Intelligence-based medicine最新文献

{"title":"Automatic glioma segmentation based on efficient U-net model using MRI images","authors":"Yessine Amri ,&nbsp;Amine Ben Slama ,&nbsp;Zouhair Mbarki ,&nbsp;Ridha Selmi ,&nbsp;Hedi Trabelsi","doi":"10.1016/j.ibmed.2025.100216","DOIUrl":"10.1016/j.ibmed.2025.100216","url":null,"abstract":"<div><div>Gliomas are among the most aggressive and challenging brain tumors to diagnose and treat. Accurate segmentation of glioma regions in Magnetic Resonance Imaging (MRI) is essential for early diagnosis and effective treatment planning. This study proposes an optimized U-Net model tailored for glioma segmentation, addressing key challenges such as boundary delineation, computational efficiency, and generalizability. The proposed model integrates streamlined encoder-decoder pathways and optimized skip connections, achieving precise segmentation while reducing computational complexity. The model was validated on two datasets: TCGA-TCIA, containing 110 patients, and the multi-modal BraTS 2021 dataset. Comparative evaluations were conducted against state-of-the-art methods, including Attention U-Net, Trans-U-Net, DeepLabV3+, and 3D U-Net, using metrics such as Dice Coefficient, Intersection over Union (IoU), Hausdorff Distance (HD), and Structural Similarity Index (SSIM). The proposed U-Net achieved the highest performance across all metrics, with a Dice score of 92.54 %, IoU of 90.42 %, HD of 4.12 mm, and SSIM of 0.962 on the TCGA-TCIA dataset. On the BraTS dataset, it achieved comparable results, with a Dice score of 91.32 % and an IoU of 89.56 %. In contrast, other methods, such as Attention U-Net and DeepLabV3+, showed lower Dice scores of 85.62 % and 84.10 %, respectively, and higher HD values, indicating inferior boundary delineation. Additionally, the proposed model demonstrated computational efficiency, processing images in 1.5 s on average, compared to 5.0 s for Attention U-Net and 9.0 s for Trans-U-Net. These results underscore the potential of the optimized U-Net as a robust, accurate, and efficient tool for glioma segmentation. Future work will focus on clinical validation and extending the model to include automated glioma grading, further enhancing its applicability in medical imaging workflows.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100216"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A robust deep learning algorithm for lung cancer detection from computed tomography images","authors":"A.A. Abe ,&nbsp;M. Nyathi ,&nbsp;A.A. Okunade ,&nbsp;W. Pilloy ,&nbsp;B. Kgole ,&nbsp;N. Nyakale","doi":"10.1016/j.ibmed.2025.100203","DOIUrl":"10.1016/j.ibmed.2025.100203","url":null,"abstract":"<div><div>Detecting lung cancer at its earliest stage offers the best possibility for a cure. Chest computed tomography (CT) scans are a valuable tool for early diagnosis. However, the initial stages of lung cancer may present patterns in the images that are not easily detectable by radiologist, potentially leading to misdiagnosis. Although automated approaches using deep learning (DL) algorithms have been proposed, it depends on a substantial amount of data to achieve diagnostic accuracy comparable to that of radiologists. To alleviate this challenge, this study proposes a DL algorithm that uses an ensemble of convolutional neural networks and trained on relatively small dataset (IQ_OTH/NCCD dataset) to automate lung cancer diagnosis from patient chest CT scans. The method achieved an accuracy of 98.17 %, a sensitivity of 98.21 %, and a specificity of 98.13 % when categorizing scans as either cancerous or non-cancerous. Similarly, it achieved an accuracy of 95.43 %, a sensitivity of 93.40 %, and a specificity of 97.09 % when classifying scans as normal or containing benign or malignant pulmonary nodules. These results demonstrate superior performance compared to previously proposed models, highlighting the effectiveness of DL algorithms for early lung cancer diagnosis and providing a valuable tool to assist radiologists in their assesments.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100203"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing tuberculosis screening: A tailored CNN approach for accurate chest X-ray analysis and practical clinical integration","authors":"K.K. Mujeeb Rahman,&nbsp;Sedra Zulaikha,&nbsp;Banan Dhafer,&nbsp;Rawan Ahmed","doi":"10.1016/j.ibmed.2024.100196","DOIUrl":"10.1016/j.ibmed.2024.100196","url":null,"abstract":"<div><div>Pulmonary tuberculosis (PTB) is a chronic infectious disease claiming approximately 1.5 million lives annually, emphasizing the need for timely diagnosis to improve survival and limit its spread. Chest X-rays are effective for identifying TB-related lung abnormalities, often before symptoms arise, making early detection crucial. Our project enhances PTB screening by leveraging a CNN model trained on 12,848 images from reliable open-access datasets. The system achieves 99.72 % accuracy in binary classification (normal vs. abnormal) and 99.61 % in distinguishing healthy, TB, and non-TB cases, outperforming existing solutions. This ML-driven tool enables swift, cost-effective, and precise PTB detection, ensuring targeted treatment and addressing medicolegal needs through reliable and accountable diagnostics.