Spaces:
Runtime error
Runtime error
File size: 25,693 Bytes
8018595 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 |
"""Tests for the PLCOm2012 Lung Cancer Risk Model.
Ground truth values are calculated from authors' reference implementation in
https://brocku.ca/lung-cancer-screening-and-risk-prediction/risk-calculators/
and the reference implementation in R: https://github.com/resplab/PLCOm2012.
"""
import pytest
from sentinel.risk_models.plcom2012 import PLCOm2012RiskModel
from sentinel.user_input import (
Anthropometrics,
CancerType,
ChronicCondition,
Demographics,
Ethnicity,
FamilyMemberCancer,
FamilyRelation,
FamilySide,
Lifestyle,
PersonalMedicalHistory,
RelationshipDegree,
Sex,
SmokingHistory,
SmokingStatus,
UserInput,
)
# Test cases with calculated ground truth data (inline UserInput like Gail tests)
GROUND_TRUTH_CASES = [
{
"name": "low_risk_current_smoker",
"input": UserInput(
demographics=Demographics(
age_years=55,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(
height_cm=175.0,
weight_kg=25.0 * (1.75**2),
),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=10,
years_smoked=20,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(
chronic_conditions=[],
previous_cancers=[],
),
family_history=[],
),
"expected": 0.31,
},
{
"name": "moderate_risk_former_smoker",
"input": UserInput(
demographics=Demographics(
age_years=62,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(
height_cm=175.0,
weight_kg=27.0 * (1.75**2),
),
education_level=3,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.FORMER,
cigarettes_per_day=20,
years_smoked=30,
years_since_quit=5,
),
),
personal_medical_history=PersonalMedicalHistory(
chronic_conditions=[],
previous_cancers=[],
),
family_history=[],
),
"expected": 1.24,
},
{
"name": "high_risk_multiple_factors",
"input": UserInput(
demographics=Demographics(
age_years=70,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(
height_cm=175.0,
weight_kg=22.0 * (1.75**2),
),
education_level=2,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=40,
years_smoked=45,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(
chronic_conditions=[ChronicCondition.COPD],
previous_cancers=[CancerType.BREAST],
),
family_history=[
FamilyMemberCancer(
relation=FamilyRelation.MOTHER,
side=FamilySide.MATERNAL,
degree=RelationshipDegree.FIRST,
cancer_type=CancerType.LUNG,
age_at_diagnosis=65,
)
],
),
"expected": 31.19,
},
{
"name": "black_race_variant",
"input": UserInput(
demographics=Demographics(
age_years=58,
sex=Sex.MALE,
ethnicity=Ethnicity.BLACK,
anthropometrics=Anthropometrics(
height_cm=175.0,
weight_kg=28.0 * (1.75**2),
),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.FORMER,
cigarettes_per_day=15,
years_smoked=25,
years_since_quit=8,
),
),
personal_medical_history=PersonalMedicalHistory(
chronic_conditions=[],
previous_cancers=[],
),
family_history=[],
),
"expected": 0.696,
},
{
"name": "hispanic_low_education",
"input": UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=Ethnicity.HISPANIC,
anthropometrics=Anthropometrics(
height_cm=175.0,
weight_kg=30.0 * (1.75**2),
),
education_level=1,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=25,
years_smoked=35,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(
chronic_conditions=[],
previous_cancers=[],
),
family_history=[],
),
"expected": 1.161,
},
{
"name": "asian_former_heavy_smoker",
"input": UserInput(
demographics=Demographics(
age_years=65,
sex=Sex.MALE,
ethnicity=Ethnicity.ASIAN,
anthropometrics=Anthropometrics(
height_cm=175.0,
weight_kg=24.0 * (1.75**2),
),
education_level=5,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.FORMER,
cigarettes_per_day=25,
years_smoked=35,
years_since_quit=3,
),
),
personal_medical_history=PersonalMedicalHistory(
chronic_conditions=[ChronicCondition.COPD],
previous_cancers=[],
),
family_history=[
FamilyMemberCancer(
relation=FamilyRelation.MOTHER,
side=FamilySide.MATERNAL,
degree=RelationshipDegree.FIRST,
cancer_type=CancerType.LUNG,
age_at_diagnosis=65,
)
],
),
"expected": 3.40,
},
]
class TestPLCOm2012Model:
"""Test suite for PLCOm2012RiskModel."""
def setup_method(self):
"""Initialize PLCOm2012RiskModel instance for testing."""
self.model = PLCOm2012RiskModel()
@pytest.mark.parametrize("case", GROUND_TRUTH_CASES, ids=lambda x: x["name"])
def test_ground_truth_validation(self, case):
"""Test against calculated ground truth results.
