Intelligence-based medicine最新文献_第7页

Arkangel AI: A conversational agent for real-time, evidence-based medical question-answering Arkangel AI：实时、循证医学问答的对话代理

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100274

Maria Camila Villa, Natalia Castano-Villegas, Isabella Llano, Julian Martinez, Maria Fernanda Guevara, Jose Zea, Laura Velásquez

Introduction

Large Language Models (LLMs) have been trained and tested on several medical question-answering (QA) datasets built from medical licensing exams and natural interactions between doctors and patients to fine-tune them for specific health-related tasks.

Objective

We aimed to develop LLM-powered Conversational Agents (CAs) equipped to produce fast, accurate, and real-time responses to medical queries in different clinical and scientific scenarios. This paper presents Arkangel AI, our first conversational agent and research assistant.

Methods

The model is based on a system containing five LLMs; each is classified within a specific workflow with pre-defined instructions to produce the best search strategy and provide evidence-based answers. We assessed accuracy, intra/inter-class variability, and Cohen's Kappa using the question-answer (QA) dataset MedQA. Additionally, we used the PubMedQA dataset and assessed both databases using the RAGAS framework, including Context, Response Relevance, and Faithfulness. Traditional statistical analysis was performed with hypothesis tests and 95 % IC.

Results

Accuracy for MedQA (n: 1273) was 90.26 % and Cohen's kappa was 87 %, surpassing current SoTAs for other LLMs (GPT-4o, MedPaLM2). The model retrieved 80 % of the expected articles and provided relevant answers in 82 % of PubMedQA.

Conclusion

Arkangel AI showed proficient retrieval and reasoning abilities and unbiased responses. Evenly distributed medical QA datasets to train improved LLMs and external validation for the model with real-world physicians in clinical scenarios are needed. Clinical decision-making remains in the hands of trained healthcare professionals.

大型语言模型（llm）已经在几个医学问答（QA）数据集上进行了培训和测试，这些数据集来自医疗许可考试和医生和患者之间的自然互动，以微调它们以适应特定的健康相关任务。我们的目标是开发基于llm的会话代理（CAs），以便在不同的临床和科学场景中对医疗查询产生快速、准确和实时的响应。本文介绍了Arkangel AI，我们的第一个会话代理和研究助理。方法基于一个包含5个llm的系统建立模型；每个都在特定的工作流中进行分类，并带有预定义的指令，以产生最佳搜索策略并提供基于证据的答案。我们使用问答（QA）数据集MedQA评估准确性、类内/类间变异性和Cohen Kappa。此外，我们使用PubMedQA数据集，并使用RAGAS框架评估两个数据库，包括上下文、响应相关性和可信度。结果MedQA （n: 1273）的准确率为90.26%,Cohen’s kappa为87%，超过了目前其他LLMs （gpt - 40、MedPaLM2）的SoTAs。该模型检索了80%的预期文章，并在82%的PubMedQA中提供了相关答案。结论arkangel人工智能具有良好的检索推理能力和无偏性反应。需要均匀分布的医疗QA数据集来训练改进的llm，并在临床场景中与现实世界的医生一起对模型进行外部验证。临床决策仍然掌握在训练有素的医疗保健专业人员手中。

{"title":"Arkangel AI: A conversational agent for real-time, evidence-based medical question-answering","authors":"Maria Camila Villa, Natalia Castano-Villegas, Isabella Llano, Julian Martinez, Maria Fernanda Guevara, Jose Zea, Laura Velásquez","doi":"10.1016/j.ibmed.2025.100274","DOIUrl":"10.1016/j.ibmed.2025.100274","url":null,"abstract":"<div><h3>Introduction</h3><div>Large Language Models (LLMs) have been trained and tested on several medical question-answering (QA) datasets built from medical licensing exams and natural interactions between doctors and patients to fine-tune them for specific health-related tasks.</div></div><div><h3>Objective</h3><div>We aimed to develop LLM-powered Conversational Agents (CAs) equipped to produce fast, accurate, and real-time responses to medical queries in different clinical and scientific scenarios. This paper presents Arkangel AI, our first conversational agent and research assistant.</div></div><div><h3>Methods</h3><div>The model is based on a system containing five LLMs; each is classified within a specific workflow with pre-defined instructions to produce the best search strategy and provide evidence-based answers. We assessed accuracy, intra/inter-class variability, and Cohen's Kappa using the question-answer (QA) dataset MedQA. Additionally, we used the PubMedQA dataset and assessed both databases using the RAGAS framework, including Context, Response Relevance, and Faithfulness. Traditional statistical analysis was performed with hypothesis tests and 95 % IC.</div></div><div><h3>Results</h3><div>Accuracy for MedQA (n: 1273) was 90.26 % and Cohen's kappa was 87 %, surpassing current SoTAs for other LLMs (GPT-4o, MedPaLM2). The model retrieved 80 % of the expected articles and provided relevant answers in 82 % of PubMedQA.</div></div><div><h3>Conclusion</h3><div>Arkangel AI showed proficient retrieval and reasoning abilities and unbiased responses. Evenly distributed medical QA datasets to train improved LLMs and external validation for the model with real-world physicians in clinical scenarios are needed. Clinical decision-making remains in the hands of trained healthcare professionals.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"12 ","pages":"Article 100274"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829353","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}

