Artificial Intelligence in Medicine最新文献

{"title":"Design and use of a Denoising Convolutional Autoencoder for reconstructing electrocardiogram signals at super resolution","authors":"Ugo Lomoio ,&nbsp;Pierangelo Veltri ,&nbsp;Pietro Hiram Guzzi ,&nbsp;Pietro Liò","doi":"10.1016/j.artmed.2024.103058","DOIUrl":"10.1016/j.artmed.2024.103058","url":null,"abstract":"<div><div>Electrocardiogram signals play a pivotal role in cardiovascular diagnostics, providing essential information on electrical hearth activity. However, inherent noise and limited resolution can hinder an accurate interpretation of the recordings. In this paper an advanced Denoising Convolutional Autoencoder designed to process electrocardiogram signals, generating super-resolution reconstructions is proposed; this is followed by in-depth analysis of the enhanced signals. The autoencoder receives a signal window (of 5 s) sampled at 50 Hz (low resolution) as input and reconstructs a denoised super-resolution signal at 500 Hz. The proposed autoencoder is applied to publicly available datasets, demonstrating optimal performance in reconstructing high-resolution signals from very low-resolution inputs sampled at 50 Hz. The results were then compared with current state-of-the-art for electrocardiogram super-resolution, demonstrating the effectiveness of the proposed method. The method achieves a signal-to-noise ratio of 12.20 dB, a mean squared error of 0.0044, and a root mean squared error of 4.86%, which significantly outperforms current state-of-the-art alternatives. This framework can effectively enhance hidden information within signals, aiding in the detection of heart-related diseases.</div></div>","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"160 ","pages":"Article 103058"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142915779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic review on the roles of remote diagnosis in telemedicine system: Coherent taxonomy, insights, recommendations, and open research directions for intelligent healthcare solutions","authors":"Sura Saad Mohsin ,&nbsp;Omar H. Salman ,&nbsp;Abdulrahman Ahmed Jasim ,&nbsp;Mohammed A. Al-Nouman ,&nbsp;Ammar Riadh Kairaldeen","doi":"10.1016/j.artmed.2024.103057","DOIUrl":"10.1016/j.artmed.2024.103057","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;Background&lt;/h3&gt;&lt;div&gt;The term ‘remote diagnosis’ in telemedicine describes the procedure wherein medical practitioners diagnose patients remotely by using telecommunications technology. With this method, patients can obtain medical care without having to physically visit a hospital, which can be helpful for people who live in distant places or have restricted mobility. When people in the past had health issues, they were usually sent to the hospital, where they received clinical examinations, diagnoses, and treatment at the facility. Thus, hospitals were overcrowded because of the increase in the number of patients or in the death of some very ill patients given that the completion of medical operations required a significant amount of time.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Objective&lt;/h3&gt;&lt;div&gt;This research aims to provide a literature review study and an in-depth analysis to (1) investigate the procedure and roles of remote diagnosis in telemedicine; (2) review the technical tools and technologies used in remote diagnosis; (3) review the diseases diagnosed remotely in telemedicine; (4) compose a crossover taxonomy among diseases, technologies, and telemedicine; (5) present lists of input variables, vital signs, data and output decisions already applied in remote diagnosis; (6) Summarize the performance assessment measures utilized to assess and validate remote diagnosis models; and (7) identify and categorize open research issues while providing recommendations for future advancements in intelligent remote diagnosis within telemedicine systems.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Methods&lt;/h3&gt;&lt;div&gt;A systematic search was conducted using online libraries for articles published from 1 January 2016 to 13 September 2023 in IEEE, PubMed, Science Direct, Springer, and Web of Science. Notably, searches were limited to articles in the English language. The papers examine remote diagnosis in telemedicine, the technologies employed for this function, and the ramifications of diagnosing patients outside hospital settings. Each selected study was synthesized to furnish proof about the implementation of remote diagnostics in telemedicine.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Results&lt;/h3&gt;&lt;div&gt;A new crossover taxonomy between the most important diagnosed diseases and technologies used for this purpose and their relationship with telemedicine tiers is proposed. The functions executed at each tier are elucidated. Additionally, a compilation of diagnostic technologies is provided. Additionally, open research difficulties, advantages of remote diagnosis in telemedicine, and suggestions for future research prospects that require attention are systematically organized and presented.