【每日郵報】人工智慧可提前六年檢測出老年癡呆
月初就準備了文章，各種雜事和偷懶延遲了，大家海涵。歡迎提出意見討論。
AI detects Alzheimers disease SIX years early - with 100% accuracy in small study人工智慧可提前六年檢測出老年癡呆，且在小樣本研究中的準確度達100%
A new artificial intelligence system can predict the development of Alzheimers with 100 percent accuracy and six years before the hallmarks that doctors use to diagnose the disease appear.
新型人工智慧設備可預測阿爾茲海默症（俗稱「老年癡呆」）病程，準確度達100%，並且比醫生通過癥狀確診提早六年。There is no cure for Alzheimers and the effectiveness of the best treatments for the disease diminishes as it progresses.
阿爾茲海默症目前無法治癒。就算是最好的治療方法，療效也會隨著疾病的發展而逐漸減弱。
This means that early detection is the single best hope for the futures of the 44 million people living with Alzheimers around the world.
也就是說，提前檢出是全球4400萬患者未來唯一的希望。Scientists at the University of California, San Francisco (UCSF), taught their AI how to detect subtle changes in the brain that would be imperceptible to the human eye.
加州大學舊金山分校的科研人員已研製出一套人工智慧設備，能夠檢測出大腦發生的一些人眼難以識別的細微變化。So far, the system has provided a seemingly fail-proof early warning before the full onset of Alzheimers devastating effects in a small sample of tests.
目前，在小樣本試驗中，這套設備似乎已經能夠在阿爾茲海默症發病、對患者產生毀滅性打擊之前發出「防錯預警」。
A new AI system can detect subtle markers of metabolic changes in the brain that predict the development of Alzheimers - six years early and with 100 percent accuracy. The system can recognize very slight declines in grey matter (A) in Alzheimers patients
新型人工智慧設備可檢測出能夠表明大腦代謝變化的細微指標，提前六年準確預測阿爾茲海默症的病程狀況。該設備能識別出患者大腦灰質（上圖中的A）發生的細微衰退。Despite the fact that Alzheimers is among the top 10 deadliest diseases in the world, weve only begun to have a rudimentary understanding of the condition in recent years.
阿爾茲海默症是全球10大惡症之一不假，但人類只是在最近幾年來才開始對該病症有了初步的瞭解。While we better understand the markers and causes, Alzheimers - like the football-related brain disease, CTE - cannot be conclusively diagnosed until death, even today.
儘管我們對阿爾茲海默症的病理指標和病因瞭解較多，但即便是現在，該病和慢性創傷性腦損傷這種與足球相關的疾病一樣，只有在患者病逝之後才能加以確診。Doctors simply use process of elimination to rule out as many other causes of memory loss as possible.
醫生只能採用排除法，盡量排除造成記憶力衰退的其他原因。This is done through memory assessments and evaluations of any potential behavioral changes as well as lab tests and brain imaging.
具體方式有記憶力評價、潛在行為變化評估、實驗室檢測、腦成像。Most people have only four to eight years left to live by the time they are diagnosed with Alzheimers disease.
大部分患者在查出阿爾茲海默症後，往往只有四到八年的存活期。There are medications available to help patients manage memory loss- such as Aricept, Namenda and Excelon - but they are not a fix, they will not stop or reverse memory loss, they simply might slightly slow its progression and help make day-to-day living a little more manageable.
患者確實可以通過一些藥物應對記憶力衰退，如安理申（鹽酸多奈哌齊）、美金剛（鹽酸美金剛胺）、憶思能（卡巴拉汀）等。然而，這些藥物並不能解決問題，不會終止或者逆轉記憶力衰退，只是可以稍微延緩這個過程，有助於患者每天生活自理。Such drugs dont work or dont work as well for everyone, and past a certain stage, they dont work at all.
這類藥物並非對每個患者都有效，不同的人藥效不一，而且一旦病程發展超過某個階段就會完全無效。The earlier an Alzheimers patient can start them, the better, but before doctors prescribe the medications, there as to be sufficient clinical evidence of the disease.
