Spaces:
Runtime error
Runtime error
cleaned up
Browse files- .gitignore +1 -1
- README.md +0 -2
- crew.py +58 -40
- crew.txt +0 -471
- firebaseLoader.py +52 -36
- modelAudiov7_ML.pk1 +0 -3
- modelLifestyleV2_ML.pk1 +0 -3
- webscraper.py +15 -3
.gitignore
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
hellothere
|
README.md
CHANGED
|
@@ -8,5 +8,3 @@ sdk_version: 5.49.1
|
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
-
|
| 12 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
|
|
|
|
|
crew.py
CHANGED
|
@@ -5,7 +5,7 @@ import joblib
|
|
| 5 |
import numpy as np
|
| 6 |
from crewai import Agent, Task, Crew, LLM
|
| 7 |
from crewai.tools import tool
|
| 8 |
-
from firebaseLoader import
|
| 9 |
from webscraper import *
|
| 10 |
from typing import Union
|
| 11 |
import shap
|
|
@@ -13,6 +13,7 @@ import xgboost as xgb
|
|
| 13 |
from xgboost import DMatrix
|
| 14 |
from math import exp
|
| 15 |
|
|
|
|
| 16 |
# ================================================================
|
| 17 |
# Loading in the prediction models
|
| 18 |
# ================================================================
|
|
@@ -48,7 +49,6 @@ llm_predict = LLM(model="huggingface/openai/gpt-oss-120b")
|
|
| 48 |
llm_news = LLM(model="huggingface/Qwen/Qwen3-4B-Thinking-2507")
|
| 49 |
|
| 50 |
|
| 51 |
-
|
| 52 |
# ================================================================
|
| 53 |
# Defining the tools for the agents to make use of
|
| 54 |
# ================================================================
|
|
@@ -132,7 +132,7 @@ def calculate_dementia_risk_audio(docID: str) -> Union[str, dict]:
|
|
| 132 |
error_msg = f"Error calculating audio-based risk: {str(e)}"
|
| 133 |
return {"status": "error", "message": error_msg}
|
| 134 |
|
| 135 |
-
#
|
| 136 |
@tool("explain_dementia_risk_audio")
|
| 137 |
def explain_dementia_risk_audio(docID: str) -> str:
|
| 138 |
"""Provides SHAP-based explanation for audio risk prediction."""
|
|
@@ -156,7 +156,8 @@ def explain_dementia_risk_audio(docID: str) -> str:
|
|
| 156 |
shap_vals = shap_values[0] # for class 1
|
| 157 |
top_indices = np.argsort(-shap_vals)[:5] # descending by impact
|
| 158 |
|
| 159 |
-
|
|
|
|
| 160 |
for i in top_indices:
|
| 161 |
feat = feature_names[i]
|
| 162 |
val = features[i]
|
|
@@ -168,6 +169,7 @@ def explain_dementia_risk_audio(docID: str) -> str:
|
|
| 168 |
|
| 169 |
return "\n".join(explanation_lines)
|
| 170 |
|
|
|
|
| 171 |
except Exception as e:
|
| 172 |
return f"SHAP explanation failed: {str(e)}"
|
| 173 |
|
|
@@ -190,11 +192,13 @@ def calculate_dementia_risk_lifestyle(docID: str) -> Union[str, dict]:
|
|
| 190 |
except json.JSONDecodeError:
|
| 191 |
pass
|
| 192 |
|
|
|
|
| 193 |
lifestyle_data = pull_lifestyle(docID)
|
| 194 |
if not lifestyle_data:
|
| 195 |
error = f"Error: No lifestyle data found for document ID '{docID}'"
|
| 196 |
return {"status": "error", "message": error}
|
| 197 |
|
|
|
|
| 198 |
FEATURE_MAPPING = {
|
| 199 |
'Age': 'age',
|
| 200 |
'Gender': 'gender',
|
|
@@ -247,10 +251,11 @@ def calculate_dementia_risk_lifestyle(docID: str) -> Union[str, dict]:
|
|
| 247 |
gender_val = lifestyle_data.get("gender")
|
| 248 |
age = lifestyle_data.get("age")
|
| 249 |
|
|
|
|
| 250 |
risk_level = "High" if prediction == 1 else "Low"
|
| 251 |
gender_str = "Male" if gender_val == 1 else "Female"
|
| 252 |
|
| 253 |
-
# Structured output
|
| 254 |
result_dict = {
|
| 255 |
"risk_level": risk_level,
|
| 256 |
"prediction": int(prediction),
|
|
@@ -262,6 +267,7 @@ def calculate_dementia_risk_lifestyle(docID: str) -> Union[str, dict]:
|
|
| 262 |
|
| 263 |
return {"status": "success", **result_dict}
|
| 264 |
|
|
|
|
| 265 |
except Exception as e:
|
| 266 |
error_msg = f"Error calculating risk: {str(e)}"
|
| 267 |
return {"status": "error", "message": error_msg}
|
|
@@ -270,10 +276,14 @@ def calculate_dementia_risk_lifestyle(docID: str) -> Union[str, dict]:
|
|
| 270 |
def explain_dementia_risk_lifestyle(docID: str) -> str:
|
| 271 |
"""Provides SHAP-based explanation for lifestyle risk prediction."""
|
| 272 |
try:
|
|
|
|
| 273 |
lifestyle_data = pull_lifestyle(docID)
|
|
|
|
|
|
|
| 274 |
if not lifestyle_data:
|
| 275 |
return f"Error: No lifestyle data for {docID}"
|
| 276 |
|
|
|
|
| 277 |
FEATURE_MAPPING = {
|
| 278 |
'Age': 'age', 'Gender': 'gender', 'Ethnicity': 'ethnicity',
|
| 279 |
'EducationLevel': 'education_level', 'BMI': 'bmi', 'Smoking': 'smoking',
|
|
@@ -291,11 +301,14 @@ def explain_dementia_risk_lifestyle(docID: str) -> str:
|
|
| 291 |
return f"Missing feature: {feat_name}"
|
| 292 |
features.append(val)
|
| 293 |
|
|
|
|
| 294 |
X_instance = np.array(features).reshape(1, -1)
|
| 295 |
-
shap_vals = lifestyle_explainer.shap_values(X_instance)[0] # class 1
|
| 296 |
|
| 297 |
-
|
|
|
|
|
|
|
| 298 |
|
|
|
|
| 299 |
explanation_lines = ["Top factors increasing dementia risk (lifestyle analysis):"]
|
| 300 |
for i in top_indices:
|
| 301 |
feat = lifestyle_feature_names[i]
|
|
@@ -319,6 +332,7 @@ def explain_dementia_risk_lifestyle(docID: str) -> str:
|
|
| 319 |
|
| 320 |
return "\n".join(explanation_lines)
|
| 321 |
|
|
|
|
| 322 |
except Exception as e:
|
| 323 |
return f"SHAP explanation failed: {str(e)}"
|
| 324 |
|
|
@@ -330,6 +344,7 @@ def gather_news_patient(count: int = 5) -> dict:
|
|
| 330 |
Returns a json object with the format: {"status": "success", "articles": [{"title", "summary", "url"}, ...]}.
|
| 331 |
"""
|
| 332 |
try:
|
|
|
|
| 333 |
raw_articles = get_patient_news_raw(count=count)
|
| 334 |
results = []
|
| 335 |
|
|
@@ -350,21 +365,25 @@ def gather_news_patient(count: int = 5) -> dict:
|
|
| 350 |
|
| 351 |
Article:
|
| 352 |
{full_text[:3000]}"""
|
| 353 |
-
|
|
|
|
| 354 |
response = llm_news.invoke(prompt)
|
| 355 |
summary = str(response).strip()
|
| 356 |
|
|
|
|
| 357 |
results.append({
|
| 358 |
"title": title,
|
| 359 |
"summary": summary,
|
| 360 |
"url": url
|
| 361 |
})
|
| 362 |
|
|
|
|
| 363 |
return {
|
| 364 |
"status": "success",
|
| 365 |
"articles": results
|
| 366 |
}
|
| 367 |
|
|
|
|
| 368 |
except Exception as e:
|
| 369 |
return {
|
| 370 |
"status": "error",
|
|
@@ -380,6 +399,7 @@ def gather_news_doctor(count: int = 5) -> dict:
|
|
| 380 |
Returns a json object with the format: {"status": "success", "articles": [{"title", "summary", "url"}, ...]}.
|
| 381 |
"""
|
| 382 |
try:
|
|
|
|
| 383 |
raw_articles = get_doctor_news_raw(count=count)
|
| 384 |
results = []
|
| 385 |
|
|
@@ -388,9 +408,11 @@ def gather_news_doctor(count: int = 5) -> dict:
|
|
| 388 |
title = item["title"]
|
| 389 |
full_text = scrape_full_text(url)
|
| 390 |
|
|
|
|
| 391 |
if not full_text.strip():
|
| 392 |
summary = "Summary unavailable."
|
| 393 |
else:
|
|
|
|
| 394 |
prompt = f"""You are a clinical expert.
|
| 395 |
Summarize the following article in 2–3 precise, evidence-based sentences for physicians.
|
| 396 |
Include: key findings, methods (if applicable), clinical relevance.
