Healthcare Datasets Research Articles

On responsible machine learning datasets emphasizing fairness, privacy and regulatory norms with examples in biometrics and healthcare

Artificial Intelligence (AI) has seamlessly integrated into numerous scientific domains, catalysing unparalleled enhancements across a broad spectrum of tasks; however, its integrity and trustworthiness have emerged as notable concerns. The scientific community has focused on the development of trustworthy AI algorithms; however, machine learning and deep learning algorithms, popular in the AI community today, intrinsically rely on the quality of their training data. These algorithms are designed to detect patterns within the data, thereby learning the intended behavioural objectives. Any inadequacy in the data has the potential to translate directly into algorithms. In this study we discuss the importance of responsible machine learning datasets through the lens of fairness, privacy and regulatory compliance, and present a large audit of computer vision datasets. Despite the ubiquity of fairness and privacy challenges across diverse data domains, current regulatory frameworks primarily address human-centric data concerns. We therefore focus our discussion on biometric and healthcare datasets, although the principles we outline are broadly applicable across various domains. The audit is conducted through evaluation of the proposed responsible rubric. After surveying over 100 datasets, our detailed analysis of 60 distinct datasets highlights a universal susceptibility to fairness, privacy and regulatory compliance issues. This finding emphasizes the urgent need for revising dataset creation methodologies within the scientific community, especially in light of global advancements in data protection legislation. We assert that our study is critically relevant in the contemporary AI context, offering insights and recommendations that are both timely and essential for the ongoing evolution of AI technologies.

A novel approach for e-health recommender systems

The increasing use of the internet for health information brings challenges due to the complexity and abundance of data, leading to information overload. This highlights the necessity of implementing recommender systems (RSs) within the healthcare domain, with the aim of facilitating more effective and precise healthcare-related decisions for both healthcare providers and users. Health recommendation systems can suggest suitable healthcare items or services based on users' health conditions and needs, including medications, diagnoses, hospitals, doctors, and healthcare services. Despite their potential benefits, RSs encounter significant limitations, including data sparsity, which can lead to recommendations that are unreliable and misleading. Considering the increasing significance of health recommendation systems and the challenge of sparse data, we propose an effective approach to improve precision and coverage in recommending healthcare items or services. This aims to assist users and healthcare practitioners in making informed decisions tailored to their unique needs and health conditions. Empirical testing on two healthcare rating datasets, including sparse datasets, illustrate that our proposed approach outperforms baseline recommendation methods. It excels in improving both the precision and coverage of health-related recommendations, demonstrating effective handling of extremely sparse datasets.

Implementing and evaluating simple resampling techniques in federated learning for imbalanced data

Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving collaborative machine learning. However, the challenge of data imbalance, exacerbated by the non-IID nature of distributed datasets, significantly impacts model performance and fairness in FL systems. This paper investigates the implementation and evaluation of simple resampling techniques to address data imbalance within the FL framework. Using the MIMIC-III healthcare dataset, a simulated FL environment with ten virtual clients was created to test various resampling methods: SMOTE, random undersampling, and a hybrid approach. The study employed logistic regression models and evaluated performance using common and novel FL-specific metrics. Experimental results demonstrate that the hybrid resampling technique significantly outperforms other methods, improving the F1-score by 13.1% and reducing communication rounds by 25.3%. Statistical analyses, including repeated measures ANOVA and hierarchical linear modeling, confirm the robustness of these findings across varied client data distributions. This research provides a replicable framework for addressing data imbalance in FL, contributing to enhanced model fairness and efficiency in privacy-sensitive applications.

Report on the Fifth International Workshop on Health Data Management in the Era of AI (HeDAI 2023)

Artificial intelligence (AI) technologies have the potential to drastically improve healthcare delivery globally. However, healthcare data are diverse, complex, and very large in size. Better information management techniques are needed to deal with the volume and heterogeneity of healthcare data. Better AI techniques are needed to fully harness healthcare datasets to improve healthcare delivery and quality of care for patients. Our workshop aimed to bring together diverse group of researchers and practitioners interested in developing next-generation solutions for challenging problems in healthcare systems. A wide range of topics ranging from federated approaches for data sharing to machine learning for predictive analytics to medical question answering were discussed during the workshop.

