Excesso de medicamentos
Overview
Technical rule to detect potential excess of medication charges. This rule prepares input data, learns a simple linear scoring model from precomputed betas, estimates an expected cost (predict) given the account context, and flags charges whose paid value exceeds this estimate. It then computes suggested disallowances (glosas) and reasons. Attributes
Architecture
| Field | Value |
|---|---|
| Name | Excesso de medicamentos |
| Agent ID | C047 |
| Version | 2 |
| Nature | tech |
| Layer | — |
Inheritance
RuleExcessiveMedication → BaseAgent → BaseAgent
Core Functionality
- load_artifacts
- prepare_data
- rule_assessment
- scoring
- motivo_glosa
Business Rules
Comportamento da cobrança
Consultar código-fonte para regras de negócio detalhadas.
Usage
from agents.ruleexcessivemedication import RuleExcessiveMedication
rule = RuleExcessiveMedication()
violations_df = rule.rule_assessment(claims_df)
Configuration
Sem parâmetros configuráveis identificados.
Input Requirements
Consultar expected_input_columns no código-fonte.
Output Format
Glosa DataFrame Columns
| Column | Description |
|---|---|
agent_id |
C047 |
version |
2 |
id_arvo |
Original record ID |
vl_glosa_arvo |
Glosa value |
qt_glosa_arvo |
Glosa quantity |
score_arvo |
Confidence score |
motivo_glosa_arvo |
Detailed reason in Portuguese |
motivo_glosa_ANS |
ANS standard code |
data_dict |
JSON metadata with calculation details |
Error Handling
- DataFrames vazios retornam estrutura vazia com colunas obrigatórias.
- Colunas ausentes geram warning mas não causam crash.
- Conversões numéricas usam
errors="coerce"para evitar falhas.