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100196"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CTCovid19: Automatic Covid-19 model for Computed Tomography Scans Using Deep Learning","authors":"Carlos Antunes ,&nbsp;João Rodrigues ,&nbsp;António Cunha","doi":"10.1016/j.ibmed.2024.100190","DOIUrl":"10.1016/j.ibmed.2024.100190","url":null,"abstract":"<div><div>COVID-19 is an extremely contagious respiratory sickness instigated by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Common symptoms encompass fever, cough, fatigue, and breathing difficulties, often leading to hospitalization and fatalities in severe cases. CTCovid19 is a novel model tailored for COVID-19 detection, specifically honing in on a distinct deep learning structure, ResNet-50 trained with ImageNet serves as the foundational framework for our model. To enhance its capability to capture pertinent features related to COVID-19 patterns in Computed Tomography scans, the network underwent fine-tuning through layer adjustments and the addition of new ones. The model achieved accuracy rates that went from 97.0 % to 99.8 % across three widely recognized and documented datasets dedicated to COVID-19 detection.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100190"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Skin cancer detection using deep machine learning techniques","authors":"Olusoji Akinrinade,&nbsp;Chunglin Du","doi":"10.1016/j.ibmed.2024.100191","DOIUrl":"10.1016/j.ibmed.2024.100191","url":null,"abstract":"<div><div>Technological advancements have allowed people to have unfettered access to the internet from anywhere in the world. However, there is still little access to healthcare in rural and remote areas. This study highlights the potential of deep learning techniques in improving the early detection of skin cancer, a condition affecting millions globally. By addressing the challenges of class imbalance and dataset limitations, this research presents a model that can be integrated into digital health platforms, potentially saving lives by enabling earlier diagnosis and intervention, especially in underserved regions. The study also suggest using deep learning and few-shot learning when using machine learning techniques for skin cancer diagnosis. This study utilized a novel approach the use of raw images for training and test images for test data. These input images were then pre-processed using a deep model to identify and predict subsequent outputs using the model. In addition, the effect of the Convolutional Neural Network (CNN) effect in predicting accuracy using a skin lesion's texture to differentiate between benign and malignant lesions in the body was also examined using retrieved image elements from skin photos that were significant to skin cancer identification. The study focuses on using deep learning techniques to improve the detection of skin cancer from dermoscopic images. Deep learning a top-tier method for classifying skin lesions, was applied to create an end-to-end algorithm that could identify skin cancer more accurately. A variety of deep learning backbones were utilized, addressing the challenge of class imbalance in large datasets and seeking ways to boost performance even when only small datasets are available. To overcome these obstacles, the research leveraged transfer learning, data augmentation, and Generative Adversarial Networks (GANs). It further explored different sampling techniques and loss functions that could be effective for imbalanced datasets. The study also involved a comparison between ensemble models and hybrid models to determine which was more effective for the early detection of skin cancer. The paper concluded with a discussion of the challenges faced in the early detection of skin cancer, suggesting that while progress has been made, there are still significant hurdles to overcome.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100191"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of resource-efficient YOLO models for rapid and accurate recognition of intestinal parasitic eggs in stool microscopy","authors":"Kotteswaran Venkatesan ,&nbsp;Muthunayagam Muthulakshmi ,&nbsp;Balaji Prasanalakshmi ,&nbsp;Elangovan Karthickeien ,&nbsp;Harshini Pabbisetty ,&nbsp;Rahayu Syarifah Bahiyah","doi":"10.1016/j.ibmed.2025.100212","DOIUrl":"10.1016/j.ibmed.2025.100212","url":null,"abstract":"<div><div>Faster and reliable recognition of the specific species of intestinal parasite eggs in stool microscopic images is required for targeted and quick intervention of soil transmitted helminths (STH) disease. The main objective of the proposed work is to identify the effective light weight basic yolo models among the recent compact yolo variants such as yolov5n, yolov5s, yolov7, yolov7-tiny, yolov8n, yolov8s, yolov10n and yolov10s, that could assist in rapid and accurate recognition of 11 parasite species egg. The real time performance of the compact yolo models have been analyzed in embedded platforms: Raspberry Pi 4, Intel upSquared with the Neural Compute Stick 2 and Jetson Nano. Finally, Gradient-weighted class activation mapping (Grad-CAM) has been used as an explainable AI (XAI) visualization method to elucidate the egg detection performance of the proposed models. Yolov7-tiny achieved the overall highest mean Average Precision (mAP) score of 98.7 %. On contrary, yolov10n yielded highest recall and F1 score of 100 % and 98.6 %. On other hand, yolov8n took least inference time with processing speed of 55 frames per second with Jetson Nano. Notably, the proposed framework demonstrates superior performance in detection of egg classes - Enterobius vermicularis, Hookworm egg, Opisthorchis viverrine, Trichuris trichiura, and Taenia spp. which is a significant outcome of the current research. Further, Grad-CAM depicts the discriminative power of unique features in parasite eggs. Thus, this study demonstrates the effectiveness, compactness and inference latency analysis of basic compact yolo variants in learning the specific patterns, texture and shape of parasitic egg species, thereby potentially enhancing the diagnostic accuracy of STH.