Informatics in Medicine Unlocked最新文献

Development of a neural network system for predicting in-hospital pressure ulcers in spinal trauma patients 神经网络系统预测脊柱创伤患者院内压疮的发展

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-27 DOI: 10.1016/j.imu.2026.101742

Rezvan Raziee , Mohsen Sadeghi-Naini , Zahra Azadmanjir

Background and objectives

This study aimed to developing and to deploying an optimal machine learning model to predict pressure ulcers (PUs) in hospitalized patients with spinal fractures, using data from the National Spinal Cord and Column Injury Registry of Iran (NSCIR-IR).

Methods

Data were from 4326 patients with traumatic spinal fractures. The preprocessing phase was included handling missing values, feature engineering, normalization, and addressing class imbalance (with a 3.4 % PU incidence) using the Synthetic Minority Oversampling Technique (SMOTE). Feature selection was carried out with univariate filtering methods such as ANOVA and chi-square tests, along with the random forest feature importance algorithm. Six traditional machine learning (ML) algorithms and six ensemble models were trained and evaluated using metrics such as the area under the receiver operating characteristic curve (AUC), recall, and Brier score.

Results

The multilayer perceptron neural network (MLP) emerged as the top-performing model, offers advantages for clinical use due to a higher AUC of 0.888 (0.85–0.92), a balanced accuracy, a good recall, calibration, and an acceptable net benefit on the decision curve. Key predictors identified included the ASIA Impairment Scale, the Glasgow Coma Scale score, SCI type, SaO2, and the number of damaged vertebrae. Shapley Additive Explanations (SHAP) analysis further highlighted the directional influence of these factors on PU risk.

Conclusion

The MLP model effectively predicts PU in patients with spinal fractures, outperforming other algorithms. Identified predictors align with clinical insights, are emphasizing the need for targeted preventive measures in hospitals. However, external validation with a larger multicenter cohort is recommended to confirm and to expand upon these findings.

背景和目的本研究旨在利用伊朗国家脊髓和脊柱损伤登记处（NSCIR-IR）的数据，开发和部署一个最佳的机器学习模型来预测脊柱骨折住院患者的压疮（pu）。方法收集4326例外伤性脊柱骨折患者的资料。预处理阶段包括使用合成少数过采样技术（SMOTE）处理缺失值、特征工程、归一化和处理类不平衡（PU发生率为3.4%）。特征选择采用单变量滤波方法，如方差分析和卡方检验，以及随机森林特征重要性算法。六种传统机器学习（ML）算法和六种集成模型进行了训练，并使用诸如接收者工作特征曲线下面积（AUC），召回率和Brier评分等指标进行了评估。结果多层感知器神经网络（MLP）是表现最好的模型，由于其较高的AUC(0.888(0.85-0.92))，平衡的准确性，良好的召回率，校准和决策曲线上可接受的净效益，为临床应用提供了优势。确定的关键预测指标包括ASIA损伤量表、格拉斯哥昏迷量表评分、SCI类型、SaO2和受损椎骨数量。Shapley加性解释（SHAP）分析进一步强调了这些因素对PU风险的方向性影响。结论MLP模型能有效预测脊柱骨折患者的PU，优于其他算法。确定的预测因素与临床见解一致，强调需要在医院采取有针对性的预防措施。然而，建议采用更大的多中心队列进行外部验证，以确认和扩展这些发现。

{"title":"Development of a neural network system for predicting in-hospital pressure ulcers in spinal trauma patients","authors":"Rezvan Raziee , Mohsen Sadeghi-Naini , Zahra Azadmanjir","doi":"10.1016/j.imu.2026.101742","DOIUrl":"10.1016/j.imu.2026.101742","url":null,"abstract":"<div><h3>Background and objectives</h3><div>This study aimed to developing and to deploying an optimal machine learning model to predict pressure ulcers (PUs) in hospitalized patients with spinal fractures, using data from the National Spinal Cord and Column Injury Registry of Iran (NSCIR-IR).</div></div><div><h3>Methods</h3><div>Data were from 4326 patients with traumatic spinal fractures. The preprocessing phase was included handling missing values, feature engineering, normalization, and addressing class imbalance (with a 3.4 % PU incidence) using the Synthetic Minority Oversampling Technique (SMOTE). Feature selection was carried out with univariate filtering methods such as ANOVA and chi-square tests, along with the random forest feature importance algorithm. Six traditional machine learning (ML) algorithms and six ensemble models were trained and evaluated using metrics such as the area under the receiver operating characteristic curve (AUC), recall, and Brier score.</div></div><div><h3>Results</h3><div>The multilayer perceptron neural network (MLP) emerged as the top-performing model, offers advantages for clinical use due to a higher AUC of 0.888 (0.85–0.92), a balanced accuracy, a good recall, calibration, and an acceptable net benefit on the decision curve. Key predictors identified included the ASIA Impairment Scale, the Glasgow Coma Scale score, SCI type, SaO2, and the number of damaged vertebrae. Shapley Additive Explanations (SHAP) analysis further highlighted the directional influence of these factors on PU risk.</div></div><div><h3>Conclusion</h3><div>The MLP model effectively predicts PU in patients with spinal fractures, outperforming other algorithms. Identified predictors align with clinical insights, are emphasizing the need for targeted preventive measures in hospitals. However, external validation with a larger multicenter cohort is recommended to confirm and to expand upon these findings.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"61 ","pages":"Article 101742"},"PeriodicalIF":0.0,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075003","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

Advancement and challenges of reinforcement learning in lung cancer imaging 强化学习在肺癌影像学中的进展与挑战

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-24 DOI: 10.1016/j.imu.2026.101740

Jamin Rahman Jim , Nasif Hannan , Md Apon Riaz Talukder , M.F. Mridha , Md Mohsin Kabir

Understanding how reinforcement learning can be applied to lung cancer imaging is essential for progress in this field. Despite increasing interest, there is a clear lack of focused survey papers that explore this intersection. To fill this gap, we conducted a comprehensive review that brings together current research across several key areas. We began by briefly outlining the primary forms of lung cancer to provide context for their imaging needs. Next, we explored RL algorithms that have been specifically adapted for lung cancer imaging tasks. We also reviewed widely used datasets and preprocessing techniques, highlighting their importance in building effective RL-based models. Furthermore, we analyzed recent state-of-the-art studies, focusing on their experimental setups, results, and limitations. This helped us map out the current research landscape. In addition, we identified major technical and practical challenges facing the field today. Based on our findings, we proposed several directions for future research that could address these gaps. Overall, this review offers a structured and in-depth overview of RL applications in lung cancer imaging, covering cancer types, RL models, datasets, preprocessing methods, current trends, open issues, and future prospects.

