Evaluating natural language generation (NLG) systems in the medical domain presents unique challenges due to the critical demands for accuracy, relevance, and domain-specific expertise. Traditional automatic evaluation metrics, such as BLEU, ROUGE, and BERTScore, often fall short in distinguishing between high-quality outputs, especially given the open-ended nature of medical question answering (QA) tasks where multiple valid responses may exist. In this work, we introduce MORQA (Medical Open-Response QA), a new multilingual benchmark designed to assess the effectiveness of NLG evaluation metrics across three medical visual and text-based QA datasets in English and Chinese. Unlike prior resources, our datasets feature 2-4+ gold-standard answers authored by medical professionals, along with expert human ratings for three English and Chinese subsets. We benchmark both traditional metrics and large language model (LLM)-based evaluators, such as GPT-4 and Gemini, finding that LLM-based approaches significantly outperform traditional metrics in correlating with expert judgments. We further analyze factors driving this improvement, including LLMs' sensitivity to semantic nuances and robustness to variability among reference answers. Our results provide the first comprehensive, multilingual qualitative study of NLG evaluation in the medical domain, highlighting the need for human-aligned evaluation methods. All datasets and annotations will be publicly released to support future research.

OBJECTIVE: Introduce the task of wound care multimodal multilingual visual question answering, provide baseline performances, and identify areas of future study. METHODS: A dataset of wound care multimodal multilingual visual question answering (VQA) was created using consumer health questions asked online. Practicing US medical doctors were tasked with providing metadata and expert responses labels. Several instruct-enabled, multilingual visual question answering models (GPT-4o, Gemini-1.5-Pro, and Qwen-VL) were tested to benchmark performances. Finally, automatic evaluations were tested against domain expert response ratings. RESULTS: A multilingual dataset of 477 wound care cases, 768 responses, 748 images, 3k structured data labels, 1362 translation instances, and 10k judgments was constructed (https://osf.io/xsj5u/). Metadata scores ranged from 0.32-0.78 accuracy depending on classification type; response generation performances 0.06 BLEU, 0.66 BERTScore, 0.45 ROUGE-L in English and 0.12 BLEU, 0.69 BERTScore, and 0.50 ROUGE-L in Chinese. CONCLUSION: We construct and explore the tasks of multimodal, multilingual VQA. We hope the work here can inspire further research in wound care metadata classification, VQA response generation, and open response automatic evaluation.

Unpredictability, especially unpredictability with unknown error characteristics, is a highly undesirable trait, particularly in medical patient care applications. Although large pre-trained language models (LLM) have been applied to a variety of unseen tasks with highly competitive and successful results, their sensitivity to language inputs and resulting performance variability is not well-studied. In this work, we test state-of-the-art pre-trained language models from a variety of families to characterize their error generation and reliability in medical assessment ability. Particularly, we experiment with general medical assessment multiple choice tests, as well as their open-ended and true-false alternatives. We also profile model consistency, error agreements with each other and to humans; and finally, quantify their ability to recover and explain errors. The findings in this work can be used to give further information about medical models so that modelers can make better-informed decisions rather than relying on standalone performance metrics alone.

Medical doctors spend on average 52 to 102 minutes per day writing clinical notes from their patient encounters (Hripcsak et al., 2011).Reducing this workload calls for relevant and efficient summarization methods.In this paper, we introduce new resources and empirical investigations for the automatic summarization of doctor-patient conversations in a clinical setting.In particular, we introduce the MTS-DIALOG dataset; a new collection of 1,700 doctor-patient dialogues and corresponding clinical notes.We use this new dataset to investigate the feasibility of this task and the relevance of existing language models, data augmentation, and guided summarization techniques.We compare standard evaluation metrics based on n-gram matching, contextual embeddings, and Fact Extraction to assess the accuracy and the factual consistency of the generated summaries.To ground these results, we perform an expert-based evaluation using relevant natural language generation criteria and task-specific criteria such as critical omissions, and study the correlation between the automatic metrics and expert judgments.To the best of our knowledge, this study is the first attempt to introduce an open dataset of doctor-patient conversations and clinical notes, with detailed automated and manual evaluations of clinical note generation.

For every patient’s visit to a clinician, a clinical note is generated documenting their medical conversation, including complaints discussed, treatments, and medical plans. Despite advances in natural language processing, automating clinical note generation from a clinic visit conversation is a largely unexplored area of research. Due to the idiosyncrasies of the task, traditional methods of corpus creation are not effective enough approaches for this problem. In this paper, we present an annotation methodology that is content- and technique- agnostic while associating note sentences to sets of dialogue sentences. The sets can further be grouped with higher order tags to mark sets with related information. This direct linkage from input to output decouples the annotation from specific language understanding or generation strategies. Here we provide data statistics and qualitative analysis describing the unique annotation challenges. Given enough annotated data, such a resource would support multiple modeling methods including information extraction with template language generation, information retrieval type language generation, or sequence to sequence modeling.

Radiology reports contain vital diagnostic information that characterizes patient disease progression. However, information from reports is represented in free text, which is difficult to query against for secondary use. Automatic extraction of important information, such as tumor events using natural language processing, offers possibilities in improved clinical decision support, cohort identification, and retrospective evidence‐based research for cancer patients. The goal of this work was to classify tumor event attributes: negation, temporality, and malignancy, using biomedical ontology and linguistically enriched features. We report our results on an annotated corpus of 101 hepatocellular carcinoma patient radiology reports, and show that the improved classification improves overall template structuring. Classification performances for negation identification, past temporality classification, and malignancy classification were at 0.94, 0.62, and 0.77 F1, respectively. Incorporating the attributes into full templates led to an improvement of 0.72 F1 for tumor‐related events over a baseline of 0.65 F1. Improvement of negation, malignancy, and temporality classifications led to significant improvements in template extraction for the majority of categories. We present our machine‐learning approach to identifying these several tumor event attributes from radiology reports, as well as highlight challenges and areas for improvement.