JBJoao H. Bettencourt-Silva

Joao H. Bettencourt-Silva

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Joao H. Bettencourt-Silva has a total of 147 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Quantifying the fidelity of in vitro human cell culture systems using a biomedical foundation model

    by Satoru Fujii, Scott T. Espenschied, Vibha Anand, Joao Bettencourt-Silva, Yi Han, Go Ito, Akira Koseki, Akihiro Kosugi, James Kozloski, Ryoma Matsumoto, et al.

    Primary cell culture is fast becoming a dominant method for discovery work regarding human disease. Currently, there are no methods to quantitatively benchmark these systems. Here, we apply a uniform in vitro culture system of human intestinal epithelial cells (IECs) to achieve this goal. We previously established methods for long-term two-dimensional (2D) cultivation of mouse IECs using an air–liquid interface (ALI) technique. Here, we further refined these methods for long-term 2D cultivation of human IECs, with histological and molecular features of differentiated intestinal epithelia. Leveraging the power and scalability of a biomedical foundation model (BMFM) trained on single-cell RNA sequencing data (BMFM-RNA), we performed classification tasks to identify cell types across sample sources and to quantitatively benchmark our in vitro differentiated cells against cells collected from patient biopsies. We observed a striking concordance between our in vitro differentiated cells and the corresponding cell types in vivo for multiple differentiated secretory cell types. This approach using BMFM-RNA holds promise to expand our understanding of the regulatory mechanisms, including gene–gene regulation underlying homeostasis and regeneration, as well as the functions of rare and poorly understood lineages within the human intestinal epithelia. Moreover, these methods may be applicable to other organs, model systems, and experimental modalities. We propose that the framework used here can be deployed as a standard benchmarking methodology, ultimately improving the fidelity of primary human culture systems.


  • Open Access

    Enhancing foundation models for scientific discovery via multimodal knowledge graph representations

    by Vanessa Lopez, Lam Hoang, Marcos Martinez-Galindo, Raúl Fernández-Díaz, Marco Luca Sbodio, Rodrigo Ordonez-Hurtado, Mykhaylo Zayats, Natasha Mulligan, Joao Bettencourt-Silva


  • Open Access

    How can quantum computing be applied in clinical trial design and optimization?

    by Hakan Doga, Aritra Bose, M. Emre Sahin, Joao Bettencourt-Silva, Anh Pham, Eunyoung Kim, Alan Andress, Sudhir Saxena, Laxmi Parida, Jan Lukas Robertus, et al.


  • Open Access

    Evaluating the Predictive Features of Person-Centric Knowledge Graph Embeddings: Unfolding Ablation Studies

    by Christos Theodoropoulos, Natasha Mulligan, Joao Bettencourt-Silva

    Developing novel predictive models with complex biomedical information is challenging due to various idiosyncrasies related to heterogeneity, standardization or sparseness of the data. We previously introduced a person-centric ontology to organize information about individual patients, and a representation learning framework to extract person-centric knowledge graphs (PKGs) and to train Graph Neural Networks (GNNs). In this paper, we propose a systematic approach to examine the results of GNN models trained with both structured and unstructured information from the MIMIC-III dataset. Through ablation studies on different clinical, demographic, and social data, we show the robustness of this approach in identifying predictive features in PKGs for the task of readmission prediction.

  • Open Access

    Representation Learning for Person or Entity-Centric Knowledge Graphs: An Application in Healthcare

    by Christos Theodoropoulos, Natalia Mulligan, Thaddeus Stappenbeck, Joao Bettencourt-Silva