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Conclusions&lt;/h3&gt;&lt;div&gt;This study reviews the role of remote diagnosis in telemedicine, with a focus on key technologies and current approaches. This study highlights research challenges, provides recommendations for future directions, and addresses research gaps and limitations to provide a clear vision of r","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"160 ","pages":"Article 103057"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Concordance-based Predictive Uncertainty (CPU)-Index: Proof-of-concept with application towards improved specificity of lung cancers on low dose screening CT","authors":"Yuqi Wang ,&nbsp;Aarzu Gupta ,&nbsp;Fakrul Islam Tushar ,&nbsp;Breylon Riley ,&nbsp;Avivah Wang ,&nbsp;Tina D. Tailor ,&nbsp;Stacy Tantum ,&nbsp;Jian-Guo Liu ,&nbsp;Mustafa R. Bashir ,&nbsp;Joseph Y. Lo ,&nbsp;Kyle J. Lafata","doi":"10.1016/j.artmed.2024.103055","DOIUrl":"10.1016/j.artmed.2024.103055","url":null,"abstract":"<div><div>In this paper, we introduce a novel concordance-based predictive uncertainty (CPU)-Index, which integrates insights from subgroup analysis and personalized AI time-to-event models. Through its application in refining lung cancer screening (LCS) predictions generated by an individualized AI time-to-event model trained with fused data of low dose CT (LDCT) radiomics with patient demographics, we demonstrate its effectiveness, resulting in improved risk assessment compared to the Lung CT Screening Reporting &amp; Data System (Lung-RADS). Subgroup-based Lung-RADS faces challenges in representing individual variations and relies on a limited set of predefined characteristics, resulting in variable predictions. Conversely, personalized AI time-to-event models are hindered by transparency issues and biases from censored data. By measuring the prediction consistency between subgroup analysis and AI time-to-event models, the CPU-Index framework offers a nuanced evaluation of the bias–variance trade-off and improves the transparency and reliability of predictions. Consistency was estimated by the concordance index of subgroup analysis-based similarity rank and model prediction similarity rank. Subgroup analysis-based similarity loss was defined as the sum-of-the-difference between Lung-RADS and feature-level 0-1 loss. Model prediction similarity loss was defined as squared loss. To test our approach, we identified 3,326 patients who underwent LDCT for LCS from 1/1/2015 to 6/30/2020 with confirmation of lung cancer on pathology within one year. For each LDCT image, the lesion associated with a Lung-RADS score was detected using a pretrained deep learning model from Medical Open Network for AI (MONAI), from which radiomic features were extracted. Radiomics were optimally fused with patient demographics via a positional encoding scheme and used to train a neural multi-task logistic regression time-to-event model that predicts malignancy. Performance was maximized when radiomics features were fused with positionally encoded demographic features. In this configuration, our algorithm raised the AUC from 0.81 ± 0.04 to 0.89 ± 0.02. Compared to standard Lung-RADS, our approach reduced the False-Positive-Rate from 0.41 ± 0.02 to 0.30 ± 0.12 while maintaining the same False-Negative-Rate. Our methodology enhances lung cancer risk assessment by estimating prediction uncertainty and adjusting accordingly. Furthermore, the optimal integration of radiomics and patient demographics improved overall diagnostic performance, indicating their complementary nature.</div></div>","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"160 ","pages":"Article 103055"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142900660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advances in diagnosis and prognosis of bacteraemia, bloodstream infection, and sepsis using machine learning: A comprehensive living literature review","authors":"Hernandez B. ,&nbsp;Ming D.K. ,&nbsp;Rawson T.M. ,&nbsp;Bolton W. ,&nbsp;Wilson R. ,&nbsp;Vasikasin V. ,&nbsp;Daniels J. ,&nbsp;Rodriguez-Manzano J. ,&nbsp;Davies F.J. ,&nbsp;Georgiou P. ,&nbsp;Holmes A.H.","doi":"10.1016/j.artmed.2024.103008","DOIUrl":"10.1016/j.artmed.2024.103008","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;Background:&lt;/h3&gt;&lt;div&gt;Blood-related infections are a significant concern in healthcare. They can lead to serious medical complications and even death if not promptly diagnosed and treated. Throughout time, medical research has sought to identify clinical factors and strategies to improve the management of these conditions. The increasing adoption of electronic health records has led to a wealth of electronically available medical information and predictive models have emerged as invaluable tools. This manuscript offers a detailed survey of machine-learning techniques used for the diagnosis and prognosis of bacteraemia, bloodstream infections, and sepsis shedding light on their efficacy, potential limitations, and the intricacies of their integration into clinical practice.