International Journal of Medical Informatics最新文献_第6页

Pathologist-level diagnosis of ulcerative colitis inflammatory activity level using an automated histological grading method 使用自动组织学分级法在病理学家层面诊断溃疡性结肠炎的炎症活动水平

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-10-09 DOI: 10.1016/j.ijmedinf.2024.105648

Chengfei Cai , Qianyun Shi , Jun Li , Yiping Jiao , Andi Xu , Yangshu Zhou , Xiangxue Wang , Chunyan Peng , Xiaoqi Zhang , Xiaobin Cui , Jun Chen , Jun Xu , Qi Sun

Background and Aims

Inflammatory bowel disease (IBD) is a global disease that is evolving with increasing incidence. However, there are few works on computationally assisted diagnosis of IBD based on pathological images. Therefore, based on the UK and Chinese IBD diagnostic guidelines, our study established an artificial intelligence-assisted diagnostic system for histologic grading of inflammatory activity in ulcerative colitis (UC).

Methods

We proposed an efficient deep-learning (DL) method for grading inflammatory activity in whole-slide images (WSIs) of UC pathology. Our model was constructed using 603 UC WSIs from Nanjing Drum Tower Hospital for model train set and internal test set. We collected 212 UC WSIs from Zhujiang Hospital as an external test set. Initially, the pre-trained ResNet50 model on the ImageNet dataset was employed to extract image patch features from UC patients. Subsequently, a multi-instance learning (MIL) approach with embedded self-attention was utilized to aggregate tissue image patch features, representing the entire WSI. Finally, the model was trained based on the aggregated features and WSI annotations provided by senior gastrointestinal pathologists to predict the level of inflammatory activity in UC WSIs.

Results

In the task of distinguishing the presence or absence of inflammatory activity, the Area Under Curve (AUC) value in the internal test set is 0.863 (95% confidence interval [CI] 0.829, 0.898), with a sensitivity of 0.913 (95% [CI] 0.866, 0.961), and specificity of 0.816 (95% [CI] 0.771, 0.861). The AUC in the external test set is 0.947 (95% confidence interval [CI] 0.939, 0.955), with a sensitivity of 0.889 (905% [CI] 0.837, 0.940), and specificity of 0.858 (95% [CI] 0.777, 0.939). For distinguishing different levels of inflammatory activity in UC, the average Macro-AUC in the internal test set and the external test set are 0.827 (95% [CI] 0.803, 0.850) and 0.908 (95% [CI] 0.882, 0.935). the average Micro-AUC in the internal test set and the external test set are 0.816 (95% [CI] 0.792, 0.840) and 0.898 (95% [CI] 0.869, 0.926).

Conclusions

Comparative analysis with diagnoses made by pathologists at different expertise levels revealed that the algorithm reached a proficiency comparable to the pathologist with 5 years of experience. Furthermore, our algorithm performed superior to other MIL algorithms.

背景和目的炎症性肠病（IBD）是一种全球性疾病，其发病率正在不断上升。然而，基于病理图像的 IBD 计算辅助诊断工作却很少。因此，根据英国和中国的 IBD 诊断指南，我们的研究建立了一个人工智能辅助诊断系统，用于对溃疡性结肠炎（UC）的炎症活动进行组织学分级。我们使用南京鼓楼医院的 603 张 UC WSI 图像构建了模型训练集和内部测试集。我们还收集了珠江医院的 212 张 UC WSI 作为外部测试集。最初，我们使用在 ImageNet 数据集上预先训练好的 ResNet50 模型来提取 UC 患者的图像斑块特征。随后，利用具有嵌入式自我关注的多实例学习（MIL）方法来聚合组织图像斑块特征，从而代表整个 WSI。最后，根据聚合特征和资深胃肠道病理学家提供的 WSI 注释对模型进行训练，以预测 UC WSI 的炎症活动水平。结果在区分是否存在炎症活动的任务中，内部测试集的曲线下面积（AUC）值为 0.863（95% 置信区间 [CI] 0.829，0.898），灵敏度为 0.913（95% [CI] 0.866，0.961），特异性为 0.816（95% [CI] 0.771，0.861）。外部测试集的 AUC 为 0.947（95% 置信区间 [CI] 0.939，0.955），灵敏度为 0.889（905% [CI] 0.837，0.940），特异性为 0.858（95% [CI] 0.777，0.939）。为了区分 UC 中不同程度的炎症活动，内部测试集和外部测试集中的平均宏观 AUC 分别为 0.827 (95% [CI] 0.803, 0.850) 和 0.908 (95% [CI] 0.882, 0.935)。结论与不同专业水平的病理学家的诊断结果进行比较分析后发现，该算法的熟练程度可与拥有 5 年经验的病理学家媲美。此外，我们的算法还优于其他 MIL 算法。

