Healthcare Datasets Research Articles

Precision Adverse Drug Reactions Prediction with Heterogeneous Graph Neural Network.

Accurate prediction of Adverse Drug Reactions (ADRs) at the patient level is essential for ensuring patient safety and optimizing healthcare outcomes. Traditional machine learning-based methods primarily focus on predicting potential ADRs for drugs, but they often fall short of capturing the complexity of individual demographics and the variations in ADRs experienced by different people. In this study, a novel framework called Precise Adverse Drug Reaction (PreciseADR) for patient-level ADR prediction is proposed. The approach effectively integrates relations between patients and ADRs, and harnesses the power of heterogeneous Graph Neural Networks (GNNs) to address the limitations of traditional methods. Specifically, a heterogeneous graph representation of patients is constructed, encompassing nodes that represent patients, diseases, drugs, and ADRs. By leveraging edges in the graph, crucial connections are captured such as a patient being affected by diseases, taking specific drugs, and experiencing ADRs. Next, a GNN-based model is utilized to learn latent representations of the patient nodes and facilitate the propagation of information throughout the graph structure. By employing patient embeddings that consider their diseases and drugs, potential ADRs can be accurately predicted. The PreciseADR is dedicated to effectively capturing both local and global dependencies within the heterogeneous graph, allowing for the identification of subtle patterns and interactions that play a significant role in ADRs. To evaluate the performance of the approach, extensive experiments are conducted on a large-scale real-world healthcare dataset with adverse reports from the FDA Adverse Event Reporting System (FAERS). Experimental results demonstrate that the PreciseADR achieves superior predictive performance in identifying patient-level ADRs, surpassing the strongest baseline by 3.2% in AUC score and by 4.9% in Hit@10.

Implementation of Distributed Machine Learning in Medicine Industry

Abstract. As a matter of fact, machine learning (ML) has become a cornerstone in modern science and engineering, evolving from early algorithms like the perceptron to sophisticated deep learning models. The rise of distributed machine learning (DML) has enabled scalable, privacy-preserving analysis of large healthcare datasets in recent years. With this in mind, this study summarizes the principles of DML, contrasting it with traditional as well as parallel computing approaches. At the same time, this research discusses its applications in medical imaging, predictive analytics, and real-time monitoring. According to the analysis, despite significant advancements, challenges related to data privacy, heterogeneity, and scalability persist. Based on the evaluations, future research is needed to overcome these limitations and further integrate DML into healthcare. Overall, these results underscore the transformative potential of DML in enhancing healthcare delivery and outcomes and pave a path as well as offer a guideline for implementations of machine leaning in medic industry.

Retrieval Integrity Verification and Multi-System Data Interoperability Mechanism of a Blockchain Oracle for Smart Healthcare with Internet of Things (IoT) Integration

The proliferation of Internet of Things (IoT) technology has significantly enhanced smart healthcare systems, enabling the collection and processing of vast healthcare datasets such as electronic medical records (EMRs) and remote health monitoring (RHM) data. However, this rapid expansion has also introduced critical challenges related to data security, privacy, and system reliability. To address these challenges, we propose a retrieval integrity verification and multi-system data interoperability mechanism for a Blockchain Oracle in smart healthcare with IoT Integration (RIVMD-BO). The mechanism uses the cuckoo filter technology to effectively reduce the computational complexity and ensures the authenticity and integrity of data transmission and use through data retrieval integrity verification. The experimental results and security analysis show that the proposed method can improve system performance while ensuring security.

DySurv: dynamic deep learning model for survival analysis with conditional variational inference.