引用次数: 0

Design and implementation of a low-cost malaria diagnostic system based on convolutional neural network 基于卷积神经网络的低成本疟疾诊断系统的设计与实现

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100272

Ekobo Akoa Brice , Ndoumbe Jean , Mohamadou Madina

This work focuses on the design and implementation of an intelligent system that can diagnose malaria from blood smear images. This system takes data in the image format and provides an instant and automated diagnosis to output the result of the patient’s condition on a screen. The methodology for achieving the system is based on the CNN (convolutional neural network). The latter has the specificity to function as a feature extractor and image classifier. The software part thus obtained is implemented in an electronic device that serves as a kit mounted with our care. The establishment of such a system has innumerable assets, such as rapidity during diagnosis by a laboratory technician or not; its portability that will facilitate its use wherever needed. From an ergonomic and functional point of view, the system has a real impact in the diagnosis of a large-scale malaria endemic. The CNN was trained on a large dataset of blood smears and was able to accurately classify infected and uninfected samples with high sensitivity and specificity. Insofar as the system carried out after testing on several samples reaches an average sensitivity of 89.50% and an average precision of 89%, this improves decision-making on the diagnosis of malaria. The system thus created allows malaria to be diagnosed at low cost from blood smear images. The use of CNNs in this project has the advantage of automatically extracting features from blood smear images and classifying them efficiently. The major advantage of the proposed system is its portability and lower cost. The performance of the proposed algorithm was evaluated on a publicly available malaria data set.

这项工作的重点是设计和实现一个智能系统，可以从血液涂片图像诊断疟疾。该系统以图像格式获取数据，并提供即时和自动的诊断，将患者的病情结果输出到屏幕上。实现该系统的方法是基于CNN（卷积神经网络）。后者具有作为特征提取器和图像分类器的特异性。由此获得的软件部分在一个电子设备中实现，该设备作为一个工具包安装在我们的护理中。建立这样一个系统具有无数的优势，例如实验室技术人员在诊断过程中是否快速；它的可移植性将使它在任何需要的地方都能使用。从人体工程学和功能的角度来看，该系统对大规模疟疾地方病的诊断具有实际影响。CNN在一个大型的血液涂片数据集上进行训练，能够以高灵敏度和特异性准确地对感染和未感染的样本进行分类。在对几个样本进行测试后，该系统的平均灵敏度达到89.50%，平均精度达到89%，这改善了疟疾诊断的决策。这样创建的系统可以通过血液涂片图像以低成本诊断疟疾。在本课题中使用cnn具有从血液涂片图像中自动提取特征并进行高效分类的优点。该系统的主要优点是可移植性和低成本。在一个公开可用的疟疾数据集上评估了所提出算法的性能。

{"title":"Design and implementation of a low-cost malaria diagnostic system based on convolutional neural network","authors":"Ekobo Akoa Brice , Ndoumbe Jean , Mohamadou Madina","doi":"10.1016/j.ibmed.2025.100272","DOIUrl":"10.1016/j.ibmed.2025.100272","url":null,"abstract":"<div><div>This work focuses on the design and implementation of an intelligent system that can diagnose malaria from blood smear images. This system takes data in the image format and provides an instant and automated diagnosis to output the result of the patient’s condition on a screen. The methodology for achieving the system is based on the CNN (convolutional neural network). The latter has the specificity to function as a feature extractor and image classifier. The software part thus obtained is implemented in an electronic device that serves as a kit mounted with our care. The establishment of such a system has innumerable assets, such as rapidity during diagnosis by a laboratory technician or not; its portability that will facilitate its use wherever needed. From an ergonomic and functional point of view, the system has a real impact in the diagnosis of a large-scale malaria endemic. The CNN was trained on a large dataset of blood smears and was able to accurately classify infected and uninfected samples with high sensitivity and specificity. Insofar as the system carried out after testing on several samples reaches an average sensitivity of 89.50% and an average precision of 89%, this improves decision-making on the diagnosis of malaria. The system thus created allows malaria to be diagnosed at low cost from blood smear images. The use of CNNs in this project has the advantage of automatically extracting features from blood smear images and classifying them efficiently. The major advantage of the proposed system is its portability and lower cost. The performance of the proposed algorithm was evaluated on a publicly available malaria data set.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"12 ","pages":"Article 100272"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596406","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}

引用次数: 0

Meta-learning driven multi disease fuzzy neural framework for clinical risk prediction 基于元学习驱动的多疾病模糊神经框架临床风险预测

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100315

Kubra Noor, Ubaida Fatima, Fahim Raees

Rising rates of chronic illnesses, including heart disease, diabetes, and cancer, demand precise and scalable early diagnostic approaches. Utilizing three datasets UCI Heart Disease, PIMA Indians Diabetes, and Breast Cancer Wisconsin we suggest a metalearning-inspired hybrid approach combining Fuzzy C-Means clustering and artificial neural networks for multidisease risk prediction. Fuzzy logic is used to cluster each dataset to model intraclass variation; cluster-specific neural networks are then trained to catch patterns. Fuzzy membership ratings are used to combine final forecasts. Achieving 85.25 % (heart disease), 81.2 % (diabetes), and 95.1 % (cancer) accuracy, respectively, the suggested system shows great accuracy, disease-wide generalization, and interpretability. The results show improved predictions for complex and varied patient profiles, confirming that the system is strong and useful for real-world health analysis.

