Clinical Decision Research Articles

Security of Magnetic Resonance Medical Images using Region-based Lossless Image Compression in Healthcare Information Systems

Purpose The purpose of region-based medical image compression is to optimize the compression process by focusing on specific regions of interest within medical images. Unlike traditional compression methods that treat the entire image uniformly, region-based compression techniques identify and prioritize certain areas or regions within the image that are deemed more diagnostically significant or relevant. By allocating more resources to compressing these critical regions while reducing compression in less important areas, region-based compression methods aim to achieve higher compression efficiency while preserving diagnostic quality. This approach is particularly valuable in medical imaging, where accurate representation of anatomical structures or pathological findings is paramount for clinical diagnosis and decision-making. Region-based compression can help reduce storage requirements, transmission bandwidth, and processing time without compromising the diagnostic integrity of medical images, thereby facilitating more efficient healthcare delivery and telemedicine applications. Methods In this study, we utilized distortion-limiting compression techniques to optimize the compression process for specific regions within medical images. We employed lossless scalable RBC (Region-Based Compression) using Discrete Wavelet Transform (DWT) for Digital Imaging and Communication in Medicine (DICOM) images. The initial step involved medical image pre-processing, followed by segmentation to separate the image into regions of interest (ROI) and non-ROI. Compression techniques were then applied to reduce network bandwidth and storage requirements. Fractal lossy compression was employed for the non-ROI portion, while context-tree weighting lossless compression was proposed for the ROI portion, effectively compressing the image while rejecting noisy background elements. During decompression, the original medical image can be reconstructed using the reverse process. This approach optimizes storage and transmission efficiency while preserving diagnostic integrity in medical imaging applications. Results The experiment involved testing various medical images, and the proposed method outperformed previous techniques in terms of results. According to the findings, the improvement in Peak Signal-to-Noise Ratio (PSNR) over current techniques reached up to 24.23 dB compared to the Joint Photographic Experts Group (JPEG). Additionally, it achieved up to 12.22 dB improvement compared to other transform approaches. These significant enhancements prompted the development of a web and mobile platform for compressing and sending medical images, particularly microscopic ones, in real time. Conclusion This research focuses on employing wavelet transform techniques to compress the Region of Interest (ROI) within medical images. This ROI-based compression approach is particularly valuable as it retains essential diagnostic information while reducing the overall file size. Such a technique holds significant promise for telemedicine systems, especially in rural regions where network resources may be limited or constrained. By selectively compressing the most diagnostically relevant areas of medical images, this approach ensures that critical information is preserved while optimizing data transmission and storage efficiency. This can ultimately enhance access to medical imaging services and facilitate remote diagnosis and treatment in underserved areas with limited network infrastructure.

Predicting survival benefits of immune checkpoint inhibitor therapy in lung cancer patients: a machine learning approach using real-world data.

Due to the heterogeneity in the effectiveness of immunotherapy for lung cancer, identifying predictors is crucial. This study aimed to develop a machine learning model to identify predictors of overall survival in lung cancer patients treated with immune checkpoint inhibitors (ICIs). A retrospective analysis was performed on data from 1314 lung cancer patients at the Chongqing University Cancer Hospital from September 2018 to September 2022. We used the random survival forest (RSF) model to identify survival-influencing factors, using backward elimination for variable selection. A Cox proportional hazards (CPH) model was constructed using the most significant predictors. We assessed model performance and generalizability using time-dependent receiver operating characteristics (ROC) and predictive error curves. The RSF model demonstrated better predictive accuracy than the CPH (IBS 0.17 vs. 0.17; C-index 0.91 vs. 0.68), with better discrimination and prediction performance. The influential variables identified included D-dimer, Karnofsky performance status, albumin, surgery, TNM stage, platelet count, and age. The RSF model, which incorporated these variables, achieved area under the curve (AUC) scores of 0.95, 0.94, and 0.98 for 1-, 3-, and 5-year survival predictions, respectively, in the training set. The validation set showed AUCs of 0.94, 0.90, and 0.95, respectively, exceeding the performance of the CPH model. The study successfully developed a machine learning model that accurately predicted the survival benefits of ICI therapy in lung cancer patients, supporting clinical decision-making in lung cancer treatment.

