hccinfhir 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

hccinfhir-0.1.5.dist-info/RECORD

@@ -0,0 +1,49 @@
+hccinfhir/__init__.py,sha256=G_5m6jm3_BK5NdcZWoi0NEKJEsE_LjAU1RaLaL9xNPU,1043
+hccinfhir/datamodels.py,sha256=Vp64Blwq8qWe-q1slCK8jMO9SIErUgkXusGZ0laXiWo,5936
+hccinfhir/extractor.py,sha256=xL9c2VT-e2I7_c8N8j4Og42UEgVuCzyn9WFp3ntM5Ro,1822
+hccinfhir/extractor_837.py,sha256=Jhxb5glRA8Yi8lbRwdltggXCvr_84nlsZEMRIgxyy4A,13169
+hccinfhir/extractor_fhir.py,sha256=Rg_L0Vg5tz_L2VJ_jvZwWz6RMlPAkHwj4LiK-OWQvrQ,8458
+hccinfhir/filter.py,sha256=j_yD2g6RBXVUV9trKkWzsQ35x3fRvfKUPvEXKUefI64,2007
+hccinfhir/hccinfhir.py,sha256=6jvLoJF1TcqTGXbDA-_l3os6-xO68SKRr2l26LjzlgM,6982
+hccinfhir/model_calculate.py,sha256=fPhSqfxN9-9EPyp8z-O8XZWMXmLU6Hun7OhXAgsgDFw,5688
+hccinfhir/model_coefficients.py,sha256=ZsVY0S_X_BzDvcCmzCEf31v8uixbGmPAsR6nVEyCbIA,5530
+hccinfhir/model_demographics.py,sha256=7W5NLW7aAjpn25BJzqfP8iSouD9uA6epGguJJ6BPuC0,7043
+hccinfhir/model_dx_to_cc.py,sha256=guJny2Mb9z8YRNWCXGSIE3APbE06zwnA2NRkjAeUs60,1765
+hccinfhir/model_hierarchies.py,sha256=0kdBmF_8e_ikMHBDhlw2I7jT3DupHfUn6o5mWj7v3Yo,2910
+hccinfhir/model_interactions.py,sha256=Ev1m6d7cHpmlJ3xk6l0EHYCTIyPynbOMR9HnLPrtj_A,20344
+hccinfhir/samples.py,sha256=cqytZ-N08cPGqnUXJfzrEhhHW2qL7SDPYLD9-CHXZIU,8446
+hccinfhir/utils.py,sha256=AAHwzMSW8O9VZp1KLcdlN3OeBbxQtqQRtbTTdrKf7M0,2784
+hccinfhir/data/__init__.py,sha256=SGiSkpGrnxbvtEFMMlk82NFHOE50hFXcgKwKUSuVZUg,45
+hccinfhir/data/hcc_is_chronic.csv,sha256=eVVI4_8mQNkiBiNO3kattfT_zfcV18XgmiltdzZEXSo,17720
+hccinfhir/data/ra_coefficients_2025.csv,sha256=I0S2hoJlfig-D0oSFxy0b3Piv7m9AzOGo2CwR6bcQ9w,215191
+hccinfhir/data/ra_coefficients_2026.csv,sha256=0gfjGgVdIEWkBO01NaAbTLMzHCYINA0rf_zl8ojngCY,288060
+hccinfhir/data/ra_dx_to_cc_2025.csv,sha256=4N7vF6VZndkl7d3Fo0cGsbAPAZdCjAizSH8BOKsZNAo,1618924
+hccinfhir/data/ra_dx_to_cc_2026.csv,sha256=YT9HwQFUddL_bxuE9nxHWsBtZzojINL0DzABBMp6kms,1751007
+hccinfhir/data/ra_eligible_cpt_hcpcs_2023.csv,sha256=VVoA4s0hsFmcRIugyFdbvSoeLcn7M7z0DITT6l4YqL8,39885
+hccinfhir/data/ra_eligible_cpt_hcpcs_2024.csv,sha256=CawKImfCb8fFMDbWwqvNLRyRAda_u9N8Q3ne8QAAe54,40191
+hccinfhir/data/ra_eligible_cpt_hcpcs_2025.csv,sha256=-tMvv2su5tsSbGUh6fZZCMUEkXInBpcTtbUCi2o_UwI,40359
+hccinfhir/data/ra_eligible_cpt_hcpcs_2026.csv,sha256=EYGN7k_rgCpJe59lL_yNInUcCkdETDWGSFTXII3LZ0Y,40497
