Abstract:This paper investigates the feasibility of using pre-trained generative Large Language Models (LLMs) to automate the assignment of ICD-10 codes to historical causes of death. Due to the complex narratives often found in historical causes of death, this task has traditionally been manually performed by coding experts. We evaluate the ability of GPT-3.5, GPT-4, and Llama 2 LLMs to accurately assign ICD-10 codes on the HiCaD dataset that contains causes of death recorded in the civil death register entries of 19,361 individuals from Ipswich, Kilmarnock, and the Isle of Skye from the UK between 1861-1901. Our findings show that GPT-3.5, GPT-4, and Llama 2 assign the correct code for 69%, 83%, and 40% of causes, respectively. However, we achieve a maximum accuracy of 89% by standard machine learning techniques. All LLMs performed better for causes of death that contained terms still in use today, compared to archaic terms. Also they perform better for short causes (1-2 words) compared to longer causes. LLMs therefore do not currently perform well enough for historical ICD-10 code assignment tasks. We suggest further fine-tuning or alternative frameworks to achieve adequate performance.
Abstract:Machine learning methods have proven useful in transcribing historical data. However, results from even highly accurate methods require manual verification and correction. Such manual review can be time-consuming and expensive, therefore the objective of this paper was to make it more efficient. Previously, we used machine learning to transcribe 2.3 million handwritten occupation codes from the Norwegian 1950 census with high accuracy (97%). We manually reviewed the 90,000 (3%) codes with the lowest model confidence. We allocated those 90,000 codes to human reviewers, who used our annotation tool to review the codes. To assess reviewer agreement, some codes were assigned to multiple reviewers. We then analyzed the review results to understand the relationship between accuracy improvements and effort. Additionally, we interviewed the reviewers to improve the workflow. The reviewers corrected 62.8% of the labels and agreed with the model label in 31.9% of cases. About 0.2% of the images could not be assigned a label, while for 5.1% the reviewers were uncertain, or they assigned an invalid label. 9,000 images were independently reviewed by multiple reviewers, resulting in an agreement of 86.43% and disagreement of 8.96%. We learned that our automatic transcription is biased towards the most frequent codes, with a higher degree of misclassification for the lowest frequency codes. Our interview findings show that the reviewers did internal quality control and found our custom tool well-suited. So, only one reviewer is needed, but they should report uncertainty.