Communicating exploratory unsupervised machine learning analysis in age clustering for paediatric disease

BackgroundDespite the increasing availability of electronic healthcare record (EHR) data and wide availability of plug-and-play machine learning (ML) Application Programming Interfaces, the adoption of data-driven decision-making within routine hospital workflows...

Optimization of machine learning models through quantization and data bit reduction in healthcare datasets

This study focuses on enhancing complex machine learning models through quantization and data bit reduction. The primary goal is to reduce processing time while maintaining model performance, which is particularly relevant for intricate models with prolonged execution times. The research employs two medical datasets, namely Heart Disease Prediction and Breast Cancer Detection, and applies optimization techniques to K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) machine-learning models. To achieve optimization, the study employs effective quantization and data bit reduction techniques such as QuantileTransformer, Numpy.round, and KBinsDiscretizer functions. These techniques are utilized to convert input data from float64 to float32 and int32, resulting in a streamlined data representation. The trade-off between processing time and model accuracy is explored, acknowledging that some compromise in accuracy might occur after optimization. The experimentation reveals that there is a noticeable reduction in time complexity after optimization, with a marginal impact on model accuracy. Interestingly, the study concludes that the outcome and efficiency of optimization techniques are influenced not only by the specific technique used but also by the nature of the dataset and machine learning model under consideration. This comprehensive research showcases the applicability of optimization techniques, specifically quantization and data bit reduction, in complex machine learning models. By conducting experiments on medical datasets and analyzing KNN and SVM models, the study underscores the delicate balance between processing time and model accuracy. The findings emphasize that the success of optimization strategies is context-dependent, relying not only on the chosen technique but also on the interplay between the technique, model, and dataset.

Accessible Ecosystem for Clinical Research (Federated Learning for Everyone): Development and Usability Study.

The integrity and reliability of clinical research outcomes rely heavily on access to vast amounts of data. However, the fragmented distribution of these data across multiple institutions, along with ethical and regulatory barriers, presents significant challenges to accessing relevant data. While federated learning offers a promising solution to leverage insights from fragmented data sets, its adoption faces hurdles due to implementation complexities, scalability issues, and inclusivity challenges. This paper introduces Federated Learning for Everyone (FL4E), an accessible framework facilitating multistakeholder collaboration in clinical research. It focuses on simplifying federated learning through an innovative ecosystem-based approach. The "degree of federation" is a fundamental concept of FL4E, allowing for flexible integration of federated and centralized learning models. This feature provides a customizable solution by enabling users to choose the level of data decentralization based on specific health care settings or project needs, making federated learning more adaptable and efficient. By using an ecosystem-based collaborative learning strategy, FL4E encourages a comprehensive platform for managing real-world data, enhancing collaboration and knowledge sharing among its stakeholders. Evaluating FL4E's effectiveness using real-world health care data sets has highlighted its ecosystem-oriented and inclusive design. By applying hybrid models to 2 distinct analytical tasks-classification and survival analysis-within real-world settings, we have effectively measured the "degree of federation" across various contexts. These evaluations show that FL4E's hybrid models not only match the performance of fully federated models but also avoid the substantial overhead usually linked with these models. Achieving this balance greatly enhances collaborative initiatives and broadens the scope of analytical possibilities within the ecosystem. FL4E represents a significant step forward in collaborative clinical research by merging the benefits of centralized and federated learning. Its modular ecosystem-based design and the "degree of federation" feature make it an inclusive, customizable framework suitable for a wide array of clinical research scenarios, promising to revolutionize the field through improved collaboration and data use. Detailed implementation and analyses are available on the associated GitHub repository.

Postpartum haemorrhage and risk of cardiovascular disease in later life: A population-based record linkage cohort study.

