Life.course digital T.wins – I.ntelligent M.onitoring for E.arly and continuous intervention and prevention (LifeTIME): Proposal for a proof-of-concept study (Preprint)

2021 ◽  
Author(s):  
Madison Milne-Ives ◽  
Lorna Fraser ◽  
Asiya Khan ◽  
David Walker ◽  
Michelle Helena van Velthoven ◽  
...  
Keyword(s):  
Risk Factors ◽  
Life Course ◽  
Data Science ◽  
Healthcare Systems ◽  
Health Conditions ◽  
Practice Research ◽  
Clinical Practice Research Datalink ◽  
Proof Of Concept ◽  
Digital Twin ◽  
Digital Twins

BACKGROUND Multimorbidity, which is associated with significant negative outcomes for individuals and healthcare systems, is increasing in the UK. However, there is a lack of knowledge about the risk factors (including health, behaviour, and environment) for multimorbidity over time. An interdisciplinary approach is essential, as data science, artificial intelligence, and concepts from engineering (digital twins), have the potential to enable personalised simulation of life-course risk for the development of multimorbidity by identifying key risk factors throughout the life course. Predicting the risk of developing clusters of health conditions before they occur would add clinical value by enabling targeted early preventive interventions, advancing personalised care to improve outcomes, and reducing the burden on the UK’s healthcare systems. OBJECTIVE This study aims to identify key risk factors that predict multimorbidity throughout the lifetime through the development of an intelligent agent using digital twins so that early interventions can be delivered to improve health outcomes. The objectives of this study are to identify key predictors of lifetime risk of multimorbidity, create a series of simulated computational digital twins that predict levels of risk for specific clusters of factors, and test the feasibility of the system. METHODS This study will use machine learning to identify key risk factors throughout life that predict the risk of later multimorbidity to develop digital twins. The first stage of the development will be the training of a base predictive model. Data from the National Child Development Study (NCDS), the North West London Integrated Care Record (NWL ICR), the Clinical Practice Research Datalink (CPRD), and Cerner's Real World Data will be split into subsets for training and validation, which will be done following the k-fold cross-validation procedure and assessed with the PROBAST risk of bias tool. Two additional datasets - from the early-LIfe data cross-LInkage in Research (eLIXIR) study and the Children and Young People’s Health Partnership (CYPHP) randomised controlled trial - will be used in addition to the model to develop a series of digital twin personas that simulate clusters of factors that predict different levels of risk of developing multimorbidity. RESULTS The expected results are a validated model, a series of digital twin personas, and an assessment of proof-of-concept. CONCLUSIONS Digital twins could provide an individualised early warning system that predicts the risk of future health conditions and recommends the intervention that is most likely to be effective at minimising that risk. These insights could have a significant positive impact on an individual’s quality of life and healthy life expectancy and reduce population-level health burdens.

scholarly journals Bespoke linkage of Public Health England laboratory data on gastrointestinal infections to the Clinical Practice Research Datalink: Ethics approval and a study proposal

2017 ◽  
Vol 1 (1) ◽  
Author(s):  
Oluwaseun Esan ◽  
Thomas Fanshawe ◽  
Mara Violato ◽  
Noel McCarthy ◽  
Rafael Perera-Salazar
Keyword(s):  
Public Health ◽  
Risk Factors ◽  
Record Linkage ◽  
Laboratory Data ◽  
Practice Research ◽  
Clinical Practice Research Datalink ◽  
Gastrointestinal Infections ◽  
Hospital Records ◽  
Gi Infections

