Search Results (270)

Background/Objectives: The COVID-19 pandemic has been associated with significant increases in mental-health-related concerns in adolescents, including eating disorders. Disparities in screening, diagnosis, and treatment impact adolescents with eating disorders. This study aimed to describe the patterns in the prevalence and the associations between eating disorder diagnoses and demographic factors in adolescent patients since the start of the COVID-19 pandemic. Methods: We performed a retrospective cohort study examining adolescent patients (aged 12 to 21) with an eating disorder (ED) diagnosis documented between January 2019 and July 2023 using Epic Systems Corporation’s Cosmos, a de-identified dataset aggregated from electronic health record (EHR) data. We examined the differences in demographic factors by utilizing chi-square and Kruskal–Wallis rank sum tests. Results: A total of 82,435 distinct adolescent and young adult patients with eating disorder diagnoses were included in the analytical dataset. The overall prevalence of EDs has increased since 2019. The median age of patients with an ED decreased between 2019 and 2023. There was a decrease in other eating disorder diagnoses and an increase in avoidant-restrictive food intake disorder (ARFID) during the study period. There was a decrease in the proportion of individuals who identified as White and an increase in the proportion of adolescents from historically minoritized racial and ethnic groups (i.e., African American or Black and Hispanic). There was also an increase, during this study period, in the proportion of adolescents with an ED diagnosis who were from more socially vulnerable communities. Conclusions: Our study describes the changes in the prevalence of sociodemographic factors in adolescent patients with EDs since the start of the COVID-19 pandemic. Further studies should address screening, diagnostic, and treatment barriers for EDs in historically underserved communities. Full article

Electronic Health Records (EHRs) offer valuable insights for healthcare prediction. Existing methods approach EHR analysis through direct imputation techniques in data space or representation learning in feature space. However, these approaches face the following two critical limitations: first, they struggle to model long-term clinical pathways due to their focus on isolated time points rather than continuous health trajectories; second, they lack mechanisms to effectively distinguish between clinically relevant and redundant features when observations are irregular. To address these challenges, we introduce PathCare, a neural framework that integrates clinical pathway information into prediction tasks at the neuron level. PathCare employs an auxiliary sub-network that models future visit patterns to capture temporal health progression, coupled with a neuron-level filtering gate that adaptively selects relevant features while filtering out redundant information. We evaluate PathCare on the following three real-world EHR datasets: CDSL, MIMIC-III, and MIMIC-IV, demonstrating consistent performance improvements in mortality and readmission prediction tasks. Our approach offers a practical solution for enhancing healthcare predictions in real-world clinical settings with varying data completeness. Full article

Since the outbreak of the COVID-19 pandemic in 2020, numerous studies have focused on the long-term effects of COVID infection. On 1 October 2021, the Centers for Disease Control (CDC) implemented a new code in the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) for reporting ‘Post COVID-19 condition, unspecified (U09.9)’. This change indicated that the CDC recognized Long COVID as a real illness with associated chronic conditions. The National COVID Cohort Collaborative (N3C) provides researchers with abundant electronic health record (EHR) data by harmonizing EHR data across more than 80 different clinical organizations in the United States. This paper describes the creation of a COVID-positive N3C cohort balanced by the presence or absence of Long COVID (U09.9) and evaluates whether or not documented Long COVID (U09.9) is associated with decreased survival length. Full article