|
|
@@ -398,6 +420,7 @@ def gather_news_doctor(count: int = 5) -> dict:
|
|
| 398 |
Article:
|
| 399 |
{full_text[:3000]}"""
|
| 400 |
|
|
|
|
| 401 |
response = llm_news.invoke(prompt)
|
| 402 |
summary = str(response).strip()
|
| 403 |
|
|
@@ -407,11 +430,13 @@ def gather_news_doctor(count: int = 5) -> dict:
|
|
| 407 |
"url": url
|
| 408 |
})
|
| 409 |
|
|
|
|
| 410 |
return {
|
| 411 |
"status": "success",
|
| 412 |
"articles": results
|
| 413 |
}
|
| 414 |
|
|
|
|
| 415 |
except Exception as e:
|
| 416 |
return {
|
| 417 |
"status": "error",
|
|
@@ -456,31 +481,36 @@ doctor_news_agent = Agent(
|
|
| 456 |
verbose=True
|
| 457 |
)
|
| 458 |
|
|
|
|
|
|
|
| 459 |
# Define tasks for agents
|
|
|
|
|
|
|
|
|
|
| 460 |
risk_assessment_task_audio = Task(
|
| 461 |
description=f"Calculate dementia risk for patient",
|
| 462 |
expected_output="Risk level, confidence score, and plain-language explanation.",
|
| 463 |
agent=risk_calculator_audio,
|
| 464 |
)
|
| 465 |
-
|
| 466 |
explanation_task_audio = Task(
|
| 467 |
description="Explain the dementia risk prediction for patient using SHAP",
|
| 468 |
expected_output="Top 5 features increasing risk from audio analysis.",
|
| 469 |
agent=risk_calculator_audio
|
| 470 |
)
|
| 471 |
|
|
|
|
| 472 |
risk_assessment_task_lifestyle = Task(
|
| 473 |
description=f"Calculate dementia risk for patient using the given patient id: {placeholder_lifestyle_ID}",
|
| 474 |
expected_output="Risk level, confidence score, and plain-language explanation.",
|
| 475 |
agent=risk_calculator_lifestyle,
|
| 476 |
)
|
| 477 |
-
|
| 478 |
explanation_task_lifestyle = Task(
|
| 479 |
description=f"Explain the dementia risk prediction for patient {placeholder_lifestyle_ID} using SHAP",
|
| 480 |
expected_output="Top 5 features increasing risk, with impact direction and magnitude.",
|
| 481 |
agent=risk_calculator_lifestyle
|
| 482 |
)
|
| 483 |
|
|
|
|
| 484 |
get_news_task_patient = Task(
|
| 485 |
description=(
|
| 486 |
"Use the `gather_news_patient` tool to fetch {count} recent dementia/caregiving news articles "
|
|
@@ -491,7 +521,6 @@ get_news_task_patient = Task(
|
|
| 491 |
expected_output="A JSON object with 'status' and 'articles': list of {title, summary, url}.",
|
| 492 |
agent=patient_news_agent
|
| 493 |
)
|
| 494 |
-
|
| 495 |
get_news_task_doctor = Task(
|
| 496 |
description=(
|
| 497 |
"Use the `gather_news_doctor` tool to fetch {count} recent dementia research articles "
|
|
@@ -503,7 +532,7 @@ get_news_task_doctor = Task(
|
|
| 503 |
agent=doctor_news_agent
|
| 504 |
)
|
| 505 |
|
| 506 |
-
# Human-readable mapping for audio features
|
| 507 |
AUDIO_FEATURE_DESCRIPTIONS = {
|
| 508 |
# MFCC means (13 coefficients)
|
| 509 |
"mfcc_mean_0": "Overall speech energy (loudness stability)",
|
|
@@ -540,7 +569,12 @@ AUDIO_FEATURE_DESCRIPTIONS = {
|
|
| 540 |
"rms": "Root-mean-square energy — average speech loudness"
|
| 541 |
}
|
| 542 |
|
|
|
|
|
|
|
| 543 |
# Helper functions
|
|
|
|
|
|
|
|
|
|
| 544 |
def parse_shap_explanation(shap_text: str, is_lifestyle: bool = True) -> dict:
|
| 545 |
"""
|
| 546 |
Converts raw string SHAP explanation into structured JSON with human-readable feature names.
|
|
@@ -584,9 +618,9 @@ def parse_shap_explanation(shap_text: str, is_lifestyle: bool = True) -> dict:
|
|
| 584 |
if is_lifestyle:
|
| 585 |
feat_name_human = feat_name_raw
|
| 586 |
else:
|
| 587 |
-
# Audio: map mfcc_mean_1
|
| 588 |
feat_name_human = AUDIO_FEATURE_DESCRIPTIONS.get(feat_name_raw, feat_name_raw).split(" (")[0].split(" —")[0].split(" -")[0].strip()
|
| 589 |
-
# e.g., from "Voice pitch stability (fundamental frequency variation)"
|
| 590 |
|
| 591 |
features.append(feat_name_human)
|
| 592 |
|
|
@@ -623,32 +657,7 @@ def parse_shap_explanation(shap_text: str, is_lifestyle: bool = True) -> dict:
|
|
| 623 |
"explanations": explanations[:5]
|
| 624 |
}
|
| 625 |
|
| 626 |
-
|
| 627 |
-
"""Robustly extract JSON from LLM output (handles markdown/code blocks)."""
|
| 628 |
-
try:
|
| 629 |
-
# Try direct parse first
|
| 630 |
-
return json.loads(text)
|
| 631 |
-
except json.JSONDecodeError:
|
| 632 |
-
pass
|
| 633 |
-
|
| 634 |
-
# Try to extract JSON from code block
|
| 635 |
-
match = re.search(r"```(?:json)?\s*({.*})\s*```", text, re.DOTALL)
|
| 636 |
-
if match:
|
| 637 |
-
try:
|
| 638 |
-
return json.loads(match.group(1))
|
| 639 |
-
except:
|
| 640 |
-
pass
|
| 641 |
-
|
| 642 |
-
# Try to find first { ... } block
|
| 643 |
-
match = re.search(r"\{.*\}", text, re.DOTALL)
|
| 644 |
-
if match:
|
| 645 |
-
try:
|
| 646 |
-
return json.loads(match.group(0))
|
| 647 |
-
except:
|
| 648 |
-
pass
|
| 649 |
-
|
| 650 |
-
raise ValueError(f"Could not parse JSON from: {text[:200]}...")
|
| 651 |
-
|
| 652 |
def parse_json_from_markdown(s: str) -> dict:
|
| 653 |
"""
|
| 654 |
Extracts and parses JSON from a string that may be wrapped in ``` or ```json.
|
|
@@ -665,6 +674,12 @@ def parse_json_from_markdown(s: str) -> dict:
|
|
| 665 |
# Parse
|
| 666 |
return json.loads(json_str)
|
| 667 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 668 |
def run_crewai_lifestyle(docID: str) -> dict:
|
| 669 |
try:
|
| 670 |
lifestyle_data = pull_lifestyle(docID)
|
|
@@ -710,6 +725,7 @@ def run_crewai_lifestyle(docID: str) -> dict:
|
|
| 710 |
except Exception as e:
|
| 711 |
return {"status": "error", "message": str(e)}
|
| 712 |
|
|
|
|
| 713 |
def run_crewai_audio(docID: str) -> dict:
|
| 714 |
try:
|
| 715 |
audio_data = pull_audio(docID)
|
|
@@ -754,6 +770,7 @@ def run_crewai_audio(docID: str) -> dict:
|
|
| 754 |
except Exception as e:
|
| 755 |
return {"status": "error", "message": str(e)}
|
| 756 |
|
|
|
|
| 757 |
def run_crewai_news_patient(count: int = 5) -> dict:
|
| 758 |
crew = Crew(
|
| 759 |
agents=[patient_news_agent],
|
|
@@ -769,6 +786,7 @@ def run_crewai_news_patient(count: int = 5) -> dict:
|
|
| 769 |
except Exception as e:
|
| 770 |
return {"status": "error", "message": f"Failed to parse crew output, <{e}>", "raw": result}
|
| 771 |
|
|
|
|
| 772 |
def run_crewai_news_doctor(count: int = 5) -> dict:
|
| 773 |
crew = Crew(
|
| 774 |
agents=[doctor_news_agent],
|
|
|
|
| 5 |
import numpy as np
|
| 6 |
from crewai import Agent, Task, Crew, LLM
|
| 7 |
from crewai.tools import tool
|
| 8 |
+
from firebaseLoader import pull_audio, pull_lifestyle
|
| 9 |
from webscraper import *
|
| 10 |
from typing import Union
|
| 11 |
import shap
|
|
|
|
| 13 |
from xgboost import DMatrix
|
| 14 |
from math import exp
|
| 15 |
|
| 16 |
+
|
| 17 |
# ================================================================
|
| 18 |
# Loading in the prediction models
|
| 19 |
# ================================================================
|
|
|
|
| 49 |
llm_news = LLM(model="huggingface/Qwen/Qwen3-4B-Thinking-2507")
|
| 50 |
|
| 51 |
|
|
|
|
| 52 |
# ================================================================
|
| 53 |
# Defining the tools for the agents to make use of
|
| 54 |
# ================================================================
|
|
|
|
| 132 |
error_msg = f"Error calculating audio-based risk: {str(e)}"
|
| 133 |
return {"status": "error", "message": error_msg}
|
| 134 |
|
| 135 |
+
# SHAP explainer tool for audio prediction results
|
| 136 |
@tool("explain_dementia_risk_audio")
|
| 137 |
def explain_dementia_risk_audio(docID: str) -> str:
|
| 138 |
"""Provides SHAP-based explanation for audio risk prediction."""
