谷歌的AI技術(shù)竟能預(yù)測(cè)病人何時(shí)會(huì)死？
人工智能知道你的死亡時(shí)間。但和科幻電影不同的是，這些信息最后可能會(huì)挽救生命。
A new paper published in Nature suggests that feeding electronic health record data to a deep learning model could substantially improve the accuracy of projected outcomes.
一篇發(fā)表在《自然》雜志上的新論文顯示，深度學(xué)習(xí)模型的進(jìn)食電子健康數(shù)據(jù)能夠大幅提高預(yù)測(cè)結(jié)果的準(zhǔn)確性。
In trials using data from two US hospitals, researchers were able to show that these algorithms could predict a patient's length of stay and time of discharge, but also the time of death.
在使用了兩家美國醫(yī)院數(shù)據(jù)的試驗(yàn)中，研究人員可以證明這些算法不僅能夠預(yù)測(cè)病人的住院天數(shù)和出院時(shí)間，還能預(yù)測(cè)死亡時(shí)間。
The neural network described in the study uses an immense amount of data, such as a patient's vitals and medical history, to make its predictions.
研究中所描述的神經(jīng)網(wǎng)絡(luò)使用了大量的數(shù)據(jù)進(jìn)行預(yù)測(cè)，比如病人的生命特征和病史。
A new algorithm lines up previous events of each patient's records into a timeline, which allowed the deep learning model to pinpoint future outcomes, including time of death.
一種新的算法將每個(gè)病人所記錄的活動(dòng)經(jīng)歷排列成一個(gè)時(shí)間軸，這使得深度學(xué)習(xí)模型能夠確定包括死亡時(shí)間在內(nèi)的未來的結(jié)果。
The neural network even includes handwritten notes, comments, and scribbles on old charts to make its predictions. And all of these calculations are done in record time, of course.
用于預(yù)測(cè)的神經(jīng)網(wǎng)絡(luò)甚至包括在舊圖表上手寫的筆記、評(píng)論和涂鴉。當(dāng)然，所有的這些計(jì)算都是在記錄時(shí)間內(nèi)完成的。
What can we do with this information, besides fear the inevitable? Hospitals could find new ways to prioritize patient care, adjust treatment plans, and catch medical emergencies before they even occur.
除了害怕這些不可避免的事情，我們還能用這些信息做什么?醫(yī)院可以找到新的方法來優(yōu)先照顧病人，調(diào)整治療方案，并在發(fā)生緊急情況之前及時(shí)處理醫(yī)療事故。
It could also free up healthcare workers, who would no longer have to manipulate the data into a standardized, legible format.
它也可以解放醫(yī)療工作者，他們不再需要將數(shù)據(jù)轉(zhuǎn)換成標(biāo)準(zhǔn)化的、更易讀取的格式。
