Hasil untuk "Computer applications to medicine. Medical informatics"

Laurel O’Connor, Leah Dunkel, Andrew C. Weitz et al.

Omar Angelo Ibrahim, Henri Trang, Qianlan Chen et al.

Thalamic atrophy is a sensitive imaging marker of neurodegeneration in multiple sclerosis (MS) and related disorders, though thalamus segmentation remains method-dependent. Quantitative magnetic resonance imaging (qMRI) may enhance thalamic boundary contrast, particularly in the context of deep learning. We benchmarked thalamic segmentations from two atlas-constrained algorithms, FreeSurfer and FIRST, and two deep learning algorithms, DBSegment and MindGlide (an MS-trained model), against ground truth (GT) labels, tested whether quantitative R1 maps improve performance, and evaluated clinical validity cross-sectionally and longitudinally. We generated thalamus masks using each algorithm from T1-weighted data in a single-scanner cohort (baseline n = 321; 1-year follow-up n = 234) including patients with MS/related disorders and healthy controls. Using MindGlide, we also produced FLAIR- and R1-based masks and ensembles. Manual GT labels were obtained for 50 MS patients using T1w and FLAIR scans. For voxel-wise GT agreement, DBSegment yielded the highest Dice-similarity coefficient; atlas-constrained methods showed the highest sensitivity but lowest precision, while MindGlide balanced both. Volumetrically, MindGlide showed the most accurate estimates; DBSegment and FreeSurfer showed proportional bias, and both atlas-constrained methods overestimated thalamic volumes. Adding R1 input to MindGlide produced modest or no gains in GT agreement. Additionally, MindGlide volumes were most consistently associated with disability and cognitive scores cross-sectionally, and longitudinally showed the largest effects between thalamic volume change and EDSS worsening. Incorporating R1 maps offered no cross-sectional benefit but strengthened longitudinal associations. Higher-resolution qMRI and multi-contrast deep learning architectures may further enhance thalamic segmentation and monitoring in neuroinflammatory diseases.

Anas Zafar, Leema Krishna Murali, Ashish Vashist

Recent work shows that text-only reinforcement learning with verifiable rewards (RLVR) can match or outperform image-text RLVR on multimodal medical VQA benchmarks, suggesting current evaluation protocols may fail to measure causal visual dependence. We introduce a counterfactual evaluation framework using real, blank, and shuffled images across four medical VQA benchmarks: PathVQA, PMC-VQA, SLAKE, and VQA-RAD. Beyond accuracy, we measure Visual Reliance Score (VRS), Image Sensitivity (IS), and introduce Hallucinated Visual Reasoning Rate (HVRR) to detect cases where models generate visual claims despite producing image-invariant answers. Our findings reveal that RLVR improves accuracy while degrading visual grounding: text-only RLVR achieves negative VRS on PathVQA (-0.09), performing better with mismatched images, while image-text RLVR reduces image sensitivity to 39.8% overall despite improving accuracy. On VQA-RAD, both variants achieve 63% accuracy through different mechanisms: text-only RLVR retains 81% performance with blank images, while image-text RLVR shows only 29% image sensitivity. Models generate visual claims in 68-74% of responses, yet 38-43% are ungrounded (HVRR). These findings demonstrate that accuracy-only rewards enable shortcut exploitation, and progress requires grounding-aware evaluation protocols and training objectives that explicitly enforce visual dependence.

Pedram Golnari, Katrina Prantzalos, Dipak Upadhyaya et al.

The state-of-the-art performance of large language models (LLMs) in medical natural language (NLP) tasks, including medical query answering, summarization of clinical notes, and generation of medical reports has led to the development of a large number of application studies. However, many of these studies have also identified the key role of human input in generating accurate results with significant efforts focused on identifying an effective mechanism to elicit, model, and integrate human medical expertise in optimizing LLMs. In this paper, we introduce a new approach based on biomedical ontologies as a knowledge model to significantly improve the performance of LLMs in biomedical natural language processing (NLP) applications. Specifically, we focus on a rare pediatric epilepsy called Dravet syndrome (DS) which there is very limited understanding about the mechanisms that result in seizure and demonstrate the effectiveness of a unique epilepsy ontology in improving the accuracy of results. The results of this study create a new pathway for integrating human expertise in LLMs to support high accuracy and consistent results in medical applications.

