Computer methods and programs in biomedicine最新文献

{"title":"Evaluation of blood- and urine-derived biomarkers for machine learning prediction models of osteoarthritis in elderly patients: A feasibility study","authors":"Jun-hee Kim","doi":"10.1016/j.cmpb.2025.108779","DOIUrl":"10.1016/j.cmpb.2025.108779","url":null,"abstract":"<div><h3>Background</h3><div>Osteoarthritis (OA) is a common degenerative joint disease, particularly affecting individuals aged &gt;50 years. It deteriorates quality of life and restricts physical activity in the elderly. Early diagnosis of OA is crucial for effective management, slowing disease progression, and alleviating symptoms.</div></div><div><h3>Objectives</h3><div>This study evaluated the feasibility of utilizing biomarkers derived from blood and urine in developing predictive models for OA diagnosis in the elderly population. Additionally, we compared the derived biomarker model with a model using standard blood and urine variables to assess the impact of the derived biomarkers on OA diagnosis.</div></div><div><h3>Methods</h3><div>Data from 10,743 participants were analyzed, including variables from blood and urine tests. Machine learning algorithms were used to develop the models. Derived biomarkers were identified based on the most significant features highlighted by Shapley Additive exPlanations (SHAP) analysis. The performance of models based on blood and urine biomarkers was compared with that of models based on derived biomarkers, and important variables were analyzed using SHAP.</div></div><div><h3>Results</h3><div>The support vector machine demonstrated the highest accuracy (0.6245) and F1 score (0.6232) for the blood dataset, whereas the random forest model achieved the best performance (0.5770) for the urine dataset. The derived biomarker model, which combined biomarkers of high importance from the best-performing models, showed improved predictive performance compared with the model using all blood and urine variables. The derived biomarker model achieved the highest performance metrics, with the logistic regression algorithm yielding an accuracy of 0.6450, precision of 0.6443, recall of 0.6450, and F1 score of 0.6430.</div></div><div><h3>Conclusions</h3><div>Biomarkers derived from routinely available blood and urine tests show promise for the early detection and comprehensive diagnosis of OA in older patients. These biomarkers are practical for clinical use, as they can be integrated into routine testing, potentially aiding early detection and improving patient outcomes.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"266 ","pages":"Article 108779"},"PeriodicalIF":4.9,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828505","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":"A radiomics approach to distinguish Progressive Supranuclear Palsy Richardson's syndrome from other phenotypes starting from MR images","authors":"Noemi Pisani ,&nbsp;Filomena Abate ,&nbsp;Anna Rosa Avallone ,&nbsp;Paolo Barone ,&nbsp;Mario Cesarelli ,&nbsp;Francesco Amato ,&nbsp;Marina Picillo ,&nbsp;Carlo Ricciardi","doi":"10.1016/j.cmpb.2025.108778","DOIUrl":"10.1016/j.cmpb.2025.108778","url":null,"abstract":"<div><h3>Background and objective</h3><div>Progressive Supranuclear Palsy (PSP) is an uncommon neurodegenerative disorder with different clinical onset, including Richardson's syndrome (PSP-RS) and other variant phenotypes (vPSP). Recognising the clinical progression of different phenotypes would enhance the accuracy of detection and treatment of PSP. The study goal was to identify radiomic biomarkers for distinguishing PSP phenotypes extracted from T1-weighted magnetic resonance images (MRI).</div></div><div><h3>Methods</h3><div>Forty PSP patients (20 PSP-RS and 20 vPSP) took part in the present work. Radiomic features were collected from 21 regions of interest (ROIs) mainly from frontal cortex, supratentorial white matter, basal nuclei, brainstem, cerebellum, 3rd and 4th ventricles. After features selection, three tree-based machine learning (ML) classifiers were implemented to classify PSP phenotypes.</div></div><div><h3>Results</h3><div>10 out of 21 ROIs performed best about sensitivity, specificity, accuracy and area under the receiver operating characteristic curve (AUCROC). Particularly, features extracted from the pons region obtained the best accuracy (0.92) and AUCROC (0.83) values while by using the other 10 ROIs, evaluation metrics range from 0.67 to 0.83. Eight features of the Gray Level Dependence Matrix were recurrently extracted for the 10 ROIs. Furthermore, by combining these ROIs, the results exceeded 0.83 in phenotypes classification and the selected areas were brain stem, pons, occipital white matter, precentral gyrus and thalamus regions.</div></div><div><h3>Conclusions</h3><div>Based on the achieved results, our proposed approach could represent a promising tool for distinguishing PSP-RS from vPSP.