Machine learning applications for longitudinal electronic health records often forecast the risk of events at fixed time points, whereas survival analysis achieves dynamic risk prediction by estimating time-to-event distributions. Here, we propose a novel conditional variational autoencoder-based method, DySurv, which uses a combination of static and longitudinal measurements from electronic health records to estimate the individual risk of death dynamically. DySurv directly estimates the cumulative risk incidence function without making any parametric assumptions on the underlying stochastic process of the time-to-event. We evaluate DySurv on 6 time-to-event benchmark datasets in healthcare, as well as 2 real-world intensive care unit (ICU) electronic health records (EHR) datasets extracted from the eICU Collaborative Research (eICU) and the Medical Information Mart for Intensive Care database (MIMIC-IV). DySurv outperforms other existing statistical and deep learning approaches to time-to-event analysis across concordance and other metrics. It achieves time-dependent concordance of over 60% in the eICU case. It is also over 12% more accurate and 22% more sensitive than in-use ICU scores like Acute Physiology and Chronic Health Evaluation (APACHE) and Sequential Organ Failure Assessment (SOFA) scores. The predictive capacity of DySurv is consistent and the survival estimates remain disentangled across different datasets. Our interdisciplinary framework successfully incorporates deep learning, survival analysis, and intensive care to create a novel method for time-to-event prediction from longitudinal health records. We test our method on several held-out test sets from a variety of healthcare datasets and compare it to existing in-use clinical risk scoring benchmarks. While our method leverages non-parametric extensions to deep learning-guided estimations of the survival distribution, further deep learning paradigms could be explored.

We Are on the Verge of Breakthrough Cures for Type 1 Diabetes, but Who Are the 2 Million Americans Who Have It?

Background: Two million Americans have type 1 diabetes (T1DM). Innovative treatments have standardized insulin delivery and improved outcomes for patients, but patients' access to such technologies depends on social determinants of health, including insurance coverage, proper diagnosis, and appropriate patient supports. Prior estimates of US prevalence, incidence, and patient characteristics have relied on data from select regions and younger ages and miss important determinants. Objectives: This study sought to use large, nationally representative healthcare claims data sets to holistically estimate the size of the current US population with T1DM and investigate geographic nuances in prevalence and incidence, patient demographics, insurance coverage, and device use. This work also aimed to project T1DM population growth over the next 10 years. Methods: We used administrative claims from 4 sources to identify prevalent and incident T1DM patients in the US, as well as various demographic and insurance characteristics of the patient population. We combined this data with information from national population growth projections and literature to construct an actuarial model to project growth of the T1DM population based on current trends and scenarios for 2024, 2029, and 2033. Results: We estimated 2.07 million T1DM patients nationally across all insurance coverages in our 2024 baseline model year: 1.79 million adults (≥20 years) and 0.28 million children. This represents a US T1DM prevalence rate of 617 per 100 000 and an incidence rate of 0.016%. By 2033, we project the US population with T1DM will grow by about 10%, reaching approximately 2.29 million patients. Discussion: Our results showed important differences in T1DM prevalence and incidence across regions, payers, and ethnic groups. This suggests studies based on more geographically concentrated data may miss important variation in prevalence and incidence across regions. It also indicates T1DM prevalence tends to vary by income, consistent with several international studies. Conclusions: Accurate projections of T1DM population growth are critical to ensure appropriate healthcare coverage and reimbursement for treatments. Our work supports future policy and research efforts with 2024, 2029, and 2033 projections of demographics and insurance coverage for people with T1DM.

We Are on the Verge of Breakthrough Cures for Type 1 Diabetes, but Who Are the 2 Million Americans Who Have It?