Diagnostic Value of Contrast-Enhanced Ultrasound in Differentiating Malignant from Benign Small Renal Masses After CT/MRI

Background: The aim of this study was to assess the diagnostic performance of contrast-enhanced ultrasound (CEUS) in characterizing small renal masses (SRMs) measuring less than 3 cm and in distinguishing between malignant and benign SRMs. Methods: A retrospective study was conducted between January 2022 and January 2023 at the Radiology Department of (Anonymized data), with a total of 43 patients assessed via CT and MRI scans, which were subsequently studied by experienced radiologists who were blinded to the pathology results. The CEUS findings were then compared with histopathological examination outcomes or follow-up imaging results. Results: The study results revealed a notably high level of diagnostic accuracy, with sensitivity at 0.875, specificity at 0.94, positive predictive value at 0.95, and negative predictive value at 0.86 for characterizing SRMs. Spearman rank correlation analysis substantiated a robust positive linear correlation between the CEUS findings and biopsy results (r = 0.972). Conclusions: These findings underscore the potential utility of CEUS as a valuable tool for discriminating between malignant and benign SRMs, carrying significant implications for clinical decision-making and leading to improved patient outcomes. However, larger validation studies are imperative to establish its role in routine clinical practice and to address potential limitations.

Artificial Intelligence-based Enhanced Brain Tumor Prediction: A Comprehensive Investigation of Machine Learning and Deep Learning

Brain tumors pose a significant threat to patients’ quality of life and survival rates, with traditional diagnostic methods often falling short due to their time-consuming nature and susceptibility to high misdiagnosis rates. Recent progress in Artificial Intelligence (AI), especially in Machine Learning (ML) and Deep Learning (DL), offer promising alternatives for the prediction and diagnosis of brain tumors. AI models, including Support Vector Machine (SVM), Random Forests, Logistic Regression, Artificial Neural Network (ANN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) models networks, have demonstrated superior performance in processing complex medical data, thereby enhancing predictive accuracy and aiding clinical decision-making. This review systematically evaluates the application of these AI techniques in brain tumor prediction, highlighting their strengths and limitations, as well as the challenges faced in terms of model interpretability, data applicability, and patient privacy. Furthermore, this paper explored future prospects for improving model interpretability, transfer learning and domain adaptation for enhancing model applicability, and federated learning for preserving patient privacy. By addressing these issues, Artificial Intelligence can significantly advance brain tumor diagnosis and treatment, ultimately improving patient outcomes.

Venous aneurysms in unruptured supratentorial brain arteriovenous malformations: a protective factor against hemorrhagic stroke and insights into hemodynamic mechanisms.

This study endeavors to clarify the impact of venous aneurysms (VA) on hemorrhagic risk in brain arteriovenous malformations (AVMs) and uncover potential hemodynamic mechanisms, utilizing quantitative digital subtraction angiography (QDSA) technology and survival dataset. Patients were enrolled in a multicenter prospective collaboration registry between August 2011 and August 2021, and subsequently categorized into the VA and non-VA cohorts. Using propensity score-matched survival analysis, we quantitatively assessed the natural risk of hemorrhagic stroke in these two cohorts. Additionally, a quantitative hemodynamic analysis was conducted to explore the distinctions in hemodynamic characteristics between these two cohorts. Among 3758 consecutive AVMs documented at a single center from the registry, 820 unruptured AVMs who maintained conservation management over 1 month were identified. Following a two-step matching process, 504 cases were retained for survival analysis and 408 cases for hemodynamic analysis. Overall, the presence of VA emerged as a protective factor, associated with a decreased risk of hemorrhagic stroke (HR, 0.21 [95% CI: 0.07-0.62], p = 0.004). Distinct hemodynamic characteristics were observed in AVMs with VA, showing a lower stasis index in two components of AVMs-the nidus (p = 0.014) and the main draining vein (p = 0.018). In this observational prospective cohort study, the presence of VA is associated with a decreased risk of hemorrhagic stroke in AVMs, suggesting an underlying hemodynamic mechanism involving the redistribution of excessive pressure loads within the AVM nidus by the VA. Questions What impact, if any, does VA have on the hemorrhagic risk in brain AVMs? Findings Presence of VA is associated with a decreased hemorrhagic stroke risk through the redistribution of pressure loads. Critical relevance VA in brain AVMs emerges as a protective factor against hemorrhagic stroke. Understanding this association and the underlying hemodynamic mechanisms offers valuable guidance for preventive strategies and informs clinical decision-making, improving overall patient care.

Revolutionizing Radiology With Artificial Intelligence.