了解如何将强化学习应用于肺癌成像对于该领域的进展至关重要。尽管越来越多的人感兴趣，但显然缺乏集中的调查论文来探索这个交叉点。为了填补这一空白，我们进行了一项综合审查，汇集了几个关键领域的当前研究。我们首先简要概述了肺癌的主要形式，为他们的影像学需求提供背景。接下来，我们探索了专门适用于肺癌成像任务的强化学习算法。我们还回顾了广泛使用的数据集和预处理技术，强调了它们在构建有效的基于强化学习的模型中的重要性。此外，我们分析了最近最先进的研究，重点是他们的实验设置，结果和局限性。这有助于我们绘制出当前的研究图景。此外，我们还确定了该领域目前面临的主要技术和实践挑战。基于我们的发现，我们提出了未来研究的几个方向，可以解决这些差距。总体而言，本文对RL在肺癌影像学中的应用进行了结构化和深入的综述，包括癌症类型、RL模型、数据集、预处理方法、当前趋势、有待解决的问题和未来展望。

{"title":"Advancement and challenges of reinforcement learning in lung cancer imaging","authors":"Jamin Rahman Jim , Nasif Hannan , Md Apon Riaz Talukder , M.F. Mridha , Md Mohsin Kabir","doi":"10.1016/j.imu.2026.101740","DOIUrl":"10.1016/j.imu.2026.101740","url":null,"abstract":"<div><div>Understanding how reinforcement learning can be applied to lung cancer imaging is essential for progress in this field. Despite increasing interest, there is a clear lack of focused survey papers that explore this intersection. To fill this gap, we conducted a comprehensive review that brings together current research across several key areas. We began by briefly outlining the primary forms of lung cancer to provide context for their imaging needs. Next, we explored RL algorithms that have been specifically adapted for lung cancer imaging tasks. We also reviewed widely used datasets and preprocessing techniques, highlighting their importance in building effective RL-based models. Furthermore, we analyzed recent state-of-the-art studies, focusing on their experimental setups, results, and limitations. This helped us map out the current research landscape. In addition, we identified major technical and practical challenges facing the field today. Based on our findings, we proposed several directions for future research that could address these gaps. Overall, this review offers a structured and in-depth overview of RL applications in lung cancer imaging, covering cancer types, RL models, datasets, preprocessing methods, current trends, open issues, and future prospects.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"61 ","pages":"Article 101740"},"PeriodicalIF":0.0,"publicationDate":"2026-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075005","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

Overcoming technical barriers in healthcare with blockchain: A systematic review 用b区块链克服医疗保健中的技术障碍：系统回顾

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-24 DOI: 10.1016/j.imu.2026.101741

Diana Costa , Paulo Jorge Coelho , Eftim Zdravevski , Carlos Albuquerque , Ivan Miguel Pires , António Jorge Gouveia

The rising digitalization of healthcare has increased reliance on complex information systems, creating the need for better integration and interoperability. Despite technology developments, healthcare organizations still confront technical challenges that restrict data transmission, scalability, and secure information sharing. This systematic review highlights important technological challenges to healthcare information system integration and examines the potential of blockchain technology to address them. Following PRISMA principles, a structured search of PubMed and Scopus revealed 24 peer-reviewed studies published from 2020 to 2024. The investigation suggests that interoperability restrictions, lack of data and language standardization, scalability challenges, cybersecurity hazards, and insufficient technical expertise are the most significant hurdles. Evidence suggests that blockchain technology can increase data integrity, security, and regulated interoperability through decentralized and permissioned systems. However, obstacles persist involving technical complexity, regulatory compliance, energy consumption, and organizational readiness. This paper highlights current knowledge on technical integration hurdles in healthcare and presents evidence-based insights on the potential role of blockchain in allowing interoperable, safe, and sustainable healthcare information systems.

医疗保健数字化的发展增加了对复杂信息系统的依赖，需要更好的集成和互操作性。尽管技术有所发展，但医疗保健组织仍然面临限制数据传输、可伸缩性和安全信息共享的技术挑战。这篇系统综述强调了医疗保健信息系统集成的重要技术挑战，并研究了区块链技术解决这些挑战的潜力。遵循PRISMA原则，对PubMed和Scopus进行结构化搜索，发现了2020年至2024年发表的24项同行评议研究。调查表明，互操作性限制、缺乏数据和语言标准化、可扩展性挑战、网络安全危害和技术专长不足是最重要的障碍。有证据表明，区块链技术可以通过分散和许可的系统提高数据完整性、安全性和规范的互操作性。然而，障碍仍然存在，包括技术复杂性、法规遵从性、能源消耗和组织准备。本文重点介绍了目前关于医疗保健技术集成障碍的知识，并介绍了区块链在实现可互操作、安全和可持续的医疗保健信息系统中的潜在作用的循证见解。

{"title":"Overcoming technical barriers in healthcare with blockchain: A systematic review","authors":"Diana Costa , Paulo Jorge Coelho , Eftim Zdravevski , Carlos Albuquerque , Ivan Miguel Pires , António Jorge Gouveia","doi":"10.1016/j.imu.2026.101741","DOIUrl":"10.1016/j.imu.2026.101741","url":null,"abstract":"<div><div>The rising digitalization of healthcare has increased reliance on complex information systems, creating the need for better integration and interoperability. Despite technology developments, healthcare organizations still confront technical challenges that restrict data transmission, scalability, and secure information sharing. This systematic review highlights important technological challenges to healthcare information system integration and examines the potential of blockchain technology to address them. Following PRISMA principles, a structured search of PubMed and Scopus revealed 24 peer-reviewed studies published from 2020 to 2024. The investigation suggests that interoperability restrictions, lack of data and language standardization, scalability challenges, cybersecurity hazards, and insufficient technical expertise are the most significant hurdles. Evidence suggests that blockchain technology can increase data integrity, security, and regulated interoperability through decentralized and permissioned systems. However, obstacles persist involving technical complexity, regulatory compliance, energy consumption, and organizational readiness. This paper highlights current knowledge on technical integration hurdles in healthcare and presents evidence-based insights on the potential role of blockchain in allowing interoperable, safe, and sustainable healthcare information systems.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"61 ","pages":"Article 101741"},"PeriodicalIF":0.0,"publicationDate":"2026-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146025321","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