Background and Objectives: Peritoneal dialysis (PD) requires well-functioning medical devices (MDs). PD complications can result in significant adverse events, including the discontinuation of PD, hospitalization, and death. This study aimed to evaluate the feasibility of detecting various PD complications and data related to MDs. Materials and Methods: A retrospective study was conducted on patients who received PD catheter insertions between January 2001 and March 2021 to evaluate PD-related complications. PD complications were evaluated through diagnostic, procedural, and MD codes using a common data model (CDM) and were compared with those from electronic health records (EHRs). The results from one CDM database were compared with those from another CDM database. Results: A total of 342 patients were enrolled. One hundred and ninety-five patients experienced PD complications more than once. Nineteen prescription codes and twenty diagnostic codes from the EHR were identified, covering 11 procedures, three MDs, and seven complications related to PD. Infectious complications were detected using the CDM, whereas mechanical complications were missed. Although data on PD catheters and adaptors were available in the EHR, they were not detected via the CDM. Some infectious and mechanical complications were identified via the CDM in the other database. After implementing amended matching, these data were detected. Conclusions: While some PD-related medical data recorded in EHRs were misrepresented or omitted during the CDM database extraction, transformation, and loading process, the CDM shows potential to serve as a source of real-world data for active surveillance. Full article

The advancement of biomedical research depends on efficient data sharing, integration, and annotation to ensure reproducibility, accessibility, and cross-disciplinary collaboration. International collaborative research is crucial for advancing biomedical science and innovation but often faces significant barriers, such as data sharing limitations, inefficient sample management, and scalability challenges. Existing infrastructures for biosample and data repositories face challenges limiting large-scale research efforts. This study presents a novel platform designed to address these issues, enabling researchers to conduct high-quality research more efficiently and at reduced costs. The platform employs a modular, distributed architecture that ensures high availability, redundancy, and interoperability among diverse stakeholders, as well as integrates advanced features, including secure access management, comprehensive query functionalities, real-time availability reporting, and robust data mining capabilities. In addition, this platform supports dynamic, multi-criteria searches tailored to disease-specific patient profiles and biosample-related data across pre-analytical, post-analytical, and cryo-storage processes. By evaluating the platform’s modular architecture and pilot testing outcomes, this study demonstrates its potential to enhance interdisciplinary collaboration, streamline research workflows, and foster transformative advancements in biomedical research. The key is the innovation of a real-time dynamic e-consent (DRT e-consent) system, which allows donors to update their consent status in real time, ensuring compliance with ethical and regulatory frameworks such as GDPR and HIPAA. The system also supports multi-modal data integration, including genomic sequences, electronic health records (EHRs), and imaging data, enabling researchers to perform complex queries and generate comprehensive insights. Full article

Brain stroke is the leading cause of death and disability globally; hence, early identification and prediction are critical for better patient outcomes. Traditional diagnostic procedures, such as manually interpreting clinical images, are time consuming and error prone. This research investigates the use of hybrid deep learning models, such as recurrent neural networks (RNNs), long short-term memory (LSTM), and convolutional neural networks (CNNs), to improve stroke prediction accuracy. The current study compared the performance of these individual models with the developed hybrid model on the brain stroke dataset. By merging these models, we reached an overall accuracy of 96% in identifying stroke risk as low, medium, or high. This categorization may offer healthcare practitioners actionable insights by assisting them and allowing them to make better decisions. This technique represents a substantial improvement in stroke prediction and preventive healthcare practices. The model’s performance can further be tested with more complicated clinical and demographic data that will help to generalize the model for real-world clinical applications. Furthermore, combining this hybrid model with electronic health records (EHR) systems can also assist in early identification, tailored therapies, and improved stroke management, enhancing patient outcomes and lowering healthcare costs. Full article

