hccinfhir 0.2.2__py3-none-any.whl → 0.2.3__py3-none-any.whl

hccinfhir/extractor_834.py

@@ -1,12 +1,20 @@
-from typing import List, Optional, Dict, Any, Tuple
+"""
+X12 834 Benefit Enrollment Parser for California DHCS Medi-Cal
+
+Extracts enrollment and demographic data from 834 transactions with focus on:
+- Risk adjustment fields (dual eligibility, OREC/CREC, SNP, LTI)
+- CA DHCS FAME-specific fields
+- HCP (Health Care Plan) coverage history
+"""
+
+from typing import List, Optional, Dict, Tuple
 from pydantic import BaseModel
 from datetime import datetime, date
-from hccinfhir.datamodels import Demographics, EnrollmentData
+from hccinfhir.datamodels import Demographics, EnrollmentData, HCPCoveragePeriod
 from hccinfhir.constants import (
     VALID_DUAL_CODES,
     FULL_BENEFIT_DUAL_CODES,
     PARTIAL_BENEFIT_DUAL_CODES,
-    VALID_OREC_VALUES,
     VALID_CREC_VALUES,
     X12_SEX_CODE_MAPPING,
     NON_DUAL_CODE,
@@ -14,33 +22,88 @@ from hccinfhir.constants import (
     map_aid_code_to_dual_status,
 )
 
-TRANSACTION_TYPES = {
-    "005010X220A1": "834",  # Benefit Enrollment and Maintenance
+# Constants
+TRANSACTION_TYPES = {"005010X220A1": "834"}
+
+LANGUAGE_CODES = {
+    'SPA': 'Spanish', 'ENG': 'English', 'CHI': 'Chinese', 'VIE': 'Vietnamese',
+    'KOR': 'Korean', 'TAG': 'Tagalog', 'ARM': 'Armenian', 'FAR': 'Farsi',
+    'ARA': 'Arabic', 'RUS': 'Russian', 'JPN': 'Japanese', 'HIN': 'Hindi',
+    'CAM': 'Cambodian', 'HMO': 'Hmong', 'LAO': 'Lao', 'THA': 'Thai',
 }
 
+MEDICARE_KEYWORDS = {'MEDICARE', 'MA', 'PART A', 'PART B', 'PART C', 'PART D', 'MEDICARE ADVANTAGE', 'MA-PD'}
+MEDICAID_KEYWORDS = {'MEDICAID', 'MEDI-CAL', 'MEDI CAL', 'MEDIC-AID', 'LTC'}
+SNP_KEYWORDS = {'SNP', 'SPECIAL NEEDS', 'D-SNP', 'DSNP', 'DUAL ELIGIBLE SNP'}
+LTI_KEYWORDS = {'LTC', 'LONG TERM CARE', 'LONG-TERM CARE', 'NURSING HOME', 'SKILLED NURSING', 'SNF', 'INSTITUTIONALIZED'}
+
+
+class HCPContext(BaseModel):
+    """Single HD loop (HCP coverage period)"""
+    start_date: Optional[str] = None
+    end_date: Optional[str] = None
+    hcp_code: Optional[str] = None
+    hcp_status: Optional[str] = None
+    aid_codes: Optional[str] = None
+
+
 class MemberContext(BaseModel):
     """Tracks member-level data across segments within 834 transaction"""
     # Identifiers
     member_id: Optional[str] = None
-    mbi: Optional[str] = None  # Medicare Beneficiary Identifier
+    mbi: Optional[str] = None
     medicaid_id: Optional[str] = None
+    hic: Optional[str] = None
+
+    # Name
+    first_name: Optional[str] = None
+    last_name: Optional[str] = None
+    middle_name: Optional[str] = None
 
     # Demographics
     dob: Optional[str] = None
     sex: Optional[str] = None
+    race: Optional[str] = None
+    language: Optional[str] = None
+    death_date: Optional[str] = None
+
+    # Address
+    address_1: Optional[str] = None
+    address_2: Optional[str] = None
+    city: Optional[str] = None
+    state: Optional[str] = None
+    zip: Optional[str] = None
+    phone: Optional[str] = None
 
     # Coverage Status
-    maintenance_type: Optional[str] = None  # 001=Change, 021=Add, 024=Cancel, 025=Reinstate
+    maintenance_type: Optional[str] = None
+    maintenance_reason_code: Optional[str] = None
+    benefit_status_code: Optional[str] = None
     coverage_start_date: Optional[str] = None
     coverage_end_date: Optional[str] = None
 
     # Medicare/Medicaid Status
     has_medicare: bool = False
     has_medicaid: bool = False
-    medicare_status_code: Optional[str] = None  # QMB, SLMB, QI, etc.
+    medicare_status_code: Optional[str] = None
     medi_cal_aid_code: Optional[str] = None
     dual_elgbl_cd: Optional[str] = None
 
+    # CA DHCS / FAME Specific
+    fame_county_id: Optional[str] = None
+    case_number: Optional[str] = None
+    fame_card_issue_date: Optional[str] = None
+    fame_redetermination_date: Optional[str] = None
+    fame_death_date: Optional[str] = None
+    primary_aid_code: Optional[str] = None
+    carrier_code: Optional[str] = None
+    fed_contract_number: Optional[str] = None
+    client_reporting_cat: Optional[str] = None
+    res_addr_flag: Optional[str] = None
+    reas_add_ind: Optional[str] = None
+    res_zip_deliv_code: Optional[str] = None
+    cin_check_digit: Optional[str] = None
+
     # Risk Adjustment Fields
     orec: Optional[str] = None
     crec: Optional[str] = None
@@ -48,93 +111,74 @@ class MemberContext(BaseModel):
     low_income: bool = False
     lti: bool = False
 