|
|
|
|
| 156 |
shap_vals = shap_values[0] # for class 1
|
| 157 |
top_indices = np.argsort(-shap_vals)[:5] # descending by impact
|
| 158 |
|
| 159 |
+
# list of shap explanations
|
| 160 |
+
explanation_lines = ["Top factors increasing dementia risk (audio analysis):"]
|
| 161 |
for i in top_indices:
|
| 162 |
feat = feature_names[i]
|
| 163 |
val = features[i]
|
|
|
|
| 169 |
|
| 170 |
return "\n".join(explanation_lines)
|
| 171 |
|
| 172 |
+
# Error handling
|
| 173 |
except Exception as e:
|
| 174 |
return f"SHAP explanation failed: {str(e)}"
|
| 175 |
|
|
|
|
| 192 |
except json.JSONDecodeError:
|
| 193 |
pass
|
| 194 |
|
| 195 |
+
# Pulls data from firebase using the patientID (docID)
|
| 196 |
lifestyle_data = pull_lifestyle(docID)
|
| 197 |
if not lifestyle_data:
|
| 198 |
error = f"Error: No lifestyle data found for document ID '{docID}'"
|
| 199 |
return {"status": "error", "message": error}
|
| 200 |
|
| 201 |
+
# feature names in firebase dont match feature names in lifestyle model, so those names need to be changed
|
| 202 |
FEATURE_MAPPING = {
|
| 203 |
'Age': 'age',
|
| 204 |
'Gender': 'gender',
|
|
|
|
| 251 |
gender_val = lifestyle_data.get("gender")
|
| 252 |
age = lifestyle_data.get("age")
|
| 253 |
|
| 254 |
+
# Setting the risk level
|
| 255 |
risk_level = "High" if prediction == 1 else "Low"
|
| 256 |
gender_str = "Male" if gender_val == 1 else "Female"
|
| 257 |
|
| 258 |
+
# Structured output for easy parsing
|
| 259 |
result_dict = {
|
| 260 |
"risk_level": risk_level,
|
| 261 |
"prediction": int(prediction),
|
|
|
|
| 267 |
|
| 268 |
return {"status": "success", **result_dict}
|
| 269 |
|
| 270 |
+
# Handles failure to predict
|
| 271 |
except Exception as e:
|
| 272 |
error_msg = f"Error calculating risk: {str(e)}"
|
| 273 |
return {"status": "error", "message": error_msg}
|
|
|
|
| 276 |
def explain_dementia_risk_lifestyle(docID: str) -> str:
|
| 277 |
"""Provides SHAP-based explanation for lifestyle risk prediction."""
|
| 278 |
try:
|
| 279 |
+
# Pulls data from firebase using the patientID (docID)
|
| 280 |
lifestyle_data = pull_lifestyle(docID)
|
| 281 |
+
|
| 282 |
+
# Handles missing patient entry
|
| 283 |
if not lifestyle_data:
|
| 284 |
return f"Error: No lifestyle data for {docID}"
|
| 285 |
|
| 286 |
+
# Remapping the feature names to work with lifestyle model
|
| 287 |
FEATURE_MAPPING = {
|
| 288 |
'Age': 'age', 'Gender': 'gender', 'Ethnicity': 'ethnicity',
|
| 289 |
'EducationLevel': 'education_level', 'BMI': 'bmi', 'Smoking': 'smoking',
|
|
|
|
| 301 |
return f"Missing feature: {feat_name}"
|
| 302 |
features.append(val)
|
| 303 |
|
| 304 |
+
|
| 305 |
X_instance = np.array(features).reshape(1, -1)
|
|
|
|
| 306 |
|
| 307 |
+
# Get top 5 positive contributors (pushing toward Dementia = class 1)
|
| 308 |
+
shap_vals = lifestyle_explainer.shap_values(X_instance)[0]
|
| 309 |
+
top_indices = np.argsort(-shap_vals)[:5] # descending by impact to prediction result
|
| 310 |
|
| 311 |
+
# list of shap explanations
|
| 312 |
explanation_lines = ["Top factors increasing dementia risk (lifestyle analysis):"]
|
| 313 |
for i in top_indices:
|
| 314 |
feat = lifestyle_feature_names[i]
|
|
|
|
| 332 |
|
| 333 |
return "\n".join(explanation_lines)
|
| 334 |
|
| 335 |
+
# Error handling
|
| 336 |
except Exception as e:
|
| 337 |
return f"SHAP explanation failed: {str(e)}"
|
| 338 |
|
|
|
|
| 344 |
Returns a json object with the format: {"status": "success", "articles": [{"title", "summary", "url"}, ...]}.
|
| 345 |
"""
|
| 346 |
try:
|
| 347 |
+
# gets the article data from webscraper
|
| 348 |
raw_articles = get_patient_news_raw(count=count)
|
| 349 |
results = []
|
| 350 |
|
|
|
|
| 365 |
|
| 366 |
Article:
|
| 367 |
{full_text[:3000]}"""
|
| 368 |
+
|
| 369 |
+
# Gets the llm_news the create a summary
|
| 370 |
response = llm_news.invoke(prompt)
|
| 371 |
summary = str(response).strip()
|
| 372 |
|
| 373 |
+
|
| 374 |
results.append({
|
| 375 |
"title": title,
|
| 376 |
"summary": summary,
|
| 377 |
"url": url
|
| 378 |
})
|
| 379 |
|
| 380 |
+
# Structured output for easy parsing
|
| 381 |
return {
|
| 382 |
"status": "success",
|
| 383 |
"articles": results
|
| 384 |
}
|
| 385 |
|
| 386 |
+
# Error handling
|
| 387 |
except Exception as e:
|
| 388 |
return {
|
| 389 |
"status": "error",
|
|
|
|
| 399 |
Returns a json object with the format: {"status": "success", "articles": [{"title", "summary", "url"}, ...]}.
|
| 400 |
"""
|
| 401 |
try:
|
| 402 |
+
# gets the article data from webscraper
|
| 403 |
raw_articles = get_doctor_news_raw(count=count)
|
| 404 |
results = []
|
| 405 |
|
|
|
|
| 408 |
title = item["title"]
|
| 409 |
full_text = scrape_full_text(url)
|
| 410 |
|
| 411 |
+
# LM summarization happens using llm_news
|
| 412 |
if not full_text.strip():
|
| 413 |
summary = "Summary unavailable."
|
| 414 |
else:
|
| 415 |
+
# Use llm_news — ensure it's in scope
|
| 416 |
prompt = f"""You are a clinical expert.
|
| 417 |
Summarize the following article in 2–3 precise, evidence-based sentences for physicians.
|
| 418 |
Include: key findings, methods (if applicable), clinical relevance.
|
|
|
|
| 420 |
Article:
|
| 421 |
{full_text[:3000]}"""
|
| 422 |
|
| 423 |
+
# Gets the llm_news the create a summary
|
| 424 |
response = llm_news.invoke(prompt)
|
| 425 |
summary = str(response).strip()
|
| 426 |
|
|
|
|
| 430 |
"url": url
|
| 431 |
})
|
| 432 |
|
| 433 |
+
# Structured output for easy parsing
|
| 434 |
return {
|
| 435 |
"status": "success",
|
| 436 |
"articles": results
|
| 437 |
}
|
| 438 |
|
| 439 |
+
# Error handling
|
| 440 |
except Exception as e:
|
| 441 |
return {
|
| 442 |
"status": "error",
|
|
|
|
| 481 |
verbose=True
|
| 482 |
)
|
| 483 |
|
| 484 |
+
|
| 485 |
+
# ================================================================
|
| 486 |
# Define tasks for agents
|
| 487 |
+
# ================================================================
|
| 488 |
+
|
| 489 |
+
# Audio prediction
|
| 490 |
risk_assessment_task_audio = Task(
|
| 491 |
description=f"Calculate dementia risk for patient",
|
| 492 |
expected_output="Risk level, confidence score, and plain-language explanation.",
|
| 493 |
agent=risk_calculator_audio,
|
| 494 |
)
|
|
|
|
| 495 |
explanation_task_audio = Task(
|
| 496 |
description="Explain the dementia risk prediction for patient using SHAP",
|
| 497 |
expected_output="Top 5 features increasing risk from audio analysis.",
|
| 498 |
agent=risk_calculator_audio
|
| 499 |
)
|
| 500 |
|
| 501 |
+
# Lifestyle prediction
|
| 502 |
risk_assessment_task_lifestyle = Task(
|
| 503 |
description=f"Calculate dementia risk for patient using the given patient id: {placeholder_lifestyle_ID}",
|
| 504 |
expected_output="Risk level, confidence score, and plain-language explanation.",
|
| 505 |
agent=risk_calculator_lifestyle,
|
| 506 |
)
|
|
|
|
| 507 |
explanation_task_lifestyle = Task(
|
| 508 |
description=f"Explain the dementia risk prediction for patient {placeholder_lifestyle_ID} using SHAP",
|
| 509 |
expected_output="Top 5 features increasing risk, with impact direction and magnitude.",
|
| 510 |
agent=risk_calculator_lifestyle
|
| 511 |
)
|
| 512 |
|
| 513 |
+
# News gathering
|
| 514 |
get_news_task_patient = Task(
|
| 515 |
description=(
|
| 516 |
"Use the `gather_news_patient` tool to fetch {count} recent dementia/caregiving news articles "
|
|
|
|
| 521 |
expected_output="A JSON object with 'status' and 'articles': list of {title, summary, url}.",
|
| 522 |
agent=patient_news_agent
|
| 523 |
)
|
|
|
|
| 524 |
get_news_task_doctor = Task(
|
| 525 |
description=(
|
| 526 |
"Use the `gather_news_doctor` tool to fetch {count} recent dementia research articles "
|
|
|
|
| 532 |
agent=doctor_news_agent
|
| 533 |
)