Args:
case: Parameterized ground truth case dict.
"""
user = case["input"]
score_str = self.model.compute_score(user)
calculated = float(score_str.rstrip("%"))
expected = case["expected"]
# Using tight tolerance since these are calculated values
assert calculated == pytest.approx(expected, abs=0.01)
def test_user_input_integration_current_smoker(self):
"""Test integration with UserInput model for current smoker."""
user = UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(
height_cm=175.0,
weight_kg=80.0,
),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(
chronic_conditions=[],
previous_cancers=[],
),
family_history=[],
)
score = self.model.compute_score(user)
assert score != "N/A: Model is for current or former smokers only."
assert "%" in score
assert float(score.replace("%", "")) > 0
def test_user_input_integration_former_smoker(self):
"""Test integration with UserInput model for former smoker."""
user = UserInput(
demographics=Demographics(
age_years=65,
sex=Sex.FEMALE,
ethnicity=Ethnicity.BLACK,
anthropometrics=Anthropometrics(
height_cm=160.0,
weight_kg=70.0,
),
education_level=3,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.FORMER,
cigarettes_per_day=15,
years_smoked=30,
years_since_quit=10,
),
),
personal_medical_history=PersonalMedicalHistory(
chronic_conditions=[ChronicCondition.COPD],
previous_cancers=[CancerType.BREAST],
),
family_history=[
FamilyMemberCancer(
relation=FamilyRelation.FATHER,
side=FamilySide.PATERNAL,
degree=RelationshipDegree.FIRST,
cancer_type=CancerType.LUNG,
age_at_diagnosis=68,
)
],
)
score = self.model.compute_score(user)
assert score != "N/A: Model is for current or former smokers only."
assert "%" in score
assert float(score.replace("%", "")) > 0
def test_never_smoker_handling(self):
"""Test that never smokers receive N/A response."""
never_smoker = UserInput(
demographics=Demographics(
age_years=55,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.NEVER,
cigarettes_per_day=0,
years_smoked=0,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
score = self.model.compute_score(never_smoker)
assert score == "N/A: Model is for current or former smokers only."
def test_validation_errors(self):
"""Test validation errors for missing required fields."""
user = UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
# This should pass validation since all required fields are present
score = self.model.compute_score(user)
assert "%" in score
def test_age_out_of_range(self):
"""Test age outside validated range raises ValueError."""
user = UserInput(
demographics=Demographics(
age_years=45, # Below minimum
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
with pytest.raises(ValueError, match=r"Invalid inputs for PLCOm2012:"):
self.model.compute_score(user)
def test_age_validation_legacy(self):
"""Test age validation (50-80 range) - legacy behavior."""
# This test is now handled by input validation, so we expect ValueError
young_user = UserInput(
demographics=Demographics(
age_years=49,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=75.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
with pytest.raises(ValueError, match=r"Invalid inputs for PLCOm2012:"):
self.model.compute_score(young_user)
old_user = UserInput(
demographics=Demographics(
age_years=81,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=75.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
with pytest.raises(ValueError, match=r"Invalid inputs for PLCOm2012:"):
self.model.compute_score(old_user)
def test_missing_bmi_data(self):
"""Test handling of missing BMI data."""
# This test is now handled by input validation since anthropometrics is required
# We can't create a UserInput without anthropometrics due to Pydantic validation
pass
def test_missing_education_level(self):
"""Test handling of missing education level."""
user = UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
# Missing education_level
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
with pytest.raises(ValueError, match=r"Invalid inputs for PLCOm2012:"):
self.model.compute_score(user)
def test_missing_smoking_intensity(self):
"""Test handling of missing smoking intensity."""
# This test is now handled by the model's internal validation
# since 0 cigarettes per day causes a division by zero in the calculation
user = UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=0, # This will cause division by zero
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
# The model should handle this gracefully and return an N/A message
score = self.model.compute_score(user)
assert "Calculation failed" in score
def test_missing_smoking_duration(self):
"""Test handling of missing smoking duration."""