+hccinfhir/data/ra_hierarchies_2025.csv,sha256=HQSPNloe6mvvwMgv8ZwYAfWKkT2b2eUvm4JQy6S_mVQ,13045
+hccinfhir/data/ra_hierarchies_2026.csv,sha256=A6ZQZb0rpRWrySBB_KA5S4PGtMxWuzB2guU3aBE09v0,19596
+hccinfhir/sample_files/__init__.py,sha256=SGiSkpGrnxbvtEFMMlk82NFHOE50hFXcgKwKUSuVZUg,45
+hccinfhir/sample_files/sample_837_0.txt,sha256=eggrD259uHa05z2dfxWBpUDseSDp_AQcLyN_adpHyTw,5295
+hccinfhir/sample_files/sample_837_1.txt,sha256=E155MdemSDYoXokuTXUZ6Br_RGGedYv5t5dh-eMRmuk,1322
+hccinfhir/sample_files/sample_837_10.txt,sha256=zSJXI78vHAksA7FFQEVLvepefdpMM2_AexLyoDimV3Q,1129
+hccinfhir/sample_files/sample_837_11.txt,sha256=suVxlZEllEOy6dYgbzGIphKW6hDAKdYQTZFM3Ob84q4,817
+hccinfhir/sample_files/sample_837_12.txt,sha256=XpEacfnnd5SMYtgByVVbVP1Re1Vi-0t4g4egxzSYz_s,2885
+hccinfhir/sample_files/sample_837_2.txt,sha256=2bvXzaiopr7pO3D3pL7nLxcpgqKXrhu3lbulveJDJ-I,1125
+hccinfhir/sample_files/sample_837_3.txt,sha256=_B1Ktpsg7bOnA5BwZ7AUB0o7MME5AmLGuxzHq42FWok,1113
+hccinfhir/sample_files/sample_837_4.txt,sha256=jpzyiHKmRGMqN1ij9s1X4zRj0a2PXwtee4mjn4BRF3g,1077
+hccinfhir/sample_files/sample_837_5.txt,sha256=eYG4URk3zAr5UsnBKO5Wezo8dnL_HXGCMmXWJu0nxPA,1300
+hccinfhir/sample_files/sample_837_6.txt,sha256=pnKQf2cVcZpUl8PGeYzZxRxjKOMcISN2dBObIMtLx7E,1331
+hccinfhir/sample_files/sample_837_7.txt,sha256=5Y-x7ZA9d_qGaIrpVGfXKQBXqbxKiQ5CWOwEW1XGlds,1253
+hccinfhir/sample_files/sample_837_8.txt,sha256=J-zm0fzp6F19r2SWfHcCtab9ezd3c4YaSRO-RatJ-c4,1250
+hccinfhir/sample_files/sample_837_9.txt,sha256=nIIurZ0tLHw6ZfDM__U-WqV8Q0u4K3WP56-r3BnAEv8,1341
+hccinfhir/sample_files/sample_eob_1.json,sha256=_NGSVR2ysFpx-DcTvyga6dFCzhQ8Vi9fNzQEMPz5awU,3124
+hccinfhir/sample_files/sample_eob_2.json,sha256=FcnJcx0ApOczxjJ_uxVLzCep9THfNf4xs9Yf7hxk8e4,1769
+hccinfhir/sample_files/sample_eob_200.ndjson,sha256=CxpjeQ1DCMUzZILaM68UEhfxO0p45YGhDDoCZeq8PxU,1917986
+hccinfhir/sample_files/sample_eob_3.json,sha256=4BW4wOMBEEU9RDfJR15rBEvk0KNHyuMEh3e055y87Hc,2306
+hccinfhir-0.1.5.dist-info/METADATA,sha256=2FjYMUdQ67RQHeayhpmAhCuVyEGYSnUxcVbyC1mTn8w,21979
+hccinfhir-0.1.5.dist-info/WHEEL,sha256=C2FUgwZgiLbznR-k0b_5k3Ai_1aASOXDss3lzCUsUug,87
+hccinfhir-0.1.5.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+hccinfhir-0.1.5.dist-info/RECORD,,

hccinfhir/sample_utils.py

@@ -1,252 +0,0 @@
-"""
-Sample Data Module for HCCInFHIR
-
-This module provides easy access to sample data files for testing and demonstration purposes.