To investigate the association between postpartum haemorrhage (PPH) and subsequent cardiovascular disease. Population-based retrospective cohort study, using record linkage between Aberdeen Maternity and Neonatal Databank (AMND) and Scottish healthcare data sets. Grampian region, Scotland. A cohort of 70 904 women who gave birth after 24 weeks of gestation in the period 1986-2016. We used extended Cox regression models to investigate the association between having had one or more occurrences of PPH in any (first or subsequent) births (exposure) and subsequent cardiovascular disease, adjusted for sociodemographic, medical, and pregnancy and birth-related factors. Cardiovascular disease identified from the prescription of selected cardiovascular medications, hospital discharge records or death from cardiovascular disease. In our cohort of 70 904 women (with 124 795 birth records), 25 177 women (36%) had at least one PPH. Compared with not having a PPH, having at least one PPH was associated with an increased risk of developing cardiovascular disease, as defined above, in the first year after birth (adjusted hazard ratio, aHR 1.96; 95% confidence interval, 95% CI 1.51-2.53; p < 0.001). The association was attenuated over time, but strong evidence of increased risk remained at 2-5 years (aHR 1.19, 95% CI 1.11-1.30, P < 0.001) and at 6-15 years after giving birth (aHR 1.17, 95% CI 1.05-1.30, p = 0.005). Compared with women who have never had a PPH, women who have had at least one episode of PPH are twice as likely to develop cardiovascular disease in the first year after birth, and some increased risk persists for up to 15 years.

RWD112 Going Beyond Claims: Unleashing the Power of Diverse Healthcare Datasets in Clinical and HEOR Assessments

RWD112 Going Beyond Claims: Unleashing the Power of Diverse Healthcare Datasets in Clinical and HEOR Assessments

Risk of drug-related death associated with co-prescribing of gabapentinoids and Z-drugs among people receiving opioid-agonist treatment: A national retrospective cohort study

BackgroundPrescribing of gabapentinoids and Z-drug-hypnotics has increased in the population and among people receiving opioid-agonist treatment (OAT) for opioid dependence. Evidence is mixed on whether co-prescribing of sedatives such as gabapentinoids and Z-drugs during OAT increases risk of drug-related death (DRD). MethodsWe conducted a retrospective cohort study of individuals prescribed OAT between 2011 and 2020 in Scotland. Prescribing records were linked to mortality data and other healthcare datasets (sociodemographic, comorbidity). We identified episodes of treatment with gabapentinoids/Z-drugs and used multivariable quasi-Poisson regression to model associations between co-prescription and DRD risk. ResultsAmong 46,602 individuals with 304,783 person-years of follow-up, we found that co-prescription was common, with 25 % and 34 % ever being co-prescribed gabapentinoids and Z-drugs, respectively. Gabapentinoid exposure was strongly associated (adjusted hazard ratio (aHR)=2·18, 95 % CI=1·92, 2·46) and Z-drug exposure moderately associated (aHR=1·39, 95 % CI=1·15, 1·66) with elevated risk of DRD. Gabapentinoid exposure was associated with DRD risk on and off OAT; Z-drug exposure was less strongly associated with DRD risk when on OAT. ConclusionsCo-prescription of gabapentinoids and Z-drugs is common among OAT patients. However, co-prescription is associated with increased risk of DRD. Alternatives to prescribing sedative medications to OAT patients and/or greater monitoring – if prescribed – are needed.

Real-life effectiveness of sacubitril/valsartan in older Belgians with heart failure, reduced ejection fraction and most severe symptoms

We assessed the real-world effectiveness of sacubitril/valsartan in patients with chronic heart failure (HF) and reduced ejection fraction (HFrEF) with an emphasis on those with older age (≥ 75 years) or with New York Heart Association (NYHA) class IV, for whom greater uncertainty existed regarding clinical outcomes. We conducted a retrospective cohort study based on patient-level linkage of electronic healthcare datasets. Data from all adults with HFrEF in Belgium receiving a prescription for sacubitril/valsartan between 01-November-2016 and 31-December-2018 were collected, with a follow-up of > 6 years. The total study population comprised 5446 patients, older than the PARADIGM-HF trial participants, and with higher NYHA class (all P < 0.0001). NYHA class improved following sacubitril/valsartan initiation (P < 0.0001 baseline vs. reassessment). Most concomitant medications were reduced. Remarkably, the risk of hospitalization for a cardiovascular reason and for HF was reduced by > 26% in the overall cohort, and in subgroups of patients ≥ 75 years, with NYHA class III/IV (all P < 0.0001) or with NYHA class IV (P < 0.05), vs. baseline. All-cause mortality did not increase in real-world patients with NYHA class III/IV. The results support the long-term beneficial effects of sacubitril/valsartan in older patients and in those experiencing the most severe symptoms.

