Computers in biology and medicine最新文献

{"title":"Enhancing search strategies for systematic reviews on drug Harms: An evaluation of the utility of ChatGPT in error detection and keyword generation","authors":"Victor Gitman,&nbsp;Colleen Maxwell,&nbsp;John-Michael Gamble","doi":"10.1016/j.compbiomed.2025.110464","DOIUrl":"10.1016/j.compbiomed.2025.110464","url":null,"abstract":"<div><h3>Objective</h3><div>Developing search strategies for synthesizing evidence on drug harms requires specialized expertise and knowledge. The aim of this study was to evaluate ChatGPT's ability to enhance search strategies for systematic reviews of drug harms by identifying missing and generating omitted keywords.</div></div><div><h3>Materials and methods</h3><div>A literature search in PubMed identified systematic reviews of drug harms from 10 high-impact journals between 1-Nov-2013 to 27-Nov-2023. Sixteen search strategies used in these reviews were selected each with a single error of omission introduced. ChatGPT's (GPT-4) performance was evaluated based on error detection, similarity between the extracted and generated search strategies via strict and semantic keyword matching, and proportion of omitted keywords generated.</div></div><div><h3>Results</h3><div>ChatGPT identified the introduced errors in all search strategies. Under strict matching, the mean Jaccard's similarity measure was 0.17 (range: 0.00–0.52) and with semantic matching this increased to 0.23 (range: 0.00–0.53). Similarly, the mean proportion of keywords recreated by ChatGPT was 49 % using strict matching increasing to 71 % with semantic matching.</div></div><div><h3>Discussion and conclusion</h3><div>ChatGPT effectively detected errors and generated relevant keywords, showing potential as a tool for evidence retrieval on drug harms.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110464"},"PeriodicalIF":7.0,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147289","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":"Ultra-low-power System-on-Chip for automated screening of central apnea and hypopnea via chin electromyography","authors":"Adil Rehman,&nbsp;Hani Saleh","doi":"10.1016/j.compbiomed.2025.110349","DOIUrl":"10.1016/j.compbiomed.2025.110349","url":null,"abstract":"<div><div>Central Apnea (CA) and Central Hypopnea (CH) are sleep disorders arising from the brain’s inability to signal respiratory muscles, potentially leading to severe complications such as heart failure. This study presents a novel system for automating CA and CH event detection in sleep apnea patients using a feedforward neural network (FdNN) architecture integrated into an ultra-low-power System-on-Chip (SoC) with chin electromyography (EMG) signals. The SoC achieves sub-1-mW power consumption through careful co-optimization of the FdNN architecture, hardware design, and circuit-level considerations, ensuring efficient operation with high-accuracy event detection. Using the ISRUC database for training and testing, the optimized FdNN model demonstrates the effectiveness of surface EMG (sEMG) features in identifying CA and CH events, achieving a notable testing accuracy of 85.7%. While the proposed support vector machine (SVM) kernel approximation model shows superior performance, optimizations to the FdNN architecture enhance its hardware compatibility. Implemented on GlobalFoundries 22 nm Fully Depleted Silicon-On-Insulator (GF 22 nm FDSOI) technology, the SoC achieves a core area of 0.0170 mm<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>, running at 100 MHz, and consumes 602 <span><math><mi>μ</mi></math></span>W at 0.72 V with a leakage power of 0.263 <span><math><mi>μ</mi></math></span>W. Additionally, slope sign change (SSC) is proposed as a digital biomarker, emphasizing the need to distinguish between CA and obstructive apnea, as well as CH and obstructive hypopnea, through statistical analysis. In conclusion, the proposed SoC provides power-efficient and sophisticated automated CA and CH event screening to help clinicians diagnose and treat sleep disorders, offering an alternative to traditional polysomnography (PSG) methods.