{"title":"Pathologist-level diagnosis of ulcerative colitis inflammatory activity level using an automated histological grading method","authors":"Chengfei Cai , Qianyun Shi , Jun Li , Yiping Jiao , Andi Xu , Yangshu Zhou , Xiangxue Wang , Chunyan Peng , Xiaoqi Zhang , Xiaobin Cui , Jun Chen , Jun Xu , Qi Sun","doi":"10.1016/j.ijmedinf.2024.105648","DOIUrl":"10.1016/j.ijmedinf.2024.105648","url":null,"abstract":"<div><h3>Background and Aims</h3><div>Inflammatory bowel disease (IBD) is a global disease that is evolving with increasing incidence. However, there are few works on computationally assisted diagnosis of IBD based on pathological images. Therefore, based on the UK and Chinese IBD diagnostic guidelines, our study established an artificial intelligence-assisted diagnostic system for histologic grading of inflammatory activity in ulcerative colitis (UC).</div></div><div><h3>Methods</h3><div>We proposed an efficient deep-learning (DL) method for grading inflammatory activity in whole-slide images (WSIs) of UC pathology. Our model was constructed using 603 UC WSIs from Nanjing Drum Tower Hospital for model train set and internal test set. We collected 212 UC WSIs from Zhujiang Hospital as an external test set. Initially, the pre-trained ResNet50 model on the ImageNet dataset was employed to extract image patch features from UC patients. Subsequently, a multi-instance learning (MIL) approach with embedded self-attention was utilized to aggregate tissue image patch features, representing the entire WSI. Finally, the model was trained based on the aggregated features and WSI annotations provided by senior gastrointestinal pathologists to predict the level of inflammatory activity in UC WSIs.</div></div><div><h3>Results</h3><div>In the task of distinguishing the presence or absence of inflammatory activity, the Area Under Curve (AUC) value in the internal test set is 0.863 (95% confidence interval [CI] 0.829, 0.898), with a sensitivity of 0.913 (95% [CI] 0.866, 0.961), and specificity of 0.816 (95% [CI] 0.771, 0.861). The AUC in the external test set is 0.947 (95% confidence interval [CI] 0.939, 0.955), with a sensitivity of 0.889 (905% [CI] 0.837, 0.940), and specificity of 0.858 (95% [CI] 0.777, 0.939). For distinguishing different levels of inflammatory activity in UC, the average Macro-AUC in the internal test set and the external test set are 0.827 (95% [CI] 0.803, 0.850) and 0.908 (95% [CI] 0.882, 0.935). the average Micro-AUC in the internal test set and the external test set are 0.816 (95% [CI] 0.792, 0.840) and 0.898 (95% [CI] 0.869, 0.926).</div></div><div><h3>Conclusions</h3><div>Comparative analysis with diagnoses made by pathologists at different expertise levels revealed that the algorithm reached a proficiency comparable to the pathologist with 5 years of experience. Furthermore, our algorithm performed superior to other MIL algorithms.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105648"},"PeriodicalIF":3.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142425742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Prediction of pre-eclampsia with machine learning approaches: Leveraging important information from routinely collected data 利用机器学习方法预测先兆子痫：利用日常收集数据中的重要信息。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-10-05 DOI: 10.1016/j.ijmedinf.2024.105645

Sofonyas Abebaw Tiruneh , Daniel Lorber Rolnik , Helena J. Teede , Joanne Enticott

Background

Globally, pre-eclampsia (PE) is a leading cause of maternal and perinatal morbidity and mortality. PE prediction using routinely collected data has the advantage of being widely applicable, particularly in low-resource settings. Early intervention for high-risk women might reduce PE incidence and related complications. We aimed to replicate our machine learning (ML) published work predicting another maternal condition (gestational diabetes) to (1) predict PE using routine health data, (2) identify the optimal ML model, and (3) compare it with logistic regression approach.

Methods

Data were from a large health service network with 48,250 singleton pregnancies between January 2016 and June 2021. Supervised ML models were employed. Maternal clinical and medical characteristics were the feature variables (predictors), and a 70/30 data split was used for training and testing the model. Predictive performance was assessed using area under the curve (AUC) and calibration plots. Shapley value analysis assessed the contribution of feature variables.

Results

The random forest approach provided excellent discrimination with an AUC of 0.84 (95% CI: 0.82–0.86) and highest prediction accuracy (0.79); however, the calibration curve (slope of 1.21, 95% CI 1.13–1.30) was acceptable only for a threshold of 0.3 or less. The next best approach was extreme gradient boosting, which provided an AUC of 0.77 (95% CI: 0.76–0.79) and well-calibrated (slope of 0.93, 95% CI 0.85–1.01). Logistic regression provided good discrimination performance with an AUC of 0.75 (95% CI: 0.74–0.76) and perfect calibration. Nulliparous, pre-pregnancy body mass index, previous pregnancy with prior PE, maternal age, family history of hypertension, and pre-existing hypertension and diabetes were the top-ranked features in Shapley value analysis.

Conclusion

Two ML models created the highest-performing prediction using routinely collected data to identify women at high risk of PE, with acceptable discrimination. However, to confirm this result and also examine model generalisability, external validation studies are needed in other settings, utilising standardised prognostic factors.

背景：在全球范围内，子痫前期（PE）是孕产妇和围产期发病率和死亡率的主要原因。利用常规收集的数据进行子痫前期预测具有广泛的适用性，尤其是在资源匮乏的环境中。对高危产妇进行早期干预可降低 PE 的发病率和相关并发症。我们的目标是复制我们已发表的预测另一种孕产妇疾病（妊娠糖尿病）的机器学习（ML）工作，(1) 利用常规健康数据预测 PE，(2) 确定最佳 ML 模型，(3) 将其与逻辑回归方法进行比较：数据来自一个大型医疗服务网络，其中包括 2016 年 1 月至 2021 年 6 月期间的 48,250 例单胎妊娠。采用了有监督的 ML 模型。孕产妇的临床和医疗特征是特征变量（预测因子），模型的训练和测试采用 70/30 的数据分配比例。预测性能通过曲线下面积（AUC）和校准图进行评估。沙普利值分析评估了特征变量的贡献：随机森林方法提供了极佳的分辨能力，AUC 为 0.84（95% CI：0.82-0.86），预测准确率最高（0.79）；然而，校准曲线（斜率为 1.21，95% CI 为 1.13-1.30）仅在阈值为 0.3 或更低时可以接受。其次是极梯度提升法，其 AUC 为 0.77（95% CI：0.76-0.79），校准良好（斜率为 0.93，95% CI 为 0.85-1.01）。逻辑回归具有良好的分辨性能，AUC 为 0.75（95% CI：0.74-0.76），校准完美。在 Shapley 值分析中，无子宫、孕前体重指数、既往妊娠合并 PE、孕产妇年龄、高血压家族史、既往高血压和糖尿病是排名靠前的特征：结论：利用常规收集的数据识别 PE 高危妇女，两个 ML 模型的预测效果最好，且具有可接受的区分度。不过，为了证实这一结果并检验模型的通用性，还需要在其他环境中利用标准化的预后因素进行外部验证研究。