包括心脏病、糖尿病和癌症在内的慢性病发病率不断上升，需要精确和可扩展的早期诊断方法。利用UCI心脏病、PIMA印第安人糖尿病和威斯康星州乳腺癌三个数据集，我们提出了一种元学习启发的混合方法，将模糊c均值聚类和人工神经网络相结合，用于多疾病风险预测。利用模糊逻辑对各数据集进行聚类，模拟类内变化；然后训练特定于集群的神经网络来捕捉模式。模糊隶属度评级用于组合最终预测。该系统分别达到85.25%（心脏病）、81.2%（糖尿病）和95.1%（癌症）的准确率，显示出很高的准确性、疾病通用性和可解释性。结果表明，对复杂和不同的患者概况的预测有所改善，证实了该系统在现实世界的健康分析中是强大和有用的。

引用次数: 0

Feature selection using hybridized Genghis Khan Shark with snow ablation optimization technique for multi-disease prognosis 成吉思汗鲨杂交特征选择与雪消融优化技术在多疾病预后中的应用

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100249

Ruqsar Zaitoon , Shaik Salma Asiya Begum , Sachi Nandan Mohanty , Deepa Jose

The exponential growth in medical data and feature dimensionality presents significant challenges in building accurate and efficient diagnostic models. High-dimensional datasets often contain redundant or irrelevant features that degrade classification performance and increase computational burden. Feature selection (FS) is therefore a critical step in medical data analysis to enhance model accuracy and interpretability. While many recent FS techniques rely on optimization algorithms, tuning their parameters and avoiding early convergence remain major challenges. This study introduces a novel hybrid optimization technique—Hybridized Genghis Khan Shark with Snow Ablation Optimization (HyGKS-SAO)—to identify the most informative features for multi-disease classification. The raw medical datasets are first pre-processed using a Tanh-based normalization method. The HyGKS-SAO algorithm then selects optimal features, balancing exploration and exploitation effectively. Finally, a multi-kernel support vector machine (SVM) is employed to classify diseases based on the selected features. The proposed framework is evaluated on six publicly available medical datasets, including breast cancer, diabetes, heart disease, stroke, lung cancer, and chronic kidney disease. Experimental results demonstrate the effectiveness of the proposed method, achieving 98 % accuracy, 97.99 % MCC, 96.31 % PPV, 97.35 % G-mean, 98.03 % Kappa Coefficient, and a low computation time of 50 s, outperforming several state-of-the-art approaches.

医疗数据和特征维数的指数级增长为建立准确、高效的诊断模型提出了重大挑战。高维数据集通常包含冗余或不相关的特征，这些特征会降低分类性能并增加计算负担。因此，特征选择（FS）是医疗数据分析中提高模型准确性和可解释性的关键步骤。虽然许多最新的FS技术依赖于优化算法，但调整其参数和避免早期收敛仍然是主要挑战。本研究引入一种新的混合优化技术-杂交成吉思汗鲨鱼与雪消融优化(HyGKS-SAO) -来识别最具信息量的特征，用于多疾病分类。首先使用基于tanh的规范化方法对原始医疗数据集进行预处理。HyGKS-SAO算法选择最优特征，有效地平衡了搜索和开发。最后，利用多核支持向量机（SVM）对所选特征进行疾病分类。拟议的框架在六个公开可用的医疗数据集上进行了评估，包括乳腺癌、糖尿病、心脏病、中风、肺癌和慢性肾病。实验结果证明了该方法的有效性，准确率为98%，MCC为97.99%，PPV为96.31%，g均值为97.35%，Kappa系数为98.03%，计算时间仅为50 s，优于几种最先进的方法。

{"title":"Feature selection using hybridized Genghis Khan Shark with snow ablation optimization technique for multi-disease prognosis","authors":"Ruqsar Zaitoon , Shaik Salma Asiya Begum , Sachi Nandan Mohanty , Deepa Jose","doi":"10.1016/j.ibmed.2025.100249","DOIUrl":"10.1016/j.ibmed.2025.100249","url":null,"abstract":"<div><div>The exponential growth in medical data and feature dimensionality presents significant challenges in building accurate and efficient diagnostic models. High-dimensional datasets often contain redundant or irrelevant features that degrade classification performance and increase computational burden. Feature selection (FS) is therefore a critical step in medical data analysis to enhance model accuracy and interpretability. While many recent FS techniques rely on optimization algorithms, tuning their parameters and avoiding early convergence remain major challenges. This study introduces a novel hybrid optimization technique—Hybridized Genghis Khan Shark with Snow Ablation Optimization (HyGKS-SAO)—to identify the most informative features for multi-disease classification. The raw medical datasets are first pre-processed using a Tanh-based normalization method. The HyGKS-SAO algorithm then selects optimal features, balancing exploration and exploitation effectively. Finally, a multi-kernel support vector machine (SVM) is employed to classify diseases based on the selected features. The proposed framework is evaluated on six publicly available medical datasets, including breast cancer, diabetes, heart disease, stroke, lung cancer, and chronic kidney disease. Experimental results demonstrate the effectiveness of the proposed method, achieving 98 % accuracy, 97.99 % MCC, 96.31 % PPV, 97.35 % G-mean, 98.03 % Kappa Coefficient, and a low computation time of 50 s, outperforming several state-of-the-art approaches.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100249"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848482","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}

引用次数: 0

AI speechbots and 3D segmentations in virtual reality improve radiology on-call training in resource-limited settings 人工智能语音机器人和虚拟现实中的3D分割改善了资源有限环境下的放射学随叫随到培训

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100245

Yusuf Alibrahim , Muhieldean Ibrahim , Devindra Gurdayal , Muhammad Munshi

Objective

Evaluate the use of large-language model (LLM) speechbot tools and deep learning-assisted generation of 3D reconstructions when integrated in a virtual reality (VR) setting to teach radiology on-call topics to radiology residents.