Rajani Rai B, Karunakara Rai B, Mamatha A S et al.

Accurate classification of focal and non-focal epilepsy is a critical healthcare analytics challenge that requires robust data preprocessing and feature optimization. This work develops an integrated analytics framework that combines hybrid filtering with hybrid dimensionality reduction to improve both signal quality and predictive performance. A multi-criteria ranking strategy based on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is employed, incorporating conventional signal measures alongside distance and divergence metrics to identify optimal preprocessing pipelines. Statistical validation is performed using the Friedman test with Nemenyi post-hoc analysis to establish the significance of competing filter–dimensionality reduction combinations. The validated framework is benchmarked across conventional, hybrid, and deep learning classifiers, with the most effective configuration—Butterworth–Wavelet Packet Decomposition (BW + WPD) filtering followed by Principal Component Analysis–Linear Discriminant Analysis (PCA + LDA)—achieving 95.63% accuracy using an Adaboost classifier on the Bern–Barcelona dataset. Evaluation on the independent Bonn dataset confirms robustness and cross-subject generalizability. These findings demonstrate the value of a multi-metric, statistically validated analytics strategy for reliable epilepsy detection, with potential applicability to broader healthcare signal classification tasks.

Saif Khairat, Jennifer Morelli, Marcella H Boynton et al.

BackgroundElectronic health records (EHRs) have been linked to information overload, which can lead to cognitive fatigue, a precursor to burnout. This can cause health care providers to miss critical information and make clinical errors, leading to delays in care delivery. This challenge is particularly pronounced in medical intensive care units (ICUs), where patients are critically ill and their EHRs contain extensive and complex data. ObjectiveWe propose to study the effect of an information visualization dashboard on ICU providers’ cognitive fatigue in 4 major US medical centers. In this randomized controlled trial, we will compare 2 leading EHRs with a visualization dashboard–based EHR called AWARE. MethodsThis crossover randomized trial will collect physiological and objective data using a screen-mounted eye-tracking device to assess cognitive fatigue among ICU providers. The study will involve 120 ICU providers from 4 US medical centers, with each site using its institutional EHR as the control and the AWARE EHR as the intervention. Participants will be randomly assigned to use either their institutional EHR or the AWARE EHR first, followed by the other EHR, with the order of EHR use and patient case order randomized by the study team. The AWARE tool is designed to integrate within an existing EHR system and provides clinical support tools, such as the ability to trend data points from body systems at a glance. Data analysis will include eye-tracking metrics, performance measures, and validated surveys to evaluate EHR usability and its impact on clinical decision-making. Primary outcomes include the number of cognitive fatigue instances per patient case, time to complete each case, overall usability of the session, number of mouse clicks per case, provider performance scores from questions asked during each patient case, and perceived usability of each EHR. Secondary outcomes include the number of eye fixations per patient case and perceived workload of each EHR. ResultsThis EHR usability study was funded in 2021 and initiated in 2022, with a completion date of 2025. Data collection began in August 2023. As of now, 3 of the 4 study sites have completed data collection, with a total of 113 completed sessions thus far. Data collection is ongoing at the fourth site. Preliminary analysis is ongoing, and we expect to begin publishing results in late 2025. ConclusionsFindings from this research may inform improvements in EHR interface design and usability, which may enhance provider performance, streamline care delivery, and improve patient safety outcomes. Trial RegistrationClinicalTrials.gov NCT05937646; https://clinicaltrials.gov/study/NCT05937646 International Registered Report Identifier (IRRID)DERR1-10.2196/74247

Xia Liang, Ruhao Zhang, Shuyun Wang et al.

