commit 8598df49309f02209b9f4982bee9f331e73b818b Author: admin <572701190@qq.com> Date: Fri May 8 21:28:29 2026 +0800 first commit diff --git a/.dockerignore b/.dockerignore new file mode 100644 index 0000000..7daea2a --- /dev/null +++ b/.dockerignore @@ -0,0 +1,7 @@ +__pycache__/ +*.pyc +.git/ +.venv/ +uploads/ +jobs/ + diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..14903b3 --- /dev/null +++ b/.gitignore @@ -0,0 +1,6 @@ +__pycache__/ +*.pyc +.venv/ +jobs/ +uploads/ + diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 0000000..86c10b5 --- /dev/null +++ b/Dockerfile @@ -0,0 +1,16 @@ +FROM python:3.12-slim + +ENV PYTHONDONTWRITEBYTECODE=1 \ + PYTHONUNBUFFERED=1 + +WORKDIR /app + +COPY requirements.txt . +RUN pip install --no-cache-dir -r requirements.txt + +COPY app ./app + +EXPOSE 8000 + +CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"] + diff --git a/README.md b/README.md new file mode 100644 index 0000000..164d258 --- /dev/null +++ b/README.md @@ -0,0 +1,33 @@ +# HIS_Sur_Data_Deal + +网页端检测数据处理工具。上传 `待处理检测数据.zip` 后，服务会自动识别 V1/V2 数据结构，调用原处理脚本生成 Excel，并返回结果压缩包。 + +## 本地运行 + +```bash +pip install -r requirements.txt +uvicorn app.main:app --host 0.0.0.0 --port 8000 +``` + +访问 `http://localhost:8000`。 + +## Docker 构建与运行 + +```bash +docker build -t his-sur-data-deal . +docker run --rm -p 8000:8000 his-sur-data-deal +``` + +## 推送镜像示例 + +```bash +docker tag his-sur-data-deal 192.168.31.5:5002/admin/his-sur-data-deal:latest +docker push 192.168.31.5:5002/admin/his-sur-data-deal:latest +``` + +## 数据模式 + +V1：zip 解压后包含 `Patients_info.csv`、`Tests_List`、`Tests_Detail_List`，输出一个汇总 Excel。 + +V2：zip 解压后包含 `Patients_info.csv`，并按患者目录分别保存检测汇总和具体检测，输出多个患者 Excel。 + diff --git a/app/__init__.py b/app/__init__.py new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/app/__init__.py @@ -0,0 +1 @@ + diff --git a/app/main.py b/app/main.py new file mode 100644 index 0000000..3956e33 --- /dev/null +++ b/app/main.py @@ -0,0 +1,244 @@ +import html +import shutil +import tempfile +import uuid +from pathlib import Path + +from fastapi import FastAPI, File, Form, HTTPException, UploadFile +from fastapi.responses import FileResponse, HTMLResponse + +from .processor import ProcessingError, run_processing + + +APP_ROOT = Path(__file__).resolve().parent +WORK_ROOT = Path(tempfile.gettempdir()) / "his_sur_data_deal_jobs" +WORK_ROOT.mkdir(parents=True, exist_ok=True) + +app = FastAPI(title="检测数据处理") + + +@app.get("/", response_class=HTMLResponse) +def index() -> str: + return """ + + + + + + 检测数据处理 + + + +

检测数据处理

上传“待处理检测数据.zip”，处理完成后自动下载结果压缩包。

+ +

V1 适用于含有 Patients_info.csv、Tests_List、Tests_Detail_List 的批量数据；V2 适用于每个患者单独目录的数据。

+ + +""" + + +@app.post("/process") +async def process( + file: UploadFile = File(...), + mode: str = Form("auto"), + data_type: str = Form("pat_no"), + result_name: str = Form("Result"), + show_not_match: str | None = Form(None), + show_all_infos: str | None = Form(None), +) -> FileResponse: + if not file.filename or not file.filename.lower().endswith(".zip"): + raise HTTPException(status_code=400, detail="请上传 zip 文件。") + + job_dir = WORK_ROOT / uuid.uuid4().hex + job_dir.mkdir(parents=True, exist_ok=True) + upload_path = job_dir / "input.zip" + try: + with upload_path.open("wb") as out: + shutil.copyfileobj(file.file, out) + + result_zip = run_processing( + zip_path=upload_path, + job_dir=job_dir, + mode=mode, + data_type=data_type, + result_name=result_name, + show_not_match=show_not_match == "true", + show_all_infos=show_all_infos == "true", + ) + except ProcessingError as exc: + safe_detail = html.escape(str(exc)) + raise HTTPException(status_code=400, detail=safe_detail) from exc + except Exception as exc: + raise HTTPException(status_code=500, detail=f"处理失败：{exc}") from exc + + return FileResponse( + result_zip, + media_type="application/zip", + filename="检测数据处理结果.zip", + ) + + +@app.get("/health") +def health() -> dict[str, str]: + return {"status": "ok"} + diff --git a/app/processor.py b/app/processor.py new file mode 100644 index 0000000..4cca040 --- /dev/null +++ b/app/processor.py @@ -0,0 +1,181 @@ +import os +import shutil +import subprocess +import sys +import zipfile +from pathlib import Path + + +PROCESSOR_DIR = Path(__file__).resolve().parent / "processors" + + +class ProcessingError(Exception): + pass + + +def run_processing( + zip_path: Path, + job_dir: Path, + mode: str, + data_type: str, + result_name: str, + show_not_match: bool, + show_all_infos: bool, +) -> Path: + if mode not in {"auto", "v1", "v2"}: + raise ProcessingError("处理模式不正确。") + if data_type not in {"pat_no", "zhuyuanhao"}: + raise ProcessingError("患者编号类型不正确。") + + extract_dir = job_dir / "input" + output_dir = job_dir / "output" + extract_dir.mkdir(parents=True, exist_ok=True) + output_dir.mkdir(parents=True, exist_ok=True) + + _safe_extract(zip_path, extract_dir) + data_dir = _find_data_root(extract_dir) + selected_mode = _detect_mode(data_dir) if mode == "auto" else mode + + clean_name = _clean_result_name(result_name) + if selected_mode == "v1": + result_path = output_dir / f"{clean_name}.xlsx" + cmd = [ + sys.executable, + str(PROCESSOR_DIR / "V1-ALL_convert_Lab_Test_data.py"), + str(data_dir), + str(result_path), + str(show_not_match), + str(show_all_infos), + data_type, + ] + elif selected_mode == "v2": + cmd = [ + sys.executable, + str(PROCESSOR_DIR / "V2-Every_Pat_File_convert_Lab_Test_data.py"), + "--file_dir", + str(data_dir), + "--result_save_file_name", + clean_name, + "--show_not_match", + str(show_not_match), + "--show_all_infos", + str(show_all_infos), + "--data_type", + data_type, + ] + else: + raise ProcessingError("无法识别数据目录结构，请手动选择 V1 或 V2。") + + env = os.environ.copy() + env["PYTHONUTF8"] = "1" + env["PYTHONIOENCODING"] = "utf-8" + + completed = subprocess.run( + cmd, + cwd=PROCESSOR_DIR, + env=env, + text=True, + encoding="utf-8", + errors="replace", + stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, + timeout=60 * 30, + ) + + log_path = output_dir / "process.log" + log_path.write_text( + "mode=" + selected_mode + "\n\n" + completed.stdout, + encoding="utf-8", + ) + if completed.returncode != 0: + raise ProcessingError(f"处理脚本退出码 {completed.returncode}。