Deidentifying sensitive information in electronic health records (EHRs) is increasingly important as legal obligations to data privacy evolve along with the need to protect patient and institutional confidentiality. This study aims to comparatively evaluate the performance of two state-of-the-art deidentification systems, Deduce and Deidentify, on both real-world and synthetic Dutch medical texts, thereby providing insights into their relative strengths and limitations in preserving privacy while maintaining data utility. We employ a replication-extension research design, utilizing two distinct datasets: (1) the Annotation-Based Dataset from the Utrecht University Medical Center (UMC Utrecht), comprising manually annotated patient records spanning 1987 to 2021, and (2) the Synthetic Dataset, generated using a two-step process involving OpenAI’s GPT-4 model. Utilizing precision, recall, and $F_1$ scores as evaluation metrics, we uncover the relative strengths and limitations of the two methods. Our findings indicate that both techniques show variable performance across different entities of deidentifying text information. Deduce outperforms Deidentify in overall accuracy by a margin of 0.42 on the synthetic datasets. On the real-world annotation-based dataset, the generalization ability of Deidentify is lower than Deduce by 0.2. However, the performance of both techniques is affected by the limitations of the dataset. In conclusion, this study provides valuable insights into the comparative performance of Deduce and Deidentify for deidentifying Dutch EHRs, contributing to the development of more effective privacy preservation techniques in the healthcare domain. Full article

Immune checkpoint inhibitors (ICIs) have transformed melanoma treatment; however, predicting patient responses remains a significant challenge. This study reviews the potential of artificial intelligence (AI) to optimize ICI therapy in melanoma by integrating various diagnostic tools. Through a comprehensive literature review, we analyzed studies on AI applications in melanoma immunotherapy, focusing on predictive modeling, biomarker identification, and treatment response prediction. Key findings highlight the efficacy of AI in improving ICI outcomes. Machine learning models successfully identified prognostic cytokine signatures linked to nivolumab clearance. The combination of AI with RNAseq analysis had the potential for the development of personalized treatment with ICIs. A machine learning-based approach was able to assess the risk-benefit ratio for the prediction of immune-related adverse events (irAEs) using the electronic health record (EHR) data. Deep learning algorithms demonstrated high accuracy in tumor microenvironment analysis, including tumor region identification and lymphocyte detection. AI-assisted quantification of tumor-infiltrating lymphocytes (TILs) proved prognostically valuable in primary melanoma and predictive of anti-PD-1 therapy response in metastatic cases. Integrating multiple diagnostic modalities, such as CT imaging and laboratory data, modestly enhanced predictive performance for 1-year survival in advanced cancers treated with immunotherapy. These findings underscore the potential of AI-driven approaches to refine biomarker identification, treatment prediction, and patient stratification in melanoma immunotherapy. While promising, clinical validation and implementation challenges remain. Full article

Background: Artificial Intelligence (AI) techniques, particularly Deep Learning (DL) and Natural Language Processing (NLP), have seen exponential growth in the biomedical field. This study focuses on enhancing predictive models for atrial fibrillation (AF) recurrence by extracting valuable data from electronic health records (EHRs) and unstructured medical reports. Although existing models show promise, their reliability is hampered by inaccuracies in coded data, with significant false positives and false negatives impacting their performance. To address this, the authors propose an automated system using DL and NLP techniques to process medical reports, extracting key predictive variables, and identifying new AF cases. The main purpose is to improve dataset reliability so future predictive models can respond more accurately Methods and Results: The study analyzed over one million discharge reports, applying regular expressions and DL tools to extract variables and identify AF onset. The performance of DL models, particularly a feedforward neural network combined with tf-idf, demonstrated high accuracy (0.986) in predicting AF onset. The application of DL tools on unstructured text reduced the error rate in AF identification by 50%, achieving an error rate of less than 2%. Conclusions: This work underscores the potential of AI in optimizing dataset accuracy to develop predictive models and consequently improving the healthcare predictions, offering valuable insights for research groups utilizing secondary data for predictive analytics in this particular setting. Full article