Methods

Three first year radiology residents in Guyana were enrolled in an 8-week radiology course that focused on preparation for on-call duties. The course, delivered via VR headsets with custom software integrating LLM-powered speechbots trained on imaging reports and 3D reconstructions segmented with the help of a deep learning model. Each session focused on a specific radiology area, employing a didactic and case-based learning approach, enhanced with 3D reconstructions and an LLM-powered speechbot. Post-session, residents reassessed their knowledge and provided feedback on their VR and LLM-powered speechbot experiences.

Results/discussion

Residents found that the 3D reconstructions segmented semi-automatically by deep learning algorithms and AI-driven self-learning via speechbot was highly valuable. The 3D reconstructions, especially in the interventional radiology session, were helpful and the benefit is augmented by VR where navigating the models is seamless and perception of depth is pronounced. Residents also found conversing with the AI-speechbot seamless and was valuable in their post session self-learning. The major drawback of VR was motion sickness, which was mild and improved over time.

Conclusion

AI-assisted VR radiology education could be used to develop new and accessible ways of teaching a variety of radiology topics in a seamless and cost-effective way. This could be especially useful in supporting radiology education remotely in regions which lack local radiology expertise.

目的评估在虚拟现实（VR）环境中集成大语言模型（LLM）语音机器人工具和深度学习辅助生成3D重建的使用，以教授放射科住院医师放射学随叫随到的主题。方法对圭亚那3名一年级放射科住院医师进行为期8周的放射学培训，重点是为随叫随到的工作做准备。该课程通过VR头显和定制软件提供，集成了llm支持的语音机器人，这些语音机器人接受过成像报告和3D重建的培训，并借助深度学习模型进行分割。每次会议都集中在一个特定的放射学领域，采用教学和基于案例的学习方法，通过3D重建和llm驱动的语音机器人进行增强。课程结束后，学员们重新评估了他们的知识，并就他们的VR和llm语音机器人体验提供了反馈。结果/讨论居民发现，通过深度学习算法和人工智能驱动的语音机器人自主学习进行半自动分割的三维重建非常有价值。3D重建，特别是在介入放射学会话中，是有帮助的，VR增强了这种好处，其中导航模型是无缝的，深度感知是明显的。居民们还发现，与人工智能语音机器人的对话是无缝的，在他们的课后自学中很有价值。VR的主要缺点是晕动病，这是轻微的，随着时间的推移会改善。结论人工智能辅助的虚拟现实放射学教学可以为各种放射学主题的教学提供新的、可访问的、无缝的、高性价比的教学方式。这对于在缺乏当地放射专业知识的地区支持远程放射学教育尤其有用。

{"title":"AI speechbots and 3D segmentations in virtual reality improve radiology on-call training in resource-limited settings","authors":"Yusuf Alibrahim , Muhieldean Ibrahim , Devindra Gurdayal , Muhammad Munshi","doi":"10.1016/j.ibmed.2025.100245","DOIUrl":"10.1016/j.ibmed.2025.100245","url":null,"abstract":"<div><h3>Objective</h3><div>Evaluate the use of large-language model (LLM) speechbot tools and deep learning-assisted generation of 3D reconstructions when integrated in a virtual reality (VR) setting to teach radiology on-call topics to radiology residents.</div></div><div><h3>Methods</h3><div>Three first year radiology residents in Guyana were enrolled in an 8-week radiology course that focused on preparation for on-call duties. The course, delivered via VR headsets with custom software integrating LLM-powered speechbots trained on imaging reports and 3D reconstructions segmented with the help of a deep learning model. Each session focused on a specific radiology area, employing a didactic and case-based learning approach, enhanced with 3D reconstructions and an LLM-powered speechbot. Post-session, residents reassessed their knowledge and provided feedback on their VR and LLM-powered speechbot experiences.</div></div><div><h3>Results/discussion</h3><div>Residents found that the 3D reconstructions segmented semi-automatically by deep learning algorithms and AI-driven self-learning via speechbot was highly valuable. The 3D reconstructions, especially in the interventional radiology session, were helpful and the benefit is augmented by VR where navigating the models is seamless and perception of depth is pronounced. Residents also found conversing with the AI-speechbot seamless and was valuable in their post session self-learning. The major drawback of VR was motion sickness, which was mild and improved over time.</div></div><div><h3>Conclusion</h3><div>AI-assisted VR radiology education could be used to develop new and accessible ways of teaching a variety of radiology topics in a seamless and cost-effective way. This could be especially useful in supporting radiology education remotely in regions which lack local radiology expertise.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100245"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747483","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}

引用次数: 0

Deep learning based detection of endometriosis lesions in laparoscopic images with 5-fold cross-validation 基于深度学习的腹腔镜子宫内膜异位症病变检测及5倍交叉验证

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100230

Shujaat Ali Zaidi , Varin Chouvatut , Chailert Phongnarisorn , Dussadee Praserttitipong