Who's afraid of synthetic data? Hybrid approaches to deliver medical digital twins 谁会害怕合成数据？提供医疗数字双胞胎的混合方法

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-16 DOI: 10.1016/j.imu.2026.101737

Joel Vanin , Amit Hagar , James A. Glazier

Despite rapidly growing volumes of clinical data, precision medicine still faces a structural data deficit: most patients and rare disease variants are sparsely sampled, labels are noisy, and counterfactual outcomes for alternative treatments are fundamentally unobservable. This position paper argues that overcoming these limits will require hybrid systems that couple multiscale virtual tissue models, synthetic data generation, and AI/ML within risk-aware digital twin frameworks. Using a structured narrative synthesis of three literatures—synthetic health data, virtual tissues and medical digital twins, and hybrid mechanistic–AI architectures including numerical weather prediction—we develop a conceptual framework centered on a mechanistic core linked to AI via forward (mechanistic → synthetic data → AI), backward (AI → mechanistic), and closed (patient-anchored digital twin) loops. We analyze how complex-systems behavior, biological adaptability, and sparse observations bound what medical digital twins can meaningfully predict, motivating ensemble and population-level forecasts rather than exact individual replicas. We then survey emerging implementation patterns, parameter-space exploration methods, and computational envelopes for using virtual tissues to generate biologically constrained synthetic cohorts and to calibrate hybrid digital twins. Finally, we adapt risk- and context-informed verification, validation, and governance frameworks to a four-layer stack spanning mechanistic cores, synthetic data products, AI components, and clinical workflows, with explicit attention to bias, drift, and provenance. We conclude that near-term impact is most likely from population- and cohort-level digital twins that support stratification and short-horizon decision support, while laying the groundwork for more individualized, trustworthy hybrids as biological and methodological uncertainties are better characterized.

尽管临床数据量迅速增长，但精准医学仍然面临结构性数据缺陷：大多数患者和罕见疾病变异样本稀疏，标签嘈杂，替代治疗的反事实结果从根本上无法观察到。本文认为，克服这些限制需要混合系统，将多尺度虚拟组织模型、合成数据生成和风险感知数字孪生框架内的AI/ML结合起来。使用三种文献的结构化叙事综合-合成健康数据，虚拟组织和医疗数字双胞胎，以及包括数值天气预报在内的混合机械-人工智能架构-我们开发了一个以机械核心为中心的概念框架，通过向前（机械→合成数据→人工智能），向后（人工智能→机械）和封闭（患者锚定的数字双胞胎）循环与人工智能联系在一起。我们分析了复杂系统行为、生物适应性和稀疏观察如何限制医学数字双胞胎能够有意义的预测，激励整体和群体水平的预测，而不是精确的个体复制品。然后，我们调查了新兴的实现模式，参数空间探索方法，以及使用虚拟组织生成生物约束合成队列和校准混合数字双胞胎的计算信封。最后，我们将风险和上下文知情的验证、验证和治理框架调整为四层堆栈，涵盖机制核心、合成数据产品、人工智能组件和临床工作流程，并明确关注偏差、漂移和来源。我们的结论是，短期影响最有可能来自人口和群体水平的数字双胞胎，它们支持分层和短期决策支持，同时为更个性化、更可靠的杂交奠定基础，因为生物学和方法上的不确定性得到了更好的表征。

{"title":"Who's afraid of synthetic data? Hybrid approaches to deliver medical digital twins","authors":"Joel Vanin , Amit Hagar , James A. Glazier","doi":"10.1016/j.imu.2026.101737","DOIUrl":"10.1016/j.imu.2026.101737","url":null,"abstract":"<div><div>Despite rapidly growing volumes of clinical data, precision medicine still faces a structural data deficit: most patients and rare disease variants are sparsely sampled, labels are noisy, and counterfactual outcomes for alternative treatments are fundamentally unobservable. This position paper argues that overcoming these limits will require hybrid systems that couple multiscale virtual tissue models, synthetic data generation, and AI/ML within risk-aware digital twin frameworks. Using a structured narrative synthesis of three literatures—synthetic health data, virtual tissues and medical digital twins, and hybrid mechanistic–AI architectures including numerical weather prediction—we develop a conceptual framework centered on a mechanistic core linked to AI via forward (mechanistic → synthetic data → AI), backward (AI → mechanistic), and closed (patient-anchored digital twin) loops. We analyze how complex-systems behavior, biological adaptability, and sparse observations bound what medical digital twins can meaningfully predict, motivating ensemble and population-level forecasts rather than exact individual replicas. We then survey emerging implementation patterns, parameter-space exploration methods, and computational envelopes for using virtual tissues to generate biologically constrained synthetic cohorts and to calibrate hybrid digital twins. Finally, we adapt risk- and context-informed verification, validation, and governance frameworks to a four-layer stack spanning mechanistic cores, synthetic data products, AI components, and clinical workflows, with explicit attention to bias, drift, and provenance. We conclude that near-term impact is most likely from population- and cohort-level digital twins that support stratification and short-horizon decision support, while laying the groundwork for more individualized, trustworthy hybrids as biological and methodological uncertainties are better characterized.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"61 ","pages":"Article 101737"},"PeriodicalIF":0.0,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146025397","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

Integrating knowledge graph embeddings with clinical data: A case study on Acute Kidney Injury prediction 知识图嵌入与临床数据的整合：急性肾损伤预测的案例研究

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-14 DOI: 10.1016/j.imu.2026.101734

Samuele Buosi , Mohan Timilsina , Conor Judge , Edward Curry

The integration of artificial intelligence (AI) and machine learning (ML) in healthcare has significantly advanced predictive analytics. Acute Kidney Injury (AKI), a condition marked by sudden kidney function loss, necessitates early intervention to improve patient outcomes. This study introduces a novel approach that leverages knowledge graph embeddings (KGE) to enhance the predictive accuracy of ML models for AKI detection. Knowledge graphs (KGs) model entities and their interrelations in a graph format, integrating heterogeneous data sources to provide a comprehensive view of complex biological systems. The AI contribution lies in the application of embedding techniques that transform these graphs into continuous vector spaces, improving the ability to capture semantic similarities and infer new relationships within the data.

