arXiv subjects

Callandra Moore

Publications and source records attributed to Callandra Moore.

3 recordsLinked to original sources

arXiv2023

Pyclipse, a library for deidentification of free-text clinical notes

Automated deidentification of clinical text data is crucial due to the high cost of manual deidentification, which has been a barrier to sharing clinical text and the advancement of clinical natural language processing. However, creating effective automated deidentification tools faces several challenges, including issues in reproducibility due to differences in text processing, evaluation methods, and a lack of consistency across clinical domains and institutions. To address these challenges, we propose the pyclipse framework, a unified and configurable evaluation procedure to streamline the comparison of deidentification algorithms. Pyclipse serves as a single interface for running open-source deidentification algorithms on local clinical data, allowing for context-specific evaluation. To demonstrate the utility of pyclipse, we compare six deidentification algorithms across four public and two private clinical text datasets. We find that algorithm performance consistently falls short of the results reported in the original papers, even when evaluated on the same benchmark dataset. These discrepancies highlight the complexity of accurately assessing and comparing deidentification algorithms, emphasizing the need for a reproducible, adjustable, and extensible framework like pyclipse. Our framework lays the foundation for a unified approach to evaluate and improve deidentification tools, ultimately enhancing patient protection in clinical natural language processing.

cs.CL↗

arXiv2023

Evaluating the Decency and Consistency of Data Validation Tests Generated by LLMs

We investigated whether large language models (LLMs) can develop data validation tests. We considered 96 conditions each for both GPT-3.5 and GPT-4, examining different prompt scenarios, learning modes, temperature settings, and roles. The prompt scenarios were: 1) Asking for expectations, 2) Asking for expectations with a given context, 3) Asking for expectations after requesting a data simulation, and 4) Asking for expectations with a provided data sample. The learning modes were: 1) zero-shot, 2) one-shot, and 3) few-shot learning. We also tested four temperature settings: 0, 0.4, 0.6, and 1. And the two distinct roles were: 1) helpful assistant, 2) expert data scientist. To gauge consistency, every setup was tested five times. The LLM-generated responses were benchmarked against a gold standard data validation suite, created by an experienced data scientist knowledgeable about the data in question. We find there are considerable returns to the use of few-shot learning, and that the more explicit the data setting can be the better, to a point. The best LLM configurations complement, rather than substitute, the gold standard results. This study underscores the value LLMs can bring to the data cleaning and preparation stages of the data science workflow, but highlights that they need considerable evaluation by experienced analysts.

stat.ME↗

arXiv2023

Implementing Automated Data Validation for Canadian Political Datasets

This paper describes a series of automated data validation tests for datasets detailing charity financial information, political donations, and government lobbying in Canada. We motivate and document a series of 200 tests that check the validity, internal consistency, and external consistency of these datasets. We present preliminary findings after application of these tests to the political donations ($\approx10.1$ million observations) and lobbying ($\approx711,200$ observations) datasets, and to a sample of $\approx380,880$ observations from the charities datasets. We conclude with areas for future work and lessons learnt for others looking to implement automated data validation in their own workflows.

stat.ME↗