Recent advancements in wearable devices have significantly enhanced remote patient monitoring, enabling healthcare professionals to evaluate conditions within home settings. While electronic health records (EHRs) offer extensive clinical data, they often lack crucial contextual information about patients’ daily lives and symptoms. By integrating continuous self-reported outcomes related to vulnerability, anxiety, and depression from older adult cancer survivors with objective data from wearables, we can develop personalised risk models that address time-varying risk factors in cancer care. Our study combines real-world data from wearable devices with self-reported information, employing process mining techniques to analyse dynamic risk models for vulnerability and anxiety. Unlike traditional static assessments, this approach recognises that risk factors evolve. Collaborating with healthcare professionals, we analysed data from the LifeChamps study to create two dynamic risk models. This collaborative effort revealed how activity and sleep patterns influence self-reported vulnerability and anxiety among participants. It underscored the potential of wearable sensors and artificial intelligence techniques for deeper analysis and understanding, making us all part of a larger effort in cancer care. Overall, patients with prolonged sedentary activity had a higher risk of vulnerability, while those with highly dynamic sleep patterns were more likely to report anxiety and depression. Prostate-metastatic patients showed an increased risk of vulnerability compared to other cancer types. Full article

Artificial intelligence (AI) is playing a dominant role in advancing heart failure detection and diagnosis, significantly furthering personalized healthcare. This review synthesizes AI-driven innovations by examining methodologies, applications, and outcomes. We investigate the integration of machine learning algorithms, diverse datasets including electronic health records (EHRs), medical records, imaging data, and clinical notes, deep learning models, and neural networks to enhance diagnostic accuracy. Key advancements include prediction models that leverage real-time data from wearable devices alongside state-of-the-art AI systems trained on patient data from hospitals and clinics. Notably, recent studies have reported diagnostic accuracies ranging from 86.7% to as high as 99.9%, with sensitivity and specificity values often exceeding 97%, underscoring the potential of these AI systems to improve early detection and clinical decision-making substantially. Our review further explores the impact of symmetry and asymmetry in model design, highlighting that symmetric architectures like U-Net offer computational efficiency and structured feature extraction. In contrast, asymmetric models improve the sensitivity to rare conditions and subtle clinical patterns. Incorporating these deep learning (DL) methods in anomaly detection and disease progression modeling further reinforces their positive impact on diagnostic accuracy and patient outcomes. Furthermore, this review identifies challenges in current AI applications, such as data quality, algorithmic transparency, model bias, and evaluation metrics, while outlining future research directions, including integrating generative models, hybrid architectures, and explainable AI techniques to optimize clinical practice. Full article

Objective: Electronic health records (EHRs) are becoming increasingly important in both academic research and business applications. Recent studies indicate that predictive tasks, such as heart failure detection, perform better when the geometric structure of EHR data, including the relationships between diagnoses and treatments, is considered. However, many EHRs lack essential structural information. This study aims to improve predictive accuracy in healthcare by constructing a Patient Knowledge Graph Ensemble Framework (PKGNN) to analyse ICU patient cohorts and predict mortality and hospital readmission outcomes. Methods: This study utilises a cohort of 42,671 patients from the MIMIC-IV dataset to build the PKGNN framework, which consists of three main components: (1) medical note extraction, (2) patient graph construction, and (3) prediction tasks. Advanced Natural Language Processing (NLP) models, including Clinical BERT, BioBERT, and BlueBERT, extract and integrate semantic representations from discharge summaries into a patient knowledge graph. This structured representation is then used to enhance predictive tasks. Results: Performance evaluations on the MIMIC-IV dataset indicate that the PKGNN framework outperforms state-of-the-art baseline models in predicting mortality and 30-day hospital readmission. A thorough framework analysis reveals that incorporating patient graph structures improves prediction accuracy. Furthermore, an ensemble model enhances risk prediction performance and identifies crucial clinical indicators. Conclusions: This study highlights the importance of leveraging structured knowledge graphs in EHR analysis to improve predictive modelling for critical healthcare outcomes. The PKGNN framework enhances the accuracy of mortality and readmission predictions by integrating advanced NLP techniques with patient graph structures. This work contributes to the literature by advancing knowledge graph-based EHR analysis strategies, ultimately supporting better clinical decision-making and risk assessment. Full article