\n{completed.stdout[-4000:]}") + + if selected_mode == "v2": + _collect_v2_outputs(data_dir, output_dir) + _collect_logs(data_dir, output_dir) + + xlsx_files = list(output_dir.rglob("*.xlsx")) + if not xlsx_files: + raise ProcessingError("处理完成但没有生成 Excel 文件，请检查数据结构和 process.log。") + + result_zip = job_dir / "result.zip" + with zipfile.ZipFile(result_zip, "w", compression=zipfile.ZIP_DEFLATED) as zf: + for path in output_dir.rglob("*"): + if path.is_file(): + zf.write(path, path.relative_to(output_dir)) + return result_zip + + +def _safe_extract(zip_path: Path, target_dir: Path) -> None: + try: + with zipfile.ZipFile(zip_path) as zf: + for member in zf.infolist(): + destination = (target_dir / member.filename).resolve() + if not str(destination).startswith(str(target_dir.resolve())): + raise ProcessingError("zip 中包含不安全路径。") + zf.extractall(target_dir) + except zipfile.BadZipFile as exc: + raise ProcessingError("zip 文件无法解压。") from exc + + +def _find_data_root(extract_dir: Path) -> Path: + candidates = [extract_dir] + children = [p for p in extract_dir.iterdir() if p.is_dir()] + if len(children) == 1 and not any(p.is_file() for p in extract_dir.iterdir()): + candidates.insert(0, children[0]) + + for candidate in candidates: + if (candidate / "Patients_info.csv").exists(): + return candidate + + for path in extract_dir.rglob("Patients_info.csv"): + return path.parent + + raise ProcessingError("未找到 Patients_info.csv。") + + +def _detect_mode(data_dir: Path) -> str: + if (data_dir / "Tests_List").is_dir() and (data_dir / "Tests_Detail_List").is_dir(): + return "v1" + + patient_dirs = [p for p in data_dir.iterdir() if p.is_dir()] + for patient_dir in patient_dirs: + names = {p.name for p in patient_dir.iterdir()} + has_summary = any(name.endswith("_检测汇总.csv") for name in names) + has_detail_dir = any(name.endswith("_具体检测") and (patient_dir / name).is_dir() for name in names) + if has_summary and has_detail_dir: + return "v2" + + raise ProcessingError("无法自动识别 V1/V2 数据结构。") + + +def _clean_result_name(result_name: str) -> str: + name = (result_name or "Result").strip() + if name.lower().endswith(".xlsx"): + name = name[:-5] + forbidden = '<>:"/\\|?*' + name = "".join("_" if ch in forbidden else ch for ch in name).strip(" .") + return name or "Result" + + +def _collect_v2_outputs(data_dir: Path, output_dir: Path) -> None: + v2_dir = output_dir / "V2患者结果" + v2_dir.mkdir(exist_ok=True) + for path in data_dir.rglob("*.xlsx"): + if path.is_file(): + target = v2_dir / path.name + if target.exists(): + target = v2_dir / f"{path.parent.name}_{path.name}" + shutil.copy2(path, target) + + +def _collect_logs(data_dir: Path, output_dir: Path) -> None: + logs_dir = output_dir / "logs" + for pattern in ("*.txt", "error.txt", "Error.txt"): + for path in data_dir.rglob(pattern): + if path.is_file(): + logs_dir.mkdir(exist_ok=True) + relative = path.relative_to(data_dir) + target = logs_dir / relative + target.parent.mkdir(parents=True, exist_ok=True) + shutil.copy2(path, target) diff --git a/app/processors/V1-ALL_convert_Lab_Test_data.py b/app/processors/V1-ALL_convert_Lab_Test_data.py new file mode 100644 index 0000000..d1e9f54 --- /dev/null +++ b/app/processors/V1-ALL_convert_Lab_Test_data.py @@ -0,0 +1,364 @@ +#!/usr/bin/env python3 +# -*- coding: UTF-8 -*- +import csv, sys, os, copy, re +import os.path as osp +from openpyxl import Workbook, load_workbook + +# 向特定excel的sheet中添加内容 +workbook = None # 全局变量，初始值为 None +file_path_g = None +def add_content_to_excel(file_path, sheet_name, content): + global workbook, file_path_g # 声明 workbook 为全局变量 + # 如果改换工作路径且workbook不为空 + if file_path_g != file_path and not (workbook is None): + # 保存工作簿 + workbook.save(file_path_g) + print("保存Excel工作表在：", file_path_g) + elif file_path_g != file_path: + try: + # 尝试加载现有的工作簿 + workbook = load_workbook(file_path) + except FileNotFoundError: + # 如果文件不存在，则创建一个新的工作簿 + workbook = Workbook() + file_path_g = file_path + + if sheet_name not in workbook.sheetnames: + # 如果工作表不存在，则创建一个新的工作表 + workbook.create_sheet(sheet_name) + + # 选择指定的工作表 + sheet = workbook[sheet_name] + + # 向工作表添加内容 + # 检查列表的第一个元素 + if isinstance(content, list) and content and isinstance(content[0], list): + # "二维列表" + for row in content: + sheet.append(row) + elif isinstance(content, list): + # "一维列表" + sheet.append(content) + elif isinstance(content, str): + # "字符串" + sheet.append([content]) + else: + print('add_content_to_excel输入参数为', content, '其不是列表、字符串') + +def save_excel(): + global workbook, file_path_g + if not (workbook is None): + # 保存工作簿 + print("Excel工作表保存在：", file_path_g) + workbook.save(file_path_g) + +# 自定义数据 +# 1.数据所在路径 +file_dir = sys.argv[1] +# 2.文件保存路径 +result_save_pth = sys.argv[2] # osp.join(file_dir, 'Result.xlsx') # +# 3.是否输出不匹配内容 +show_not_match = sys.argv[3] +# 4. 数据类型：pat_no / zhuyuanhao +data_type = sys.argv[5] + +if (show_not_match.lower() == 'true'): + show_not_match = True +else: + show_not_match = False +# 4.是否输出全部信息（包括全无项） +show_all_infos = sys.argv[4] +if (show_all_infos.lower() == 'true'): + show_all_infos = True +else: + show_all_infos = False + +####### 生成信息 ####### +# Patients_info文件的路径 +Patients_info_pth = osp.join(file_dir, 'Patients_info.csv') +# Tests_List目录的路径 +patno_dir = osp.join(file_dir, 'Tests_List') +# Tests_List目录的路径 +Patient_detail_infos_dir = osp.join(file_dir, 'Tests_Detail_List') +RED = '\033[91m' +RESET = '\033[0m' +error_dir = osp.join(file_dir, 'error.txt') + +# 输出错误函数 +def Error(output_str="Error:", error_dir=error_dir): + # 打开 error.txt 文件并写入字符串 + with open(error_dir, "a+") as file: + # 将字符串输出到标准错误流 sys.stderr + file.write(output_str+'\n') + print(RED+output_str+RESET) + +# 判断字符串是否匹配正则表达式 +def match_re(string, pattern): + # 使用 str() 强制转换，防止出现 None 或数字导致的报错 + if re.match(str(pattern), str(string)): + return True + else: + return False + +# 1.删除Error文件 +if os.path.exists(error_dir): + os.remove(error_dir) + print("删除Error文件:", error_dir) + +# 2.打开Patients_info.csv文件，遍历出所有有效患者 +with open(Patients_info_pth, "r", encoding='utf-8-sig') as file: + reader_ = csv.DictReader(file) + reader_Patients_info = [] + for r in reader_: + reader_Patients_info.append(r) + # 读取pat_no列数据 + if data_type == "pat_no": + pat_no_col = [f"{int(row['pat_no']):010}" for row in reader_Patients_info] + elif data_type == "zhuyuanhao": + pat_no_col = [f"{row['pat_no']}" for row in reader_Patients_info] + else: + print("数据类型需要为pat_no或zhuyuanhao") + pat_no_col = list(set(pat_no_col)) # 去除数组中重复内容 + + # *** 注意： TODO for循环和list的remove相冲突，因此深拷贝原有元素 + # 遍历所有pat_no，查看pat_no中是否有对应文件 + pat_no_col_ = copy.deepcopy(pat_no_col) + for i in range(len(pat_no_col_)): + pat_no = pat_no_col_[i] + # 查看Tests_List目录下是否有对应的文件 + file_path = osp.join(patno_dir, pat_no+'.csv') + if not osp.exists(file_path): + # 去除对应元素并报错 + pat_no_col.remove(pat_no) + Error(f"{pat_no}.csv 在 {patno_dir} 中不存在") + + # 遍历所有pat_no，查看Patient_detail_infos中是否有对应文件 + pat_no_col_ = copy.deepcopy(pat_no_col) + for i in range(len(pat_no_col_)): + pat_no = pat_no_col_[i] + # 查看Patient_detail_infos目录下是否有对应的文件夹 + file_path = osp.join(Patient_detail_infos_dir, pat_no) + if not osp.exists(file_path): + pat_no_col.remove(pat_no) + Error(f"{pat_no} 文件夹在 {Patient_detail_infos_dir} 中不存在") + + print("有效可处理患者数为：", len(pat_no_col), f"\n无效数据已存储至{error_dir}中了") + +# 3.