Artificial intelligence (AI) is rapidly transforming the field of radiology, offering significant advancements in diagnostic accuracy, workflow efficiency, and patient care. This article explores AI's impact on various subfields of radiology, emphasizing its potential to improve clinical practices and enhance patient outcomes. AI-driven technologies such as machine learning, deep learning, and natural language processing (NLP) are playing a pivotal role in automating routine tasks, aiding in early disease detection, and supporting clinical decision-making, allowing radiologists to focus on more complex diagnostic challenges. Key applications of AI in radiology include improving image analysis through computer-aided diagnosis (CAD) systems, which enhance the detection of abnormalities in imaging, such as tumors. AI tools have demonstrated high accuracy in analyzing medical images, integrating data from multiple imaging modalities such as CT, MRI, and PET to provide comprehensive diagnostic insights. These advancements facilitate personalized treatment planning and complement radiologists' workflows. However, for AI to be fully integrated into radiology workflows, several challenges must be addressed, including ensuring transparency in how AI algorithms work, protecting patient data, and avoiding biases that could affect diverse populations. Developing explainable AI systems that can clearly show how decisions are made is crucial, as is ensuring AI tools can seamlessly fit into existing radiology systems. Collaboration between radiologists, AI developers, and policymakers, alongside strong ethical guidelines and regulatory oversight, will be key to ensuring AI is implemented safely and effectively in clinical practice. Overall, AI holds tremendous promise in revolutionizing radiology. Through its ability to automate complex tasks, enhance diagnostic capabilities, and streamline workflows, AI has the potential to significantly improve the quality and efficiency of radiology practices. Continued research, development, and collaboration will be crucial in unlocking AI's full potential and addressing the challenges that accompany its adoption.

Tracer-Separator: A Deep Learning Model for Brain PET Dual-Tracer (18F-FDG and Amyloid) Separation.

Multiplexed PET imaging revolutionized clinical decision-making by simultaneously capturing various radiotracer data in a single scan, enhancing diagnostic accuracy and patient comfort. Through a transformer-based deep learning, this study underscores the potential of advanced imaging techniques to streamline diagnosis and improve patient outcomes. The research cohort consisted of 120 patients spanning from cognitively unimpaired individuals to those with mild cognitive impairment, dementia, and other mental disorders. Patients underwent various imaging assessments, including 3D T1-weighted MRI, amyloid PET scans using either 18F-florbetapir (FBP) or 18F-flutemetamol (FMM), and 18F-FDG PET. Summed images of FMM/FBP and FDG were used as proxy for simultaneous scanning of 2 different tracers. A SwinUNETR model, a convolution-free transformer architecture, was trained for image translation. The model was trained using mean square error loss function and 5-fold cross-validation. Visual evaluation involved assessing image similarity and amyloid status, comparing synthesized images with actual ones. Statistical analysis was conducted to determine the significance of differences. Visual inspection of synthesized images revealed remarkable similarity to reference images across various clinical statuses. The mean centiloid bias for dementia, mild cognitive impairment, and healthy control subjects and for FBP tracers is 15.70 ± 29.78, 0.35 ± 33.68, and 6.52 ± 25.19, respectively, whereas for FMM, it is -6.85 ± 25.02, 4.23 ± 23.78, and 5.71 ± 21.72, respectively. Clinical evaluation by 2 readers further confirmed the model's efficiency, with 97 FBP/FMM and 63 FDG synthesized images (from 120 subjects) found similar to ground truth diagnoses (rank 3), whereas 3 FBP/FMM and 15 FDG synthesized images were considered nonsimilar (rank 1). Promising sensitivity, specificity, and accuracy were achieved in amyloid status assessment based on synthesized images, with an average sensitivity of 95 ± 2.5, specificity of 72.5 ± 12.5, and accuracy of 87.5 ± 2.5. Error distribution analyses provided valuable insights into error levels across brain regions, with most falling between -0.1 and +0.2 SUV ratio. Correlation analyses demonstrated strong associations between actual and synthesized images, particularly for FMM images (FBP: Y = 0.72X + 20.95, R2 = 0.54; FMM: Y = 0.65X + 22.77, R2 = 0.77). This study demonstrated the potential of a novel convolution-free transformer architecture, SwinUNETR, for synthesizing realistic FDG and FBP/FMM images from summation scans mimicking simultaneous dual-tracer imaging.

