The Verbose Context Problem in Medical Records
For researchers working on large-scale medical record analysis, this paper highlights a critical bottleneck and provides a benchmark to drive future work.
The paper identifies the verbose context problem in medical records, where token-inefficient representations hinder population health analysis, and introduces PopMedQA, a benchmark to isolate this issue. Experiments show that domain-independent methods fail to address the problem, highlighting the need for domain-specific solutions.
The verbose context problem occurs when structured concepts have token-inefficient textual representations. This bottleneck is acute in population health: cohort-level analysis of longitudinal patient records requires reasoning over thousands of medically-coded events, often exceeding 400K tokens in total. We present PopMedQA, a benchmark isolating this problem through computational tasks on groups of longitudinal patient records. We construct the benchmark using neopatient, a new library for language-controlled generation of artificial patient records. Through extensive ablations -- including prompting strategies, prompt compression, and agentic decomposition -- we find that domain-independent methods fail to alleviate the verbose context problem. There remains significant opportunity to exploit domain-specific structure in language model inputs for population-scale reasoning.