|
| 534 |
|
| 535 |
+
# Human-readable mapping for audio features, as the names are not very understandable.
|
| 536 |
AUDIO_FEATURE_DESCRIPTIONS = {
|
| 537 |
# MFCC means (13 coefficients)
|
| 538 |
"mfcc_mean_0": "Overall speech energy (loudness stability)",
|
|
|
|
| 569 |
"rms": "Root-mean-square energy — average speech loudness"
|
| 570 |
}
|
| 571 |
|
| 572 |
+
|
| 573 |
+
# ================================================================
|
| 574 |
# Helper functions
|
| 575 |
+
# ================================================================
|
| 576 |
+
|
| 577 |
+
# Converts the raw explanations to something more understandable for patients/doctors
|
| 578 |
def parse_shap_explanation(shap_text: str, is_lifestyle: bool = True) -> dict:
|
| 579 |
"""
|
| 580 |
Converts raw string SHAP explanation into structured JSON with human-readable feature names.
|
|
|
|
| 618 |
if is_lifestyle:
|
| 619 |
feat_name_human = feat_name_raw
|
| 620 |
else:
|
| 621 |
+
# Audio: map mfcc_mean_1 to "Voice pitch stability", etc.
|
| 622 |
feat_name_human = AUDIO_FEATURE_DESCRIPTIONS.get(feat_name_raw, feat_name_raw).split(" (")[0].split(" —")[0].split(" -")[0].strip()
|
| 623 |
+
# e.g., from "Voice pitch stability (fundamental frequency variation)" to "Voice pitch stability"
|
| 624 |
|
| 625 |
features.append(feat_name_human)
|
| 626 |
|
|
|
|
| 657 |
"explanations": explanations[:5]
|
| 658 |
}
|
| 659 |
|
| 660 |
+
# Extract the json from the returned string that the llm gives, as the llm is stupid.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 661 |
def parse_json_from_markdown(s: str) -> dict:
|
| 662 |
"""
|
| 663 |
Extracts and parses JSON from a string that may be wrapped in ``` or ```json.
|
|
|
|
| 674 |
# Parse
|
| 675 |
return json.loads(json_str)
|
| 676 |
|
| 677 |
+
|
| 678 |
+
# ================================================================
|
| 679 |
+
# Crews
|
| 680 |
+
# ================================================================
|
| 681 |
+
|
| 682 |
+
# Lifestyle predicton crew
|
| 683 |
def run_crewai_lifestyle(docID: str) -> dict:
|
| 684 |
try:
|
| 685 |
lifestyle_data = pull_lifestyle(docID)
|
|
|
|
| 725 |
except Exception as e:
|
| 726 |
return {"status": "error", "message": str(e)}
|
| 727 |
|
| 728 |
+
# Audio prediction crew
|
| 729 |
def run_crewai_audio(docID: str) -> dict:
|
| 730 |
try:
|
| 731 |
audio_data = pull_audio(docID)
|
|
|
|
| 770 |
except Exception as e:
|
| 771 |
return {"status": "error", "message": str(e)}
|
| 772 |
|
| 773 |
+
# Patient news crew
|
| 774 |
def run_crewai_news_patient(count: int = 5) -> dict:
|
| 775 |
crew = Crew(
|
| 776 |
agents=[patient_news_agent],
|
|
|
|
| 786 |
except Exception as e:
|
| 787 |
return {"status": "error", "message": f"Failed to parse crew output, <{e}>", "raw": result}
|
| 788 |
|
| 789 |
+
# Doctor news crew
|
| 790 |
def run_crewai_news_doctor(count: int = 5) -> dict:
|
| 791 |
crew = Crew(
|
| 792 |
agents=[doctor_news_agent],
|
crew.txt
DELETED
|
@@ -1,471 +0,0 @@
|
|
| 1 |
-
import os
|
| 2 |
-
import re
|
| 3 |
-
import json
|
| 4 |
-
import joblib
|
| 5 |
-
import numpy as np
|
| 6 |
-
from crewai import Agent, Task, Crew, LLM
|
| 7 |
-
from crewai.tools import tool
|
| 8 |
-
from dataloaderImp import *
|
| 9 |
-
from typing import Union
|
| 10 |
-
import shap
|
| 11 |
-
import xgboost as xgb
|
| 12 |
-
from huggingface_hub import InferenceClient
|
| 13 |
-
|
| 14 |
-
# Load audio model & metadata
|
| 15 |
-
audio_model = xgb.Booster()
|
| 16 |
-
audio_model.load_model('modelAudiov8_ML.json')
|
| 17 |
-
|
| 18 |
-
metadata = joblib.load('modelAudiov8_metadata.pk1')
|
| 19 |
-
audio_feature_names = metadata['feature_names']
|
| 20 |
-
audio_mmse_index = metadata['mmse_index']
|
| 21 |
-
|
| 22 |
-
# Load lifestyle model & metadata
|
| 23 |
-
lifestyle_model = xgb.Booster()
|
| 24 |
-
lifestyle_model.load_model('modelLifestyleV3_ML.json')
|
| 25 |
-
|
| 26 |
-
metadata = joblib.load('modelLifestyleV3_metadata.pk1')
|
| 27 |
-
lifestyle_feature_names = metadata['feature_names']
|
| 28 |
-
|
| 29 |
-
# Load model explainers
|
| 30 |
-
audio_explainer = shap.TreeExplainer(audio_model)
|
| 31 |
-
lifestyle_explainer = shap.TreeExplainer(lifestyle_model)
|
| 32 |
-
|
| 33 |
-
placeholder_lifestyle_ID = "umWSG13rLSfHqqJlq1WluPzjLB93"
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
# Define tools for the agents
|
| 37 |
-
@tool("calculate_dementia_risk_audio")
|
| 38 |
-
def calculate_dementia_risk_audio(docID: str, return_json: bool = False) -> Union[str, dict]:
|
| 39 |
-
"""
|
| 40 |
-
Calculates dementia risk for a specific patient using audio and transcript data from Firebase.
|
| 41 |
-
If return_json=True, returns a structured dict. Otherwise, returns a formatted report string.
|
| 42 |
-
"""
|
| 43 |
-
try:
|
| 44 |
-
# Handle JSON-wrapped input (from CrewAI)
|
| 45 |
-
if docID.strip().startswith('{'):
|
| 46 |
-
try:
|
| 47 |
-
parsed = json.loads(docID)
|
| 48 |
-
if isinstance(parsed, dict):
|
| 49 |
-
if "Audio" in parsed and isinstance(parsed["Audio"], dict):
|
| 50 |
-
docID = parsed["Audio"].get("docID", docID)
|
| 51 |
-
elif "docID" in parsed:
|
| 52 |
-
docID = parsed["docID"]
|
| 53 |
-
except json.JSONDecodeError:
|
| 54 |
-
pass
|
| 55 |
-
|
| 56 |
-
audio_data = pull_audio(docID)
|
| 57 |
-
|
| 58 |
-
if audio_data is None:
|
| 59 |
-
error_msg = f"Error: Could not retrieve or process audio data for patient '{docID}'"
|
| 60 |
-
if return_json:
|
| 61 |
-
return {"status": "error", "message": error_msg}
|
| 62 |
-
return error_msg
|
| 63 |
-
|
| 64 |
-
# Extract values
|
| 65 |
-
age = audio_data.get("age")
|
| 66 |
-
gender_val = audio_data.get("gender")
|
| 67 |
-
mmse = audio_data.get("mmse") # Always None in current implementation
|
| 68 |
-
combined_features = audio_data.get("full_features")
|
| 69 |
-
|
| 70 |
-
if combined_features is None:
|
| 71 |
-
error_msg = f"Error: Feature extraction failed for patient '{docID}'"
|
| 72 |
-
if return_json:
|
| 73 |
-
return {"status": "error", "message": error_msg}
|
| 74 |
-
return error_msg
|
| 75 |
-
|
| 76 |
-
# Predict
|
| 77 |
-
prediction = audio_model.predict(combined_features.reshape(1, -1))[0]
|
| 78 |
-
probability = audio_model.predict_proba(combined_features.reshape(1, -1))[0]
|
| 79 |
-
confidence = float(max(probability))
|
| 80 |
-
risk_level = "High" if prediction == 1 else "Low"
|
| 81 |
-
gender_str = "Male" if gender_val == 1 else "Female"
|
| 82 |
-
|
| 83 |
-
# Structured output
|
| 84 |
-
result_dict = {
|
| 85 |
-
"risk_level": risk_level,
|
| 86 |
-
"prediction": int(prediction),
|
| 87 |
-
"confidence": confidence,
|
| 88 |
-
"age": age,
|
| 89 |
-
"gender": gender_str,
|
| 90 |
-
"docID": docID
|
| 91 |
-
}
|
| 92 |
-
|
| 93 |
-
if return_json:
|
| 94 |
-
return {"status": "success", **result_dict}
|
| 95 |
-
|
| 96 |
-
# Fallback: formatted string report (for CrewAI agents)
|
| 97 |
-
explanation = (
|
| 98 |
-
f"Based on speech analysis and linguistic patterns, "
|
| 99 |
-
f"the AI model detected {'concerning patterns' if prediction == 1 else 'normal patterns'} "
|
| 100 |
-
f"in speech fluency, vocabulary diversity, and cognitive response time."