Advances in Treatment for Oestrogen Receptor-Positive Breast Cancer

THIS YEAR the European Society for Medical Oncology (ESMO) Congress was hosted in Barcelona, Spain from 13th–17th September. Among the many impactful sessions, a symposium titled ‘Incorporating Novel Treatment Insights for Estrogen Receptor-Positive (ER+) Early Breast Cancer Patients’ garnered particular attention. Featuring presentations by Stephen Johnston, Royal Marsden, London, UK; Nadia Harbeck, Ludwig Maximilian University of Munich, Germany; and Etienne Brain, Institut Curie in Paris & Saint-Cloud, France, the session provided a comprehensive overview of current advances in ER+ early breast cancer treatment. The speakers explored adjuvant endocrine therapies, prognostic and predictive factors for clinical decision-making, and the unique challenges of optimising treatment for older patients, underscoring the evolving landscape of personalised care in ER+ early breast cancer.

A New Easy-to-Perform Flow Cytometry Assay for Determining Bacterial- and Viral-Infection-Induced Polymorphonuclear Neutrophil and Monocyte Membrane Marker Modulation in Febrile Patients

We developed a flow cytometry (FC) assay enabling the rapid and accurate identification of bacterial and viral infections using whole blood samples. The streamlined flow cytometry assay is designed to be user-friendly, making it accessible even for operators with limited experience in FC techniques. The key components of the assay focus on the expression levels of specific surface markers—CD64 on polymorphonuclear neutrophils (PMN) as a marker for bacterial infection, and CD169 on monocytes (MO) for viral infection. The strong performance indicated by an area under the receiver operating characteristic (ROC) curve of 0.94 for both PMN CD64 positive predictive value (PPV) 97.96% and negative predictive value (NPV) 76.67%, and MO CD169 PPV 82.6% and NPV 86.9%, highlight the assay’s robustness in differentiating between bacterial and viral infections accurately. The FC assay includes the assessment of immune system status through HLA-DR and IL-1R2 modulation in MO, providing a useful insight into the patients’ immune response. The significant increase in the frequency of MO exhibiting reduced HLA-DR expression and elevated IL-1R2 levels in infected patients (compared to healthy controls) underscores the potential of these markers as indicators of infection severity. Although the overall correlation between HLA-DR and IL-1R2 expression levels was not significant across all patients, there was a trend in patients with more severe disease suggesting that these markers may have the potential to assist in stratifying patient risk. The present FC assay has the potential to become routine in the clinical microbiology laboratory community and to be helpful in guiding clinical decision making.

Kidney Disease Classification

Kidney diseases, such as tumors, cysts, and stones, are serious health conditions that affect millions globally. Medical imaging, particularly Computed-Tomography (CT) scans, plays an important role in diagnosing these conditions. Although, manual analysis of CT images by radiologist can be tiresome, fallible, and affected by human variability. This paper introduces a deep learning approach that employs Convolutional Neural Networks (CNN) for the automated classification of kidney CT scan images into four distinct categories : normal, cysts, tumors, and stones. The system is designed to boost diagnostic accuracy, reduce human error, and expedite clinical decision making. Through data preprocessing, CNN architecture design, training, and evaluation, the proposed model achieved a classification accuracy of 92%. This study highlights the significance of CNNs in medical image analysis anddtheir implicit for real- time deployment in clinical surroundings. Additionally, we compare our CNN-based approach with other advanced architectures like Vision Transformers, demonstrating CNNs' robustness and efficiency in this domain.

The Investigation of the Application of RAG Technology in the Field of EHR

Electronic Health Records (EHR) play a crucial role in contemporary medical information systems, capturing extensive data in multiple scenarios. This review explores the impact of Retrieval Augmented Generation (RAG) on managing EHR. By integrating retrieval and generation processes, RAG significantly enhances data handling, clinical decision support, and patient management. EHRs contain extensive data like patient histories and diagnostic information, which are becoming increasingly complex. The RAG improves the accuracy and richness of this data processing by using a retrieval module to extract relevant text fragments and a generation module to create precise outputs. Despite its potential, RAG faces challenges such as data inconsistency, privacy concerns, and the need for efficient training. Recent studies highlight the RAG’s effectiveness in summarizing clinical notes and enhancing prediction accuracy, suggesting a promising future in healthcare. However, ongoing research is necessary to optimize the RAG’s application and address these challenges, aiming to transform healthcare delivery effectively.

