Hasil untuk "Computer applications to medicine. Medical informatics"

Sarah N. Abdulkader, Ayman Atia, Mostafa-Sami M. Mostafa

Wenbo Li, Bao Wang, Tianzun Li et al.

Abstract Cranioplasty is associated with a substantial burden of postoperative complications. In this multicenter study, we developed a machine learning–based clinical decision-support tool to predict the risk of postoperative complications following cranioplasty. A set of nine features was selected for model development. Among the 15 algorithms evaluated, the random forest model demonstrated the best overall performance and was validated on data from both spatial and temporal external cohorts (AUROC = 0.949, internal cross-validation; 0.930, geographical validation; and 0.932, temporal validation). Subgroup analyses by age and sex demonstrated consistently high discriminative performance (lowest AUROC = 0.927) and good calibration (O/E ratio = 1.16, 95% CI: 0.97–1.40). Analysis of causal effects of modifiable intraoperative variables on postoperative complications, with diverse counterfactual explanations and causal inference methods, including double machine learning and the T-learner framework, revealed a protective effect of subcutaneous negative-pressure drainage (ATE = −0.241) and titanium mesh (ATE = −0.191). Finally, we present the model as an accessible web-based tool for individualized, real-time clinical decision-making ( http://www.cranioplastycomplicationprediction.top ). These findings provide a practical framework for postoperative risk stratification and support the optimization of intraoperative decision-making in cranioplasty.

Kyra L. Rosen, Margaret Sui, Ariel Yuhan Ong et al.

Yakdan et al. demonstrate that foundation models (FMs) trained to predict cervical spondylotic myelopathy from electronic health record data outperform traditional models on internal datasets but lose their advantage during external validation. This suggests that the feature-dense patterns learned by FMs may reduce their portability across settings, particularly for rare outcomes. As FMs approach clinical deployment, local validation, subgroup analysis, and attention to implementation burden are essential to inform health system planning and stewardship.

Phuong Lien To

This study explores the development of a financial management application for young people using Alan Cooper's Goal-Directed Design method. Through interviews, surveys, and usability testing, the application was designed to improve financial literacy by combining personalised features and gamification. Findings highlight the effectiveness of gamified learning and tailored experiences in encouraging better financial behaviour among young users.

Marcus A Rauhut

Background Many adults are overdue for important screenings and vaccines, but providers have limited resources to address these care gaps. Electronic messaging, including patient portal messaging, can be an effective intervention to increase screening and vaccine adherence. However, there is limited research examining variables influencing intervention efficacy beyond demographic variables. Objective This study aims to identify whether patient portal engagement and primary care visits affect the efficacy of patient portal-based screening or vaccine reminders. Methods A retrospective analysis of electronic medical record data was used to evaluate the completion of screening mammograms, influenza vaccinations, and fecal immunochemical test (FIT) screenings for approximately 400,000 MyChart patient portal users at a large integrated health system. A logistic regression analysis was performed to calculate odds ratios associated with intervention completion. Results When adjusted for age, race, and sex, MyChart engagement is associated with increased odds of completing patient portal interventions for mammograms, flu vaccines, and FIT screenings. When adjusted for age, race, and sex, primary care visits are associated with increased odds of completing flu vaccines and FIT screenings but not mammograms following a patient portal intervention. Conclusions Overall patient portal engagement is critical to portal-based preventive health interventions. These interventions are most successful when combined with office-based interventions, but there is a potential in some scenarios that digital interventions can be successful without office-based interventions. This research contributes to the existing literature around screening adherence and patient portals’ impact on health outcomes.

Wael Hafez, Feras Al-Obeidat, Asrar Rashid et al.