-# Helper methods for EnrollmentData - added as standalone functions
-def enrollment_to_demographics(enrollment: EnrollmentData) -> Demographics:
-    """Convert EnrollmentData to Demographics model for risk calculation"""
-    return Demographics(
-        age=enrollment.age or 0,
-        sex=enrollment.sex or 'M',
-        dual_elgbl_cd=enrollment.dual_elgbl_cd,
-        orec=enrollment.orec or '',
-        crec=enrollment.crec or '',
-        new_enrollee=enrollment.new_enrollee,
-        snp=enrollment.snp,
-        low_income=enrollment.low_income,
-        lti=enrollment.lti
-    )
-
-def is_losing_medicaid(enrollment: EnrollmentData, within_days: int = 90) -> bool:
-    """Check if member will lose Medicaid within specified days
-
-    Args:
-        enrollment: EnrollmentData object
-        within_days: Number of days to look ahead (default 90)
-
-    Returns:
-        True if Medicaid coverage ends within specified days
-    """
-    if not enrollment.coverage_end_date or not enrollment.has_medicaid:
-        return False
+    # HCP Info
+    hcp_code: Optional[str] = None
+    hcp_status: Optional[str] = None
+    amount: Optional[str] = None
 
-    try:
-        end_date = datetime.strptime(enrollment.coverage_end_date, "%Y-%m-%d").date()
-        today = date.today()
-        days_until_end = (end_date - today).days
+    # HCP History
+    hcp_history: List[HCPContext] = []
+    current_hcp: Optional[HCPContext] = None
 
-        return 0 <= days_until_end <= within_days
-    except (ValueError, AttributeError):
-        return False
 
-def is_medicaid_terminated(enrollment: EnrollmentData) -> bool:
-    """Check if Medicaid coverage is being terminated (maintenance type 024)"""
-    return enrollment.maintenance_type == '024'
+# ============================================================================
+# Utility Functions
+# ============================================================================
 
-def medicaid_status_summary(enrollment: EnrollmentData) -> Dict[str, Any]:
-    """Get summary of Medicaid coverage status for monitoring
+def get_segment_value(segment: List[str], index: int, default: Optional[str] = None) -> Optional[str]:
+    """Safely get value from segment at given index"""
+    if len(segment) > index and segment[index]:
+        return segment[index]
+    return default
 
-    Args:
-        enrollment: EnrollmentData object
-
-    Returns:
-        Dictionary with Medicaid status, dual eligibility, and loss indicators
-    """
-    return {
-        'member_id': enrollment.member_id,
-        'has_medicaid': enrollment.has_medicaid,
-        'has_medicare': enrollment.has_medicare,
-        'dual_status': enrollment.dual_elgbl_cd,
-        'is_full_benefit_dual': enrollment.is_full_benefit_dual,
-        'is_partial_benefit_dual': enrollment.is_partial_benefit_dual,
-        'coverage_end_date': enrollment.coverage_end_date,
-        'is_termination': is_medicaid_terminated(enrollment),
-        'losing_medicaid_30d': is_losing_medicaid(enrollment, 30),
-        'losing_medicaid_60d': is_losing_medicaid(enrollment, 60),
-        'losing_medicaid_90d': is_losing_medicaid(enrollment, 90)
-    }
 
 def parse_date(date_str: str) -> Optional[str]:
-    """Convert 8-digit date string to ISO format YYYY-MM-DD"""
-    if not isinstance(date_str, str) or len(date_str) != 8:
+    """Convert 8-digit date string (YYYYMMDD) to ISO format (YYYY-MM-DD)"""
+    if not date_str or len(date_str) < 8:
         return None
     try:
         year, month, day = int(date_str[:4]), int(date_str[4:6]), int(date_str[6:8])
-        if not (1900 <= year <= 2100 and 1 <= month <= 12 and 1 <= day <= 31):
-            return None
-        return f"{year:04d}-{month:02d}-{day:02d}"
+        if 1900 <= year <= 2100 and 1 <= month <= 12 and 1 <= day <= 31:
+            return f"{year:04d}-{month:02d}-{day:02d}"
+    except (ValueError, IndexError):
+        pass
+    return None
+
+
+def parse_yymmdd(date_str: str) -> Optional[str]:
+    """Convert 6-digit date (YYMMDD) to ISO format"""
+    if not date_str or len(date_str) < 6:
+        return None
+    try:
+        yy = int(date_str[:2])
+        year = 2000 + yy if yy < 50 else 1900 + yy
+        return f"{year}-{date_str[2:4]}-{date_str[4:6]}"
     except (ValueError, IndexError):
         return None
 
+
+def strip_leading_zeros(value: str) -> str:
+    """Strip leading zeros but keep at least one character"""
+    return value.lstrip('0') or value
+
+
+def get_composite_part(value: str, index: int) -> Optional[str]:
+    """Get part from semicolon-delimited composite value (0-indexed)"""
+    if not value:
+        return None
+    parts = value.split(';')
+    if len(parts) > index and parts[index]:
+        return parts[index]
+    return None
+
+
 def calculate_age(dob: str, reference_date: Optional[str] = None) -> Optional[int]:
     """Calculate age from DOB in YYYY-MM-DD format"""
     if not dob:
         return None
     try:
         birth_date = datetime.strptime(dob, "%Y-%m-%d").date()
-        if reference_date:
-            ref_date = datetime.strptime(reference_date, "%Y-%m-%d").date()
-        else:
-            ref_date = date.today()
-
+        ref_date = datetime.strptime(reference_date, "%Y-%m-%d").date() if reference_date else date.today()
         age = ref_date.year - birth_date.year
         if (ref_date.month, ref_date.day) < (birth_date.month, birth_date.day):
             age -= 1
@@ -142,121 +186,325 @@ def calculate_age(dob: str, reference_date: Optional[str] = None) -> Optional[in
     except (ValueError, AttributeError):
         return None
 