Health Catch-UP!: a realist evaluation of an innovative multi-disease screening and vaccination tool in UK primary care for at-risk migrant patients

BackgroundMigrants to the UK face disproportionate risk of infections, non-communicable diseases, and under-immunisation compounded by healthcare access barriers. Current UK migrant screening strategies are unstandardised with poor implementation and low uptake. Health Catch-UP! is a collaboratively produced digital clinical decision support system that applies current guidelines (UKHSA and NICE) to provide primary care professionals with individualised multi-disease screening (7 infectious diseases/blood-borne viruses, 3 chronic parasitic infections, 3 non-communicable disease or risk factors) and catch-up vaccination prompts for migrant patients.MethodsWe carried out a mixed-methods process evaluation of Health Catch-UP! in two urban primary healthcare practices to integrate Health Catch-UP! into the electronic health record system of primary care, using the Medical Research Council framework for complex intervention evaluation. We collected quantitative data (demographics, patients screened, disease detection and catch-up vaccination rates) and qualitative participant interviews to explore acceptability and feasibility.ResultsNinety-nine migrants were assessed by Health Catch-UP! across two sites (S1, S2). 96.0% (n = 97) had complete demographics coding with Asia 31.3% (n = 31) and Africa 25.2% (n = 25), the most common continents of birth (S1 n = 92 [48.9% female (n = 44); mean age 60.6 years (SD 14.26)]; and S2 n = 7 [85.7% male (n = 6); mean age 39.4 years (SD16.97)]. 61.6% (n = 61) of participants were eligible for screening for at least one condition and uptake of screening was high 86.9% (n = 53). Twelve new conditions were identified (12.1% of study population) including hepatitis C (n = 1), hypercholesteraemia (n = 6), pre-diabetes (n = 4), and diabetes (n = 1). Health Catch-UP! identified that 100% (n = 99) of patients had no immunisations recorded; however, subsequent catch-up vaccination uptake was poor (2.0%, n = 1). Qualitative data supported acceptability and feasibility of Health Catch-UP! from staff and patient perspectives, and recommended Health Catch-UP! integration into routine care (e.g. NHS health checks) with an implementation package including staff and patient support materials, standardised care pathways (screening and catch-up vaccination, laboratory, and management), and financial incentivisation.ConclusionsClinical Decision Support Systems like Health Catch-UP! can improve disease detection and implementation of screening guidance for migrant patients but require robust testing, resourcing, and an effective implementation package to support both patients and staff.

Radiomics for Predicting Prognostic Factors in Breast Cancer: Insights from Contrast-Enhanced Mammography (CEM)

Objectives: To evaluate the correlation between radiomic features extracted from contrast-enhanced mammography (CEM) tumor lesions and peritumoral background with prognostic factors in breast cancer (BC). Methods: In this retrospective, single-center study, 134 women with histologically confirmed breast cancer underwent CEM examination. Radiomic features were extracted from manually segmented lesions and lesion contours were automatically delineated using PyRadiomics. The extracted features were categorized into seven classes: First-order Features, Shape Features (2D), Gray Level Co-occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), and Neighboring Gray Tone Difference Matrix (NGTDM). Histological examination assessed tumor type, grade, receptor structure (ER, PgR, HER2), Ki67 index, and lymph node involvement. Pearson correlation and multivariate regression were applied to evaluate associations between radiomic features and prognostic factors. Results: Significant correlations were found between First-order Features and prognostic factors such as ER, PgR, and Ki67 (p < 0.05). GLCM-based texture features showed strong associations with Ki67 and HER2 (p < 0.01). Radiomic features from peritumoral regions, especially shape and GLSZM metrics, were significantly correlated with Ki67 and lymph node involvement. Conclusions: Radiomic analysis of both tumor and peritumoral regions offers significant insights into BC prognosis. These findings support the integration of radiomics into personalized diagnostic and therapeutic strategies, potentially improving clinical decision making in BC management.

Integrating genomic and molecular data to predict antimicrobial minimum inhibitory concentration in Klebsiella pneumoniae

Minimum inhibitory concentration (MIC) denotes the in vitro benchmark indicating the quantity of antibiotic required to inhibit proliferation of specific bacterial strains. Determining MIC values corresponding to the infecting bacterial strain is paramount for tailoring appropriate antibiotic therapy. In the interim between specimen collection and laboratory-derived MIC outcomes, clinicians frequently resort to empirical therapy informed by retrospective analyses. Here introduces two deep learning approaches, a Convolutional Neural Network (CNN)-based model and an Enformer-based model, integrating genomic data of Klebsiella Pneumoniae and molecular structural data of 20 antibiotics to anticipate the MIC value of the bacterium for each antibiotic under consideration. These models demonstrate enhanced raw accuracy over the existing state-of-the-art model, which rely exclusively on genomic data. The CNN-based model achieves a notable 20% increase in raw accuracy while further mirroring the 1-tier accuracy of the state-of-the-art model. Although the Enformer-based model does not quite reach the performance levels of the CNN-based model, it offers an advantage by eliminating the need for arbitrary data processing steps. This streamlining of the data processing pipeline facilitates fast updates and improves the model interpretability. It is expected that these deep learning paradigms can significantly inform and bolster clinician decision-making during the empirical treatment phase.

