Computers in biology and medicine最新文献

{"title":"Machine learning techniques to classify emotions from electroencephalogram topographic maps: A systematic review","authors":"Marla P. Melo ,&nbsp;Diana F. Adamatti ,&nbsp;Marilton S. Aguiar","doi":"10.1016/j.compbiomed.2025.111022","DOIUrl":"10.1016/j.compbiomed.2025.111022","url":null,"abstract":"<div><div>In the task of image classification for emotion recognition, facial expression data is commonly used. However, electrical brain signals generated by neural activity provide data with greater integrity. We can capture these signals non-invasively using electroencephalogram (EEG) recording devices. Conversion techniques can graphically represent the signal information as EEG topographic maps (ETMs). This review aims to identify machine learning techniques for recognizing emotional states from EEG topographic data maps. This review follows the PRISMA guidelines, and we conducted the literature search up to July 2025. Fourteen publications met the inclusion criteria. The identified machine learning techniques encompass a range of models, from Support Vector Machines (SVM) to deep neural models, which include seven Convolutional Neural Networks (CNNs), a lightweight convolutional neural network (LCNN), a Visual Geometry Group network (VGG-16), two Bidirectional Long Short-Term Memory networks (Bi-LSTM), two Residual Networks (ResNet), and a Multilayer Perceptron (MLP). This review presents the state of the art by providing a comprehensive mapping of machine learning techniques used for emotion recognition based on EEG topographic maps. It also summarizes the correlations evaluated in the fourteen studies, including emotional datasets, feature extraction techniques, and approaches for converting EEG signals into EEG topographic maps. Furthermore, it discusses classification accuracy based on subject-dependent, subject-independent, transfer learning, and cross-subject approaches, offering insights into potential directions for future research.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111022"},"PeriodicalIF":6.3,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019376","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":"Automated detection of lameness in dairy cattle through computer vision analysis of back shape characteristics","authors":"S. Serhan Narli,&nbsp;Hendrik Schmidt,&nbsp;Ali Firouzabadi,&nbsp;Lukas Schönnagel,&nbsp;Marcel Simon Reich,&nbsp;Sandra Reitmaier","doi":"10.1016/j.compbiomed.2025.111038","DOIUrl":"10.1016/j.compbiomed.2025.111038","url":null,"abstract":"<div><div>Lameness in dairy cattle is a prevalent issue that significantly impacts both animal welfare and farm productivity. Traditional lameness detection methods often rely on subjective visual assessment, focusing on changes in locomotion and back curvature. However, these methods can lack consistency and accuracy, particularly for early-stage detection. Typically, lameness is classified using the Locomotion Scoring System (LCS), which grades severity based on observable changes in movement and posture. This study presents an objective analysis of cow back shape in a sample of 260 Holstein-Friesian cows to identify specific regions associated with varying levels of lameness.</div><div>A keypoint detection algorithm was employed to map 12 keypoints along the cow's back, which was divided into three regions: cranial, middle, and caudal. Curvature analysis was performed by angles at each keypoint, enabling the extraction of relevant kinematic features, as back posture can be reliably captured with a single side-view camera and may reflect early signs of lameness. These features were subsequently input into a deep learning model to classify cows based on their locomotion scores.</div><div>The model achieved a high classification accuracy of 97 % in distinguishing lame from non-lame cows. While the cranial region contributed minimally to lameness detection (η² = 0.02), the middle (η² = 0.14) and caudal (η² = 0.068) regions were critical, especially for identifying more severe cases.</div><div>These findings suggest that analyzing back shape characteristics, particularly in the middle and caudal regions, provides valuable indicators for detecting lameness severity and may enhance the accuracy of automated lameness assessment in dairy cattle.