ABSTRACT ObjectivesGastrointestinal (GI) infections are common. Most infections are self-limiting, with some people developing long-term sequelae following their GI infection. Currently, the surveillance of GI infections such as Campylobacter and Salmonella is primarily based on laboratory data held by Public Health England (PHE). Information on symptoms severity, treatment of infection and subsequent complications is not captured by this data source. Electronic Health Records (EHR) provide a platform to assemble cohorts for long-term follow-up at relatively low costs. Record linkage of existing EHR provides a powerful resource to estimate the burden of complications following gastrointestinal Infections (GI) and the associated risk factors such as treatment of the primary GI infection. A range of ethical and data governance approvals processes, motivated to protect patients and patient data, are required to allow use of routine and linked data for research. The aim of this project is to establish a bespoke linkage of PHE laboratory data on Campylobacter, non-typhoidal Salmonella (NTS) and verocytotoxin producing Escherichia coli (VTEC) to the Clinical Practice Research Datalink (CPRD, primary care records), hospital records and other secondary datasets in order to estimate the burden of complications following GI infections. ApproachLinkage of laboratory data, primary care data, hospital records, deaths and deprivation index were proposed following an initial data completeness check of laboratory data on Campylobacter spp., NTS and VTEC over a ten year (2004-2014) period. Linkage plans were discussed with all relevant organisations. Finalised study protocols were completed and application for approval for linkage was submitted to the Independent Scientific Advisory Committee (ISAC) and the NHS Research Ethics Committee. An additional application was sent to the Confidential Advisory Group (CAG) to comply with section 251 of the UK NHS Act 2006 on accessing patient identifiable information. ResultsISAC approval for CPRD linkage is dependent on CAG approval. Completion of data linkage will allow the measurement of complications following GI infections to be estimated more accurately than is possible using routine, unlinked population-level data. It allows the implementation of designs such as the case-crossover design for the investigation of patient-level risk factors such as use of antibiotics and their association with complications. ConclusionsBespoke record linkage to CPRD can allow the measurement of risk of long-term sequelae following acute infections. Considerable time should be built into research timelines to allow completion of all ethical, governance and data access procedures.

Variation in the Association between Antineoplastic Therapies and Venous Thromboembolism in Patients with Active Cancer

2020 ◽  
Vol 120 (05) ◽  
pp. 847-856 ◽  
Author(s):  
Michela Giustozzi ◽  
Antonio Curcio ◽  
Bob Weijs ◽  
Thalia S. Field ◽  
Saulius Sudikas ◽  
...  
Keyword(s):  
Risk Factors ◽  
Radiation Therapy ◽  
Venous Thromboembolism ◽  
Cause Of Death ◽  
Cancer Diagnosis ◽  
Practice Research ◽  
Clinical Practice Research Datalink ◽  
Cancer Type ◽  
Increased Risk ◽  
Active Cancer

Abstract Background Venous thromboembolism (VTE) is a major cause of death in cancer patients. Although patients with cancer have numerous risk factors for VTE, the relative contribution of cancer treatments is unclear. Objective The objective of this study is to evaluate the association between cancer therapies and the risk of VTE. Methods From UK Clinical Practice Research Datalink, data on patients with first cancer diagnosis between 2008 and 2016 were extracted along with information on hospitalization, treatments, and cause of death. Primary outcome was active cancer-associated VTE. To establish the independent effects of risk factors, adjusted subhazard ratios (adj-SHR) were calculated using Fine and Gray regression analysis accounting for death as competing risk. Results Among 67,801 patients with a first cancer diagnosis, active cancer-associated VTE occurred in 1,473 (2.2%). During a median observation time of 1.2 years, chemotherapy, surgery, hormonal therapy, radiation therapy, and immunotherapy were given to 71.1, 37.2, 17.2, 17.5, and 1.4% of patients with VTE, respectively. The active cancers associated with the highest risk of VTE—as assessed by incidence rates—included pancreatic cancer, brain cancer, and metastatic cancer. Chemotherapy was associated with an increased risk of VTE (adj-SHR: 3.17, 95% confidence interval [CI]: 2.76–3.65) while immunotherapy with a not significant reduced risk (adj-SHR: 0.67, 95% CI: 0.30–1.52). There was no association between VTE and radiation therapy (adj-SHR: 0.91, 95% CI: 0.65–1.27) and hormonal therapies. Conclusion VTE risk varies with cancer type. Chemotherapy was associated with an increased VTE risk, whereas with radiation and immunotherapy therapy, an association was not confirmed.

scholarly journals Validation of cardiovascular outcomes and risk factors in the Clinical Practice Research Datalink in the United Kingdom

2020 ◽  
Vol 30 (2) ◽  
pp. 237-247
Author(s):  
Alejandro Arana ◽  
Andrea V Margulis ◽  
Cristina Varas‐Lorenzo ◽  
Christine L Bui ◽  
Alicia Gilsenan ◽  
...  
Keyword(s):  
Risk Factors ◽  
United Kingdom ◽  
Clinical Practice ◽  
Cardiovascular Outcomes ◽  
Practice Research ◽  
Clinical Practice Research Datalink ◽  
The United Kingdom

scholarly journals Healthcare resource utilisation and mortality outcomes in international migrants to the UK: analysis protocol for a linked population-based cohort study using Clinical Practice Research Datalink (CPRD), Hospital Episode Statistics (HES) and the Office for National Statistics (ONS)

