ML of Mortality’s prediction in micmic iii

In medical treatment, precision medicine is extremely needed. It is a good thing to have a tool that can assist doctors in making judgments and analyzing the patient’s condition. In this project, MIMIC III data set is used as the data source to predict COPD patients Whether there is a risk of death in the ICU, I hope to provide physicians with real-time information to assist in judgment. 在醫療當中，精準醫療是極度需要的，若有一個工具能夠輔助醫生做判斷與分析病人病情，是一個好事情，在這次的專案中，採用MIMIC III 資料集作為資料來源，預測以COPD病患在ICU中是否有死亡風險，希望藉此提供醫師即時資訊做輔助判斷。

We analyzed the importance of each feature in the entire Model for COPD patients.Even though our accuracy rate has reached 80%, we still need to adjust the model to meet the usability standard of ML 在裡面我們分析出針對COPD病患中，以Sharp進行分析各個特徵在整個Model中所佔的重要度。縱然我們的準確率已達8成，但仍須針對模型進行調整，達到ML的可用性標準