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111038"},"PeriodicalIF":6.3,"publicationDate":"2025-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010255","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":"In-silico modeling of SHLP6: A novel mitochondrial peptide controlling neurodegeneration and cellular aging","authors":"H Thamarai Kannan,&nbsp;Suganiya Umapathy,&nbsp;Ieshita Pan","doi":"10.1016/j.compbiomed.2025.111054","DOIUrl":"10.1016/j.compbiomed.2025.111054","url":null,"abstract":"<div><div>Small humanin-like peptide-6 (SHLP6), is derived from the mitochondrial genome. The 3D structure of SHLP6 was evaluated using PEPstr, with homology modeling predicting a Cyt-C structure with a DOPE score of −645.717 and a GA341 score of 0.2832. The analysis showed that 96.5 % of residues were in favored regions in the Ramachandran plot, indicating a stable protein conformation. Molecular docking studies revealed that SHLP6 has binding affinities with apoptotic proteins such as Caspase 8 (−77.6 ± 2.9 kcal/mol), Bcl-2 (39.2 ± 15.3 kcal/mol), Bax (43.6 ± 7.7 kcal/mol), Cyt-C (−53.2 ± 8.7 kcal/mol), and CAT (−62.5 ± 1.3 kcal/mol). The interaction of SHLP6 with DRP1 (−47.7 ± 1.9 kcal/mol) was found to promote apoptosis, while interactions with SIRT1 (−49.1 ± 4.7 kcal/mol), IGF-1 (−58.7 ± 3.6 kcal/mol), and INSR (−66.4 ± 3.4 kcal/mol) suggest a potential role in controlling neurodegeneration. Molecular dynamics simulations confirmed the compact conformation of Caspase-8, high structural stability of SIRT1, and flexibility of DRP1. Treatment with SHLP6 (40 μg/ml) reduced developmental toxicity and improved antioxidant enzyme levels (SOD and CAT) in stress-induced zebrafish larvae. SHLP6 treatment also improved AChE levels in H₂O₂-exposed zebrafish larvae. SHLP6 treatment upregulated SOD, CAT, PRKN, p62, LCIII, SIRT1 and NDUFS4 genes, while modulating inflammation by downregulating TNF-α through IL-10 upregulation. SHLP6 efficiently restored locomotory activity in stress-induced zebrafish larvae. FTIR analysis indicated alterations in the secondary structure of proteins, and Congo red staining showed a 10 % decrease in BSA aggregation with SHLP6 treatment. These findings suggest that SHLP6 can be a promising therapeutic agent in enhancing antioxidant defenses, restoring mitochondrial health, and modulating inflammatory responses to mitigate oxidative stress-induced cellular dysfunction.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111054"},"PeriodicalIF":6.3,"publicationDate":"2025-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010256","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":"Self-supervised representation learning with continuous training data improves the feel and performance of myoelectric control","authors":"Shriram Tallam Puranam Raghu,&nbsp;Dawn T. MacIsaac,&nbsp;Erik J. Scheme","doi":"10.1016/j.compbiomed.2025.111029","DOIUrl":"10.1016/j.compbiomed.2025.111029","url":null,"abstract":"<div><div>Pattern recognition-based myoelectric control is traditionally trained with static or ramp contractions, but this fails to capture the dynamic nature of real-world movements. This study investigated the benefits of training classifiers with continuous dynamic data, encompassing transitions between various movement classes. We employed both conventional (LDA) and deep learning (LSTM) classifiers, comparing their performance when trained with ramp data, continuous dynamic data, and an LSTM pre-trained with a self-supervised learning technique (VICReg). Twenty participants completed a Fitts’ Law-inspired target acquisition test to evaluate the usability and effectiveness of each classifier. Results demonstrate that temporal models, particularly LSTMs trained with continuous dynamic data, significantly outperformed traditional approaches. Furthermore, VICReg pre-training led to additional improvements in online performance and user experience. Qualitative feedback highlighted the importance of smooth, jitter-free control and consistent performance across movement classes. These findings underscore the potential of continuous dynamic data and self-supervised learning for advancing sEMG-PR-based myoelectric control, paving the way for more intuitive and user-friendly prosthetic devices.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111029"},"PeriodicalIF":6.3,"publicationDate":"2025-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010257","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":"How does it affect the willingness to continue rehabilitation training? A usability evaluation of a multi-sensory rehabilitation interactive game system (MRIGS) for older adults with mild dementia","authors":"Chien-Hsiang Chang ,&nbsp;Chun-Chun Wei ,&nbsp;Wei-Chih Lien ,&nbsp;Lenka Lhotská ,&nbsp;Josef Cernohorsky ,&nbsp;Yang-Cheng Lin","doi":"10.1016/j.compbiomed.2025.111020","DOIUrl":"10.1016/j.compbiomed.2025.111020","url":null,"abstract":"<div><div>The prevalence of dementia is increasing every year, with one person developing dementia every 3 s. Therefore, this study proposes a novel multi-sensory rehabilitation interactive game system (MRIGS), which uses grip assistive devices combined with different colors and tactile stimulation to achieve multi-sensory training effects of vision, hearing, and touch. This study involved 17 older adults (72.2 years) with mild dementia (the MMSE between 17 and 23 points). To explore how the MRIGS affects their willingness to continue rehabilitation training, the system usability scale (SUS) with ten items was adopted to compare the differences between traditional multi-sensory rehabilitation (TMR) and MRIGS regarding gender, rehabilitation experience, and age.