-def get_segment_value(segment: List[str], index: int, default: Optional[str] = None) -> Optional[str]:
-    """Safely get value from segment at given index"""
-    try:
-        if len(segment) > index and segment[index]:
-            return segment[index]
-    except (IndexError, TypeError):
-        pass
-    return default
-
-def parse_composite_ref_value(value: str) -> str:
-    """Parse X12 composite element format: 'qualifier;id;...'
-
-    X12 uses semicolons to separate sub-elements within a composite data element.
-    Example: REF*23*9;20061234; where 9 is the ID type qualifier
 
-    Args:
-        value: Raw REF segment value (e.g., '9;20061234;' or '20061234')
+def is_new_enrollee(coverage_start_date: Optional[str], reference_date: Optional[str] = None) -> bool:
+    """Determine if member is new enrollee (<= 3 months since coverage start)"""
+    if not coverage_start_date:
+        return False
+    try:
+        start_date = datetime.strptime(coverage_start_date, "%Y-%m-%d").date()
+        ref_date = datetime.strptime(reference_date, "%Y-%m-%d").date() if reference_date else date.today()
+        months_diff = (ref_date.year - start_date.year) * 12 + (ref_date.month - start_date.month)
+        return months_diff <= 3
+    except (ValueError, AttributeError):
+        return False
 
-    Returns:
-        The last non-empty sub-element (the actual ID)
-    """
-    if not value:
-        return value
 
-    if ';' in value:
-        # Split by semicolon and filter out empty parts
-        parts = [p for p in value.split(';') if p]
-        return parts[-1] if parts else value
+def contains_any_keyword(text: str, keywords: set) -> bool:
+    """Check if text contains any of the keywords"""
+    text_upper = text.upper()
+    return any(kw in text_upper for kw in keywords)
 
-    return value
 
+# ============================================================================
+# Dual Eligibility Logic
+# ============================================================================
 
 def determine_dual_status(member: MemberContext) -> str:
-    """Intelligently derive dual eligibility code from available data
-
-    Priority order:
-    1. Explicit dual_elgbl_cd from REF segment
-    2. California Medi-Cal aid code mapping
-    3. Medicare status code (QMB, SLMB, etc.)
-    4. Presence of both Medicare and Medicaid coverage
-    5. Default to non-dual ('00')
+    """Derive dual eligibility code from available data
+
+    Priority: explicit code > aid code mapping > medicare status > both coverages > default
     """
-    # Priority 1: Explicit dual_elgbl_cd
-    if member.dual_elgbl_cd and member.dual_elgbl_cd in VALID_DUAL_CODES:
+    if member.dual_elgbl_cd in VALID_DUAL_CODES:
         return member.dual_elgbl_cd
 
-    # Priority 2: California aid code mapping
     if member.medi_cal_aid_code:
         dual_code = map_aid_code_to_dual_status(member.medi_cal_aid_code)
         if dual_code != NON_DUAL_CODE:
             return dual_code
 
-    # Priority 3: Medicare status code
     if member.medicare_status_code:
         dual_code = map_medicare_status_to_dual_code(member.medicare_status_code)
         if dual_code != NON_DUAL_CODE:
             return dual_code
 
-    # Priority 4: Both Medicare and Medicaid coverage present
     if member.has_medicare and (member.has_medicaid or member.medicaid_id):
-        # Conservative: assign '08' (Other Full Dual) to ensure dual coefficients
-        return '08'
+        return '08'  # Other Full Dual
 
-    # Default: Non-dual
     return NON_DUAL_CODE
 
+
 def classify_dual_benefit_level(dual_code: str) -> Tuple[bool, bool]:
-    """Classify as Full Benefit Dual (FBD) or Partial Benefit Dual (PBD)
+    """Return (is_full_benefit_dual, is_partial_benefit_dual)"""
+    return dual_code in FULL_BENEFIT_DUAL_CODES, dual_code in PARTIAL_BENEFIT_DUAL_CODES
 
-    Full Benefit Dual codes: 02, 04, 08
-    - Uses CFA_ (Community, Full Benefit Dual, Aged) prefix
-    - Uses CFD_ (Community, Full Benefit Dual, Disabled) prefix
 
-    Partial Benefit Dual codes: 01, 03, 05, 06
-    - Uses CPA_ (Community, Partial Benefit Dual, Aged) prefix
-    - Uses CPD_ (Community, Partial Benefit Dual, Disabled) prefix
-    """
-    is_fbd = dual_code in FULL_BENEFIT_DUAL_CODES
-    is_pbd = dual_code in PARTIAL_BENEFIT_DUAL_CODES
+# ============================================================================
+# REF Segment Parsers (CA DHCS specific composites)
+# ============================================================================
 
-    return is_fbd, is_pbd
+def parse_ref_23(value: str, member: MemberContext) -> None:
+    """REF*23: Cin_Check_Digit;Fame_Card_Issue_Date;;..."""
+    member.cin_check_digit = get_composite_part(value, 0)
+    card_date = get_composite_part(value, 1)
+    if card_date and len(card_date) >= 8:
+        member.fame_card_issue_date = card_date[:8]
 
-def is_new_enrollee(coverage_start_date: Optional[str], reference_date: Optional[str] = None) -> bool:
-    """Determine if member is new enrollee (<= 3 months since coverage start)"""
-    if not coverage_start_date:
-        return False
 