Background: Two million Americans have type 1 diabetes (T1DM). Innovative treatments have standardized insulin delivery and improved outcomes for patients, but patients’ access to such technologies depends on social determinants of health, including insurance coverage, proper diagnosis, and appropriate patient supports. Prior estimates of US prevalence, incidence, and patient characteristics have relied on data from select regions and younger ages and miss important determinants. Objectives: This study sought to use large, nationally representative healthcare claims data sets to holistically estimate the size of the current US population with T1DM and investigate geographic nuances in prevalence and incidence, patient demographics, insurance coverage, and device use. This work also aimed to project T1DM population growth over the next 10 years. Methods: We used administrative claims from 4 sources to identify prevalent and incident T1DM patients in the US, as well as various demographic and insurance characteristics of the patient population. We combined this data with information from national population growth projections and literature to construct an actuarial model to project growth of the T1DM population based on current trends and scenarios for 2024, 2029, and 2033. Results: We estimated 2.07 million T1DM patients nationally across all insurance coverages in our 2024 baseline model year: 1.79 million adults (≥20 years) and 0.28 million children. This represents a US T1DM prevalence rate of 617 per 100 000 and an incidence rate of 0.016%. By 2033, we project the US population with T1DM will grow by about 10%, reaching approximately 2.29 million patients. Discussion: Our results showed important differences in T1DM prevalence and incidence across regions, payers, and ethnic groups. This suggests studies based on more geographically concentrated data may miss important variation in prevalence and incidence across regions. It also indicates T1DM prevalence tends to vary by income, consistent with several international studies. Conclusions: Accurate projections of T1DM population growth are critical to ensure appropriate healthcare coverage and reimbursement for treatments. Our work supports future policy and research efforts with 2024, 2029, and 2033 projections of demographics and insurance coverage for people with T1DM.

The Role of Artificial Intelligence in Revolutionizing Mental Health Services: A Data-Driven Approach

The potential of artificial intelligence (AI) to transform mental health care through individualized treatment approaches is significant. This research investigates the application of AI and extensive healthcare datasets to improve the precision of mental health diagnoses and treatments. The study employs various machine learning techniques, such as Random Forest, CatBoost, K-Nearest Neighbors, XGBoost, Convolutional Neural Networks, and Long Short-Term Memory networks, to analyze diverse data sources including electronic health records, neuroimaging, genetic information, and demographic data. Following thorough data preprocessing, model training, and evaluation using metrics like accuracy, precision, recall, F1 score, and Cohen's Kappa, the Random Forest algorithm emerges as the top performer with 98.7% accuracy. The research highlights the importance of addressing ethical considerations, such as protecting patient privacy, ensuring data security, and mitigating algorithmic bias when implementing AI in mental health services. The findings indicate that AI-based approaches can markedly improve diagnostic accuracy, provide tailored treatment suggestions, and facilitate early relapse detection, thus promoting proactive mental health management. Key Words: Artificial Intelligence, Mental Health, Data- Driven approach, Personalized Treatment, Machine Learning, Natural Language Processing.

Privacy-Preserving Data Analytics in Internet of Medical Things

The healthcare sector has changed dramatically in recent years due to depending more and more on big data to improve patient care, enhance or improve operational effectiveness, and forward medical research. Protecting patient privacy in the era of digital health records is a major challenge, as there could be a chance of privacy leakage during the process of collecting patient data. To overcome this issue, we propose a secure, privacy-preserving scheme for healthcare data to ensure maximum privacy of an individual while also maintaining their utility and allowing for the performance of queries based on sensitive attributes under differential privacy. We implemented differential privacy on two publicly available healthcare datasets, the Breast Cancer Prediction Dataset and the Nursing Home COVID-19 Dataset. Moreover, we examined the impact of varying privacy parameter (ε) values on both the privacy and utility of the data. A significant part of this study involved the selection of ε, which determines the degree of privacy protection. We also conducted a computational time comparison by performing multiple complex queries on these datasets to analyse the computational overhead introduced by differential privacy. The outcomes demonstrate that, despite a slight increase in query processing time, it remains within reasonable bounds, ensuring the practicality of differential privacy for real-time applications.