{"title":"Prediction of pre-eclampsia with machine learning approaches: Leveraging important information from routinely collected data","authors":"Sofonyas Abebaw Tiruneh , Daniel Lorber Rolnik , Helena J. Teede , Joanne Enticott","doi":"10.1016/j.ijmedinf.2024.105645","DOIUrl":"10.1016/j.ijmedinf.2024.105645","url":null,"abstract":"<div><h3>Background</h3><div>Globally, pre-eclampsia (PE) is a leading cause of maternal and perinatal morbidity and mortality. PE prediction using routinely collected data has the advantage of being widely applicable, particularly in low-resource settings. Early intervention for high-risk women might reduce PE incidence and related complications. We aimed to replicate our machine learning (ML) published work predicting another maternal condition (gestational diabetes) to (1) predict PE using routine health data, (2) identify the optimal ML model, and (3) compare it with logistic regression approach.</div></div><div><h3>Methods</h3><div>Data were from a large health service network with 48,250 singleton pregnancies between January 2016 and June 2021. Supervised ML models were employed. Maternal clinical and medical characteristics were the feature variables (predictors), and a 70/30 data split was used for training and testing the model. Predictive performance was assessed using area under the curve (AUC) and calibration plots. Shapley value analysis assessed the contribution of feature variables.</div></div><div><h3>Results</h3><div>The random forest approach provided excellent discrimination with an AUC of 0.84 (95% CI: 0.82–0.86) and highest prediction accuracy (0.79); however, the calibration curve (slope of 1.21, 95% CI 1.13–1.30) was acceptable only for a threshold of 0.3 or less. The next best approach was extreme gradient boosting, which provided an AUC of 0.77 (95% CI: 0.76–0.79) and well-calibrated (slope of 0.93, 95% CI 0.85–1.01). Logistic regression provided good discrimination performance with an AUC of 0.75 (95% CI: 0.74–0.76) and perfect calibration. Nulliparous, pre-pregnancy body mass index, previous pregnancy with prior PE, maternal age, family history of hypertension, and pre-existing hypertension and diabetes were the top-ranked features in Shapley value analysis.</div></div><div><h3>Conclusion</h3><div>Two ML models created the highest-performing prediction using routinely collected data to identify women at high risk of PE, with acceptable discrimination. However, to confirm this result and also examine model generalisability, external validation studies are needed in other settings, utilising standardised prognostic factors.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105645"},"PeriodicalIF":3.7,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142407214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CureMate: A clinical decision support system for breast cancer treatment CureMate：乳腺癌治疗临床决策支持系统。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-10-05 DOI: 10.1016/j.ijmedinf.2024.105647

Rodrigo Martín Gómez Del Moral Herranz , María Jesús López Rodríguez , Alexander P. Seiffert , Javier Soto Pérez-Olivares , Miguel Chiva De Agustín , Patricia Sánchez-González

Background

Breast Cancer (BC) poses significant challenges in treatment decision-making. Multiple first treatment lines are currently available, determined by several patient-specific factors that need to be considered in the decision-making process.

Purpose

To present CureMate, a Clinical Decision Support System to predict the most effective initial treatment for BC patients. Different artificial intelligence models based on demographic, anatomopathological and magnetic resonance imaging variables are studied. CureMate’s web application allows for easy use of the best model.

Methods

A database of 232 BCE patients, each described by 29 variables, was established. Out of four machine learning algorithms, specifically Decision Tree Classifier (DTC), Gaussian Naïve Bayes (GNB), k-Nearest Neighbor (K-NN), and Support Vector Machine (SVM), the most suitable model for the task was identified, optimized and independently tested.

Results

SVM was identified as the best model for BC treatment planning, resulting in a test accuracy of 0.933. CureMate’s web application, including the SVM model, allows for introducing the relevant patient variables and displays the suggested first treatment step, as well as a diagram of the following steps.

Conclusion

The results demonstrate CureMate’s high accuracy and effectiveness in clinical settings, indicating its potential to aid practitioners in making informed therapeutic decisions.

背景：乳腺癌（BC）给治疗决策带来了巨大挑战。目的：介绍临床决策支持系统 CureMate，该系统可预测乳腺癌患者最有效的初始治疗方案。研究了基于人口统计学、解剖病理学和磁共振成像变量的不同人工智能模型。CureMate的网络应用程序可以方便地使用最佳模型：方法：建立了一个包含 232 名 BCE 患者的数据库，每个患者由 29 个变量描述。在四种机器学习算法中，即决策树分类器 (DTC)、高斯奈夫贝叶斯 (GNB)、k-近邻 (K-NN) 和支持向量机 (SVM) 中，确定了最适合该任务的模型，并对其进行了优化和独立测试：结果：SVM 被确定为 BC 治疗计划的最佳模型，测试准确率为 0.933。包括 SVM 模型在内的 CureMate 网络应用程序允许引入相关的患者变量，并显示建议的第一步治疗步骤以及后续步骤的图表：结果表明，CureMate 在临床环境中具有很高的准确性和有效性，这表明它具有帮助医生做出明智治疗决定的潜力。