2021 ◽  
Vol 5 ◽  
pp. 156
Author(s):  
Neha Pathak ◽  
Parth Patel ◽  
Rachel Burns ◽  
Lucinda Haim ◽  
Claire X. Zhang ◽  
...  
Keyword(s):  
Primary Care ◽  
Healthcare Resource ◽  
Health Conditions ◽  
Practice Research ◽  
Resource Utilisation ◽  
Clinical Practice Research Datalink ◽  
Main Study ◽  
Healthcare Resource Utilisation ◽  
International Migrants ◽  
The Uk

An estimated 14.2% (9.34 million people) of people living in the UK in 2019 were international migrants. Despite this, there are no large-scale national studies of their healthcare resource utilisation and little is known about how migrants access and use healthcare services. One ongoing study of migration health in the UK, the Million Migrants study, links electronic health records (EHRs) from hospital-based data, national death records and Public Health England migrant and refugee data. However, the Million Migrants study cannot provide a complete picture of migration health resource utilisation as it lacks data on migrants from Europe and utilisation of primary care for all international migrants. Our study seeks to address this limitation by using primary care EHR data linked to hospital-based EHRs and national death records.  Our study is split into a feasibility study and a main study. The feasibility study will assess the validity of a migration phenotype, a transparent reproducible algorithm using clinical terminology codes to determine migration status in Clinical Practice Research Datalink (CPRD), the largest UK primary care EHR. If the migration phenotype is found to be valid, the main study will involve using the phenotype in the linked dataset to describe primary care and hospital-based healthcare resource utilisation and mortality in migrants compared to non-migrants. All outcomes will be explored according to sub-conditions identified as research priorities through patient and public involvement, including preventable causes of inpatient admission, sexual and reproductive health conditions/interventions and mental health conditions. The results will generate evidence to inform policies that aim to improve migration health and universal health coverage.

scholarly journals Risk factors for Burkitt lymphoma: a nested case-control study in the UK Clinical Practice Research Datalink

2018 ◽  
Vol 181 (4) ◽  
pp. 505-514 ◽  
Author(s):  
Parisa Karimi ◽  
Brenda M. Birmann ◽  
Lesley A. Anderson ◽  
Charlene M. McShane ◽  
Shahinaz M. Gadalla ◽  
...  
Keyword(s):  
Risk Factors ◽  
Clinical Practice ◽  
Burkitt Lymphoma ◽  
Case Control Study ◽  
Case Control ◽  
Practice Research ◽  
Clinical Practice Research Datalink ◽  
The Uk ◽  
Nested Case Control ◽  
Control Study

scholarly journals Clustering of physical health multimorbidity in 68,392 people with severe mental illness and matched comparators: a lifetime prevalence analysis of United Kingdom primary care data

2021 ◽  
Author(s):  
Naomi J Launders ◽  
Joseph F Hayes ◽  
Gabriele Price ◽  
David PJ Osborn
Keyword(s):  
Mental Illness ◽  
Physical Health ◽  
Severe Mental Illness ◽  
Neurological Disease ◽  
Health Conditions ◽  
Drug Misuse ◽  
Practice Research ◽  
Clinical Practice Research Datalink ◽  
Disease Cluster ◽  
Younger Age

Objective: To investigate the clustering of physical health multimorbidity in people with severe mental illness (SMI) compared to matched comparators. Design: A cohort-nested analysis of lifetime diagnoses of physical health conditions. Setting: Over 1,800 UK general practices (GP) contributing to Clinical Practice Research DataLink (CPRD) Gold or Aurum databases. Participants: 68,392 adult patients with a diagnosis of SMI between 2000 and 2018, with at least one year of follow up data, matched 1:4 to patients without an SMI diagnosis, on age, sex, GP, and year of GP registration. Main outcome measures: Odds ratios for 24 physical health conditions derived using Elixhauser and Charlson comorbidity indices. We controlled for age, sex, region, and ethnicity; and then additionally for smoking status, alcohol and drug misuse and body mass index. We defined multimorbidity clusters using Multiple Correspondence Analysis and K-Means cluster analysis and described them based on the observed/expected ratio. Results: Patients with a diagnosis of SMI had an increased odds of 19 of 24 physical health conditions and had a higher prevalence of multimorbidity at a younger age compared to comparators (aOR: 2.47; 95%CI: 2.25 to 2.72 in patients aged 20-29). Smoking, obesity, alcohol, and drug misuse were more prevalent in the SMI group and adjusting for these reduced the odds ratio of all comorbid conditions. In patients with multimorbidity (SMI cohort: n=22,843, comparators: n=68,856), we identified six multimorbidity clusters in the SMI cohort, and five in the comparator cohort. Five profiles were common to both. The "hypertension and varied multimorbidity" cluster was most common: 49.8% in the SMI cohort, and 56.7% in comparators. 41.5% of the SMI cohort were in a "respiratory and neurological disease" cluster, compared to 28.7% of comparators. Conclusions: Physical health multimorbidity clusters similarly in people with and without SMI, though patients with SMI develop multimorbidity earlier and a greater proportion fall into a "respiratory and neurological disease" cluster. There is a need for interventions aimed at younger-age multimorbidity in those with SMI.

