Upload 19 files

README.md

@@ -1,14 +1,21 @@
----
-title: Group056IntroToHealthInfo
-emoji: ⚡
-colorFrom: purple
-colorTo: pink
-sdk: gradio
-sdk_version: 5.49.1
-app_file: app.py
-pinned: false
-license: mit
-short_description: Transparent Health-Insurance Cost Chatbot
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## Prerequisites
+
+- Python 3.8 or higher
+- Install the required dependencies:
+
+```bash
+pip install -r requirements.txt
+```
+
+## How to Run
+
+1. Run the application:
+   ```bash
+   python thicc/app.py
+   ```
+
+3. Open the Gradio interface in your browser using the URL provided in the terminal (e.g., `http://127.0.0.1:7860`).
+
+## Sample Data
+
+The application uses a sample CSV file (`sample_data.csv`) located in the project directory. You can modify this file to include your own data.

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+pandas

thicc/ai_logic/intent_parser.py

@@ -0,0 +1,25 @@
+import pandas as pd
+
+# TODO: Use LLM to parse user intent.
+# For now adding simple rules
+def parse_intent(user_input: str, services_data: pd.DataFrame):
+    """
+    Parses the user's input to determine their intent.
+
+    Args:
+        user_input (str): The input string from the user.
+
+    Returns:
+        str: The identified intent of the user.
+    """
+    user_input = user_input.lower()
+    if "help" in user_input or "support" in user_input or "services" in user_input:
+        return "list_services"
+
+    res = services_data[
+        services_data["description"].apply(lambda desc: desc.lower() in user_input)
+    ]
+
+    if res.empty is False:
+        return res.iloc[0]["intent"]
+    return None

thicc/app.py

@@ -0,0 +1,65 @@
+import gradio as gr
+from ai_logic.intent_parser import parse_intent
+from data.data_loader import list_services, load_services_data, HOSPITALS
+from insurance import plans, cost_estimator
+
+# Dropdown so the user can choose their insurance plan
+plan_dropdown = gr.Dropdown(
+    choices=list(plans.SAMPLE_PLANS.keys()) + ["No Insurance"],
+    value="PPO",
+    label="Select plan",
+)
+
+hospital_dropdown = gr.Dropdown(
+    choices=HOSPITALS.keys(),
+    value=list(HOSPITALS.keys())[0],
+    label="Select a Hospital",
+)
+
+#  - plan_name is now a parameter
+def respond(message, history, plan_name: str, hospital_name: str) -> str:
+    hospital_data_path = HOSPITALS.get(hospital_name)
+    services_data = load_services_data(hospital_data_path)
+
+    requested_info = parse_intent(message, services_data)
+
+    if requested_info is None or requested_info == "list_services":
+        services_list = list_services(services_data)
+        return "Available services:\n" + "\n".join(services_list)
+
+    service_data = services_data[
+        services_data["intent"].str.contains(
+            requested_info,
+            case=False,
+            na=False,
+        )
+    ]
+    
+    if service_data.empty:
+        return "Sorry, no information found for your request."
+
+    service_description = service_data.iloc[0]["description"]
+    price = service_data.iloc[0]["negotiated_rate"]
+
+    # Map dropdown choice -> InsurancePlan object
+    if plan_name == "No Insurance":
+        plan = plans.NO_INSURANCE_PLAN
+    else:
+        plan = plans.SAMPLE_PLANS.get(plan_name, plans.NO_INSURANCE_PLAN)
+
+    cost = cost_estimator.estimate_cost(price, plan, deductible_met=True)
+
+    return f"The estimated cost for {service_description} under the {plan_name} plan is ${cost:.2f}."
+
+
+demo = gr.ChatInterface(
+    fn=respond,
+    title="THICC Cost Chatbot",
+    type="messages",
+    additional_inputs=[plan_dropdown, hospital_dropdown],
+    additional_inputs_accordion="Tells us about your insurance plan and hospital",
+)
+
+if __name__ == "__main__":
+    # share=True for Colab; locally use demo.launch()
+    demo.launch()