The Evolving Role of Artificial Intelligence in Radiotherapy Treatment Planning—A Literature Review

This paper examines the integration of artificial intelligence (AI) in radiotherapy for cancer treatment. The importance of radiotherapy in cancer management and its time-intensive planning process make AI adoption appealing especially with the escalating demand for radiotherapy.This review highlights the efficacy of AI across medical domains, where it surpasses human capabilities in areas such as cardiology and dermatology. Focusing on radiotherapy, the paper details AI's applications in target segmentation, dose optimization, and outcome prediction. It discusses adaptive radiotherapy's benefits and AI's potential to enhance patient outcomes with much improved treatment accuracy. The paper explores ethical concerns, including data privacy and bias, stressing the need for robust guidelines. Educating healthcare professionals and patients about AI's role is crucial as it acknowledges potential job-role changes and concerns about patients' trust in the use of AI.Overall, the integration of AI in radiotherapy holds transformative potential in streamlining processes, improving outcomes, and reducing costs. AI's potential to reduce healthcare costs underscores its significance with impactful change globally. However, successful implementation hinges on addressing ethical and logistical challenges and fostering collaboration among healthcare professionals and patient population data sets for its optimal utilization. Rigorous education, collaborative efforts, and global data sharing will be the compass guiding its' success in radiotherapy and healthcare.

The risk of repeated suicidal presentations following residential treatment for substance use disorders: A recurrent event analysis using linked administrative data

BackgroundIndividuals seeking alcohol and other drug (AOD) treatment consistently experience higher rates of suicidal behaviours and death by suicide when compared to the general population. By linking residential AOD treatment data to administrative healthcare and death datasets, we aimed to examine suicide-related behaviours and identify risk and protective factors for these events following discharge from residential treatment. MethodsParticipants included 1056 individuals aged 18–69 (M = 32.06, SD = 9.55, male = 696,65.9 %) admitted to three residential treatment facilities in Queensland, Australia from January 1, 2014 to December 31, 2016. Treatment data was linked to administrative hospital, emergency department (ED), mental health service, and Registry of Deaths data 2-years post-discharge. ICD-10 codes were used to identify and analyse suicide-related events. ResultsWithin 2-years post-discharge, 175 (16.6 %) individuals had a suicide-related event (n = 298 episodes). The highest proportion of episodes (11.1 %) occurred within 1-month of discharge. Higher risk of a recurrent suicide-related event was associated with receiving a Disability Support Pension (aHR = 1.69 (95%CI:1.10,2.59), two or more previous episodes of residential AOD treatment (aHR = 1.49 (95%CI:1.30,2.15). Completing residential treatment was associated with a lower risk of suicide-related events (aHR = 0.54 (95%CI:0.35,0.83). LimitationsThe amalgamation of suicidal ideation, attempts, and death into a single outcome oversimplifies their complex nature and interplay. The exclusive focus on one service provider limits generalisability, and data constraints and missingness preclude many analyses. ConclusionsUnderstanding suicidal behaviours and critical risk periods following discharge from residential treatment is crucial for improving continuing care, developing effective suicide prevention, and implementing targeted interventions among this high-risk population.

ETL-FEXIC Model For Secured Heart Rate Abnormality Healthcare Framework

In traditional methods, it is critical for an effective continuous pulse monitor for humans prone to heart rate abnormalities. This paper proposes a secured heartrate abnormality detector which continuously monitors human pulse rate and SpO2 level. The current studies proposes that machine learning (ML) models performs well in classification; also, TinyML model shows better performance for data from resource constrained IoT devices. Hence, the research first analyses abnormal heart rate detection and spam data identification using standard ML algorithms such as SVM, Random Forest, Decision Tree, and TinyML. Though ML models are superior in classification, deep learning approaches outperforms them in feature learning. Hence, our proposed framework combines the merits of both ML and DL models. In our approach, the generated healthcare dataset is fed to DL models such as ANN, and autoencoder and also to SHAP XAI (eXplainable Artificial Intelligence) for feature extraction and learning. These learnt features are fed to ML models for classification. In this experiment, the proposed ETL-FEXIC (Enhanced Tiny Machine Learning with Automated Feature Extraction) outperforms the other ML models where the extracted features from XAI is fed to optimized TinyML classification model.