Objective To reveal the characteristics, development trend and potential opportunities of China–ASEAN collaboration in the medical and health field based on bibliometrics. Methods Scopus and International Center for the Study of Research Lab (ICSR Lab) was used to analyze the scale, collaboration network and distribution, impact of cooperative papers, collaboration dominance and evolution of the literature on China–ASEAN medical and health collaboration in the Scopus database from 1992 to 2022. Results From 1992 to 2022, 19,764 articles on medical and health collaboration between China and ASEAN were filtered for analysis. The number of China–ASEAN collaborations has shown a clear upward trend over the years, indicating a gradually closer and improved collaboration relationship overall. The institutional collaboration network between China and ASEAN countries was obviously clustered, and the network connectivity was limited. The substantial differences between the median and mean values of citation impact of China–ASEAN medical and health research collaboration reflected that the collaboration was ‘less’ but ‘better’. The dominance share of collaboration between China and the main ASEAN countries was fluctuating upward and has become more and more stable after 2004. Most of the China–ASEAN collaboration focused on their own characteristic research topics. In recent years, collaboration in infectious diseases and public health had expanded significantly, while other research topics had maintained in a complementary development trend. Conclusion Collaboration between China and ASEAN in the medical and health field has exhibited a progressively closer relationship, and the trend of complementary research has remained stable. However, there are still areas of concern, including the limited scale of collaboration, narrow scope of participation and weak dominance.

Jodi Hall, Bradley Hiebert, Danica Facca et al.

This paper builds on thematic findings from a larger study that explored how digital technologies (e.g. smartphones, apps, search engines) shape expectant and new mothers’ early parenting practices. An overarching theme that arose across these mothers’ experiences which deserved deeper exploration was relational digital surveillance. In the context of this paper, relational digital surveillance describes how mothers evaluate their sense of preparedness, goodness or suitability for motherhood as they transition into parenting in relation to: their own use of digital technologies when caring for their pregnant bodies (self-surveillance), partners’ and family members’ commentary and/or judgement regarding their use of digital technologies to support their parenting and decision-making (familial surveillance) in addition to service/health care providers’ commentary and/or judgement concerning their technology use (systemic surveillance). Mothers’ use of digital technologies in this study not only provided others (partners, family members, health care providers) with means to watch over their actions and bodies as they transitioned into motherhood but offered a new evaluative dimension for others to scrutinize their behaviour as a new mother. Such understandings of relational digital surveillance within the transition to parenting context raise critical questions concerning the promotion and commercialization of digital self-surveillance technologies among expectant/new parents given the ways these technologies can further push the boundaries of hegemonic mothering practices and contribute to feelings of inadequacy and self-doubt. Alternatively, these insights offer avenues where health care providers can intervene to facilitate activities that enhance digital health literacy skills and mitigate parents’ exposure to platforms that amplify anxieties.

Sergio Andreu‐Sánchez, Jiafei Wu, Jingyuan Fu

Eva Lusekelo, Mlyashimbi Helikumi, Dmitry Kuznetsov et al.

In recent decades, media campaigns have played an important role in assessing, preventing and controlling infectious diseases. However, little progress has been made in quantifying its impact during chikungunya epidemics. In order to address this critical gap, this paper develops and analyzes a climate-based model of chikungunya virus disease that incorporates mass media campaigns and heterogeneous biting exposures. We obtained the basic reproduction numbers associated with the proposed model and determined the results of the threshold dynamics. We calibrated our model based on literature data and validated it with monthly observed chikungunya cases in Madhya Pradesh, India (2016–2017). The results show that mass media campaigns can significantly reduce the spread of the disease. It can also limit the occurrence of future outbreaks in the next few years. We also observed that media fatigue may reduce the impact of media to mitigate the spread of chikungunya virus.

Mingyuan Meng, Lei Bi, Michael Fulham et al.