Prediction of outcome in malignant hypertension patients using machine learning: a report from the West Birmingham malignant hypertension registry

Abstract Objectives Malignant hypertension (MHT) is a rare, yet severe condition characterized by high morbidity and mortality rates. This study aimed to assess the potential of machine learning (ML) algorithms in forecasting prognostic outcomes in MHT patients. Methods The dataset from the West Birmingham MHT Registry was used. We evaluated the efficacy of 9 ML algorithms, CatBoost, Decision Tree (DT), Light-Gradient Boosting Machine (LightGBM), K-Nearest Neighbors (KNN), Logistic Regression (LR), Multi-Layer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM) and XGBoost, in predicting a composite outcome of all-cause mortality or dialysis. Evaluation metrics included the area under the receiver operating characteristic curve (AUC) and the F1 score. The SHapley Additive exPlanations values were employed to quantify the importance of each feature in the models. Results The study cohort comprised 385 individuals diagnosed with MHT (mean age of 48±13 years, 66% male). During a median follow-up period of 11 years (interquartile range: 3-18 years), 282 patients (73%) experienced the composite outcome. From 24 demographic and clinical variables, 16 were selected into the ML models. Among 9 models, the SVM and LR models exhibited robust predictive performance, achieving AUCs of 0.86 (95% CI: 0.76-0.93) and 0.81 (95% CI: 0.72-0.93), respectively. Furthermore, these models demonstrated high F1 scores (SVM: 0.89, LR: 0.85) and sensitivity (SVM: 0.89, LR: 0.83) (Table). Age, smoking history, systolic blood pressure at follow-up and baseline creatinine levels were commonly identified as primary prognostic features in both SVM and LR models (Figure). Conclusions The application of ML algorithms facilitates effective prediction of prognostic outcomes in patients with MHT, illustrating their potential utility in clinical decision-making through more targeted risk stratification and individualized patient care in these high-risk patients.

Development and implementation of a guideline-based decision support system for etiological diagnosis of Sustained Monomorphic Ventricular Tachycardia (SMVT)

Abstract Background Guideline (GL)-based decision support systems (DSSs) play a significant role in supporting physicians in their decision-making processes by providing structured clinical guidance. While these systems have shown significant success in enhancing practitioner performance and patient outcomes in general practice, their application in the context of ventricular arrhythmias remains limited. Moreover, the clinical etiological diagnosis of ventricular arrhythmias presents various challenges for healthcare professionals, such as adherence to updated diagnostic criteria and understanding of complex arrhythmia mechanisms. Purpose In this study, we aim to design, implement, and evaluate a guideline-based decision support systems for etiological diagnosis of sustained monomorphic ventricular tachycardia (SMVT), which could potentially address critical challenges associated with the disease diagnosis and management. Methods To comprehensively capture the semantics embedded in clinical guidelines, we first developed a dedicated knowledge graph tailored to the clinical decision-making. This involved extracting entities and relationships pertinent to key decision procedures from ESC guidelines for ventricular arrhythmias, clinical textbooks or literatures. Subsequently, we translated instances within the knowledge graph into archetypes within openEHR, amplifying the interoperability of clinical information. To enhance the interpretability of the DSS, we established executable diagnostic and treatment processes to offer visual representation of clinical steps in diagnosis and treatment. Ultimately, we constructed a decision support engine to implement the GL-DSS, and its effectiveness was evaluated with anonymous real-world data. Results The proposed GL-DSS was found to be quite feasible and could provide etiological diagnosis for SMVT. The knowledge base for the constructed GL-DDS included more than 2000 entities and relations, which played a vital role in representing disease pathogenesis. The proposed system can map the clinical entities to a set of openEHR archetypes, thus mitigate the interoperability issues of the hospital information systems and CDSS data integration. Also, this module improved system usability and ensured that guidelines could be easily translated and updated into decision support tools. Real-word medical records from 20 patient were collected for model evaluation, the results showed that the GL-DSS covered most of the entities and relations between diseases and diagnostic evidence recorded in clinical texts and achieved a diagnosis accuracy of 80%. Conclusions The results demonstrated that our proposed GL-DSS could completely and accurately capture the diagnostic information under the concrete EHR data. Thus, the implement decision support system could have the potential to improve clinical decision-making, patient care, and outcomes in this specialized medical domain.