遍历所有患者打开patno文件夹中的patno.csv +# 获取患者头部信息（提取于Patients_info.csv） +Front_line = {'姓名':'pat_name', '住院号':'pat_no'} +# 获取患者检测基本信息（提取于patno文件夹） +Basic_line = {'采样时间': 'sampled_dt', '检测原因':'req_reason'} +# 所有检测具体信息（提取于Patient_detail_infos文件夹） +# 一个检查包括：检测rptunitids、检查名(自主命名)、检查项、检查结果所在列、存放结果dict +#{'test_rptunitid':[str(X), str(X)], 'test_check_name':'XXX', 'test_check_list':["XXX", "XXX", ], 'test_check_list_all':["XXX", "XXX", ], 'test_result_col_name':"result_str"}, +ALL_tests = [# 血细胞 # (1):血细胞分析+五分类；(2):血细胞分析+五分类；(4):血细胞五分类+CRP；东院区：(106):血细胞分析+五分类 + {'test_rptunitid':[str(1), str(2), str(4), str(106)], 'test_check_name':'血细胞', 'test_check_list':["血红蛋白", "红细胞压积", "平均红细胞体积", "平均血红蛋白含量", "平均血红蛋白浓度", "红细胞宽度-CV值", "红细胞宽度-SD值", "血小板计数", "血小板分布宽度", "平均血小板体积", "大血小板比率", "血小板压积", "淋巴细胞计数", "单核细胞计数", "中性粒细胞计数", "嗜酸细胞计数", "嗜碱细胞计数", "淋巴细胞百分比", "单核细胞百分比", "中性粒细胞百分比", "嗜酸细胞百分比", "嗜碱细胞百分比", "白细胞计数", "红细胞计数", "CRP检验=====", "C反应蛋白", "超敏CRP", ], 'test_check_list_all':["血红蛋白", "红细胞压积", "平均红细胞体积", "平均血红蛋白含量", "平均血红蛋白浓度", "红细胞宽度-CV值", "红细胞宽度-SD值", "血小板计数", "血小板分布宽度", "平均血小板体积", "大血小板比率", "血小板压积", "淋巴细胞计数", "单核细胞计数", "中性粒细胞计数", "嗜酸细胞计数", "嗜碱细胞计数", "淋巴细胞百分比", "单核细胞百分比", "中性粒细胞百分比", "嗜酸细胞百分比", ["嗜碱细胞百分比", "嗜碱细胞%"], ["白细胞计数", "白细胞"], "红细胞计数", "CRP检验=====", "C反应蛋白", ["超敏CRP", "超敏C反应蛋白"], ], 'test_result_col_name':"result_str"}, + # 凝血 # (3):凝血六项；(110):东院区；(90):凝血和血小板功能监测 + {'test_rptunitid':[str(3), str(110),str(90)], 'test_check_name':'凝血', 'test_check_list':["凝血酶原时间", "凝血酶原活动度", "血浆凝血酶原时间比值", "凝血酶原国际标准化比值", "活化部分凝血活酶时间", "活化部分凝血活酶比值", "凝血酶时间", "凝血酶时间比值", "纤维蛋白原含量", "D-二聚体测定", "纤维蛋白原降解产物", "凝血酶生成时间","凝血速率","血小板功能"],\ + 'test_check_list_all':["凝血酶原时间*", ["凝血酶原活动度", r"凝血酶原活度\(%\)"], ["凝血酶原比值", "血浆凝血酶原时间比值"], ["凝血酶原标准化比值", "凝血酶原国际标准化比值"], ["活化部分凝血活酶时间*", "活化部分凝血酶时间*"], "活化部分凝血活酶比值", "凝血酶时间", "凝血酶时间比值", "纤维蛋白原含量", [r"D-二聚体\(sysmex\)", "D-二聚体测定*"], [r"纤维蛋白\(原\)降解产物", "纤维蛋白原降解产物"], "凝血酶生成时间","凝血速率","血小板功能"], 'test_result_col_name':"result_str"}, + # 肝功 # (5):平诊肝功十四项+平诊电解质八项+平诊肾功七项；(20)急诊肝功十二项_急诊肾功五项[复]_急诊电解质七项[复]；东院区：（108）：传染性指标检测八项 + {'test_rptunitid':[str(5), str(20), str(108)], 'test_check_name':'肝功', 'test_check_list':["谷草转氨酶", "谷丙转氨酶", "谷草/谷丙", "碱性磷酸酶", "γ谷氨酰氨转肽酶", "总胆红素", "直接胆红素", "间接胆红素", "胆碱脂酶", "总胆固醇", "总蛋白", "白蛋白", "球蛋白", "白球比", "总胆汁酸", "a-L-岩藻糖苷酶", "前白蛋白", "超氧化物歧化酶", "尿素", "肌酐", "胱抑素C", "葡萄糖", "尿酸", "钾", "钠", "氯", "磷", "钙", "镁", "二氧化碳结合率", "离子间隙", "糖化白蛋白", "视黄醇结合蛋白", "eGFR(CKD-EPI)", "a-l岩藻糖苷酶", "超氧化物歧化酶", "eGFR(MDRD)", r"eGFR单位ml/min/1.73m^2", "8597", "乳酸测定", "乳酸脱氢酶", "羟丁酸脱氢酶", "肌酸激酶", "肌酸激酶同工酶", "载脂蛋白A", "载脂蛋白B", "载脂蛋白E", "脂蛋白（a）", "缺血修饰白蛋白", "甘油三酯", "高密度脂蛋白", "低密度脂蛋白", ], \ + 'test_check_list_all':["谷草转氨酶", "谷丙转氨酶", "谷草/谷丙", "碱性磷酸酶", ["γ谷氨酰氨转肽酶", "γ-谷氨酰转肽酶"], "总胆红素", "直接胆红素", "间接胆红素", "胆碱脂酶", "总胆固醇", "总蛋白", "白蛋白", "球蛋白", "白球比", "总胆汁酸", "a-L-岩藻糖苷酶", "前白蛋白", "超氧化物歧化酶", "尿素", "肌酐", "胱抑素C", "葡萄糖", "尿酸", "钾", "钠", "氯", "磷", "钙", "镁", "二氧化碳结合率", "离子间隙", "糖化白蛋白", "视黄醇结合蛋白", r"eGFR\(CKD-EPI\)", "a-l岩藻糖苷酶", "超氧化物歧化酶", r"eGFR\(MDRD\)", r"eGFR单位ml/min/1.73m\^2", "8597", "乳酸测定", "乳酸脱氢酶", "羟丁酸脱氢酶", "肌酸激酶", "肌酸激酶同工酶", "载脂蛋白A", "载脂蛋白B", "载脂蛋白E", "脂蛋白（a）", "缺血修饰白蛋白", "甘油三酯", "高密度脂蛋白", "低密度脂蛋白", ], 'test_result_col_name':"result_str"}, + # 各类肿瘤标志物 # (6):各类肿瘤标志物，e.g.肿瘤标志物肺癌六项[复]、肿瘤标志物十项(男)；东院区：（108）：肿瘤标志物肺癌六项[复] + {'test_rptunitid':[str(6), str(108)], 'test_check_name':'各类肿瘤标志物', 'test_check_list':["胃泌素释放肽前体(罗氏)", "鳞状上皮细胞癌抗原(罗氏)", "癌胚抗原", "甲胎蛋白", "糖类抗原125", "糖类抗原199", "糖类抗原724", "细胞角蛋白19片段", "神经元特异性烯醇化酶测定", "总前列腺特异性抗原", "游离前列腺抗原", "游离/总", "糖类抗原153","人附睾蛋白","绝经前 ROMA","绝经后 ROMA","铁蛋白","叶酸","维生素B12","高尔基体蛋白73测定","胃蛋白酶原Ⅰ","胃蛋白酶原Ⅱ","胃蛋白酶原Ⅰ/Ⅱ","降钙素","甲状腺球蛋白"],\ + 'test_check_list_all':[r"胃泌素释放肽前体\(罗氏\)", ["鳞状上皮细胞癌相关抗原", r"鳞状上皮细胞癌抗原\(罗氏\)"], "癌胚抗原", "甲胎蛋白", "糖类抗原125", "糖类抗原199", "糖类抗原724", "细胞角蛋白19片段", "神经元特异性烯醇化酶测定", "总前列腺特异性抗原", "游离前列腺抗原", "游离/总", "糖类抗原153","人附睾蛋白","绝经前 ROMA","绝经后 ROMA","铁蛋白","叶酸","维生素B12","高尔基体蛋白73测定","胃蛋白酶原Ⅰ","胃蛋白酶原Ⅱ","胃蛋白酶原Ⅰ/Ⅱ","降钙素","甲状腺球蛋白"], 'test_result_col_name':"result_str"}, + # 七抗 # (10):肺癌七种自身抗体检测 + {'test_rptunitid':str(10), 'test_check_name':'七抗', 'test_check_list':["p53自身抗体", "PGP9.5自身抗体", "SOX2自身抗体", "GAGE7自身抗体", "GBU4-5自身抗体", "MAGE A1自身抗体", "CAGE自身抗体", ], 'test_check_list_all':["p53自身抗体", "PGP9.5自身抗体", "SOX2自身抗体", "GAGE7自身抗体", "GBU4-5自身抗体", "MAGE A1自身抗体", "CAGE自身抗体", ], 'test_result_col_name':"result_str"}, + # 传染指标 # (52):传染指标八项-急诊；(53):传染性指标检测八项[复]；东院区:(108):传染性指标检测八项[复] + {'test_rptunitid':[str(52), str(53), str(108)], 'test_check_name':'传染指标', 'test_check_list':["乙肝表面抗原定量", "乙肝表面抗体定量", "乙肝e抗原", "乙肝e抗体", "乙肝核心抗体", "丙型肝炎抗体", "梅毒螺旋体抗体", "人类免疫缺陷病毒", ], 'test_check_list_all':["乙肝表面抗原定量", "乙肝表面抗体定量", "乙肝e抗原", "乙肝e抗体", "乙肝核心抗体", "丙型肝炎抗体", ["螺旋体特异抗体", "梅毒螺旋体抗体"], ["人免疫缺陷病毒", "人类免疫缺陷病毒"], ], 'test_result_col_name':"result_str"}, + # 血气分析+生化分析 # (16):血气分析+生化六项[复]/血气分析3, (49):血气分析+生化六项[复], (50):血气分析+生化五项[复], (73/74):血气分析+生化十项[复], (89):血气分析+生化六项[复], (112):血气分析/血气分析+生化七项[复], (158):血气分析+生化六项[复]；(42):血气分析+生化六项[复] + {'test_rptunitid':[str(16), str(49), str(50), str(73), str(74), str(89), str(112), str(158),str(42)], 'test_check_name':'血气分析+生化分析', 'test_check_list':["体温", "吸氧流量", "酸碱度", "氧分压", "二氧化碳分压", "二氧化碳总量", "红细胞压积", "总血红蛋白", "氧饱和度", "Na+钠离子浓度", "钾离子浓度", "钙离子浓度", "氯离子浓度", "标准离子钙", "氢离子浓度", "酸碱度计算值", "PCO2分压计算值", "p氧分压计算值", "pO2(A-a)(T)_r", "pO2(a/A)(T)_r", "呼吸指数计算值", "pO2(T)/FIO2_r", "氢离子浓度", "HCO3-act_r", "HCO3-std_r", "BE(ecf)_r", "血液缓冲碱", "ctCO2", "pO2(A-a)_r", "pO2(a/A)_r", "呼吸指数", "氧和指数", "阴离子间隙", "渗透压", "血糖", "乳酸", "实际碳酸氢盐", "标准碳酸氢盐", "实际碱剩余", "标准碱剩余", "细胞外液剩余碱","氧合血红蛋白","一氧化碳血红蛋白", "还原血红蛋白","高铁血红蛋白", "总胆红素", "A-aDO2", "pAO2", "paO2/pAO2", "50%饱和度氧分压", "动脉血氧含量", "肺泡动脉氧分压差", "动脉氧分压与肺泡氧分压之比", "pCO2(T)", "pO2(T)", "PH(T)", "吸氧浓度","平均肺泡氧分压"],\ + 'test_check_list_all':["体温", "吸氧流量", "酸碱度", "氧分压", "二氧化碳分压", "二氧化碳总量", "红细胞压积", "总血红蛋白", "氧饱和度", ["Na\+钠离子浓度", "钠离子"], ["钾离子浓度","钾离子"], ["钙离子浓度","钙离子"], ["氯离子浓度","氯离子"], ["标准离子钙","PH=7.4的钙"], "氢离子浓度", "酸碱度计算值", "PCO2分压计算值", "p氧分压计算值", r"pO2\(A-a\)\(T\)_r", r"pO2\(a/A\)\(T\)_r", "呼吸指数计算值", r"pO2\(T\)/FIO2_r", "氢离子浓度", "HCO3-act_r", "HCO3-std_r", r"BE\(ecf\)_r", "血液缓冲碱", "ctCO2", r"pO2\(A-a\)_r", r"pO2\(a/A\)_r", "呼吸指数", "氧和指数", "阴离子间隙", "渗透压", "血糖", "乳酸", ["实际碳酸氢盐","血浆碳酸氢盐浓度"], "标准碳酸氢盐", ["血液剩余碱","实际碱剩余"], "标准碱剩余", "细胞外液剩余碱","氧合血红蛋白","一氧化碳血红蛋白", "还原血红蛋白","高铁血红蛋白", "总胆红素", "A-aDO2", "pAO2", "paO2/pAO2", "50%饱和度氧分压", "动脉血氧含量", "肺泡动脉氧分压差", "动脉氧分压与肺泡氧分压之比", r"pCO2\(T\)", r"pO2\(T\)", r"PH\(T\)", "吸氧浓度","平均肺泡氧分压"], 'test_result_col_name':"result_str"}, + # 感染指标 # (77)/(92)/(113)/(126)/(77)/(82)/:新型冠状病毒核酸检测[复]； (75):新型冠状病毒抗体； (25):新冠核酸检测[复]/乙肝病毒DNA含量/结核杆菌定量测定；str(121)/str(37):一般细菌涂片检查；str(111):乙型肝炎DNA定量测定；str(29):免疫8项；str(34):内毒素+D葡聚糖测定，str(38)/(116):红细胞沉降率测定；str(36):结核Xpert鉴定及耐药[复]；str(10):结核感染T细胞检测；str(24):自身抗体谱测定(18项)；str(23):血清肌钙蛋白I测定 + {'test_rptunitid':[str(77),str(25),str(92),str(113),str(126),str(75),str(77),str(82),str(30),str(121),str(37),str(111),str(29),str(34),str(38),str(116),str(36),str(10),str(23)], 'test_check_name':'感染指标', 