{"title":"CureMate: A clinical decision support system for breast cancer treatment","authors":"Rodrigo Martín Gómez Del Moral Herranz , María Jesús López Rodríguez , Alexander P. Seiffert , Javier Soto Pérez-Olivares , Miguel Chiva De Agustín , Patricia Sánchez-González","doi":"10.1016/j.ijmedinf.2024.105647","DOIUrl":"10.1016/j.ijmedinf.2024.105647","url":null,"abstract":"<div><h3>Background</h3><div>Breast Cancer (BC) poses significant challenges in treatment decision-making. Multiple first treatment lines are currently available, determined by several patient-specific factors that need to be considered in the decision-making process.</div></div><div><h3>Purpose</h3><div>To present CureMate, a Clinical Decision Support System to predict the most effective initial treatment for BC patients. Different artificial intelligence models based on demographic, anatomopathological and magnetic resonance imaging variables are studied. CureMate’s web application allows for easy use of the best model.</div></div><div><h3>Methods</h3><div>A database of 232 BCE patients, each described by 29 variables, was established. Out of four machine learning algorithms, specifically Decision Tree Classifier (DTC), Gaussian Naïve Bayes (GNB), k-Nearest Neighbor (K-NN), and Support Vector Machine (SVM), the most suitable model for the task was identified, optimized and independently tested.</div></div><div><h3>Results</h3><div>SVM was identified as the best model for BC treatment planning, resulting in a test accuracy of 0.933. CureMate’s web application, including the SVM model, allows for introducing the relevant patient variables and displays the suggested first treatment step, as well as a diagram of the following steps.</div></div><div><h3>Conclusion</h3><div>The results demonstrate CureMate’s high accuracy and effectiveness in clinical settings, indicating its potential to aid practitioners in making informed therapeutic decisions.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105647"},"PeriodicalIF":3.7,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142407211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

HERALD: A domain-specific query language for longitudinal health data analytics HERALD：用于纵向健康数据分析的特定领域查询语言。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-10-05 DOI: 10.1016/j.ijmedinf.2024.105646

Lena Baum, Marco Johns, Armin Müller, Hammam Abu Attieh, Fabian Prasser

Background

Large-scale health data has significant potential for research and innovation, especially with longitudinal data offering insights into prevention, disease progression, and treatment effects. Yet, analyzing this data type is complex, as data points are repeatedly documented along the timeline. As a consequence, extracting cross-sectional tabular data suitable for statistical analysis and machine learning can be challenging for medical researchers and data scientists alike, with existing tools lacking balance between ease-of-use and comprehensiveness.

Objective

This paper introduces HERALD, a novel domain-specific query language designed to support the transformation of longitudinal health data into cross-sectional tables. We describe the basic concepts, the query syntax, a graphical user interface for constructing and executing HERALD queries, as well as an integration into Informatics for Integrating Biology and the Bedside (i2b2).

Methods

The syntax of HERALD mimics natural language and supports different query types for selection, aggregation, analysis of relationships, and searching for data points based on filter expressions and temporal constraints. Using a hierarchical concept model, queries are executed individually for the data of each patient, while constructing tabular output. HERALD is closed, meaning that queries process data points and generate data points. Queries can refer to data points that have been produced by previous queries, providing a simple, but powerful nesting mechanism.

Results

The open-source implementation consists of a HERALD query parser, an execution engine, as well as a web-based user interface for query construction and statistical analysis. The implementation can be deployed as a standalone component and integrated into self-service data analytics environments like i2b2 as a plugin. HERALD can be valuable tool for data scientists and machine learning experts, as it simplifies the process of transforming longitudinal health data into tables and data matrices.

Conclusion

The construction of cross-sectional tables from longitudinal data can be supported through dedicated query languages that strike a reasonable balance between language complexity and transformation capabilities.

背景：大规模健康数据在研究和创新方面具有巨大的潜力，尤其是纵向数据能为预防、疾病进展和治疗效果提供洞察力。然而，分析这种数据类型非常复杂，因为数据点是沿着时间轴重复记录的。因此，对于医学研究人员和数据科学家来说，提取适合统计分析和机器学习的横截面表格数据具有挑战性，现有工具在易用性和全面性之间缺乏平衡：本文介绍了 HERALD，这是一种新颖的特定领域查询语言，旨在支持将纵向健康数据转换为横截面表格。我们介绍了 HERALD 的基本概念、查询语法、用于构建和执行 HERALD 查询的图形用户界面，以及与整合生物学和床旁信息学（i2b2）的集成：HERALD 的语法模仿自然语言，支持不同的查询类型，包括选择、聚合、关系分析，以及根据过滤表达式和时间限制搜索数据点。利用分层概念模型，对每个病人的数据单独执行查询，同时构建表格输出。HERALD 是封闭的，这意味着查询可处理数据点并生成数据点。查询可以引用之前查询生成的数据点，从而提供了一个简单但功能强大的嵌套机制：开源实现包括一个 HERALD 查询解析器、一个执行引擎，以及一个用于查询构建和统计分析的基于网络的用户界面。该实现可作为独立组件部署，也可作为插件集成到 i2b2 等自助服务数据分析环境中。HERALD 可以简化将纵向健康数据转换为表格和数据矩阵的过程，是数据科学家和机器学习专家的宝贵工具：结论：通过专用的查询语言，可以支持从纵向数据构建横截面表格，这种语言在语言复杂性和转换能力之间取得了合理的平衡。

{"title":"HERALD: A domain-specific query language for longitudinal health data analytics","authors":"Lena Baum, Marco Johns, Armin Müller, Hammam Abu Attieh, Fabian Prasser","doi":"10.1016/j.ijmedinf.2024.105646","DOIUrl":"10.1016/j.ijmedinf.2024.105646","url":null,"abstract":"<div><h3>Background</h3><div>Large-scale health data has significant potential for research and innovation, especially with longitudinal data offering insights into prevention, disease progression, and treatment effects. Yet, analyzing this data type is complex, as data points are repeatedly documented along the timeline. As a consequence, extracting cross-sectional tabular data suitable for statistical analysis and machine learning can be challenging for medical researchers and data scientists alike, with existing tools lacking balance between ease-of-use and comprehensiveness.</div></div><div><h3>Objective</h3><div>This paper introduces HERALD, a novel domain-specific query language designed to support the transformation of longitudinal health data into cross-sectional tables. We describe the basic concepts, the query syntax, a graphical user interface for constructing and executing HERALD queries, as well as an integration into Informatics for Integrating Biology and the Bedside (i2b2).</div></div><div><h3>Methods</h3><div>The syntax of HERALD mimics natural language and supports different query types for selection, aggregation, analysis of relationships, and searching for data points based on filter expressions and temporal constraints. Using a hierarchical concept model, queries are executed individually for the data of each patient, while constructing tabular output. HERALD is closed, meaning that queries process data points and generate data points. Queries can refer to data points that have been produced by previous queries, providing a simple, but powerful nesting mechanism.</div></div><div><h3>Results</h3><div>The open-source implementation consists of a HERALD query parser, an execution engine, as well as a web-based user interface for query construction and statistical analysis. The implementation can be deployed as a standalone component and integrated into self-service data analytics environments like i2b2 as a plugin. HERALD can be valuable tool for data scientists and machine learning experts, as it simplifies the process of transforming longitudinal health data into tables and data matrices.</div></div><div><h3>Conclusion</h3><div>The construction of cross-sectional tables from longitudinal data can be supported through dedicated query languages that strike a reasonable balance between language complexity and transformation capabilities.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105646"},"PeriodicalIF":3.7,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142407213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unleashing innovation in first-line healthcare: The barriers to realizing platform openness 在一线医疗保健领域实现创新：实现平台开放的障碍。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-10-03 DOI: 10.1016/j.ijmedinf.2024.105643

