Andrew A. S. Soltan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Andrew A. S. Soltan has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
- David Andrew Clifton
University of Oxford
3 shared publications - Jenny Yang
Institute of Biomedical Engineering, Dept. Engineering Science, University of Oxford, Oxford, England
2 shared publications - Alice Margaret Turner
Respiratory Medicine, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
1 shared publication - Alvina Grace Lai
Institute of Health Informatics, University College London, London, UK
1 shared publication - Ana Torralbo
Institute of Health Informatics, University College London, London, UK
1 shared publication - Andreea Avramescu
University of Manchester
1 shared publication
Latest Publications
- Open Access
DECOVID: A UK Two-Center Harmonized Database of Acute Care Electronic Health Records for COVID-19 Research
The DECOVID database contains harmonized pseudonymized electronic health record (EHR) data on all adult (≥18 years old) patients presenting to two large, digitally mature centers in the United Kingdom between 1 January 2020 and 28 February 2021, with follow-up until at least 28 March 2021. The database was originally developed to support the COVID-19 response but is now available via the PIONEER data hub for researchers to explore a wide range of research questions, including exploratory analyses, risk factor assessment, prediction modeling, and comparative effectiveness studies. Raw data were extracted from local EHRs and transformed into a standardized form (Observational Health Data Sciences and Informatics-Common Data Model version 5.3.1). The database includes 165,420 patients across 256,804 hospital presentations. For these patients, highly granular data are available, including patient demographics, longitudinal vital signs, physiology, treatments, laboratory findings, clinical diagnoses, and outcomes. There are 10,030 patients with COVID-19, of whom 1472 died in hospital.
Open AccessDECOVID: A UK Two-Center Harmonized Database of Acute Care Electronic Health Records for COVID-19 Research
The DECOVID database contains harmonized pseudonymized electronic health record (EHR) data on all adult (≥18 years old) patients presenting to two large, digitally mature centers in the United Kingdom between 1 January 2020 and 28 February 2021, with follow-up until at least 28 March 2021. The database was originally developed to support the COVID-19 response but is now available via the PIONEER data hub for researchers to explore a wide range of research questions, including exploratory analyses, risk factor assessment, prediction modeling, and comparative effectiveness studies. Raw data were extracted from local EHRs and transformed into a standardized form (Observational Health Data Sciences and Informatics-Common Data Model version 5.3.1). The database includes 165,420 patients across 256,804 hospital presentations. For these patients, highly granular data are available, including patient demographics, longitudinal vital signs, physiology, treatments, laboratory findings, clinical diagnoses, and outcomes. There are 10,030 patients with COVID-19, of whom 1472 died in hospital.
- Open Access
- 24 January 2024
- Published by Elsevier in The Lancet Digital Health
- Vol. 6 (2) , e93-e104
A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals
- 24 January 2024
- Published by Elsevier in The Lancet Digital Health
- Vol. 6 (2) , e93-e104
Open AccessA scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals
- Open Access
Geometrically-aggregated training samples: Leveraging summary statistics to enable healthcare data democratization
Healthcare data is highly sensitive and confidential, with strict regulations and laws to protect patient privacy and security. However, these regulations impede the access of healthcare data to a wider AI research community. As a result, AI healthcare research is often dominated by organisations with access to larger datasets or limited to silo-based development, where models are trained and evaluated on a limited population. Taking inspiration from the non-sensitive nature of the summary statistics (mean, variance, etc.) of healthcare data, this paper proposes geometrically-aggregated training samples (GATS) where each training sample is a convex combination of multiple patients’ characteristics. Thus, mappings from patients to any constructed sample are highly convoluted, preserving patient privacy. We demonstrate that these “summary training units” provide effective training on different tabular and time-series datasets (CURIAL, UCI Adult, and eICU), and indeed behave as a summary of the original training datasets. This approach takes important steps towards data accessibility and democratization.
Open AccessGeometrically-aggregated training samples: Leveraging summary statistics to enable healthcare data democratization
Healthcare data is highly sensitive and confidential, with strict regulations and laws to protect patient privacy and security. However, these regulations impede the access of healthcare data to a wider AI research community. As a result, AI healthcare research is often dominated by organisations with access to larger datasets or limited to silo-based development, where models are trained and evaluated on a limited population. Taking inspiration from the non-sensitive nature of the summary statistics (mean, variance, etc.) of healthcare data, this paper proposes geometrically-aggregated training samples (GATS) where each training sample is a convex combination of multiple patients’ characteristics. Thus, mappings from patients to any constructed sample are highly convoluted, preserving patient privacy. We demonstrate that these “summary training units” provide effective training on different tabular and time-series datasets (CURIAL, UCI Adult, and eICU), and indeed behave as a summary of the original training datasets. This approach takes important steps towards data accessibility and democratization.
- Open Access
Addressing Label Noise for Electronic Health Records: Insights from Computer Vision for Tabular Data
The analysis of extensive electronic health records (EHR) datasets often calls for automated solutions, with machine learning (ML) techniques, including deep learning (DL), taking a lead role. One common task involves categorizing EHR data into predefined groups. However, the vulnerability of EHRs to noise and errors stemming from data collection processes, as well as potential human labeling errors, poses a significant risk. This risk is particularly prominent during the training of DL models, where the possibility of overfitting to noisy labels can have serious repercussions in healthcare. Despite the well-documented existence of label noise in EHR data, few studies have tackled this challenge within the EHR domain. Our work addresses this gap by adapting computer vision (CV) algorithms to mitigate the impact of label noise in DL models trained on EHR data. Notably, it remains uncertain whether CV methods, when applied to the EHR domain, will prove effective, given the substantial divergence between the two domains. We present empirical evidence demonstrating that these methods, whether used individually or in combination, can substantially enhance model performance when applied to EHR data, especially in the presence of noisy/incorrect labels. We validate our methods and underscore their practical utility in real-world EHR data, specifically in the context of COVID-19 diagnosis. Our study highlights the effectiveness of CV methods in the EHR domain, making a valuable contribution to the advancement of healthcare analytics and research.
Open AccessAddressing Label Noise for Electronic Health Records: Insights from Computer Vision for Tabular Data
The analysis of extensive electronic health records (EHR) datasets often calls for automated solutions, with machine learning (ML) techniques, including deep learning (DL), taking a lead role. One common task involves categorizing EHR data into predefined groups. However, the vulnerability of EHRs to noise and errors stemming from data collection processes, as well as potential human labeling errors, poses a significant risk. This risk is particularly prominent during the training of DL models, where the possibility of overfitting to noisy labels can have serious repercussions in healthcare. Despite the well-documented existence of label noise in EHR data, few studies have tackled this challenge within the EHR domain. Our work addresses this gap by adapting computer vision (CV) algorithms to mitigate the impact of label noise in DL models trained on EHR data. Notably, it remains uncertain whether CV methods, when applied to the EHR domain, will prove effective, given the substantial divergence between the two domains. We present empirical evidence demonstrating that these methods, whether used individually or in combination, can substantially enhance model performance when applied to EHR data, especially in the presence of noisy/incorrect labels. We validate our methods and underscore their practical utility in real-world EHR data, specifically in the context of COVID-19 diagnosis. Our study highlights the effectiveness of CV methods in the EHR domain, making a valuable contribution to the advancement of healthcare analytics and research.