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110349"},"PeriodicalIF":7.0,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138781","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":"Illicit uptake of peptide-based antibiotics through bacterial peptide transporters: an approach towards overcoming drug resistance","authors":"Kalyan Ghosh,&nbsp;Shankar Prasad Kanaujia","doi":"10.1016/j.compbiomed.2025.110444","DOIUrl":"10.1016/j.compbiomed.2025.110444","url":null,"abstract":"<div><div>Illicit transport pertains to the unauthorized entry of molecules into cells through transporters that are initially intended for other physiological substances. Recently, it has been demonstrated that the peptide-based antibiotic negamycin can permeate the cytosolic membrane of <em>Escherichia coli</em> via dipeptide (<em>Ec</em>Dpp), <u>s</u>ensitivity to <u>a</u>ntimicrobial <u>p</u>eptide (<em>Ec</em>Sap), and oligopeptide (<em>Ec</em>Opp) transporters. However, no example of such an illicit transport mechanism for the <em>Haemophilus influenzae</em> Sap (<em>Hi</em>Sap) transporter has been reported. So, an in-depth <em>in silico</em> study was performed to identify new peptide-based antibiotics showing binding affinities for the substrate-binding proteins <em>Ec</em>DppA, <em>Ec</em>SapA, and <em>Hi</em>SapA. The results indicated that the three target proteins share sequence and structural similarities among them. Moreover, a virtual screening of 230 peptide-based antibiotics against these proteins identified eight compounds with higher binding affinities. Among these, three compounds (1, 6, and 129) demonstrate superior absorption, distribution, metabolism, excretion, and toxicity (ADMET) profiles as well as drug-like characteristics. Comprehensive molecular dynamics (MD) simulation hints towards the conformational stability and favourable binding energy of these compounds with <em>Ec</em>DppA, <em>Ec</em>SapA, and <em>Hi</em>SapA. The probability density function (PDF) and dynamic cross-correlation map (DCCM) underscored the significance of the binding-site loop in ligand dynamics and major domain movements, respectively. In conclusion, the results from this study propose that Compounds 1, 6, and 129 could function as effective broad-spectrum antibiotics against Gram-negative pathogens and can also act as a template for designing more such peptide-based antibiotics for illicit transport across various other pathogens.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110444"},"PeriodicalIF":7.0,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138780","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":"Estimation of time-to-total knee replacement surgery with multimodal modeling and artificial intelligence","authors":"Ozkan Cigdem ,&nbsp;Eisa Hedayati ,&nbsp;Haresh R. Rajamohan ,&nbsp;Kyunghyun Cho ,&nbsp;Gregory Chang ,&nbsp;Richard Kijowski ,&nbsp;Cem M. Deniz","doi":"10.1016/j.compbiomed.2025.110364","DOIUrl":"10.1016/j.compbiomed.2025.110364","url":null,"abstract":"<div><h3>Background:</h3><div>The methods for predicting time-to-total knee replacement (TKR) do not provide enough information to make robust and accurate predictions.</div></div><div><h3>Purpose:</h3><div>Develop and evaluate an artificial intelligence-based model for predicting time-to-TKR by analyzing longitudinal knee data and identifying key features associated with accelerated knee osteoarthritis progression.</div></div><div><h3>Methods:</h3><div>A total of 547 subjects underwent TKR in the Osteoarthritis Initiative over nine years, and their longitudinal data was used for model training and testing. 518 and 164 subjects from Multi-Center Osteoarthritis Study and internal hospital data were used for external testing, respectively. The clinical variables, magnetic resonance (MR) images, radiographs, and quantitative and semi-quantitative assessments from images were analyzed. Deep learning (DL) models were used to extract features from radiographs and MR images. DL features were combined with clinical and image assessment features for survival analysis. A Lasso Cox feature selection method combined with a random survival forest model was used to estimate time-to-TKR.</div></div><div><h3>Results:</h3><div>Utilizing only clinical variables for time-to-TKR predictions provided the estimation accuracy of 60.4% and C-index of 62.9%. Combining DL features extracted from radiographs, MR images with clinical, quantitative, and semi-quantitative image assessment features achieved the highest accuracy of 73.2%, (p=.001) and C-index of 77.3% for predicting time-to-TKR.</div></div><div><h3>Conclusions:</h3><div>The proposed predictive model demonstrated the potential of DL models and multimodal data fusion in accurately predicting time-to-TKR surgery that may help assist physicians to personalize treatment strategies and improve patient outcomes.