-End users can call functions to retrieve sample EOB (Explanation of Benefits) and 837 claim data.
-"""
-
-import importlib.resources
-import json
-from typing import List, Dict, Any, Union, Optional
-from pathlib import Path
-
-
-class SampleData:
-    """
-    A class that provides access to sample data files included with the HCCInFHIR package.
-    
-    This class allows end users to easily retrieve sample EOB and 837 claim data
-    for testing, development, and demonstration purposes.
-    """
-    
-    @staticmethod
-    def get_eob_sample(case_number: int = 1) -> Dict[str, Any]:
-        """
-        Retrieve a specific EOB sample by case number.
-        
-        Args:
-            case_number: The case number (1, 2, or 3). Default is 1.
-            
-        Returns:
-            A dictionary containing the EOB data
-            
-        Raises:
-            ValueError: If case_number is not 1, 2, or 3
-            FileNotFoundError: If the sample file cannot be found
-            
-        Example:
-            >>> sample_data = SampleData.get_eob_sample(1)
-            >>> print(sample_data['resourceType'])
-            'ExplanationOfBenefit'
-        """
-        if case_number not in [1, 2, 3]:
-            raise ValueError("case_number must be 1, 2, or 3")
-        
-        try:
-            with importlib.resources.open_text('hccinfhir.samples', f'sample_eob_{case_number}.json') as f:
-                return json.load(f)
-        except FileNotFoundError:
-            raise FileNotFoundError(f"Sample EOB case {case_number} not found")
-    
-    @staticmethod
-    def get_eob_sample_list(limit: Optional[int] = None) -> List[Dict[str, Any]]:
-        """
-        Retrieve a list of EOB samples from the large sample file.
-        
-        Args:
-            limit: Maximum number of samples to return. If None, returns all 200 samples.
-            
-        Returns:
-            A list of EOB data dictionaries
-            
-        Raises:
-            FileNotFoundError: If the sample file cannot be found
-            
-        Example:
-            >>> # Get first 10 samples
-            >>> samples = SampleData.get_eob_sample_list(limit=10)
-            >>> print(len(samples))
-            10
-            
-            >>> # Get all 200 samples
-            >>> all_samples = SampleData.get_eob_sample_list()
-            >>> print(len(all_samples))
-            200
-        """
-        try:
-            output = []
-            with importlib.resources.open_text('hccinfhir.samples', 'sample_eob_200.ndjson') as f:
-                for i, line in enumerate(f):
-                    if limit is not None and i >= limit:
-                        break
-                    eob_data = json.loads(line)
-                    output.append(eob_data)
-            return output
-        except FileNotFoundError:
-            raise FileNotFoundError("Sample EOB list file not found")
-    
-    @staticmethod
-    def get_837_sample(case_number: int = 0) -> str:
-        """
-        Retrieve a specific 837 claim sample by case number.
-        
-        Args:
-            case_number: The case number (0 through 11). Default is 0.