On the engineering side, we applied this AI-driven approach to healthcare by leveraging the Medical Information Mart for Intensive Care (MIMIC) III dataset to construct a KG, generate embeddings, and incorporate them into ML models for AKI prediction. This engineering application aims to demonstrate the utility of KGEs in clinical settings. Our approach involved extracting patient features, generating KGE, and training various models, such as those utilizing complex, translational, holographic, and multiplicative embeddings. The models were evaluated through ranking-based and binary classification protocols. The transparency of the AI models enhances their trustworthiness in clinical practice, and the findings underscore the need for continued collaboration with clinicians to refine these techniques and ensure successful deployment in healthcare.

人工智能（AI）和机器学习（ML）在医疗保健领域的集成显著推进了预测分析。急性肾损伤（AKI）是一种以突然肾功能丧失为特征的疾病，需要早期干预以改善患者的预后。本研究引入了一种利用知识图嵌入（KGE）来提高AKI检测的ML模型预测准确性的新方法。知识图谱（Knowledge graphs, KGs）以图形形式对实体及其相互关系进行建模，整合异构数据源，提供复杂生物系统的全面视图。人工智能的贡献在于应用嵌入技术，将这些图转换为连续向量空间，提高捕获语义相似性和推断数据中新关系的能力。在工程方面，我们利用重症监护医疗信息市场（MIMIC） III数据集，将这种人工智能驱动的方法应用于医疗保健，构建KG，生成嵌入，并将其合并到ML模型中用于AKI预测。这个工程应用旨在展示kge在临床环境中的效用。我们的方法包括提取患者特征、生成KGE和训练各种模型，例如使用复杂、平移、全息和乘法嵌入的模型。通过基于排序和二元分类协议对模型进行评价。人工智能模型的透明度增强了其在临床实践中的可信度，研究结果强调了与临床医生继续合作以完善这些技术并确保在医疗保健领域成功部署的必要性。

{"title":"Integrating knowledge graph embeddings with clinical data: A case study on Acute Kidney Injury prediction","authors":"Samuele Buosi , Mohan Timilsina , Conor Judge , Edward Curry","doi":"10.1016/j.imu.2026.101734","DOIUrl":"10.1016/j.imu.2026.101734","url":null,"abstract":"<div><div>The integration of artificial intelligence (AI) and machine learning (ML) in healthcare has significantly advanced predictive analytics. Acute Kidney Injury (AKI), a condition marked by sudden kidney function loss, necessitates early intervention to improve patient outcomes. This study introduces a novel approach that leverages knowledge graph embeddings (KGE) to enhance the predictive accuracy of ML models for AKI detection. Knowledge graphs (KGs) model entities and their interrelations in a graph format, integrating heterogeneous data sources to provide a comprehensive view of complex biological systems. The AI contribution lies in the application of embedding techniques that transform these graphs into continuous vector spaces, improving the ability to capture semantic similarities and infer new relationships within the data.</div><div>On the engineering side, we applied this AI-driven approach to healthcare by leveraging the Medical Information Mart for Intensive Care (MIMIC) III dataset to construct a KG, generate embeddings, and incorporate them into ML models for AKI prediction. This engineering application aims to demonstrate the utility of KGEs in clinical settings. Our approach involved extracting patient features, generating KGE, and training various models, such as those utilizing complex, translational, holographic, and multiplicative embeddings. The models were evaluated through ranking-based and binary classification protocols. The transparency of the AI models enhances their trustworthiness in clinical practice, and the findings underscore the need for continued collaboration with clinicians to refine these techniques and ensure successful deployment in healthcare.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"61 ","pages":"Article 101734"},"PeriodicalIF":0.0,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145969415","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

Clinical validation of artificial intelligence for gastrointestinal diseases 人工智能治疗胃肠道疾病的临床验证

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-13 DOI: 10.1016/j.imu.2026.101736

Marjan Talebi , Negar Bozorgchami , Gauransh Mishra , Gaurav Mishra , Rouzbeh Almasi Ghale

Artificial intelligence (AI), particularly deep convolutional neural networks (DCNNs), has demonstrated significant potential for transforming the diagnosis and management of gastrointestinal (GI) diseases. This review critically examines the evolving landscape of AI applications in gastroenterology, moving beyond a simple catalog of tools to analyze their pathway to clinical integration. We synthesize current evidence across key functional domains including computer-aided detection (CADe), computer-aided diagnosis (CADx), and predictive outcome modeling highlighting performance metrics and early clinical adoption. Crucially, we identify a pronounced translational gap between technical validation and demonstrable improvement in patient-centered outcomes. The narrative underscores that while AI systems show high diagnostic accuracy in controlled studies, their ultimate clinical utility remains unproven. The conclusion distills core challenges including the need for rigorous multicenter randomized trials, solutions for algorithmic generalizability, and effective human-AI collaboration and emphasizes the urgent imperative for structured clinical validation frameworks to realize AI's promise in routine GI care. We further synthesize evidence by validation stage and study design, highlighting clinical endpoints such as ADR, APC, and complication rates, with GI Genius and ENDOANGEL exemplifying the gap between technical metrics and patient outcomes.