Mental health illness is the single biggest cause of inability within the UK, contributing up to 22.8% of the whole burden compared to 15.9% for cancer and 16.2% for cardiovascular disease. The more extensive financial costs of mental ailments in Britain have been evaluated at British Pound Sterling (GBP) 105.2 billion each year. This burden could be decreased with productive forms and utilization of computerized innovations. Electronical health records (EHRs), for instance, could offer an extraordinary opportunity for research and provide improved and optimized care. Consequently, this technological advance would unburden the mental health system and help provide optimized and efficient care to the patients. Using natural language processing methods to explore unstructured EHR text data from mental health services in the National Health Service (NHS) UK brings opportunities and technical challenges in the use of such data and possible solutions. This descriptive study compared technical methods and approaches to leverage large-scale text data in EHRs of mental health service providers in the NHS. We conclude that the method used is suitable for mental health services. However, broader studies including other hospital sites are still needed to validate the method. Full article

Background/Objective: Subarachnoid hemorrhage (SAH) is associated with high morbidity and mortality rates, necessitating prognostic algorithms to guide decisions. Our study evaluates the use of machine learning (ML) models for predicting 1-month and 1-year mortality among SAH patients using national electronic health records (EHR) system. Methods: Retrospective cohort of 29,274 SAH patients, identified through national EHR system from January 2017 to December 2022, was analyzed, with mortality data obtained from central civil registration system in Türkiye. Variables included (n = 102) pre- (n = 65) and post-admission (n = 37) data, such as patient demographics, clinical presentation, comorbidities, laboratory results, and complications. We employed logistic regression (LR), decision trees (DTs), random forests (RFs), and artificial neural networks (ANN). Model performance was evaluated using area under the curve (AUC), average precision, and accuracy. Feature significance analysis was conducted using LR. Results: The average age was 56.23 ± 16.45 years (47.8% female). The overall mortality rate was 22.8% at 1 month and 33.3% at 1 year. One-month mortality increased from 20.9% to 24.57% (p < 0.001), and 1-year mortality rose from 30.85% to 35.55% (p < 0.001) in the post-COVID period compared to the pre-COVID period. For 1-month mortality prediction, the ANN, LR, RF, and DT models achieved AUCs of 0.946, 0.942, 0.931, and 0.916, with accuracies of 0.905, 0.901, 0.893, and 0.885, respectively. For 1-year mortality, the AUCs were 0.941, 0.927, 0.926, and 0.907, with accuracies of 0.884, 0.875, 0.861, and 0.851, respectively. Key predictors of mortality included age, cardiopulmonary arrest, abnormal laboratory results (such as abnormal glucose and lactate levels) at presentation, and pre-existing comorbidities. Incorporating post-admission features (n = 37) alongside pre-admission features (n = 65) improved model performance for both 1-month and 1-year mortality predictions, with average AUC improvements of 0.093 ± 0.011 and 0.089 ± 0.012, respectively. Conclusions: Our study demonstrates the effectiveness of ML models in predicting mortality in SAH patients using big data. LR models’ robustness, interpretability, and feature significance analysis validate its importance. Including post-admission data significantly improved all models’ performances. Our results demonstrate the utility of big data analytics in population-level health outcomes studies. Full article

Many efforts have proved that deep learning models are effective for disease prediction using electronic health records (EHRs). However, these models are not yet precise enough to predict diseases. Additionally, ethical concerns and the use of clustering and classification algorithms on small datasets limit their effectiveness. The complexity of data processing further complicates the interpretation of patient representation learning models, even though data augmentation strategies may help. Incomplete patient data also hinder model accuracy. This study aims to develop and evaluate a deep learning model that addresses these challenges. Our proposed approach is to design a disease prediction model based on deep Q-learning (DQL), which replaces the traditional Q-learning reinforcement learning algorithm with a neural network deep learning model, and the mapping capabilities of the Q-network are utilized. We conclude that the proposed model achieves the best accuracy (98%) compared with other models. Full article