Gijs van der Wielen , Antragama Ewa Abbas , Mark de Reuver

Purpose

Digital platforms are essential for fostering innovation in first-line healthcare. These platforms require openness, allowing external parties to utilize, enhance, or profit from them. Yet, knowledge about barriers to realizing platform openness is lacking. This research investigates the barriers to realizing platform openness in first-line healthcare.

Method

This research employed a qualitative exploratory approach. We collected data through thirteen semi-structured interviews with platform experts, application developers, and healthcare practitioners. As a study setting, we focused on Dutch first-line healthcare. We then analyzed the data using thematic analysis.

Result

We identify barriers in three main categories that hinder platform openness: technology-related (e.g., redundancy in development work), business-related (e.g., profit-maximizing strategy), and healthcare-related (e.g., reluctance to change).

Scientific contribution

We contribute to the platform literature in medical informatics by being among the first to examine openness barriers that hinder platform-based innovation. We thus explain why platform implementations often do not result in substantial improvements in healthcare delivery despite their transformative impact in other industries.

目的：数字平台对于促进一线医疗保健的创新至关重要。这些平台需要开放，允许外部人员利用、改进或从中获利。然而，人们对实现平台开放性的障碍还缺乏了解。本研究调查了在一线医疗保健领域实现平台开放的障碍：本研究采用了定性探索方法。我们通过对平台专家、应用程序开发人员和医疗从业人员进行 13 次半结构化访谈收集数据。作为研究背景，我们重点关注荷兰的一线医疗保健。然后，我们使用主题分析法对数据进行了分析：结果：我们发现了三大类阻碍平台开放的障碍：与技术相关的障碍（如开发工作中的冗余）、与业务相关的障碍（如利润最大化战略）以及与医疗相关的障碍（如不愿改变）：我们首次研究了阻碍基于平台的创新的开放性障碍，为医学信息学领域的平台文献做出了贡献。因此，我们解释了为什么尽管平台实施在其他行业产生了变革性影响，但却往往无法实质性地改善医疗服务。

{"title":"Unleashing innovation in first-line healthcare: The barriers to realizing platform openness","authors":"Gijs van der Wielen , Antragama Ewa Abbas , Mark de Reuver","doi":"10.1016/j.ijmedinf.2024.105643","DOIUrl":"10.1016/j.ijmedinf.2024.105643","url":null,"abstract":"<div><h3>Purpose</h3><div>Digital platforms are essential for fostering innovation in first-line healthcare. These platforms require openness, allowing external parties to utilize, enhance, or profit from them. Yet, knowledge about barriers to realizing platform openness is lacking. This research investigates the barriers to realizing platform openness in first-line healthcare.</div></div><div><h3>Method</h3><div>This research employed a qualitative exploratory approach. We collected data through thirteen semi-structured interviews with platform experts, application developers, and healthcare practitioners. As a study setting, we focused on Dutch first-line healthcare. We then analyzed the data using thematic analysis.</div></div><div><h3>Result</h3><div>We identify barriers in three main categories that hinder platform openness: technology-related (e.g., redundancy in development work), business-related (e.g., profit-maximizing strategy), and healthcare-related (e.g., reluctance to change).</div></div><div><h3>Scientific contribution</h3><div>We contribute to the platform literature in medical informatics by being among the first to examine openness barriers that hinder platform-based innovation. We thus explain why platform implementations often do not result in substantial improvements in healthcare delivery despite their transformative impact in other industries.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105643"},"PeriodicalIF":3.7,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142378633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A perspective on integration and outreach: Guiding concepts in the evolution of health informatics 从整合与推广的角度看问题：卫生信息学发展过程中的指导概念。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-10-02 DOI: 10.1016/j.ijmedinf.2024.105638

Marion J. Ball , Gabriela Mustata Wilson , William M. Tierney , Jon Weidanz , Denise Hernandez , George R. Kim , Judith V. Douglas

Background

The National Library of Medicine’s Integrated Academic/Advanced Information Management Systems (IAIMS) initiative played a central role in the evolution of health informatics over the project’s lifetime (1983–2009) and continues to do so.

Aim

Our objective is to demonstrate how IAIMS and two key IAIMS concepts, integration and outreach, have functioned at very different times during this evolutionary process.

Approach

Using a framework drawn from Lorenzi and Stead’s 2021 history of IAIMS, we examine the role of integration and outreach in work at the University of Maryland Baltimore (UMB) in the early 1980s and at the University of Texas Arlington (UTA) in 2020.

Results

Guided by these concepts, UMB implemented a campus-wide information utility, while UTA established a center to accelerate research and innovation.

Conclusions

Outreach and integration have been formative in the evolution of health informatics and will continue to hold their power.

