has a very low percentage of non-coding regions and is marked by...
9.3K
Serum Studies: Renal Function Tests
464
Renal function tests are crucial for assessing kidney health, monitoring disease progression, and evaluating the kidneys' efficiency in waste elimination, fluid balance, and electrolyte regulation. These tests offer critical insights into kidney function, even though routine measurements may appear normal until there is a significant decline in the glomerular filtration rate or GFR. Typically, signs of kidney impairment only become evident when the GFR falls to about 50% of its normal level.
464
Genetics of Speciation
22.0K
Speciation is the evolutionary process resulting in the formation of new, distinct species—groups of reproductively isolated populations.
22.0K
What is Genetic Engineering?
80.4K
Overview
80.4K
Types of Genetic Transfer Between Organisms
31.2K
Genetic transfer occurs when genetic information is passed from one organism to another. It occurs via two mechanisms: vertical gene transfer and horizontal gene transfer. Vertical gene transfer occurs when genetic information is transferred from one generation to the next, which happens much more frequently than horizontal gene transfer. Both sexual and asexual reproduction are forms of vertical gene transfer, where one or more organisms pass some or all of their genome onto their progeny.
31.2K