Background: Kawasaki disease (KD) is a complex acquired condition characterized by systemic blood vessel inflammation that primarily affects children under five years of age. It is clinically diagnosed as a syndrome, making it susceptible to misdiagnoses. Severe complications such as myocardial damage and coronary artery abnormalities can be fatal; thus, early diagnosis is critical for preventing disease progression. Currently, no specific diagnostic test can distinguish KD from viral or bacterial infections. Additionally, the molecular mechanisms underlying the disease remain unclear, hindering the development of targeted therapies. Objective: This study aimed to identify the genetic patterns and molecular mechanisms associated with KD using a comprehensive gene expression analysis. Methods: RNA sequencing and microarray genomic datasets were retrieved from the NCBI Gene Expression Omnibus (GEO). Four datasets (GSE68004, GSE63881, GSE73461, and GSE73463) were used for the final analysis. These datasets compared patients with KD to healthy controls, and patients with acute KD to convalescent patients. Differentially expressed genes (DEGs) were identified in the datasets. Enrichment analysis was conducted, followed by protein-protein interaction (PPI) network analysis to identify hub genes. Heatmaps were generated to visualize gene expression patterns. Results: Eighteen hub genes were identified in the KD versus control comparison, whereas 20 hub genes were identified in the acute versus convalescent analysis. These genes play key roles in inflammation, cytokine storm, innate immune modulation, and endothelial damage. Conclusion: This study provides valuable insights into the molecular mechanisms underlying KD, and identifies potential diagnostic biomarkers and therapeutic targets.

Ziyun Zhang, Xinyi Liu, Xiaoyi Zhang et al.

External knowledge has played a crucial role in the recent development of computer use agents. We identify a critical knowledge-execution gap: retrieved knowledge often fails to translate into effective real-world task execution. Our analysis shows even 90% correct knowledge yields only 41% execution success rate. To bridge this gap, we propose UI-Evol, a plug-and-play module for autonomous GUI knowledge evolution. UI-Evol consists of two stages: a Retrace Stage that extracts faithful objective action sequences from actual agent-environment interactions, and a Critique Stage that refines existing knowledge by comparing these sequences against external references. We conduct comprehensive experiments on the OSWorld benchmark with the state-of-the-art Agent S2. Our results demonstrate that UI-Evol not only significantly boosts task performance but also addresses a previously overlooked issue of high behavioral standard deviation in computer use agents, leading to superior performance on computer use tasks and substantially improved agent reliability.

Andrej Kolar-Požun, Gregor Kosec

The finite difference time domain method is one of the simplest and most popular methods in computational electromagnetics. This work considers two possible ways of generalising it to a meshless setting by employing local radial basis function interpolation. The resulting methods remain fully explicit and are convergent if properly chosen hyperviscosity terms are added to the update equations. We demonstrate that increasing the stencil size of the approximation has a desirable effect on numerical dispersion. Furthermore, our proposed methods can exhibit a decreased dispersion anisotropy compared to the finite difference time domain method.

Rui Yang, Huitao Li, Matthew Yu Heng Wong et al.

Natural language processing (NLP) has been traditionally applied to medicine, and generative large language models (LLMs) have become prominent recently. However, the differences between them across different medical tasks remain underexplored. We analyzed 19,123 studies, finding that generative LLMs demonstrate advantages in open-ended tasks, while traditional NLP dominates in information extraction and analysis tasks. As these technologies advance, ethical use of them is essential to ensure their potential in medical applications.

David Eppstein, Michael T. Goodrich, Abraham M. Illickan et al.

We study entropy-bounded computational geometry, that is, geometric algorithms whose running times depend on a given measure of the input entropy. Specifically, we introduce a measure that we call range-partition entropy, which unifies and subsumes previous definitions of entropy used for sorting problems and structural entropy used in computational geometry. We provide simple algorithms for several problems, including 2D maxima, 2D and 3D convex hulls, and some visibility problems, and we show that they have running times depending on the range-partition entropy.

Nahid Azdaki, Fatemeh Salmani, Toba Kazemi et al.

Abstract Background Coronary artery disease (CAD) is recognized as the leading cause of death worldwide. This study analyses CAD risk factors using an artificial neural network (ANN) to predict CAD. Methods The research data were obtained from a multi-center study, namely the Iran-premature coronary artery disease (I-PAD). The current study used the medical records of 415 patients with CAD hospitalized in Razi Hospital, Birjand, Iran, between May 2016 and June 2019. A total of 43 variables that affect CAD were selected, and the relevant data was extracted. Once the data were cleaned and normalized, they were imported into SPSS (V26) for analysis. The present study used the ANN technique. Results The study revealed that 48% of the study population had a history of CAD, including 9.4% with premature CAD and 38.8% with CAD. The variables of age, sex, occupation, smoking, opium use, pesticide exposure, anxiety, sexual activity, and high fasting blood sugar were found to be significantly different among the three groups of CAD, premature CAD, and non-CAD individuals. The neural network achieved success with five hidden fitted layers and an accuracy of 81% in non-CAD diagnosis, 79% in premature diagnosis, and 78% in CAD diagnosis. Anxiety, acceptance, eduction and gender were the four most important factors in the ANN model. Conclusions The current study shows that anxiety is a high-prevalence risk factor for CAD in the hospitalized population. There is a need to implement measures to increase awareness about the psychological factors that can be managed in individuals at high risk for future CAD.