雖說患者服藥越早越好，但醫生必須得到充分的臨牀證據才能開處方。But AI may be the key to detecting Alzheimers early enough to preserve some memory function - for six years longer, the new study, published in Radiology, suggests.
不過，新發表在《放射學》上的研究結果認為，人工智慧可對阿爾茲海默症的提早檢測發揮重要作用，提前六年檢出，在一定程度上保留記憶功能。The clearest sign of the disease is the build up of amyloid beta protein plaques in the brain.
阿爾茲海默症最明顯的標誌是β-澱粉樣蛋白在大腦中堆積，形成斑塊。But recently, scientists have linked the certain metabolic changes to Alzheimers disease.
不過，科學家日前還發現某些代謝方面的病變與該病有關。It isnt clear why yet, but the brains of both Alzheimers and diabetes sufferers dont absorb and process glucose - our primary source of energy - in the same way that healthy brains do.
葡萄糖是我們身體的主要能量來源，健康人的大腦能夠吸收、處理葡萄糖，而阿爾茲海默症和糖尿病患者的大腦則無法發揮這樣的功能。原因尚不明確。
This metabolic change happens early, but differences in the pattern of glucose uptake in the brain are very subtle and diffuse, said study co-author Dr Jae Ho Sohn, a radiologist at UCSF.
儘管這種代謝病變發生的時間較早，但參與研究的放射科醫師Jae Ho Sohn博士指出：「葡萄糖在大腦中的吸收機制差別非常小，而且分散。」People are good at finding specific biomarkers of disease, but metabolic changes represent a more global and subtle process.
「要找到疾病的具體生物標誌物問題不大，可是代謝病變過程不僅範圍廣，變化也不明顯。」So while a doctor might see the signs of the a change in disparate images, it would take an impossibly long time for humans to map out these changes and their subtle patterns in enough patients over a long-enough span of time, to say with certainty which changes predict Alzheimers.
因此，就算醫生能夠在不同的片子中發現某種病變的徵兆，要通過人力搞清楚足夠數量的患者在充分長的時期內發生的病變及其細微差別，進而斷定哪些病變可以預測阿爾茲海默症，估計要等到猴年馬月了。
But this is exactly the kind of task that artificial intelligence is intended for.
對於這樣的任務，人工智慧正好派上用場。Specifically, the new systems machine learning system was able to learn patterns in nearly 2,000 brain scans taken of 1,000 patients.
具體而言，這套新設備的機器學習系統可以學習一千多名患者的近2000張腦部掃描片。Dr Sohn, lead study author Dr Benjamin Franc and their team tested the system on 40 scans that were completely new to the algorithm.
Sohn博士、第一作者Benjamin Franc博士和研究組其他成員利用該系統演算法完全沒有接觸過的40張新掃描片對其進行了測試。The AI system detected every single patient that eventually developed Alzheimers from brain scans taken an average of six years before a persons diagnosis was made.
最終，該人工智慧系統從拍片時間距離最後確診平均六年的腦部掃描片中檢測出了所有患有阿爾茲海默症的患者，無一漏檢。We were very pleased with the algorithms performance, Dr Sohn said.
Sohn博士表示：「我們對演算法的表現特別滿意。」
It will be some time - and more testing - before the system is publicly available. But Dr Sohn and his team have high hopes for the AIs potential.
該系統會進行更多測試，上市尚需時日。不過，Sohn博士和研究組其他成員對人工智慧的潛力期望頗高。If we diagnose Alzheimers disease when all the symptoms have manifested, the brain volume loss is so significant that its too late to intervene, he said.
Sohn博士說：「如果我們等到各項癥狀都明確的時候才確診，此時大腦體積的萎縮已經非常嚴重，再進行幹預為時已晚。」If we can detect it earlier, thats an opportunity for investigators to potentially find better ways to slow down or even halt the disease process.
「倘若可以提前檢出，研究人員就有機會找到更好的辦法來延緩甚至終止該病的發展。」【完】
點此訪問原文
推薦閱讀：