-            
-        Returns:
-            A string containing the 837 X12 claim data
-            
-        Raises:
-            ValueError: If case_number is not between 0 and 11
-            FileNotFoundError: If the sample file cannot be found
-            
-        Example:
-            >>> sample_837 = SampleData.get_837_sample(0)
-            >>> print("ISA" in sample_837)
-            True
-        """
-        if case_number < 0 or case_number > 11:
-            raise ValueError("case_number must be between 0 and 11")
-        
-        try:
-            with importlib.resources.open_text('hccinfhir.samples', f'sample_837_{case_number}.txt') as f:
-                return f.read()
-        except FileNotFoundError:
-            raise FileNotFoundError(f"Sample 837 case {case_number} not found")
-    
-    @staticmethod
-    def get_837_sample_list(case_numbers: Optional[List[int]] = None) -> List[str]:
-        """
-        Retrieve multiple 837 claim samples.
-        
-        Args:
-            case_numbers: List of case numbers to retrieve. If None, returns all 12 samples.
-            
-        Returns:
-            A list of 837 X12 claim data strings
-            
-        Raises:
-            ValueError: If any case_number is not between 0 and 11
-            FileNotFoundError: If any sample file cannot be found
-            
-        Example:
-            >>> # Get specific cases
-            >>> samples = SampleData.get_837_sample_list([0, 1, 2])
-            >>> print(len(samples))
-            3
-            
-            >>> # Get all samples
-            >>> all_samples = SampleData.get_837_sample_list()
-            >>> print(len(all_samples))
-            12
-        """
-        if case_numbers is None:
-            case_numbers = list(range(12))  # 0 through 11
-        
-        # Validate case numbers
-        for case_num in case_numbers:
-            if case_num < 0 or case_num > 11:
-                raise ValueError(f"case_number {case_num} must be between 0 and 11")
-        
-        output = []
-        for case_num in case_numbers:
-            try:
-                with importlib.resources.open_text('hccinfhir.samples', f'sample_837_{case_num}.txt') as f:
-                    output.append(f.read())
-            except FileNotFoundError:
-                raise FileNotFoundError(f"Sample 837 case {case_num} not found")
-        
-        return output
-    
-    @staticmethod
-    def list_available_samples() -> Dict[str, Any]:
-        """
-        Get information about all available sample data.
-        
-        Returns:
-            A dictionary containing information about available samples
-            
-        Example:
-            >>> info = SampleData.list_available_samples()
-            >>> print(info['eob_samples'])
-            ['sample_eob_1.json', 'sample_eob_2.json', 'sample_eob_3.json', 'sample_eob_200.ndjson']
-        """
-        return {
-            "eob_samples": [
-                "sample_eob_1.json",
-                "sample_eob_2.json", 
-                "sample_eob_3.json",
-                "sample_eob_200.ndjson"
-            ],
-            "eob_case_numbers": [1, 2, 3],
-            "eob_list_size": 200,
-            "837_samples": [f"sample_837_{i}.txt" for i in range(12)],
-            "837_case_numbers": list(range(12)),
-            "description": {
-                "eob": "Explanation of Benefits (FHIR resources) for testing HCC calculations",
-                "837": "X12 837 claim data for testing claim processing"
-            }
-        }
-
-
-# Convenience functions for easy access
-def get_eob_sample(case_number: int = 1) -> Dict[str, Any]:
-    """
-    Convenience function to get an EOB sample.
-    
-    Args:
-        case_number: The case number (1, 2, or 3). Default is 1.
-        
-    Returns:
-        A dictionary containing the EOB data
-    """
-    return SampleData.get_eob_sample(case_number)
-
-
-def get_eob_sample_list(limit: Optional[int] = None) -> List[Dict[str, Any]]:
-    """
-    Convenience function to get a list of EOB samples.
-    
-    Args:
-        limit: Maximum number of samples to return. If None, returns all 200 samples.
-        
-    Returns:
-        A list of EOB data dictionaries
-    """
-    return SampleData.get_eob_sample_list(limit)
-
-
-def get_837_sample(case_number: int = 0) -> str:
-    """
-    Convenience function to get an 837 claim sample.
-    
-    Args:
-        case_number: The case number (0 through 11). Default is 0.
-        
-    Returns:
-        A string containing the 837 X12 claim data
-    """
-    return SampleData.get_837_sample(case_number)
-
-
-def get_837_sample_list(case_numbers: Optional[List[int]] = None) -> List[str]:
-    """
-    Convenience function to get multiple 837 claim samples.