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"266 ","pages":"Article 108778"},"PeriodicalIF":4.9,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838768","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":"Automation of hospital workflows using international standards: A case study with imaging exams","authors":"Cristiana Neto,&nbsp;Francini Hak,&nbsp;Diana Ferreira,&nbsp;António Abelha,&nbsp;José Machado","doi":"10.1016/j.cmpb.2025.108777","DOIUrl":"10.1016/j.cmpb.2025.108777","url":null,"abstract":"<div><h3>Background</h3><div>Hospital workflow automation holds paramount importance in modern healthcare systems. By streamlining complex processes, it is possible to enhance operational efficiency and patient care. Automated workflows aligned with open standards, such as openEHR, enable accurate data capture, seamless communication, and timely task execution among healthcare professionals. This leads to reduced errors, improved patient outcomes, and optimized resource utilization.</div></div><div><h3>Objective</h3><div>This study aims to advance knowledge in healthcare workflow automation by improving a Portuguese hospital's medical imaging exams circuit through the implementation of clinical standards. Specifically, the study explores how openEHR specifications, particularly the Task Planning component, can be applied to streamline workflows and enhance interoperability.</div></div><div><h3>Methods</h3><div>A case study research design was selected to examine the imaging exams circuit in a Portuguese hospital, enabling detailed observation of system implementation and its effects. The focus was on implementing openEHR's Task Planning specification, along with forms and decision rules, to achieve comprehensive workflow automation.</div></div><div><h3>Results</h3><div>Following implementation, data from over 6800 imaging exam requests were analyzed, demonstrating health professionals' willingness to adopt the automated tools. A significant reduction in waiting times for outsourcing management was observed, with fewer waiting days on average in 2022 compared to 2019.</div></div><div><h3>Conclusion</h3><div>This study shows the development of a new approach to the imaging exams workflow using the openEHR specifications achieving an automated process with structured data generation. The authors believe that the developed system represents an important step towards efficient knowledge discovery from the registry of high-quality and structured data.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"266 ","pages":"Article 108777"},"PeriodicalIF":4.9,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838906","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":"Lag-Net: Lag correction for cone-beam CT via a convolutional neural network","authors":"Chenlong Ren ,&nbsp;Shengqi Kan ,&nbsp;Wenhui Huang ,&nbsp;Yan Xi ,&nbsp;Xu Ji ,&nbsp;Yang Chen","doi":"10.1016/j.cmpb.2025.108753","DOIUrl":"10.1016/j.cmpb.2025.108753","url":null,"abstract":"<div><h3>Background and objective:</h3><div>Due to the presence of charge traps in amorphous silicon flat-panel detectors, lag signals are generated in consecutively captured projections. These signals lead to ghosting in projection images and severe lag artifacts in cone-beam computed tomography (CBCT) reconstructions. Traditional Linear Time-Invariant (LTI) correction need to measure lag correction factors (LCF) and may leave residual lag artifacts. This incomplete correction is partly attributed to the lack of consideration for exposure dependency.</div></div><div><h3>Methods:</h3><div>To measure the lag signals more accurately and suppress lag artifacts, we develop a novel hardware correction method. This method requires two scans of the same object, with adjustments to the operating timing of the CT instrumentation during the second scan to measure the lag signal from the first. While this hardware correction significantly mitigates lag artifacts, it is complex to implement and imposes high demands on the CT instrumentation. To enhance the process, We introduce a deep learning method called Lag-Net to remove lag signal, utilizing the nearly lag-free results from hardware correction as training targets for the network.</div></div><div><h3>Results:</h3><div>Qualitative and quantitative analyses of experimental results on both simulated and real datasets demonstrate that deep learning correction significantly outperforms traditional LTI correction in terms of lag artifact suppression and image quality enhancement. Furthermore, the deep learning method achieves reconstruction results comparable to those obtained from hardware correction while avoiding the operational complexities associated with the hardware correction approach.</div></div><div><h3>Conclusion:</h3><div>The proposed hardware correction method, despite its operational complexity, demonstrates superior artifact suppression performance compared to the LTI algorithm, particularly under low-exposure conditions. The introduced Lag-Net, which utilizes the results of the hardware correction method as training targets, leverages the end-to-end nature of deep learning to circumvent the intricate operational drawbacks associated with hardware correction. Furthermore, the network’s correction efficacy surpasses that of the LTI algorithm in low-exposure scenarios.