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110364"},"PeriodicalIF":7.0,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138783","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":"Classification of COVID-19 via Homology of CT-SCAN","authors":"Sohail Iqbal ,&nbsp;Hafiz Fareed Ahmed ,&nbsp;Talha Qaiser ,&nbsp;Muhammad Imran Qureshi ,&nbsp;Nasir Rajpoot","doi":"10.1016/j.compbiomed.2025.110226","DOIUrl":"10.1016/j.compbiomed.2025.110226","url":null,"abstract":"<div><div>Automated analysis of biomedical images plays a crucial role in enabling early diagnosis. In this article, we propose a novel approach based on persistent homology, a central technique from topological data analysis, for detecting traces of COVID-19 infection in CT-scan images. Our method is based on an intuitive and natural idea of analyzing shapes and opacities. We quantify these topological features using persistent homology and transform them into vector representations suitable for classification. These features are then reduced in dimensionality and classified using a support vector machine (SVM), capturing the global structure of key radiological patterns such as ground-glass opacities and consolidations.</div><div>To ensure reproducibility and external validation, we conducted experiments on two distinct publicly available datasets: the SARS-CoV-2 CT-scan and the HRCT Chest COVID dataset. Our approach achieved F1 scores of 99.4% and 99.6%, respectively.</div><div>These results demonstrate that our method offers both high performance and clinical interpretability. By leveraging stable and descriptive topological features, our approach generalizes well across datasets without requiring data augmentation or pretraining, making it especially suitable for deployment in data-limited healthcare settings.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110226"},"PeriodicalIF":7.0,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147290","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":"Mobile applications for non-communicable disease Management: A systematic review of development methods and effectiveness","authors":"Emma Camino Ortega ,&nbsp;Ana Baroja Gil de Gómez ,&nbsp;Amelia González Gamarra ,&nbsp;Miguel Angel Cuevas-Budhart ,&nbsp;José Luis García Klepzig ,&nbsp;Mercedes Gómez del Pulgar García-Madrid","doi":"10.1016/j.compbiomed.2025.110411","DOIUrl":"10.1016/j.compbiomed.2025.110411","url":null,"abstract":"<div><h3>Aim</h3><div>T<strong>o</strong> evaluate the most effective development methods for mobile applications that support self-management of non-communicable diseases and to determine the features that enhance their effectiveness and user adoption.</div></div><div><h3>Methods</h3><div>The design was a systematic review of research papers published in the period 2019–2024. The review included randomized and quasi-experimental clinical trials. The search was performed in six databases (PubMed, Scopus, Scielo, CINAHL, Web of Science, and Clinical Trials). Bias and methodological quality were assessed using the RoB2 and MINORS tools.</div></div><div><h3>Results</h3><div>The review included six studies involving 2421 patients across four countries. The applications demonstrated improvements in treatment adherence, self-efficacy, and control of clinical variables such as glycemia and blood pressure. The most effective applications incorporated therapeutic education, monitoring, and reminders. However, limitations were noted, including insufficient user involvement in early development stages, which could affect relevance and usability. The heterogeneity of study designs and populations, coupled with the lack of large-scale clinical trials, limits the generalizability of the findings. Additionally, variability in technological platforms and the absence of standardized evaluation metrics complicate outcome comparisons.</div></div><div><h3>Conclusion</h3><div>Mobile applications for chronic disease self-management are most effective when developed with a user-centered approach and continuous validation. Despite these findings, further research is necessary to generalize the results and optimize the integration of these applications into healthcare systems.</div></div><div><h3>Prospero registration number</h3><div>CRD42024571644.