-    try:
-        start_date = datetime.strptime(coverage_start_date, "%Y-%m-%d").date()
-        if reference_date:
-            ref_date = datetime.strptime(reference_date, "%Y-%m-%d").date()
-        else:
-            ref_date = date.today()
+def parse_ref_3h(value: str, member: MemberContext) -> None:
+    """REF*3H: County;AID_Code;Case_Number;;..."""
+    member.fame_county_id = get_composite_part(value, 0)
+    aid_code = get_composite_part(value, 1)
+    if aid_code and not member.medi_cal_aid_code:
+        member.medi_cal_aid_code = aid_code
+    member.case_number = get_composite_part(value, 2)
 
-        # Calculate months difference
-        months_diff = (ref_date.year - start_date.year) * 12 + (ref_date.month - start_date.month)
 
-        return months_diff <= 3
+def parse_ref_6o(value: str, member: MemberContext) -> None:
+    """REF*6O: ?;RES-ADDR-FLAG;REAS-ADD-IND;?;RES-ZIP-DELIV-CODE;?"""
+    member.res_addr_flag = get_composite_part(value, 1)
+    member.reas_add_ind = get_composite_part(value, 2)
+    zip_code = get_composite_part(value, 4)
+    if zip_code:
+        member.res_zip_deliv_code = strip_leading_zeros(zip_code)
+
+
+def parse_ref_dx(value: str, member: MemberContext) -> None:
+    """REF*DX: Fed_Contract_Number;Carrier_Code;Policy_Start;..."""
+    member.fed_contract_number = get_composite_part(value, 0)
+    carrier = get_composite_part(value, 1)
+    if carrier:
+        member.carrier_code = strip_leading_zeros(carrier)
+    policy_start = get_composite_part(value, 2)
+    if policy_start and len(policy_start) >= 8:
+        member.coverage_start_date = policy_start[:8]
+
+
+def parse_ref_17(value: str, member: MemberContext) -> None:
+    """REF*17: YYYYMM;;... (FAME redetermination date)"""
+    yyyymm = get_composite_part(value, 0)
+    if yyyymm and len(yyyymm) >= 6:
+        member.fame_redetermination_date = f"{yyyymm[:4]}-{yyyymm[4:6]}-01"
+
+
+# ============================================================================
+# Public API Functions
+# ============================================================================
+
+def enrollment_to_demographics(enrollment: EnrollmentData) -> Demographics:
+    """Convert EnrollmentData to Demographics model for risk calculation"""
+    return Demographics(
+        age=enrollment.age or 0,
+        sex=enrollment.sex or 'M',
+        dual_elgbl_cd=enrollment.dual_elgbl_cd,
+        orec=enrollment.orec or '',
+        crec=enrollment.crec or '',
+        new_enrollee=enrollment.new_enrollee,
+        snp=enrollment.snp,
+        low_income=enrollment.low_income,
+        lti=enrollment.lti
+    )
+
+
+def is_losing_medicaid(enrollment: EnrollmentData, within_days: int = 90) -> bool:
+    """Check if member will lose Medicaid within specified days"""
+    if not enrollment.coverage_end_date or not enrollment.has_medicaid:
+        return False
+    try:
+        end_date = datetime.strptime(enrollment.coverage_end_date, "%Y-%m-%d").date()
+        days_until_end = (end_date - date.today()).days
+        return 0 <= days_until_end <= within_days
     except (ValueError, AttributeError):
         return False
 