    Knowledge graphs (KGs) are a popular way to organise information based on ontologies or schemas. Despite advances in KGs, representing knowledge remains a non-trivial task across industries and it is especially challenging in the biomedical and healthcare domains due to complex interdependent relations between entities, heterogeneity, lack of standardization, and sparseness of data. KGs are used to discover diagnoses or prioritize genes relevant to disease, but they often rely on schemas that are not centred around a node or entity of interest, such as a person. Entity-centric KGs are relatively unexplored but hold promise in representing important facets connected to a central node and unlocking downstream tasks beyond graph traversal and reasoning, such as training graph neural networks (GNNs) for a wide range of predictive tasks. This paper presents an end-to-end representation learning framework to extract entity-centric KGs from structured and unstructured data. We introduce a star-shaped ontology to represent the multiple facets of a person and use it to guide KG creation. Compact representations of the graphs are created leveraging GNNs and experiments are conducted using different levels of heterogeneity or explicitness. A readmission prediction task is used to evaluate the results of the proposed framework, showing a stable system, robust to missing data, that outperforms a range of baseline machine learning classifiers. We highlight that this approach has several potential applications across domains and is open-sourced.


  • Open Access

    Identifying social aspects in real world data to support health outcomes

    by Hector Upegui, Joao Bettencourt-Silva

  • Open Access

    Combining digital trends and scientific literature: a case study on Social Determinants of COVID-19

    by J Bettencourt-Silva, C Cullen, N Mulligan, A Di Bari, M Gleize

    Background: Digital sources such as Internet-based search tools have created prospects for augmenting traditional public health surveillance. These can support the identification of emerging public health concerns, intervention evaluation or policy making. Social Determinants of Health(SDoH) are key factors linked to health outcomes yet they are poorly recorded and seldom used. Scientific papers have reported SDoH impacts on various outcomes yet this data has not been explored for population trend analyses. We present an analysis of our approach to combining insights mined from PubMed with online search trends. Methods: PubMed-2019 database was used to build a knowledge graph(KG) of connected health and social concepts based on relative co-occurrences found throughout the abstracts. We then observed Google search trends for 10 SDoH concepts at the outset of the 2020 pandemic (March-May) and compared them with the previous 4 years. For concepts with increasing trends, the KG was used to identify other potentially relevant concepts. Subsequently we continued observing online trends for a further 12 months in order to examine the KG concepts' trends. Results: Our analysis showed Food Security and Unemployment trended the highest compared to previous years. These became the seed concepts used to traverse the KG, where the top 20 relevant concepts were identified for each seed. An analysis of the 8 concepts overlapping both seeds showed 6 with increasing trends during follow-up. Correlation coefficients were computed and positive relations observed (Unemployment+Anxiety, r=.72; Distress+Food Security, r =.62). Data will be discussed. Conclusions: Positive correlations were observed between data from a 2019 PubMed KG and online search trends during COVID-19. These preliminary results suggest value in combining these digital sources to strengthen public health systems. This is important to understand the interactions between health and social factors and identify emerging trends. Key messages: Combining data from scientific research papers with online search trends yielded interesting results that may further complement traditional surveillance systems and clinical case ascertainment. Social determinants of health data should play an increasingly important part in complementing public health surveillance systems and in strengthening population trend analyses.

  • Open Access

    Impact of Diabetes on Complications, Long Term Mortality and Recurrence in 608,890 Hospitalised Patients with Stroke

    by Weronika A. Szlachetka, Tiberiu A. Pana, Somsak Tiamkao, Allan B. Clark, Kannikar Kongbunkiat, Kittisak Sawanyawisuth, Joao H. Bettencourt-Silva, Narongrit Kasemap, Mamas A. Mamas, Phyo K. Myint