|
| 101 |
-
)
|
| 102 |
-
|
| 103 |
-
mmse_note = "\n[Note: MMSE score not provided. Assessment based on speech and demographics only. Accuracy may be reduced.]"
|
| 104 |
-
|
| 105 |
-
report = f"""
|
| 106 |
-
DEMENTIA RISK ASSESSMENT (AUDIO)
|
| 107 |
-
================================
|
| 108 |
-
Risk Level: {risk_level}
|
| 109 |
-
Confidence: {confidence:.2%}
|
| 110 |
-
Prediction: {'Positive' if prediction == 1 else 'Negative'}
|
| 111 |
-
Age: {age}
|
| 112 |
-
Gender: {gender_str}
|
| 113 |
-
{mmse_note}
|
| 114 |
-
|
| 115 |
-
EXPLANATION:
|
| 116 |
-
{explanation}
|
| 117 |
-
"""
|
| 118 |
-
return report
|
| 119 |
-
|
| 120 |
-
except Exception as e:
|
| 121 |
-
error_msg = f"Error calculating audio-based risk: {str(e)}"
|
| 122 |
-
if return_json:
|
| 123 |
-
return {"status": "error", "message": error_msg}
|
| 124 |
-
return error_msg
|
| 125 |
-
|
| 126 |
-
@tool("explain_dementia_risk_audio")
|
| 127 |
-
def explain_dementia_risk_audio(docID: str) -> str:
|
| 128 |
-
"""Provides SHAP-based explanation for audio risk prediction."""
|
| 129 |
-
try:
|
| 130 |
-
# Reuse feature extraction logic (DRY: refactor if needed later)
|
| 131 |
-
audio_data = pull_audio(docID)
|
| 132 |
-
if audio_data is None:
|
| 133 |
-
return f"Error: No data for {docID}"
|
| 134 |
-
|
| 135 |
-
features = audio_data["full_features"]
|
| 136 |
-
feature_names = audio_feature_names
|
| 137 |
-
|
| 138 |
-
# SHAP values for this instance
|
| 139 |
-
shap_values = audio_explainer.shap_values(features.reshape(1, -1))
|
| 140 |
-
# shap_values is array of shape (1, n_features) for class 1 (Dementia)
|
| 141 |
-
|
| 142 |
-
# Get top 5 positive contributors (pushing toward Dementia = class 1)
|
| 143 |
-
shap_vals = shap_values[0] # for class 1
|
| 144 |
-
top_indices = np.argsort(-shap_vals)[:5] # descending by impact
|
| 145 |
-
|
| 146 |
-
explanation_lines = ["🔍 Top factors increasing dementia risk (audio analysis):"]
|
| 147 |
-
for i in top_indices:
|
| 148 |
-
feat = feature_names[i]
|
| 149 |
-
val = features[i]
|
| 150 |
-
impact = shap_vals[i]
|
| 151 |
-
if abs(impact) < 1e-4:
|
| 152 |
-
continue
|
| 153 |
-
direction = "↑" if impact > 0 else "↓"
|
| 154 |
-
explanation_lines.append(f" • {feat} = {val:.3f} → {direction} risk ({impact:+.3f})")
|
| 155 |
-
|
| 156 |
-
return "\n".join(explanation_lines)
|
| 157 |
-
|
| 158 |
-
except Exception as e:
|
| 159 |
-
return f"SHAP explanation failed: {str(e)}"
|
| 160 |
-
|
| 161 |
-
@tool("calculate_dementia_risk_lifestyle")
|
| 162 |
-
def calculate_dementia_risk_lifestyle(docID: str, return_json: bool = False) -> Union[str, dict]:
|
| 163 |
-
"""
|
| 164 |
-
Calculates dementia risk for a specific patient using lifestyle data.
|
| 165 |
-
If return_json=True, returns a structured dict. Otherwise, returns a formatted report string.
|
| 166 |
-
"""
|
| 167 |
-
try:
|
| 168 |
-
# Handle JSON-wrapped input (from CrewAI)
|
| 169 |
-
if docID.strip().startswith('{'):
|
| 170 |
-
try:
|
| 171 |
-
parsed = json.loads(docID)
|
| 172 |
-
if isinstance(parsed, dict):
|
| 173 |
-
if "Lifestyle" in parsed and isinstance(parsed["Lifestyle"], dict):
|
| 174 |
-
docID = parsed["Lifestyle"].get("docID", docID)
|
| 175 |
-
elif "docID" in parsed:
|
| 176 |
-
docID = parsed["docID"]
|
| 177 |
-
except json.JSONDecodeError:
|
| 178 |
-
pass
|
| 179 |
-
|
| 180 |
-
lifestyle_data = pull_lifestyle(docID)
|
| 181 |
-
if not lifestyle_data:
|
| 182 |
-
error = f"Error: No lifestyle data found for document ID '{docID}'"
|
| 183 |
-
if return_json:
|
| 184 |
-
return {"status": "error", "message": error}
|
| 185 |
-
return error
|
| 186 |
-
|
| 187 |
-
FEATURE_MAPPING = {
|
| 188 |
-
'Age': 'age',
|
| 189 |
-
'Gender': 'gender',
|
| 190 |
-
'Ethnicity': 'ethnicity',
|
| 191 |
-
'EducationLevel': 'education_level',
|
| 192 |
-
'BMI': 'bmi',
|
| 193 |
-
'Smoking': 'smoking',
|
| 194 |
-
'AlcoholConsumption': 'alcohol_consumption',
|
| 195 |
-
'PhysicalActivity': 'physical_activity',
|
| 196 |
-
'DietQuality': 'diet_quality',
|
| 197 |
-
'SleepQuality': 'sleep_quality',
|
| 198 |
-
'FamilyHistoryAlzheimers': 'family_history_dementia',
|
| 199 |
-
'CardiovascularDisease': 'cardiovascular_disease',
|
| 200 |
-
'Diabetes': 'diabetes',
|
| 201 |
-
'Depression': 'depression',
|
| 202 |
-
'HeadInjury': 'head_injury',
|
| 203 |
-
'Hypertension': 'hypertension'
|
| 204 |
-
}
|
| 205 |
-
|
| 206 |
-
features = []
|
| 207 |
-
for feat_name in lifestyle_feature_names:
|
| 208 |
-
firestore_key = FEATURE_MAPPING.get(feat_name)
|
| 209 |
-
if firestore_key is None:
|
| 210 |
-
error = f"Error: No mapping defined for feature '{feat_name}'"
|
| 211 |
-
if return_json:
|
| 212 |
-
return {"status": "error", "message": error}
|
| 213 |
-
return error
|
| 214 |
-
val = lifestyle_data.get(firestore_key)
|
| 215 |
-
if val is None:
|
| 216 |
-
error = f"Error: Missing required lifestyle feature '{feat_name}' (Firestore key: '{firestore_key}')"
|
| 217 |
-
if return_json:
|
| 218 |
-
return {"status": "error", "message": error}
|
| 219 |
-
return error
|
| 220 |
-
features.append(val)
|
| 221 |
-
|
| 222 |
-
life = np.array(features).reshape(1, -1)
|
| 223 |
-
age = lifestyle_data.get("age")
|
| 224 |
-
gender_val = lifestyle_data.get("gender")
|
| 225 |
-
|
| 226 |
-
prediction = lifestyle_model.predict(life)[0]
|
| 227 |
-
probability = lifestyle_model.predict_proba(life)[0]
|
| 228 |
-
confidence = float(max(probability))
|
| 229 |
-
risk_level = "High" if prediction == 1 else "Low"
|
| 230 |
-
gender_str = "Male" if gender_val == 1 else "Female"
|
| 231 |
-
|
| 232 |
-
# Structured output
|
| 233 |
-
result_dict = {
|
| 234 |
-
"risk_level": risk_level,
|
| 235 |
-
"prediction": int(prediction),
|
| 236 |
-
"confidence": confidence,
|
| 237 |
-
"age": age,
|
| 238 |
-
"gender": gender_str,
|
| 239 |
-
"docID": docID
|
| 240 |
-
}
|
| 241 |
-
|
| 242 |
-
if return_json:
|
| 243 |
-
return result_dict
|
| 244 |
-
|
| 245 |
-
# Original string report
|
| 246 |
-
explanation = (
|
| 247 |
-
f"Based on lifestyle factors including diet, physical activity, and medical history, "
|
| 248 |
-
f"the AI model detected {'concerning patterns' if prediction == 1 else 'normal patterns'} "
|
| 249 |
-
f"associated with increased dementia risk."
