Papers by Iain Marshall
Automatically Summarizing Evidence from Clinical Trials: A Prototype Highlighting Current Challenges (2023.eacl-demo)
Copied to clipboard
| Challenge: | Existing systems that retrieve trial publications matching a query are inefficient and introduce unsupported statements. |
| Approach: | They propose a system that aims to automatically summarize evidence presented in the set of randomized controlled trials most relevant to a given query. |
| Outcome: | The proposed system retrieves trial publications matching a query specifying a combination of condition, intervention(s), and outcome(s) and ranks them according to sample size and estimated study quality. |
Summarizing, Simplifying, and Synthesizing Medical Evidence using GPT-3 (with Varying Success) (2023.acl-short)
Copied to clipboard
| Challenge: | Large language models are capable of producing high quality summaries of general domain news articles in few- and zero-shot settings, but it is unclear whether they are similarly capable in more specialized domains such as biomedicine. |
| Approach: | They use GPT-3 to generate single- and multi-document summaries of biomedical articles, given no supervision, using a set of annotations. |
| Outcome: | The proposed model outperforms fully supervised models in generic news summarization, but struggles to synthesize evidence across multiple documents. |
Paragraph-level Simplification of Medical Texts (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for simplification of medical texts are limited due to jargon and technical content. |
| Approach: | They propose to automate the simplification of medical texts by penalizing decoders for producing "jargon" terms. |
| Outcome: | The proposed method improves on existing heuristics by penalizing the decoder for producing "jargon" terms. |
Appraising the Potential Uses and Harms of LLMs for Medical Systematic Reviews (2023.emnlp-main)
Copied to clipboard
| Challenge: | Medical systematic reviews are time-consuming and often generate inaccurate outputs . authors: a model that generates scientific-sounding outputs can be unusable at best . |
| Approach: | They conduct interviews with systematic review experts to characterize perceived utility and risks of LLMs in medical evidence reviews. |
| Outcome: | a new study characterizes perceived utility and risks of medical evidence reviews . experts say they can assist in the writing process by drafting summaries, distilling information . authors say they expect the model to be more accurate and more reliable . |
Trialstreamer: Mapping and Browsing Medical Evidence in Real-Time (2020.acl-demos)
Copied to clipboard
| Challenge: | Trialstreamer extracts key pieces of information that clinicians need when appraising the literature . the highest-quality evidence to inform healthcare practice comes from randomized controlled trials . |
| Approach: | They propose a system that extracts key pieces of information from biomedical abstracts and combines them into a database of clinical trial reports. |
| Outcome: | The proposed system extracts descriptions of trial participants, treatments compared in each arm, and which outcomes were measured. |
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature (P18-1)
Copied to clipboard
| Challenge: | In 2015 alone, about 100 manuscripts describing randomized controlled trials for medical interventions were published every day. |
| Approach: | They propose a corpus of 5,000 medical articles annotated with demarcations of text spans that describe the Patient population enrolled, the Interventions studied and to what they were Compared, and the Outcomes measured. |
| Outcome: | The proposed corpus includes 5,000 medical articles describing clinical randomized controlled trials. |
Syntactic Patterns Improve Information Extraction for Medical Search (N18-2)
Copied to clipboard
| Challenge: | Medical professionals search the literature by specifying the type of patients, the medical intervention(s) and the outcome measure(s). |
| Approach: | They propose to exploit the availability of structured abstracts to extract medically relevant information from syntactic patterns. |
| Outcome: | The proposed models differ from the constituent unigrams in the extracted patterns, suggesting that they capture contextual information that is otherwise lost. |
Structured Multi-Label Biomedical Text Tagging via Attentive Neural Tree Decoding (D18-1)
Copied to clipboard
| Challenge: | Existing methods for tagging unstructured texts with arbitrary number of terms drawn from an ontology are lacking. |
| Approach: | They propose a model for tagging unstructured texts with an arbitrary number of terms drawn from an ontology. |
| Outcome: | The proposed model yields state-of-the-art results on the important task of assigning MeSH terms to biomedical abstracts. |