Developing healthcare language model embedding spaces

Pre-trained Large Language Models (LLMs) have revolutionised Natural Language Processing (NLP) tasks, but often struggle when applied to specialised domains such as healthcare. The traditional approach of pre-training on large datasets followed by task-specific fine-tuning is resource-intensive and poorly aligned with the constraints of many healthcare settings. This presents a significant challenge for deploying LLM-based NLP solutions in medical contexts, where data privacy, computational resources, and domain-specific language pose unique obstacles.This study aims to develop and evaluate efficient methods for adapting smaller LLMs to healthcare-specific datasets and tasks. We seek to identify pre-training approaches that can effectively instil healthcare competency in compact LLMs under tight computational budgets, a crucial capability for responsible and sustainable deployment in local healthcare settings.We explore three specialised pre-training methods to adapt smaller LLMs to different healthcare datasets: traditional Masked Language modelling (MLM), Deep Contrastive Learning for Unsupervised Textual Representations (DeCLUTR), and a novel approach utilising metadata categories from healthcare settings. These methods are assessed across multiple healthcare datasets, with a focus on downstream document classification tasks. We evaluate the performance of the resulting LLMs through classification accuracy and analysis of the derived embedding spaces.Contrastively trained models consistently outperform other approaches on classification tasks, delivering strong performance with limited labelled data and fewer model parameter updates. While our novel metadata-based pre-training does not further improve classifications across datasets, it yields interesting embedding cluster separability. Importantly, all domain-adapted LLMs outperform their publicly available, general-purpose base models, validating the importance of domain specialisation.This research demonstrates the efficacy of specialised pre-training methods in adapting compact LLMs to healthcare tasks, even under resource constraints. We provide guidelines for pre-training specialised healthcare LLMs and motivate continued inquiry into contrastive objectives. Our findings underscore the potential of these approaches for aligning small LLMs with privacy-sensitive medical tasks, offering a path toward more efficient and responsible NLP deployment in healthcare settings. This work contributes to the broader goal of making advanced NLP techniques accessible and effective in specialised domains, particularly where resource limitations and data sensitivity are significant concerns.

Implications of Big Data Analytics, AI, Machine Learning, and Deep Learning in the Health Care System of Bangladesh: Scoping Review.

The rapid advancement of digital technologies, particularly in big data analytics (BDA), artificial intelligence (AI), machine learning (ML), and deep learning (DL), is reshaping the global health care system, including in Bangladesh. The increased adoption of these technologies in health care delivery within Bangladesh has sparked their integration into health care and public health research, resulting in a noticeable surge in related studies. However, a critical gap exists, as there is a lack of comprehensive evidence regarding the research landscape; regulatory challenges; use cases; and the application and adoption of BDA, AI, ML, and DL in the health care system of Bangladesh. This gap impedes the attainment of optimal results. As Bangladesh is a leading implementer of digital technologies, bridging this gap is urgent for the effective use of these advancing technologies. This scoping review aims to collate (1) the existing research in Bangladesh's health care system, using the aforementioned technologies and synthesizing their findings, and (2) the limitations faced by researchers in integrating the aforementioned technologies into health care research. MEDLINE (via PubMed), IEEE Xplore, Scopus, and Embase databases were searched to identify published research articles between January 1, 2000, and September 10, 2023, meeting the following inclusion criteria: (1) any study using any of the BDA, AI, ML, and DL technologies and health care and public health datasets for predicting health issues and forecasting any kind of outbreak; (2) studies primarily focusing on health care and public health issues in Bangladesh; and (3) original research articles published in peer-reviewed journals and conference proceedings written in English. With the initial search, we identified 1653 studies. Following the inclusion and exclusion criteria and full-text review, 4.66% (77/1653) of the articles were finally included in this review. There was a substantial increase in studies over the last 5 years (2017-2023). Among the 77 studies, the majority (n=65, 84%) used ML models. A smaller proportion of studies incorporated AI (4/77, 5%), DL (7/77, 9%), and BDA (1/77, 1%) technologies. Among the reviewed articles, 52% (40/77) relied on primary data, while the remaining 48% (37/77) used secondary data. The primary research areas of focus were infectious diseases (15/77, 19%), noncommunicable diseases (23/77, 30%), child health (11/77, 14%), and mental health (9/77, 12%). This scoping review highlights remarkable progress in leveraging BDA, AI, ML, and DL within Bangladesh's health care system. The observed surge in studies over the last 5 years underscores the increasing significance of AI and related technologies in health care research. Notably, most (65/77, 84%) studies focused on ML models, unveiling opportunities for advancements in predictive modeling. This review encapsulates the current state of technological integration and propels us into a promising era for the future of digital Bangladesh.