Broňa Brejová, Travis Gagie, Eva Herencsárová et al.

We generalize a problem of finding maximum-scoring segment sets, previously studied by Csűrös (IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2004, 1, 139–150), from sequences to graphs. Namely, given a vertex-weighted graph G and a non-negative startup penalty c, we can find a set of vertex-disjoint paths in G with maximum total score when each path’s score is its vertices’ total weight minus c. We call this new problem maximum-scoring path sets (MSPS). We present an algorithm that has a linear-time complexity for graphs with a constant treewidth. Generalization from sequences to graphs allows the algorithm to be used on pangenome graphs representing several related genomes and can be seen as a common abstraction for several biological problems on pangenomes, including searching for CpG islands, ChIP-seq data analysis, analysis of region enrichment for functional elements, or simple chaining problems.

Kerstin Gierend, Frank Krüger, Sascha Genehr et al.

BackgroundThe record of the origin and the history of data, known as provenance, holds importance. Provenance information leads to higher interpretability of scientific results and enables reliable collaboration and data sharing. However, the lack of comprehensive evidence on provenance approaches hinders the uptake of good scientific practice in clinical research. ObjectiveThis scoping review aims to identify approaches and criteria for provenance tracking in the biomedical domain. We reviewed the state-of-the-art frameworks, associated artifacts, and methodologies for provenance tracking. MethodsThis scoping review followed the methodological framework developed by Arksey and O’Malley. We searched the PubMed and Web of Science databases for English-language articles published from 2006 to 2022. Title and abstract screening were carried out by 4 independent reviewers using the Rayyan screening tool. A majority vote was required for consent on the eligibility of papers based on the defined inclusion and exclusion criteria. Full-text reading and screening were performed independently by 2 reviewers, and information was extracted into a pretested template for the 5 research questions. Disagreements were resolved by a domain expert. The study protocol has previously been published. ResultsThe search resulted in a total of 764 papers. Of 624 identified, deduplicated papers, 66 (10.6%) studies fulfilled the inclusion criteria. We identified diverse provenance-tracking approaches ranging from practical provenance processing and managing to theoretical frameworks distinguishing diverse concepts and details of data and metadata models, provenance components, and notations. A substantial majority investigated underlying requirements to varying extents and validation intensities but lacked completeness in provenance coverage. Mostly, cited requirements concerned the knowledge about data integrity and reproducibility. Moreover, these revolved around robust data quality assessments, consistent policies for sensitive data protection, improved user interfaces, and automated ontology development. We found that different stakeholder groups benefit from the availability of provenance information. Thereby, we recognized that the term provenance is subjected to an evolutionary and technical process with multifaceted meanings and roles. Challenges included organizational and technical issues linked to data annotation, provenance modeling, and performance, amplified by subsequent matters such as enhanced provenance information and quality principles. ConclusionsAs data volumes grow and computing power increases, the challenge of scaling provenance systems to handle data efficiently and assist complex queries intensifies, necessitating automated and scalable solutions. With rising legal and scientific demands, there is an urgent need for greater transparency in implementing provenance systems in research projects, despite the challenges of unresolved granularity and knowledge bottlenecks. We believe that our recommendations enable quality and guide the implementation of auditable and measurable provenance approaches as well as solutions in the daily tasks of biomedical scientists. International Registered Report Identifier (IRRID)RR2-10.2196/31750

