Skip to main content

Table 3 Features of the Part D Dataset

From: Evaluating classifier performance with highly imbalanced Big Data

Feature name

Description

Prscrbr_Type

Derived from the Medicare provider/supplier specialty code; categorical, 249 distinct values

Prscrbr_Type_Src

Source of the Medicare provider/supplier specialty code; categorical, 2 distinct values

Brnd_Name

Brand name (trademarked name) of the drug filled; categorical, 3,907 distinct values

Gnrc_Name

A term referring to the chemical ingredient of a drug rather than the trademarked brand name under which the drug is sold; categorical, 22,72 distinct values

Tot_Clms

The number of Medicare Part D claims

Tot_30day_Fills

The aggregate number of Medicare Part D standardized 30-day fills

Tot_Day_Suply

The aggregate number of day’s supply for which this drug was dispensed

Tot_Drug_Cst

The aggregate drug cost paid for all associated claims

Tot_Benes

The total number of unique Medicare Part D beneficiaries with at least one claim for the drug