ChatGPT 醫生診斷準確度超越人類醫生!

Ai




ChatGPT 在準確診斷病人方面超越人類醫生

「我對結果感到震驚。」

在最近發表的一項研究中,50名醫生被要求根據病例報告進行醫療診斷,其中部分醫生被隨機分配使用 ChatGPT 來協助他們的決策。在這個實驗中,參與的醫生不僅根據最終診斷的正確性進行評分,還評估他們解釋思考過程的能力。

根據這些標準,獨立工作的醫生平均得分為74%,而那些與AI聊天機器人合作進行診斷的醫生得分為76%。然而,兩組的表現都遠遠不及從未上過醫學院的 ChatGPT,該AI獨立操作的平均得分達到90%。

這項研究發表在《JAMA Network Open》期刊,範圍雖小——50名醫生只檢視了六個案例——但對AI在醫療領域的角色以及人類醫生可能存在的偏見卻有著驚人的啟示。研究的共同作者、波士頓貝斯以色列醫療中心的內科專家亞當·羅德曼在《紐約時報》播客《Hard Fork》中表示:「我對結果感到震驚。我的假設是使用 [ChatGPT] 的人會是最好的,所以我對此感到驚訝。」

這些案例基於真實的醫療病人,故意設計得相當具有挑戰性。儘管如此,ChatGPT卻以壓倒性的優勢勝出。羅德曼指出,這可能既是對AI模型能力的證明,也反映了人類醫生的固執。使用ChatGPT的醫生可能對聊天機器人的第二意見感到抵觸,並因而忽視了它的建議,堅持自己的第一個猜測。

另一個可能解釋醫生為何落後於技術的因素是,他們對使用這種工具並不熟悉。但羅德曼反駁了這種認知,即 ChatGPT 明顯優於普通醫生。他指出:「差異在於,整理案例的專業醫生將信息組織得當。如果你想考慮提示的話,我們是以這種方式組織的。」換句話說,人類醫療專業人員在最終病例報告中準確收集和呈現醫療信息的艱苦工作是AI目前無法完成的。因此,宣稱AI明顯超越醫生的說法有點像廚師因使用他人的食譜而獨佔美味佳餚的功勞。

這項研究主要旨在測試聊天機器人能多有效地幫助醫生,而結果顯示其實際效果並不理想,而並非證明AI優於人類醫生。事實上,類似的研究已發現 ChatGPT 在診斷案例方面表現很差。

然而,令人驚訝的是,這項實驗是在一年前使用較舊版本的 ChatGPT 進行的。如今的結果可能更為令人印象深刻。「也許AI模型在診斷方面比人類醫生更出色。但我不認為這是使用 GPT-4 Turbo 的情況,這是這裡用的模型。」羅德曼說。「不過,這在某個時候會變成事實,而我們正迅速接近那一點。」

這項研究引發了人們對AI在醫療診斷領域的潛力的深思,也提醒我們,儘管AI技術不斷進步,但人類醫生的專業知識和經驗仍然是無法被替代的。未來,AI或許能成為醫療診斷的重要輔助工具,但醫生的角色仍然不可或缺,特別是在理解患者的情感和背景方面。這不僅是技術的進步,更是人性與技術如何協同合作的未來挑戰。

以上文章由特價GPT API KEY所翻譯及撰寫。而圖片則由FLUX根據內容自動生成。

發佈留言

發佈留言必須填寫的電子郵件地址不會公開。 必填欄位標示為 *

🎨 Nano Banana Pro 圖像生成器|打幾句說話就出圖

想畫人像、產品圖、插畫?SSFuture 圖像生成器支援 Flux Gemini Nano Banana Pro 改圖 / 合成, 打廣東話都得,仲可以沿用上一張圖繼續微調。

🆓 Flux 模型即玩,不用登入
🤖 登入後解鎖 Gemini 改圖
📷 支援上載參考圖再生成
⚡ 每天免費額度任你玩
✨ 即刻玩 AI 畫圖
A dynamic, ultra-realistic action shot of a snowboarder performing a high-air jump on a snowy mountain slope. The rider wears a bright green winter jacket, black snow pants, gloves, and a dark beanie, with reflective goggles catching the cold mountain light. A cloud of visible breath escapes from the rider’s mouth in the freezing air. Snow explodes upward from the snowboard, creating sharp, frozen particles suspended mid-air. The background features a dramatic high-altitude landscape with forested slopes and distant mountains under soft, cold blue lighting. Capture cinematic contrast, DSLR realism, 85mm lens, f/2.8, crisp details, slow-motion energy, dynamic composition, atmospheric depth, high-clarity sports photography. A whimsical, artistic scene set in a classic Hong Kong cha chaan teng (茶餐廳): A charming cat sits comfortably at a small table, elegantly sipping a traditional Hong Kong-style milk tea from a delicate glass. The cat's fur is soft and expressive, and its posture is relaxed yet attentive, suggesting it is a regular at the tea shop. The restaurant interior is bustling yet cozy, adorned with retro posters, old ceiling fans, patterned floor tiles, and Formica tables reflecting the local culture. Sunlight streams through the window, casting warm highlights on the cat and creating a vivid play of shadows. Details include steaming milk tea cups, egg tarts and pineapple buns on the table, and waiters in classic uniforms moving in the background. The overall color palette is rich and atmospheric, blending nostalgia with the lively charm of Hong Kong. Base Setup

keep 100 percent facial information adherence of the attached image and turn her into a fashion model walking through a dim stone tunnel toward a bright exit, captured as a live action photograph or movie still, not an illustration or CGI render. Her styling leans seductive and attractive through fashion, attitude, and mood rather than explicit content.

Shot and Camera

Full body silhouette shot from behind at slightly low camera height, matching the original perspective and narrow tunnel framing. Keep her stride, tunnel curvature, and vanishing light exactly as seen.

Identity and Pose

Preserve her height impression, slim silhouette, hair length, and body proportions. She walks forward with one hip subtly angled, natural arm swing, confident stride, and a slow, sensual rhythm. Her head tilts slightly as if aware of being watched. Include 8k Photorealistic and hyper realistic.

Lighting and Environment

Strong backlight from the tunnel exit creates a glowing rim around her body, with soft, scattered reflections on the wet stone floor. The tunnel remains dark with textured stone irregularities and real moisture streaks. Add subtle haze for realism and keep the environment grounded with accurate shadows and surface wear.

Masking and Constraints

Change only the outfit and styling, keep lighting, perspective, white balance, pose, face geometry, body proportions, and silhouette the same. Absolutely no added text, no cartoon look, no CGI sheen, no plastic skin, no floating feet, and no overly clean backgrounds. Maintain consistent perspective, grounded contact shadows, film like grain, and full live action realism.