-    
-    Args:
-        case_numbers: List of case numbers to retrieve. If None, returns all 12 samples.
-        
-    Returns:
-        A list of 837 X12 claim data strings
-    """
-    return SampleData.get_837_sample_list(case_numbers)
-
-
-def list_available_samples() -> Dict[str, Any]:
-    """
-    Convenience function to get information about available samples.
-    
-    Returns:
-        A dictionary containing information about available samples
-    """
-    return SampleData.list_available_samples()

hccinfhir-0.1.3.dist-info/METADATA

@@ -1,390 +0,0 @@
-Metadata-Version: 2.3
-Name: hccinfhir
-Version: 0.1.3
-Summary: HCC Algorithm for FHIR Resources
-Project-URL: Homepage, https://github.com/mimilabs/hccinfhir
-Project-URL: Issues, https://github.com/mimilabs/hccinfhir/issues
-Author-email: Yubin Park <yubin.park@mimilabs.ai>
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Requires-Python: >=3.8
-Requires-Dist: pydantic>=2.10.3
-Description-Content-Type: text/markdown
-
-# `hccinfhir` (HCC in FHIR)
-A Python library for extracting standardized service-level data from FHIR ExplanationOfBenefit resources, with a focus on supporting HCC (Hierarchical Condition Category) risk adjustment calculations.
-
-## Features
-- Extract diagnosis codes, procedures, providers, and other key data elements from FHIR EOBs
-- Support for both BCDA (Blue Button 2.0) and standard FHIR R4 formats
-- Pydantic models for type safety and data validation
-- Standardized Service Level Data (SLD) output format
-- Multiple HCC model support (V22, V24, V28, ESRD V21, ESRD V24, RxHCC V08)
-- Flexible input options: FHIR EOBs, service data, or direct diagnosis codes
-
-
-## Installation
-```bash
-pip install hccinfhir
-```
-
-## Why FHIR-Based HCC Processing?
-Risk Adjustment calculations traditionally rely on processed claims data, leading to information loss and reconciliation challenges. `hccinfhir` processes FHIR resources directly because:
-- FHIR represents the source of truth with complete clinical and administrative data
-- Risk Adjustment requires multiple data elements beyond diagnosis codes
-- Direct processing eliminates data transformation errors and simplifies reconciliation
-
-## Data Model & Flexibility
-While built for native FHIR processing, `hccinfhir` works with any data source that can be transformed into the SLD (Service Level Data) format:
-
-```python
-sld = [{
-    "procedure_code": "99214",
-    "diagnosis_codes": ["E11.9", "I10"],
-    "claim_type": "71",
-    "provider_specialty": "01", 
-    "service_date": "2024-01-15"
-}, ...]
-```
-
-Or, for direct risk score calculation from a list of diagnosis codes, you only need the model name, diagnosis codes, and basic demographic factors:
-
-```python
-from hccinfhir.model_calculate import calculate_raf
-
-diagnosis_codes = ['E119', 'I509']  # Diabetes without complications, Heart failure
-age = 67
-sex = 'F'
-model_name = "CMS-HCC Model V24"
-
-result = calculate_raf(
-   diagnosis_codes=diagnosis_codes,
-   model_name=model_name,
-   age=age,
-   sex=sex
-)
-```
-
-
-For more details on the SLD format, see the `datamodels.py` file.
-
-## Sample Data
-
-The package includes comprehensive sample data for testing and demonstration purposes:
-
-```python
-from hccinfhir import (
-    get_eob_sample,
-    get_eob_sample_list,
-    get_837_sample,
-    get_837_sample_list,
-    list_available_samples
-)
-
-# Get individual EOB samples (cases 1, 2, or 3)
-eob_data = get_eob_sample(1)
-
-# Get multiple EOB samples (up to 200 available)
-eob_list = get_eob_sample_list(limit=10)
-
-# Get 837 claim samples (cases 0 through 11)
-claim_data = get_837_sample(0)
-
-# Get information about available samples
-info = list_available_samples()
-```
-
-For detailed usage examples, see the `examples/sample_data_usage.py` file.