    Patients with diabetes mellitus (DM) have been found to be at an increased risk of suffering a stroke. However, research on the impact of DM on stroke outcomes is limited. We aimed to examine the influence of DM on outcomes in ischaemic (IS) and haemorrhagic stroke (HS) patients. We included 608,890 consecutive stroke patients from the Thailand national insurance registry. In-hospital mortality, sepsis, pneumonia, acute kidney injury (AKI), urinary tract infection (UTI) and cardiovascular events were evaluated using logistic regressions. Long-term analysis was performed on first-stroke patients with a determined pathology (n = 398,663) using Royston-Parmar models. Median follow-ups were 4.21 and 4.78 years for IS and HS, respectively. All analyses were stratified by stroke sub-type. Mean age (SD) was 64.3 (13.7) years, 44.9% were female with 61% IS, 28% HS and 11% undetermined strokes. DM was associated with in-hospital death, pneumonia, sepsis, AKI and cardiovascular events (odds ratios ranging from 1.13–1.78, p < 0.01) in both stroke types. In IS, DM was associated with long-term mortality and recurrence throughout the follow-up: HRmax (99% CI) at t = 4108 days: 1.54 (1.27, 1.86) and HR (99% CI) = 1.27(1.23,1.32), respectively. In HS, HRmax (t = 4108 days) for long-term mortality was 2.10 (1.87, 2.37), significant after day 14 post-discharge. HRmax (t = 455) for long-term recurrence of HS was 1.29 (1.09, 1.53), significant after day 116 post-discharge. Regardless of stroke type, DM was associated with in-hospital death and complications, long-term mortality and stroke recurrence.


  • Open Access

    An Extensible De-Identification Framework for Privacy Protection of Unstructured Health Information: Creating Sustainable Privacy Infrastructures

    by Braghin Stefano, Bettencourt-Silva Joao H., Levacher Killian, Antonatos Spiros

    The volume of unstructured health records has increased exponentially across healthcare settings. Similarly, the number of healthcare providers that wish to exchange records has also increased and, as a result, de-identification and the preservation of privacy features have become increasingly important and necessary. Governance guidelines now require sensitive information to be masked or removed yet this remains a difficult and often ad-hoc task, particularly when dealing with unstructured text. Annotators are typically used to identify such sensitive information but they may only be effective in certain text fragments. There is at present no hybrid, sustainable framework that aggregates different annotators together. This paper proposes a novel framework that leverages a combination of state-of-the-art annotators in order to maximize the effectiveness of the de-identification of health information.


  • Open Access

    Determinants of Length of Stay Following Total Anterior Circulatory Stroke

    by James P. Curtain, Man Yu, Allan B. Clark, Nicholas D. Gollop, Joao H. Bettencourt-Silva, Anthony Kneale Metcalf, Kristian M. Bowles, Marcus D. Flather, John F. Potter, Phyo Kyaw Myint

    Identification of factors that determine length of stay (LOS) in total anterior circulatory stroke (TACS) has potential for targeted intervention to reduce the associated health care burden. This study aimed to determine which factors predict LOS following either ischaemic or haemorrhagic TACS. The study sample population was drawn from the Norfolk and Norwich Stroke and Transient Ischemic Attack (TIA) Register (1996–2012), a prospective registry. 2965 patients admitted with TACS verified by a stroke specialist team were included. Primary analysis identified predictors of length of stay (LOS) in either haemorrhagic or ischaemic TACS. Secondary analyses identified predictors of LOS in patients who were discharged alive or who died during admission separately. Moderate (p = 0.014) to severe disability (p = 0.015) and history of congestive heart failure (p = 0.027) in the primary analysis and pre-stroke residence in a care facility among patients who survived to discharge (p = 0.013) were associated with a shorter length of stay. Factors associated with increased length of stay included presence of neurological lateralisation in the primary analysis (p = 0.004) and amongst patients who died (p = 0.003 and p = 0.014 for ischaemic and haemorrhagic stroke, respectively). Patients with advanced age (≥85 years) with haemorrhagic stroke had longer LOS regardless of mortality outcome. Patients with low pre-morbid disability (modified Rankin score ≤2 who died following haemorrhagic TACS also had longer LOS. Our study found predictors of LOS following TACS include neurological lateralisation, pre-stroke disability status, congestive heart failure, pre-morbid residence and age. The identification of such factors would assist in resource allocation and discharge planning.