scholarly journals The Camp Nou Stadium as a Testbed for City Physiology: A Modular Framework for Urban Digital Twins

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Irene Meta ◽  
Feliu Serra-Burriel ◽  
José C. Carrasco-Jiménez ◽  
Fernando M. Cucchietti ◽  
Carla Diví-Cuesta ◽  
...  
Keyword(s):  
Nonlinear Process ◽  
Point Of View ◽  
Statistical Techniques ◽  
Proof Of Concept ◽  
Agent Based ◽  
Digital Twin ◽  
Domain Specific ◽  
Digital Twins ◽  
Modular Framework

In this paper, the Camp Nou stadium is used as a testbed for City Physiology, a theoretical framework for urban digital twins. With this case study, the modularity and adaptability of the framework, originally intended for city-scale simulations, are tested on a large facility venue. As a proof of concept, several statistical techniques and an agent-based simulation platform are coupled to simulate a crowd in the stadium, and a process of four steps is followed to build the case study. Both the conceptual (interdomain) and technical (domain specific) layers of the digital twin are defined and connected in a nonlinear process so that they represent the complexity of the object to be simulated. The result obtained is a strategy to build a digital twin from the domain point of view, paving the way for more complex, more ambitious simulators.

scholarly journals Risk factors associated with poor pain outcomes following primary knee replacement surgery: Analysis of data from the clinical practice research datalink, hospital episode statistics and patient reported outcomes as part of the STAR research programme

PLoS ONE ◽  
2021 ◽  
Vol 16 (12) ◽  
pp. e0261850
Author(s):  
Hasan Raza Mohammad ◽  
Rachael Gooberman-Hill ◽  
Antonella Delmestri ◽  
John Broomfield ◽  
Rita Patel ◽  
...  
Keyword(s):  
Risk Factors ◽  
Knee Replacement ◽  
Patient Reported Outcomes ◽  
Hospital Episode Statistics ◽  
Practice Research ◽  
Clinical Practice Research Datalink ◽  
Replacement Surgery ◽  
Patient Reported ◽  
Pain Outcomes ◽  
Pain State

Objective Identify risk factors for poor pain outcomes six months after primary knee replacement surgery. Methods Observational cohort study on patients receiving primary knee replacement from the UK Clinical Practice Research Datalink, Hospital Episode Statistics and Patient Reported Outcomes. A wide range of variables routinely collected in primary and secondary care were identified as potential predictors of worsening or only minor improvement in pain, based on the Oxford Knee Score pain subscale. Results are presented as relative risk ratios and adjusted risk differences (ARD) by fitting a generalized linear model with a binomial error structure and log link function. Results Information was available for 4,750 patients from 2009 to 2016, with a mean age of 69, of whom 56.1% were female. 10.4% of patients had poor pain outcomes. The strongest effects were seen for pre-operative factors: mild knee pain symptoms at the time of surgery (ARD 18.2% (95% Confidence Interval 13.6, 22.8), smoking 12.0% (95% CI:7.3, 16.6), living in the most deprived areas 5.6% (95% CI:2.3, 9.0) and obesity class II 6.3% (95% CI:3.0, 9.7). Important risk factors with more moderate effects included a history of previous knee arthroscopy surgery 4.6% (95% CI:2.5, 6.6), and use of opioids 3.4% (95% CI:1.4, 5.3) within three months after surgery. Those patients with worsening pain state change had more complications by 3 months (11.8% among those in a worse pain state vs. 2.7% with the same pain state). Conclusions We quantified the relative importance of individual risk factors including mild pre-operative pain, smoking, deprivation, obesity and opioid use in terms of the absolute proportions of patients achieving poor pain outcomes. These findings will support development of interventions to reduce the numbers of patients who have poor pain outcomes.

Sign in / Sign up

Export Citation Format

Share Document