107 lines
5.6 KiB
Python
107 lines
5.6 KiB
Python
from typing import List, Dict, Any
|
||
import json
|
||
|
||
class ReportIntegrator:
|
||
"""医疗报告整合分析器"""
|
||
|
||
def __init__(self, llm_service):
|
||
self.llm_service = llm_service
|
||
|
||
def integrate_reports(self, reports: List[Dict[str, Any]]) -> Dict[str, Any]:
|
||
"""整合多份医疗报告"""
|
||
|
||
if len(reports) == 1:
|
||
return self._single_report_summary(reports[0])
|
||
|
||
# 构建整合分析的提示词
|
||
prompt = self._build_integration_prompt(reports)
|
||
|
||
# 调用LLM进行整合分析
|
||
if self.llm_service.llm_type == "openai":
|
||
result = self._call_openai_integration(prompt)
|
||
elif self.llm_service.llm_type == "ollama":
|
||
result = self._call_ollama_integration(prompt)
|
||
else:
|
||
result = self._mock_integration(reports)
|
||
|
||
# 添加报告列表
|
||
result["reports_included"] = [
|
||
{"filename": report["filename"], "summary": report["analysis"].get("summary", "无摘要")}
|
||
for report in reports
|
||
]
|
||
|
||
return result
|
||
|
||
def _build_integration_prompt(self, reports: List[Dict[str, Any]]) -> str:
|
||
"""构建整合分析提示词"""
|
||
report_details = []
|
||
for i, report in enumerate(reports, 1):
|
||
analysis = report["analysis"]
|
||
report_details.append(f"【报告{i}: {report['filename']}】\n摘要: {analysis.get('summary', '无')}")
|
||
|
||
prompt = f"""你是专业医疗分析专家。整合以下{len(reports)}份报告，提供综合评估。
|
||
{chr(10).join(report_details)}
|
||
|
||
请以JSON格式返回：
|
||
{{"overall_summary": "整体摘要", "health_trends": ["趋势"], "priority_concerns": [{{"concern": "关注点", "severity": "低/中/高", "description": "描述"}}], "comprehensive_assessment": "综合评估", "integrated_recommendations": ["建议"], "follow_up_suggestions": ["后续建议"]}}"""
|
||
return prompt
|
||
|
||
def _call_openai_integration(self, prompt: str) -> Dict[str, Any]:
|
||
"""调用OpenAI进行整合分析"""
|
||
try:
|
||
response = self.llm_service.client.chat.completions.create(
|
||
model=self.llm_service.model,
|
||
messages=[{"role": "system", "content": "你是医疗分析专家。"}, {"role": "user", "content": prompt}],
|
||
temperature=0.7, max_tokens=3000
|
||
)
|
||
content = response.choices[0].message.content
|
||
return self.llm_service._parse_llm_response(content)
|
||
except Exception as e:
|
||
return self._create_error_result(f"OpenAI分析失败: {str(e)}")
|
||
|
||
def _call_ollama_integration(self, prompt: str) -> Dict[str, Any]:
|
||
"""调用Ollama进行整合分析"""
|
||
try:
|
||
import requests
|
||
response = requests.post(f"{self.llm_service.ollama_host}/api/generate",
|
||
json={"model": self.llm_service.model, "prompt": prompt, "stream": False}, timeout=90)
|
||
if response.status_code == 200:
|
||
return self.llm_service._parse_llm_response(response.json().get("response", ""))
|
||
raise Exception(f"Ollama错误: {response.status_code}")
|
||
except Exception as e:
|
||
return self._create_error_result(f"Ollama分析失败: {str(e)}")
|
||
|
||
def _mock_integration(self, reports: List[Dict[str, Any]]) -> Dict[str, Any]:
|
||
"""模拟整合分析结果"""
|
||
total_abnormal = sum(len(report["analysis"].get("abnormal_items", [])) for report in reports)
|
||
return {
|
||
"overall_summary": f"综合分析了{len(reports)}份报告，发现{total_abnormal}项异常指标。整体健康状况良好。",
|
||
"health_trends": ["各项指标整体稳定", "未发现明显恶化趋势", "建议持续监测"],
|
||
"priority_concerns": [{"concern": "定期体检", "severity": "低", "description": "建议保持定期体检"}] if total_abnormal == 0 else [{"concern": "异常指标", "severity": "中", "description": f"发现{total_abnormal}项异常"}],
|
||
"comprehensive_assessment": "整体健康状况可控，建议关注生活方式、定期复查。",
|
||
"integrated_recommendations": ["保持均衡饮食", "坚持适量运动", "保证充足睡眠", "定期体检"],
|
||
"follow_up_suggestions": ["3-6个月后复查关键指标", "如有不适及时就医", "保持健康记录"],
|
||
"note": "这是模拟结果。实际使用请配置OpenAI或Ollama。"
|
||
}
|
||
|
||
def _single_report_summary(self, report: Dict[str, Any]) -> Dict[str, Any]:
|
||
"""单个报告摘要"""
|
||
analysis = report["analysis"]
|
||
return {
|
||
"overall_summary": f"单份报告分析：{analysis.get('summary', '无摘要')}",
|
||
"reports_included": [{"filename": report["filename"], "summary": analysis.get("summary", "无")}],
|
||
"health_trends": analysis.get("key_findings", []),
|
||
"priority_concerns": [{"concern": item, "severity": "中", "description": "需关注"} for item in analysis.get("abnormal_items", [])[:3]],
|
||
"comprehensive_assessment": analysis.get("risk_assessment", "请查看详细分析"),
|
||
"integrated_recommendations": analysis.get("recommendations", []),
|
||
"follow_up_suggestions": ["定期复查", "咨询医生"]
|
||
}
|
||
|
||
def _create_error_result(self, error_msg: str) -> Dict[str, Any]:
|
||
"""创建错误结果"""
|
||
return {
|
||
"error": error_msg, "overall_summary": "分析失败", "health_trends": [],
|
||
"priority_concerns": [], "comprehensive_assessment": "无法完成分析",
|
||
"integrated_recommendations": [], "follow_up_suggestions": []
|
||
}
|