Application of artificial intelligence to hepatobiliary cancer clinical outcomes research

The rapid evolution of modern technology has made artificial intelligence (AI) an important emerging tool in healthcare. AI, which is a broad field of computer science, can be used to develop systems or machines equipped with the ability to tackle tasks that traditionally necessitate human intelligence. AI can be used to perform multifaceted tasks that involve the synthesis of large amounts of data with the generation of solutions, algorithms, and decision support tools. Various AI approaches, including machine learning (ML) and natural language processing (NLP), are increasingly being used to analyze vast healthcare datasets. In addition, visual AI has the potential to revolutionize surgery and the intraoperative experience for surgeons through augmented reality enhancing surgical navigation in real-time. Specific applications of AI in hepatobiliary tumors such as hepatocellular carcinoma and biliary tract cancer can improve patient diagnosis, prognostic risk stratification, as well as treatment allocation based on ML-based models. The integration of radiomics data and AI models can also improve clinical decision making. We herein review how AI may be of particular interest in the care of patients with complex cancers, such as hepatobiliary tumors, as these patients often require a multimodal treatment approach.

AI ASSISTANCE FOR HEALTHCARE USING NLP

Artificial Intelligence (AI) integration into healthcare has the potential to transform patient care, diagnostics, and treatment. This paper provides a detailed overview of AI support in healthcare, focusing on the intersection of (NLP) Natural Language Processing, (ML) Machine Learning, and (DS) Data Science. By employing the power of these slice- edge technologies, AI can offer intelligent, data- driven results to ameliorate healthcare delivery. Natural Language Processing( NLP) is employed to prize precious perceptivity from medical textbooks, clinical notes, and case records. This enables healthcare providers to more understand patient histories and make informed opinions. Machine literacy ways are abused to prognosticate complaint issues, identify anomalies, and epitomize treatment plans. also, data wisdom plays a vital part in aggregating and analysing large healthcare datasets, icing data security, and maintaining compliance with nonsupervisory norms. The paper explores colorful AI operations in healthcare, similar as automated opinion and triage, medical image analysis, medicine discovery, and patient monitoring. These operations have the eventuality to enhance clinical decision- timber, reduce medical crimes, and ameliorate patientoutcomes.AI backing in healthcare isn't without its challenges, including data sequestration enterprises, the need for robust model interpretability, and ethical considerations. The paper discusses these issues and presents strategies to address them. In conclusion, the integration of AI, NLP, Machine literacy, and Data Science in healthcare has the implicit to marshal in a new period of perfection drug and case- centred care. Then we used SVM Algorithm for training the data set and the delicacy position is 97 percent. This technology confluence is poised to revise healthcare by perfecting opinion delicacy, treatment efficacy-ity, and patient issues while icing data security and ethical use.

Shortcut learning in medical AI hinders generalization: method for estimating AI model generalization without external data

Healthcare datasets are becoming larger and more complex, necessitating the development of accurate and generalizable AI models for medical applications. Unstructured datasets, including medical imaging, electrocardiograms, and natural language data, are gaining attention with advancements in deep convolutional neural networks and large language models. However, estimating the generalizability of these models to new healthcare settings without extensive validation on external data remains challenging. In experiments across 13 datasets including X-rays, CTs, ECGs, clinical discharge summaries, and lung auscultation data, our results demonstrate that model performance is frequently overestimated by up to 20% on average due to shortcut learning of hidden data acquisition biases (DAB). Shortcut learning refers to a phenomenon in which an AI model learns to solve a task based on spurious correlations present in the data as opposed to features directly related to the task itself. We propose an open source, bias-corrected external accuracy estimate, PEst, that better estimates external accuracy to within 4% on average by measuring and calibrating for DAB-induced shortcut learning.