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110411"},"PeriodicalIF":7.0,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138698","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":"MHS U-Net: Multi-scale hybrid subtraction network for medical image segmentation","authors":"Junran Qian ,&nbsp;Haiyan Li ,&nbsp;Shuran Liao ,&nbsp;Zhe Xiao ,&nbsp;Weihua Li ,&nbsp;Hongsong Li","doi":"10.1016/j.compbiomed.2025.110431","DOIUrl":"10.1016/j.compbiomed.2025.110431","url":null,"abstract":"<div><div>Medical image segmentation plays a critical role in modern clinical diagnosis. However, existing methods face challenges such as insufficient feature extraction, limited spatial modeling capabilities, and restricted generalization ability with low computational cost. To address these challenges, we propose a Multi-scale Hybrid Subtraction Network (MHS U-Net) for Medical Image Segmentation. First, a pretrained PVTv2-B2 is integrated as the encoder to enhance the model's adaptability and feature extraction capability for complex multi-modal medical images. Second, a Multi-Layer Shift Perception Attention (MSPA) mechanism is designed at the bottleneck to capture fine-grained high-level features by deepening the network structure, while effectively suppressing the surge in computational cost through shift operations. In the decoder, a Multi-Scale Hybrid Convolution Subtraction Decoder (MSHCSD) is developed, to improve the modeling of spatial relationships within and around lesions and significantly enhance the model's generalization ability through integrating group convolution, gating mechanisms, and deep convolutional blocks. Additionally, to address the insufficient utilization of multi-scale feature interactions, a Multi-Scale Subtraction Module (MSSM) is proposed to strengthen cross-scale feature fusion through differential information extraction and complementary feature enhancement, thereby achieving the precise localization and segmentation of lesion regions. Experimental results on 14 public datasets across five imaging modalities demonstrate that MHS U-Net consistently outperforms state-of-the-art methods in metrics and visual results. Moreover, MHS U-Net requires only 5.48G FLOPs and 11.59M parameters, significantly lower than most existing models. Overall, MHS U-Net offers an excellent balance between model performance and size in multi-modal medical image segmentation tasks.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110431"},"PeriodicalIF":7.0,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138782","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":"Advancing emotion recognition with Virtual Reality: A multimodal approach using physiological signals and machine learning","authors":"Edoardo Maria Polo ,&nbsp;Francesco Iacomi ,&nbsp;Alberto Valdes Rey ,&nbsp;Davide Ferraris ,&nbsp;Alessia Paglialonga ,&nbsp;Riccardo Barbieri","doi":"10.1016/j.compbiomed.2025.110310","DOIUrl":"10.1016/j.compbiomed.2025.110310","url":null,"abstract":"<div><h3>Introduction</h3><div>: Emotion recognition systems have traditionally relied on basic visual elicitation. Virtual reality (VR) offers an immersive alternative that better resembles real-world emotional experiences.</div></div><div><h3>Objective:</h3><div>To develop and evaluate custom-built VR scenarios designed to evoke sadness, relaxation, happiness, and fear, and to utilize physiological signals together with machine learning techniques for accurate prediction and classification of emotional states.</div></div><div><h3>Methods:</h3><div>Physiological signals (electrocardiogram, blood volume pulse, galvanic skin response, and respiration) were acquired from 36 participants during VR experiences. Machine learning models, including Logistic Regression with Square Method feature selection, were applied in a subject-independent approach in order to discern the four emotional states.</div></div><div><h3>Results:</h3><div>Features extracted by physiological signal analysis highlighted significant differences among emotional states. The machine learning models achieved high accuracies of 80%, 85%, and 70% for arousal, valence, and 4-class emotion classification, respectively. Explainable AI techniques further provided insights into the decision-making processes and the relevance of specific physiological features, with galvanic skin response peaks emerging as the most significant feature for both valence and arousal dimensions.</div></div><div><h3>Conclusion:</h3><div>The proposed study demonstrates efficacy of VR in eliciting genuine emotions and the potential of using physiological signals for emotion recognition, with important implications for affective computing and psychological research. The non-invasive approach, robust subject-independent generalizability, and compatibility with wearable technology position this methodology favorably for practical applications in mental health contexts and user experience evaluation.