Image registration is a fundamental requirement for medical image analysis. Deep registration methods based on deep learning have been widely recognized for their capabilities to perform fast end-to-end registration. Many deep registration methods achieved state-of-the-art performance by performing coarse-to-fine registration, where multiple registration steps were iterated with cascaded networks. Recently, Non-Iterative Coarse-to-finE (NICE) registration methods have been proposed to perform coarse-to-fine registration in a single network and showed advantages in both registration accuracy and runtime. However, existing NICE registration methods mainly focus on deformable registration, while affine registration, a common prerequisite, is still reliant on time-consuming traditional optimization-based methods or extra affine registration networks. In addition, existing NICE registration methods are limited by the intrinsic locality of convolution operations. Transformers may address this limitation for their capabilities to capture long-range dependency, but the benefits of using transformers for NICE registration have not been explored. In this study, we propose a Non-Iterative Coarse-to-finE Transformer network (NICE-Trans) for image registration. Our NICE-Trans is the first deep registration method that (i) performs joint affine and deformable coarse-to-fine registration within a single network, and (ii) embeds transformers into a NICE registration framework to model long-range relevance between images. Extensive experiments with seven public datasets show that our NICE-Trans outperforms state-of-the-art registration methods on both registration accuracy and runtime.

Mehrvash Haghighi, Dayanandan Adhimoolam, Ricky Kwan et al.

Background: Pandemics are unpredictable and can rapidly spread. Proper planning and preparation for managing the impact of outbreaks is only achievable through continuous and systematic collection and analysis of health-related data. We describe our experience on how to comply with required reporting and develop a robust platform for surveillance data during an outbreak. Materials and Methods: At Mount Sinai Health System, New York City, we applied Visiun, a laboratory analytics dashboard, to support main response activities. Epic System Inc.’s SlicerDicer application was used to develop clinical and research reports. We followed World Health Organization (WHO); federal and state guidelines; departmental policies; and expert consultation to create the framework. Results: The developed dashboard integrated data from scattered sources are used to seamlessly distribute reports to key stakeholders. The main report categories included federal, state, laboratory, clinical, and research. The first two groups were created to meet government and state reporting requirements. The laboratory group was the most comprehensive category and included operational reports such as performance metrics, technician performance assessment, and analyzer metrics. The close monitoring of testing volumes and lab operational efficiency was essential to manage increasing demands and provide timely and accurate results. The clinical data reports were valuable for proper managing of medical surge requirements, such as healthcare workforce and medical supplies. The reports included in the research category were highly variable and depended on healthcare setting, research priorities, and available funding. We share a few examples of queries that were included in the designed framework for research projects. Conclusion: We reviewed here the key components of a conceptual surveillance framework required for a robust response to COVID-19 pandemics. We demonstrated leveraging a lab analytics dashboard, Visiun, combined with Epic reporting tools to function as a surveillance system. The framework could be used as a generic template for possible future outbreak events.

Natalia Escobar-Váquiro, Lina Buchely-Ibarra, Sandra Balanta-Cobo

In this article, we describe the dataset on the conditions for gender-based violence (GBV) for women in four municipalities of Colombia: Cali, Buenaventura, Jamundí, and Yumbo. The database was developed by the Observatory for Women's Equity (OEM), an entity resulting from an alliance between Universidad Icesi and Fundación WWB Colombia. The OEM's purpose is to construct measurements that make it possible to account for GBV suffered by women. The following types of violence were classified: psychological violence, physical violence, sexual violence, workplace violence, and economic violence. In addition to the module on GBV, the survey has other modules with which to establish a socioeconomic characterization of women and households, through which to identify how these conditions can be linked to GBV. The sample size was 1,593 women in the four mentioned municipalities.

Md Mahfuzur Rahman Siddiquee, Jay Shah, Teresa Wu et al.