Intracranial haemorrhage following treatment for pulmonary embolism: analysis of the german nationwide inpatient sample

Abstract Background Intracranial haemorrhage (ICH) can be a life-threatening complication of pulmonary embolism (PE) and its treatment during the acute phase. Purpose To characterize patients hospitalized with PE and ICH by identifying risk factors across different treatment groups, and to detect temporal trends in a large nationwide sample. Methods The German nationwide inpatient sample was screened for patients admitted with PE during the period 2005-2020. All hospitalizations were stratified based on the occurrence of ICH and accordingly, risk factors for ICH were investigated (source: Research data center [RDC] of the Federal Statistical Office and the Statistical Offices of the federal states, DRG Statistics 2005-2020, own calculations). Results Overall, 816,653 hospitalizations were included in the present study; among them, 2516 (0.3%) experienced an ICH event and 84,810 (10.4%) died in-hospital. The annual number of hospitalizations of patients admitted due to PE increased steadily from 38,749 in 2005 to 54,966 in 2020, whereas the incidence of ICH remained, despite annual fluctuations, largely stable over time, both in the entire study population and in the subgroup of patients with severe PE as defined by clinical and haemodynamic parameters (n=270,980 [33.2%]). ICH was overall more frequent after the seventh decade of life but, interestingly, no correlation with age was found amongst patients with severe PE (Figure 1). ICH in hospitalized PE patients was associated with an aggravated comorbidity burden mirrored by a higher Charlson Comorbidity Index (5.0 [interquartile range 4.0-7.0] vs. 4.0 [2.0-5.0], P<0.001). This was mainly driven by the higher prevalence of heart failure (27.3% vs. 19.4%, P<0.001) and acute or chronic kidney disease (27.6% vs. 18.1%, P<0.001) in patients with ICH. In addition, severe PE (OR 3.09 [95% CI 2.84-3.35], P<0.001), acute kidney injury (OR 3.60 [3.09-4.18], P<0.001), and particularly ischaemic stroke (OR 14.64 [12.61-17.00], P<0.001) were identified as independent predictors of ICH by multivariable logistic regressions. Overall, 27% of the ICH cases were related to systemic thrombolysis. In PE patients treated with systemic thrombolysis, age ≥70 years as well as female sex were independent predictors of ICH. Finally, ICH was independently associated with a substantial increase in case-fatality in patients hospitalized with PE (univariate OR: 5.38 [4.97-5.84], P<0.001; multivariable OR: 6.16 [5.64-6.72], P<0.001). Conclusions In this healthcare dataset of the German nationwide inpatient sample, the overall incidence of ICH remained low at 0.3% over the 15-year study period. Severe PE, age, comorbidity burden, kidney disease, heart failure and ischaemic stroke were independent risk factors for ICH.

Utilizing Attention-Enhanced Deep Neural Networks for Large-Scale Preliminary Diabetes Screening in Population Health Data

Early screening for diabetes can promptly identify potential early stage patients, possibly delaying complications and reducing mortality rates. This paper presents a novel technique for early diabetes screening and prediction, called the Attention-Enhanced Deep Neural Network (AEDNN). The proposed AEDNN model incorporates an Attention-based Feature Weighting Layer combined with deep neural network layers to achieve precise diabetes prediction. In this study, we utilized the Diabetes-NHANES dataset and the Pima Indians Diabetes dataset. To handle significant missing values and outliers, group median imputation was applied. Oversampling techniques were used to balance the diabetes and non-diabetes groups. The data were processed through an Attention-based Feature Weighting Layer for feature extraction, producing a feature matrix. This matrix was subjected to Hadamard product operations with the raw data to obtain weighted data, which were subsequently input into deep neural network layers for training. The parameters were fine-tuned and the L2 regularization and dropout layers were added to enhance the generalization performance of the model. The model’s reliability was thoroughly assessed through various metrics, including the accuracy, precision, recall, F1 score, mean squared error (MSE), and R2 score, as well as the ROC and AUC curves. The proposed model achieved a prediction accuracy of 98.4% in the Pima Indians Diabetes dataset. When the test dataset was expanded to the large-scale Diabetes-NHANES dataset, which contains 52,390 samples, the test precision of the model improved further to 99.82%, with an AUC of 0.9995. A comparative analysis was conducted using multiple models, including logistic regression with L1 regularization, support vector machine (SVM), random forest, K-nearest neighbors (KNNs), AdaBoost, XGBoost, and the latest semi-supervised XGBoost. The feature extraction method using attention mechanisms was compared with the classical feature selection methods, Lasso and Ridge. The experiments were performed on the same dataset, and the conclusion was that the Attention-based Ensemble Deep Neural Network (AEDNN) outperformed all the aforementioned methods. These results indicate that the model not only performs well on smaller datasets but also fully leverages its advantages on larger datasets, demonstrating strong generalization ability and robustness. The proposed model can effectively assist clinicians in the early screening of diabetes patients. This is particularly beneficial for the preliminary screening of high-risk individuals in large-scale, extensive healthcare datasets, followed by detailed examination and diagnosis. Compared to the existing methods, our AEDNN model showed an overall performance improvement of 1.75%.