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100212"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143175219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a bilingual healthcare chatbot for pregnant women: A comparative study of deep learning models with BiGRU optimization","authors":"Ablavi Ericka Armela Kaneho ,&nbsp;Nabila Zrira ,&nbsp;Khadija Ouazzani-Touhami ,&nbsp;Haris Ahmad Khan ,&nbsp;Shah Nawaz","doi":"10.1016/j.ibmed.2025.100261","DOIUrl":"10.1016/j.ibmed.2025.100261","url":null,"abstract":"<div><div>With the growing demand for healthcare services and a persistent shortage of medical professionals, intelligent systems such as chatbots are gaining relevance in improving patient support. In obstetrics, pregnant women require fast, accessible, and reliable information to monitor their health and the progression of their pregnancy. This study aims to design and evaluate a bilingual chatbot tailored to the healthcare needs of pregnant women, leveraging recent advances in deep learning for natural language processing (NLP).</div><div>We developed and compared five deep learning architectures – artificial neural networks (ANN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent units (GRU), and bidirectional GRU (BiGRU) – to identify the most suitable model for chatbot implementation. Each model was trained on a bilingual dataset of pregnancy-related questions and answers, and evaluated using accuracy, computational efficiency, and contextual relevance of responses.</div><div>The BiGRU model achieved the highest performance, demonstrating superior accuracy and response efficiency over the other models. It consistently delivered context-aware, personalized answers in both languages, showing its robustness in handling sequential healthcare queries.</div><div>These findings suggest that BiGRU networks offer a promising solution for building intelligent, bilingual healthcare chatbots aimed at supporting pregnant women. Future work will focus on expanding the dataset, incorporating voice-based input, and deploying the chatbot in real-world healthcare settings for clinical validation.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"12 ","pages":"Article 100261"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144263586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Risk stratification in hip and knee replacement using artificial intelligence: a dual centre study to support the utility of high-volume low-complexity hubs and ambulatory surgery centres","authors":"Christopher Woodward ,&nbsp;Justin Green ,&nbsp;M.R. Reed ,&nbsp;David J. Beard ,&nbsp;Paul R. Williams","doi":"10.1016/j.ibmed.2025.100256","DOIUrl":"10.1016/j.ibmed.2025.100256","url":null,"abstract":"<div><div>The COVID-19 pandemic has resulted in a significant backlog of hip and knee replacement surgeries in the United Kingdom (UK). ^1,2 To address this, surgical hubs have been proposed to enhance efficiency, particularly for high-volume, low-complexity cases. ^3,4 These hubs and Ambulatory Surgery Centres often lack higher level care support such as intensive care facilities and are thus suited to patients with less co-morbidity and systemic illness. Pre-operative risk assessment is required to enable correct patient allocation to the appropriate site and reduce unwarranted risk.</div><div>This study explores the use of artificial intelligence (AI) for risk stratification in hip and knee arthroplasty. A polynomial regression model was developed using patient demographics, blood results, and comorbidities to assign risk scores for postoperative complications. The model was generated from 29,658 patient records from two UK National Health Service (NHS) healthcare organisations. It demonstrated an area under the receiver operating characteristic curve (AUROC) as the evaluation metric and was capable of categorising patients into high and low risk. Validation was performed using a retrospective analysis of 445 patients. Predicted versus actual complications and need for further care were used to examine agreement. The model's sensitivity was 70 % for identifying high-risk patients and had a negative predictive value of 96 %. This AI risk prediction was comparable to consultant-led care in risk stratification.</div><div>These findings suggest that AI can support more streamlined and efficient preoperative risk stratification, potentially reducing the burden on preoperative assessment teams and optimising resource allocation. While not without limitations, the AI model offers a sophisticated adjunct to clinical decision-making around determining risk. This can support facilities like hubs in the UK NHS or Ambulatory Surgery Centres in the United States.