将医疗数据从XML转换为CSV或JSON格式?

时间:2018-07-25 00:35:55

标签: json csv xml-parsing nlp data-science

这是患者的病历,其中包含有关病史,过去,家庭等的大量信息。这是一个XML文件。我想得到的是json或CSV格式。

某些记录的报告格式与这些主题相同,而某些记录在其他记录中的命名也有所不同,例如“出院日期和时间”,而不仅仅是“出院日期”,或者还有其他主题,例如“已完成的保全”等。

我将“ xxxx”或“ .....”放在关于患者的长文本行中(8-10行)。

  <doc id="1">
<text>
490646815 | WMC | 31530471 | | 9629480 | xx/xx/xxxx xx:xx/:xx**strong text** AM | ANEMIA 
| Signed | DIS | Admission Date: xx/xx/xxxx Report Status: Signed
Discharge Date: xxxxx
ATTENDING: xxxx
PRINCIPAL DIAGNOSIS: xxx and xxx.
SECONDARY DIAGNOSES: Diabetes , xxxx.
HISTORY OF PRESENT ILLNESS: The patient is xxxxx......
PRE-ADMISSION MEDICATIONS: Caltrate , xxx,.....
PAST MEDICAL HISTORY: Chronic xxxx....
FAMILY HISTORY: No family history xxxxx
SOCIAL HISTORY: She has xxxx
ALLERGIES: Codeine and Benadryl.
ADMISSION PHYSICAL EXAMINATION: Vital signs xxx....
STUDIES: EKG showed atrial fibrillation with slow ventricular
response with heart rate of 53 , widened QRS , a Q wave in aVL , and
U waves in the lateral leads......
PROCEDURE: xxxx.
HOSPITAL COURSE BY PROBLEM:
1.xxxx
2.xxx
3.xxx
DISCHARGE MEDICATIONS: Norvasc 5 mg daily , Caltrate plus.....
DISPOSITION: To home with services.
FOLLOW-UP APPOINTMENTS: The patient will follow up with xxxx
CODE STATUS: The patient is full code , and her healthcare proxy
is her daughter , xxxx
PRIMARY CARE PHYSICIAN: xxxxx
eScription document: 6xxxx
Dictated By: xxxx
Attending: xxxx
Dictation ID xxxx
D: 10/15/06
T: 10/10/06</text>
</doc>

0 个答案:

没有答案