Table 1 Mixed known/unknown entity mapping

From: Iterative refinement and goal articulation to optimize large language models for clinical information extraction

Report Texta

Review of outside slides

A. Skin, abdomen

- Metastatic carcinoma, IHC profile suggestive of renal primary

B. Skin, upper back

- Metastatic carcinoma, IHC profile suggestive of renal primary

IHC slides are positive for CK7, … IHC stains were performed on block A2 and showed the following reactivity: PAX8 * Positive

Discordant Labels

X_block_X0_IHC_CK7: Positive

A_block_A2_IHC_PAX-8: Positive

A_block_A0_IHC_CK7: Positive

B_block_B0_IHC_CK7: Positive

A_block_A2_IHC_PAX-8: Positive

Context

- The initial schema instructed the use of specimen “X” as a stand-in when it is not clear which specimen was used for a test.

- In cases with multiple specimens of identical histology, for IHC tests lacking a specified specimen, the LLM would continue to provide a duplicate set of results for all specimens.

Addressing

Action

- A brief description of this situation along with a properly constructed output was added to the IHC/FISH segmentation II and standardization prompt. This new example provided additional reinforcement to maintain using X when specimen/block is not specified and the provided names only for the tests for which specimen/block correspondence is explicit.

Continued Error Severity Examples

- Major: If the duplicated set of results was returned for both A & B but B was benign tissue.

- Minor: Continued duplicated results, but only in the context of both specimens containing identical histology.

  1. aNote that report text details and exact wording for this example and all subsequent examples have been modified for brevity and to further enhance anonymity.