Gurucharan Marthi Krishna Kumar, Janine Mendola, Amir Shmuel

Deformable image registration is crucial for aligning medical images in a nonlinear fashion across different modalities, allowing for precise spatial correspondence between varying anatomical structures. This paper presents NestedMorph, a novel network utilizing a Nested Attention Fusion approach to improve intra-subject deformable registration between T1-weighted (T1w) MRI and diffusion MRI (dMRI) data. NestedMorph integrates high-resolution spatial details from an encoder with semantic information from a decoder using a multi-scale framework, enhancing both local and global feature extraction. Our model notably outperforms existing methods, including CNN-based approaches like VoxelMorph, MIDIR, and CycleMorph, as well as Transformer-based models such as TransMorph and ViT-V-Net, and traditional techniques like NiftyReg and SyN. Evaluations using the HCP dataset demonstrate that NestedMorph achieves superior performance across key metrics, including SSIM, HD95, and SDlogJ, with the highest SSIM of 0.89, the lowest HD95 of 2.5 and SDlogJ of 0.22. These results highlight NestedMorph's ability to capture both local and global image features effectively, leading to superior registration performance. The promising outcomes of this study underscore NestedMorph's potential to significantly advance deformable medical image registration, providing a robust framework for future research and clinical applications. The source code and our implementation are available at: https://github.com/AS-Lab/Marthi-et-al-2024-NestedMorph-Deformable-Medical-Image-Registration

Xiaofei Chen

This article explores the critical role of statistical analysis in precision medicine. It discusses how personalized healthcare is enhanced by statistical methods that interpret complex, multidimensional datasets, focusing on predictive modeling, machine learning algorithms, and data visualization techniques. The paper addresses challenges in data integration and interpretation, particularly with diverse data sources like electronic health records (EHRs) and genomic data. It also delves into ethical considerations such as patient privacy and data security. In addition, the paper highlights the evolution of statistical analysis in medicine, core statistical methodologies in precision medicine, and future directions in the field, emphasizing the integration of artificial intelligence (AI) and machine learning (ML).

Li Guo, Anas M. Tahir, Dong Zhang et al.

The increasing demand for medical imaging has surpassed the capacity of available radiologists, leading to diagnostic delays and potential misdiagnoses. Artificial intelligence (AI) techniques, particularly in automatic medical report generation (AMRG), offer a promising solution to this dilemma. This review comprehensively examines AMRG methods from 2021 to 2024. It (i) presents solutions to primary challenges in this field, (ii) explores AMRG applications across various imaging modalities, (iii) introduces publicly available datasets, (iv) outlines evaluation metrics, (v) identifies techniques that significantly enhance model performance, and (vi) discusses unresolved issues and potential future research directions. This paper aims to provide a comprehensive understanding of the existing literature and inspire valuable future research.

Mariano Torcal, Emily Carty, Josep Maria Comellas et al.

The TRI-POL project explores the triangle of interactive relationships between affective and ideological polarisation, political distrust, and the politics of party competition. In this project there are two complementary groups of datasets with individual-level survey data and digital trace data collected in five countries: Argentina, Chile, Italy, Portugal and Spain. These datasets are comprised of three waves carried out over a six-month period between late September 2021 and April 2022. In addition, the survey datasets include a series of experiments embedded in the different waves that examine social exposure, polarisation framing, and social sorting. The digital trace datasets include variables on individuals’ behaviours and exposure to information received via digital media and social media. This data was collected using a combination of tracking technologies that the interviewees installed in their different devices. This digital trace data is matched with the individual-level survey data. These datasets are especially useful for researchers who wish to explore dynamics of polarisation, political attitudes, and political communication.

Vera Stara, Luca Soraci, Eiko Takano et al.

BackgroundThe worldwide aging trend requires conceptually new prevention, care, and innovative living solutions to support human-based care using smart technology, and this concerns the whole world. Enabling access to active and healthy aging through personalized digital coaching services like physical activity coaching, cognitive training, emotional well-being, and social connection for older adults in real life could offer valuable advantages to both individuals and societies. A starting point might be the analysis of the perspectives of different professionals (eg, geriatricians) on such technologies. The perspectives of experts in the sector may allow the individualization of areas of improvement of clinical interventions, supporting the positive perspective pointed out by the intrinsic capacity framework. ObjectiveThe overall aim of this study was to explore the cross-national perspectives and experiences of different professionals in the field of intrinsic capacity, and how it can be supported by eHealth interventions. To our knowledge, this is the first study to explore geriatric care providers’ perspectives about technology-based interventions to support intrinsic capacity. MethodsA survey involving 20 geriatricians or clinical experts in the fields of intrinsic capacity and active and healthy aging was conducted in Italy, France, Germany, and Japan between August and September 2021. ResultsThe qualitative findings pointed out relevant domains for eHealth interventions and provided examples for successful practices that support subjective well-being under the intrinsic capacity framework (the benefits offered by personalized interventions, especially by promoting health literacy but avoiding intrusiveness). Moreover, eHealth interventions could be used as a bridge that facilitates and enables social engagement; an instrument that facilitates communication between doctors and patients; and a tool to enrich the monitoring actions of medical staff. ConclusionsThere is an unexplored and significant role for such geriatric perspectives to help the development process and evaluate the evidence-based results on the effectiveness of technologies for older people. This is possible only when clinicians collaborate with data scientists, engineers, and developers in order to match the complex daily needs of older adults.

