Kirk Roberts
YOU?
Author Swipe
View article: Context Matching is not Reasoning: Assessing Generalized Evaluation of Generative Language Models in Clinical Settings
Context Matching is not Reasoning: Assessing Generalized Evaluation of Generative Language Models in Clinical Settings Open
Current discussion surrounding the clinical capabilities of generative language models (GLMs) predominantly center around multiple-choice question-answer (MCQA) benchmarks derived from clinical licensing examinations. While accepted for hu…
View article: A Multi-Modal Pelvic MRI Dataset for Deep Learning-Based Pelvic Organ Segmentation in Endometriosis
A Multi-Modal Pelvic MRI Dataset for Deep Learning-Based Pelvic Organ Segmentation in Endometriosis Open
Endometriosis affects approximately 190 million females of reproductive age worldwide. Magnetic Resonance Imaging (MRI) has been recommended as the primary non-invasive diagnostic method for endometriosis. This study presents new female pe…
View article: Correction: Toward Personalized Digital Experiences to Promote Diabetes Self-Management: Mixed Methods Social Computing Approach
Correction: Toward Personalized Digital Experiences to Promote Diabetes Self-Management: Mixed Methods Social Computing Approach Open
View article: Synthesized Annotation Guidelines are Knowledge-Lite Boosters for Clinical Information Extraction
Synthesized Annotation Guidelines are Knowledge-Lite Boosters for Clinical Information Extraction Open
Generative information extraction using large language models, particularly through few-shot learning, has become a popular method. Recent studies indicate that providing a detailed, human-readable guideline-similar to the annotation guide…
View article: Leveraging large language models for knowledge-free weak supervision in clinical natural language processing
Leveraging large language models for knowledge-free weak supervision in clinical natural language processing Open
The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning o…
View article: Toward Personalized Digital Experiences to Promote Diabetes Self-Management: Mixed Methods Social Computing Approach
Toward Personalized Digital Experiences to Promote Diabetes Self-Management: Mixed Methods Social Computing Approach Open
Background Type 2 diabetes affects nearly 34.2 million adults and is the seventh leading cause of death in the United States. Digital health communities have emerged as avenues to provide social support to individuals engaging in diabetes …
View article: P307: Smart categories: LLM-based automatic tagging of categorical information in genomic articles outperforms manual curators yielding improved curation efficiency
P307: Smart categories: LLM-based automatic tagging of categorical information in genomic articles outperforms manual curators yielding improved curation efficiency Open
View article: Overview of TREC 2024 Biomedical Generative Retrieval (BioGen) Track
Overview of TREC 2024 Biomedical Generative Retrieval (BioGen) Track Open
With the advancement of large language models (LLMs), the biomedical domain has seen significant progress and improvement in multiple tasks such as biomedical question answering, lay language summarization of the biomedical literature, cli…
View article: A Natural Language Processing Tool for Extracting Medication Adherence Information from Electronic Health Records
A Natural Language Processing Tool for Extracting Medication Adherence Information from Electronic Health Records Open
View article: LLM-IE: A Python Package for Generative Information Extraction with Large Language Models
LLM-IE: A Python Package for Generative Information Extraction with Large Language Models Open
Objectives: Despite the recent adoption of large language models (LLMs) for biomedical information extraction, challenges in prompt engineering and algorithms persist, with no dedicated software available. To address this, we developed LLM…
View article: Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?
Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models? Open
Backgrounds: Information extraction (IE) is critical in clinical natural language processing (NLP). While large language models (LLMs) excel on generative tasks, their performance on extractive tasks remains debated. Methods: We investigat…
View article: Quantitatively assessing the impact of the quality of SNOMED CT subtype hierarchy on cohort queries
Quantitatively assessing the impact of the quality of SNOMED CT subtype hierarchy on cohort queries Open
Objective SNOMED CT provides a standardized terminology for clinical concepts, allowing cohort queries over heterogeneous clinical data including Electronic Health Records (EHRs). While it is intuitive that missing and inaccurate subtype (…
View article: A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients
A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients Open
Generating discharge summaries is a crucial yet time-consuming task in clinical practice, essential for conveying pertinent patient information and facilitating continuity of care. Recent advancements in large language models (LLMs) have s…
View article: Addressing ethical issues in healthcare artificial intelligence using a lifecycle-informed process
Addressing ethical issues in healthcare artificial intelligence using a lifecycle-informed process Open
Objectives Artificial intelligence (AI) proceeds through an iterative and evaluative process of development, use, and refinement which may be characterized as a lifecycle. Within this context, stakeholders can vary in their interests and p…
View article: Using Large Language Models to Generate Clinical Trial Tables and Figures
Using Large Language Models to Generate Clinical Trial Tables and Figures Open
Tables, figures, and listings (TFLs) are essential tools for summarizing clinical trial data. Creation of TFLs for reporting activities is often a time-consuming task encountered routinely during the execution of clinical trials. This stud…
View article: Question Answering for Electronic Health Records: Scoping Review of Datasets and Models
Question Answering for Electronic Health Records: Scoping Review of Datasets and Models Open
Background Question answering (QA) systems for patient-related data can assist both clinicians and patients. They can, for example, assist clinicians in decision-making and enable patients to have a better understanding of their medical hi…
View article: Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing
Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing Open
View article: Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing
Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing Open
The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning o…
View article: Exploring the Generalization of Cancer Clinical Trial Eligibility Classifiers Across Diseases
Exploring the Generalization of Cancer Clinical Trial Eligibility Classifiers Across Diseases Open
Clinical trials are pivotal in medical research, and NLP can enhance their success, with application in recruitment. This study aims to evaluate the generalizability of eligibility classification across a broad spectrum of clinical trials.…
View article: Ensemble pretrained language models to extract biomedical knowledge from literature
Ensemble pretrained language models to extract biomedical knowledge from literature Open
Objectives The rapid expansion of biomedical literature necessitates automated techniques to discern relationships between biomedical concepts from extensive free text. Such techniques facilitate the development of detailed knowledge bases…
View article: Improving large language models for clinical named entity recognition via prompt engineering
Improving large language models for clinical named entity recognition via prompt engineering Open
Importance The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt…
View article: Clinical Information Retrieval: A Literature Review
Clinical Information Retrieval: A Literature Review Open
View article: Linking Cancer Clinical Trials to their Result Publications.
Linking Cancer Clinical Trials to their Result Publications. Open
The results of clinical trials are a valuable source of evidence for researchers, policy makers, and healthcare professionals. However, online trial registries do not always contain links to the publications that report on their results, i…
View article: Identifying Genomic Data Sources from Biomedical Literature.
Identifying Genomic Data Sources from Biomedical Literature. Open
Genomic research is becoming increasingly data-intensive, yet the proper reference of data remains a persistent challenge. Despite various efforts to establish and standardize data citation practices, scientists frequently fall short of ac…
View article: PheNormGPT: a framework for extraction and normalization of key medical findings
PheNormGPT: a framework for extraction and normalization of key medical findings Open
This manuscript presents PheNormGPT, a framework for extraction and normalization of key findings in clinical text. PheNormGPT relies on an innovative approach, leveraging large language models to extract key findings and phenotypic data i…
View article: Sequencing conversational turns in peer interactions: An integrated approach for evidence-based conversational agent for just-in-time nicotine cravings intervention
Sequencing conversational turns in peer interactions: An integrated approach for evidence-based conversational agent for just-in-time nicotine cravings intervention Open
Background Risky health behaviors place an enormous toll on public health systems. While relapse prevention support is integrated with most behavior modification programs, the results are suboptimal. Recent advances in artificial intellige…
View article: Question Answering for Electronic Health Records: Scoping Review of Datasets and Models (Preprint)
Question Answering for Electronic Health Records: Scoping Review of Datasets and Models (Preprint) Open
BACKGROUND Question answering (QA) systems for patient-related data can assist both clinicians and patients. They can, for example, assist clinicians in decision-making and enable patients to have a better understanding of their medical h…
View article: Question Answering for Electronic Health Records: A Scoping Review of datasets and models
Question Answering for Electronic Health Records: A Scoping Review of datasets and models Open
Question Answering (QA) systems on patient-related data can assist both clinicians and patients. They can, for example, assist clinicians in decision-making and enable patients to have a better understanding of their medical history. Signi…
View article: Text Classification of Cancer Clinical Trial Eligibility Criteria
Text Classification of Cancer Clinical Trial Eligibility Criteria Open
Automatic identification of clinical trials for which a patient is eligible is complicated by the fact that trial eligibility is stated in natural language. A potential solution to this problem is to employ text classification methods for …
View article: The IMPACT framework and implementation for accessible in silico clinical phenotyping in the digital era
The IMPACT framework and implementation for accessible in silico clinical phenotyping in the digital era Open
Clinical phenotyping is often a foundational requirement for obtaining datasets necessary for the development of digital health applications. Traditionally done via manual abstraction, this task is often a bottleneck in development due to …