-def parse_834_enrollment(segments: List[List[str]]) -> List[EnrollmentData]:
-    """Extract enrollment and demographic data from 834 transaction
-
-    California DHCS Medi-Cal 834 Structure:
-    Loop 2000 - Member Level
-        INS - Member Level Detail (subscriber/dependent, maintenance type)
-        REF - Member Identifiers (0F, 1L, F6, 6P, ZZ, AB, ABB)
-        DTP - Date Time Periods (303, 348, 349, 338)
-        NM1 - Member Name (IL qualifier)
-        DMG - Demographics (DOB, Sex) ***CRITICAL***
-        HD  - Health Coverage ***CRITICAL FOR DUAL STATUS***
-    """
+
+def is_medicaid_terminated(enrollment: EnrollmentData) -> bool:
+    """Check if Medicaid coverage is being terminated (maintenance type 024)"""
+    return enrollment.maintenance_type == '024'
+
+
+def medicaid_status_summary(enrollment: EnrollmentData) -> Dict:
+    """Get summary of Medicaid coverage status for monitoring"""
+    return {
+        'member_id': enrollment.member_id,
+        'has_medicaid': enrollment.has_medicaid,
+        'has_medicare': enrollment.has_medicare,
+        'dual_status': enrollment.dual_elgbl_cd,
+        'is_full_benefit_dual': enrollment.is_full_benefit_dual,
+        'is_partial_benefit_dual': enrollment.is_partial_benefit_dual,
+        'coverage_end_date': enrollment.coverage_end_date,
+        'is_termination': is_medicaid_terminated(enrollment),
+        'losing_medicaid_30d': is_losing_medicaid(enrollment, 30),
+        'losing_medicaid_60d': is_losing_medicaid(enrollment, 60),
+        'losing_medicaid_90d': is_losing_medicaid(enrollment, 90)
+    }
+
+
+# ============================================================================
+# Main Parsing Logic
+# ============================================================================
+
+def _process_ref_segment(qualifier: str, value: str, member: MemberContext, in_hd_loop: bool) -> None:
+    """Process REF segment based on qualifier"""
+    # HD-loop specific
+    if in_hd_loop and member.current_hcp and qualifier == 'CE':
+        member.current_hcp.aid_codes = value
+        # Also set primary_aid_code from position 0 if not already set
+        if not member.primary_aid_code:
+            member.primary_aid_code = get_composite_part(value, 0)
+        return
+
+    # Member identifiers
+    if qualifier == '0F' and not member.member_id:
+        member.member_id = value
+    elif qualifier == 'ZZ' and not member.member_id:
+        member.member_id = value
+    elif qualifier == '6P':
+        member.mbi = value
+        member.has_medicare = True
+    elif qualifier == 'F6':
+        member.hic = value
+        if not member.mbi:
+            member.mbi = value
+        member.has_medicare = True
+    elif qualifier == '1D':
+        parts = [p for p in value.split(';') if p]
+        member.medicaid_id = parts[-1] if parts else value
+        member.has_medicaid = True
+    elif qualifier == '23':
+        parse_ref_23(value, member)
+        member.has_medicaid = True
+    # California Medi-Cal
+    elif qualifier == 'ABB':
+        member.medicare_status_code = value
+    elif qualifier == 'AB':
+        member.medi_cal_aid_code = value
+    # CA DHCS custom
+    elif qualifier == '3H':
+        parse_ref_3h(value, member)
+    elif qualifier == '6O':
+        parse_ref_6o(value, member)
+    elif qualifier == 'RB':
+        member.primary_aid_code = value
+    elif qualifier == 'CE' and not member.primary_aid_code:
+        # Fallback: get primary_aid_code from REF*CE position 0 if not set by REF*RB
+        member.primary_aid_code = get_composite_part(value, 0)
+    elif qualifier == 'ZX' and not member.fame_county_id:
+        member.fame_county_id = value
+    elif qualifier == '17':
+        if in_hd_loop:
+            member.client_reporting_cat = value
+        else:
+            parse_ref_17(value, member)
+    elif qualifier == 'DX':
+        parse_ref_dx(value, member)
+    # Dual eligibility
+    elif qualifier == 'F5' and value in VALID_DUAL_CODES:
+        member.dual_elgbl_cd = value
+    elif qualifier == 'DY' and value in VALID_CREC_VALUES:
+        member.crec = value
+    elif qualifier == 'EJ':
+        member.low_income = value.upper() in ('Y', 'YES', '1', 'TRUE')
+
+
+def _process_hd_segment(segment: List[str], member: MemberContext) -> None:
+    """Process HD (Health Coverage) segment"""
+    # Save previous HCP context
+    if member.current_hcp:
+        member.hcp_history.append(member.current_hcp)
+
+    member.current_hcp = HCPContext()
+
+    # Parse HCP code and status from HD04
+    plan_desc = get_segment_value(segment, 4, '')
+    if plan_desc and ';' in plan_desc:
+        parts = plan_desc.split(';')
+        if parts[0]:
+            hcp_code = strip_leading_zeros(parts[0])
+            member.current_hcp.hcp_code = hcp_code
+            if not member.hcp_code:
+                member.hcp_code = hcp_code
+        if len(parts) > 1 and parts[1]:
+            hcp_status = strip_leading_zeros(parts[1])
+            member.current_hcp.hcp_status = hcp_status
+            if not member.hcp_status:
+                member.hcp_status = hcp_status
+
+    # Detect coverage types from combined fields
+    insurance_line = get_segment_value(segment, 3, '')
+    insurance_type = get_segment_value(segment, 6, '')
+    combined = f"{insurance_line} {plan_desc} {insurance_type}"
+
+    if contains_any_keyword(combined, MEDICARE_KEYWORDS):
+        member.has_medicare = True
+    if contains_any_keyword(combined, MEDICAID_KEYWORDS):
+        member.has_medicaid = True
+    if contains_any_keyword(combined, SNP_KEYWORDS):
+        member.snp = True
+        if any(kw in combined.upper() for kw in ('D-SNP', 'DSNP', 'DUAL')):
+            member.has_medicare = True
+            member.has_medicaid = True
+    if contains_any_keyword(combined, LTI_KEYWORDS):
+        member.lti = True
+
+
+def _finalize_member(member: MemberContext, source: str, report_date: str) -> EnrollmentData:
+    """Convert MemberContext to EnrollmentData"""
+    if member.current_hcp:
+        member.hcp_history.append(member.current_hcp)
+        member.current_hcp = None
+
+    age = calculate_age(member.dob)
+    dual_code = determine_dual_status(member)
+    is_fbd, is_pbd = classify_dual_benefit_level(dual_code)
+    new_enrollee = is_new_enrollee(member.coverage_start_date)
+
+    hcp_history = [
+        HCPCoveragePeriod(
+            start_date=hcp.start_date, end_date=hcp.end_date,
+            hcp_code=hcp.hcp_code, hcp_status=hcp.hcp_status, aid_codes=hcp.aid_codes
+        )
+        for hcp in member.hcp_history
+    ]
+
+    return EnrollmentData(
+        source=source, report_date=report_date,
+        member_id=member.member_id, mbi=member.mbi, medicaid_id=member.medicaid_id,
+        hic=member.hic, cin_check_digit=member.cin_check_digit,
+        first_name=member.first_name, last_name=member.last_name, middle_name=member.middle_name,
+        dob=member.dob, age=age, sex=member.sex, race=member.race,
+        language=member.language, death_date=member.death_date,
+        address_1=member.address_1, address_2=member.address_2,
+        city=member.city, state=member.state, zip=member.zip, phone=member.phone,
+        maintenance_type=member.maintenance_type,
+        maintenance_reason_code=member.maintenance_reason_code,
+        benefit_status_code=member.benefit_status_code,
+        coverage_start_date=member.coverage_start_date,
+        coverage_end_date=member.coverage_end_date,
+        has_medicare=member.has_medicare, has_medicaid=member.has_medicaid,
+        dual_elgbl_cd=dual_code, is_full_benefit_dual=is_fbd, is_partial_benefit_dual=is_pbd,
+        medicare_status_code=member.medicare_status_code,
+        medi_cal_aid_code=member.medi_cal_aid_code,
+        fame_county_id=member.fame_county_id, case_number=member.case_number,
+        fame_card_issue_date=member.fame_card_issue_date,
+        fame_redetermination_date=member.fame_redetermination_date,
+        fame_death_date=member.fame_death_date, primary_aid_code=member.primary_aid_code,
+        carrier_code=member.carrier_code, fed_contract_number=member.fed_contract_number,
+        client_reporting_cat=member.client_reporting_cat,
+        res_addr_flag=member.res_addr_flag, reas_add_ind=member.reas_add_ind,
+        res_zip_deliv_code=member.res_zip_deliv_code,
+        orec=member.orec, crec=member.crec, snp=member.snp,
+        low_income=member.low_income, lti=member.lti, new_enrollee=new_enrollee,
+        hcp_code=member.hcp_code, hcp_status=member.hcp_status, amount=member.amount,
+        hcp_history=hcp_history
+    )
+
+
+def parse_834_enrollment(segments: List[List[str]], source: str = None, report_date: str = None) -> List[EnrollmentData]:
+    """Extract enrollment data from 834 transaction segments"""
     enrollments = []
     member = MemberContext()
+    in_hd_loop = False
 