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"266 ","pages":"Article 108753"},"PeriodicalIF":4.9,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828504","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":"GDReCo: Fine-grained gene-disease relationship extraction corpus","authors":"Hui Yu ,&nbsp;Jing Wu ,&nbsp;Suyan Bian ,&nbsp;Sheng Zhang ,&nbsp;Yibin Wu ,&nbsp;Ziyan Zhou ,&nbsp;Qian Jia ,&nbsp;Yuan Ni ,&nbsp;Zhengxing Huang ,&nbsp;Huiyu Yan ,&nbsp;Weidong Wang ,&nbsp;Kunlun He ,&nbsp;Jinlong Shi","doi":"10.1016/j.cmpb.2025.108773","DOIUrl":"10.1016/j.cmpb.2025.108773","url":null,"abstract":"<div><h3>Background and objective</h3><div>Understanding gene-disease relationships is crucial for medical research, drug discovery, clinical diagnosis, and other fields. However, there is currently no high-quality, fine-grained corpus available for training Natural Language Processing (NLP) models, which have proven to be effective in knowledge extraction.</div></div><div><h3>Methods</h3><div>This study introduces a novel ontology framework for gene-disease associations, addressing the absence of a formal descriptive system and training corpus for NLP models.</div></div><div><h3>Results</h3><div>We developed the Gene Disease Relationship Extraction Corpus (GDReCo), a refined dataset of over 24,000+ cases, including 2300+ manually annotated and 22,000+ model-predicted instances. BERT-based models trained on this data achieved high F1-scores for \"event\" and \"rel\" relationships, validating its effectiveness for Gene-Disease Relationship Extraction (GDRE) tasks.</div></div><div><h3>Conclusions</h3><div>GDReCo serves as a valuable resource for biomedical research, though ChatGPT's limitations in fine-grained relation extraction are noted.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"266 ","pages":"Article 108773"},"PeriodicalIF":4.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838905","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":"Assessing the impact of magnetic nanoparticle assemblies on magnetic hyperthermia performance: A predictive study","authors":"Max Schoenen,&nbsp;Thomas Schmitz-Rode,&nbsp;Ioana Slabu","doi":"10.1016/j.cmpb.2025.108775","DOIUrl":"10.1016/j.cmpb.2025.108775","url":null,"abstract":"<div><h3>Background and objective</h3><div>Magnetic hyperthermia-based therapies depend on heating performances of magnetic nanoparticles (MNP). Beyond specific MNP properties, dipole-dipole interactions resulting from the formation of MNP assemblies have a pivotal influence on heating performance. There is, however, limited understanding of the range of attributable negative and positive effects.</div></div><div><h3>Methods</h3><div>Numerical simulations were used to unravel the effect of various spherical, elongated assemblies as well as MNP chains on heating performance. An advancing front assembly generating method was combined with a stochastic Langevin simulation. Experimental values of a hyperthermia application to destroy hollow organ tumours with heatable stent fibres were used to validate simulation results.</div></div><div><h3>Results</h3><div>Limited impact of assembly size on the heating performance was observed, whereas assembly geometry was crucial. Spherical assemblies lead to a decrease in specific loss power while elongated assemblies and chains yielded up to eightfold increase compared to randomly dispersed MNP. The heating performance of elongated assemblies and chains was dependent on their major-minor axes ratios, excitation field amplitude and assembly orientation relative to the field direction. The simulations unravelled that chains dominated the heating of stent fibres.</div></div><div><h3>Conclusions</h3><div>The simulation is a valuable and versatile tool for the optimization of heating output of all sorts of MNP, which undergo structural changes in interaction with artificial and biological surroundings. This capability is demonstrated for fibre-based implants with incorporated MNP. Comparison between simulation and experiments demonstrates the susceptibility to the design of MNP assemblies. Precise information about assembly geometry is crucial to improve the prediction accuracy.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"267 ","pages":"Article 108775"},"PeriodicalIF":4.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864466","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":"Puncture path planning algorithm of flexible needle in percutaneous nephrolithotomy with a hybrid NSGA optimizer","authors":"Tianmu Wang ,&nbsp;Zhenguo Nie ,&nbsp;Yanjie Xu ,&nbsp;Boxing Su ,&nbsp;Fugui Xie ,&nbsp;Jinsong Wang ,&nbsp;Jianxing Li ,&nbsp;Xin-Jun Liu","doi":"10.1016/j.cmpb.2025.108763","DOIUrl":"10.1016/j.cmpb.2025.108763","url":null,"abstract":"<div><h3>Background:</h3><div>Percutaneous nephrolithotomy is the standard treatment for large or irregularly shaped kidney stones, especially staghorn calculus. However, establishing a precise and safe puncture is challenging and requires extensive training for the surgeon. Navigation surgery is a commonly employed technique that facilitates the puncture through generating a path before surgery. One critical challenge for navigation is skin-kidney path planning due to the complex anatomical deconstruction of the kidney as well as the irregular shape of kidney stones.