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"12 ","pages":"Article 100256"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning prediction of histological types of breast cancer: a case study in Morocco","authors":"Fatima Ezahra Mouas ,&nbsp;Latifa Doudach ,&nbsp;Achraf Benba ,&nbsp;Youssef Bakri ,&nbsp;Nasri Issad ,&nbsp;Abderrahim Ammar ,&nbsp;Hanae Terchoune ,&nbsp;Yahia Cherrah ,&nbsp;Khan Wen Goh ,&nbsp;Abdelhakim Bouyahya ,&nbsp;Taoufiq Fechtali","doi":"10.1016/j.ibmed.2025.100275","DOIUrl":"10.1016/j.ibmed.2025.100275","url":null,"abstract":"<div><div>Breast cancer remains a major global public health issue, especially among women, as the leading cause of cancer-related death. This study evaluated nine machine learning algorithms including Random Forest, support vector machines with <span>RBF</span>, linear, and polynomial kernels, K-Nearest Neighbors, logistic regression, AdaBoost, XGBoost, and a stacking classifier to predict histological types of breast cancer. The stacking classifier achieved the highest accuracy of 99.1 percent, followed by Random Forest at 98.3 percent and SVM with RBF kernel at 97.68 percent. XGBoost reached 97.4 percent accuracy, while K-Nearest Neighbors and SVM with polynomial kernel showed accuracies of 90.7 and 88.1 percent respectively. AdaBoost obtained 83.6 percent, with SVM linear and logistic regression performing lowest at 56.8 and 53.9 percent respectively. Hyperparameter optimization with Optuna improved Random Forest accuracy from 96.94 percent to 98.3 percent. Using RandomOverSampler to balance classes increased recall for the minority class from 92 percent to 98 percent, improving sensitivity to rare cases.</div><div>The studied cohort had a mean age of 51 years, with 71.6 percent diagnosed with invasive ductal carcinoma. The average tumor size was 3.3 cm, and 11.81 percent of cases were of the triple negative breast cancer type. Postmenopausal women represented 46.24 percent of the sample. Spearman correlation analysis showed positive links between age, menopause, and the presence of invasive ductal carcinoma. Feature importance analysis using Random Forest identified age, menopause, city, and marital status as the main predictive factors.</div><div>To facilitate clinical application, integration of the model into electronic health records is proposed, allowing automated data entry, real time predictions with confidence levels, and a clinician validation interface that ensures continuous model improvement and secure support for diagnosis.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"12 ","pages":"Article 100275"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144633427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence for the diagnosis of Helicobacter pylori infection in endoscopic and pathological tissues images: A systematic review and meta-analysis","authors":"Yuting Wen ,&nbsp;Yao Huang ,&nbsp;Yu Liu ,&nbsp;Shasha Zhang ,&nbsp;Zhe Liu ,&nbsp;Chan Hui ,&nbsp;Yi Wang","doi":"10.1016/j.ibmed.2025.100244","DOIUrl":"10.1016/j.ibmed.2025.100244","url":null,"abstract":"<div><h3>Background</h3><div>In recent years, artificial intelligence (AI) algorithms, including deep learning, have shown remarkable progress in image-recognition tasks. This study aimed to evaluate the diagnostic performance of AI in diagnosing Helicobacter pylori (H. pylori) infection using endoscopic and pathological images.</div></div><div><h3>Methods</h3><div>A literature search was conducted across multiple databases to identify all primary studies related to the diagnostic performance of AI algorithms for H. pylori infection published before 2024. True positive (TP), false positive (FP), false negative (FN), and true negative (TN) values were extracted or calculated for each study. Pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), precision-recall (PR), and diagnostic odds ratio (DOR) were calculated. A summary receiver operating characteristic curve (SROC) was used to assess overall diagnostic performance.</div></div><div><h3>Results</h3><div>Twelve studies were included in the final analysis. The pooled sensitivity was 0.87 (95 % CI 0.78–0.92), pooled specificity was 0.79 (95 % CI 0.54–0.92), pooled PLR was 4.1 (95 % CI 1.7–9.8), and pooled NLR was 0.17 (95 % CI 0.10–0.29). The DOR was 24 (95 % CI 7–78), and the SROC was 0.90 (95 % CI 0.87–0.92). Substantial heterogeneity was observed among the studies (sensitivity: I² = 90.50 %, 95 % CI 86.37–94.62; specificity: I² = 98.66 %, 95 % CI 98.34–98.97). Deek's funnel plot indicated low publication bias (P = 0.89).</div></div><div><h3>Conclusions</h3><div>AI algorithms show potential in diagnosing HP infection by improving accuracy and lesion detection. However, due to heterogeneity in study results, more comprehensive clinical validation is needed before widespread application. Future research should focus on multicenter validation, standardized datasets, integration into clinical workflows, and addressing data privacy and ethics to promote broader use of AI in HP diagnosis.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100244"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}