人工智能（AI），特别是深度卷积神经网络（DCNNs），已经显示出改变胃肠道疾病诊断和管理的巨大潜力。这篇综述批判性地审视了人工智能在胃肠病学应用的发展前景，超越了简单的工具目录，分析了它们的临床整合途径。我们综合了关键功能领域的现有证据，包括计算机辅助检测（CADe）、计算机辅助诊断（CADx）和预测结果建模，突出了性能指标和早期临床采用。至关重要的是，我们发现在技术验证和以患者为中心的结果的明显改善之间存在明显的转化差距。这种说法强调，尽管人工智能系统在对照研究中显示出很高的诊断准确性，但它们的最终临床用途仍未得到证实。结论提炼了核心挑战，包括需要严格的多中心随机试验，算法可推广性的解决方案，以及有效的人类与人工智能协作，并强调迫切需要结构化的临床验证框架，以实现人工智能在常规胃肠道护理中的承诺。我们进一步通过验证阶段和研究设计来综合证据，突出临床终点，如不良反应、APC和并发症发生率，GI Genius和ENDOANGEL举例说明了技术指标与患者结果之间的差距。

{"title":"Clinical validation of artificial intelligence for gastrointestinal diseases","authors":"Marjan Talebi , Negar Bozorgchami , Gauransh Mishra , Gaurav Mishra , Rouzbeh Almasi Ghale","doi":"10.1016/j.imu.2026.101736","DOIUrl":"10.1016/j.imu.2026.101736","url":null,"abstract":"<div><div>Artificial intelligence (AI), particularly deep convolutional neural networks (DCNNs), has demonstrated significant potential for transforming the diagnosis and management of gastrointestinal (GI) diseases. This review critically examines the evolving landscape of AI applications in gastroenterology, moving beyond a simple catalog of tools to analyze their pathway to clinical integration. We synthesize current evidence across key functional domains including computer-aided detection (CADe), computer-aided diagnosis (CADx), and predictive outcome modeling highlighting performance metrics and early clinical adoption. Crucially, we identify a pronounced translational gap between technical validation and demonstrable improvement in patient-centered outcomes. The narrative underscores that while AI systems show high diagnostic accuracy in controlled studies, their ultimate clinical utility remains unproven. The conclusion distills core challenges including the need for rigorous multicenter randomized trials, solutions for algorithmic generalizability, and effective human-AI collaboration and emphasizes the urgent imperative for structured clinical validation frameworks to realize AI's promise in routine GI care. We further synthesize evidence by validation stage and study design, highlighting clinical endpoints such as ADR, APC, and complication rates, with GI Genius and ENDOANGEL exemplifying the gap between technical metrics and patient outcomes.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"61 ","pages":"Article 101736"},"PeriodicalIF":0.0,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146025398","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

Impact assessment of digital ecosystem in healthcare services: A qualitative case study of hospital data management in Bikaner District in India 医疗保健服务中数字生态系统的影响评估：印度比卡内尔地区医院数据管理的定性案例研究

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-10 DOI: 10.1016/j.imu.2026.101735

Nikhil Maurya , Arya Veer Singh Chauhan , Inder Puri , Mukesh Kumar Rohil , Sanjay Kumar Kochar , Tanmaya Mahapatra

The proliferation of digitalization, along with advanced computational techniques, in the healthcare ecosystem has expedited the process of patient care, treatment, and disease diagnosis globally. Medical research, especially involving computational techniques, is heavily dependent on the availability of high-quality datasets generated at the point of care for effective translational research. Our study aims to understand the state of the digital ecosystem (i.e., digitalization, usage of electronic health records (EHRs), and medical data) for the purpose of improving healthcare services and research in hospitals. We conducted a questionnaire-based survey at 16 upper-primary health care centers and public hospitals in the district of Bikaner, Rajasthan, India, to understand the current practices of medical data digitalization and data repository development. The survey results have been analyzed using Principal Component Factor Analysis (PCFA) and statistical tests, including Cronbach's Alpha, the Kaiser-Meyer-Olkin (KMO) measure, and Bartlett's test of sampling adequacy, which indicate that the state of digitalization is in its initial phase. Among technical professionals, 35.6 % agreed that digitalization has been implemented, while 12.3 % remained neutral and 52.1 % disagreed. For the same, 41.4 % agreed, 13.0 % remained neutral, and 45.6 % disagreed among non-technical professionals. These highlight that almost half of the groups recognize slow progress in this area, implying that digitalization is still in its initial phase. Our study also indicates that the lack of access to structured and semi-structured medical datasets is a key barrier to applying Artificial Intelligence (AI) and Machine Learning (ML) in Indian healthcare research, where these technologies could play a crucial role in improving healthcare diagnostics, outcome prediction, and enhancing clinical decision-making, for better healthcare services, esp. in resource-constrained settings.

在医疗保健生态系统中，数字化的普及以及先进的计算技术加快了全球患者护理、治疗和疾病诊断的进程。医学研究，特别是涉及计算技术的医学研究，严重依赖于在护理点生成的高质量数据集的可用性，以便进行有效的转化研究。我们的研究旨在了解数字生态系统的状态（即数字化，电子健康记录（EHRs）和医疗数据的使用），以改善医院的医疗服务和研究。我们对印度拉贾斯坦邦Bikaner地区的16家高级初级卫生保健中心和公立医院进行了问卷调查，以了解当前医疗数据数字化和数据存储库开发的实践。利用主成分因子分析（PCFA）和统计检验（包括Cronbach's Alpha、Kaiser-Meyer-Olkin （KMO）测量和Bartlett抽样充分性检验）对调查结果进行了分析，表明数字化的状态处于初级阶段。在技术专业人士中，35.6%的人同意数字化已经实施，而12.3%的人保持中立，52.1%的人不同意。同样，41.4%的人同意，13.0%保持中立，45.6%的非技术专业人员不同意。这些数据突出表明，几乎一半的集团认识到这一领域的进展缓慢，这意味着数字化仍处于初级阶段。我们的研究还表明，缺乏对结构化和半结构化医疗数据集的访问是在印度医疗保健研究中应用人工智能（AI）和机器学习（ML）的关键障碍，这些技术可以在改善医疗保健诊断、结果预测和加强临床决策方面发挥关键作用，以获得更好的医疗保健服务，特别是在资源受限的环境中。