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Methods:&lt;/h3&gt;&lt;div&gt;This study presents a comprehensive analysis derived from a thorough search across prominent databases, namely EMBASE, Google Scholar, PubMed, Scopus, and Web of Science, spanning from their inception dates to October 25, 2023. Eligibility assessment was conducted independently by investigators, with inclusion criteria encompassing peer-reviewed articles and pertinent non-peer-reviewed literature. Clinical and technical data were meticulously extracted and integrated into a registry, facilitating a holistic examination of the subject matter. To maintain currency and comprehensiveness, readers are encouraged to contribute manuscript suggestions and/or reports for integration into this living registry.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Results:&lt;/h3&gt;&lt;div&gt;While machine learning (ML) models exhibit promise in advanced disease stages such as sepsis, early stages remain underexplored due to data limitations. Biochemical markers emerge as pivotal predictors during early stages such as bacteraemia, or bloodstream infections, while vital signs assume significance in sepsis prognosis. Integrating temporal trend information into conventional machine learning models appears to enhance performance. Unfortunately, sequential deep learning models face challenges, showing minimal performance improvements and significant drops in external datasets, potentially due to learning missing patterns within the scarce data available rather than understanding disease dynamics. Real-life implementation receives limited attention, as meeting design requirements proves challenging within existing healthcare infrastructure. The data collected in an event-based fashion during clinical practice is insufficient to fully harness the potential of these data-hungry models. Despite limitations, opportunities abound in leveraging flexible models and exploiting real-time non-invasive data collection technologies such as wearable devices or microneedles. Addressing research gaps in early disease stages, harnessing patient history data often underused, and embracing continual diagnostics beyond treatment initiation are crucial for improving healthcare decision-making support and adoption","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"160 ","pages":"Article 103008"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Practical X-ray gastric cancer diagnostic support using refined stochastic data augmentation and hard boundary box training","authors":"Hideaki Okamoto ,&nbsp;Quan Huu Cap ,&nbsp;Takakiyo Nomura ,&nbsp;Kazuhito Nabeshima ,&nbsp;Jun Hashimoto ,&nbsp;Hitoshi Iyatomi","doi":"10.1016/j.artmed.2025.103075","DOIUrl":"10.1016/j.artmed.2025.103075","url":null,"abstract":"<div><div>Endoscopy is widely used to diagnose gastric cancer and has a high diagnostic performance, but it must be performed by a physician, which limits the number of people who can be diagnosed. In contrast, gastric X-rays can be taken by radiographers, thus allowing a much larger number of patients to undergo imaging. However, the diagnosis of X-ray images relies heavily on the expertise and experience of physicians, and few machine learning methods have been developed to assist in this process. We propose a novel and practical gastric cancer diagnostic support system for gastric X-ray images that will enable more people to be screened. The system is based on a general deep learning-based object detection model and incorporates two novel techniques: refined probabilistic stomach image augmentation (R-sGAIA) and hard boundary box training (HBBT). R-sGAIA enhances the probabilistic gastric fold region and provides more learning patterns for cancer detection models. HBBT is an efficient training method that improves model performance by allowing the use of unannotated negative (i.e., healthy control) samples, which are typically unusable in conventional detection models. The proposed system achieved a sensitivity (SE) for gastric cancer of 90.2%, higher than that of an expert (85.5%). Under these conditions, two out of five candidate boxes identified by the system were cancerous (precision = 42.5%), with an image processing speed of 0.51 s per image. The system also outperformed methods using the same object detection model and state-of-the-art data augmentation by showing a 5.9-point improvement in the F1 score. In summary, this system efficiently identifies areas for radiologists to examine within a practical time frame, thus significantly reducing their workload.</div></div>","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"161 ","pages":"Article 103075"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143326565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intrinsic-dimension analysis for guiding dimensionality reduction and data fusion in multi-omics data processing","authors":"Jessica Gliozzo ,&nbsp;Mauricio Soto-Gomez ,&nbsp;Valentina Guarino ,&nbsp;Arturo Bonometti ,&nbsp;Alberto Cabri ,&nbsp;Emanuele Cavalleri ,&nbsp;Justin Reese ,&nbsp;Peter N. Robinson ,&nbsp;Marco Mesiti ,&nbsp;Giorgio Valentini ,&nbsp;Elena Casiraghi","doi":"10.1016/j.artmed.2024.103049","DOIUrl":"10.1016/j.artmed.2024.103049","url":null,"abstract":"<div><div>Multi-omics data have revolutionized biomedical research by providing a comprehensive understanding of biological systems and the molecular mechanisms of disease development. However, analyzing multi-omics data is challenging due to high dimensionality and limited sample sizes, necessitating proper data-reduction pipelines to ensure reliable analyses. Additionally, its multimodal nature requires effective data-integration pipelines.