-
-## Core Components
-
-### 1. Extractor Module
-Processes FHIR ExplanationOfBenefit resources to extract Minimum Data Elements (MDE):
-```python
-from hccinfhir.extractor import extract_sld, extract_sld_list
-
-sld = extract_sld(eob_data)  # Process single EOB
-
-sld_list = extract_sld_list([eob1, eob2])  # Process multiple EOBs
-```
-
-### 2. Filter Module
-Implements claim filtering rules:
-- Inpatient/outpatient criteria - Type of Bill + Eligible CPT/HCPCS
-- Professional service requirements - Eligible CPT/HCPCS
-- Provider validation (Not in scope for this release, applicable to RAPS)
-```python
-from hccinfhir.filter import apply_filter
-
-filtered_sld = apply_filter(sld_list)
-```
-
-
-### 3. Logic Module 
-Implements core HCC calculation logic:
-- Maps diagnosis codes to HCC categories
-- Applies hierarchical rules and interactions
-- Calculates final RAF scores
-- Integrates with standard CMS data files
-
-```python
-from hccinfhir.model_calculate import calculate_raf
-
-diagnosis_codes = ['E119', 'I509']  # Diabetes without complications, Heart failure
-result = calculate_raf(
-   diagnosis_codes=diagnosis_codes,
-   model_name="CMS-HCC Model V24",
-   age=67,
-   sex='F'
-)
-```
-
-### 4. HCCInFHIR Class
-The main processor class that integrates extraction, filtering, and calculation components:
-
-```python
-from hccinfhir.hccinfhir import HCCInFHIR
-from hccinfhir.datamodels import Demographics
-
-# Initialize with custom configuration
-hcc_processor = HCCInFHIR(
-    filter_claims=True,                                    # Enable claim filtering
-    model_name="CMS-HCC Model V28",                       # Choose HCC model version
-    proc_filtering_filename="ra_eligible_cpt_hcpcs_2025.csv",  # CPT/HCPCS filtering rules
-    dx_cc_mapping_filename="ra_dx_to_cc_2025.csv"         # Diagnosis to CC mapping
-)
-
-# Define beneficiary demographics
-demographics = {
-    age=67,
-    sex='F'
-}
-
-# Method 1: Process FHIR EOB resources
-raf_result = hcc_processor.run(eob_list, demographics)
-
-# Method 2: Process service level data
-service_data = [{
-    "procedure_code": "99214",
-    "claim_diagnosis_codes": ["E11.9", "I10"],
-    "claim_type": "71",
-    "service_date": "2024-01-15"
-}]
-raf_result = hcc_processor.run_from_service_data(service_data, demographics)
-
-# Method 3: Direct diagnosis processing
-diagnosis_codes = ['E119', 'I509']
-raf_result = hcc_processor.calculate_from_diagnosis(diagnosis_codes, demographics)
-
-# RAF Result contains:
-print(f"Risk Score: {raf_result['risk_score']}")
-print(f"HCC List: {raf_result['hcc_list']}")
-print(f"CC to Diagnosis Mapping: {raf_result['cc_to_dx']}")
-print(f"Applied Coefficients: {raf_result['coefficients']}")
-print(f"Applied Interactions: {raf_result['interactions']}")
-```
-
-The HCCInFHIR class provides three main processing methods:
-
-1. `run(eob_list, demographics)`: Process FHIR ExplanationOfBenefit resources
-   - Extracts service data from FHIR resources
-   - Applies filtering rules if enabled
-   - Calculates RAF scores using the specified model
-
-2. `run_from_service_data(service_data, demographics)`: Process standardized service data
-   - Accepts pre-formatted service level data
-   - Validates data structure using Pydantic models
-   - Applies filtering and calculates RAF scores
-
-3. `calculate_from_diagnosis(diagnosis_codes, demographics)`: Direct diagnosis processing
-   - Processes raw diagnosis codes without service context
-   - Useful for quick RAF calculations or validation
-   - Bypasses service-level filtering
-
-Each method returns a RAFResult containing:
-- Final risk score
-- List of HCCs
-- Mapping of condition categories to diagnosis codes
-- Applied coefficients and interactions
-- Processed service level data (when applicable)
-
-## Testing
-
-After installing `hatch`
-```bash
-$ hatch shell
-$ pip install -e .