Patterns of Service Utilization across the Full Continuum of Care: Using Patient Journeys to Assess Disparities in Access to Health Services

Healthcare organizations have a contractual obligation to the public to address population-level inequities to health services access and shed light on them. Various studies have focused on achieving equitable access to healthcare services for vulnerable patients. However, these studies do not provide a nuanced perspective based on the local reality across the full continuum of care. In previous work, graph topology was used to provide visual depictions of the dynamics of patients’ movement across a complex healthcare system. Using patients’ encounters data represented as a graph, this study expands on previous work and proposes a methodology to identify and quantify cohort-specific disparities in accessing healthcare services across the continuum of care. The result has demonstrated that a more nuanced approach to assessing access-to-care disparity is doable using patients’ patterns of service utilization from a longitudinal cross-continuum healthcare dataset. The proposed method can be used as part of a toolkit to support healthcare organizations that wish to structure their services to provide better care to their vulnerable populations based on the local realities. This provides a first step in addressing inequities for vulnerable patients in accessing healthcare services. However, additional steps need to be considered to fully address these inequities.

A comparison of frailty measures in population-based data for patients with colorectal cancer.

Numerous studies have revealed age-related inequalities in colorectal cancer care. Increasing levels of frailty in an ageing population may be contributing to this, but quantifying frailty in population-based studies is challenging. To assess the feasibility, validity and reliability of the Hospital Frailty Risk Score (HFRS), the Secondary Care Administrative Records Frailty (SCARF) index and the frailty syndromes (FS) measures in a national colorectal cancer cohort. Retrospective population-based study using 136,008 patients with colorectal cancer treated within the English National Health Service. Each measure was generated in the dataset to assess their feasibility. The diagnostic codes used in each measure were compared with those in the Charlson Comorbidity Index (CCI). Validity was assessed using the prevalence of frailty and relationship with 1-year survival. The Brier score and the c-statistic were used to assess performance and discriminative ability of models with included each measure. All measures demonstrated feasibility, validity and reliability. Diagnostic codes used in SCARF and CCI have considerable overlap. Prevalence of frailty determined by each differed; SCARF allocating 55.4% of the population to the lowest risk group compared with 85.1% (HFRS) and 81.2% (FS). HFRS and FS demonstrated the greatest difference in 1-year overall survival between those with the lowest and highest measured levels of frailty. Differences in model performance were marginal. HFRS, SCARF and FS all have value in quantifying frailty in routine administrative health care datasets. The most suitable measure will depend on the context and requirements of each individual epidemiological study.

Modelling of healthcare data analytics using optimal machine learning model in big data environment

AbstractRecent advances in wireless networking, big data technologies, namely Internet of Things (IoT) 5G networks, health care big data analytics, and other technologies in artificial intelligence (AI) and wearables, have supported the progression of intellectual disease diagnosis methods. Medical data covers all patient data such as pharmacy texts, electronic health reports (EHR), prescriptions, study data from medical journals, clinical photographs, and diagnostic reports. Big data is a renowned method in the healthcare sector, with beneficial datasets that are highly difficult, voluminous, and rapid for healthcare providers for interpreting and computing using prevailing tools. This study combines concepts like deep learning (DL) and big data analytics in medical field. This article develops a new healthcare data analytics using optimal machine learning model in big data environment (HDAOML‐BDE) technique. The presented HDAOML‐BDE technique mainly aims to examine the healthcare data for disease detection and classification in the big data environment. For handling big data, the HDAOML‐BDE technique uses Hadoop MapReduce environment. In addition, the HDAOML‐BDE technique uses manta ray foraging optimization‐based feature selection (MRFO‐FS) technique to reduce high dimensionality problems. Moreover, the HDAOML‐BDE method uses relevance vector machine (RVM) model for the healthcare data environment. Furthermore, the arithmetic optimization algorithm (AOA) is utilized for the parameter tuning of the RVM classifier. The simulation results of the HDAOML‐BDE technique are tested on a healthcare dataset, and the outcomes portray the improved performance of the HDAOML‐BDE strategy over recent approaches in different measures.