</div><div>While several dimensionality reduction and data fusion algorithms have been proposed, crucial aspects are often overlooked. Specifically, the choice of projection space dimension is typically heuristic and uniformly applied across all omics, neglecting the unique high dimension small sample size challenges faced by individual omics.</div><div>This paper introduces a novel multi-modal dimensionality reduction pipeline tailored to individual views. By leveraging intrinsic dimensionality estimators, we assess the curse-of-dimensionality impact on each view and propose a two-step reduction strategy for significantly affected views, combining feature selection with feature extraction.</div><div>Compared to traditional uniform reduction pipelines in a crucial and supervised multi-omics analysis setting, our approach shows significant improvement. Additionally, we explore three effective unsupervised multi-omics data fusion methods rooted in the main data fusion strategies to gain insights into their performance under crucial, yet overlooked, settings.</div></div>","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"160 ","pages":"Article 103049"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142824829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computer model for gait assessments in Parkinson's patients using a fuzzy inference model and inertial sensors","authors":"Luis Pastor Sánchez-Fernández ,&nbsp;Luis Alejandro Sánchez-Pérez ,&nbsp;Juan Manuel Martínez-Hernández","doi":"10.1016/j.artmed.2024.103059","DOIUrl":"10.1016/j.artmed.2024.103059","url":null,"abstract":"<div><div>Patients with Parkinson's disease (PD) in the moderate and severe stages can present several walk alterations. They can show slow movements and difficulty initiating, varying, or interrupting their gait; freezing; short steps; speed changes; shuffling; little arm swing; and festinating gait. The Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) has a good reputation for uniformly evaluating motor and non-motor aspects of PD. However, the motor clinical assessment depends on visual observations, the results are qualitative, and subtle differences are not identified. This study presents a fuzzy inference model for gait assessments in PD patients with detailed descriptions of signal processing and eight biomechanical indicators computations; as such, other authors can replicate the presented methods. The computer model uses 334 bilateral measurements of 58 Parkinson's patients and 15 healthy control subjects performed over one year. The computer model validations are based on physician evaluations in real-time and post-analysis using an extensive database of videos and signals. The assessment results are explainable, quantitative, and qualitative, increasing their acceptance and use in clinical environments. The computer system design considers three expert motor evaluations, including the PD patients' evolutions; this facilitates correlation with medication doses and appropriate intervals for follow-up medical consultations. The assessments include three qualitative gait conditions of MDS-UPDRS—normal, slight, and mild—as well as a numerical evaluation of up to two decimal places.</div></div>","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"160 ","pages":"Article 103059"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142900658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fraud detection in healthcare claims using machine learning: A systematic review","authors":"Anli du Preez ,&nbsp;Sanmitra Bhattacharya ,&nbsp;Peter Beling ,&nbsp;Edward Bowen","doi":"10.1016/j.artmed.2024.103061","DOIUrl":"10.1016/j.artmed.2024.103061","url":null,"abstract":"<div><h3>Objective:</h3><div>Identifying fraud in healthcare programs is crucial, as an estimated 3%–10% of the total healthcare expenditures are lost to fraudulent activities. This study presents a systematic literature review of machine learning techniques applied to fraud detection in health insurance claims. We aim to analyze the data and methodologies documented in the literature over the past two decades, providing insights into research challenges and opportunities.</div></div><div><h3>Methods:</h3><div>We identified research studies on health insurance fraud detection using machine learning approaches from databases such as Google Scholar, Springer-Link journals, Elsevier, PubMed, Excerpta Medica Database (EMBASE), Scopus, the Association for Computing Machinery (ACM) Digital Library, and the Institute of Electrical and Electronics Engineers (IEEE) Xplore Digital Library. We included only articles that presented experimental results of machine learning-based approaches applied to healthcare claims. From the reviewed articles, 137 were selected for the final qualitative and quantitative analyses.