Current echocardiographic indices for right ventricular function are inadequate to predict patient outcomes in chronic tricuspid regurgitation

Abstract Background/Introduction The presence of chronic tricuspid regurgitation (TR) can lead to pseudo-normalization of right ventricular (RV) functional indices on transthoracic echocardiography (TTE). Thus, the current cutoffs for RV free wall strain (FWS), functional area change (FAC), and tricuspid annular plane systolic excursion (TAPSE) (1) are not optimal for the volume overload associated with TR (2). Purpose We aimed to evaluate the sensitivity and specificity of the current cutoffs for RV FWS (>-23%), FAC (<35%), and TAPSE (<17 mm) in predicting adverse patient outcomes in a multi-centric population with chronic TR. We also evaluated whether interventricular septal shape was correlated with patient outcomes and aimed to develop cutoffs for this novel index. Methods We studied 753 patients (mean age 70.3 ± 15.0 years, 42.5% male) with >mild, medically managed TR who presented to our centers between 2018 and 2023. We measured TR grade (3), RV size, RV FWS, FAC, TAPSE, and eccentricity index (EI) for each patient (Figure 1). We subsequently tracked time to cardiac-related hospitalization or death, whichever came first. Using receiver operating characteristics (ROC), we estimated the area-under-the-curve (AUC) for RV FWS, FAC, and TAPSE as well as systolic and diastolic EI in predicting adverse patient outcomes. We used the modified Youden index (4) to analyze the current cutoffs for RV FWS, FAC, and TAPSE and specify novel cutoffs for all indices (including systolic and diastolic EI). Results Over a mean follow-up of 52 ± 16 months, there were 282 hospitalizations and 146 deaths across the 753 patients. AUC values for RV FWS, FAC, and TAPSE in predicting adverse clinical outcomes were 0.54, 0.62, and 0.54, respectively (p < 0.05 each, Figure 2A). Systolic and diastolic EI had the highest AUC (0.86 each, p < 0.0001) and were equivalent to one another in predicting adverse outcomes (Z-score = 0.0471, p = 0.9624) (Figure 2B). Sensitivity and specificity for the current cutoffs for RV FWS, FAC, and TAPSE are shown in Figure 2C. Using maximized Youden indices, the proposed cutoffs for normal RV FWS, FAC, TAPSE, systolic EI, and diastolic EI in chronic TR were ≤-24%, ≥38%, ≥22 mm, <1.3, and <1.3, respectively, which are all notably higher than the currently cutoffs (Figure 2C). Conclusions Given the pseudo-normalization of RV FWS, FAC, and TAPSE in chronic TR, waiting to intervene until these values become "abnormal" (per the current cutoffs) may in fact be too late. Our data suggest that the new cutoffs are needed to identify compensated RV function in the setting of TR. Moreover, interventricular septal shape (assessed via EI) predicts adverse patient outcomes with greater accuracy than conventional indices and should perhaps be incorporated in clinical decision-making.Figure 1.Eccentricity MeasurementFigure 2.ROC Curves for RV Indices

Assessing the need for coronary angiography in high-risk acute coronary syndrome patients using artificial intelligence and computed tomography

Abstract Background/Introduction The use of coronary computed tomography angiography (CCTA) in managing high-risk acute coronary syndrome (ACS) patients is increasingly common. Yet, its role remains unvalidated in this context, posing challenges to traditional clinical decision-making algorithms. Physicians, accustomed to a hierarchical and structured approach involving symptom assessment, electrocardiograms, and biomarkers for deciding on the necessity of invasive coronary angiography (ICA), now face dilemmas when CCTA results challenge established diagnostic pathways and contradict clinical decisions based on usual criteria. Meanwhile, the potential of artificial intelligence (AI) which processes information in a way fundamentally different from human clinical reasoning, has been shown to aid decision-making in cardiovascular medicine. Yet, it has not been tested in this acute setting. Purpose This study aimed to evaluate the efficacy of the Chat Generative Pre-trained Transformer (ChatGPT) in guiding the need for ICA in high-risk ACS patients based on both standard clinical data and CCTA findings. Methods This investigation is a sub-study of a larger research project where high-risk ACS patients (all having a theoretical guideline-based indication for ICA) underwent CCTA prior to ICA. ChatGPT analyzed clinical vignettes containing patient data, electrocardiograms, troponin levels, and CCTA results to determine the necessity of ICA. The AI's recommendations were then compared to actual ICA findings to assess its decision-making accuracy. Results Among 86 patients with a clear indication for ICA, ChatGPT recommended against it for 19 patients, 16 of whom indeed had no significant findings at ICA (Figure). For 67 patients, ChatGPT advised proceeding with ICA, and a significant lesion was confirmed in 58 of them. Consequently, ChatGPT's overall accuracy stood at 86%, with a sensitivity of 95% and a specificity of 64%. The model's negative predictive value was 84%, and its positive predictive value was 87%. Conclusion These preliminary data suggest that ChatGPT can effectively assist in guiding the need for ICA among high-risk ACS patients, potentially reducing unnecessary procedures but further clinical studies to refine AI's role in clinical decision-making are required.ChatGPT's decision as per ICA's results