{"title":"Impact assessment of digital ecosystem in healthcare services: A qualitative case study of hospital data management in Bikaner District in India","authors":"Nikhil Maurya , Arya Veer Singh Chauhan , Inder Puri , Mukesh Kumar Rohil , Sanjay Kumar Kochar , Tanmaya Mahapatra","doi":"10.1016/j.imu.2026.101735","DOIUrl":"10.1016/j.imu.2026.101735","url":null,"abstract":"<div><div>The proliferation of digitalization, along with advanced computational techniques, in the healthcare ecosystem has expedited the process of patient care, treatment, and disease diagnosis globally. Medical research, especially involving computational techniques, is heavily dependent on the availability of high-quality datasets generated at the point of care for effective translational research. Our study aims to understand the state of the digital ecosystem (i.e., digitalization, usage of electronic health records (EHRs), and medical data) for the purpose of improving healthcare services and research in hospitals. We conducted a questionnaire-based survey at 16 upper-primary health care centers and public hospitals in the district of Bikaner, Rajasthan, India, to understand the current practices of medical data digitalization and data repository development. The survey results have been analyzed using Principal Component Factor Analysis (PCFA) and statistical tests, including Cronbach's Alpha, the Kaiser-Meyer-Olkin (KMO) measure, and Bartlett's test of sampling adequacy, which indicate that the state of digitalization is in its initial phase. Among technical professionals, 35.6 % agreed that digitalization has been implemented, while 12.3 % remained neutral and 52.1 % disagreed. For the same, 41.4 % agreed, 13.0 % remained neutral, and 45.6 % disagreed among non-technical professionals. These highlight that almost half of the groups recognize slow progress in this area, implying that digitalization is still in its initial phase. Our study also indicates that the lack of access to structured and semi-structured medical datasets is a key barrier to applying Artificial Intelligence (AI) and Machine Learning (ML) in Indian healthcare research, where these technologies could play a crucial role in improving healthcare diagnostics, outcome prediction, and enhancing clinical decision-making, for better healthcare services, esp. in resource-constrained settings.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"61 ","pages":"Article 101735"},"PeriodicalIF":0.0,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145969414","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

Interpretable deep learning for rotator cuff tear diagnosis: A novel convolutional neural network with Grad-CAM visualization on MRI 可解释的深度学习用于肩袖撕裂诊断：一种新的卷积神经网络与MRI上的Grad-CAM可视化

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-06 DOI: 10.1016/j.imu.2026.101733

Mohammad Amin Esfandiari , Iman Ahanian , Ali Broumandnia , Nader Jafarnia Dabanloo

Accurate diagnosis of rotator cuff tears from magnetic resonance imaging (MRI) is essential for effective clinical management and treatment planning. In this study, we propose a novel convolutional neural network (CNN) architecture specifically designed for classifying rotator cuff tears, integrated with gradient-weighted class activation mapping (Grad-CAM) to provide interpretable insights into the model's decision-making process. We utilized MRI data from 150 subjects, equally divided between normal and pathological cases, and applied data augmentation techniques, including rotation, scaling, and reflection, to enhance model generalization. The proposed CNN demonstrated superior performance, achieving an average accuracy of 94.5 %, sensitivity of 94.6 %, precision of 94.1 %, and specificity of 93.4 %, outperforming established lightweight models such as MobileNetV2 and SqueezeNet. Grad-CAM visualizations confirmed that the model accurately focused on anatomically relevant regions associated with tendon ruptures, thereby enhancing trust in its predictions. These results underscore the potential of our interpretable deep learning framework to deliver reliable, transparent, and clinically actionable diagnostic support for shoulder injuries, paving the way for improved decision-making in orthopedic care. This approach highlights the synergy of advanced CNN design and explainable AI for robust medical imaging applications.

通过磁共振成像（MRI）准确诊断肩袖撕裂对于有效的临床管理和治疗计划至关重要。在这项研究中，我们提出了一种新颖的卷积神经网络（CNN）架构，专门用于对肩袖撕裂进行分类，并与梯度加权类激活映射（Grad-CAM）相结合，为模型的决策过程提供可解释的见解。我们利用150名受试者的MRI数据，将正常病例和病理病例平均划分，并应用数据增强技术，包括旋转、缩放和反射，以增强模型的泛化。所提出的CNN表现出优异的性能，平均准确率为94.5%，灵敏度为94.6%，精度为94.1%，特异性为93.4%，优于已建立的轻量级模型，如MobileNetV2和SqueezeNet。Grad-CAM可视化证实了该模型准确地聚焦于与肌腱断裂相关的解剖相关区域，从而增强了其预测的可信度。这些结果强调了我们可解释的深度学习框架在为肩伤提供可靠、透明和临床可操作的诊断支持方面的潜力，为改善骨科护理决策铺平了道路。这种方法强调了先进的CNN设计和可解释的人工智能在强大的医学成像应用中的协同作用。

{"title":"Interpretable deep learning for rotator cuff tear diagnosis: A novel convolutional neural network with Grad-CAM visualization on MRI","authors":"Mohammad Amin Esfandiari , Iman Ahanian , Ali Broumandnia , Nader Jafarnia Dabanloo","doi":"10.1016/j.imu.2026.101733","DOIUrl":"10.1016/j.imu.2026.101733","url":null,"abstract":"<div><div>Accurate diagnosis of rotator cuff tears from magnetic resonance imaging (MRI) is essential for effective clinical management and treatment planning. In this study, we propose a novel convolutional neural network (CNN) architecture specifically designed for classifying rotator cuff tears, integrated with gradient-weighted class activation mapping (Grad-CAM) to provide interpretable insights into the model's decision-making process. We utilized MRI data from 150 subjects, equally divided between normal and pathological cases, and applied data augmentation techniques, including rotation, scaling, and reflection, to enhance model generalization. The proposed CNN demonstrated superior performance, achieving an average accuracy of 94.5 %, sensitivity of 94.6 %, precision of 94.1 %, and specificity of 93.4 %, outperforming established lightweight models such as MobileNetV2 and SqueezeNet. Grad-CAM visualizations confirmed that the model accurately focused on anatomically relevant regions associated with tendon ruptures, thereby enhancing trust in its predictions. These results underscore the potential of our interpretable deep learning framework to deliver reliable, transparent, and clinically actionable diagnostic support for shoulder injuries, paving the way for improved decision-making in orthopedic care. This approach highlights the synergy of advanced CNN design and explainable AI for robust medical imaging applications.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"61 ","pages":"Article 101733"},"PeriodicalIF":0.0,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075113","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

A joint frailty model to assess the relationship between time to curative treatment and biochemical recurrence in prostate cancer patients 一个评估前列腺癌患者治愈时间与生化复发关系的关节衰弱模型

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-01 DOI: 10.1016/j.imu.2025.101727

Abderrahim Oussama Batouche , Denis Rustand , Eugen Czeizler , Håvard Rue , Tuomas Mirtti , Antti Rannikko

Objective:

Conflicting evidence exists regarding the effect of delaying prostate cancer (PCa) treatment on outcomes after curative treatment. Ideally, modelling this would require a joint analysis of the time to treatment initiation and the time to PCa recurrence. However, traditional Cox models are limited to analysing a single time-to-event outcome. In this study, we build a joint frailty model to assess the effect of delayed or expedited primary curative treatment (surgery or radiotherapy) on the risk of biochemical recurrence (BCR).

