エビデンス合成における生成的人工知能の使用:システマティックレビュー
Justin Clark1, Belinda Barton2, Loai Albarqouni1
1Institute for Evidence-Based Healthcare, Bond University, Gold Coast, QLD, Australia.
Research synthesis methods
|February 2, 2026
まとめ
生成的人工知能(GenAI)は、検索やスクリーニングなどのエビデンス合成タスクにおいて重大な不正確さを示しています。現在のエビデンスでは、人間の監視なしでの使用はサポートされていませんが、特定のタスクを支援する可能性があります。
科学分野:
- 医療情報学; 研究における人工知能; エビデンス合成方法論
背景:
- 生成的人工知能(GenAI)ツールは研究でますます利用可能になっています。GenAIはエビデンス合成を加速するツールとして提案されています。本研究では、従来のメソッドと比較してエビデンス合成におけるGenAIのパフォーマンスを評価します。
研究 の 目的:
- エビデンス合成におけるGenAIの精度、エラー率、および時間節約の可能性を評価すること。専門家主導のエビデンス合成アプローチと比較してGenAIのパフォーマンスを評価すること。
主な方法:
- 2025年1月17日に5つのデータベースを検索するシステマティックレビューを実施しました。結果には、エビデンス合成におけるGenAIの精度、エラー率、および所要時間が含まれます。バイアスリスクは、修正されたQUADAS-2ツールを使用して評価されました。
主要な成果:
- GenAIは検索中に68%-96%の研究を見逃しました。不正確なスクリーニング決定は、包含で0%-29%、除外で1%-83%の範囲でした。データ抽出エラー(4%-31%)およびバイアスリスク評価エラー(10%-56%)も観察されました。
結論:
- 現在のエビデンスでは、エビデンス合成における監視されていないGenAIの使用はサポートされていません。GenAIは、初期検索以外のタスクのエビデンス合成において人間を支援する可能性があります。信頼性の高いGenAI支援エビデンス合成には、人間の監視が不可欠です。
関連する概念動画
The Evidence for Evolution
48.2K
Genetic variations accumulating within populations over generations give rise to biological evolution. Evolutionary changes can result in the formation of novel varieties and entire new species. These changes are responsible for the diverse forms of life inhabiting the planet. The evidence for evolution suggests that all living organisms descended from common ancestors.
48.2K
Review and Preview
8.4K
In statistics, several tools are used to interpret the data. Measures of central tendency represent the characteristics of the data, such as mean, median, and mode. Additionally, measures of variance like standard deviation and range are used to find the spread of data from the mean. Relative standing measures the distance between data locations. Commonly used measures of relative standings are percentile, z score, and quartiles.
Percentiles are a type of fractile that partition data into...
Percentiles are a type of fractile that partition data into...
8.4K
Review and Preview
11.3K
Data are individual items of information obtained from a population or sample. Data may be classified as qualitative (categorical), quantitative continuous, or quantitative discrete. Because it is not practical to measure the entire population in a study, researchers use samples to represent the population. A random sample is a representative group from the population chosen by using a method that gives each individual in the population an equal chance of being included in the sample. Random...
11.3K
Intelligence
8.6K
The term "intelligence" is complex because it refers to both behavior and individuals, and its interpretation varies across cultures. European Americans tend to link intelligence with reasoning and cognitive skills, while in Kenya, it is tied to responsible participation in family and social life. In Uganda, intelligence is seen as the ability to know the right actions and carry them out effectively, while the Iatmul people of Papua New Guinea associate it with the capacity to remember...
8.6K
Random and Systematic Errors
14.9K
Scientists always try their best to record measurements with the utmost accuracy and precision. However, sometimes errors do occur. These errors can be random or systematic. Random errors are observed due to the inconsistency or fluctuation in the measurement process, or variations in the quantity itself that is being measured. Such errors fluctuate from being greater than or less than the true value in repeated measurements. Consider a scientist measuring the length of an earthworm using a...
14.9K
Systematic Sampling Method
13.3K
Sampling is a technique to select a portion (or subset) of the larger population and study that portion (the sample) to gain information about the population. Data are the result of sampling from a population. The sampling method ensures that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
Systematic sampling is one of the simplest methods...
Systematic sampling is one of the simplest methods...
13.3K