背景：目的：我们的目标是展示IAIMS以及IAIMS的两个关键概念--整合与推广--是如何在这一演变过程中的不同时期发挥作用的：方法：我们利用从洛伦兹（Lorenzi）和斯蒂德（Stead）2021 年 IAIMS 历史中提取的框架，研究了 20 世纪 80 年代早期马里兰大学巴尔的摩分校（UMB）和 2020 年德克萨斯大学阿灵顿分校（UTA）的工作中整合和推广的作用：在这些理念的指导下，马里兰大学实施了一项全校范围的信息实用程序，而德克萨斯大学阿灵顿分校则建立了一个中心来加速研究和创新：结论：拓展和整合在卫生信息学的发展过程中起到了决定性作用，并将继续发挥其力量。

{"title":"A perspective on integration and outreach: Guiding concepts in the evolution of health informatics","authors":"Marion J. Ball , Gabriela Mustata Wilson , William M. Tierney , Jon Weidanz , Denise Hernandez , George R. Kim , Judith V. Douglas","doi":"10.1016/j.ijmedinf.2024.105638","DOIUrl":"10.1016/j.ijmedinf.2024.105638","url":null,"abstract":"<div><h3>Background</h3><div>The National Library of Medicine’s Integrated Academic/Advanced Information Management Systems (IAIMS) initiative played a central role in the evolution of health informatics over the project’s lifetime (1983–2009) and continues to do so.</div></div><div><h3>Aim</h3><div>Our objective is to demonstrate how IAIMS and two key IAIMS concepts, integration and outreach, have functioned at very different times during this evolutionary process.</div></div><div><h3>Approach</h3><div>Using a framework drawn from Lorenzi and Stead’s 2021 history of IAIMS, we examine the role of integration and outreach in work at the University of Maryland Baltimore (UMB) in the early 1980s and at the University of Texas Arlington (UTA) in 2020.</div></div><div><h3>Results</h3><div>Guided by these concepts, UMB implemented a campus-wide information utility, while UTA established a center to accelerate research and innovation.</div></div><div><h3>Conclusions</h3><div>Outreach and integration have been formative in the evolution of health informatics and will continue to hold their power.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105638"},"PeriodicalIF":3.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142407210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Connecting verified databases with clinical practice and the patient’ s experience through omnichannel communication 通过全渠道通信将经过验证的数据库与临床实践和患者体验联系起来

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-09-29 DOI: 10.1016/j.ijmedinf.2024.105639

Leonardo Pellizzoni, Asdrubal Falavigna

Introduction

Patient-reported outcomes (PRO) collect data directly from patients. These data are utilized in clinical practice, helping decision-making. Studies emphasize the importance of omnichannel communication (WhatsApp, e-mail, SMS) with healthcare professionals and patients. Omnichannel communication enables the integration of different communication channels to improve the end-client experience. In addition to the means of communication, the daily practice of professionals requires different activities that can be performed in distinct systems. The existence of various separate systems for other activities in medical practice may result in complexities and bottlenecks in their use by healthcare professionals and patients. Objective: To present the Digital Health Ecosystem (DHE) that unifies scientific research with medical practice in omnichannel communication and mechanisms to verify the authenticity and integrity of the data collected and stored. Methodology: The system requirements and needs were met utilizing the Iconix development methodology. Microsoft Dot Net was used to develop software. Usability, usefulness and user satisfaction with the system were measured using the Post-Study System Usability Questionnaire (PSSUQ). Results: Omnichannel communication was utilized to contact patients and healthcare professionals autonomously. A single system enabled the carrying out of patientreported outcome data collection, telemedicine, image storage, and notes from patient consultations. The data was collected through structured questionnaires via link and chatbot. The functionalities created in the HDE allowed the integrity and authenticity verification of the data collected and stored. Conclusion: Personalized omnichannel communication via links and chatbots using WhatsApp, E-mail, and SMS accelerates autonomous interaction with patients and healthcare professionals. In addition, the structured and non-structured data were stored in the EHD and able to be verified for integrity and authenticity.

导言患者报告结果（PRO）直接从患者那里收集数据。这些数据可用于临床实践，帮助决策制定。研究强调了与医护人员和患者进行全渠道沟通（WhatsApp、电子邮件、短信）的重要性。全渠道沟通能够整合不同的沟通渠道，改善最终客户的体验。除了通信手段外，专业人员的日常工作还需要不同的活动，这些活动可以在不同的系统中进行。医疗实践中的其他活动存在各种不同的系统，这可能会导致医护人员和患者在使用这些系统时遇到复杂性和瓶颈。目标介绍数字医疗生态系统（DHE），该系统将科学研究与医疗实践统一起来，实现全渠道交流，并建立机制来验证所收集和存储数据的真实性和完整性。方法：采用 Iconix 开发方法满足系统要求和需要。使用 Microsoft Dot Net 开发软件。使用 "研究后系统可用性问卷"（PSSUQ）对系统的可用性、实用性和用户满意度进行了测量。结果利用全渠道通信自主联系患者和医护人员。患者报告的结果数据收集、远程医疗、图像存储和患者会诊记录均由单一系统完成。数据是通过链接和聊天机器人的结构化问卷收集的。HDE 中创建的功能可对收集和存储的数据进行完整性和真实性验证。结论通过链接和聊天机器人使用 WhatsApp、电子邮件和短信进行个性化全渠道交流，加快了与患者和医疗保健专业人员的自主互动。此外，结构化和非结构化数据都存储在 EHD 中，并能够验证其完整性和真实性。