Methods:

We used HUS (Helsinki Metropolitan Hospital District) data lake for data mining and to categorise PCa patients by Gleason grade group (1-5), treatment, and biochemical recurrence for a final sample size of n=9934 patients (1993–2019). A broader definition of BCR was established considering secondary treatments as an additional indicator of relapse alongside traditional PSA cut-offs. We applied the INLA method for Bayesian inference, utilising the INLAJoint R package, to fit a shared frailty joint survival model. This model was used to analyse the relationship between the time from diagnosis to curative treatment (treatment risk) and the time from diagnosis to biochemical recurrence (relapse risk).

Results:

Conditional on covariates, including age at diagnosis and Gleason grade group, our joint survival model revealed a significant association

γ

= -1.32 [-1.50, -1.14] between the risk of treatment and risk of BCR. As an example, regardless of the grade group, patients within the top 5% with the lowest risk of receiving treatment (i.e., the longest time to treatment) exhibited an HR=5.27 [4.28, 6.62] fold (increased) risk of recurrence compared to the average patient.

Conclusion:

We successfully employed a joint frailty model to simultaneously model the effect of time to curative primary treatment on time to biochemical recurrence. We show that the time to curative treatment is associated with the risk of relapse. Patients of the same age, same diagnostic PSA, and same grade group who are treated early are less likely to develop biochemical recurrence.

目的：关于延迟前列腺癌（PCa）治疗对治愈性治疗后预后的影响，存在相互矛盾的证据。理想情况下，建模这将需要联合分析开始治疗的时间和PCa复发的时间。然而，传统的Cox模型仅限于分析单一的时间到事件的结果。在这项研究中，我们建立了一个关节脆弱模型来评估延迟或加速初级治愈治疗（手术或放疗）对生化复发（BCR）风险的影响。方法：我们使用HUS（赫尔辛基大都会医院区）数据湖进行数据挖掘，并根据Gleason分级组（1-5）、治疗和生化复发对PCa患者进行分类，最终样本量为n=9934例患者（1993-2019）。BCR的更广泛的定义被建立，考虑到二次治疗作为复发的附加指标，与传统的PSA切断。我们应用INLA方法进行贝叶斯推理，利用INLAJoint R包，拟合共享脆弱关节生存模型。该模型用于分析从诊断到治愈治疗的时间（治疗风险）与从诊断到生化复发的时间（复发风险）之间的关系。结果：根据协变量，包括诊断年龄和Gleason分级组，我们的联合生存模型显示治疗风险与BCR风险之间存在显著关联γ = -1.32[-1.50, -1.14]。例如，无论分级组如何，接受治疗风险最低（即治疗时间最长）的前5%患者的复发风险比平均患者高5.27[4.28,6.62]倍。结论：我们成功地建立了关节脆弱模型，同时模拟了首次治疗治愈时间对生化复发时间的影响。我们表明，治愈治疗的时间与复发的风险有关。相同年龄、相同诊断PSA、相同分级组的患者早期治疗后发生生化复发的可能性较小。

{"title":"A joint frailty model to assess the relationship between time to curative treatment and biochemical recurrence in prostate cancer patients","authors":"Abderrahim Oussama Batouche , Denis Rustand , Eugen Czeizler , Håvard Rue , Tuomas Mirtti , Antti Rannikko","doi":"10.1016/j.imu.2025.101727","DOIUrl":"10.1016/j.imu.2025.101727","url":null,"abstract":"<div><h3>Objective:</h3><div>Conflicting evidence exists regarding the effect of delaying prostate cancer (PCa) treatment on outcomes after curative treatment. Ideally, modelling this would require a joint analysis of the time to treatment initiation and the time to PCa recurrence. However, traditional Cox models are limited to analysing a single time-to-event outcome. In this study, we build a joint frailty model to assess the effect of delayed or expedited primary curative treatment (surgery or radiotherapy) on the risk of biochemical recurrence (BCR).</div></div><div><h3>Methods:</h3><div>We used HUS (Helsinki Metropolitan Hospital District) data lake for data mining and to categorise PCa patients by Gleason grade group (1-5), treatment, and biochemical recurrence for a final sample size of n=9934 patients (1993–2019). A broader definition of BCR was established considering secondary treatments as an additional indicator of relapse alongside traditional PSA cut-offs. We applied the INLA method for Bayesian inference, utilising the <span>INLAJoint</span> R package, to fit a shared frailty joint survival model. This model was used to analyse the relationship between the time from diagnosis to curative treatment (treatment risk) and the time from diagnosis to biochemical recurrence (relapse risk).</div></div><div><h3>Results:</h3><div>Conditional on covariates, including age at diagnosis and Gleason grade group, our joint survival model revealed a significant association <span><math><mi>γ</mi></math></span> = -1.32 [-1.50, -1.14] between the risk of treatment and risk of BCR. As an example, regardless of the grade group, patients within the top 5% with the lowest risk of receiving treatment (i.e., the longest time to treatment) exhibited an HR=5.27 [4.28, 6.62] fold (increased) risk of recurrence compared to the average patient.</div></div><div><h3>Conclusion:</h3><div>We successfully employed a joint frailty model to simultaneously model the effect of time to curative primary treatment on time to biochemical recurrence. We show that the time to curative treatment is associated with the risk of relapse. Patients of the same age, same diagnostic PSA, and same grade group who are treated early are less likely to develop biochemical recurrence.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101727"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921551","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