     for segment in segments:
         if len(segment) < 2:
@@ -264,217 +512,140 @@ def parse_834_enrollment(segments: List[List[str]]) -> List[EnrollmentData]:
 
         seg_id = segment[0]
 
-        # ===== INS - Member Level Detail (Start of 2000 loop) =====
-        if seg_id == 'INS' and len(segment) >= 3:
-            # Save previous member before starting new one
+        # BGN - Source identifier
+        if seg_id == 'BGN' and len(segment) >= 3:
+            bgn_ref = get_segment_value(segment, 2)
+            if bgn_ref and '-' in bgn_ref:
+                parts = bgn_ref.split('-')
+                if len(parts) >= 2:
+                    source = f"{parts[0]}-{parts[1]}"
+                    if 'south la' in bgn_ref.lower():
+                        source = f"SLA-{source}"
+
+        # N1*IN - Plan name (for SLA prefix)
+        elif seg_id == 'N1' and get_segment_value(segment, 1) == 'IN':
+            plan_name = get_segment_value(segment, 2, '')
+            if 'South LA' in plan_name and source and not source.startswith('SLA-'):
+                source = f"SLA-{source}"
+
+        # INS - Start of member loop
+        elif seg_id == 'INS' and len(segment) >= 3:
             if member.member_id or member.has_medicare or member.has_medicaid:
-                enrollments.append(create_enrollment_data(member))
-
-            # Start new member
+                enrollments.append(_finalize_member(member, source, report_date))
             member = MemberContext()
-
-            # INS03 - Maintenance Type Code
+            in_hd_loop = False
             member.maintenance_type = get_segment_value(segment, 3)
-            # 001=Change, 021=Addition, 024=Cancellation/Term, 025=Reinstatement
+            member.maintenance_reason_code = get_segment_value(segment, 4)
+            member.benefit_status_code = get_segment_value(segment, 5)
 
-        # ===== REF - Reference Identifiers =====
+        # REF - Reference identifiers
         elif seg_id == 'REF' and len(segment) >= 3:
-            qualifier = segment[1]
-            value = segment[2] if len(segment) > 2 else None
-
-            if not value:
-                continue
-
-            # Standard REF qualifiers
-            if qualifier == '0F':  # Subscriber Number
-                if not member.member_id:
-                    member.member_id = value
-            elif qualifier == 'ZZ':  # Mutually Defined (often member ID or MBI)
-                if not member.member_id:
-                    member.member_id = value
-
-            # Medicare Identifiers
-            elif qualifier == '6P':  # Medicare MBI (new identifier)
-                member.mbi = value
-                member.has_medicare = True
-            elif qualifier == 'F6':  # Medicare HICN (legacy) or MBI
-                if not member.mbi:
-                    member.mbi = value
-                member.has_medicare = True
-
-            # Medicaid Identifiers
-            elif qualifier == '1D':  # Medicaid/Recipient ID
-                member.medicaid_id = parse_composite_ref_value(value)
-                member.has_medicaid = True
-            elif qualifier == '23':  # Medicaid Recipient ID (alternative)
-                if not member.medicaid_id:
-                    member.medicaid_id = parse_composite_ref_value(value)
-                member.has_medicaid = True
-
-            # California Medi-Cal Specific
-            elif qualifier == 'ABB':  # Medicare Status Code (QMB, SLMB, QI, etc.)
-                member.medicare_status_code = value
-            elif qualifier == 'AB':  # Aid Code (California specific)
-                member.medi_cal_aid_code = value
-
-            # Custom dual eligibility indicators
-            elif qualifier == 'F5':  # Dual Eligibility Code (custom)
-                if value in VALID_DUAL_CODES:
-                    member.dual_elgbl_cd = value
-            elif qualifier == 'DX':  # OREC (custom)
-                if value in VALID_OREC_VALUES:
-                    member.orec = value
-            elif qualifier == 'DY':  # CREC (custom)
-                if value in VALID_CREC_VALUES:
-                    member.crec = value
-            elif qualifier == 'EJ':  # Low Income Subsidy indicator
-                member.low_income = (value.upper() in ['Y', 'YES', '1', 'TRUE'])
-
-        # ===== NM1 - Member Name =====
-        elif seg_id == 'NM1' and len(segment) >= 4:
-            qualifier = segment[1]
-
-            if qualifier == 'IL':  # Insured or Subscriber
-                # NM109 = Identification Code (Member ID)
-                if len(segment) > 9:
-                    id_value = get_segment_value(segment, 9)
-                    if id_value and not member.member_id:
-                        member.member_id = id_value
-
-        # ===== DMG - Demographics ***CRITICAL SEGMENT*** =====
+            value = get_segment_value(segment, 2)
+            if value:
+                _process_ref_segment(segment[1], value, member, in_hd_loop)
+
+        # NM1*IL - Member name
+        elif seg_id == 'NM1' and get_segment_value(segment, 1) == 'IL':
+            member.last_name = get_segment_value(segment, 3)
+            member.first_name = get_segment_value(segment, 4)
+            member.middle_name = get_segment_value(segment, 5)
+            if len(segment) > 9:
+                id_val = get_segment_value(segment, 9)
+                if id_val and not member.member_id:
+                    member.member_id = id_val
+
+        # PER - Contact (phone)
+        elif seg_id == 'PER':
+            for i, val in enumerate(segment):
+                if val == 'TE' and i + 1 < len(segment):
+                    member.phone = segment[i + 1]
+                    break
+
+        # N3 - Address
+        elif seg_id == 'N3':
+            member.address_1 = get_segment_value(segment, 1)
+            member.address_2 = get_segment_value(segment, 2)
+
+        # N4 - City/State/Zip
+        elif seg_id == 'N4' and len(segment) >= 4:
+            city = get_segment_value(segment, 1)
+            state = get_segment_value(segment, 2)
+            # Strip state suffix from city if embedded
+            if city and state and city.upper().endswith(' ' + state.upper()):
+                city = city[:-len(state)-1].strip()
+            member.city = city.lower() if city else None
+            member.state = state.lower() if state else None
+            member.zip = get_segment_value(segment, 3)
+            # County code
+            if len(segment) > 6 and segment[5] == 'CY' and not member.fame_county_id:
+                member.fame_county_id = get_segment_value(segment, 6)
+
+        # LUI - Language
+        elif seg_id == 'LUI' and len(segment) >= 3:
+            lang_code = get_segment_value(segment, 2)
+            if lang_code:
+                member.language = LANGUAGE_CODES.get(lang_code.upper(), lang_code)
+
+        # DMG - Demographics
         elif seg_id == 'DMG' and len(segment) >= 3:
-            # DMG02 = Date of Birth
             dob_str = get_segment_value(segment, 2)
             if dob_str:
                 member.dob = parse_date(dob_str)
-
-            # DMG03 = Gender Code
             sex = get_segment_value(segment, 3)
             if sex in X12_SEX_CODE_MAPPING:
                 member.sex = X12_SEX_CODE_MAPPING[sex]
+            member.race = get_segment_value(segment, 5)
+            death_str = get_segment_value(segment, 6)
+            if death_str and len(death_str) >= 8:
+                member.death_date = parse_date(death_str[:8])
 