</div><div>The novel MRIGS interested older adults and improved their willingness for continuous rehabilitation. According to the overall SUS score, the MRIGS had better overall usability performance (86.18, being “<em>Good+</em>”) than the TMR (66.62, only being “<em>Average-</em>”) (t = −4.44, p = 0.00 &lt; 0.05). In addition, the result shows that the MRIGS was a promising way to improve seven (out of 10) usability items (<em>Willingness</em>, <em>Convenience</em>, <em>Stress</em>, <em>etc.</em>) compared to TMR. For males, the MRIGS had better usability in “<em>Willingness,” “Convenience,” and “Difficulty,”</em> while “<em>Consistency</em>” was better for females. We also found a significant difference in “<em>Willingness</em>” for those with previous rehabilitation experience because they had experienced the difficulties and boring feelings encountered in TMR in medical institutions. On the contrary, the MRIGS could make rehabilitation more exciting and motivating. For those over 70, the MRIGS performed better in “<em>Convenience</em>” and “<em>Consistency,”</em> indicating that improving the overall convenience of training operations had become more important along with their natural decline of physical functions by aging. In addition, among older adults with weak grip strength in their dominant hand, the hand grip strength significantly influences their willingness to use the novel MRIGS.</div><div>The MRIGS developed in this study could integrate multi-sensory training to help older adults with mild dementia improve their motivation and willingness to continue rehabilitation training.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111020"},"PeriodicalIF":6.3,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145004743","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":"Highly reliable personalized noninvasive hemoglobin estimation by using Vision Transformers and dual fine-tuning","authors":"Mauro Camporeale ,&nbsp;Felice Clemente ,&nbsp;Giovanni Dimauro ,&nbsp;Nunzia Lomonte ,&nbsp;Rosalia Maglietta ,&nbsp;Crescenza Pasciolla ,&nbsp;Davide Sacco ,&nbsp;Gian Maria Zaccaria","doi":"10.1016/j.compbiomed.2025.111026","DOIUrl":"10.1016/j.compbiomed.2025.111026","url":null,"abstract":"<div><div>Artificial intelligence is revolutionizing health care, particularly in precision medicine and noninvasive diagnostics. Anemia, which is a widespread condition that affects billions of people worldwide, compromises oxygen transport due to low hemoglobin levels, which leads to severe complications if left undetected. Early and frequent monitoring is essential, yet traditional blood tests can be invasive, costly, and impractical for continuous assessment. This study presents the first patient-specific system for noninvasive hemoglobin estimation from palpebral conjunctiva images. Unlike previous approaches, our model integrates the vision transformer (ViT) architecture with dual fine-tuning, which enables personalized adaptation to each patient’s unique physiological characteristics. The dataset consists of conjunctival images captured over multiple days from the same patients, which allows for an individualized calibration process that enhances predictive accuracy. Our model achieved an R2 of 0.94, an accuracy of 98%, and a mean absolute error (MAE) of 0.25 g/dL, thus demonstrating a performance comparable to that of laboratory tests. Additionally, the model’s 100% sensitivity ensured that all anemic cases were detected, thereby minimizing the risk of false-negatives. By providing highly precise, rapid, and accessible anemia screening, this approach has the potential to redefine long-term hematological monitoring, thereby reducing reliance on frequent blood tests and improving clinical decision-making in resource-limited settings.