Scoring Transcription Accuracy

Scoring Transcription Accuracy

Similar to Field ID QA, the machine measures transcription accuracy by establishing Quality Assurance (QA) consensus; consensus means that two entries for a given field must have matching normalized transcriptions. In other words, when the transcription of the machine (with high confidence) or that of a data keyer matches what is determined in QA consensus, then the data keyer or the machine is marked as accurate.

With Release 25.0.0, the system scores every human entry for Field ID. However, as in previous releases, there are specific instances where this is not the case:

Scoring transcription

Here are a few example scenarios: Example 1

Extraction source Entry Accuracy
Machine William Zamora DDS Accurate
QA (Keyer 1) William Zamora DDS Accurate
Consensus William Zamora DDS --

Example 2

Extraction source Entry Accuracy
Machine William Zamora OOS
(low confidence)
Not Measured
Supervision Transcription (Keyer 1) William Zamora DDS Accurate
QA (Keyer 2) William Zamora ODS Inaccurate
QA (Keyer 3) William Zamora DDS Accurate
Consensus William Zamora DDS

Example 3

Extraction source Entry Accuracy
Machine William Zamora 00S
(low confidence)
Not Measured
Supervision (Keyer 1) William Zamora DDS Accurate
QA (Keyer 2) William Zamora DDS Accurate
Consensus William Zamora DDS --

QA consensus can be established without generating additional tasks if the previous Supervision entries established consensus. Here is an example of that scenario:

Example 4

Extraction source Entry Accuracy
Machine William Zamora DDS
(low confidence)
Not Measured
Supervision (keyer 1) William Zamora DDS Accurate
Consensus William Zamora DDS --

Abandoned fields

There are two situations where a field may be abandoned and therefore have its corresponding entries not counted towards accuracy reporting:

  1. A QA field is abandoned if no consensus is reached after 3 human entries. If the field was sent to Supervision, the Supervision entry would count towards the total 3.

Example 1

Extraction source Entry Accuracy
Machine William Zamora 00S Abandoned
QA (keyer 1) William Zamora DDS Abandoned
QA (keyer 2) William Zamora OOS Abandoned
QA (keyer 3) *illegible* Abandoned
Consensus -- --

Example2

Extraction source Entry Accuracy
Machine William Zamora 00S Abandoned
QA (keyer 1) *illegible* Abandoned
QA (keyer 2) *illegible* Abandoned
Consensus -- --