# This test is now handled by input validation since years_smoked >= 0 is required
# The model will accept 0 years smoked as valid input
user = UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=0, # This is valid input
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
# This should work fine with 0 years smoked
score = self.model.compute_score(user)
assert "%" in score
def test_missing_quit_years_former_smoker(self):
"""Test handling of missing quit years for former smoker."""
user = UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.FORMER,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None, # This will trigger N/A message
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
score = self.model.compute_score(user)
assert "Missing years since quitting for former smoker" in score
def test_copd_detection(self):
"""Test COPD detection from chronic illnesses."""
user = UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(
chronic_conditions=[ChronicCondition.COPD, ChronicCondition.DIABETES],
),
family_history=[],
)
score = self.model.compute_score(user)
assert "%" in score
def test_family_history_lung_cancer_detection(self):
"""Test lung cancer family history detection."""
user = UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=Ethnicity.WHITE,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[
FamilyMemberCancer(
relation=FamilyRelation.MOTHER,
side=FamilySide.MATERNAL,
degree=RelationshipDegree.FIRST,
cancer_type=CancerType.LUNG,
age_at_diagnosis=65,
),
FamilyMemberCancer(
relation=FamilyRelation.MATERNAL_UNCLE,
side=FamilySide.MATERNAL,
degree=RelationshipDegree.SECOND,
cancer_type=CancerType.LUNG,
age_at_diagnosis=70,
), # Should not count (not first-degree relative)
],
)
score = self.model.compute_score(user)
assert "%" in score
def test_race_handling(self):
"""Test different race/ethnicity handling."""
races = [
Ethnicity.WHITE,
Ethnicity.BLACK,
Ethnicity.HISPANIC,
Ethnicity.ASIAN,
Ethnicity.PACIFIC_ISLANDER,
]
for race in races:
user = UserInput(
demographics=Demographics(
age_years=60,
sex=Sex.MALE,
ethnicity=race,
anthropometrics=Anthropometrics(height_cm=175.0, weight_kg=80.0),
education_level=4,
),
lifestyle=Lifestyle(
smoking=SmokingHistory(
status=SmokingStatus.CURRENT,
cigarettes_per_day=20,
years_smoked=25,
years_since_quit=None,
),
),
personal_medical_history=PersonalMedicalHistory(),
family_history=[],
)
score = self.model.compute_score(user)
assert "%" in score
assert float(score.replace("%", "")) > 0
def test_model_metadata(self):
"""Test model metadata methods."""
assert self.model.name == "plcom2012"
assert self.model.cancer_type() == "lung"
assert "PLCOm2012" in self.model.description()
assert "6-year" in self.model.description()
assert "percentage chance" in self.model.interpretation()
assert isinstance(self.model.references(), list)
assert len(self.model.references()) > 0
assert "Tammemägi" in self.model.references()[0]
def test_smoking_status_encoding(self):
"""Test smoking status encoding (current=0, former=1)."""
# Test current smoker
current_input = dict(
age=60,
race="white",
education=4,
bmi=25.0,
copd=0,
cancer_hist=0,
family_hist_lung_cancer=0,
smoking_status=0,
smoking_intensity=20,
duration_smoking=25,
smoking_quit_time=0,
)
current_risk = self.model.calculate_risk(**current_input)
# Test former smoker (same parameters except status and quit time)
former_input = dict(
age=60,
race="white",
education=4,
bmi=25.0,
copd=0,
cancer_hist=0,
family_hist_lung_cancer=0,
smoking_status=1,
smoking_intensity=20,
duration_smoking=25,
smoking_quit_time=5,
)
former_risk = self.model.calculate_risk(**former_input)
# Both should be positive numbers
assert current_risk > 0
assert former_risk > 0
def test_smoking_intensity_transformation(self):
"""Test smoking intensity transformation ((intensity/10)^-1)."""
# Test with different intensities
intensities = [10, 20, 30, 40]
risks = []
for intensity in intensities:
input_data = dict(
age=60,
race="white",
education=4,
bmi=25.0,
copd=0,
cancer_hist=0,
family_hist_lung_cancer=0,
smoking_status=0,
smoking_intensity=intensity,
duration_smoking=25,
smoking_quit_time=0,
)
risk = self.model.calculate_risk(**input_data)
risks.append(risk)
# All risks should be positive
for risk in risks:
assert risk > 0
|