Gondy Leroy

Yue Guo, Wei Qiu, Gondy Leroy et al. · uw

Recent lay language generation systems have used Transformer models trained on a parallel corpus to increase health information accessibility. However, the applicability of these models is constrained by the limited size and topical breadth of available corpora. We introduce CELLS, the largest (63k pairs) and broadest-ranging (12 journals) parallel corpus for lay language generation. The abstract and the corresponding lay language summary are written by domain experts, assuring the quality of our dataset. Furthermore, qualitative evaluation of expert-authored plain language summaries has revealed background explanation as a key strategy to increase accessibility. Such explanation is challenging for neural models to generate because it goes beyond simplification by adding content absent from the source. We derive two specialized paired corpora from CELLS to address key challenges in lay language generation: generating background explanations and simplifying the original abstract. We adopt retrieval-augmented models as an intuitive fit for the task of background explanation generation, and show improvements in summary quality and simplicity while maintaining factual correctness. Taken together, this work presents the first comprehensive study of background explanation for lay language generation, paving the path for disseminating scientific knowledge to a broader audience. CELLS is publicly available at: https://github.com/LinguisticAnomalies/pls_retrieval.

Abigail E. Whitlock, Gondy Leroy, Fariba M. Donovan et al.

In medicine, machine learning (ML) datasets are often built using the International Classification of Diseases (ICD) codes. As new models are being developed, there is a need for larger datasets. However, ICD codes are intended for billing. We aim to determine how suitable ICD codes are for creating datasets to train ML models. We focused on a rare and common disease using the All of Us database. First, we compared the patient cohort created using ICD codes for Valley fever (coccidioidomycosis, CM) with that identified via serological confirmation. Second, we compared two similarly created patient cohorts for myocardial infarction (MI) patients. We identified significant discrepancies between these two groups, and the patient overlap was small. The CM cohort had 811 patients in the ICD-10 group, 619 patients in the positive-serology group, and 24 with both. The MI cohort had 14,875 patients in the ICD-10 group, 23,598 in the MI laboratory-confirmed group, and 6,531 in both. Demographics, rates of disease symptoms, and other clinical data varied across our case study cohorts.

Yue Guo, Tal August, Gondy Leroy et al.

While there has been significant development of models for Plain Language Summarization (PLS), evaluation remains a challenge. PLS lacks a dedicated assessment metric, and the suitability of text generation evaluation metrics is unclear due to the unique transformations involved (e.g., adding background explanations, removing jargon). To address these questions, our study introduces a granular meta-evaluation testbed, APPLS, designed to evaluate metrics for PLS. We identify four PLS criteria from previous work -- informativeness, simplification, coherence, and faithfulness -- and define a set of perturbations corresponding to these criteria that sensitive metrics should be able to detect. We apply these perturbations to extractive hypotheses for two PLS datasets to form our testbed. Using APPLS, we assess performance of 14 metrics, including automated scores, lexical features, and LLM prompt-based evaluations. Our analysis reveals that while some current metrics show sensitivity to specific criteria, no single method captures all four criteria simultaneously. We therefore recommend a suite of automated metrics be used to capture PLS quality along all relevant criteria. This work contributes the first meta-evaluation testbed for PLS and a comprehensive evaluation of existing metrics. APPLS and our evaluation code is available at https://github.com/LinguisticAnomalies/APPLS.

Chancellor R. Woolsey, Prakash Bisht, Joshua Rothman et al.

An important issue impacting healthcare is a lack of available experts. Machine learning (ML) models could resolve this by aiding in diagnosing patients. However, creating datasets large enough to train these models is expensive. We evaluated large language models (LLMs) for data creation. Using Autism Spectrum Disorders (ASD), we prompted ChatGPT and GPT-Premium to generate 4,200 synthetic observations to augment existing medical data. Our goal is to label behaviors corresponding to autism criteria and improve model accuracy with synthetic training data. We used a BERT classifier pre-trained on biomedical literature to assess differences in performance between models. A random sample (N=140) from the LLM-generated data was evaluated by a clinician and found to contain 83% correct example-label pairs. Augmenting data increased recall by 13% but decreased precision by 16%, correlating with higher quality and lower accuracy across pairs. Future work will analyze how different synthetic data traits affect ML outcomes.

Yue Guo, Jae Ho Sohn, Gondy Leroy et al. · uw

Plain language summaries (PLSs) are essential for facilitating effective communication between clinicians and patients by making complex medical information easier for laypeople to understand and act upon. Large language models (LLMs) have recently shown promise in automating PLS generation, but their effectiveness in supporting health information comprehension remains unclear. Prior evaluations have generally relied on automated scores that do not measure understandability directly, or subjective Likert-scale ratings from convenience samples with limited generalizability. To address these gaps, we conducted a large-scale crowdsourced evaluation of LLM-generated PLSs using Amazon Mechanical Turk with 150 participants. We assessed PLS quality through subjective Likert-scale ratings focusing on simplicity, informativeness, coherence, and faithfulness; and objective multiple-choice comprehension and recall measures of reader understanding. Additionally, we examined the alignment between 10 automated evaluation metrics and human judgments. Our findings indicate that while LLMs can generate PLSs that appear indistinguishable from human-written ones in subjective evaluations, human-written PLSs lead to significantly better comprehension. Furthermore, automated evaluation metrics fail to reflect human judgment, calling into question their suitability for evaluating PLSs. This is the first study to systematically evaluate LLM-generated PLSs based on both reader preferences and comprehension outcomes. Our findings highlight the need for evaluation frameworks that move beyond surface-level quality and for generation methods that explicitly optimize for layperson comprehension.

