Power of big data to improve patient care in gastroenterology

2021 ◽  
pp. flgastro-2019-101239
Author(s):  
Jamie Catlow ◽  
Benjamin Bray ◽  
Eva Morris ◽  
Matt Rutter
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Real World ◽  
Common Good ◽  
Treatment Effectiveness ◽  
Healthcare Delivery ◽  
Improve Patient Care ◽  
Patient Registries ◽  
General Data Protection Regulation ◽  
Improve Patient

Big data is defined as being large, varied or frequently updated, and usually generated from real-world interaction. With the unprecedented availability of big data, comes an obligation to maximise its potential for healthcare improvements in treatment effectiveness, disease prevention and healthcare delivery. We review the opportunities and challenges that big data brings to gastroenterology. We review its sources for healthcare improvement in gastroenterology, including electronic medical records, patient registries and patient-generated data. Big data can complement traditional research methods in hypothesis generation, supporting studies and disseminating findings; and in some cases holds distinct advantages where traditional trials are unfeasible. There is great potential power in patient-level linkage of datasets to help quantify inequalities, identify best practice and improve patient outcomes. We exemplify this with the UK colorectal cancer repository and the potential of linkage using the National Endoscopy Database, the inflammatory bowel disease registry and the National Health Service bowel cancer screening programme. Artificial intelligence and machine learning are increasingly being used to improve diagnostics in gastroenterology, with image analysis entering clinical practice, and the potential of machine learning to improve outcome prediction and diagnostics in other clinical areas. Big data brings issues with large sample sizes, real-world biases, data curation, keeping clinical context at analysis and General Data Protection Regulation compliance. There is a tension between our obligation to use data for the common good and protecting individual patient’s data. We emphasise the importance of engaging with our patients to enable them to understand their data usage as fully as they wish.

scholarly journals Distortion in Real-World Analytic Processes

2019 ◽  
Author(s):  
Peter Kieseberg ◽  
Lukas Daniel Klausner ◽  
Andreas Holzinger
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Learning Environments ◽  
Real World ◽  
Data Protection ◽  
Privacy Protection ◽  
Data Analytics ◽  
Big Data Analytics ◽  
General Data Protection Regulation ◽  
General Data

In discussions on the General Data Protection Regulation (GDPR), anonymisation and deletion are frequently mentioned as suitable technical and organisational methods (TOMs) for privacy protection. The major problem of distortion in machine learning environments, as well as related issues with respect to privacy, are rarely mentioned. The Big Data Analytics project addresses these issues.

scholarly journals Multi-Drug Featurization and Deep Learning Improve Patient-Specific Predictions of Adverse Events

2021 ◽  
Vol 18 (5) ◽  
pp. 2600
Author(s):  
Ioannis N. Anastopoulos ◽  
Chloe K. Herczeg ◽  
Kasey N. Davis ◽  
Atray C. Dixit
Keyword(s):  
Machine Learning ◽  
Real World ◽  
Variable Number ◽  
Patient Specific ◽  
Real World Evidence ◽  
Genetic Features ◽  
The Uk ◽  
Therapeutic Compounds ◽  
Improve Patient ◽  
Reaction Profile

While the clinical approval process is able to filter out medications whose utility does not offset their adverse drug reaction profile in humans, it is not well suited to characterizing lower frequency issues and idiosyncratic multi-drug interactions that can happen in real world diverse patient populations. With a growing abundance of real-world evidence databases containing hundreds of thousands of patient records, it is now feasible to build machine learning models that incorporate individual patient information to provide personalized adverse event predictions. In this study, we build models that integrate patient specific demographic, clinical, and genetic features (when available) with drug structure to predict adverse drug reactions. We develop an extensible graph convolutional approach to be able to integrate molecular effects from the variable number of medications a typical patient may be taking. Our model outperforms standard machine learning methods at the tasks of predicting hospitalization and death in the UK Biobank dataset yielding an R2 of 0.37 and an AUC of 0.90, respectively. We believe our model has potential for evaluating new therapeutic compounds for individualized toxicities in real world diverse populations. It can also be used to prioritize medications when there are multiple options being considered for treatment.