{"title":"Connecting verified databases with clinical practice and the patient’ s experience through omnichannel communication","authors":"Leonardo Pellizzoni, Asdrubal Falavigna","doi":"10.1016/j.ijmedinf.2024.105639","DOIUrl":"10.1016/j.ijmedinf.2024.105639","url":null,"abstract":"<div><h3>Introduction</h3><div>Patient-reported outcomes (PRO) collect data directly from patients. These data are utilized in clinical practice, helping decision-making. Studies emphasize the importance of omnichannel communication (WhatsApp, e-mail, SMS) with healthcare professionals and patients. Omnichannel communication enables the integration of different communication channels to improve the end-client experience. In addition to the means of communication, the daily practice of professionals requires different activities that can be performed in distinct systems. The existence of various separate systems for other activities in medical practice may result in complexities and bottlenecks in their use by healthcare professionals and patients. Objective: To present the Digital Health Ecosystem (DHE) that unifies scientific research with medical practice in omnichannel communication and mechanisms to verify the authenticity and integrity of the data collected and stored. Methodology: The system requirements and needs were met utilizing the Iconix development methodology. Microsoft Dot Net was used to develop software. Usability, usefulness and user satisfaction with the system were measured using the Post-Study System Usability Questionnaire (PSSUQ). Results: Omnichannel communication was utilized to contact patients and healthcare professionals autonomously. A single system enabled the carrying out of patientreported outcome data collection, telemedicine, image storage, and notes from patient consultations. The data was collected through structured questionnaires via link and chatbot. The functionalities created in the HDE allowed the integrity and authenticity verification of the data collected and stored. Conclusion: Personalized omnichannel communication via links and chatbots using WhatsApp, E-mail, and SMS accelerates autonomous interaction with patients and healthcare professionals. In addition, the structured and non-structured data were stored in the EHD and able to be verified for integrity and authenticity.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105639"},"PeriodicalIF":3.7,"publicationDate":"2024-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142356930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Commentary on “ Assessing the accuracy and reliability of ChatGPT’s medical responses about thyroid cancer” 关于 "评估 ChatGPT 有关甲状腺癌的医疗回复的准确性和可靠性 "的评论

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-09-28 DOI: 10.1016/j.ijmedinf.2024.105642

Mohammad Jameel Rahmatullah Suhotoo

引用次数: 0

Data quality in hospital information systems: Lessons learned from analyzing 30 years of patient data in a regional German hospital 医院信息系统的数据质量：分析德国一家地区医院 30 年病人数据的经验教训。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-09-24 DOI: 10.1016/j.ijmedinf.2024.105636

Stefan Förstel , Markus Förstel , Markus Gallistl , Dario Zanca , Bjoern M. Eskofier , Eva M. Rothgang

Background: The integration of Hospital Information Systems (HIS) into healthcare delivery has significantly enhanced patient care and operational efficiency. Nonetheless, the rapid acceleration of digital transformation has led to a substantial increase in the volume of data managed by these systems. This emphasizes the need for robust mechanisms for data management and quality assurance.

Objective: This study addresses data quality issues related to patient identifiers within the Hospital Information System (HIS) of a regional German hospital, focusing on improving the accuracy and consistency of these administrative data entries.

Methods: Employing a combination of data analysis and expert interviews, this study reviews and programmatically cleanses a dataset with over 2,000,000 patient data entries extracted from the HIS. The areas of investigation are patient admissions, discharges, and geographical data.

Results: The analysis revealed that roughly 25% of the dataset was rendered unusable by errors and inconsistencies. By implementing a thorough data cleansing process, we significantly enhanced the utility of the dataset. In doing so, we identified the primary issues affecting data quality, including ambiguities among similar variables and a gap between the intended and actual use of the system.

Conclusion: The findings highlight the critical importance of enhancing data quality in healthcare information systems. This study shows the necessity of a careful review of data extracted from the HIS before it can be reliably utilized for machine learning tasks, thereby rendering the data more usable for both clinical and analytical purposes.

背景：医院信息系统（HIS）与医疗保健服务的整合大大提高了患者护理和运营效率。然而，数字化转型的迅猛发展导致这些系统管理的数据量大幅增加。这就强调了建立健全的数据管理和质量保证机制的必要性：本研究探讨了德国一家地区医院的医院信息系统（HIS）中与患者标识符相关的数据质量问题，重点是提高这些管理数据条目的准确性和一致性：本研究采用数据分析和专家访谈相结合的方法，对从 HIS 中提取的超过 2,000,000 条患者数据进行了审查和程序化清理。调查领域包括病人入院、出院和地理数据：分析结果显示，大约 25% 的数据集因错误和不一致而无法使用。通过实施彻底的数据清理流程，我们大大提高了数据集的实用性。在此过程中，我们发现了影响数据质量的主要问题，包括类似变量之间的歧义以及系统预期用途与实际用途之间的差距：研究结果凸显了提高医疗信息系统数据质量的重要性。这项研究表明，有必要对从医疗信息系统中提取的数据进行仔细审查，然后才能将其可靠地用于机器学习任务，从而使数据更适用于临床和分析目的。

{"title":"Data quality in hospital information systems: Lessons learned from analyzing 30 years of patient data in a regional German hospital","authors":"Stefan Förstel , Markus Förstel , Markus Gallistl , Dario Zanca , Bjoern M. Eskofier , Eva M. Rothgang","doi":"10.1016/j.ijmedinf.2024.105636","DOIUrl":"10.1016/j.ijmedinf.2024.105636","url":null,"abstract":"<div><div><em>Background</em>: The integration of Hospital Information Systems (HIS) into healthcare delivery has significantly enhanced patient care and operational efficiency. Nonetheless, the rapid acceleration of digital transformation has led to a substantial increase in the volume of data managed by these systems. This emphasizes the need for robust mechanisms for data management and quality assurance.</div><div><em>Objective</em>: This study addresses data quality issues related to patient identifiers within the Hospital Information System (HIS) of a regional German hospital, focusing on improving the accuracy and consistency of these administrative data entries.</div><div><em>Methods</em>: Employing a combination of data analysis and expert interviews, this study reviews and programmatically cleanses a dataset with over 2,000,000 patient data entries extracted from the HIS. The areas of investigation are patient admissions, discharges, and geographical data.</div><div><em>Results</em>: The analysis revealed that roughly 25% of the dataset was rendered unusable by errors and inconsistencies. By implementing a thorough data cleansing process, we significantly enhanced the utility of the dataset. In doing so, we identified the primary issues affecting data quality, including ambiguities among similar variables and a gap between the intended and actual use of the system.</div><div><em>Conclusion</em>: The findings highlight the critical importance of enhancing data quality in healthcare information systems. This study shows the necessity of a careful review of data extracted from the HIS before it can be reliably utilized for machine learning tasks, thereby rendering the data more usable for both clinical and analytical purposes.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105636"},"PeriodicalIF":3.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142367520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A conversational agent for enhanced Self-Management after cardiothoracic surgery 加强心胸手术后自我管理的对话代理

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-09-24 DOI: 10.1016/j.ijmedinf.2024.105640

Ana Martins , Luís Velez Lapão , Isabel L. Nunes , Ana Paula Giordano , Helena Semedo , Clara Vital , Raquel Silva , Pedro Coelho , Ana Londral

Background

Enhanced self-management is crucial for long-term survival following cardiothoracic surgery.