|
| 250 |
-
)
|
| 251 |
-
|
| 252 |
-
report = f"""
|
| 253 |
-
DEMENTIA RISK ASSESSMENT (LIFESTYLE)
|
| 254 |
-
===================================
|
| 255 |
-
Risk Level: {risk_level}
|
| 256 |
-
Confidence: {confidence:.2%}
|
| 257 |
-
Prediction: {'Positive' if prediction == 1 else 'Negative'}
|
| 258 |
-
Age: {age}
|
| 259 |
-
Gender: {gender_str}
|
| 260 |
-
|
| 261 |
-
EXPLANATION:
|
| 262 |
-
{explanation}
|
| 263 |
-
"""
|
| 264 |
-
return report
|
| 265 |
-
|
| 266 |
-
except Exception as e:
|
| 267 |
-
error_msg = f"Error calculating risk: {str(e)}"
|
| 268 |
-
if return_json:
|
| 269 |
-
return {"status": "error", "message": error_msg}
|
| 270 |
-
return error_msg
|
| 271 |
-
|
| 272 |
-
@tool("explain_dementia_risk_lifestyle")
|
| 273 |
-
def explain_dementia_risk_lifestyle(docID: str) -> str:
|
| 274 |
-
"""Provides SHAP-based explanation for lifestyle risk prediction."""
|
| 275 |
-
try:
|
| 276 |
-
lifestyle_data = pull_lifestyle(docID)
|
| 277 |
-
if not lifestyle_data:
|
| 278 |
-
return f"Error: No lifestyle data for {docID}"
|
| 279 |
-
|
| 280 |
-
FEATURE_MAPPING = {
|
| 281 |
-
'Age': 'age', 'Gender': 'gender', 'Ethnicity': 'ethnicity',
|
| 282 |
-
'EducationLevel': 'education_level', 'BMI': 'bmi', 'Smoking': 'smoking',
|
| 283 |
-
'AlcoholConsumption': 'alcohol_consumption', 'PhysicalActivity': 'physical_activity',
|
| 284 |
-
'DietQuality': 'diet_quality', 'SleepQuality': 'sleep_quality',
|
| 285 |
-
'FamilyHistoryAlzheimers': 'family_history_dementia',
|
| 286 |
-
'CardiovascularDisease': 'cardiovascular_disease', 'Diabetes': 'diabetes',
|
| 287 |
-
'Depression': 'depression', 'HeadInjury': 'head_injury', 'Hypertension': 'hypertension'
|
| 288 |
-
}
|
| 289 |
-
|
| 290 |
-
features = []
|
| 291 |
-
for feat_name in lifestyle_feature_names:
|
| 292 |
-
val = lifestyle_data.get(FEATURE_MAPPING[feat_name])
|
| 293 |
-
if val is None:
|
| 294 |
-
return f"Missing feature: {feat_name}"
|
| 295 |
-
features.append(val)
|
| 296 |
-
|
| 297 |
-
X_instance = np.array(features).reshape(1, -1)
|
| 298 |
-
shap_vals = lifestyle_explainer.shap_values(X_instance)[0] # class 1
|
| 299 |
-
|
| 300 |
-
top_indices = np.argsort(-shap_vals)[:5]
|
| 301 |
-
|
| 302 |
-
explanation_lines = ["🔍 Top factors increasing dementia risk (lifestyle analysis):"]
|
| 303 |
-
for i in top_indices:
|
| 304 |
-
feat = lifestyle_feature_names[i]
|
| 305 |
-
val = features[i]
|
| 306 |
-
impact = shap_vals[i]
|
| 307 |
-
if abs(impact) < 1e-4:
|
| 308 |
-
continue
|
| 309 |
-
# Map categorical to readable (optional but nice)
|
| 310 |
-
readable_val = val
|
| 311 |
-
if feat == "Gender":
|
| 312 |
-
readable_val = "Male" if val == 1 else "Female"
|
| 313 |
-
elif feat in ["Smoking", "AlcoholConsumption", "FamilyHistoryAlzheimers",
|
| 314 |
-
"CardiovascularDisease", "Diabetes", "Depression", "HeadInjury", "Hypertension"]:
|
| 315 |
-
readable_val = "Yes" if val == 1 else "No"
|
| 316 |
-
elif feat == "EducationLevel":
|
| 317 |
-
edu_map = {1: "Primary", 2: "Secondary", 3: "Bachelor", 4: "Postgrad"}
|
| 318 |
-
readable_val = edu_map.get(val, val)
|
| 319 |
-
|
| 320 |
-
direction = "↑" if impact > 0 else "↓"
|
| 321 |
-
explanation_lines.append(f" • {feat} = {readable_val} → {direction} risk ({impact:+.3f})")
|
| 322 |
-
|
| 323 |
-
return "\n".join(explanation_lines)
|
| 324 |
-
|
| 325 |
-
except Exception as e:
|
| 326 |
-
return f"SHAP explanation failed: {str(e)}"
|
| 327 |
-
|
| 328 |
-
|
| 329 |
-
# Load LLM from huggingface repos
|
| 330 |
-
client = InferenceClient(token=os.getenv("HF_TOKEN"))
|
| 331 |
-
def llm_invoke(prompt: str) -> str:
|
| 332 |
-
return client.text_generation(prompt, model="mistralai/Mistral-7B-Instruct-v0.2", max_new_tokens=512, temperature=0.7)
|
| 333 |
-
|
| 334 |
-
llm = type("SimpleLLM", (), {"invoke": llm_invoke})()
|
| 335 |
-
|
| 336 |
-
# Define agents for Alzheimer's detection system
|
| 337 |
-
risk_calculator_audio = Agent(
|
| 338 |
-
role="Risk Calculator Audio Agent",
|
| 339 |
-
goal="Calculate dementia risk for a specific patient using ML model and LLM interpretation",
|
| 340 |
-
backstory="You combine machine learning predictions with natural language explanations to provide personalized risk assessments.",
|
| 341 |
-
verbose=True,
|
| 342 |
-
llm=llm,
|
| 343 |
-
tools=[calculate_dementia_risk_audio, explain_dementia_risk_audio]
|
| 344 |
-
)
|
| 345 |
-
|
| 346 |
-
risk_calculator_lifestyle = Agent(
|
| 347 |
-
role="Risk Calculator Lifestyle Agent",
|
| 348 |
-
goal="Calculate dementia risk for a specific patient using ML model and LLM interpretation",
|
| 349 |
-
backstory="You combine machine learning predictions with natural language explanations to provide personalized risk assessments.",
|
| 350 |
-
verbose=True,
|
| 351 |
-
llm=llm,
|
| 352 |
-
tools=[calculate_dementia_risk_lifestyle, explain_dementia_risk_lifestyle]
|
| 353 |
-
)
|
| 354 |
-
|
| 355 |
-
|
| 356 |
-
# Define tasks for agents
|
| 357 |
-
risk_assessment_task_audio = Task(
|
| 358 |
-
description=f"Calculate dementia risk for patient",
|
| 359 |
-
expected_output="Risk level, confidence score, and plain-language explanation.",
|
| 360 |
-
agent=risk_calculator_audio,
|
| 361 |
-
)
|
| 362 |
-
|
| 363 |
-
explanation_task_audio = Task(
|
| 364 |
-
description="Explain the dementia risk prediction for patient using SHAP",
|
| 365 |
-
expected_output="Top 5 features increasing risk from audio analysis.",
|
| 366 |
-
agent=risk_calculator_audio
|
| 367 |
-
)
|
| 368 |
-
|
| 369 |
-
risk_assessment_task_lifestyle = Task(
|
| 370 |
-
description=f"Calculate dementia risk for patient using the given patient id: {placeholder_lifestyle_ID}",
|
| 371 |
-
expected_output="Risk level, confidence score, and plain-language explanation.",
|
| 372 |
-
agent=risk_calculator_lifestyle,
|
| 373 |
-
)
|
| 374 |
-
|
| 375 |
-
explanation_task_lifestyle = Task(
|
| 376 |
-
description=f"Explain the dementia risk prediction for patient {placeholder_lifestyle_ID} using SHAP",
|
| 377 |
-
expected_output="Top 5 features increasing risk, with impact direction and magnitude.",
|
| 378 |
-
agent=risk_calculator_lifestyle
|
| 379 |
-
)
|
| 380 |
-
|
| 381 |
-
# Create crew of agents
|
| 382 |
-
crew = Crew(
|
| 383 |
-
agents=[risk_calculator_audio, risk_calculator_lifestyle],
|
| 384 |
-
tasks=[risk_assessment_task_lifestyle],
|
| 385 |
-
verbose=True
|
| 386 |
-
)
|
| 387 |
-
|
| 388 |
-
def run_crewai_lifestyle(docID: str) -> dict:
|
| 389 |
-
"""
|
| 390 |
-
Runs the full CrewAI pipeline for lifestyle risk + SHAP + LLM summary.