Get Real: Integration of Real‐World Data to Improve Patient Care

2020 ◽  
Vol 107 (4) ◽  
pp. 722-725 ◽  
Author(s):  
Ron J. Keizer ◽  
Erik Dvergsten ◽  
Andrej Kolacevski ◽  
Aaron Black ◽  
Sanja Karovic ◽  
...  
Keyword(s):  
Patient Care ◽  
Real World ◽  
Improve Patient Care ◽  
Real World Data ◽  
World Data ◽  
Improve Patient

scholarly journals Machine learning concepts for correlated Big Data privacy

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Sreemoyee Biswas ◽  
Nilay Khare ◽  
Pragati Agrawal ◽  
Priyank Jain
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Correlation Analysis ◽  
Real World ◽  
Data Privacy ◽  
Correlated Data ◽  
Data Correlation ◽  
The Real ◽  
Big Data Privacy ◽  
Real World Datasets

AbstractWith data becoming a salient asset worldwide, dependence amongst data kept on growing. Hence the real-world datasets that one works upon in today’s time are highly correlated. Since the past few years, researchers have given attention to this aspect of data privacy and found a correlation among data. The existing data privacy guarantees cannot assure the expected data privacy algorithms. The privacy guarantees provided by existing algorithms were enough when there existed no relation between data in the datasets. Hence, by keeping the existence of data correlation into account, there is a dire need to reconsider the privacy algorithms. Some of the research has considered utilizing a well-known machine learning concept, i.e., Data Correlation Analysis, to understand the relationship between data in a better way. This concept has given some promising results as well. Though it is still concise, the researchers did a considerable amount of research on correlated data privacy. Researchers have provided solutions using probabilistic models, behavioral analysis, sensitivity analysis, information theory models, statistical correlation analysis, exhaustive combination analysis, temporal privacy leakages, and weighted hierarchical graphs. Nevertheless, researchers are doing work upon the real-world datasets that are often large (technologically termed big data) and house a high amount of data correlation. Firstly, the data correlation in big data must be studied. Researchers are exploring different analysis techniques to find the best suitable. Then, they might suggest a measure to guarantee privacy for correlated big data. This survey paper presents a detailed survey of the methods proposed by different researchers to deal with the problem of correlated data privacy and correlated big data privacy and highlights the future scope in this area. The quantitative analysis of the reviewed articles suggests that data correlation is a significant threat to data privacy. This threat further gets magnified with big data. While considering and analyzing data correlation, then parameters such as Maximum queries executed, Mean average error values show better results when compared with other methods. Hence, there is a grave need to understand and propose solutions for correlated big data privacy.

Remote ultrasound diagnostics disrupting traditional military frontline healthcare delivery

2021 ◽  
pp. bmjmilitary-2021-001821
Author(s):  
Georgina Blenkinsop ◽  
R A Heller ◽  
N J Carter ◽  
A Burkett ◽  
M Ballard ◽  
...  
Keyword(s):  
Patient Care ◽  
Healthcare Delivery ◽  
Improve Patient Care ◽  
Guidance System ◽  
Diagnostic Quality ◽  
Aeromedical Evacuation ◽  
Care Experience ◽  
Ultrasound Diagnostics ◽  
Diagnostic Capability ◽  
Improve Patient