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111026"},"PeriodicalIF":6.3,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145004744","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":"CISCA and CytoDArk0: A cell instance segmentation and classification method for histo(patho)logical image Analyses and a new, open, Nissl-stained dataset for brain cytoarchitecture studies","authors":"Valentina Vadori ,&nbsp;Jean-Marie Graïc ,&nbsp;Antonella Peruffo ,&nbsp;Giulia Vadori ,&nbsp;Livio Finos ,&nbsp;Enrico Grisan","doi":"10.1016/j.compbiomed.2025.111018","DOIUrl":"10.1016/j.compbiomed.2025.111018","url":null,"abstract":"<div><div>Delineating and classifying individual cells in microscopy tissue images is inherently challenging yet remains essential for advances in medical and neuroscientific research. In this work, we propose a new deep learning framework, CISCA, for automatic cell instance segmentation and classification in histological slices. At the core of CISCA is a network architecture featuring a lightweight U-Net with three heads in the decoder. The first head classifies pixels into boundaries between neighboring cells, cell bodies, and background, while the second head regresses four distance maps along four directions. The outputs from the first and second heads are integrated through a tailored post-processing step, which ultimately produces the segmentation of individual cells. The third head enables the simultaneous classification of cells into relevant classes, if required. We demonstrate the effectiveness of our method using four datasets, including CoNIC, PanNuke, and MoNuSeg, which are publicly available H&amp;E-stained datasets that cover diverse tissue types and magnifications. In addition, we introduce CytoDArk0, the first annotated dataset of Nissl-stained histological images of the mammalian brain, containing nearly 40,000 annotated neurons and glial cells, aimed at facilitating advancements in digital neuropathology and brain cytoarchitecture studies. We evaluate CISCA against other state-of-the-art methods, demonstrating its versatility, robustness, and accuracy in segmenting and classifying cells across diverse tissue types, magnifications, and staining techniques. This makes CISCA well suited for detailed analyses of cell morphology and efficient cell counting in both digital pathology workflows and brain cytoarchitecture research.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111018"},"PeriodicalIF":6.3,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144991642","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":"From histology to diagnosis: Leveraging pathology foundation models for glioma classification","authors":"Camillo Saueressig ,&nbsp;Claire Delbridge ,&nbsp;Daniel Scholz ,&nbsp;Azar Kazemi ,&nbsp;Mohammad Zaid Khan ,&nbsp;Marie Metz ,&nbsp;Bernhard Meyer ,&nbsp;Meike Mitsdoerffer ,&nbsp;Peter J. Schüffler ,&nbsp;Benedikt Wiestler","doi":"10.1016/j.compbiomed.2025.110988","DOIUrl":"10.1016/j.compbiomed.2025.110988","url":null,"abstract":"<div><div>The fifth edition of the WHO classification of brain tumors increasingly emphasizes the role of extensive genetic testing in the diagnosis of gliomas. In this context, computational pathology foundation models (FMs) present a promising approach for inferring molecular entities directly from conventional, H&amp;E-stained histological images, potentially reducing the need for genetic analysis. We conducted a robust investigation into the ability of five established FMs to generate effective embeddings for downstream glioma classification using three datasets (TCGA, n=839 samples; EBRAINS, n=786 samples; TUM, n=250 samples) and state-of-the-art augmentation techniques. Our results demonstrate that FM embeddings enable competitive glioma classification performance, even with limited training data, achieving one-vs-rest AUC<span><math><mo>&gt;</mo></math></span>0.93 on all three datasets. However, we observed substantial differences between FMs in their downstream performance, susceptibility to perturbations, and consistency across multiple datasets. Dataset diversity and content of central nervous tissue were associated with improved generalization, while model and dataset size were not. Common to all FMs was a propensity to capture dataset-specific features in their embeddings. We examined Macenko normalization and random convolutions as potential solutions to combat dataset-dominated embeddings and show that ensembling FM embeddings over multiple augmented views improves downstream classifier performance. In summary, our findings highlight both the promise and current limitations of computational pathology foundation models for glioma classification, emphasizing the critical roles of training data composition and downstream augmentation to achieve strong task performance.