Endometriosis, a complex gynecological condition, presents significant diagnostic challenges due to the subtle and varied appearance of its lesions. This study leverages deep learning to classify endometriosis lesions in laparoscopic images using the Gynecologic Laparoscopy Endometriosis Dataset (GLENDA). Three deep learning models VGG19, ResNet50, and Inception V3 were trained and evaluated with 5-fold cross-validation to enhance generalizability and mitigate overfitting. Robust data augmentation techniques were applied to address dataset limitations. The models were tasked with classifying lesions into pathological and nonpathological categories. Experimental results demonstrated strong performance, with VGG19, ResNet50, and Inception V3 achieving accuracies of 0.89, 0.91, and 0.93, respectively. Inception V3 outperformed the others, highlighting its efficacy for this task. The findings underscore the potential of deep learning in improving endometriosis diagnosis, offering a reliable tool for clinicians. This study contributes to the growing field of AI-driven medical image analysis, emphasizing the value of cross-validation and data augmentation in enhancing model performance for specialized medical applications.

子宫内膜异位症是一种复杂的妇科疾病，由于其病变的微妙和多样的外观，提出了重大的诊断挑战。本研究利用妇科腹腔镜子宫内膜异位症数据集（GLENDA），利用深度学习对腹腔镜图像中的子宫内膜异位症病变进行分类。三个深度学习模型VGG19， ResNet50和Inception V3进行了训练和评估，并进行了5倍交叉验证，以增强泛化性并减少过拟合。应用稳健的数据增强技术来解决数据集的局限性。这些模型的任务是将病变分为病理和非病理两类。实验结果显示了较强的性能，VGG19、ResNet50和Inception V3的准确率分别为0.89、0.91和0.93。Inception V3的表现优于其他版本，突出了它在此任务中的有效性。研究结果强调了深度学习在改善子宫内膜异位症诊断方面的潜力，为临床医生提供了可靠的工具。这项研究促进了人工智能驱动的医学图像分析领域的发展，强调了交叉验证和数据增强在提高专业医疗应用的模型性能方面的价值。

{"title":"Deep learning based detection of endometriosis lesions in laparoscopic images with 5-fold cross-validation","authors":"Shujaat Ali Zaidi , Varin Chouvatut , Chailert Phongnarisorn , Dussadee Praserttitipong","doi":"10.1016/j.ibmed.2025.100230","DOIUrl":"10.1016/j.ibmed.2025.100230","url":null,"abstract":"<div><div>Endometriosis, a complex gynecological condition, presents significant diagnostic challenges due to the subtle and varied appearance of its lesions. This study leverages deep learning to classify endometriosis lesions in laparoscopic images using the Gynecologic Laparoscopy Endometriosis Dataset (GLENDA). Three deep learning models VGG19, ResNet50, and Inception V3 were trained and evaluated with 5-fold cross-validation to enhance generalizability and mitigate overfitting. Robust data augmentation techniques were applied to address dataset limitations. The models were tasked with classifying lesions into pathological and nonpathological categories. Experimental results demonstrated strong performance, with VGG19, ResNet50, and Inception V3 achieving accuracies of 0.89, 0.91, and 0.93, respectively. Inception V3 outperformed the others, highlighting its efficacy for this task. The findings underscore the potential of deep learning in improving endometriosis diagnosis, offering a reliable tool for clinicians. This study contributes to the growing field of AI-driven medical image analysis, emphasizing the value of cross-validation and data augmentation in enhancing model performance for specialized medical applications.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100230"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621027","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}

引用次数: 0

Leveraging Conv-XGBoost algorithm for perceived mental stress detection using Photoplethysmography 利用卷积- xgboost算法利用光电容积脉搏波检测感知精神压力

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100209

Geethu S. Kumar, B. Ankayarkanni

Stress detection is crucial for monitoring mental health and preventing stress-related disorders. Real-time stress detection shows promise with photoplethysmography (PPG), a non-invasive optical technology that analyzes blood volume changes in the microvascular bed of tissue. This study introduces a novel hybrid model, Conv-XGBoost, which combines Convolutional Neural Networks (CNN) and eXtreme Gradient Boosting (XGBoost) to improve the accuracy and robustness of stress detection from PPG signals. The Conv-XGBoost model utilizes the feature extraction capabilities of CNNs to process PPG signals, converting them into spectrograms that capture the time–frequency characteristics of data. The XGBoost component is essential for handling the complex, high-dimensional feature sets provided by the CNN, enhancing prediction capabilities through gradient boosting. This customized approach addresses the limitations of traditional machine learning algorithms in dealing with hand-crafted features. The Pulse Rate Variability-based Photoplethysmography dataset was chosen for training and validation. The outcomes of the experiments revealed that the proposed Conv-XGBoost model outperformed more conventional machine learning techniques with a training accuracy of 98.87%, validation accuracy of 93.28% and an F1-score of 97.25%. Additionally, the model demonstrated superior resilience to noise and variability in PPG signals, common in real-world scenarios. This study underscores how hybrid models can improve stress detection and sets the stage for future research integrating physiological signals with advanced deep learning techniques.