Akrivia Health Database—deep patient characterisation using a secondary mental healthcare dataset in England and Wales: cohort profile

PurposeThe Akrivia Health cohort was created to extract data from electronic health records in secondary mental health and dementia care services in England and Wales. The data are anonymised, structured...

Knowledge abstraction and filtering based federated learning over heterogeneous data views in healthcare

Robust data privacy regulations hinder the exchange of healthcare data among institutions, crucial for global insights and developing generalised clinical models. Federated learning (FL) is ideal for training global models using datasets from different institutions without compromising privacy. However, disparities in electronic healthcare records (EHRs) lead to inconsistencies in ML-ready data views, making FL challenging without extensive preprocessing and information loss. These differences arise from variations in services, care standards, and record-keeping practices. This paper addresses data view heterogeneity by introducing a knowledge abstraction and filtering-based FL framework that allows FL over heterogeneous data views without manual alignment or information loss. The knowledge abstraction and filtering mechanism maps raw input representations to a unified, semantically rich shared space for effective global model training. Experiments on three healthcare datasets demonstrate the framework’s effectiveness in overcoming data view heterogeneity and facilitating information sharing in a federated setup.

RCLNet: an effective anomaly-based intrusion detection for securing the IoMT system.

The Internet of Medical Things (IoMT) has revolutionized healthcare with remote patient monitoring and real-time diagnosis, but securing patient data remains a critical challenge due to sophisticated cyber threats and the sensitivity of medical information. Traditional machine learning methods struggle to capture the complex patterns in IoMT data, and conventional intrusion detection systems often fail to identify unknown attacks, leading to high false positive rates and compromised patient data security. To address these issues, we propose RCLNet, an effective Anomaly-based Intrusion Detection System (A-IDS) for IoMT. RCLNet employs a multi-faceted approach, including Random Forest (RF) for feature selection, the integration of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models to enhance pattern recognition, and a Self-Adaptive Attention Layer Mechanism (SAALM) designed specifically for the unique challenges of IoMT. Additionally, RCLNet utilizes focal loss (FL) to manage imbalanced data distributions, a common challenge in IoMT datasets. Evaluation using the WUSTL-EHMS-2020 healthcare dataset demonstrates that RCLNet outperforms recent state-of-the-art methods, achieving a remarkable accuracy of 99.78%, highlighting its potential to significantly improve the security and confidentiality of patient data in IoMT healthcare systems.

National stakeholder consultation on how to measure care home residents' quality of life.