</div></div><div><h3>Method:</h3><div>In this paper, we propose a hybrid strategy puncture path planning algorithm, where we follow a 2-step flow path that considers the selection of puncture renal calyces and planning of a B-spine curve path. We imitate the decision-making process of the clinician in selecting the puncture calyx based on the projective area of the calculi to be cleared. We summarize subjective judgment and clinical experience during puncture, where parametric optimization indicators are proposed to realize the optimization of puncture path.</div></div><div><h3>Results:</h3><div>An optimal frontier consisting of puncture pathways focused on different puncture factors can be generated from the proposed algorithm, where the physician can choose the path that works best under real circumstances. Results in 2D simulation show that the planned pathway is similar to that planned by a urologist.</div></div><div><h3>Conclusions:</h3><div>The proposed 2-Step hybrid strategy reaches a balance on both optimal effect and efficiency. This automatic planning method based on the long axis section of the kidney can quickly and autonomously provide physicians with a series of optimized puncture paths, and provide auxiliary guidance for clinicians, especially young physicians. Nevertheless, the proposed method shows considerable potential in percutaneous nephrolithotomy surgical demonstration and teaching, and can integrated into robotic surgical navigation system.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"266 ","pages":"Article 108763"},"PeriodicalIF":4.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870001","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":"Global-Local Transformer Network for Automatic Retinal Pathological Fluid Segmentation in Optical Coherence Tomography Images","authors":"Feng Li ,&nbsp;Hao Wei ,&nbsp;Xinyu Sheng ,&nbsp;Yuyang Chen ,&nbsp;Haidong Zou ,&nbsp;Song Huang","doi":"10.1016/j.cmpb.2025.108772","DOIUrl":"10.1016/j.cmpb.2025.108772","url":null,"abstract":"<div><h3>Background and Objective</h3><div>As a pivotal biomarker, the accurate segmentation of retinal pathological fluid such as intraretinal fluid (IRF), subretinal fluid (SRF), and pigment epithelial detachment (PED), was a critical task for diagnosis and treatment management in various retinopathy. However, segmenting pathological fluids from optical coherence tomography (OCT) images still faced several challenges, including large variations in location, size and shape, low intensity contrast between fluids and peripheral tissues, speckle noise interference, and high similarity between fluid and background. Further, owing to the intrinsic local nature of convolution operations, most automatic retinal fluid segmentation approaches built upon deep convolutional neural network had limited capacity in capturing pathological features with global dependencies, prone to deviations. Accordingly, it was of great significance to develop automatic methods for accurate segmentation and quantitative analysis on multi-type retinal fluids in OCT images.</div></div><div><h3>Methods</h3><div>In this paper, we developed a novelty global-local Transformer network (GLTNet) based on U-shape architecture for simultaneously segmenting multiple types of pathological fluids from retinal OCT images. In our GLTNet, we designed a global-local attention module (GLAM) and aggregated it into the VGG-19 backbone to learn more pathological fluid related discriminative feature representations and suppress irrelevant noise information in OCT images. At the same time, we constructed multi-scale Transformer module (MSTM) on top of the encoder pathway to explore various scales of non-local characteristics with long-term dependency information from multiple layers of encoder part. By integrating both blocks for serving as a strong encoder of U-Net, our network improved the model's ability to capture finer details, thereby enabling precise segmentation of multi-type retinal fluids within OCT images.</div></div><div><h3>Results</h3><div>We evaluated the segmentation performance of the presented GLTNet on Kermany, DUKE and UMN datasets. Comprehensive experimental results on Kermany dataset showed that our model achieved overall 0.8395, 0.7657, 0.8631, and 0.8202, on the Dice coefficient, IoU, Sensitivity and precision, respectively, which remarkably outperformed other state-of-the-art retinal fluid segmentation approaches. The experimental results on DUKE and UMN datasets suggested our model had satisfactory generalizability.