Meredith Martyn

Meredith Martyn

Auto-generated profile, based on publicly available information

Meredith Martyn

Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology C Neuroscience, King’s College London, London, UK

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 May 2020 in Trials
Verified
Journal Article
Open access
PDF file
SLSarah Lensen
Sarah Lensen
AMArchie Macnair
Archie Macnair
SLSharon B. Love
Sharon B. Love
VYVictoria Yorke-Edwards
Victoria Yorke-Edwards
Nurulamin M NoorNurulamin M Noor
Nurulamin M Noor
MSMatthew R. Sydes
Matthew R. Sydes
Background: Clinical trials generally each collect their own data despite routinely collected health data (RCHD) increasing in quality and breadth. Our aim is to quantify UK-based randomised controlled trials (RCTs) accessing RCHD for participant data, characterise how these data are used and thereby recommend how more trials could use RCHD. Methods: We conducted a systematic review of RCTs accessing RCHD from at least one registry in the UK between 2013 and 2018 for the purposes of informing or supplementing participant data. A list of all registries holding RCHD in the UK was compiled. In cases where registries published release registers, these were searched for RCTs accessing RCHD. Where no release register was available, registries were contacted to request a list of RCTs. For each identified RCT, information was collected from all publicly available sources (release registers, websites, protocol etc.). The search and data extraction were undertaken between January and May 2019. Results: We identified 160 RCTs accessing RCHD between 2013 and 2018 from a total of 22 registries; this corresponds to only a very small proportion of all UK RCTs (about 3%). RCTs accessing RCHD were generally large (median sample size 1590), commonly evaluating treatments for cancer or cardiovascular disease. Most of the included RCTs accessed RCHD from NHS Digital (68%), and the most frequently accessed datasets were mortality (76%) and hospital visits (55%). RCHD was used to inform the primary trial (82%) and long-term follow-up (57%). There was substantial variation in how RCTs used RCHD to inform participant outcome measures. A limitation was the lack of information and transparency from registries and RCTs with respect to which datasets have been accessed and for what purposes. Conclusions: In the last five years, only a small minority of UK-based RCTs have accessed RCHD to inform participant data. We ask for improved accessibility, confirmed data quality and joined-up thinking between the registries and the regulatory authorities. Trial registration: PROSPERO CRD42019123088.

19 July 2024 in medRxiv
Verified
Preprint
Open access
PDF file
MLMaximin Lange
Maximin Lange
MMMeredith Martyn
Meredith Martyn
EGEoin Gogarty
Eoin Gogarty
PBPhilip Braude
Philip Braude
FFFeras Fayez
Feras Fayez
BCBen Carter
Ben Carter
We will develop a novel approach to drug repurposing, utilising Natural Language Processing (NLP) and Literature Based Discovery (LBD) techniques. This will present a simplified, accessible drug repurposing pipeline using Word2Vec embeddings trained on PubMed abstracts to identify potential new medications to be repurposed. We present this approach in the context of antipsychotics, but it could be repeated for any available medication. The research is structured in three stages: Identification of candidate medications using Word2Vec algorithm trained on scientific literature. Empirical testing of identified candidates using a large hospital dataset to explore protective effects against disease onset. Validation of findings using a second, independent dataset to assess generalizability. This method addresses limitations in current machine learning-based drug repurposing approaches, including lack of external validation and limited accessibility. By leveraging Word2Vec’s ability to capture semantic relationships between words, the study aims to uncover hidden connections in medical literature that may lead to novel therapeutic discoveries. The protocol emphasizes transparency and reproducibility, utilizing publicly available electronic health record (EHR) databases for validation. This approach allows for tangible results even for researchers with limited machine learning expertise, bridging the gap between biomedical and information systems communities.

10 April 2020 in medRxiv
Verified
Preprint
Open access
PDF file
SLSarah Lensen
Sarah Lensen
AMArchie Macnair
Archie Macnair
SLSharon B Love
Sharon B Love
VYVictoria Yorke-Edwards
Victoria Yorke-Edwards
Nurulamin M NoorNurulamin M Noor
Nurulamin M Noor
MSMatthew R Sydes
Matthew R Sydes
Background: Clinical trials generally each collect their own data despite routinely-collected health data (RCHD) increasing in quality and breadth. Our aim is to quantify UK-based randomised controlled trials (RCTs) accessing RCHD for participant data, characterise how these data are used and thereby recommend how more trials could use RCHD. Methods: We conducted a systematic review of RCTs accessing RCHD from at least one registry in the UK between 2013-2018, for the purposes of informing or supplementing participant data. A list of all registries holding RCHD in the UK was compiled. In cases where registries published release registers, these were searched for RCTs accessing RCHD. Where no release register was available, registries were contacted to request a list of RCTs. For each identified RCT, information was collected from all publicly available sources (release registers, websites, protocol etc.). The search and data extraction was undertaken between Jan-2019 and May-2019. Results: We identified 160 RCTs accessing RCHD between 2013 and 2018 from a total of 22 registries; this corresponds to only a very small proportion of all UK RCTs (approximately 3%). RCTs accessing RCHD were generally large (median sample size 1590), commonly evaluating treatments for cancer or cardiovascular disease. Most of the included RCTs accessed RCHD from NHS Digital (68%), and the most frequently accessed datasets were mortality (76%) and hospital visits (55%). RCHD was used to inform the primary trial (82%) and long-term follow-up (57%). There was substantial variation in how RCTs used RCHD to inform participant outcome measures. A limitation was the lack of information and transparency from registries and RCTs with respect to which datasets have been accessed and for what purposes. Conclusions: In the last five years, only a small minority of UK-based RCTs have accessed RCHD to inform participant data. We ask for improved accessibility, confirmed data quality and joined up thinking between the registries and the regulatory authorities. Registration: PROSPERO CRD42019123088