The Developing research resources And minimum data set for Care Homes' Adoption and use or DACHA study aims to create a prototype minimum data set combining residents' information recorded by care homes with their data held in health and social care data sets. The DACHA minimum data set will contain information on quality of life. Internationally and in the UK, there is no consensus on collecting information on quality of life in a standardised format equivalent to the consensus for health measures. This paper describes an online consultation with stakeholder representatives about how to measure the quality of life of residents in UK older-adult care homes, for inclusion in the DACHA minimum data set. We drew on principles of the Delphi technique, identifying participants knowledgeable about living, working in and visiting care homes, and preference scoring. We used a bespoke online research engagement platform (Thiscovery, www.thiscovery.org, Cambridge, UK) to engage the participants. Participants included care home staff and managers, old age specialists (clinical/research), commissioners/providers/regulators, primary care professionals, relatives/family carers of care home residents. The consultation is complementary to DACHA's research and patient and public involvement and engagement activities, which have involved people living in care homes; thus, care home residents were not included in this consultation. The first round asked 30 participants to rank the most important principles and domains to consider when measuring quality of life in care homes. Responses to round 1 informed the selection of quality of life measures that round 2 (September 2022) participants were asked to report their familiarity with and confidence in a range of outcome measures all of which met the criteria identified as important in round 1. Recruitment was extended in round 2, and 72 individuals participated. Based on the rankings and the qualitative feedback in round 2, we included four of the shortlisted quality of life outcome measures in DACHA's prototype minimum data set for care homes. The qualitative feedback suggested a shared understanding across the different representative groups about the strengths and limitations of the selected measures. This work makes an important contribution, understanding the opportunities that quality of life measures pose for different stakeholder groups as regular users of care home resident data. In future DACHA work, interviews and focus groups will collect further data about the perceptions of care home staff who completed measures during the pilot study and about the usefulness of the data collected via these measures. The quality-of-life section of the DACHA minimum data set can contribute to informing similar care home data sets internationally. This article presents independent research funded by the National Institute for Health and Care Research (NIHR) Health and Social Care Delivery Research programme as award number NIHR127234.

Intelligent cardiovascular disease diagnosis using deep learning enhanced neural network with ant colony optimization

To identify patterns in big medical datasets and use Deep Learning and Machine Learning (ML) to reliably diagnose Cardio Vascular Disease (CVD), researchers are currently delving deeply into these fields. Training on large datasets and producing highly accurate validation results is exceedingly difficult. Furthermore, early and precise diagnosis is necessary due to the increased global prevalence of cardiovascular disease (CVD). However, the increasing complexity of healthcare datasets makes it challenging to detect feature connections and produce precise predictions. To address these issues, the Intelligent Cardiovascular Disease Diagnosis based on Ant Colony Optimisation with Enhanced Deep Learning (ICVD-ACOEDL) model was developed. This model employs feature selection (FS) and hyperparameter optimization to diagnose CVD. Applying a min–max scaler, medical data is first consistently prepared. The key feature that sets ICVD-ACOEDL apart is the use of Ant Colony Optimisation (ACO) to select an optimal feature subset, which in turn helps to upgrade the performance of the ensuring deep learning enhanced neural network (DLENN) classifier. The model reforms the hyperparameters of DLENN for CVD classification using Bayesian optimization. Comprehensive evaluations on benchmark medical datasets show that ICVD-ACOEDL exceeds existing techniques, indicating that it could have a significant impact on CVD diagnosis. The model furnishes a workable way to increase CVD classification efficiency and accuracy in real-world medical situations by incorporating ACO for feature selection, min–max scaling for data pre-processing, and Bayesian optimization for hyperparameter tweaking.

The Networked Data Lab: lessons from four years of analytical collaboration on common problems in health on social care

ObjectiveThe Networked Data Lab (NDL) is a UK-wide network of analytical teams embedded in the health and care system. Each year, we support five local partners to acquire and link new health and social care datasets on a different topic. The NDL provides insights from this linked data to help UK policymakers improve health and care, leveraging public, patient, and stakeholder engagement to prioritise topics of shared local interest. Approach Now in its fourth year, the NDL has commissioned a Learning Study (LS) to evaluate progress towards its aims. This employs a theory-based approach to test and assess key assumptions about programme impact through a Theory of Change. For the study, semi-structured interviews with analysts and stakeholders at the five NDL sites were conducted to identify factors influencing the programme’s impact. ResultsDrawing on interim LS findings, we will describe the types of impact the programme has achieved, and some of the key barriers and enablers to analytical collaboration across geographic and organisational boundaries. Themes include senior sponsorship; stakeholder input into problem definition; information governance and tools and skills. Themes will be illustrated with case studies drawn from the different NDL topic areas, including children and young people’s mental health and unpaid carers. Conclusions and ImplicationsThe Networked Data Lab shows that data linkages can provide unique insights that local service planners can act on, but highlights a complex set of conditions that need to be met to enable impactful analytics using real-world health and care data.