压力检测对于监测心理健康和预防压力相关疾病至关重要。实时应力检测显示了光容积脉搏波（PPG）的前景，这是一种非侵入性光学技术，可以分析组织微血管床中的血容量变化。本研究引入了一种新的混合模型，convv -XGBoost，它结合了卷积神经网络（CNN）和极限梯度增强（XGBoost），以提高从PPG信号中检测应力的准确性和鲁棒性。convv - xgboost模型利用cnn的特征提取能力来处理PPG信号，将其转换成捕获数据时频特征的频谱图。XGBoost组件对于处理CNN提供的复杂、高维特征集至关重要，通过梯度增强增强预测能力。这种定制的方法解决了传统机器学习算法在处理手工制作的特征方面的局限性。选择基于脉冲速率变异性的光容积脉搏波数据集进行训练和验证。实验结果表明，该模型的训练准确率为98.87%，验证准确率为93.28%，f1分数为97.25%，优于传统的机器学习技术。此外，该模型对PPG信号的噪声和变异性具有优异的恢复能力，这在现实世界中很常见。这项研究强调了混合模型如何改善应力检测，并为未来将生理信号与先进的深度学习技术相结合的研究奠定了基础。

{"title":"Leveraging Conv-XGBoost algorithm for perceived mental stress detection using Photoplethysmography","authors":"Geethu S. Kumar, B. Ankayarkanni","doi":"10.1016/j.ibmed.2025.100209","DOIUrl":"10.1016/j.ibmed.2025.100209","url":null,"abstract":"<div><div>Stress detection is crucial for monitoring mental health and preventing stress-related disorders. Real-time stress detection shows promise with photoplethysmography (PPG), a non-invasive optical technology that analyzes blood volume changes in the microvascular bed of tissue. This study introduces a novel hybrid model, Conv-XGBoost, which combines Convolutional Neural Networks (CNN) and eXtreme Gradient Boosting (XGBoost) to improve the accuracy and robustness of stress detection from PPG signals. The Conv-XGBoost model utilizes the feature extraction capabilities of CNNs to process PPG signals, converting them into spectrograms that capture the time–frequency characteristics of data. The XGBoost component is essential for handling the complex, high-dimensional feature sets provided by the CNN, enhancing prediction capabilities through gradient boosting. This customized approach addresses the limitations of traditional machine learning algorithms in dealing with hand-crafted features. The Pulse Rate Variability-based Photoplethysmography dataset was chosen for training and validation. The outcomes of the experiments revealed that the proposed Conv-XGBoost model outperformed more conventional machine learning techniques with a training accuracy of 98.87%, validation accuracy of 93.28% and an F1-score of 97.25%. Additionally, the model demonstrated superior resilience to noise and variability in PPG signals, common in real-world scenarios. This study underscores how hybrid models can improve stress detection and sets the stage for future research integrating physiological signals with advanced deep learning techniques.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100209"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377342","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}

引用次数: 0

BreastCare application: Moroccan Breast cancer diagnosis through deep learning-based image segmentation and classification

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100254

Nouhaila Erragzi , Nabila Zrira , Safae Lanjeri , Youssef Omor , Anwar Jimi , Ibtissam Benmiloud , Rajaa Sebihi , Rachida Latib , Nabil Ngote , Haris Ahmad Khan , Shah Nawaz

Breast cancer remains a critical health problem worldwide. Increasing survival rates requires early detection. Accurate classification and segmentation are crucial for effective diagnosis and treatment. Although breast imaging modalities offer many advantages for the diagnosis of breast cancer, the interpretation of breast ultrasound images has always been a vital issue for physicians and radiologists due to misdiagnosis. Moreover, detecting cancer at an early stage increases the chances of survival. This article presents two approaches: Attention-DenseUNet for the segmentation task and EfficientNetB7 for the classification task using public datasets: BUSI, UDIAT, BUSC, BUSIS, and STUHospital. These models are proposed in the context of Computer-Aided Diagnosis (CAD) for breast cancer detection. In the first study, we obtained an impressive Dice coefficient for all datasets, with scores of 88.93%, 95.35%, 92.79%, 93.29%, and 94.24%, respectively. In the classification task, we achieved a high accuracy using only four public datasets that include the two classes benign and malignant: BUSI, UDIAT, BUSC, and BUSIS, with an accuracy of 97%, 100%, 99%, and 94%, respectively. Generally, the results show that our proposed methods are considerably better than other state-of-the-art methods, which will undoubtedly help improve cancer diagnosis and reduce the number of false positives. Finally, we used the suggested approaches to create “Moroccan BreastCare”, an advanced breast cancer segmentation and classification software that automatically processes, segments, and classifies breast ultrasound images.

乳腺癌在世界范围内仍然是一个严重的健康问题。提高生存率需要早期发现。准确的分类和分割是有效诊断和治疗的关键。尽管乳腺超声成像方式为乳腺癌的诊断提供了许多优势，但由于误诊，乳腺超声图像的解释一直是医生和放射科医生面临的一个重要问题。此外，在早期发现癌症会增加生存的机会。本文介绍了两种方法：用于分割任务的Attention-DenseUNet和用于分类任务的EfficientNetB7，使用公共数据集：BUSI、UDIAT、BUSC、BUSIS和STUHospital。这些模型是在计算机辅助诊断（CAD）乳腺癌检测的背景下提出的。在第一项研究中，我们对所有数据集都获得了令人印象深刻的Dice系数，得分分别为88.93%,95.35%,92.79%，93.29%和94.24%。在分类任务中，我们仅使用四个公共数据集（包括良性和恶性两个类别：BUSI， UDIAT， BUSC和BUSIS）就获得了很高的准确率，准确率分别为97%，100%，99%和94%。总的来说，结果表明我们提出的方法比其他最先进的方法要好得多，这无疑将有助于提高癌症诊断和减少假阳性的数量。最后，我们使用建议的方法创建了“摩洛哥乳房护理”，这是一个先进的乳腺癌分割和分类软件，可以自动处理，分割和分类乳房超声图像。