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110310"},"PeriodicalIF":7.0,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138776","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":"Brain Fractal Dimension and Machine Learning can predict first-episode psychosis and risk for transition to psychosis","authors":"Yaxin Hu ,&nbsp;Marina Frisman ,&nbsp;Christina Andreou ,&nbsp;Mihai Avram ,&nbsp;Anita Riecher-Rössler ,&nbsp;Stefan Borgwardt ,&nbsp;Erhardt Barth ,&nbsp;Alexandra Korda","doi":"10.1016/j.compbiomed.2025.110333","DOIUrl":"10.1016/j.compbiomed.2025.110333","url":null,"abstract":"<div><div>Although there are notable structural abnormalities in the brain associated with psychotic diseases, it is still unclear how these abnormalities relate to clinical presentation. However, the fractal dimension (FD), which offers details on the complexity and irregularity of brain microstructures, may be a promising feature, as demonstrated by neuropsychiatric disorders such as Parkinson’s and Alzheimer’s. It may offer a possible biomarker for the detection and prognosis of psychosis when paired with machine learning. The purpose of this study is to investigate FD as a structural magnetic resonance imaging (sMRI) feature from individuals with a high clinical risk of psychosis who did not transit to psychosis (CHR_NT), clinical high risk who transit to psychosis (CHR_T), patients with first-episode psychosis (FEP) and healthy controls (HC). Using a machine learning approach that ultimately classifies sMRI images, the goals are (a) to evaluate FD as a potential biomarker and (b) to investigate its ability to predict a subsequent transition to psychosis from the high-risk clinical condition. We obtained sMRI images from 194 subjects, including 44 HCs, 77 FEPs, 16 CHR_Ts, and 57 CHR_NTs. We extracted the FD features and analyzed them using machine learning methods under five classification schemas (a) FEP vs. HC, (b) FEP vs. CHR_NT, (c) FEP vs. CHR_T, (d) CHR_NT vs. CHR_T, (d) CHR_NT vs. HC and (e) CHR_T vs. HC. In addition, the CHR_T group was used as external validation in (a), (b) and (d) comparisons to examine whether the progression of the disorder followed the FEP or CHR_NT patterns. The proposed algorithm resulted in a balanced accuracy greater than 0.77. This study has shown that FD can function as a predictive neuroimaging marker, providing fresh information on the microstructural alterations triggered throughout the course of psychosis. The effectiveness of FD in the detection of psychosis and transition to psychosis should be established by further research using larger datasets.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110333"},"PeriodicalIF":7.0,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144134025","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":"Beyond Accuracy: Evaluating certainty of AI models for brain tumour detection","authors":"Zaib Un Nisa ,&nbsp;Sohail Masood Bhatti ,&nbsp;Arfan Jaffar ,&nbsp;Tehseen Mazhar ,&nbsp;Tariq Shahzad ,&nbsp;Yazeed Yasin Ghadi ,&nbsp;Ahmad Almogren ,&nbsp;Habib Hamam","doi":"10.1016/j.compbiomed.2025.110375","DOIUrl":"10.1016/j.compbiomed.2025.110375","url":null,"abstract":"<div><div>Brain tumors pose a severe health risk, often leading to fatal outcomes if not detected early. While most studies focus on improving classification accuracy, this research emphasizes prediction certainty, quantified through loss values. Traditional metrics like accuracy and precision do not capture confidence in predictions, which is critical for medical applications. This study establishes a correlation between lower loss values and higher prediction certainty, ensuring more reliable tumor classification.</div><div>We evaluate CNN, ResNet50, XceptionNet, and a Proposed Model (VGG19 with customized classification layers) using accuracy, precision, recall, and loss. Results show that while accuracy remains comparable across models, the Proposed Model achieves the best performance (96.95 % accuracy, 0.087 loss), outperforming others in both precision and recall. These findings demonstrate that certainty-aware AI models are essential for reliable clinical decision-making.</div><div>This study highlights the potential of AI to bridge the shortage of medical professionals by integrating reliable diagnostic tools in healthcare. AI-powered systems can enhance early detection and improve patient outcomes, reinforcing the need for certainty-driven AI adoption in medical imaging.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"193 ","pages":"Article 110375"},"PeriodicalIF":7.0,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138777","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}