Arif Ahmed, Gondy Leroy, Stephen A. Rains et al.

Health literacy is crucial to supporting good health and is a major national goal. Audio delivery of information is becoming more popular for informing oneself. In this study, we evaluate the effect of audio enhancements in the form of information emphasis and pauses with health texts of varying difficulty and we measure health information comprehension and retention. We produced audio snippets from difficult and easy text and conducted the study on Amazon Mechanical Turk (AMT). Our findings suggest that emphasis matters for both information comprehension and retention. When there is no added pause, emphasizing significant information can lower the perceived difficulty for difficult and easy texts. Comprehension is higher (54%) with correctly placed emphasis for the difficult texts compared to not adding emphasis (50%). Adding a pause lowers perceived difficulty and can improve retention but adversely affects information comprehension.

Gondy Leroy, David Kauchak, Philip Harber et al.

Text and audio simplification to increase information comprehension are important in healthcare. With the introduction of ChatGPT, an evaluation of its simplification performance is needed. We provide a systematic comparison of human and ChatGPT simplified texts using fourteen metrics indicative of text difficulty. We briefly introduce our online editor where these simplification tools, including ChatGPT, are available. We scored twelve corpora using our metrics: six text, one audio, and five ChatGPT simplified corpora. We then compare these corpora with texts simplified and verified in a prior user study. Finally, a medical domain expert evaluated these texts and five, new ChatGPT simplified versions. We found that simple corpora show higher similarity with the human simplified texts. ChatGPT simplification moves metrics in the right direction. The medical domain expert evaluation showed a preference for the ChatGPT style, but the text itself was rated lower for content retention.

Gondy Leroy, Prakash Bisht, Sai Madhuri Kandula et al.

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition whose rising prevalence places increasing demands on a lengthy diagnostic process. Machine learning (ML) has shown promise in automating ASD diagnosis, but most existing models operate as black boxes and are typically trained on a single dataset, limiting their generalizability. In this study, we introduce a transparent and interpretable ML approach that leverages BioBERT, a state-of-the-art language model, to analyze unstructured clinical text. The model is trained to label descriptions of behaviors and map them to diagnostic criteria, which are then used to assign a final label (ASD or not). We evaluate transfer learning, the ability to transfer knowledge to new data, using two distinct real-world datasets. We trained on datasets sequentially and mixed together and compared the performance of the best models and their ability to transfer to new data. We also created a black-box approach and repeated this transfer process for comparison. Our transparent model demonstrated robust performance, with the mixed-data training strategy yielding the best results (97 % sensitivity, 98 % specificity). Sequential training across datasets led to a slight drop in performance, highlighting the importance of training data order. The black-box model performed worse (90 % sensitivity, 96 % specificity) when trained sequentially or with mixed data. Overall, our transparent approach outperformed the black-box approach. Mixing datasets during training resulted in slightly better performance and should be the preferred approach when practically possible. This work paves the way for more trustworthy, generalizable, and clinically actionable AI tools in neurodevelopmental diagnostics.

Abhay Kumara Sri Krishna Nandiraju, Gondy Leroy, David Kauchak et al.

Understanding health information is essential in achieving and maintaining a healthy life. We focus on simplifying health information for better understanding. With the availability of generative AI, the simplification process has become efficient and of reasonable quality, however, the algorithms remove information that may be crucial for comprehension. In this study, we compare generative AI to detect missing information in simplified text, evaluate its importance, and fix the text with the missing information. We collected 50 health information texts and simplified them using gpt-4-0613. We compare five approaches to identify missing elements and regenerate the text by inserting the missing elements. These five approaches involve adding missing entities and missing words in various ways: 1) adding all the missing entities, 2) adding all missing words, 3) adding the top-3 entities ranked by gpt-4-0613, and 4, 5) serving as controls for comparison, adding randomly chosen entities. We use cosine similarity and ROUGE scores to evaluate the semantic similarity and content overlap between the original, simplified, and reconstructed simplified text. We do this for both summaries and full text. Overall, we find that adding missing entities improves the text. Adding all the missing entities resulted in better text regeneration, which was better than adding the top-ranked entities or words, or random words. Current tools can identify these entities, but are not valuable in ranking them.

Sumi Lee, Gondy Leroy, David Kauchak et al.

This study investigates human and ChatGPT text simplification and its relationship to dependency distance. A set of 220 sentences, with increasing grammatical difficulty as measured in a prior user study, were simplified by a human expert and using ChatGPT. We found that the three sentence sets all differed in mean dependency distances: the highest in the original sentence set, followed by ChatGPT simplified sentences, and the human simplified sentences showed the lowest mean dependency distance.

Hoang Van, David Kauchak, Gondy Leroy

The goal of text simplification (TS) is to transform difficult text into a version that is easier to understand and more broadly accessible to a wide variety of readers. In some domains, such as healthcare, fully automated approaches cannot be used since information must be accurately preserved. Instead, semi-automated approaches can be used that assist a human writer in simplifying text faster and at a higher quality. In this paper, we examine the application of autocomplete to text simplification in the medical domain. We introduce a new parallel medical data set consisting of aligned English Wikipedia with Simple English Wikipedia sentences and examine the application of pretrained neural language models (PNLMs) on this dataset. We compare four PNLMs(BERT, RoBERTa, XLNet, and GPT-2), and show how the additional context of the sentence to be simplified can be incorporated to achieve better results (6.17% absolute improvement over the best individual model). We also introduce an ensemble model that combines the four PNLMs and outperforms the best individual model by 2.1%, resulting in an overall word prediction accuracy of 64.52%.