thicc/data/data_loader.py

@@ -0,0 +1,31 @@
+import pandas as pd
+from pathlib import Path
+
+# Directory of this file: .../thicc/data
+BASE_DIR = Path(__file__).resolve().parent
+
+HOSPITALS = {
+    "Mayo Clinic": BASE_DIR / "hospitals" / "mayo_clinic_data.csv",
+    "Cleveland Clinic": BASE_DIR / "hospitals" / "cleveland_clinic_data.csv",
+    "Johns Hopkins Hospital": BASE_DIR / "hospitals" / "johns_hopkins_hospital_data.csv",
+    "Massachusetts General Hospital": BASE_DIR / "hospitals" / "massachusetts_general_hospital_data.csv",
+    "UCLA Medical Center": BASE_DIR / "hospitals" / "ucla_medical_center_data.csv",
+    "Cedars-Sinai Medical Center": BASE_DIR / "hospitals" / "cedars_sinai_medical_center_data.csv",
+    "NewYork-Presbyterian Hospital": BASE_DIR / "hospitals" / "newyork_presbyterian_hospital_data.csv",
+    "Northwestern Memorial Hospital": BASE_DIR / "hospitals" / "northwestern_memorial_hospital_data.csv",
+    "UCSF Medical Center": BASE_DIR / "hospitals" / "ucsf_medical_center_data.csv",
+    "Houston Methodist Hospital": BASE_DIR / "hospitals" / "houston_methodist_hospital_data.csv",
+}
+
+def load_services_data(path) -> pd.DataFrame:
+    """Load price data from a CSV file."""
+    df = pd.read_csv(path)
+    return df[[
+        "intent",
+        "description",
+        "gross_charge",
+        "negotiated_rate",
+    ]]
+
+def list_services(services_data: pd.DataFrame) -> list[str]:
+    return services_data["description"].tolist()

thicc/data/hospitals/cedars_sinai_medical_center_data.csv

@@ -0,0 +1,8 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1300,1080
+"xray_information","X-Ray",2180,1780
+"general_consultation","General Consultation",1620,1320
+"neurosurgery_information","Neurosurgery",20000,17000
+"pain_management_information","Pain Management",2500,2000
+"endocrinology_information","Endocrinology",3700,3100
+"bariatric_surgery_information","Bariatric Surgery",15000,12000

thicc/data/hospitals/cleveland_clinic_data.csv

@@ -0,0 +1,6 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1320,1100
+"xray_information","X-Ray",2200,1800
+"general_consultation","General Consultation",1550,1250
+"cardiac_surgery_information","Cardiac Surgery",15000,12000
+"dialysis_information","Dialysis",4000,3200

thicc/data/hospitals/houston_methodist_hospital_data.csv

@@ -0,0 +1,8 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1310,1090
+"xray_information","X-Ray",2130,1730
+"general_consultation","General Consultation",1610,1310
+"transplant_surgery_information","Transplant Surgery",48000,40000
+"wound_care_information","Wound Care",1800,1400
+"hyperbaric_therapy_information","Hyperbaric Therapy",3500,3000
+"occupational_therapy_information","Occupational Therapy",2100,1700

thicc/data/hospitals/johns_hopkins_hospital_data.csv

@@ -0,0 +1,8 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1400,1150
+"xray_information","X-Ray",2050,1600
+"general_consultation","General Consultation",1700,1400
+"organ_transplant_information","Organ Transplant",50000,42000
+"pediatric_care_information","Pediatric Care",3000,2500
+"sleep_disorder_clinic_information","Sleep Disorder Clinic",2100,1700
+"infectious_disease_information","Infectious Disease",4200,3500