The Networked Data Lab: using linked data to understand intermediate care services in the United Kingdom

Intermediate care (IC) is short-term care aimed at maximising patients’ independence. Across the UK, scaling up IC is included in post-pandemic recovery plans. This could reduce pressures on acute services through timely discharge or preventing admissions. The issues IC seeks to address are common across high-income countries. The Networked Data Lab is a network of analytical teams embedded in the UK health and care system. Each year, we support five local partners with acquisition, linkage and analysis of health and social care datasets. Our 2023-24 project is focused on IC. Patients and the public (PP) played an integral role in throughout our project. We established a panel of individuals with lived experience of IC to assist with the research questions, interpretation, and communication of results. Our partners all consult PP in their areas to inform their analyses. Our partners’ analyses of linked patient-level data on IC will provide information about who is receiving IC, changes over time and outcomes for patients. We are also analysing national linked data for England on intermediate care following hospital discharge. Preliminary results include: The age and health needs of people receiving bed-based intermediate care has increased over time (Grampian, Scotland) Intermediate care following a hospital admission is more common for emergency admissions than elective admissions (Leeds, England) Large variation in intermediate care delivery between neighbouring boroughs (North West London, England) Full results are expected in April 2024. Our work highlights the importance of linking data to answer important health and care questions.

Results from a retrospective case finding and re-engagement exercise for people previously diagnosed with hepatitis C virus to increase uptake of directly acting antiviral treatment

BackgroundDirect acting antivirals (DAAs) for the Hepatitis C virus (HCV) have shifted the World Health Organisation global strategic focus to the elimination of HCV by 2030. In England, the UK Health Security Agency (UKHSA) led a national ‘patient re-engagement exercise’, using routine surveillance data, which was delivered through the HCV Operational Delivery Networks (ODNs) with support from National Health Service England (NHSE), to help find and support people with a positive HCV PCR test result to access treatment. We report a quantitative evaluation of outcomes of this exercise.MethodsIndividuals with a recorded positive HCV antibody or PCR result between 1996 and 2017 were identified using UKHSA’s records of HCV laboratory diagnosis. Linkage with established health-care datasets helped to enhance patient identification and minimise attempts to contact deceased or previously treated individuals. From September to November 2018 each ODN was provided with a local list of diagnosed individuals. ODNs were asked to perform further data quality checks through local systems and then write to each individual’s GP to inform them that the individual would be contacted by the ODN to offer confirmatory HCV PCR testing, assessment and treatment unless the GP advised otherwise. Outcomes of interest were receipt of treatment, a negative PCR result, and death. Data were collected in 2022.ResultsOf 176,555 individuals with a positive HCV laboratory report, 55,329 individuals were included in the exercise following linkage to healthcare datasets and data reconciliation. Participants in the study had a median age of 51 years (IQR: 43, 59), 36,779 (66.5%) were males, 47,668 (86.2%) were diagnosed before 2016 and 11,148 (20.2%) lived in London. Of the study population, 7,442 (13.4%) had evidence of treatment after the re-engagement exercise commenced, 6,435 (11.6%) were reported as PCR negative (96% had no previous treatment records), 4,195 (7.6%) had prescription data indicating treatment before the exercise commenced or were reported to have been treated previously by their ODN, and 2,990 (5.4%) had died. The status of 32,802 (59.3%) people remains unknown.ConclusionsA substantial number of those included had treatment recorded after the exercise commenced, however, many more remain unengaged. Evaluation of the exercise highlighted areas that could be streamlined to improve future exercises.