'test_check_list':["新型冠状病毒抗体IgG","新型冠状病毒抗体IgM", "新型冠状病毒核酸检测","新型冠状病毒核酸混检", "乙肝病毒DNA含量","结核杆菌定量测定", "EB病毒定量测定","巨细胞病毒定量测定","白细胞","上皮细胞","革兰氏阳性球菌","革兰氏阴性球菌","革兰氏阴性球杆菌","革兰氏阳性杆菌","革兰氏阴性杆菌","真菌菌丝" ,"真菌孢子","抗酸染色", "HPV6","HPV11","抗链球菌溶血素O定量测定","KAP轻链","LAM轻链","免疫球蛋白IgE","免疫球蛋白G","免疫球蛋白M","免疫球蛋白A","补体C3","补体C4","类风湿因子","C反应蛋白","G-脂多糖","1-3-β-D葡聚糖","抗心磷脂IgG抗体","EB病毒核心抗原IgG抗体","EB病毒衣壳抗原IgG抗体","EB病毒早期抗原IgM抗体","EB病毒衣壳抗原IgM抗体","红细胞沉降率测定","降钙素原",r"淋巴细胞培养+干扰素\(基础水平N\)",r"结核杆菌γ干扰素释放试验\(T-N\)",r"结核杆菌阳性对照反应\(M-N\)",r"结核杆菌特异性细胞免疫反应提示", "抗dsDNA抗体","抗核小体抗体","抗组蛋白抗体","抗SmD1抗体","抗PCNA抗体","抗核糖体P蛋白测定","抗SSA/Ro60kD抗体","抗SSA/Ro52kD抗体","抗ssb抗体","抗CENPB抗体","抗Scl-70抗体","抗U1-snRNP抗体","抗Jo-1抗体","抗PM-Scl抗体","抗Ku抗体","抗AMA-M2抗体","抗Mi-2抗体",r"抗核抗体\(1:80\)","高敏肌钙蛋白I" ],\ + 'test_check_list_all':["新型冠状病毒抗体IgG","新型冠状病毒抗体IgM",["新型冠状病毒核酸检测", "新型冠状病毒核酸快速检测"], r"新型冠状病毒核酸检测\(混检\)",["乙肝病毒DNA含量","乙型肝炎病毒DNA定量"],"结核杆菌定量测定", "EB病毒定量测定","巨细胞病毒定量测定","白细胞","上皮细胞",["革兰氏阳性球菌","革兰阳性球菌"],["革兰阴性球菌","革兰氏阴性球菌"],"革兰氏阴性球杆菌",["革兰阳性杆菌","革兰氏阳性杆菌"],["革兰阴性杆菌","革兰氏阴性杆菌"],"真菌菌丝","真菌孢子","抗酸染色","HPV6","HPV11","抗链球菌溶血素O定量测定","KAP轻链","LAM轻链","免疫球蛋白IgE","免疫球蛋白G","免疫球蛋白M","免疫球蛋白A","补体C3","补体C4","类风湿因子","C反应蛋白","G-脂多糖","1-3-β-D葡聚糖","抗心磷脂IgG抗体","EB病毒核心抗原IgG抗体","EB病毒衣壳抗原IgG抗体","EB病毒早期抗原IgM抗体","EB病毒衣壳抗原IgM抗体","红细胞沉降率测定","降钙素原",r"淋巴细胞培养+干扰素\(基础水平N\)",r"结核杆菌γ干扰素释放试验\(T-N\)",r"结核杆菌阳性对照反应\(M-N\)",r"结核杆菌特异性细胞免疫反应提示","抗dsDNA抗体","抗核小体抗体","抗组蛋白抗体","抗SmD1抗体","抗PCNA抗体","抗核糖体P蛋白测定","抗SSA/Ro60kD抗体","抗SSA/Ro52kD抗体","抗ssb抗体","抗CENPB抗体","抗Scl-70抗体","抗U1-snRNP抗体","抗Jo-1抗体","抗PM-Scl抗体","抗Ku抗体","抗AMA-M2抗体","抗Mi-2抗体",r"抗核抗体\(1:80\)","高敏肌钙蛋白I"], 'test_result_col_name':"result_str"}, + # 基因检测指标 # (41):CYP2C19基因检测[复] + {'test_rptunitid':[str(41)], 'test_check_name':'基因检测指标', 'test_check_list':[r"GG_681GG\)",r"GG_681GA\)",r"GA_681GG\)",r"GG_681AA\)",r"AA_681GG\)",r"GA_681GA\)" ],\ + 'test_check_list_all':[r"\*1/\*1\(636", r"\*1/\*2\(636",r"\*1/\*3\(636", r"\*2/\*2\(636",r"\*3/\*3\(636", r"\*2/\*3\(636", ], 'test_result_col_name':"result_ref"}, + # 心衰系列 # str(20):B型前脑尿钠肽, str(16):B型前脑尿钠肽检测（Pro-BN_降钙素原检；str(108):B型尿钠肽检测（BNP) + {'test_rptunitid':[str(20),str(16)], 'test_check_name':'心衰系列', 'test_check_list':['B型前脑尿钠肽','高敏肌钙蛋白T'],\ + 'test_check_list_all':['B型前脑尿钠肽','高敏肌钙蛋白T'], 'test_result_col_name':"result_str"}, + # 普通指标 # str(79),str(51):卡式血型鉴定；str(12):肝纤维化指标（五项）；str(22)/(33):胃液常规检查；str(161):甲功五项（化学发光法）[复] + {'test_rptunitid':[str(79),str(51),str(12),str(22),str(33),str(161)], 'test_check_name':'普通指标', 'test_check_list':['ABO正定型','ABO反定型','ABO血型',r'Rh\(D\)血型','TPO过氧化物酶自身抗体','T4甲状腺素','T3三碘甲腺原氨酸','FT4游离甲状腺素','FT3游离三碘甲腺原氨酸','h-TSH促甲状腺激素','TGAB甲状腺球蛋白抗体','TMAB甲状腺微粒体抗体','隐血'],\ + 'test_check_list_all':['ABO正定型','ABO反定型','ABO血型',r'Rh\(D\)血型','TPO过氧化物酶自身抗体','T4甲状腺素','T3三碘甲腺原氨酸','FT4游离甲状腺素','FT3游离三碘甲腺原氨酸','h-TSH促甲状腺激素','TGAB甲状腺球蛋白抗体','TMAB甲状腺微粒体抗体','隐血'], 'test_result_col_name':"result_str"}, + # 免疫系列 # str(14):'促甲状腺素受体抗体测定 + {'test_rptunitid':[str(14)], 'test_check_name':'免疫系列', 'test_check_list':['甲状腺球蛋白','促甲状腺激素','血清甲状腺素','血清三碘甲状原氨酸','血清游离甲状腺素','血清游离三碘甲状原氨酸','抗甲状腺球蛋白抗体','抗甲状腺过氧化物酶抗体'],\ + 'test_check_list_all':['甲状腺球蛋白','促甲状腺激素','血清甲状腺素','血清三碘甲状原氨酸','血清游离甲状腺素','血清游离三碘甲状原氨酸','抗甲状腺球蛋白抗体','抗甲状腺过氧化物酶抗体'], 'test_result_col_name':"result_str"}, + # 特殊指标 # str(10):血管内皮生长因子检测；str(46): + {'test_rptunitid':[str(10)], 'test_check_name':'特殊指标', 'test_check_list':['血管内皮生长因子_血管内皮生长因子检测',r'Th1/Th2/Th17亚群十二项细胞因子_白介素\(IL\)检测\(IL-1β\)',r'白介素（IL）检测\(IL-2\)',r'白介素（IL）检测\(IL-4\)',r'白介素（IL）检测\(IL-5\)',r'白介素（IL）检测\(IL-6\)',r'白介素（IL）检测\(IL-8\)',r'白介素（IL）检测\(IL-10\)',r'白介素（IL）检测\(IL-12p\)',r'白介素（IL）检测\(IL-17\)',r'干扰素（IFN）测定\(IFN-α\)',r'干扰素（IFN）测定\(IFN-γ\)',r'肿瘤坏死因子测定'],\ + 'test_check_list_all':['血管内皮生长因子检测',r'白介素\(IL\)检测\(IL-1β\)',r'白介素（IL）检测\(IL-2\)',r'白介素（IL）检测\(IL-4\)',r'白介素（IL）检测\(IL-5\)',r'白介素（IL）检测\(IL-6\)',r'白介素（IL）检测\(IL-8\)',r'白介素（IL）检测\(IL-10\)',r'白介素（IL）检测\(IL-12p\)',r'白介素（IL）检测\(IL-17\)',r'干扰素（IFN）测定\(IFN-α\)',r'干扰素（IFN）测定\(IFN-γ\)',r'肿瘤坏死因子测定',], 'test_result_col_name':"result_str"}, + # 内分泌代谢系列 # str(12):尿β2-MG；str(7):尿液儿茶酚胺测定八项[复]；str(7):抗中性粒细胞胞浆抗体测定（ANC; + {'test_rptunitid':[str(12),str(7),str(17),str(161)], 'test_check_name':'内分泌代谢系列', 'test_check_list':['尿β2-MG','游离肾上腺素','游离去甲肾上腺素','游离多巴胺','游离甲氧基肾上腺素','游离甲氧基去甲肾上腺素','游离3-甲氧基酪胺','尿香草扁桃酸','高香草酸','24小时尿（体液）量','尿24小时游离肾上腺素','尿24小时游离去甲肾上腺素','尿24小时游离多巴胺','尿24小时游离甲氧基肾上腺素','尿24小时游离甲氧基去甲肾上腺素','尿24小时游离3-甲氧基酪胺','尿24小时香草扁桃酸','尿24小时高香草酸', 'cANCA','pANCA','抗蛋白酶3抗体','抗髓过氧化物酶抗体','ANA','非典型性ANCA','*MPO标准品1','*MPO标准品2','*MPO标准品3','*PR3标准品1','*PR3标准品2','*PR3标准品3'],\ + 'test_check_list_all':['尿β2-MG','游离肾上腺素','游离去甲肾上腺素','游离多巴胺','游离甲氧基肾上腺素','游离甲氧基去甲肾上腺素','游离3-甲氧基酪胺','尿香草扁桃酸','高香草酸','24小时尿（体液）量','尿24小时游离肾上腺素','尿24小时游离去甲肾上腺素','尿24小时游离多巴胺','尿24小时游离甲氧基肾上腺素','尿24小时游离甲氧基去甲肾上腺素','尿24小时游离3-甲氧基酪胺','尿24小时香草扁桃酸','尿24小时高香草酸','cANCA','pANCA','抗蛋白酶3抗体','抗髓过氧化物酶抗体','ANA','非典型性ANCA',r'\*MPO标准品1',r'\*MPO标准品2',r'\*MPO标准品3',r'\*PR3标准品1',r'\*PR3标准品2',r'\*PR3标准品3'], 'test_result_col_name':"result_str"}, + # 用药指导 # str(78):用药指导基因检测他汀类药物两项 + {'test_rptunitid':[str(78),str(40)], 'test_check_name':'用药指导', 'test_check_list':[r'VKORC1\(1639G>A\)',r'CYP2C9*3\(1075A>C\)',r'ALDH2\(1510G>A\)',r'ApoE\(526',r'SLCO1B1*5\(521'],\ + 'test_check_list_all':[r'VKORC1\(1639G>A\)',r'CYP2C9*3\(1075A>C\)',r'ALDH2\(1510G>A\)',r'ApoE\(526',r'SLCO1B1*5\(521'], 'test_result_col_name':"result_str"}, + ] + +# 生成基本存储信息文件 +# 如果有文件则将其删除 +if os.path.exists(result_save_pth): + os.remove(result_save_pth) +# 生成抬头信息 +front_content=[] # 抬头个人信息 +for front in Front_line: + front_content.append(front) +# 生成basic存储信息 +basic_content=[] # basic个人信息 +for basic in Basic_line: + basic_content.append(basic) +# 生成各个检测sheet：head+basic+items+[not_match] +for test in ALL_tests: # 各项检测信息 + # 生成未匹配检查内容 + if show_not_match == True: + add_content_to_excel(result_save_pth, test['test_check_name'], front_content + basic_content + test["test_check_list"] + ['未匹配检测内容']) + else: + add_content_to_excel(result_save_pth, test['test_check_name'], front_content + basic_content + test["test_check_list"]) + + +####### 获取所有患者头部信息（Front_line） ####### +front_line_data = [] +# 遍历所有患者（pat_no） +for row in reader_Patients_info: + data = {} + for item in Front_line: + if Front_line[item] == 'pat_no': + if data_type == "pat_no": + data[Front_line[item]] = f"{int(row['pat_no']):010}" + elif data_type == "zhuyuanhao": + data[Front_line[item]] = f"{row['pat_no']}" + else: + data[Front_line[item]] = row[Front_line[item]] + front_line_data.append(data) +# 将字典转换为元组，并放入集合中去重 +front_line_data = set(tuple(sorted(d.items())) for d in front_line_data) +# 将去重后的元组转换回字典，并放入新的列表 +front_line_data = [dict(t) for t in front_line_data] + +####### 获取所有患者检测信息（base_line，pat_no/pato_no.csv） ####### +# 遍历所有患者（pat_no） +for pat_no in pat_no_col: + # 信息头生成 + excel_head = [] + for d in front_line_data: + if d["pat_no"] == pat_no: + for item in Front_line: + excel_head.append(d[Front_line[item]]) + break + # 如果头文件为空 + if excel_head == []: + Error(str(pat_no)+"的excel_head为空") + exit() + print("__处理患者头为__:", excel_head) + # 遍历所有rptunitid + for test in ALL_tests: + # 特定检查rptunitid + test_rptunitid = test['test_rptunitid'] + if not isinstance(test_rptunitid, list) and not