thicc/data/hospitals/massachusetts_general_hospital_data.csv

@@ -0,0 +1,8 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1280,1050
+"xray_information","X-Ray",2150,1750
+"general_consultation","General Consultation",1650,1350
+"fertility_treatment_information","Fertility Treatment",12000,10000
+"oncology_information","Oncology",8000,7000
+"burn_unit_information","Burn Unit",6000,5000
+"speech_therapy_information","Speech Therapy",1800,1400

thicc/data/hospitals/mayo_clinic_data.csv

@@ -0,0 +1,8 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1234,1000
+"xray_information","X-Ray",2100,1700
+"general_consultation","General Consultation",1600,1300
+"sleep_medicine_information","Sleep Medicine",2200,1800
+"rheumatology_information","Rheumatology",3500,2900
+"geriatrics_information","Geriatrics",2500,2000
+"nutrition_counseling_information","Nutrition Counseling",1200,900

thicc/data/hospitals/newyork_presbyterian_hospital_data.csv

@@ -0,0 +1,8 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1370,1130
+"xray_information","X-Ray",2120,1720
+"general_consultation","General Consultation",1680,1380
+"psychiatric_care_information","Psychiatric Care",4000,3500
+"rehabilitation_information","Rehabilitation",2200,1800
+"neonatal_care_information","Neonatal Care",5000,4200
+"speech_pathology_information","Speech Pathology",2100,1700

thicc/data/hospitals/northwestern_memorial_hospital_data.csv

@@ -0,0 +1,8 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1290,1060
+"xray_information","X-Ray",2170,1770
+"general_consultation","General Consultation",1630,1330
+"dermatology_information","Dermatology",1200,900
+"allergy_treatment_information","Allergy Treatment",1100,850
+"urology_information","Urology",2700,2200
+"pulmonology_information","Pulmonology",3500,2900

thicc/data/hospitals/ucla_medical_center_data.csv

@@ -0,0 +1,8 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1350,1120
+"xray_information","X-Ray",2250,1850
+"general_consultation","General Consultation",1580,1280
+"sports_medicine_information","Sports Medicine",3500,3000
+"plastic_surgery_information","Plastic Surgery",9000,7500
+"immunology_information","Immunology",3200,2700
+"gastroenterology_information","Gastroenterology",4100,3500

thicc/data/hospitals/ucsf_medical_center_data.csv

@@ -0,0 +1,8 @@
+intent,description,gross_charge,negotiated_rate
+"mri_information","MRI",1390,1160
+"xray_information","X-Ray",2190,1790
+"general_consultation","General Consultation",1690,1390
+"aids_hiv_care_information","AIDS/HIV Care",7000,6000
+"genetic_counseling_information","Genetic Counseling",2500,2000
+"transgender_health_information","Transgender Health",6000,5000
+"integrative_medicine_information","Integrative Medicine",3200,2700

thicc/insurance/cost_estimator.py

@@ -0,0 +1,13 @@
+from .plans import InsurancePlan
+
+def estimate_cost(price: float, plan: InsurancePlan | None = None, deductible_met: bool = False) -> float:
+    price = float(price)
+
+    if plan is None or getattr(plan, "plan_name", "") == "No Insurance":
+        return price  # No insurance, full price
+
+    if deductible_met:
+        # If deductible is met, only copay and coinsurance apply
+        return plan.copay or (price * plan.coinsurance)
+
+    return min(price, plan.deductible) + plan.copay

thicc/insurance/plans.py

@@ -0,0 +1,14 @@
+class InsurancePlan:
+    def __init__(self, plan_name, copay, deductible, coinsurance):
+        self.plan_name = plan_name
+        self.copay = copay
+        self.deductible = deductible
+        self.coinsurance = coinsurance
+
+SAMPLE_PLANS = {
+    "HMO": InsurancePlan("HMO", 25, 0, 0.0),
+    "PPO": InsurancePlan("PPO", 20, 500, 0.2),
+    "HDHP": InsurancePlan("HDHP", 20, 1500, 0.1),
+}
+
+NO_INSURANCE_PLAN = InsurancePlan("No Insurance", 0, 0, 1.0)