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 110988"},"PeriodicalIF":6.3,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144996946","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":"Studying therapy effects and disease outcomes in silico using artificial counterfactual tissue samples","authors":"Martin Paulikat ,&nbsp;Christian M. Schürch ,&nbsp;Christian F. Baumgartner","doi":"10.1016/j.compbiomed.2025.110997","DOIUrl":"10.1016/j.compbiomed.2025.110997","url":null,"abstract":"<div><div>Understanding the interactions of different cell types inside the immune tumor microenvironment (iTME) is crucial for the development of immunotherapy treatments as well as for predicting their outcomes. Highly multiplexed tissue imaging (HMTI) technologies offer a tool which can capture cell properties of tissue samples by measuring expression of various proteins and storing them in separate image channels. HMTI technologies can be used to gain insights into the iTME and in particular how the iTME differs for different patient outcome groups of interest (e.g., treatment responders vs. non-responders). Understanding the systematic differences in the iTME of different patient outcome groups is crucial for developing better treatments and personalising existing treatments. However, such analyses are inherently limited by the fact that any two tissue samples vary due to a large number of factors unrelated to the outcome. Here, we present CF-HistoGAN, a machine learning framework that employs generative adversarial networks (GANs) to create artificial counterfactual tissue samples that resemble the original tissue samples as closely as possible but capture the characteristics of a different patient outcome group. Specifically, we learn to “translate” HMTI samples from one patient group to create artificial paired samples. We show that this approach allows to directly study the effects of different patient outcomes on the iTMEs of individual tissue samples. We demonstrate that CF-HistoGAN can be employed as an explorative tool for understanding iTME effects on the pixel level. Moreover, we show that our method can be used to identify statistically significant differences in the expression of different proteins between patient groups with greater sensitivity compared to conventional approaches.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 110997"},"PeriodicalIF":6.3,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144991597","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 new theoretical model of apparent blood viscosity with the Fåhræus-Lindqvist effect using informational entropy-based approach","authors":"Saloni Gupta,&nbsp;Snehasis Kundu","doi":"10.1016/j.compbiomed.2025.111003","DOIUrl":"10.1016/j.compbiomed.2025.111003","url":null,"abstract":"<div><div>The behavior of blood viscosity is influenced by several physical factors, particularly hematocrit levels and vessel diameter. For a fixed hematocrit, apparent blood viscosity decreases with tube diameters in the range of <span><math><mrow><mn>9</mn><mspace></mspace><mi>μ</mi><mi>m</mi></mrow></math></span> to <span><math><mrow><mn>1000</mn><mspace></mspace><mi>μ</mi><mi>m</mi></mrow></math></span>, a phenomenon known as the Fåhræus-Lindqvist (FL) effect. Almost all existing models of the apparent blood viscosity are empirically proposed describing that viscosity exponentially increases with hematocrit. To predict apparent blood viscosity, this study proposes a new model derived from an iterative approach based on Einstein’s complete formula by considering different blood samples with varying RBC levels. To predict model parameters, this work proposes the informational entropy approach based on a probabilistic concept, which is new in this field. The model generalizes several existing models and successfully predicts the FL effects. We validate its accuracy against a wide range of experimental data sets (from infants to adults, along with the original data set of Fåhræus-Lindqvist) and perform a comparative analysis with existing models. To illustrate the model performance the error analysis has been carried out. The results show that our model offers a better prediction across a wide range of considered data sets and existing models. The model is tested for predicting RBC transport efficiency and analyzing vessel oxygen transport rates and the results are found satisfactory. Apart from these, a new entropy theory based computational methodology is proposed allowing flexibility in adapting the model to different data sets. The suggested hybrid methodology can be used for future similar research.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111003"},"PeriodicalIF":6.3,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144996326","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}