{"title":"BreastCare application: Moroccan Breast cancer diagnosis through deep learning-based image segmentation and classification","authors":"Nouhaila Erragzi , Nabila Zrira , Safae Lanjeri , Youssef Omor , Anwar Jimi , Ibtissam Benmiloud , Rajaa Sebihi , Rachida Latib , Nabil Ngote , Haris Ahmad Khan , Shah Nawaz","doi":"10.1016/j.ibmed.2025.100254","DOIUrl":"10.1016/j.ibmed.2025.100254","url":null,"abstract":"<div><div>Breast cancer remains a critical health problem worldwide. Increasing survival rates requires early detection. Accurate classification and segmentation are crucial for effective diagnosis and treatment. Although breast imaging modalities offer many advantages for the diagnosis of breast cancer, the interpretation of breast ultrasound images has always been a vital issue for physicians and radiologists due to misdiagnosis. Moreover, detecting cancer at an early stage increases the chances of survival. This article presents two approaches: Attention-DenseUNet for the segmentation task and EfficientNetB7 for the classification task using public datasets: BUSI, UDIAT, BUSC, BUSIS, and STUHospital. These models are proposed in the context of Computer-Aided Diagnosis (CAD) for breast cancer detection. In the first study, we obtained an impressive Dice coefficient for all datasets, with scores of 88.93%, 95.35%, 92.79%, 93.29%, and 94.24%, respectively. In the classification task, we achieved a high accuracy using only four public datasets that include the two classes benign and malignant: BUSI, UDIAT, BUSC, and BUSIS, with an accuracy of 97%, 100%, 99%, and 94%, respectively. Generally, the results show that our proposed methods are considerably better than other state-of-the-art methods, which will undoubtedly help improve cancer diagnosis and reduce the number of false positives. Finally, we used the suggested approaches to create “Moroccan BreastCare”, an advanced breast cancer segmentation and classification software that automatically processes, segments, and classifies breast ultrasound images.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100254"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943162","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}

引用次数: 0

An intelligent ensemble EfficientNet prediction system for interpretations of cardiac magnetic resonance images in heart failure severity diagnosis 用于心衰严重程度诊断的心脏磁共振图像解释的智能集成effentnet预测系统

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100218

Muthunayagam Muthulakshmi , Kotteswaran Venkatesan , Balaji Prasanalakshmi , Rahayu Syarifah Bahiyah , Vijayakumar Divya

Ensemble models as part of federated learning leverage the ability of individual models to learn unique patterns from the training dataset to make more efficient predictions than single predicting systems. This study aggregates the output of four best-performing EfficientNet models to arrive at the final heart failure severity prediction through federated learning. The seven variants of EfficientNet models (B0-B7) learn the features from the cardiac magnetic resonance images that are most relevant to heart failure severity. Further, the performance of every model variant has been analysed with three different optimizers i.e. Adam, SGD, and RMSprop. It has been observed that the developed ensemble prediction system provides an improved overall testing accuracy of 0.95. It is also worthy to note that the ensemble prediction has yielded significant improvement in the prediction of individual classes which is evident from sensitivity measure of 0.95, 0.88, 1.00, 0.93, and 0.98 for hyperdynamic, mild, moderate, normal and severe classes respectively. It is obvious from these results that the proposed ensemble EfficientNet prediction system would assist the radiologist in better interpretation of cardiac magnetic resonance images. This in turn would benefit the cardiologist in understanding the HF progress and planning effective therapeutic intervention.

作为联邦学习的一部分，集成模型利用单个模型从训练数据集中学习独特模式的能力，以进行比单个预测系统更有效的预测。本研究汇总了四个表现最好的effentnet模型的输出，通过联合学习得出最终的心力衰竭严重程度预测。高效率网络模型的七个变体（B0-B7）从心脏磁共振图像中学习与心力衰竭严重程度最相关的特征。此外，使用三个不同的优化器（即Adam、SGD和RMSprop）分析了每个模型变体的性能。结果表明，所开发的集成预测系统总体测试精度提高到0.95。值得注意的是，集合预测在单个类别的预测方面取得了显著的进步，这一点从超动力、轻度、中度、正常和严重类别的灵敏度分别为0.95、0.88、1.00、0.93和0.98可以明显看出。从这些结果可以明显看出，所提出的集成effentnet预测系统将帮助放射科医生更好地解释心脏磁共振图像。反过来，这将有利于心脏科医生了解心衰的进展和计划有效的治疗干预。