Gary OSTERTAG

Recently, Mann et al.1 proposed the use of “personalized” Large Language Models (LLMs) to create professional-grade academic writing. Their model, AUTOGEN, is first trained on a standard corpus and then “fine-tuned” by further training on the academic writings of a small cohort of authors. The resulting LLMs outperform the GPT-3 base model, producing text that rivals expert-written text in readability and coherence. With judicious prompting, such LLMs have the capacity to generate academic papers. Mann et al. even go so far as to claim that these LLMs can “enhance” academic prose and be useful in “idea generation”1. I argue that these bold claims cannot be correct. While we can grant that the sample texts appear coherent and may seem to contain “new ideas”, any appearance of coherence or novelty is solely “in the eye of the beholder” (Bender et al.2). Since the generated text is not produced by an agent with communicative intentions (Grice 19573) our ordinary notions of interpretation – and, derivatively, of such notions as coherence – break down. As readers, we proceed with the default assumption that a text has been produced in good faith, naturally trusting what it says to be true (absent indications to the contrary) and expecting these truths to form a coherent whole. But this default assumption is misplaced in generated texts and, if unchecked, will allow both falsehoods and inconsistencies to pass under our radar. Whatever one thinks of the use of LLMs to help create content for commercial publications, their use in generating articles for publication in scientific journals should raise alarms.

Youran Noh, Maryanne Kim, Song Hee Hong

BackgroundPatient medication reviews on social networking sites provide valuable insights into the experiences and sentiments of individuals taking specific medications. Understanding the emotional spectrum expressed by patients can shed light on their overall satisfaction with medication treatment. This study aims to explore the emotions expressed by patients taking phosphodiesterase type 5 (PDE5) inhibitors and their impact on sentiment. ObjectiveThis study aimed to (1) identify the distribution of 6 Parrot emotions in patient medication reviews across different patient characteristics and PDE5 inhibitors, (2) determine the relative impact of each emotion on the overall sentiment derived from the language expressed in each patient medication review while controlling for different patient characteristics and PDE5 inhibitors, and (3) assess the predictive power of the overall sentiment in explaining patient satisfaction with medication treatment. MethodsA data set of patient medication reviews for sildenafil, vardenafil, and tadalafil was collected from 3 popular social networking sites such as WebMD, Ask-a-Patient, and Drugs.com. The Parrot emotion model, which categorizes emotions into 6 primary classes (surprise, anger, love, joy, sadness, and fear), was used to analyze the emotional content of the reviews. Logistic regression and sentiment analysis techniques were used to examine the distribution of emotions across different patient characteristics and PDE5 inhibitors and to quantify their contribution to sentiment. ResultsThe analysis included 3070 patient medication reviews. The most prevalent emotions expressed were joy and sadness, with joy being the most prevalent among positive emotions and sadness being the most prevalent among negative emotions. Emotion distributions varied across patient characteristics and PDE5 inhibitors. Regression analysis revealed that joy had the strongest positive impact on sentiment, while sadness had the most negative impact. The sentiment score derived from patient reviews significantly predicted patient satisfaction with medication treatment, explaining 19% of the variance (increase in R2) when controlling for patient characteristics and PDE5 inhibitors. ConclusionsThis study provides valuable insights into the emotional experiences of patients taking PDE5 inhibitors. The findings highlight the importance of emotions in shaping patient sentiment and satisfaction with medication treatment. Understanding these emotional dynamics can aid health care providers in better addressing patient needs and improving overall patient care.