isinstance(test_rptunitid, tuple): + test_rptunitid = [test_rptunitid] + # 检查名 + test_check_name = test['test_check_name'] + # 检查项 + test_check_list_all = test['test_check_list_all'] + # 检查项_名 + test_check_list = test['test_check_list'] + if len(test_check_list_all) != len(test_check_list): + Error("test_check_list_all长度和test_check_list不同") + print(f"test_check_list_all:{test_check_list_all}\ntest_check_list:{test_check_list}") + exit() + # 检查结果所在列的列名 + test_result_col_name = test['test_result_col_name'] + # 存放检查结果的dict + test_check_result = {} + + print("获取患者 ", test_check_name, " 检查结果") + + ### 打开patno/pat_no.csv文件获取更详细信息 ### + with open(osp.join(patno_dir, pat_no+'.csv'), "r", encoding='utf-8-sig') as file: + reader = csv.DictReader(file) # 读取文件 + # 汇总特定检查行 + test_rptunitid_rows = [ row for row in reader if row['rptunitid'] in test_rptunitid ] + print("患者检查 ", test_check_name, "次数为", len(test_rptunitid_rows)) + + # 遍历所有特定检查行，提取关键信息 + rows_not_match = [] # 每一行内不匹配的内容 + for i in range(len(test_rptunitid_rows)): + print("处理患者第", i+1, "次检查") + row_1 = test_rptunitid_rows[i] + sampled_dt = row_1['sampled_dt'] # 获取时间信息 + ###### basic信息头生成 ###### + excel_basic = [] + for item in Basic_line: + excel_basic.append(row_1[Basic_line[item]]) + + ### 打开Patient_detail_infos/pat_no/文件 ###，获取特定检查文件存储路径 + if data_type == "zhuyuanhao": + row_file_path = os.path.join(Patient_detail_infos_dir, pat_no, 'None' + "_" + row_1['reporttype'] + "_" + row_1['rptunitid'] + "_" + row_1['reportid'].replace("_","-") + "_" + row_1['rechkdt'].replace(" ","-").replace(":","-").replace("_","-") +".csv") + elif data_type == "pat_no": + row_file_path = os.path.join(Patient_detail_infos_dir, pat_no, pat_no + "_" + row_1['reporttype'] + "_" + row_1['rptunitid'] + "_" + row_1['reportid'].replace("_","-") + "_" + row_1['rechkdt'].replace(" ","-").replace(":","-").replace("_","-") +".csv") + with open(row_file_path, "r") as row_file: + row_reader_ = csv.DictReader(row_file) # 读取文件，迭代器只能读取一次 + row_reader = [] + for r in row_reader_: + row_reader.append(r) + # 寻找所有检查项的值 + match = False # 检测内容中是否含有检测项目 + rows_not_match = [] # 每一行内不匹配的内容 + # 遍历所有行，查看对应检查结果 + for row_2 in row_reader: + row_test_name_exist = False + row_test_name = row_2['rpt_itemname'] + # 遍历所有待检查项 + for j in range(len(test_check_list_all)): + # 检查项名称 + test_result_name = test_check_list[j] + # 遍历所有完整版检查项目 + test_checks = test_check_list_all[j] + if isinstance(test_checks, str): + test_checks = [test_checks] + for test_check in test_checks: + # print(test_check, row_2['rpt_itemname'],"___") + if match_re(row_test_name, test_check):# test_check == row_test_name: # 检测项目属于其中 + match = True + row_test_name_exist = True + # temp临时存储变量，如果其为'.'，则结果变为'None' + temp = row_2[test_result_col_name] + if (temp == '.' or temp == '') : + temp = 'None' + test_check_result[test_result_name] = temp + break + # 如果结果中存在row_test_name_exist的话，退出循环 + if row_test_name_exist == True: + break + # 如果没有row_test_name_exist的话，将信息加入行信息中 + if row_test_name_exist == False: + rows_not_match.append(row_test_name) + + # 如果没有寻找到对应test_check_result的话，设置为Not_Find + for test_result_name in test_check_list: + if not test_result_name in test_check_result: + test_check_result[test_result_name] = 'Not_Find' + + # 如果没有检测到相匹配内容，且不输出所有信息，continue + if (match == False and show_all_infos == False): + continue + # 进行进一步操作 ing... + + + # 抽取结果格式转换 + excel_fromat_result = [] + for test_item in test['test_check_list']: + excel_fromat_result.append(test_check_result[test_item]) + # print("输出结果：", excel_fromat_result) + if show_not_match == True: + add_content_to_excel(result_save_pth, test['test_check_name'], excel_head + excel_basic + excel_fromat_result + rows_not_match) + else: + add_content_to_excel(result_save_pth, test['test_check_name'], excel_head + excel_basic + excel_fromat_result) + + # 每处理一个患者数据，保存相关信息 +save_excel() + + + + diff --git a/app/processors/V2-Every_Pat_File_convert_Lab_Test_data.py b/app/processors/V2-Every_Pat_File_convert_Lab_Test_data.py new file mode 100644 index 0000000..f56601d --- /dev/null +++ b/app/processors/V2-Every_Pat_File_convert_Lab_Test_data.py @@ -0,0 +1,325 @@ +#!/usr/bin/env python3 +# -*- coding: UTF-8 -*- +import csv, sys, os, copy, re, argparse +import os.path as osp +from openpyxl import Workbook, load_workbook +from V2_Data import Front_line, Basic_line, ALL_tests + +# 向特定excel的sheet中添加内容 +workbook = None # 全局变量，初始值为 None +file_path_g = None +def add_content_to_excel(file_path, sheet_name, content): + global workbook, file_path_g # 声明 workbook 为全局变量 + # 如果改换工作路径且workbook不为空 + if file_path_g != file_path and not (workbook is None): + # 保存工作簿 + workbook.save(file_path_g) + print("保存Excel工作表在：", file_path_g) + elif file_path_g != file_path: + try: + # 尝试加载现有的工作簿 + workbook = load_workbook(file_path) + except FileNotFoundError: + # 如果文件不存在，则创建一个新的工作簿 + workbook = Workbook() + file_path_g = file_path + + if sheet_name not in workbook.sheetnames: + # 如果工作表不存在，则创建一个新的工作表 + workbook.create_sheet(sheet_name) + + # 选择指定的工作表 + sheet = workbook[sheet_name] + + # 向工作表添加内容 + # 检查列表的第一个元素 + if isinstance(content, list) and content and isinstance(content[0], list): + # "二维列表" + for row in content: + sheet.append(row) + elif isinstance(content, list): + # "一维列表" + sheet.append(content) + elif isinstance(content, str): + # "字符串" + sheet.append([content]) + else: + print('add_content_to_excel输入参数为', content, '其不是列表、字符串') + +def save_excel(): + global workbook, file_path_g + if not (workbook is None): + # 保存工作簿 + print("Excel工作表保存在：", file_path_g) + workbook.save(file_path_g) + +# 判断字符串是否匹配正则表达式 +def match_re(string, pattern): + if re.match(pattern, string): + return True + else: + return False + +# 输出错误函数 +def Error(output_str="Error:", error_dir="Error.txt"): + # 打开 error.txt 文件并写入字符串 + with open(error_dir, "a+", encoding="utf-8-sig") as file: + # 将字符串输出到标准错误流 sys.stderr + file.write(output_str+'\n') + RED = '\033[91m' + RESET = '\033[0m' + print(RED+output_str+RESET) + +parser = argparse.ArgumentParser(description='数据处理脚本参数解析') +# 1. 数据文件夹所在路径 +parser.add_argument('--file_dir', type=str, required=True, help='数据文件夹所在路径') +# 2. 最终结果保存文件名 +parser.add_argument('--result_save_file_name', type=str, required=True, help='最终结果保存文件名') +# 3. 是否输出不匹配内容【True/False】 +parser.add_argument('--show_not_match', type=str, choices=['True', 'False'], required=True, help='是否输出不匹配内容') +# 4. 是否输出全部信息（包括全无项）【True/False】 +parser.add_argument('--show_all_infos', type=str, choices=['True', 'False'], required=True, help='是否输出全部信息（包括全无项）') +# 5. 患者数据类型【pat_no / zhuyuanhao】 +parser.add_argument('--data_type', type=str, choices=['pat_no', 'zhuyuanhao'], required=True, help='患者数据类型') +args = parser.parse_args() + +# 1.获取参数 +file_dir = args.file_dir +result_save_file_name = args.result_save_file_name +data_type = args.data_type +# 将布尔类型的字符串转换为布尔值 +show_not_match = args.show_not_match == 'True' +show_all_infos = args.show_all_infos == 'True' + +# 2.1. 