{"title":"An intelligent ensemble EfficientNet prediction system for interpretations of cardiac magnetic resonance images in heart failure severity diagnosis","authors":"Muthunayagam Muthulakshmi , Kotteswaran Venkatesan , Balaji Prasanalakshmi , Rahayu Syarifah Bahiyah , Vijayakumar Divya","doi":"10.1016/j.ibmed.2025.100218","DOIUrl":"10.1016/j.ibmed.2025.100218","url":null,"abstract":"<div><div>Ensemble models as part of federated learning leverage the ability of individual models to learn unique patterns from the training dataset to make more efficient predictions than single predicting systems. This study aggregates the output of four best-performing EfficientNet models to arrive at the final heart failure severity prediction through federated learning. The seven variants of EfficientNet models (B0-B7) learn the features from the cardiac magnetic resonance images that are most relevant to heart failure severity. Further, the performance of every model variant has been analysed with three different optimizers i.e. Adam, SGD, and RMSprop. It has been observed that the developed ensemble prediction system provides an improved overall testing accuracy of 0.95. It is also worthy to note that the ensemble prediction has yielded significant improvement in the prediction of individual classes which is evident from sensitivity measure of 0.95, 0.88, 1.00, 0.93, and 0.98 for hyperdynamic, mild, moderate, normal and severe classes respectively. It is obvious from these results that the proposed ensemble EfficientNet prediction system would assist the radiologist in better interpretation of cardiac magnetic resonance images. This in turn would benefit the cardiologist in understanding the HF progress and planning effective therapeutic intervention.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100218"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143173638","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}

引用次数: 0

Comparing machine learning approaches for predicting the success of ICSI treatment: A study on clinical applications 比较预测ICSI治疗成功的机器学习方法：临床应用研究

Intelligence-based medicine

Pub Date : 2025-01-01 DOI: 10.1016/j.ibmed.2025.100204

Abrar Mohammad , Haneen Awad , Huthaifa I. Ashqar

Intracytoplasmic Sperm Injection (ICSI) is widely used to treat almost all forms of male infertility and to overcome fertilization failure. While ICSI is a powerful procedure, it's also considered quite expensive, which means couples and clinicians have to make informed decisions about whether or not to proceed with this treatment. About 10,036 patient records, 46 attribute sets, and one label column that indicates the success or failure of pregnancy after the ICSI treatment were used to conduct this research. The data were gathered from Razan infertility center in Palestine. The ICSI dataset contains only clinical features that are known prior to deciding on ICSI treatment. The dataset contains 46 features, 5 of the independent features have categorical values, 12 are numerical, 3 are string, and 26 are binary. Based on the results, RF algorithm achieved the highest AUC score of 0.97, followed by the NN with a score of 0.95, and the RIMARC algorithm with a score of 0.92. AUC is a widely used metric for evaluating the performance of binary classification models. Therefore, judging by the AUC scores, it appears that RF algorithm outperformed the other two algorithms in terms of the evaluated metric. The method employed in our analysis demonstrates considerable promise, practicality, and generalizability, driving advancements in fertility treatments and ultimately improving the chances of couples achieving their desired family goals.

胞浆内单精子注射（ICSI）被广泛用于治疗几乎所有形式的男性不育症和克服受精失败。虽然ICSI是一个强大的程序，但也被认为是相当昂贵的，这意味着夫妇和临床医生必须做出明智的决定，是否继续进行这种治疗。本研究使用了约10036例患者记录、46个属性集和1个标记列来表明ICSI治疗后妊娠成功或失败。这些数据来自巴勒斯坦的Razan不孕不育中心。ICSI数据集仅包含在决定ICSI治疗之前已知的临床特征。该数据集包含46个特征，其中5个独立特征具有分类值，12个为数值，3个为字符串，26个为二进制。结果显示，RF算法的AUC得分最高，为0.97，其次是NN算法，得分为0.95，RIMARC算法得分为0.92。AUC是一种广泛用于评估二元分类模型性能的度量。因此，从AUC分数来看，似乎RF算法在评估指标方面优于其他两种算法。在我们的分析中采用的方法显示了相当大的前景，实用性和普遍性，推动了生育治疗的进步，并最终提高了夫妇实现其理想家庭目标的机会。

{"title":"Comparing machine learning approaches for predicting the success of ICSI treatment: A study on clinical applications","authors":"Abrar Mohammad , Haneen Awad , Huthaifa I. Ashqar","doi":"10.1016/j.ibmed.2025.100204","DOIUrl":"10.1016/j.ibmed.2025.100204","url":null,"abstract":"<div><div>Intracytoplasmic Sperm Injection (ICSI) is widely used to treat almost all forms of male infertility and to overcome fertilization failure. While ICSI is a powerful procedure, it's also considered quite expensive, which means couples and clinicians have to make informed decisions about whether or not to proceed with this treatment. About 10,036 patient records, 46 attribute sets, and one label column that indicates the success or failure of pregnancy after the ICSI treatment were used to conduct this research. The data were gathered from Razan infertility center in Palestine. The ICSI dataset contains only clinical features that are known prior to deciding on ICSI treatment. The dataset contains 46 features, 5 of the independent features have categorical values, 12 are numerical, 3 are string, and 26 are binary. Based on the results, RF algorithm achieved the highest AUC score of 0.97, followed by the NN with a score of 0.95, and the RIMARC algorithm with a score of 0.92. AUC is a widely used metric for evaluating the performance of binary classification models. Therefore, judging by the AUC scores, it appears that RF algorithm outperformed the other two algorithms in terms of the evaluated metric. The method employed in our analysis demonstrates considerable promise, practicality, and generalizability, driving advancements in fertility treatments and ultimately improving the chances of couples achieving their desired family goals.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"11 ","pages":"Article 100204"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143174353","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}

引用次数: 0