-        # ===== DTP - Date Time Periods =====
+        # DTP - Dates
         elif seg_id == 'DTP' and len(segment) >= 4:
-            date_qualifier = segment[1]
-            date_format = segment[2]
-            date_value = segment[3] if len(segment) > 3 else None
-
-            if not date_value or not date_format.endswith('D8'):
-                continue
-
-            parsed_date = parse_date(date_value[:8] if len(date_value) >= 8 else date_value)
-
-            if not parsed_date:
-                continue
+            qualifier = segment[1]
+            fmt = segment[2]
+            date_val = get_segment_value(segment, 3)
+            if date_val and fmt.endswith('D8'):
+                parsed = parse_date(date_val[:8] if len(date_val) >= 8 else date_val)
+                if parsed:
+                    if in_hd_loop and member.current_hcp:
+                        if qualifier == '348':
+                            member.current_hcp.start_date = parsed
+                            # Also set member-level coverage_start_date
+                            if not member.coverage_start_date:
+                                member.coverage_start_date = parsed
+                        elif qualifier == '349':
+                            member.current_hcp.end_date = parsed
+                            # Also set member-level coverage_end_date
+                            if not member.coverage_end_date:
+                                member.coverage_end_date = parsed
+                    else:
+                        if qualifier == '348' and not member.coverage_start_date:
+                            member.coverage_start_date = parsed
+                        elif qualifier == '349' and not member.coverage_end_date:
+                            member.coverage_end_date = parsed
+                        elif qualifier == '338':
+                            if not member.coverage_start_date:
+                                member.coverage_start_date = parsed
+                            member.has_medicare = True
+                        elif qualifier == '435':
+                            member.death_date = parsed
+                            member.fame_death_date = parsed
+
+        # HD - Health coverage
+        elif seg_id == 'HD' and len(segment) >= 4:
+            _process_hd_segment(segment, member)
+            in_hd_loop = True
 
-            # Date qualifiers
-            if date_qualifier == '348':  # Benefit Begin Date
-                member.coverage_start_date = parsed_date
-            elif date_qualifier == '349':  # Benefit End Date
-                member.coverage_end_date = parsed_date
-            elif date_qualifier == '338':  # Medicare Part A/B Effective Date
-                if not member.coverage_start_date:
-                    member.coverage_start_date = parsed_date
-                member.has_medicare = True
+        # AMT - Amount
+        elif seg_id == 'AMT' and len(segment) >= 3:
+            member.amount = get_segment_value(segment, 2)
 