|
| 391 |
-
Returns a JSON-serializable dict (success/error).
|
| 392 |
-
"""
|
| 393 |
-
try:
|
| 394 |
-
# Update task with dynamic docID
|
| 395 |
-
risk_assessment_task_lifestyle.description = f"Calculate dementia risk for patient using lifestyle data for ID: {docID}"
|
| 396 |
-
explanation_task_lifestyle.description = f"Explain the dementia risk prediction for patient {docID} using SHAP"
|
| 397 |
-
|
| 398 |
-
# Rebuild crew with updated tasks
|
| 399 |
-
crew_lifestyle = Crew(
|
| 400 |
-
agents=[risk_calculator_lifestyle],
|
| 401 |
-
tasks=[risk_assessment_task_lifestyle, explanation_task_lifestyle],
|
| 402 |
-
verbose=False # Keep logs clean for API
|
| 403 |
-
)
|
| 404 |
-
|
| 405 |
-
# Run
|
| 406 |
-
raw_output = crew_lifestyle.kickoff()
|
| 407 |
-
|
| 408 |
-
# Parse raw_output (usually a string) → try to extract JSON or format
|
| 409 |
-
# Since agents return natural language, we'll wrap it + add structured fields
|
| 410 |
-
# First, get raw model output for structured data
|
| 411 |
-
lifestyle_data = pull_lifestyle(docID)
|
| 412 |
-
if not lifestyle_data:
|
| 413 |
-
return {"status": "error", "message": f"No lifestyle data for {docID}"}
|
| 414 |
-
|
| 415 |
-
# Reuse function logic just for prediction (fast, reliable)
|
| 416 |
-
risk_result = calculate_dementia_risk_lifestyle(docID, return_json=True)
|
| 417 |
-
if risk_result["status"] != "success":
|
| 418 |
-
return risk_result
|
| 419 |
-
|
| 420 |
-
# Add explanation
|
| 421 |
-
shap_explanation = explain_dementia_risk_lifestyle(docID)
|
| 422 |
-
|
| 423 |
-
return {
|
| 424 |
-
"status": "success",
|
| 425 |
-
**risk_result,
|
| 426 |
-
"shap_explanation": shap_explanation,
|
| 427 |
-
"crew_summary": str(raw_output).strip()
|
| 428 |
-
}
|
| 429 |
-
|
| 430 |
-
except Exception as e:
|
| 431 |
-
return {"status": "error", "message": str(e)}
|
| 432 |
-
|
| 433 |
-
|
| 434 |
-
def run_crewai_audio(docID: str) -> dict:
|
| 435 |
-
"""Same for audio."""
|
| 436 |
-
try:
|
| 437 |
-
risk_assessment_task_audio.description = f"Calculate dementia risk for patient using audio data for ID: {docID}"
|
| 438 |
-
explanation_task_audio.description = f"Explain the dementia risk prediction for patient {docID} using SHAP"
|
| 439 |
-
|
| 440 |
-
crew_audio = Crew(
|
| 441 |
-
agents=[risk_calculator_audio],
|
| 442 |
-
tasks=[risk_assessment_task_audio, explanation_task_audio],
|
| 443 |
-
verbose=False
|
| 444 |
-
)
|
| 445 |
-
|
| 446 |
-
raw_output = crew_audio.kickoff()
|
| 447 |
-
|
| 448 |
-
# Get structured result
|
| 449 |
-
risk_result = calculate_dementia_risk_audio(docID, return_json=True)
|
| 450 |
-
if risk_result["status"] != "success":
|
| 451 |
-
return risk_result
|
| 452 |
-
|
| 453 |
-
shap_explanation = explain_dementia_risk_audio(docID)
|
| 454 |
-
|
| 455 |
-
return {
|
| 456 |
-
"status": "success",
|
| 457 |
-
**risk_result,
|
| 458 |
-
"shap_explanation": shap_explanation,
|
| 459 |
-
"crew_summary": str(raw_output).strip()
|
| 460 |
-
}
|
| 461 |
-
|
| 462 |
-
except Exception as e:
|
| 463 |
-
return {"status": "error", "message": str(e)}
|
| 464 |
-
|
| 465 |
-
|
| 466 |
-
# Run crew
|
| 467 |
-
if __name__ == "__main__":
|
| 468 |
-
print("Starting Alzheimer's Detection Crew with Llama3.1:8b...")
|
| 469 |
-
result = crew.kickoff()
|
| 470 |
-
print("\n=== FINAL REPORT ===\n")
|
| 471 |
-
print(result)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
firebaseLoader.py
CHANGED
|
@@ -9,7 +9,11 @@ import numpy as np
|
|
| 9 |
import firebase_admin
|
| 10 |
from firebase_admin import credentials, firestore, storage
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
if not firebase_admin._apps:
|
| 14 |
firebase_key = os.getenv("FIREBASE_SERVICE_ACCOUNT_JSON")
|
| 15 |
if firebase_key:
|
|
@@ -28,10 +32,13 @@ bucket = storage.bucket()
|
|
| 28 |
_whisper_model = None
|
| 29 |
_nlp = None
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
def _load_whisper():
|
| 32 |
global _whisper_model
|
| 33 |
if _whisper_model is None:
|
| 34 |
-
import whisper
|
| 35 |
print("Loading Whisper model...")
|
| 36 |
_whisper_model = whisper.load_model("medium")
|
| 37 |
return _whisper_model
|
|
@@ -39,44 +46,10 @@ def _load_whisper():
|
|
| 39 |
def _load_spacy():
|
| 40 |
global _nlp
|
| 41 |
if _nlp is None:
|
| 42 |
-
import spacy
|
| 43 |
print("Loading spaCy model...")
|
| 44 |
_nlp = spacy.load("en_core_web_sm")
|
| 45 |
return _nlp
|
| 46 |
|
| 47 |
-
def extract_audio_features(wav_path):
|
| 48 |
-
"""Extract MFCC, ZCR, RMS from a single .wav file"""
|
| 49 |
-
try:
|
| 50 |
-
y, sr = librosa.load(wav_path, sr=None)
|
| 51 |
-
mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
|
| 52 |
-
mfccs_mean = np.mean(mfccs, axis=1)
|
| 53 |
-
mfccs_std = np.std(mfccs, axis=1)
|
| 54 |
-
zcr = np.mean(librosa.feature.zero_crossing_rate(y))
|
| 55 |
-
rms = np.mean(librosa.feature.rms(y=y))
|
| 56 |
-
return np.concatenate([mfccs_mean, mfccs_std, [zcr, rms]])
|
| 57 |
-
except Exception as e:
|
| 58 |
-
print(f"Audio extraction failed for {wav_path}: {e}")
|
| 59 |
-
return None
|
| 60 |
-
|
| 61 |
-
def extract_text_features(cha_path):
|
| 62 |
-
"""Extract linguistic features from .cha file"""
|
| 63 |
-
try:
|
| 64 |
-
with open(cha_path, 'r', encoding='utf-8') as f:
|
| 65 |
-
lines = f.readlines()
|
| 66 |
-
utterances = [line.strip() for line in lines if line.startswith('*')]
|
| 67 |
-
if not utterances:
|
| 68 |
-
return None
|
| 69 |
-
word_count = sum(len(line.split()) for line in utterances)
|
| 70 |
-
sentence_count = len(utterances)
|
| 71 |
-
avg_words_per_sentence = word_count / sentence_count if sentence_count > 0 else 0
|
| 72 |
-
unique_words = len(set(word.lower().strip('.,!?;:') for line in utterances for word in line.split()))
|
| 73 |
-
lexical_diversity = unique_words / word_count if word_count > 0 else 0
|
| 74 |
-
pause_count = sum(line.count('<') + line.count('...') for line in utterances)
|
| 75 |
-
return np.array([word_count, sentence_count, avg_words_per_sentence, lexical_diversity, pause_count])
|
| 76 |
-
except Exception as e:
|
| 77 |
-
print(f"Text extraction failed for {cha_path}: {e}")
|
| 78 |
-
return None
|
| 79 |
-
|
| 80 |
def text_to_cha_lines(text):
|
| 81 |
text = text.replace("...", " ELLIPSIS_MARKER ")
|
| 82 |
sentences = []
|
|
@@ -112,6 +85,48 @@ def generate_mor_gra_line(doc):
|
|
| 112 |
return " ".join(mor_tokens), " ".join(gra_tokens)
|
| 113 |
|
| 114 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
def pull_audio(docID: str):
|
| 116 |
"""
|
| 117 |
Downloads .wav from Firebase Storage, fetches age/gender from Firestore,
|
|
@@ -254,6 +269,7 @@ def pull_audio(docID: str):
|
|
| 254 |
|
| 255 |
def pull_lifestyle(document_id: str):
|
| 256 |
"""Fetches lifestyle data from Firestore."""