Dual-tiered insights: cross-examining entities in free text electronic health records

Abstract Background Poor determination and processing of actions at the primary care level are found to be associated with unstructured and cluttered electronic health records (EHRs). Physicians recommend that EHRs must highlight entities, such as action items, findings, follow-ups, and reasons for medication changes. There’s consensus around the success of large language models (LLMs) in detecting clinical and non-clinical entities in EHRs. However, end-to-end systems make limited efforts to go beyond entity and relationship detection to support clinical decision-making. Methods We propose a two-tier system that generates case-based comparative reports for entities highlighted by physicians in EHRs. First, we fine-tuned a custom Bidirectional Encoder Representations from Transformers (BERT) model that detects the required entities within the EHRs. Second, a clustering-based service generates a report comparing the detected entities of a specific EHR with other EHRs sharing the same conditions determined by the healthcare professional. Results The system leverages the MIMIC IV deidentified free-text clinical notes dataset. The first-tier successfully classified entities with a macro-score average range of [0.87 - 0.94]. For the second tier, preliminary simulations on a set of test samples were made to cluster the entities. The simulations leverage a custom statistical tests engine offering a suite of entity-type specific tests. The results of these tests are used to generate the case-based detected entities comparative report. Conclusions Highlighting clinical and non-clinical entities bridges the communication gap between primary and secondary care. Clustering these entities extends the capability of LLMs in clinical support decision systems by providing healthcare professionals with the ability to run comparative analyses between EHRs. The comparative analysis reports provide a factual comparison between a selected number of detected entities and their thresholds. Key messages • Clustering clinical and non-clinical entities extends the capacity of named entity recognition in clinical decision-making systems. • Ability to generate a comparative analysis report based on figures extracted from recognised entities in free-text electronic health records.

Endoscopic Epilepsy Surgery: Systematic Review and Meta-Analysis

AbstractEndoscopic epilepsy surgery is a fast emerging minimally invasive alternative to open surgery. The approach minimizes the extent of bone and brain resection and reduces surgical morbidity. This systematic review and meta-analysis sought to evaluate the favorable outcome of seizure improvement in patients undergoing endoscopic epilepsy surgery. The search was conducted by two independent researchers using PubMed and Web of Science until January 2023 to find studies reporting results of patients who underwent endoscopic epilepsy surgery. We extracted data on the clinical profile and outcomes of the patients from the eligible studies. Fifteen studies yielded 340 patients, of which 293 underwent endoscopic epilepsy surgery. The patient cohort consisted of 189 (55.6%) males. A total of 171 (58.3) patients had a favorable outcome of either Engel I or II or > 90% seizure control. Thirteen studies were included in our meta-analysis, and demonstrated improved seizure control after endoscopic epilepsy surgery, with a pooled seizure freedom rate of 58% (95% CI: 0.43–0.71, I2 = 77.1%, τ2 = 0.6836). Studies focusing on pediatric populations reported a higher proportion of positive outcomes, with a rate of 73.27% (95% CI: 62–82%, I2 = 0.0%). In comparison, mixed-age populations showed a lower success rate of 48% (95% CI: 32–65%, I2 = 79.0%). Furthermore, there was significant difference in treatment outcomes between the pediatric and mixed age groups (p = 0.014). The hypothalamic hamartomas (HH) patient population demonstrated a favorable outcome proportion of 61.71% (95% CI: 48.92–73.06%), with a moderate level of heterogeneity (I 2 = 62.9%, tau2 = 0.4266). Five patients developed postoperative complications, and there were three deaths. Our findings suggest that endoscopic epilepsy surgery is particularly effective in pediatric populations and among patients with HH, underscoring the importance of considering patient demographics and disease characteristics in clinical decision-making. The heterogeneity across studies necessitates cautious interpretation of the pooled results, advocating for tailored approaches in treatment planning. Prospective trials are required to establish class I evidence for the role of endoscopic epilepsy surgery compared with the recognized open surgical techniques.