-$ pytest tests/*
-``` 
-
-## Dependencies
-- Pydantic >= 2.10.3
-- Standard Python libraries
-
-## Research: FHIR BCDA and 837 Field Mapping Analysis
-
-### Core Identifiers
-| Field | 837 Source | FHIR BCDA Source | Alignment Analysis |
-|-------|------------|------------------|-------------------|
-| claim_id | CLM01 segment | eob.id | ✓ Direct mapping |
-| patient_id | NM109 when NM101='IL' | eob.patient.reference (last part after '/') | ✓ Aligned but different formats |
-
-### Provider Information
-| Field | 837 Source | FHIR BCDA Source | Alignment Analysis |
-|-------|------------|-------------------|-------------------|
-| performing_provider_npi | NM109 when NM101='82' and NM108='XX' | careTeam member with role 'performing'/'rendering' | ✓ Aligned |
-| billing_provider_npi | NM109 when NM101='85' and NM108='XX' | contained resources with NPI system identifier | ✓ Conceptually aligned |
-| provider_specialty | PRV03 when PRV01='PE' | careTeam member qualification with specialty system | ✓ Aligned but different code systems |
-
-### Claim Type Information
-| Field | 837 Source | FHIR BCDA Source | Alignment Analysis |
-|-------|------------|-------------------|-------------------|
-| claim_type | GS08 (mapped via CLAIM_TYPES) | eob.type with claim_type system | ✓ Aligned but different coding |
-| facility_type | CLM05-1 (837I only) | facility.extension with facility_type system | ✓ Aligned for institutional claims |
-| service_type | CLM05-2 (837I only) | extension or eob.type with service_type system | ✓ Aligned for institutional claims |
-
-### Service Line Information
-| Field | 837 Source | FHIR BCDA Source | Alignment Analysis |
-|-------|------------|-------------------|-------------------|
-| procedure_code | SV1/SV2 segment, element 2 | item.productOrService with pr system | ✓ Aligned |
-| ndc | LIN segment after service line | item.productOrService with ndc system or extension | ✓ Aligned but different locations |
-| quantity | SV1/SV2 element 4 | item.quantity.value | ✓ Direct mapping |
-| quantity_unit | SV1/SV2 element 5 | item.quantity.unit | ✓ Direct mapping |
-| service_date | DTP segment with qualifier 472 | item.servicedPeriod or eob.billablePeriod | ✓ Aligned |
-| place_of_service | SV1 element 6 | item.locationCodeableConcept with place_of_service system | ✓ Aligned |
-| modifiers | SV1/SV2 segment, additional qualifiers | item.modifier with pr system | ✓ Aligned |
-
-### Diagnosis Information
-| Field | 837 Source | FHIR BCDA Source | Alignment Analysis |
-|-------|------------|-------------------|-------------------|
-| linked_diagnosis_codes | SV1/SV2 diagnosis pointers + HI segment codes | item.diagnosisSequence + diagnosis lookup | ✓ Aligned but different structure |
-| claim_diagnosis_codes | HI segment codes | diagnosis array with icd10cm/icd10 systems | ✓ Aligned |
-
-### Additional Fields
-| Field | 837 Source | FHIR BCDA Source | Alignment Analysis |
-|-------|------------|-------------------|-------------------|
-| allowed_amount | Not available in 837 | item.adjudication with 'eligible' category | ⚠️ Only in FHIR |
-
-### Key Differences and Notes
-
-1. **Structural Differences**:
-   - 837 uses a segment-based approach with positional elements
-   - FHIR uses a nested object structure with explicit systems and codes
