Extract Social Determinants of Health

The model is a powerful tool for extracting SDoH entities from clinical text.

It was specifically trained to identify the conditions in which people are born, grow, live, work, and age that impacts their health outcomes.

Use the provided Streamlit playground application to test this service.

<p><br/></p>

**Entity Recognition**: Initially, the model accurately identifies entities such as Access_To_Care, Age, Alcohol, Chidhood_Event, Communicable_Disease, Community_Safety, Diet, Disability, Eating_Disorder, Education, Employment, Environmental_Condition, Exercise, Family_Member, Financial_Status, Food_Insecurity, Gender, Geographic_Entity, Healthcare_Institution, Housing, Hyperlipidemia, Hypertension, Income, Insurance_Status, Language, Legal_Issues, Marital_Status, Mental_Health, and much more.

**Assertion Status Detection**: Subsequently, it assigns an assertion status to each identified entity (e.g. Present, Absent, Possible, Past, Hypotetical, Someone_Else)

**Relation Extraction Labels**: The final step involves the detection of relationships between the extracted entities, like access to care and financial status, income, social support, substance use and much more, financial status and housing, income, insurance status, mental health, quality of life and much more

(e.g. Access_To_Care-Financial_Status, Access_To_Care–Income, Access_To_Care-Social_Support, Access_To_Care-Substance_Use, Alcohol-Mental_Health, Alcohol-Quality_Of_Life, Alcohol–Smoking, Alcohol-Substance_Use, Alcohol-Violence_Or_Abuse, Childhood_Event-Violence_Or_Abuse, Community_Safety-Quality_Of_Life, Community_Safety-Violence_Or_Abuse, Diet-Eating_Disorder, Diet–Exercise, Diet–Gender, Diet–Obesity, Disability-Insurance_Status, Disability-Mental_Health, Disability-Quality_Of_Life, Disability-Social_Exclusion, Eating_Disorder-Food_Insecurity, Eating_Disorder-Mental_Health, Eating_Disorder–Obesity, Education–Employment, Education-Financial_Status, Education–Income, Education-Legal_Issues, Education-Quality_Of_Life, Education-Substance_Use, Employment-Financial_Status, Employment–Income, Employment-Insurance_Status, Employment-Quality_Of_Life, Environmental_Condition-Quality_Of_Life, Exercise-Mental_Health, Exercise–Obesity, Exercise-Quality_Of_Life, Exercise–Smoking, Exercise-Substance_Use, Financial_Status-Food_Insecurity, Financial_Status-Housing, Financial_Status-Income, Financial_Status-Insurance_Status, Financial_Status-Mental_Health, Financial_Status-Quality_Of_Life, Financial_Status-Social_Support, Food_Insecurity-Income, Food_Insecurity-Mental_Health, Food_Insecurity-Quality_Of_Life, Housing-Income, Housing-Insurance_Status, Housing-Quality_Of_Life, Income-Insurance_Status, Income-Quality_Of_Life, Language-Population_Group, Language-Race_Ethnicity, Language-Social_Exclusion, Legal_Issues-Race_Ethnicity, Legal_Issues-Substance_Use, Legal_Issues-Violence_Or_Abuse, Marital_Status-Mental_Health, Marital_Status-Violence_Or_Abuse, Mental_Health-Obesity, Mental_Health-Quality_Of_Life, Mental_Health-Smoking, Mental_Health-Social_Exclusion, Mental_Health-Social_Support, Mental_Health-Substance_Use, and much more)

<p><br/></p>

搜集汇总

背景与挑战

背景概述

该数据集包含一个专门训练的模型，用于从临床文本中提取健康社会决定因素（SDoH）实体，例如医疗可及性、年龄、就业等。模型功能包括识别这些实体、分配断言状态（如存在、缺失），并检测实体间的关系，如医疗可及性与财务状况之间的关联。