Automated anomaly detection from medical images, such as MRIs and X-rays, can significantly reduce human effort in disease diagnosis. Owing to the complexity of modeling anomalies and the high cost of manual annotation by domain experts (e.g., radiologists), a typical technique in the current medical imaging literature has focused on deriving diagnostic models from healthy subjects only, assuming the model will detect the images from patients as outliers. However, in many real-world scenarios, unannotated datasets with a mix of both healthy and diseased individuals are abundant. Therefore, this paper poses the research question of how to improve unsupervised anomaly detection by utilizing (1) an unannotated set of mixed images, in addition to (2) the set of healthy images as being used in the literature. To answer the question, we propose HealthyGAN, a novel one-directional image-to-image translation method, which learns to translate the images from the mixed dataset to only healthy images. Being one-directional, HealthyGAN relaxes the requirement of cycle consistency of existing unpaired image-to-image translation methods, which is unattainable with mixed unannotated data. Once the translation is learned, we generate a difference map for any given image by subtracting its translated output. Regions of significant responses in the difference map correspond to potential anomalies (if any). Our HealthyGAN outperforms the conventional state-of-the-art methods by significant margins on two publicly available datasets: COVID-19 and NIH ChestX-ray14, and one institutional dataset collected from Mayo Clinic. The implementation is publicly available at https://github.com/mahfuzmohammad/HealthyGAN.

Twisha Titirsha, Shihao Song, Adarsha Balaji et al.

Neuromorphic computing systems such as DYNAPs and Loihi have recently been introduced to the computing community to improve performance and energy efficiency of machine learning programs, especially those that are implemented using Spiking Neural Network (SNN). The role of a system software for neuromorphic systems is to cluster a large machine learning model (e.g., with many neurons and synapses) and map these clusters to the computing resources of the hardware. In this work, we formulate the energy consumption of a neuromorphic hardware, considering the power consumed by neurons and synapses, and the energy consumed in communicating spikes on the interconnect. Based on such formulation, we first evaluate the role of a system software in managing the energy consumption of neuromorphic systems. Next, we formulate a simple heuristic-based mapping approach to place the neurons and synapses onto the computing resources to reduce energy consumption. We evaluate our approach with 10 machine learning applications and demonstrate that the proposed mapping approach leads to a significant reduction of energy consumption of neuromorphic computing systems.

Yao, Xiaopeng, Huang, Xinqiao, Yang, Chunmei et al.

BackgroundRadiomics can improve the accuracy of traditional image diagnosis to evaluate extrahepatic cholangiocarcinoma (ECC); however, this is limited by variations across radiologists, subjective evaluation, and restricted data. A radiomics-based particle swarm optimization and support vector machine (PSO-SVM) model may provide a more accurate auxiliary diagnosis for assessing differentiation degree (DD) and lymph node metastasis (LNM) of ECC. ObjectiveThe objective of our study is to develop a PSO-SVM radiomics model for predicting DD and LNM of ECC. MethodsFor this retrospective study, the magnetic resonance imaging (MRI) data of 110 patients with ECC who were diagnosed from January 2011 to October 2019 were used to construct a radiomics prediction model. Radiomics features were extracted from T1-precontrast weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI) using MaZda software (version 4.6; Institute of Electronics, Technical University of Lodz). We performed dimension reduction to obtain 30 optimal features of each sequence, respectively. A PSO-SVM radiomics model was developed to predict DD and LNM of ECC by incorporating radiomics features and apparent diffusion coefficient (ADC) values. We randomly divided the 110 cases into a training group (88/110, 80%) and a testing group (22/110, 20%). The performance of the model was evaluated by analyzing the area under the receiver operating characteristic curve (AUC). ResultsA radiomics model based on PSO-SVM was developed by using 110 patients with ECC. This model produced average AUCs of 0.8905 and 0.8461, respectively, for DD in the training and testing groups of patients with ECC. The average AUCs of the LNM in the training and testing groups of patients with ECC were 0.9036 and 0.8889, respectively. For the 110 patients, this model has high predictive performance. The average accuracy values of the training group and testing group for DD of ECC were 82.6% and 80.9%, respectively; the average accuracy values of the training group and testing group for LNM of ECC were 83.6% and 81.2%, respectively. ConclusionsThe MRI-based PSO-SVM radiomics model might be useful for auxiliary clinical diagnosis and decision-making, which has a good potential for clinical application for DD and LNM of ECC.