Views
No views yet
| Feature | Description |
|---|---|
| age | Age |
| female | Gender (0=Male, 1=Female) |
| education_years | Years of education |
| married | Marital status (0=Unmarried, 1=Married) |
| has_diabetes | Diabetes |
| has_hypertension | Hypertension |
| has_heart_disease | Heart disease |
| has_stroke | Stroke history |
| has_lung_disease | Lung disease |
| adl_total | ADL limitation count (0-6) |
| iadl_total | IADL limitation count (0-6) |
| cognition_total | Cognitive score (0-21) |
| grip_strength | Grip strength (kg) |
| fall_history | Fall history |
| drink_now | Current drinking |
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained("your-username/geriatric-depression-llm")
4tokenizer = AutoTokenizer.from_pretrained("your-username/geriatric-depression-llm")
5
6system_prompt = "你是一位临床医生，请根据患者健康档案判断抑郁风险。回答必须以'该患者抑郁风险较高'或'该患者抑郁风险较低'开头。"
7profile = "年龄72岁，女性，独居，患有糖尿病和高血压，ADL受限2项，认知得分8/21，握力18kg，生活满意度2。"
8
9messages = [
10 {"role": "system", "content": system_prompt},
11 {"role": "user", "content": f"请评估以下患者的抑郁风险：\n\n{profile}"},
12]
13text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
14inputs = tokenizer(text, return_tensors="pt")
15outputs = model.generate(**inputs, max_new_tokens=400, do_sample=True, temperature=0.3)
16print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))[Paper title TBD]
[Authors TBD]