</div></div><div><h3>Results:</h3><div>In recent years, there has been a surge in publications centered on the use of machine learning to detect health insurance fraud. Among these studies, those focused on the detection of fraud committed by healthcare providers was the most prevalent, followed by fraud committed by patients. A wide variety of machine learning algorithms are highlighted in these studies, ranging from unsupervised (41 studies) and supervised methods (94 studies), to hybrid approaches (12 studies). While traditional machine learning approaches remain dominant in this research area, the adoption of advanced deep learning techniques is on the rise. Considering the type of healthcare claims data used, 30 studies utilized private data sources, while the rest used publicly available datasets. Data from 16 countries were utilized, with a majority coming from the United States (96 studies), followed by China (11 studies) and Australia (5 studies).</div></div><div><h3>Discussion and Conclusion:</h3><div>Detecting fraud in healthcare claims using machine learning presents several challenges. These include inconsistent data, absence of data standardization and integration, privacy concerns, and a limited number of labeled fraudulent cases to train models on. Future work should focus on enhancing transparency in data preparation, promoting the sharing of fraud investigation outcomes by authorities, and developing benchmark datasets to enhance accessibility and comparability. Furthermore, innovative techniques in data sampling, feature encoding methods for training machine learning models, and exploring the latest advancements in deep learning can significantly advance research in health insurance fraud detection.</div></div>","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"160 ","pages":"Article 103061"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142933715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of radiological decision errors from longitudinal analysis of gaze and image features","authors":"Anna Anikina ,&nbsp;Diliara Ibragimova ,&nbsp;Tamerlan Mustafaev ,&nbsp;Claudia Mello-Thoms ,&nbsp;Bulat Ibragimov","doi":"10.1016/j.artmed.2024.103051","DOIUrl":"10.1016/j.artmed.2024.103051","url":null,"abstract":"<div><div>Medical imaging, particularly radiography, is an indispensable part of diagnosing many chest diseases. Final diagnoses are made by radiologists based on images, but the decision-making process is always associated with a risk of incorrect interpretation. Incorrectly interpreted data can lead to delays in treatment, a prescription of inappropriate therapy, or even a completely missed diagnosis. In this context, our study aims to determine whether it is possible to predict diagnostic errors made by radiologists using eye-tracking technology. For this purpose, we asked 4 radiologists with different levels of experience to analyze 1000 images covering a wide range of chest diseases. Using eye-tracking data, we calculated the radiologists’ gaze fixation points and generated feature vectors based on this data to describe the radiologists’ gaze behavior during image analysis. Additionally, we emulated the process of revealing the read images following radiologists’ gaze data to create a more comprehensive picture of their analysis. Then we applied a recurrent neural network to predict diagnostic errors. Our results showed a 0.7755 ROC AUC score, demonstrating a significant potential for this approach in enhancing the accuracy of diagnostic error recognition.</div></div>","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"160 ","pages":"Article 103051"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142873483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rough hypervolume-driven feature selection with groupwise intelligent sampling for detecting clinical characterization of lupus nephritis","authors":"Xinsen Zhou ,&nbsp;Yi Chen ,&nbsp;Ali Asghar Heidari ,&nbsp;Huiling Chen ,&nbsp;Xiaowei Chen","doi":"10.1016/j.artmed.2024.103042","DOIUrl":"10.1016/j.artmed.2024.103042","url":null,"abstract":"<div><div>Systemic lupus erythematosus (SLE) is an autoimmune inflammatory disease. Lupus nephritis (LN) is a major risk factor for morbidity and mortality in SLE. Proliferative and pure membranous LN have different prognoses and may require different treatments. This study proposes a binary rough hypervolume-driven spherical evolution algorithm with groupwise intelligent sampling (bRGSE). The efficient dimensionality reduction capability of the bRGSE is verified across twelve datasets. These datasets are from the public datasets, with feature dimensions ranging from seven hundred to fifty thousand. The experimental results indicate that bRGSE performs better than seven high-performing alternatives. Then, the bRGSE was combined with adaptive boosting (AdaBoost) to form a new model (bRGSE_AdaBoost), which analyzed clinical records collected from 110 patients with LN. Experimental results show that the proposed bRGSE_AdaBoost can identify the most critical indicators, including urine latent blood, white blood cells, endogenous creatinine clearing rate, and age. These indicators may help differentiate between proliferative LN and membranous LN. The proposed bRGSE algorithm is an efficient dimensionality reduction method. The developed bRGSE_AdaBoost model, a computer-aided model, achieved an accuracy of 96.687 % and is expected to provide early warning for the treatment and diagnosis of LN.</div></div>","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"160 ","pages":"Article 103042"},"PeriodicalIF":6.1,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142824848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}