</div></div><div><h3>Conclusions</h3><div>By comparison with current cutting-edge methods, the developed GLTNet gained a significantly boost in retinal fluid segmentation performance, manifested good generalization and robustness, which had a great potential of assisting ophthalmologists in diagnosing diversity of eye disorders and developing as-needed therapy regiments.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"266 ","pages":"Article 108772"},"PeriodicalIF":4.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143825383","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":"Combining radiomics and connectomics in MRI studies of the human brain: A systematic literature review","authors":"Maria Agnese Pirozzi,&nbsp;Federica Franza,&nbsp;Marianna Chianese,&nbsp;Simone Papallo,&nbsp;Alessandro Pasquale De Rosa,&nbsp;Federica Di Nardo,&nbsp;Giuseppina Caiazzo,&nbsp;Fabrizio Esposito,&nbsp;Leandro Donisi","doi":"10.1016/j.cmpb.2025.108771","DOIUrl":"10.1016/j.cmpb.2025.108771","url":null,"abstract":"<div><div>Advances in MRI techniques continue to open new avenues to investigate the structure and function of the human brain. Radiomics, involving the extraction of quantitative image features, and connectomics, involving the estimation of structural and functional neural connections, from large amounts and different types of MRI data sets, represent two key research areas for advancing neuroimaging while exploiting progress in computational and theoretical modelling applied to MRI.</div><div>This systematic literature review aimed at exploring the combination of radiomics and connectomics in human brain MRI studies, highlighting how the combination of these approaches can provide novel or additional insights into the human brain under normal and pathological conditions.</div><div>The review was conducted according to the Preferred Reported Item for Systematic Reviews and Meta-Analyses (PRISMA) statement, seeking documents from Scopus and PubMed archives. Eleven studies (out of the initial 675 records) have met the established criteria and reported combined approaches from radiomics and connectomics. Three subgroups of approaches were identified, based on the MRI modalities used to obtain radiomic and connectomic features. The first group of 3 studies combined radiomics and connectomics applied to structural MRI (sMRI) data sets; the second group of 5 studies combined radiomics applied to sMRI data and connectomics applied to diffusion (dMRI) and/or functional MRI (fMRI) data sets; the third group of 3 studies combined radiomics and connectomics applied to fMRI.</div><div>This review highlighted the recent growing interest in combining MRI-based radiomics and connectomics to explore the human brain for neurological, psychiatric, and oncological conditions. Current methodologies and challenges were discussed, pointing out future research directions to improve or standardize these approaches and the gaps to be filled to advance the field.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"266 ","pages":"Article 108771"},"PeriodicalIF":4.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828503","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":"Factors influencing the estimation of phacoemulsification procedure time in cataract surgery: Analysis using neural networks","authors":"Magdalena Jędzierowska ,&nbsp;Robert Koprowski ,&nbsp;Michele Lanza ,&nbsp;Michał Walczak ,&nbsp;Anna Deda","doi":"10.1016/j.cmpb.2025.108770","DOIUrl":"10.1016/j.cmpb.2025.108770","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Realistic and accurate estimation of the surgery duration is one of the key factors influencing the optimization of hospital work and, consequently, the planning and management of the budget. In the present study, the authors proposed a method for predicting the phacoemulsification cataract surgery based on ophthalmic and systemic factors.</div></div><div><h3>Methods</h3><div>The study group included 1192 patients aged 70.4 ± 10 years who underwent phacoemulsification cataract surgery. The surgical procedures were performed by both experienced surgeons and trainees (15 % of procedures). 25 parameters were extracted, on the basis of which, using neural networks with backpropagation, an algorithm was proposed that predicted the surgery duration based on a set of input features.</div></div><div><h3>Results</h3><div>For the proposed method, the mean absolute error between the actual and predicted operation time was 5.09 min, whereas the accuracy of the obtained results was 69.74 % (for the best set of 7 input features).</div></div><div><h3>Conclusions</h3><div>The obtained results indicate that machine learning algorithms can be successfully used to predict the time of cataract surgery, and factors such as: surgeon's experience, patient's visual acuity (UCVA), intraocular pressure (IOP), corneal curvature and sphere value (SF) significantly influence the phacoemulsification cataract surgery duration.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"266 ","pages":"Article 108770"},"PeriodicalIF":4.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143844342","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}