打开Patients_info.csv文件，遍历出所有有效患者 + +Patients_info_pth = osp.join(file_dir, 'Patients_info.csv') +# 检查文件是否存在 +if not os.path.exists(Patients_info_pth): + print(f"{Patients_info_pth}不存在，请将 Patients_info.csv 移动到文件夹中") + sys.exit(1) # 退出程序 +with open(Patients_info_pth, "r", encoding="utf-8-sig") as file: + reader_ = csv.DictReader(file) + reader_Patients_info = [] + for r in reader_: + reader_Patients_info.append(r) + # 读取pat_no列数据 + if data_type == "pat_no": + pat_no_col = [f"{int(row['pat_no']):010}" for row in reader_Patients_info] + elif data_type == "zhuyuanhao": + pat_no_col = [f"{row['pat_no']}" for row in reader_Patients_info] + else: + print("数据类型需要为pat_no或zhuyuanhao") + pat_no_col = list(set(pat_no_col)) # 去除数组中重复内容 + +# 2.2. 获取所有患者头部信息（Front_line） +front_line_data = [] +# 遍历所有患者（pat_no） +for row in reader_Patients_info: + data = {} + for item in Front_line: + if Front_line[item] == 'pat_no': + if data_type == "pat_no": + data[Front_line[item]] = f"{int(row['pat_no']):010}" + elif data_type == "zhuyuanhao": + data[Front_line[item]] = f"{row['pat_no']}" + else: + data[Front_line[item]] = row[Front_line[item]] + front_line_data.append(data) +# 将字典转换为元组，并放入集合中去重 +front_line_data = set(tuple(sorted(d.items())) for d in front_line_data) +# 将去重后的元组转换回字典，并放入新的列表 +front_line_data = [dict(t) for t in front_line_data] + +# 3. 生成信息 +for pat_no in os.listdir(file_dir): # 遍历 file_dir 下的所有文件和文件夹 + + # 向特定excel的sheet中添加内容 + workbook = None # 全局变量，初始值为 None + file_path_g = None + + # 获取文件夹的完整路径 + pat_file_dir = os.path.join(file_dir, pat_no) # 获取完整路径 + result_save_pth = osp.join(pat_file_dir, pat_no+"_"+result_save_file_name+".xlsx") + + if os.path.isdir(pat_file_dir): # 判断是否是文件夹 + print(f"处理文件夹: {pat_file_dir}") + If_continue = False + # Tests_List目录的路径 + patno_pth = osp.join(pat_file_dir, pat_no+"_检测汇总.csv") + if not osp.exists(patno_pth): + Error(f"{pat_no+'_检测汇总.csv'} 在 {pat_no} 文件夹中不存在", error_dir=osp.join(pat_file_dir, f"{pat_no+'_检测汇总.csv'} 在文件夹中不存在.txt")) + If_continue = True + # Tests_List目录的路径 + Patient_detail_infos_dir = osp.join(pat_file_dir, pat_no+'_具体检测') + if not osp.exists(Patient_detail_infos_dir): + Error(f"{pat_no+'_具体检测'} 在 {pat_no} 文件夹中不存在", error_dir=osp.join(pat_file_dir, f"{pat_no+'_具体检测.csv'} 在文件夹中不存在.txt")) + If_continue = True + RED = '\033[91m' + RESET = '\033[0m' + if If_continue == True: + continue + else: + continue + + + + print("") + print(f"※当前住院号为：{pat_no}") + + # 删除Error文件 + error_dir=osp.join(pat_file_dir, "Error.txt") + if os.path.exists(error_dir): + os.remove(error_dir) + print("删除Error文件:", error_dir) + + # 生成基本存储信息文件 + # 如果有文件则将其删除 + if os.path.exists(result_save_pth): + os.remove(result_save_pth) + # 生成抬头信息 + front_content=[] # 抬头个人信息 + for front in Front_line: + front_content.append(front) + # 生成basic存储信息 + basic_content=[] # basic个人信息 + for basic in Basic_line: + basic_content.append(basic) + # 生成各个检测sheet：head+basic+items+[not_match] + for test in ALL_tests: # 各项检测信息 + # 生成未匹配检查内容 + if show_not_match == True: + add_content_to_excel(result_save_pth, test['test_check_name'], front_content + basic_content + test["test_check_list"] + ['未匹配检测内容']) + else: + add_content_to_excel(result_save_pth, test['test_check_name'], front_content + basic_content + test["test_check_list"]) + + # 信息头生成 + excel_head = [] + for d in front_line_data: + if d["pat_no"] == pat_no: + for item in Front_line: + excel_head.append(d[Front_line[item]]) + break + # 如果头文件为空 + if excel_head == []: + Error(str(pat_no)+"的excel_head为空", error_dir=osp.join(pat_file_dir, "Error.txt")) + exit() + + # 读取pat_no列数据 + if data_type == "pat_no": + pat_no = f"{int(pat_no):010}" + elif data_type == "zhuyuanhao": + pat_no = f"{pat_no}" + else: + print("数据类型需要为pat_no或zhuyuanhao") + + ####### 获取所有患者检测信息（base_line，pat_no/pato_no.csv） ####### + # 遍历所有患者（pat_no） + + # 遍历所有rptunitid + for test in ALL_tests: + # 特定检查rptunitid + test_rptunitid = test['test_rptunitid'] + if not isinstance(test_rptunitid, list) and not isinstance(test_rptunitid, tuple): + test_rptunitid = [test_rptunitid] + # 检查名 + test_check_name = test['test_check_name'] + # 检查项 + test_check_list_all = test['test_check_list_all'] + # 检查项_名 + test_check_list = test['test_check_list'] + if len(test_check_list_all) != len(test_check_list): + Error("test_check_list_all长度和test_check_list不同", error_dir=osp.join(pat_file_dir, "Error.txt")) + print(f"test_check_list_all:{test_check_list_all}\ntest_check_list:{test_check_list}") + exit() + # 检查结果所在列的列名 + test_result_col_name = test['test_result_col_name'] + # 存放检查结果的dict + test_check_result = {} + + print("获取患者 ", test_check_name, " 检查结果") + + ### 打开patno/pat_no.csv文件获取更详细信息 ### + with open(patno_pth, "r", encoding="utf-8-sig") as file: + reader = csv.DictReader(file) # 读取文件 + # 汇总特定检查行 + test_rptunitid_rows = [ row for row in reader if row['rptunitid'] in test_rptunitid ] + print("患者检查 ", test_check_name, "次数为", len(test_rptunitid_rows)) + + # 遍历所有特定检查行，提取关键信息 + rows_not_match = [] # 每一行内不匹配的内容 + for i in range(len(test_rptunitid_rows)): + print("处理患者第", i+1, "次检查") + row_1 = test_rptunitid_rows[i] + sampled_dt = row_1['sampled_dt'] # 获取时间信息 + ###### basic信息头生成 ###### + excel_basic = [] + for item in Basic_line: + excel_basic.append(row_1[Basic_line[item]]) + + ### 打开Patient_detail_infos/pat_no/文件 ###，获取特定检查文件存储路径 + if data_type == "zhuyuanhao": + row_file_path = os.path.join(Patient_detail_infos_dir, 'None' + "_" + row_1['reporttype'] + "_" + row_1['rptunitid'] + "_" + row_1['reportid'].replace("_","-") + "_" + row_1['rechkdt'].replace(" ","-").replace(":","-").replace("_","-") +".csv") + elif data_type == "pat_no": + row_file_path = os.path.join(Patient_detail_infos_dir, pat_no + "_" + row_1['reporttype'] + "_" + row_1['rptunitid'] + "_" + row_1['reportid'].replace("_","-") + "_" + row_1['rechkdt'].replace(" ","-").replace(":","-").replace("_","-") +".csv") + with open(row_file_path, "r", encoding="utf-8-sig") as row_file: + row_reader_ = csv.DictReader(row_file) # 读取文件，迭代器只能读取一次 + row_reader = [] + for r in row_reader_: + row_reader.append(r) + # 寻找所有检查项的值 + match = False # 检测内容中是否含有检测项目 + rows_not_match = [] # 每一行内不匹配的内容 + # 遍历所有行，查看对应检查结果 + for row_2 in row_reader: + row_test_name_exist = False + row_test_name = row_2['rpt_itemname'] + # 遍历所有待检查项 + for j in range(len(test_check_list_all)): + # 检查项名称 + test_result_name = test_check_list[j] + # 遍历所有完整版检查项目 + test_checks = test_check_list_all[j] + if isinstance(test_checks, str): + test_checks = [test_checks] + for test_check in test_checks: + # print(test_check, row_2['rpt_itemname'],"___") + if match_re(row_test_name, test_check):# test_check == row_test_name: # 检测项目属于其中 + match = True + row_test_name_exist = True + # temp临时存储变量，如果其为'.'