|
|
|
|
| 257 |
try:
|
| 258 |
doc_ref = db.collection("Questionnaire").document(document_id)
|
| 259 |
doc = doc_ref.get()
|
|
|
|
| 9 |
import firebase_admin
|
| 10 |
from firebase_admin import credentials, firestore, storage
|
| 11 |
|
| 12 |
+
|
| 13 |
+
# ================================================================
|
| 14 |
+
# Firebase Initialization
|
| 15 |
+
# ================================================================
|
| 16 |
+
|
| 17 |
if not firebase_admin._apps:
|
| 18 |
firebase_key = os.getenv("FIREBASE_SERVICE_ACCOUNT_JSON")
|
| 19 |
if firebase_key:
|
|
|
|
| 32 |
_whisper_model = None
|
| 33 |
_nlp = None
|
| 34 |
|
| 35 |
+
# ================================================================
|
| 36 |
+
# Helper Fuctions for creating transcripts from audio files (.wav)
|
| 37 |
+
# ================================================================
|
| 38 |
+
|
| 39 |
def _load_whisper():
|
| 40 |
global _whisper_model
|
| 41 |
if _whisper_model is None:
|
|
|
|
| 42 |
print("Loading Whisper model...")
|
| 43 |
_whisper_model = whisper.load_model("medium")
|
| 44 |
return _whisper_model
|
|
|
|
| 46 |
def _load_spacy():
|
| 47 |
global _nlp
|
| 48 |
if _nlp is None:
|
|
|
|
| 49 |
print("Loading spaCy model...")
|
| 50 |
_nlp = spacy.load("en_core_web_sm")
|
| 51 |
return _nlp
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
def text_to_cha_lines(text):
|
| 54 |
text = text.replace("...", " ELLIPSIS_MARKER ")
|
| 55 |
sentences = []
|
|
|
|
| 85 |
return " ".join(mor_tokens), " ".join(gra_tokens)
|
| 86 |
|
| 87 |
|
| 88 |
+
# ================================================================
|
| 89 |
+
# Helper Functions for audio data pulling
|
| 90 |
+
# ================================================================
|
| 91 |
+
|
| 92 |
+
def extract_audio_features(wav_path):
|
| 93 |
+
"""Extract MFCC, ZCR, RMS from a single .wav file"""
|
| 94 |
+
try:
|
| 95 |
+
y, sr = librosa.load(wav_path, sr=None)
|
| 96 |
+
mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
|
| 97 |
+
mfccs_mean = np.mean(mfccs, axis=1)
|
| 98 |
+
mfccs_std = np.std(mfccs, axis=1)
|
| 99 |
+
zcr = np.mean(librosa.feature.zero_crossing_rate(y))
|
| 100 |
+
rms = np.mean(librosa.feature.rms(y=y))
|
| 101 |
+
return np.concatenate([mfccs_mean, mfccs_std, [zcr, rms]])
|
| 102 |
+
except Exception as e:
|
| 103 |
+
print(f"Audio extraction failed for {wav_path}: {e}")
|
| 104 |
+
return None
|
| 105 |
+
|
| 106 |
+
def extract_text_features(cha_path):
|
| 107 |
+
"""Extract linguistic features from .cha file"""
|
| 108 |
+
try:
|
| 109 |
+
with open(cha_path, 'r', encoding='utf-8') as f:
|
| 110 |
+
lines = f.readlines()
|
| 111 |
+
utterances = [line.strip() for line in lines if line.startswith('*')]
|
| 112 |
+
if not utterances:
|
| 113 |
+
return None
|
| 114 |
+
word_count = sum(len(line.split()) for line in utterances)
|
| 115 |
+
sentence_count = len(utterances)
|
| 116 |
+
avg_words_per_sentence = word_count / sentence_count if sentence_count > 0 else 0
|
| 117 |
+
unique_words = len(set(word.lower().strip('.,!?;:') for line in utterances for word in line.split()))
|
| 118 |
+
lexical_diversity = unique_words / word_count if word_count > 0 else 0
|
| 119 |
+
pause_count = sum(line.count('<') + line.count('...') for line in utterances)
|
| 120 |
+
return np.array([word_count, sentence_count, avg_words_per_sentence, lexical_diversity, pause_count])
|
| 121 |
+
except Exception as e:
|
| 122 |
+
print(f"Text extraction failed for {cha_path}: {e}")
|
| 123 |
+
return None
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
# ================================================================
|
| 127 |
+
# Data loading functions
|
| 128 |
+
# ================================================================
|
| 129 |
+
|
| 130 |
def pull_audio(docID: str):
|
| 131 |
"""
|
| 132 |
Downloads .wav from Firebase Storage, fetches age/gender from Firestore,
|
|
|
|
| 269 |
|
| 270 |
def pull_lifestyle(document_id: str):
|
| 271 |
"""Fetches lifestyle data from Firestore."""
|
| 272 |
+
# Just gets all the fields and there data from firebase
|
| 273 |
try:
|
| 274 |
doc_ref = db.collection("Questionnaire").document(document_id)
|
| 275 |
doc = doc_ref.get()
|
modelAudiov7_ML.pk1
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5df642a21b54b684a1f5bdb50f687329652be0e35763c260338ec34b5b46c202
|
| 3 |
-
size 123297
|
|
|
|
|
|
|
|
|
|
|
|
modelLifestyleV2_ML.pk1
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d77641897ca44426851e0fba91af99d96e68795b487e473978fb7048a5dae880
|
| 3 |
-
size 436054
|
|
|
|
|
|
|
|
|
|
|
|
webscraper.py
CHANGED
|
@@ -1,9 +1,13 @@
|
|
| 1 |
-
# webscraper.py
|
| 2 |
import requests
|
| 3 |
from bs4 import BeautifulSoup
|
| 4 |
import time
|
| 5 |
import os
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
def clean_text(text):
|
| 8 |
return " ".join(text.split())
|
| 9 |
|
|
@@ -48,9 +52,10 @@ def scrape_article_links(base_url: str, max_links=10) -> list[dict]:
|
|
| 48 |
return items
|
| 49 |
|
| 50 |
except Exception as e:
|
| 51 |
-
print(f"
|
| 52 |
return []
|
| 53 |
|
|
|
|
| 54 |
def scrape_full_text(url: str) -> str:
|
| 55 |
"""Return raw full article text (no summarization)."""
|
| 56 |
headers = {
|
|
@@ -72,9 +77,15 @@ def scrape_full_text(url: str) -> str:
|
|
| 72 |
return text[:8000] # Cap for token efficiency
|
| 73 |
|
| 74 |
except Exception as e:
|
| 75 |
-
print(f"
|
| 76 |
return ""
|
| 77 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
def get_patient_news_raw(count: int = 5) -> list[dict]:
|
| 79 |
base_urls = [
|
| 80 |
"https://www.caregiving.org/?s=dementia",
|
|
@@ -92,6 +103,7 @@ def get_patient_news_raw(count: int = 5) -> list[dict]:
|
|
| 92 |
articles.append(item)
|
| 93 |
return articles[:count]
|
| 94 |
|
|
|
|
| 95 |
def get_doctor_news_raw(count: int = 5) -> list[dict]:
|
| 96 |
base_urls = [
|
| 97 |
"https://www.nature.com/search?q=dementia&order=date",
|
|
|
|
|
|
|
| 1 |
import requests
|
| 2 |
from bs4 import BeautifulSoup
|
| 3 |
import time
|
| 4 |
import os
|
| 5 |
|
| 6 |
+
|
| 7 |
+
# ================================================================
|
| 8 |
+
# Helper Functions
|
| 9 |
+
# ================================================================
|
| 10 |
+
|
| 11 |
def clean_text(text):
|
| 12 |
return " ".join(text.split())
|
| 13 |
|
|
|
|
| 52 |
return items
|
| 53 |
|
| 54 |
except Exception as e:
|
| 55 |
+
print(f"scrape_article_links({base_url}) failed: {e}")
|
| 56 |
return []
|
| 57 |
|
| 58 |
+
# Attempts to get the full raw article text
|
| 59 |
def scrape_full_text(url: str) -> str:
|
| 60 |
"""Return raw full article text (no summarization)."""
|
| 61 |
headers = {
|
|
|
|
| 77 |
return text[:8000] # Cap for token efficiency
|
| 78 |
|
| 79 |
except Exception as e:
|
| 80 |
+
print(f"scrape_full_text({url}) failed: {e}")
|
| 81 |
return ""
|
| 82 |
|
| 83 |
+
|
| 84 |
+
# ================================================================
|
| 85 |
+
# News webscraping
|
| 86 |
+
# ================================================================
|
| 87 |
+
|
| 88 |
+
# Gets new articles for patients
|
| 89 |
def get_patient_news_raw(count: int = 5) -> list[dict]:
|
| 90 |
base_urls = [
|
| 91 |
"https://www.caregiving.org/?s=dementia",
|
|
|
|
| 103 |
articles.append(item)
|
| 104 |
return articles[:count]
|
| 105 |
|
| 106 |
+
# Gets new articles for doctors
|
| 107 |
def get_doctor_news_raw(count: int = 5) -> list[dict]:
|
| 108 |
base_urls = [
|
| 109 |
"https://www.nature.com/search?q=dementia&order=date",
|