Objectives

This study aimed to develop a conversational agent to enhance patient self-management after cardiothoracic surgery.

Methodology

The solution was designed and implemented following the Design Science Research Methodology. A pilot study was conducted at the hospital to assess the feasibility, usability, and perceived effectiveness of the solution. Feedback was gathered to inform further interactions. Additionally, a focus group with clinicians was conducted to evaluate the acceptability of the solution, integrating insights from the pilot study.

Results

The conversational agent, implemented using a rule-based model, was successfully tested with patients in the cardiothoracic surgery unit (n = 4). Patients received one month of text messages reinforcing clinical team recommendations on a healthy diet and regular physical activity. The system received a high usability score, and two patients suggested adding a feature to answer user prompts for future improvements. The focus group feedback indicated that while the solution met the initial requirements, further testing with a larger patient cohort is necessary to establish personalized profiles. Moreover, clinicians recommended that future iterations prioritize enhanced personalization and interoperability with other hospital platforms. Additionally, while the use of artificial generative intelligence was seen as relevant for content personalization, clinicians expressed concerns regarding content safety, highlighting the necessity for rigorous testing.

Conclusions

This study marks a significant step towards enhancing post-cardiothoracic surgery care through conversational agents. The integration of a diversity of stakeholder knowledge enriches the solution, grants ownership and ensures its sustainability. Future research should focus on automating message generation and delivery based on patient data and environmental factors. While the integration of artificial generative intelligence holds promise for enhancing patient interaction, ensuring the safety of its content is essential.

背景加强自我管理对心胸外科手术后的长期生存至关重要。研究目的本研究旨在开发一种对话代理，以加强心胸外科手术后患者的自我管理。在医院进行了试点研究，以评估解决方案的可行性、可用性和感知效果。收集的反馈意见为进一步的互动提供了依据。此外，还与临床医生进行了一次焦点小组讨论，以评估解决方案的可接受性，并将试点研究中获得的见解进行了整合。患者收到了一个月的短信，强化了临床团队关于健康饮食和定期体育锻炼的建议。该系统获得了较高的可用性评分，两名患者建议增加回答用户提示的功能，以便今后改进。焦点小组的反馈表明，虽然该解决方案满足了最初的要求，但仍有必要在更大的患者群体中进行进一步测试，以建立个性化档案。此外，临床医生建议，未来的迭代应优先考虑增强个性化和与其他医院平台的互操作性。此外，虽然人工生成智能的使用被认为与内容个性化相关，但临床医生对内容的安全性表示担忧，强调了严格测试的必要性。整合利益相关者的各种知识丰富了解决方案，赋予了自主权并确保了其可持续性。未来的研究应侧重于根据患者数据和环境因素自动生成和传递信息。虽然人工生成智能的整合有望增强与患者的互动，但确保其内容的安全性至关重要。

{"title":"A conversational agent for enhanced Self-Management after cardiothoracic surgery","authors":"Ana Martins , Luís Velez Lapão , Isabel L. Nunes , Ana Paula Giordano , Helena Semedo , Clara Vital , Raquel Silva , Pedro Coelho , Ana Londral","doi":"10.1016/j.ijmedinf.2024.105640","DOIUrl":"10.1016/j.ijmedinf.2024.105640","url":null,"abstract":"<div><h3>Background</h3><div>Enhanced self-management is crucial for long-term survival following cardiothoracic surgery.</div></div><div><h3>Objectives</h3><div>This study aimed to develop a conversational agent to enhance patient self-management after cardiothoracic surgery.</div></div><div><h3>Methodology</h3><div>The solution was designed and implemented following the Design Science Research Methodology. A pilot study was conducted at the hospital to assess the feasibility, usability, and perceived effectiveness of the solution. Feedback was gathered to inform further interactions. Additionally, a focus group with clinicians was conducted to evaluate the acceptability of the solution, integrating insights from the pilot study.</div></div><div><h3>Results</h3><div>The conversational agent, implemented using a rule-based model, was successfully tested with patients in the cardiothoracic surgery unit (n = 4). Patients received one month of text messages reinforcing clinical team recommendations on a healthy diet and regular physical activity. The system received a high usability score, and two patients suggested adding a feature to answer user prompts for future improvements. The focus group feedback indicated that while the solution met the initial requirements, further testing with a larger patient cohort is necessary to establish personalized profiles. Moreover, clinicians recommended that future iterations prioritize enhanced personalization and interoperability with other hospital platforms. Additionally, while the use of artificial generative intelligence was seen as relevant for content personalization, clinicians expressed concerns regarding content safety, highlighting the necessity for rigorous testing.</div></div><div><h3>Conclusions</h3><div>This study marks a significant step towards enhancing post-cardiothoracic surgery care through conversational agents. The integration of a diversity of stakeholder knowledge enriches the solution, grants ownership and ensures its sustainability. Future research should focus on automating message generation and delivery based on patient data and environmental factors. While the integration of artificial generative intelligence holds promise for enhancing patient interaction, ensuring the safety of its content is essential.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"192 ","pages":"Article 105640"},"PeriodicalIF":3.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1386505624003034/pdfft?md5=3f8741712ca7df049bcf7ce1e5d11a08&pid=1-s2.0-S1386505624003034-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0