-        # ===== HD - Health Coverage ***CRITICAL FOR DUAL STATUS*** =====
-        elif seg_id == 'HD' and len(segment) >= 4:
-            # HD03 = Insurance Line Code
-            insurance_line = get_segment_value(segment, 3, '').upper()
-
-            # HD04 = Plan Coverage Description
-            plan_desc = get_segment_value(segment, 4, '').upper()
-
-            # HD06 = Insurance Type Code
-            insurance_type = get_segment_value(segment, 6, '').upper()
-
-            # Combine all fields for pattern matching
-            combined = f"{insurance_line} {plan_desc} {insurance_type}"
-
-            # Detect Medicare coverage
-            if any(keyword in combined for keyword in [
-                'MEDICARE', 'MA', 'PART A', 'PART B', 'PART C', 'PART D',
-                'MEDICARE ADVANTAGE', 'MA-PD'
-            ]):
-                member.has_medicare = True
-
-            # Detect Medicaid/Medi-Cal coverage
-            if any(keyword in combined for keyword in [
-                'MEDICAID', 'MEDI-CAL', 'MEDI CAL', 'MEDIC-AID'
-            ]):
-                member.has_medicaid = True
-
-            # Detect SNP (Special Needs Plan)
-            if any(keyword in combined for keyword in [
-                'SNP', 'SPECIAL NEEDS', 'D-SNP', 'DSNP', 'DUAL ELIGIBLE SNP'
-            ]):
-                member.snp = True
-                # If it's a D-SNP, they are definitely dual eligible
-                if 'D-SNP' in combined or 'DSNP' in combined or 'DUAL' in combined:
-                    member.has_medicare = True
-                    member.has_medicaid = True
-
-            # Detect LTI (Long Term Institutionalized)
-            if any(keyword in combined for keyword in [
-                'LTC', 'LONG TERM CARE', 'LONG-TERM CARE', 'NURSING HOME',
-                'SKILLED NURSING', 'SNF', 'INSTITUTIONALIZED'
-            ]):
-                member.lti = True
-
-    # Don't forget last member
+    # Finalize last member
     if member.member_id or member.has_medicare or member.has_medicaid:
-        enrollments.append(create_enrollment_data(member))
+        enrollments.append(_finalize_member(member, source, report_date))
 
     return enrollments
 
-def create_enrollment_data(member: MemberContext) -> EnrollmentData:
-    """Convert MemberContext to EnrollmentData with risk adjustment fields"""
-
-    # Calculate age
-    age = calculate_age(member.dob) if member.dob else None
-
-    # Determine dual eligibility status
-    dual_code = determine_dual_status(member)
-
-    # Classify FBD vs PBD
-    is_fbd, is_pbd = classify_dual_benefit_level(dual_code)
-
-    # Determine new enrollee status
-    new_enrollee = is_new_enrollee(member.coverage_start_date)
-
-    return EnrollmentData(
-        # Identifiers
-        member_id=member.member_id,
-        mbi=member.mbi,
-        medicaid_id=member.medicaid_id,
-
-        # Demographics
-        dob=member.dob,
-        age=age,
-        sex=member.sex,
-
-        # Coverage tracking
-        maintenance_type=member.maintenance_type,
-        coverage_start_date=member.coverage_start_date,
-        coverage_end_date=member.coverage_end_date,
-
-        # Dual Eligibility
-        has_medicare=member.has_medicare,
-        has_medicaid=member.has_medicaid,
-        dual_elgbl_cd=dual_code,
-        is_full_benefit_dual=is_fbd,
-        is_partial_benefit_dual=is_pbd,
-        medicare_status_code=member.medicare_status_code,
-        medi_cal_aid_code=member.medi_cal_aid_code,
-
-        # Risk Adjustment
-        orec=member.orec,
-        crec=member.crec,
-        snp=member.snp,
-        low_income=member.low_income,
-        lti=member.lti,
-        new_enrollee=new_enrollee
-    )
 
 def extract_enrollment_834(content: str) -> List[EnrollmentData]:
     """Main entry point for 834 parsing
@@ -483,29 +654,51 @@ def extract_enrollment_834(content: str) -> List[EnrollmentData]:
         content: Raw X12 834 transaction file content
 
     Returns:
-        List of EnrollmentData objects with demographic and dual eligibility info
+        List of EnrollmentData objects
 
     Raises:
-        ValueError: If content is empty or invalid 834 format
+        ValueError: If content is empty or invalid format
     """
     if not content:
         raise ValueError("Input X12 834 data cannot be empty")
 
-    # Split content into segments
-    segments = [seg.strip().split('*')
-                for seg in content.split('~') if seg.strip()]
-
+    segments = [seg.strip().split('*') for seg in content.split('~') if seg.strip()]
     if not segments:
         raise ValueError("No valid segments found in 834 data")
 
-    # Validate transaction type from GS segment
-    transaction_type = None
+    # Validate 834 structure - must have ISA or ST*834 segment
+    segment_ids = {seg[0] for seg in segments if seg}
+    has_isa = 'ISA' in segment_ids
+    has_st_834 = any(
+        seg[0] == 'ST' and len(seg) > 1 and seg[1] == '834'
+        for seg in segments
+    )
+    if not has_isa and not has_st_834:
+        raise ValueError("Invalid or unsupported 834 format")
+
+    # Extract header info
+    source = None
+    report_date = None
+
     for segment in segments:
-        if segment[0] == 'GS' and len(segment) > 8:
-            transaction_type = TRANSACTION_TYPES.get(segment[8])
-            break
+        seg_id = segment[0]
 
-    if not transaction_type:
-        raise ValueError("Invalid or unsupported 834 format (missing GS segment or wrong version)")
+        if seg_id == 'ISA' and len(segment) > 9:
+            source = get_segment_value(segment, 6)
+            if source:
+                source = source.strip()
+            isa_date = get_segment_value(segment, 9)
+            if isa_date:
+                report_date = parse_yymmdd(isa_date)
+
+        elif seg_id == 'GS' and len(segment) > 4:
+            if not source:
+                source = get_segment_value(segment, 2)
+            gs_date = get_segment_value(segment, 4)
+            if gs_date and len(gs_date) >= 8:
+                report_date = f"{gs_date[:4]}-{gs_date[4:6]}-{gs_date[6:8]}"
+            if len(segment) > 8 and segment[8] not in TRANSACTION_TYPES:
+                raise ValueError("Invalid or unsupported 834 format")
+            break
 
-    return parse_834_enrollment(segments)
+    return parse_834_enrollment(segments, source, report_date)