PAL-Net: A point-wise CNN with patch-attention for 3D anatomical facial landmark localization PAL-Net：一种具有斑块注意的点向CNN，用于三维解剖面部地标定位

Q1 Medicine

Informatics in Medicine Unlocked

Pub Date : 2026-01-01 DOI: 10.1016/j.imu.2025.101729

Ali Shadman Yazdi , Annalisa Cappella , Benedetta Baldini , Riccardo Solazzo , Gianluca Tartaglia , Chiarella Sforza , Giuseppe Baselli

Manual annotation of anatomical landmarks on 3D facial scans is a time-consuming and expertise-dependent task, yet it remains critical for clinical assessments, morphometric analysis, and craniofacial research. While several deep learning methods have been proposed for facial landmark localization, most focus on pseudo-landmarks or require complex input representations, limiting their clinical applicability. This study presents a fully automated deep learning pipeline (PAL-Net) for localizing 50 anatomical landmarks on facial models acquired via stereo-photogrammetry. The method combines coarse alignment, region-of-interest filtering, and an initial landmark approximation with a patch-based pointwise CNN enhanced by attention mechanisms. Trained and evaluated on 214 annotated scans from healthy adults, PAL-Net achieved a mean localization error of 3.686 mm and preserved relevant anatomical distances with an average error of 2.822 mm. While the geometric error exceeds expert intra-observer variability, the distance-wise error maintains structural integrity sufficient for high-throughput anthropometric analysis. To assess generalization, the model was further evaluated on 700 subjects from the FaceScape dataset, achieving a mean localization error of 0.41 mm and a distance error of 0.38 mm. Comparing with existing methods, PAL-Net offers a favorable trade-off between accuracy and computational cost. While performance degrades in regions with poor mesh quality (e.g., ears, hairline), the method demonstrates consistent accuracy across most anatomical regions. PAL-Net generalizes effectively across datasets and facial regions, outperforming existing methods in both point-wise and structural evaluations. It provides a lightweight, scalable solution for high-throughput 3D anthropometric analysis, with potential to support clinical workflows and reduce reliance on manual annotation. Source code can be accessed at https://github.com/Ali5hadman/PAL-Net-A-Point-Wise-CNN-with-Patch-Attention.

在3D面部扫描上手动标注解剖标志是一项耗时且依赖专业知识的任务，但它对于临床评估、形态计量分析和颅面研究仍然至关重要。虽然已经提出了几种用于面部地标定位的深度学习方法，但大多数方法都侧重于伪地标或需要复杂的输入表示，限制了它们的临床适用性。本研究提出了一种全自动深度学习管道（PAL-Net），用于定位通过立体摄影测量获得的面部模型上的50个解剖地标。该方法将粗对齐、感兴趣区域过滤和初始地标近似与基于补丁的点向CNN相结合，并通过注意机制增强。PAL-Net对214张健康成人带注释的扫描图进行了训练和评估，平均定位误差为3.686 mm，保留相关解剖距离的平均误差为2.822 mm。虽然几何误差超过了专家内部观察者的可变性，但距离误差保持了结构完整性，足以进行高通量人体测量分析。为了评估该模型的泛化程度，我们对来自FaceScape数据集的700名受试者进行了进一步评估，平均定位误差为0.41 mm，距离误差为0.38 mm。与现有方法相比，PAL-Net在精度和计算成本之间提供了良好的平衡。虽然在网格质量较差的区域（如耳朵、发际线）性能会下降，但该方法在大多数解剖区域显示出一致的准确性。PAL-Net有效地泛化了数据集和面部区域，在点和结构评估方面都优于现有方法。它为高通量3D人体测量分析提供了一种轻量级、可扩展的解决方案，具有支持临床工作流程和减少对手动注释依赖的潜力。源代码可以在https://github.com/Ali5hadman/PAL-Net-A-Point-Wise-CNN-with-Patch-Attention上访问。

{"title":"PAL-Net: A point-wise CNN with patch-attention for 3D anatomical facial landmark localization","authors":"Ali Shadman Yazdi , Annalisa Cappella , Benedetta Baldini , Riccardo Solazzo , Gianluca Tartaglia , Chiarella Sforza , Giuseppe Baselli","doi":"10.1016/j.imu.2025.101729","DOIUrl":"10.1016/j.imu.2025.101729","url":null,"abstract":"<div><div>Manual annotation of anatomical landmarks on 3D facial scans is a time-consuming and expertise-dependent task, yet it remains critical for clinical assessments, morphometric analysis, and craniofacial research. While several deep learning methods have been proposed for facial landmark localization, most focus on pseudo-landmarks or require complex input representations, limiting their clinical applicability. This study presents a fully automated deep learning pipeline (PAL-Net) for localizing 50 anatomical landmarks on facial models acquired via stereo-photogrammetry. The method combines coarse alignment, region-of-interest filtering, and an initial landmark approximation with a patch-based pointwise CNN enhanced by attention mechanisms. Trained and evaluated on 214 annotated scans from healthy adults, PAL-Net achieved a mean localization error of 3.686 mm and preserved relevant anatomical distances with an average error of 2.822 mm. While the geometric error exceeds expert intra-observer variability, the distance-wise error maintains structural integrity sufficient for high-throughput anthropometric analysis. To assess generalization, the model was further evaluated on 700 subjects from the FaceScape dataset, achieving a mean localization error of 0.41 mm and a distance error of 0.38 mm. Comparing with existing methods, PAL-Net offers a favorable trade-off between accuracy and computational cost. While performance degrades in regions with poor mesh quality (e.g., ears, hairline), the method demonstrates consistent accuracy across most anatomical regions. PAL-Net generalizes effectively across datasets and facial regions, outperforming existing methods in both point-wise and structural evaluations. It provides a lightweight, scalable solution for high-throughput 3D anthropometric analysis, with potential to support clinical workflows and reduce reliance on manual annotation. Source code can be accessed at <span><span>https://github.com/Ali5hadman/PAL-Net-A-Point-Wise-CNN-with-Patch-Attention</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"60 ","pages":"Article 101729"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921552","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