Accurate and reliable diagnostic capability is essential in deployed healthcare to aid decision-making and mitigate risk. This is important for both the patient and the deployed healthcare system, especially when considering the prioritisation of scarce aeromedical evacuation assets and frontline resources. Novel ultrasound tele-guidance technology presents a valuable diagnostic solution for remotely deployed military clinicians. This report discusses the first use of a consultant radiologist guiding a clinician, untrained in ultrasound, to perform an ultrasound scan via a live tele-guidance feed in the deployed environment using the Butterfly iQ+ tele-guidance system. Distance scanning provided a diagnostic quality report when compared with locally performed imaging to improve patient care and maintain operational output. This example demonstrates feasibility of remote point-of-care imaging systems in provision of location-agnostic high-quality diagnostic capability. Future opportunities to develop care pathways using bedside tele-diagnostics will democratise access, drive efficiency and improve patient care experience and outcomes.

scholarly journals Italian multiple sclerosis register as the basis for post-authorization safety studies

2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
M Ponzio ◽  
M Trojano ◽  
M Capobianco ◽  
M Pugliatti ◽  
M Ulivelli ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Pharmaceutical Industry ◽  
Real World ◽  
Treatment Effectiveness ◽  
Patient Registries ◽  
Real World Data ◽  
World Data ◽  
Disease Modifying Therapy ◽  
Disease Modifying

Abstract While the safety and efficacy of Disease Modifying Therapy (DMT) in multiple sclerosis (MS) are assessed in clinical trials, these are of relatively short duration and always confined to highly selected patient groups. The evaluation of real-world data such as patient registries, is vital as it offers long-term data collection and is patient rather than product-focused during the lifetime of MS, and allows to document a patient's treatment history throughout the disease course. Patient registries can play an important role in monitoring the safety of drus. Regulators and the pharmaceutical industry have shown interest in complementing or even replacing phase 4 clinical studies with data from MS registries. The Italian MS Register (IMSR), in collaboration with the Big MS Data initiative, that also includes the national MS registries of Denmark, France, and Sweden and the international database network MSBase, came together with industry to conduct studies on post-authorization safety (PASS) and treatment effectiveness. The IMSR includes the clinical history of approximately 55,000 patients, or approximatively 45% of the estimated cases of MS in Italy. More than 10,000 patients have a follow-up duration of over 10 years. A Core Protocol outlining principles of PASS projects was created in which aggregated results made available to sponsors and health authorities. The Core Protocol specifies variables, emphasizes improved capture of adverse events, in particular cancer, non-melanoma skin cancers and immunosuppression-related infections, all MedDRA-coded. EUROCAT codes for pregnancy outcomes are also documented. Regulators, the pharmaceutical industry and national-level registries have jointly identified a format of collaboration on PASS for DMT in MS to benefit patients and the larger society. In this way, we hope to contribute to a framework that will include emerging and existing registries with the common goal of contributing to the advancement of knowledge in MS. Key messages The real-world data can contribute to understanding of the impact of disease-modifying therapy on long term. A format of collaboration among clinical research, regulators and pharmaceutical industry could be a winning framework to improve the knowledge on safety and treatment effectiveness in MS.

Big Data in Healthcare and Social Sciences

2017 ◽  
Vol 8 (3) ◽  
pp. 1-16 ◽  
Author(s):  
Victoria López ◽  
Diego Urgelés ◽  
Óscar Sánchez ◽  
Gabriel Valverde
Keyword(s):  
Social Sciences ◽  
Big Data ◽  
Predictive Analytics ◽  
Healthcare Providers ◽  
Improve Patient Care ◽  
Predictive Analysis ◽  
Patient Access ◽  
Cad System ◽  
Lean Methods ◽  
Improve Patient

Healthcare providers and payers are increasingly turning to Big Data and analytics, to help them understand their patients and the context of their illnesses in more detail. Industry leaders are exploring/using Big Data to reduce costs, increase efficiency and improve patient care. The next future is an innovative approach to improving patient access using lean methods and predictive analytics. Social sciences are very much related to healthcare and both areas develop in a parallel way. In this article, we introduce one example of application: Bip4cast (a bipolar disorder CAD system). This paper shows how Bip4cast deals with different data sources to enrich the knowledge and improve predictive analysis.

Sign in / Sign up

Export Citation Format

Share Document