，则结果变为'None' + temp = row_2[test_result_col_name] + if (temp == '.' or temp == '') : + temp = 'None' + test_check_result[test_result_name] = temp + break + # 如果结果中存在row_test_name_exist的话，退出循环 + if row_test_name_exist == True: + break + # 如果没有row_test_name_exist的话，将信息加入行信息中 + if row_test_name_exist == False: + rows_not_match.append(row_test_name) + + # 如果没有寻找到对应test_check_result的话，设置为Not_Find + for test_result_name in test_check_list: + if not test_result_name in test_check_result: + test_check_result[test_result_name] = 'Not_Find' + + # 如果没有检测到相匹配内容，且不输出所有信息，continue + if (match == False and show_all_infos == False): + continue + # 进行进一步操作 ing... + + + # 抽取结果格式转换 + excel_fromat_result = [] + for test_item in test['test_check_list']: + excel_fromat_result.append(test_check_result[test_item]) + # print("输出结果：", excel_fromat_result) + if show_not_match == True: + add_content_to_excel(result_save_pth, test['test_check_name'], excel_head + excel_basic + excel_fromat_result + rows_not_match) + else: + add_content_to_excel(result_save_pth, test['test_check_name'], excel_head + excel_basic + excel_fromat_result) + + # 每处理一个患者数据，保存相关信息 + save_excel() \ No newline at end of file diff --git a/app/processors/V2_Data.py b/app/processors/V2_Data.py new file mode 100644 index 0000000..7a9da95 --- /dev/null +++ b/app/processors/V2_Data.py @@ -0,0 +1,54 @@ +global Front_line +global Basic_line +global ALL_tests +# 3.遍历所有患者打开patno文件夹中的patno.csv +# 获取患者头部信息（提取于Patients_info.csv） +Front_line = {'姓名':'pat_name', '住院号':'pat_no'} +# 获取患者检测基本信息（提取于patno文件夹） +Basic_line = {'采样时间': 'sampled_dt', '检测原因':'req_reason'} +# 所有检测具体信息（提取于Patient_detail_infos文件夹） +# 一个检查包括：检测rptunitids、检查名(自主命名)、检查项、检查结果所在列、存放结果dict +#{'test_rptunitid':[str(X), str(X)], 'test_check_name':'XXX', 'test_check_list':["XXX", "XXX", ], 'test_check_list_all':["XXX", "XXX", ], 'test_result_col_name':"result_str"}, +ALL_tests = [# 血细胞 # (1):血细胞分析+五分类；(2):血细胞分析+五分类；(4):血细胞五分类+CRP；东院区：(106):血细胞分析+五分类 + {'test_rptunitid':[str(1), str(2), str(4), str(106)], 'test_check_name':'血细胞', 'test_check_list':["血红蛋白", "红细胞压积", "平均红细胞体积", "平均血红蛋白含量", "平均血红蛋白浓度", "红细胞宽度-CV值", "红细胞宽度-SD值", "血小板计数", "血小板分布宽度", "平均血小板体积", "大血小板比率", "血小板压积", "淋巴细胞计数", "单核细胞计数", "中性粒细胞计数", "嗜酸细胞计数", "嗜碱细胞计数", "淋巴细胞百分比", "单核细胞百分比", "中性粒细胞百分比", "嗜酸细胞百分比", "嗜碱细胞百分比", "白细胞计数", "红细胞计数", "CRP检验=====", "C反应蛋白", "超敏CRP", ], 'test_check_list_all':["血红蛋白", "红细胞压积", "平均红细胞体积", "平均血红蛋白含量", "平均血红蛋白浓度", "红细胞宽度-CV值", "红细胞宽度-SD值", "血小板计数", "血小板分布宽度", "平均血小板体积", "大血小板比率", "血小板压积", "淋巴细胞计数", "单核细胞计数", "中性粒细胞计数", "嗜酸细胞计数", "嗜碱细胞计数", "淋巴细胞百分比", "单核细胞百分比", "中性粒细胞百分比", "嗜酸细胞百分比", ["嗜碱细胞百分比", "嗜碱细胞%"], ["白细胞计数", "白细胞"], "红细胞计数", "CRP检验=====", "C反应蛋白", ["超敏CRP", "超敏C反应蛋白"], ], 'test_result_col_name':"result_str"}, + # 凝血 # (3):凝血六项；(110):东院区；(90):凝血和血小板功能监测 + {'test_rptunitid':[str(3), str(110),str(90)], 'test_check_name':'凝血', 'test_check_list':["凝血酶原时间", "凝血酶原活动度", "血浆凝血酶原时间比值", "凝血酶原国际标准化比值", "活化部分凝血活酶时间", "活化部分凝血活酶比值", "凝血酶时间", "凝血酶时间比值", "纤维蛋白原含量", "D-二聚体测定", "纤维蛋白原降解产物", "凝血酶生成时间","凝血速率","血小板功能"],\ + 'test_check_list_all':["凝血酶原时间*", ["凝血酶原活动度", r"凝血酶原活度\(%\)"], ["凝血酶原比值", "血浆凝血酶原时间比值"], ["凝血酶原标准化比值", "凝血酶原国际标准化比值"], ["活化部分凝血活酶时间*", "活化部分凝血酶时间*"], "活化部分凝血活酶比值", "凝血酶时间", "凝血酶时间比值", "纤维蛋白原含量", [r"D-二聚体\(sysmex\)", "D-二聚体测定*"], [r"纤维蛋白\(原\)降解产物", "纤维蛋白原降解产物"], "凝血酶生成时间","凝血速率","血小板功能"], 'test_result_col_name':"result_str"}, + # 肝功 # (5):平诊肝功十四项+平诊电解质八项+平诊肾功七项；(20)急诊肝功十二项_急诊肾功五项[复]_急诊电解质七项[复]；东院区：（108）：传染性指标检测八项 + {'test_rptunitid':[str(5), str(20), str(108)], 'test_check_name':'肝功', 'test_check_list':["谷草转氨酶", "谷丙转氨酶", "谷草/谷丙", "碱性磷酸酶", "γ谷氨酰氨转肽酶", "总胆红素", "直接胆红素", "间接胆红素", "胆碱脂酶", "总胆固醇", "总蛋白", "白蛋白", "球蛋白", "白球比", "总胆汁酸", "a-L-岩藻糖苷酶", "前白蛋白", "超氧化物歧化酶", "尿素", "肌酐", "胱抑素C", "葡萄糖", "尿酸", "钾", "钠", "氯", "磷", "钙", "镁", "二氧化碳结合率", "离子间隙", "糖化白蛋白", "视黄醇结合蛋白", "eGFR(CKD-EPI)", "a-l岩藻糖苷酶", "超氧化物歧化酶", "eGFR(MDRD)", r"eGFR单位ml/min/1.73m^2", "8597", "乳酸测定", "乳酸脱氢酶", "羟丁酸脱氢酶", "肌酸激酶", "肌酸激酶同工酶", "载脂蛋白A", "载脂蛋白B", "载脂蛋白E", "脂蛋白（a）", "缺血修饰白蛋白", "甘油三酯", "高密度脂蛋白", "低密度脂蛋白", ], \ + 'test_check_list_all':["谷草转氨酶", "谷丙转氨酶", "谷草/谷丙", "碱性磷酸酶", ["γ谷氨酰氨转肽酶", "γ-谷氨酰转肽酶"], "总胆红素", "直接胆红素", "间接胆红素", "胆碱脂酶", "总胆固醇", "总蛋白", "白蛋白", "球蛋白", "白球比", "总胆汁酸", "a-L-岩藻糖苷酶", "前白蛋白", "超氧化物歧化酶", "尿素", "肌酐", "胱抑素C", "葡萄糖", "尿酸", "钾", "钠", "氯", "磷", "钙", "镁", "二氧化碳结合率", "离子间隙", "糖化白蛋白", "视黄醇结合蛋白", r"eGFR\(CKD-EPI\)", "a-l岩藻糖苷酶", "超氧化物歧化酶", r"eGFR\(MDRD\)", r"eGFR单位ml/min/1.73m\^2", "8597", "乳酸测定", "乳酸脱氢酶", "羟丁酸脱氢酶", "肌酸激酶", "肌酸激酶同工酶", "载脂蛋白A", "载脂蛋白B", "载脂蛋白E", "脂蛋白（a）", "缺血修饰白蛋白", "甘油三酯", "高密度脂蛋白", "低密度脂蛋白", ], 'test_result_col_name':"result_str"}, + # 各类肿瘤标志物 # (6):各类肿瘤标志物，e.g.肿瘤标志物肺癌六项[复]、肿瘤标志物十项(男)；东院区：（108）：肿瘤标志物肺癌六项[复] + {'test_rptunitid':[str(6), str(108)], 'test_check_name':'各类肿瘤标志物', 'test_check_list':["胃泌素释放肽前体(罗氏)", "鳞状上皮细胞癌抗原(罗氏)", "癌胚抗原", "甲胎蛋白", "糖类抗原125", "糖类抗原199", "糖类抗原724", "细胞角蛋白19片段", "神经元特异性烯醇化酶测定", "总前列腺特异性抗原", "游离前列腺抗原", "游离/总", "糖类抗原153","人附睾蛋白","绝经前 ROMA","绝经后 ROMA","铁蛋白","叶酸","维生素B12","高尔基体蛋白73测定","胃蛋白酶原Ⅰ","胃蛋白酶原Ⅱ","胃蛋白酶原Ⅰ/Ⅱ","降钙素","甲状腺球蛋白"],\ + 'test_check_list_all':[r"胃泌素释放肽前体\(罗氏\)", ["鳞状上皮细胞癌相关抗原", r"鳞状上皮细胞癌抗原\(罗氏\)"], "癌胚抗原", "甲胎蛋白", "糖类抗原125", "糖类抗原199", "糖类抗原724", "细胞角蛋白19片段", "神经元特异性烯醇化酶测定", "总前列腺特异性抗原", "游离前列腺抗原", "游离/总", "糖类抗原153","人附睾蛋白","绝经前 ROMA","绝经后 ROMA","铁蛋白","叶酸","维生素B12","高尔基体蛋白73测定","胃蛋白酶原Ⅰ","胃蛋白酶原Ⅱ","胃蛋白酶原Ⅰ/Ⅱ","降钙素","甲状腺球蛋白"], 'test_result_col_name':"result_str"}, + # 七抗 # (10):肺癌七种自身抗体检测 + {'test_rptunitid':str(10), 'test_check_name':'七抗', 'test_check_list':["p53自身抗体", "PGP9.5自身抗体", "SOX2自身抗体", "GAGE7自身抗体", "GBU4-5自身抗体", "MAGE A1自身抗体", "CAGE自身抗体", ], 'test_check_list_all':["p53自身抗体", "PGP9.5自身抗体", "SOX2自身抗体", "GAGE7自身抗体", "GBU4-5自身抗体", "MAGE A1自身抗体", "CAGE自身抗体", ], 'test_result_col_name':"result_str"}, + # 传染指标 # (52):传染指标八项-急诊；(53):传染性指标检测八项[复];(23):传染性指标检测八项[复]；东院区:(108):传染性指标检测八项[复] + {'test_rptunitid':[str(52), str(53), str(108), str(23)], 'test_check_name':'传染指标', 'test_check_list':["乙肝表面抗原定量", "乙肝表面抗体定量", "乙肝e抗原", "乙肝e抗体", "乙肝核心抗体", "丙型肝炎抗体", "梅毒螺旋体抗体", "人类免疫缺陷病毒", ], 'test_check_list_all':["乙肝表面抗原定量", "乙肝表面抗体定量", "乙肝e抗原", "乙肝e抗体", "乙肝核心抗体", "丙型肝炎抗体", ["螺旋体特异抗体", "梅毒螺旋体抗体"], ["人免疫缺陷病毒", "人类免疫缺陷病毒"], ], 'test_result_col_name':"result_str"}, + # 血气分析+生化分析 # (16):血气分析+生化六项[复]/血气分析3, (49):血气分析+生化六项[复], (50):血气分析+生化五项[复], (73/74):血气分析+生化十项[复], (89):血气分析+生化六项[复], (112):血气分析/血气分析+生化七项[复], (158):血气分析+生化六项[复]；(42):血气分析+生化六项[复] + {'test_rptunitid':[str(16), str(49), str(50), str(73), str(74), str(89), str(112), str(158),str(42)], 'test_check_name':'血气分析+生化分析', 'test_check_list':["体温", "吸氧流量", "酸碱度", "氧分压", "二氧化碳分压", "二氧化碳总量", "红细胞压积", "总血红蛋白", "氧饱和度", "Na+钠离子浓度", "钾离子浓度", "钙离子浓度", "氯离子浓度", "标准离子钙", "氢离子浓度", "酸碱度计算值", "PCO2分压计算值", "p氧分压计算值", "pO2(A-a)(T)_r", "pO2(a/A)(T)_r", "呼吸指数计算值", "pO2(T)/FIO2_r", "氢离子浓度", "HCO3-act_r", "HCO3-std_r", "BE(ecf)_r", "血液缓冲碱", "ctCO2", "pO2(A-a)_r", "pO2(a/A)_r", "呼吸指数", "氧和指数", "阴离子间隙", "渗透压", "血糖", "乳酸", "实际碳酸氢盐", "标准碳酸氢盐", "实际碱剩余", "标准碱剩余", "细胞外液剩余碱","氧合血红蛋白","一氧化碳血红蛋白", "还原血红蛋白","高铁血红蛋白", "总胆红素", "A-aDO2", "pAO2", "paO2/pAO2", "50%饱和度氧分压", "动脉血氧含量", "肺泡动脉氧分压差", "动脉氧分压与肺泡氧分压之比", "pCO2(T)", "pO2(T)", "PH(T)", "吸氧浓度","平均肺泡氧分压"],\ + 'test_check_list_all':["体温", "吸氧流量", "酸碱度", "氧分压", "二氧化碳分压", "二氧化碳总量", "红细胞压积", "总血红蛋白", "氧饱和度", ["Na\+钠离子浓度", "钠离子"], ["钾离子浓度","钾离子"], ["钙离子浓度","钙离子"], ["氯离子浓度","氯离子"], ["标准离子钙","PH=7.4的钙"], "氢离子浓度", "酸碱度计算值", "PCO2分压计算值", "p氧分压计算值", r"pO2\(A-a\)\(T\)_r", r"pO2\(a/A\)\(T\)_r", "呼吸指数计算值", r"pO2\(T\)/FIO2_r", "氢离子浓度", "HCO3-act_r", "HCO3-std_r", r"BE\(ecf\)_r", "血液缓冲碱", "ctCO2", r"pO2\(A-a\)_r", r"pO2\(a/A\)_r", "呼吸指数", "氧和指数", "阴离子间隙", "渗透压", "血糖", "乳酸", ["实际碳酸氢盐","血浆碳酸氢盐浓度"], "标准碳酸氢盐", ["血液剩余碱","实际碱剩余"], "标准碱剩余", "细胞外液剩余碱","氧合血红蛋白","一氧化碳血红蛋白", "还原血红蛋白","高铁血红蛋白", "总胆红素", "A-aDO2", "pAO2", "paO2/pAO2", "50%饱和度氧分压", "动脉血氧含量", "肺泡动脉氧分压差", "动脉氧分压与肺泡氧分压之比", r"pCO2\(T\)", r"pO2\(T\)", r"PH\(T\)", "吸氧浓度","平均肺泡氧分压"], 'test_result_col_name':"result_str"}, + # 感染指标 # (77)/(92)/(113)/(126)/(77)/(82)/:新型冠状病毒核酸检测[复]； (75):新型冠状病毒抗体； (25):新冠核酸检测[复]/乙肝病毒DNA含量/结核杆菌定量测定；str(121)/str(37):一般细菌涂片检查；str(111):乙型肝炎DNA定量测定；str(29):免疫8项；str(34):内毒素+D葡聚糖测定，str(38)/(116):红细胞沉降率测定；str(36):结核Xpert鉴定及耐药[复]；str(10):结核感染T细胞检测；str(24):自身抗体谱测定(18项)；str(23):血清肌钙蛋白I测定 + {'test_rptunitid':[str(77),str(25),str(92),str(113),str(126),str(75),str(77),str(82),str(30),str(121),str(37),str(111),str(29),str(34),str(38),str(116),str(36),str(10)], 'test_check_name':'感染指标', 'test_check_list':["新型冠状病毒抗体IgG","新型冠状病毒抗体IgM", "新型冠状病毒核酸检测","新型冠状病毒核酸混检", "乙肝病毒DNA含量","结核杆菌定量测定", "EB病毒定量测定","巨细胞病毒定量测定","白细胞","上皮细胞","革兰氏阳性球菌","革兰氏阴性球菌","革兰氏阴性球杆菌","革兰氏阳性杆菌","革兰氏阴性杆菌","真菌菌丝" ,"真菌孢子","抗酸染色", "HPV6","HPV11","抗链球菌溶血素O定量测定","KAP轻链","LAM轻链","免疫球蛋白IgE","免疫球蛋白G","免疫球蛋白M","免疫球蛋白A","补体C3","补体C4","类风湿因子","C反应蛋白","G-脂多糖","1-3-β-D葡聚糖","抗心磷脂IgG抗体","EB病毒核心抗原IgG抗体","EB病毒衣壳抗原IgG抗体","EB病毒早期抗原IgM抗体","EB病毒衣壳抗原IgM抗体","红细胞沉降率测定","降钙素原",r"淋巴细胞培养+干扰素\(基础水平N\)",r"结核杆菌γ干扰素释放试验\(T-N\)",r"结核杆菌阳性对照反应\(M-N\)",r"结核杆菌特异性细胞免疫反应提示", "抗dsDNA抗体","抗核小体抗体","抗组蛋白抗体","抗SmD1抗体","抗PCNA抗体","抗核糖体P蛋白测定","抗SSA/Ro60kD抗体","抗SSA/Ro52kD抗体","抗ssb抗体","抗CENPB抗体","抗Scl-70抗体","抗U1-snRNP抗体","抗Jo-1抗体","抗PM-Scl抗体","抗Ku抗体","抗AMA-M2抗体","抗Mi-2抗体",r"抗核抗体\(1:80\)","高敏肌钙蛋白I" ],\ + 'test_check_list_all':["新型冠状病毒抗体IgG","新型冠状病毒抗体IgM",["新型冠状病毒核酸检测", "新型冠状病毒核酸快速检测"], r"新型冠状病毒核酸检测\(混检\)",["乙肝病毒DNA含量","乙型肝炎病毒DNA定量"],"结核杆菌定量测定", "EB病毒定量测定","巨细胞病毒定量测定","白细胞","上皮细胞",["革兰氏阳性球菌","革兰阳性球菌"],["革兰阴性球菌","革兰氏阴性球菌"],"革兰氏阴性球杆菌",["革兰阳性杆菌","革兰氏阳性杆菌"],["革兰阴性杆菌","革兰氏阴性杆菌"],"真菌菌丝","真菌孢子","抗酸染色","HPV6","HPV11","抗链球菌溶血素O定量测定","KAP轻链","LAM轻链","免疫球蛋白IgE","免疫球蛋白G","免疫球蛋白M","免疫球蛋白A","补体C3","补体C4","类风湿因子","C反应蛋白","G-脂多糖","1-3-β-D葡聚糖","抗心磷脂IgG抗体","EB病毒核心抗原IgG抗体","EB病毒衣壳抗原IgG抗体","EB病毒早期抗原IgM抗体","EB病毒衣壳抗原IgM抗体","红细胞沉降率测定","降钙素原",r"淋巴细胞培养+干扰素\(基础水平N\)",r"结核杆菌γ干扰素释放试验\(T-N\)",r"结核杆菌阳性对照反应\(M-N\)",r"结核杆菌特异性细胞免疫反应提示","抗dsDNA抗体","抗核小体抗体","抗组蛋白抗体","抗SmD1抗体","抗PCNA抗体","抗核糖体P蛋白测定","抗SSA/Ro60kD抗体","抗SSA/Ro52kD抗体","抗ssb抗体","抗CENPB抗体","抗Scl-70抗体","抗U1-snRNP抗体","抗Jo-1抗体","抗PM-Scl抗体","抗Ku抗体","抗AMA-M2抗体","抗Mi-2抗体",r"抗核抗体\(1:80\)","高敏肌钙蛋白I"], 'test_result_col_name':"result_str"}, + # 基因检测指标 # (41):CYP2C19基因检测[复] + {'test_rptunitid':[str(41)], 'test_check_name':'基因检测指标', 'test_check_list':[r"GG_681GG\)",r"GG_681GA\)",r"GA_681GG\)",r"GG_681AA\)",r"AA_681GG\)",r"GA_681GA\)" ],\ + 'test_check_list_all':[r"\*1/\*1\(636", r"\*1/\*2\(636",r"\*1/\*3\(636", r"\*2/\*2\(636",r"\*3/\*3\(636", r"\*2/\*3\(636", ], 'test_result_col_name':"result_ref"}, + # 心衰系列 # str(20):B型前脑尿钠肽, str(16):B型前脑尿钠肽检测（Pro-BN_降钙素原检；str(108):B型尿钠肽检测（BNP) + {'test_rptunitid':[str(20),str(16)], 'test_check_name':'心衰系列', 'test_check_list':['B型前脑尿钠肽','高敏肌钙蛋白T'],\ + 'test_check_list_all':['B型前脑尿钠肽','高敏肌钙蛋白T'], 'test_result_col_name':"result_str"}, + # 普通指标 # str(79),str(51):卡式血型鉴定；str(12):肝纤维化指标（五项）；str(22)/(33):胃液常规检查；str(161):甲功五项（化学发光法）[复] + {'test_rptunitid':[str(79),str(51),str(12),str(22),str(33),str(161)], 'test_check_name':'普通指标', 'test_check_list':['ABO正定型','ABO反定型','ABO血型',r'Rh\(D\)血型','TPO过氧化物酶自身抗体','T4甲状腺素','T3三碘甲腺原氨酸','FT4游离甲状腺素','FT3游离三碘甲腺原氨酸','h-TSH促甲状腺激素','TGAB甲状腺球蛋白抗体','TMAB甲状腺微粒体抗体','隐血'],\ + 'test_check_list_all':['ABO正定型','ABO反定型','ABO血型',r'Rh\(D\)血型','TPO过氧化物酶自身抗体','T4甲状腺素','T3三碘甲腺原氨酸','FT4游离甲状腺素','FT3游离三碘甲腺原氨酸','h-TSH促甲状腺激素','TGAB甲状腺球蛋白抗体','TMAB甲状腺微粒体抗体','隐血'], 'test_result_col_name':"result_str"}, + # 免疫系列 # str(14):'促甲状腺素受体抗体测定 + {'test_rptunitid':[str(14)], 'test_check_name':'免疫系列', 'test_check_list':['甲状腺球蛋白','促甲状腺激素','血清甲状腺素','血清三碘甲状原氨酸','血清游离甲状腺素','血清游离三碘甲状原氨酸','抗甲状腺球蛋白抗体','抗甲状腺过氧化物酶抗体'],\ + 'test_check_list_all':['甲状腺球蛋白','促甲状腺激素','血清甲状腺素','血清三碘甲状原氨酸','血清游离甲状腺素','血清游离三碘甲状原氨酸','抗甲状腺球蛋白抗体','抗甲状腺过氧化物酶抗体'], 'test_result_col_name':"result_str"}, + # 特殊指标 # str(10):血管内皮生长因子检测；str(46): + {'test_rptunitid':[str(10)], 'test_check_name':'特殊指标', 'test_check_list':['血管内皮生长因子_血管内皮生长因子检测',r'Th1/Th2/Th17亚群十二项细胞因子_白介素\(IL\)检测\(IL-1β\)',r'白介素（IL）检测\(IL-2\)',r'白介素（IL）检测\(IL-4\)',r'白介素（IL）检测\(IL-5\)',r'白介素（IL）检测\(IL-6\)',r'白介素（IL）检测\(IL-8\)',r'白介素（IL）检测\(IL-10\)',r'白介素（IL）检测\(IL-12p\)',r'白介素（IL）检测\(IL-17\)',r'干扰素（IFN）测定\(IFN-α\)',r'干扰素（IFN）测定\(IFN-γ\)',r'肿瘤坏死因子测定'],\ + 'test_check_list_all':['血管内皮生长因子检测',r'白介素\(IL\)检测\(IL-1β\)',r'白介素（IL）检测\(IL-2\)',r'白介素（IL）检测\(IL-4\)',r'白介素（IL）检测\(IL-5\)',r'白介素（IL）检测\(IL-6\)',r'白介素（IL）检测\(IL-8\)',r'白介素（IL）检测\(IL-10\)',r'白介素（IL）检测\(IL-12p\)',r'白介素（IL）检测\(IL-17\)',r'干扰素（IFN）测定\(IFN-α\)',r'干扰素（IFN）测定\(IFN-γ\)',r'肿瘤坏死因子测定',], 'test_result_col_name':"result_str"}, + # 内分泌代谢系列 # str(12):尿β2-MG；str(7):尿液儿茶酚胺测定八项[复]；str(7):抗中性粒细胞胞浆抗体测定（ANC; + {'test_rptunitid':[str(12),str(7),str(17),str(161)], 'test_check_name':'内分泌代谢系列', 'test_check_list':['尿β2-MG','游离肾上腺素','游离去甲肾上腺素','游离多巴胺','游离甲氧基肾上腺素','游离甲氧基去甲肾上腺素','游离3-甲氧基酪胺','尿香草扁桃酸','高香草酸','24小时尿（体液）量','尿24小时游离肾上腺素','尿24小时游离去甲肾上腺素','尿24小时游离多巴胺','尿24小时游离甲氧基肾上腺素','尿24小时游离甲氧基去甲肾上腺素','尿24小时游离3-甲氧基酪胺','尿24小时香草扁桃酸','尿24小时高香草酸', 'cANCA','pANCA','抗蛋白酶3抗体','抗髓过氧化物酶抗体','ANA','非典型性ANCA','*MPO标准品1','*MPO标准品2','*MPO标准品3','*PR3标准品1','*PR3标准品2','*PR3标准品3'],\ + 'test_check_list_all':['尿β2-MG','游离肾上腺素','游离去甲肾上腺素','游离多巴胺','游离甲氧基肾上腺素','游离甲氧基去甲肾上腺素','游离3-甲氧基酪胺','尿香草扁桃酸','高香草酸','24小时尿（体液）量','尿24小时游离肾上腺素','尿24小时游离去甲肾上腺素','尿24小时游离多巴胺','尿24小时游离甲氧基肾上腺素','尿24小时游离甲氧基去甲肾上腺素','尿24小时游离3-甲氧基酪胺','尿24小时香草扁桃酸','尿24小时高香草酸','cANCA','pANCA','抗蛋白酶3抗体','抗髓过氧化物酶抗体','ANA','非典型性ANCA',r'\*MPO标准品1',r'\*MPO标准品2',r'\*MPO标准品3',r'\*PR3标准品1',r'\*PR3标准品2',r'\*PR3标准品3'], 'test_result_col_name':"result_str"}, + # 用药指导 # str(78):用药指导基因检测他汀类药物两项 + {'test_rptunitid':[str(78),str(40)], 'test_check_name':'用药指导', 'test_check_list':[r'VKORC1\(1639G>A\)',r'CYP2C9*3\(1075A>C\)',r'ALDH2\(1510G>A\)',r'ApoE\(526',r'SLCO1B1*5\(521'],\ + 'test_check_list_all':[r'VKORC1\(1639G>A\)',r'CYP2C9*3\(1075A>C\)',r'ALDH2\(1510G>A\)',r'ApoE\(526',r'SLCO1B1*5\(521'], 'test_result_col_name':"result_str"}, + ] \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..c4895a2 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,5 @@ +fastapi==0.115.6 +uvicorn[standard]==0.34.0 +python-multipart==0.0.20 +openpyxl==3.1.5 +