科學家發明"死神計算機",超準預測死亡

Boston researchers have developed a supercomputer they claim can predict with 96% probability if a patient is about to die.

波士頓的研究人員發明了一種超級計算機，據說能預測病人是不是快要死亡，準確性高達96%。

The Beth Israel Deaconess Medical Center has linked monitors on its patients to the system, which is said to be better at spotting illnesses than human doctors.

貝斯以色列女執事醫療中心將病人身上的監測器與該系統相連，據說這樣可以比醫生更準確地發現病情。

It is loaded with information about more than 250,000 people from the past 30 years, drawing on this data to make speedy diagnoses.

該系統中擁有近30年來超25萬位患者的信息，並利用這些資料做出快速的診斷。

This speedy disease recognition could allow a quick cure, potentially saving lives as well as predicting patients' imminent demise.

這種快速的疾病診斷方法既可以預測病人是否即將死亡，也可以使患者儘早接受治療，從而可能挽救患者的生命。

'The big picture is that we're trying to harness the power of big data,' said Dr Steve Horng, who is leading the project.

“重點是，我們正在儘可能地利用大數據的力量。”該項目的負責人史蒂芬·黃博士說。

'If you come in, we can take everything we know about you, both in your current visit and previous visits.

“如果你來看病，我們可以向你展示我們所知道的所有關於你的情況，包括你現在和之前看醫生的記錄。”

'We can compare that to other patients with similar conditions, and predict diagnoses you might have in the future.'

“我們可以將你的情況和其他症狀相似的患者進行對比，預測出你將來可能患的疾病。”

It collects data on patients every three minutes, measuring everything from oxygen levels to blood pressure.

該系統每三分鐘就收集一次患者的信息，測量氧氣含量、血壓等各項指標。

The groundbreaking research is the first time the 'big data' principles have been applied in this way.

這一突破性的研究是大數據理論首次以這種方式運用到該領域。

Dr Steve Horng told the BBC: 'We can predict with 96% confidence when patients [are facing a high] probability of dying,'

史蒂芬·黃博士告訴英國廣播公司說：“我們可以判斷出患者很可能即將死亡的時間，準確率高達96%。”

'If the computer says you're going to die, you probably will die in the next 30 days.'

“如果計算機表示，你即將死亡，那麼你很可能活不過一個月了。”