22 May 2025 in BMC Digital Health
Verified
Journal Article
Open access
PDF file
MLMaximin Lange
Maximin Lange
EGEoin Gogarty
Eoin Gogarty
MMMeredith Martyn
Meredith Martyn
PBPhilip Braude
Philip Braude
FFFeras Fayez
Feras Fayez
BCBen Carter
Ben Carter
Background: Drug development is lengthy and costly, making drug repurposing an attractive alternative. Identifying repurposing candidates from vast biomedical literature is challenging. Natural language processing (NLP) offers potential for literature-based discovery. We present and evaluate a novel, accessible NLP-based method using the Word2Vec algorithm to identify, test, and validate candidate medications for repurposing, demonstrated by seeking treatments for psychotic disorders. Results: A Word2Vec model trained on 2.3 million PubMed abstracts (2000–2023) identified potential repurposing candidates based on cosine similarity to a known antipsychotic drug. We tested one candidate, a cephalosporin antibiotic, across independent datasets: MIMIC-IV, CRIS, and BRATECA. Cephalosporin antibiotics in MIMIC-IV demonstrated a reduced hazard ratio (aHR) for psychosis hospitalisation overall (0.94, 95% CI: 0.90–0.99) and more substantially for severe mental illness (0.52, 95% CI: 0.45–0.60). However, CRIS showed an increased risk (HR: 3.56, 95% CI: 2.66–4.77). BRATECA lacked suitable diagnostic data for analysis. Conclusions: This methodological framework demonstrates the potential for machine learning approaches to systematically identify drug repurposing candidates, while highlighting population-specific variations in therapeutic effectiveness that warrant caution in translational applications. Our findings should not be interpreted as cephalosporins to be recommended for or against treating psychosis. Our findings merely offer validity to the application of our repurposing methodology, and should serve as a foundation for further investigation rather than direct clinical application.

19 March 2026 in medRxiv
Verified
Preprint
Open access
PDF file
HJHassan Jafari
Hassan Jafari
PCPetrina Chu
Petrina Chu
MLMaximin Lange
Maximin Lange
FMFrancesca Maher
Francesca Maher
CGCallum Glen
Callum Glen
GFGordon Forbes
Gordon Forbes
Background: Statistical Analysis Plans (SAPs) are essential for trial transparency and credibility but are resource-intensive to produce. While Large Language Models (LLMs) have shown promise in drafting protocols, their ability to generate high-quality, protocol-compliant SAPs remains untested against current content guidance. This study developed and validated an LLM-based pipeline for drafting SAPs from clinical trial protocols. Methods: We developed a structured, section-by-section prompting pipeline aligned with standard SAP guidance. We applied this pipeline to nine clinical trial protocols using three leading LLMs: OpenAI GPT-5, Anthropic Claude Sonnet 4, and Google Gemini 2.5 Pro. The resulting 27 SAPs were evaluated against a 46-item quality checklist derived from the published SAP guidelines. Items were double-scored by independent trial statisticians on a 0–3 scale for accuracy. We compared performance across LLMs and between item types (descriptive vs. statistical reasoning) using mixed-effects logistic regression. Results: Across 9 trials, the models produced SAP drafts with high overall accuracy (77%–78%), with no difference in performance between the three LLMs (p=0.79) but varied by content type (p < 0.001). All models performed well on descriptive items (e.g., administrative details, trial design), with lower accuracy for items requiring statistical reasoning (e.g., modelling strategies, sensitivity analyses). Accuracy for statistical items ranged from 67% to 72%, whereas descriptive items achieved 81% to 83% accuracy. Ǫualitatively, models were prone to specific failure modes in complex sections, such as omitting necessary details for secondary outcome models or hallucinating sensitivity analyses. Discussion: Current LLMs can effectively draft portions of SAPs, offering the potential for substantial time savings in trial documentation. However, a human-in-the-loop approach remains mandatory; while models demonstrate strong capability in producing descriptive content, their independent application to complex statistical methodology design still requires further methodological development and training. Future work should explore advanced prompt engineering, such as retrieval-augmented generation or agentic workflows, to improve reasoning capabilities.