A critical assessment of using ChatGPT for extracting structured data from clinical notes.

Existing natural language processing (NLP) methods to convert free-text clinical notes into structured data often require problem-specific annotations and model training. This study aims to evaluate ChatGPT's capacity to extract information from free-text medical notes efficiently and comprehensively. We developed a large language model (LLM)-based workflow, utilizing systems engineering methodology and spiral "prompt engineering" process, leveraging OpenAI's API for batch querying ChatGPT. We evaluated the effectiveness of this method using a dataset of more than 1000 lung cancer pathology reports and a dataset of 191 pediatric osteosarcoma pathology reports, comparing the ChatGPT-3.5 (gpt-3.5-turbo-16k) outputs with expert-curated structured data. ChatGPT-3.5 demonstrated the ability to extract pathological classifications with an overall accuracy of 89%, in lung cancer dataset, outperforming the performance of two traditional NLP methods. The performance is influenced by the design of the instructive prompt. Our case analysis shows that most misclassifications were due to the lack of highly specialized pathology terminology, and erroneous interpretation of TNM staging rules. Reproducibility shows the relatively stable performance of ChatGPT-3.5 over time. In pediatric osteosarcoma dataset, ChatGPT-3.5 accurately classified both grades and margin status with accuracy of 98.6% and 100% respectively. Our study shows the feasibility of using ChatGPT to process large volumes of clinical notes for structured information extraction without requiring extensive task-specific human annotation and model training. The results underscore the potential role of LLMs in transforming unstructured healthcare data into structured formats, thereby supporting research and aiding clinical decision-making.

Thyrotoxic Periodic Paralysis in a Young Hispanic Male With Newly Diagnosed Grave's Disease.

Thyrotoxic periodic paralysis (TPP) is a unique cause of hypokalemia from transcellular shift into muscle in the setting of active thyrotoxicosis. It is essential to recognize TPP, given the specific management considerations, which would otherwise easily go unaddressed. TPP can also be clinically indistinguishable from other causes of hypokalemia. In particular, familial periodic paralysis can present similar to TPP. This case illustrates a young Hispanic male who presented with paralysis and was found to be hypokalemic. Patient was also found to have thyromegaly with further testing consistent with Grave's disease, despite no hyperthyroid symptoms. Ultimately, identifying TPP early will allow for swift and appropriate treatment, avoid unnecessary interventions and testing, and reduce cost of care.