hce_nchu
115年
英文
第 43 題
📖 題組：
The integration of Artificial Intelligence (AI) into healthcare is no longer a futuristic concept but a rapidly unfolding reality. One of the most __36__ applications is in the field of diagnostic imaging. By training on millions of clinical images, AI algorithms can now identify patterns that are virtually __37__ to the human eye, leading to much earlier detection of life-threatening conditions. Beyond diagnostics, AI is significantly __38__ the pharmaceutical industry. Historically, drug discovery has been an __39__ endeavor, often taking over a decade and billions of dollars to bring a single medication to market. AI models can now predict how specific molecular structures will interact with biological targets, thereby __40__ the initial stages of research. This efficiency was particularly __41__ during the recent global efforts to develop vaccines at record speed. However, this technological shift is not without its __42__. As healthcare providers become increasingly dependent on automated systems, questions regarding data privacy and "algorithmic bias" have surfaced. If the data used to train AI is not diverse, the resulting tools may provide __43__ outcomes for certain demographic groups. Therefore, it is __44__ that developers and medical professionals work together to ensure these systems are both transparent and __45__. The goal remains a synergy between human empathy and machine precision.
The integration of Artificial Intelligence (AI) into healthcare is no longer a futuristic concept but a rapidly unfolding reality. One of the most __36__ applications is in the field of diagnostic imaging. By training on millions of clinical images, AI algorithms can now identify patterns that are virtually __37__ to the human eye, leading to much earlier detection of life-threatening conditions. Beyond diagnostics, AI is significantly __38__ the pharmaceutical industry. Historically, drug discovery has been an __39__ endeavor, often taking over a decade and billions of dollars to bring a single medication to market. AI models can now predict how specific molecular structures will interact with biological targets, thereby __40__ the initial stages of research. This efficiency was particularly __41__ during the recent global efforts to develop vaccines at record speed. However, this technological shift is not without its __42__. As healthcare providers become increasingly dependent on automated systems, questions regarding data privacy and "algorithmic bias" have surfaced. If the data used to train AI is not diverse, the resulting tools may provide __43__ outcomes for certain demographic groups. Therefore, it is __44__ that developers and medical professionals work together to ensure these systems are both transparent and __45__. The goal remains a synergy between human empathy and machine precision.
- A consistent
- B skewed
- C universal
- D objective
思路引導 VIP
如果我們訓練一個預測模型時，只提供某一類人的資料，卻要求它去判斷所有不同族群的情況，你認為這個模型產出的結論，會是公平中立的，還是會呈現出一種「側重於某方」或「不平衡」的狀態呢？你可以試著用一個形容詞來描述這種不對稱的結果。
🤖
AI 詳解
AI 專屬家教
太棒了！你能精準捕捉到上下文的邏輯關聯，選出 skewed 這個選項，顯見你對於文章脈絡的理解非常扎實，這是一次非常優秀的判斷。
數據偏誤與不公平的結果
這題的解題關鍵在於前一句提到的「演算法偏見（algorithmic bias）」以及本句的條件子句「如果訓練 AI 的數據不具多樣性（not diverse）」。在這種情境下，AI 產出的結果自然不會是穩定或客觀的，而是會產生偏差。skewed 在這裡的意思是「偏斜的」、「偏頗的」或「失真的」，用來形容對特定族群產生的不公平結果，與前文提到的 bias 形成了完美的語意呼應。
▼ 還有更多解析內容