-
-2. **Code Systems**:
-   - FHIR explicitly defines systems for each code (via SYSTEMS constant)
-   - 837 uses implicit coding based on segment position and qualifiers
-
-3. **Data Validation**:
-   - FHIR implementation uses Pydantic models for validation
-   - 837 implements manual validation and parsing
-
-4. **Diagnosis Handling**:
-   - 837: Direct parsing from HI segment with position-based lookup
-   - FHIR: Uses sequence numbers and separate diagnosis array
-
-5. **Provider Information**:
-   - 837: Direct from NM1 segments with role qualifiers
-   - FHIR: Through careTeam structure with role coding
-
-### TODO: Enhancement Suggestions
-
-1. Consider adding validation for code systems in 837 parser to match FHIR's explicitness
-2. Standardize date handling between both implementations
-3. Add support for allowed_amount in 837 if available in different segments
-4. Consider adding more robust error handling in both implementations
-
-## Data Files
-
-`ra_dx_to_cc_mapping_2026.csv`
-```sql
-WITH latest_years AS (
-  SELECT 
-    model_name,
-    MAX(year) as latest_year
-  FROM mimi_ws_1.cmspayment.ra_dx_to_cc_mapping 
-  WHERE model_type = 'Initial'
-    AND year <= 2026  -- Don't go beyond 2026
-  GROUP BY model_name
-)
-SELECT 
-  r.diagnosis_code, 
-  r.cc, 
-  r.model_name
-FROM mimi_ws_1.cmspayment.ra_dx_to_cc_mapping r
-INNER JOIN latest_years l 
-  ON r.model_name = l.model_name 
-  AND r.year = l.latest_year
-WHERE r.model_type = 'Initial'
-ORDER BY r.model_name, r.diagnosis_code;
-```
-
-`ra_hierarchies_2026.csv`
-```sql
-WITH latest_dates AS (
-  SELECT 
-    model_domain,
-    model_version,
-    model_fullname,
-    MAX(eff_last_date) as latest_eff_last_date
-  FROM mimi_ws_1.cmspayment.ra_hierarchies 
-  GROUP BY model_domain, model_version, model_fullname
-)
-SELECT 
-  r.cc_parent, 
-  r.cc_child, 
-  r.model_domain, 
-  r.model_version, 
-  r.model_fullname
-FROM mimi_ws_1.cmspayment.ra_hierarchies r
-INNER JOIN latest_dates l 
-  ON r.model_domain = l.model_domain 
-  AND r.model_version = l.model_version
-  AND r.model_fullname = l.model_fullname
-  AND r.eff_last_date = l.latest_eff_last_date
-ORDER BY r.model_domain, r.model_version, r.model_fullname, r.cc_parent, r.cc_child;
-```
-
-`ra_coefficients_2026.csv`
-```sql
-WITH preferred_records AS (
-  SELECT 
-    model_domain,
-    model_version,
-    MAX(eff_last_date) as latest_eff_last_date
-  FROM mimi_ws_1.cmspayment.ra_coefficients
-  GROUP BY model_domain, model_version
-)
-SELECT 
-  r.coefficient,
-  r.value, 
-  r.model_domain, 
-  r.model_version
-FROM mimi_ws_1.cmspayment.ra_coefficients r
-INNER JOIN preferred_records p
-  ON r.model_domain = p.model_domain 
-  AND r.model_version = p.model_version
-  AND r.eff_last_date = p.latest_eff_last_date
-ORDER BY r.model_domain, r.model_version, r.coefficient;
-```   
-
-`ra_eligible_cpt_hcpcs_2026.csv`
-```sql
-SELECT DISTINCT cpt_hcpcs_code
-FROM mimi_ws_1.cmspayment.ra_eligible_cpt_hcpcs
-WHERE is_included = 'yes' AND YEAR(mimi_src_file_date) = 2025;
-```
-
-## Contributing
-Join us at [mimilabs](https://mimilabs.ai/signup). Reference data available in MIMILabs data lakehouse.
-
-## Publishing (only for those maintainers...)
-Inside the hatch
-```bash
-$ hatch build
-$ hatch publish
-```
-
-## License
-Apache License 2.0