CL-ETM/ingredientevents

该数据集包含多个与医疗相关的字段，如患者ID（subject_id）、住院ID（hadm_id）、住院期间ID（stay_id）、护理人员ID（caregiver_id）等。这些字段可能用于记录和分析患者的住院信息、护理记录、药物使用情况等。数据集还包含时间相关的字段，如开始时间（starttime）、结束时间（endtime）和存储时间（storetime），以及药物或治疗相关的字段，如项目ID（itemid）、数量（amount）、单位（amountuom）、速率（rate）、速率单位（rateuom）等。数据集的分割信息显示，训练集包含14,253,480个样本，总大小为2,711,998,534字节。

This dataset contains multiple fields related to healthcare, such as patient ID (subject_id), hospital admission ID (hadm_id), stay ID (stay_id), caregiver ID (caregiver_id), etc. These fields may be used to record and analyze patient hospitalization information, nursing records, medication usage, etc. The dataset also includes time-related fields such as start time (starttime), end time (endtime), and storage time (storetime), as well as medication or treatment-related fields such as item ID (itemid), amount (amount), unit (amountuom), rate (rate), rate unit (rateuom), etc. The datasets split information shows that the training set contains 14,253,480 samples with a total size of 2,711,998,534 bytes.