Large Language Models for Automated Icd-10 Coding of Obstetric Clinical Notes in Portuguese: Comparison With Human Coders
Santos RdS; Gazzola MG; Figueira PM; Luz AG; Pacagnella RdC; Torezzan C · 2026 · Preprint
WASTE classifies this as Negative / Null Result Report · AI classification, approximate
The study found no significant effect — useful as a negative control or null benchmark for your own design.
Abstract (excerpt)
Abstract Background Despite rapid advances in large language models (LLMs), automated ICD-10 coding of real-world clinical narratives remains unreliable. A key challenge lies not only in model limitations, but in the intrinsic ambiguity of…
Excerpt shown for reference under fair use — read the full paper at the publisher.
Hosted by the publisher — may require access.
About to run something similar?
Run an AI Precheck on your own design to catch failure modes like this one before you spend the time. Your first desk check is free.
Related failures
t-Test at the Probe Level: An Alternative Method to Identify Statistically Significant Genes for Microarray Data
Negative / Null Result ReportMeteorological Causes of the Secular Variations in Observed Extreme Precipitation Events for the Conterminous United States
Negative / Null Result ReportThe Next Generation of Sepsis Clinical Trial Designs
Negative / Null Result ReportAnalysis of DNA Methylation in Young People: Limited Evidence for an Association Between Victimization Stress and Epigenetic Variation in Blood
Negative / Null Result ReportStudy preregistration: an early example and analysis.
Negative / Null Result ReportInsights Into LSTM Fully Convolutional Networks for Time Series Classification
WASTE indexes this work — it does not host or republish it. Failure-type classification is automated and approximate.
Metadata source: Europe PMC · DOI 10.21203/rs.3.rs-8712058/v1