Methods of Information in Medicine最新文献

{"title":"Semantic Textual Similarity in Japanese Clinical Domain Texts Using BERT.","authors":"Faith Wavinya Mutinda, Shuntaro Yada, Shoko Wakamiya, Eiji Aramaki","doi":"10.1055/s-0041-1731390","DOIUrl":"10.1055/s-0041-1731390","url":null,"abstract":"<p><strong>Background: </strong>Semantic textual similarity (STS) captures the degree of semantic similarity between texts. It plays an important role in many natural language processing applications such as text summarization, question answering, machine translation, information retrieval, dialog systems, plagiarism detection, and query ranking. STS has been widely studied in the general English domain. However, there exists few resources for STS tasks in the clinical domain and in languages other than English, such as Japanese.</p><p><strong>Objective: </strong>The objective of this study is to capture semantic similarity between Japanese clinical texts (Japanese clinical STS) by creating a Japanese dataset that is publicly available.</p><p><strong>Materials: </strong>We created two datasets for Japanese clinical STS: (1) Japanese case reports (CR dataset) and (2) Japanese electronic medical records (EMR dataset). The CR dataset was created from publicly available case reports extracted from the CiNii database. The EMR dataset was created from Japanese electronic medical records.</p><p><strong>Methods: </strong>We used an approach based on bidirectional encoder representations from transformers (BERT) to capture the semantic similarity between the clinical domain texts. BERT is a popular approach for transfer learning and has been proven to be effective in achieving high accuracy for small datasets. We implemented two Japanese pretrained BERT models: a general Japanese BERT and a clinical Japanese BERT. The general Japanese BERT is pretrained on Japanese Wikipedia texts while the clinical Japanese BERT is pretrained on Japanese clinical texts.</p><p><strong>Results: </strong>The BERT models performed well in capturing semantic similarity in our datasets. The general Japanese BERT outperformed the clinical Japanese BERT and achieved a high correlation with human score (0.904 in the CR dataset and 0.875 in the EMR dataset). It was unexpected that the general Japanese BERT outperformed the clinical Japanese BERT on clinical domain dataset. This could be due to the fact that the general Japanese BERT is pretrained on a wide range of texts compared with the clinical Japanese BERT.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 S 01","pages":"e56-e64"},"PeriodicalIF":1.7,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/79/46/10-1055-s-0041-1731390.PMC8294940.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39164921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging Artificial Intelligence to Improve Chronic Disease Care: Methods and Application to Pharmacotherapy Decision Support for Type-2 Diabetes Mellitus.","authors":"Shinji Tarumi, Wataru Takeuchi, George Chalkidis, Salvador Rodriguez-Loya, Junichi Kuwata, Michael Flynn, Kyle M Turner, Farrant H Sakaguchi, Charlene Weir, Heidi Kramer, David E Shields, Phillip B Warner, Polina Kukhareva, Hideyuki Ban, Kensaku Kawamoto","doi":"10.1055/s-0041-1728757","DOIUrl":"10.1055/s-0041-1728757","url":null,"abstract":"<p><strong>Objectives: </strong>Artificial intelligence (AI), including predictive analytics, has great potential to improve the care of common chronic conditions with high morbidity and mortality. However, there are still many challenges to achieving this vision. The goal of this project was to develop and apply methods for enhancing chronic disease care using AI.</p><p><strong>Methods: </strong>Using a dataset of 27,904 patients with diabetes, an analytical method was developed and validated for generating a treatment pathway graph which consists of models that predict the likelihood of alternate treatment strategies achieving care goals. An AI-driven clinical decision support system (CDSS) integrated with the electronic health record (EHR) was developed by encapsulating the prediction models in an OpenCDS Web service module and delivering the model outputs through a SMART on FHIR (Substitutable Medical Applications and Reusable Technologies on Fast Healthcare Interoperability Resources) web-based dashboard. This CDSS enables clinicians and patients to review relevant patient parameters, select treatment goals, and review alternate treatment strategies based on prediction results.</p><p><strong>Results: </strong>The proposed analytical method outperformed previous machine-learning algorithms on prediction accuracy. The CDSS was successfully integrated with the Epic EHR at the University of Utah.</p><p><strong>Conclusion: </strong>A predictive analytics-based CDSS was developed and successfully integrated with the EHR through standards-based interoperability frameworks. The approach used could potentially be applied to many other chronic conditions to bring AI-driven CDSS to the point of care.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 S 01","pages":"e32-e43"},"PeriodicalIF":1.3,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/31/6d/10-1055-s-0041-1728757.PMC8294941.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38901351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"InspirerMundi-Remote Monitoring of Inhaled Medication Adherence through Objective Verification Based on Combined Image Processing Techniques.","authors":"Pedro Vieira-Marques,&nbsp;Rute Almeida,&nbsp;João F Teixeira,&nbsp;José Valente,&nbsp;Cristina Jácome,&nbsp;Afonso Cachim,&nbsp;Rui Guedes,&nbsp;Ana Pereira,&nbsp;Tiago Jacinto,&nbsp;João A Fonseca","doi":"10.1055/s-0041-1726277","DOIUrl":"https://doi.org/10.1055/s-0041-1726277","url":null,"abstract":"<p><strong>Background: </strong>The adherence to inhaled controller medications is of critical importance for achieving good clinical results in patients with chronic respiratory diseases. Self-management strategies can result in improved health outcomes and reduce unscheduled care and improve disease control. However, adherence assessment suffers from difficulties on attaining a high grade of trustworthiness given that patient self-reports of high-adherence rates are known to be unreliable.</p><p><strong>Objective: </strong>Aiming to increase patient adherence to medication and allow for remote monitoring by health professionals, a mobile gamified application was developed where a therapeutic plan provides insight for creating a patient-oriented self-management system. To allow a reliable adherence measurement, the application includes a novel approach for objective verification of inhaler usage based on real-time video capture of the inhaler's dosage counters.</p><p><strong>Methods: </strong>This approach uses template matching image processing techniques, an off-the-shelf machine learning framework, and was developed to be reusable within other applications. The proposed approach was validated by 24 participants with a set of 12 inhalers models.</p><p><strong>Results: </strong>Performed tests resulted in the correct value identification for the dosage counter in 79% of the registration events with all inhalers and over 90% for the three most widely used inhalers in Portugal. These results show the potential of exploring mobile-embedded capabilities for acquiring additional evidence regarding inhaler adherence.</p><p><strong>Conclusion: </strong>This system helps to bridge the gap between the patient and the health professional. By empowering the first with a tool for disease self-management and medication adherence and providing the later with additional relevant data, it paves the way to a better-informed disease management decision.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 S 01","pages":"e9-e19"},"PeriodicalIF":1.7,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1055/s-0041-1726277","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38921889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and Validation of a Useful Taxonomy of Patient Portals Based on Characteristics of Patient Engagement.","authors":"Michael Glöggler, Elske Ammenwerth","doi":"10.1055/s-0041-1730284","DOIUrl":"10.1055/s-0041-1730284","url":null,"abstract":"<p><strong>Objective: </strong>Taxonomies are classification systems used to reduce complexity and better understand a domain. The present research aims to develop a useful taxonomy for health information managers to classify and compare patient portals based on characteristics appropriate to promote patient engagement. As a result, the taxonomy should contribute to understanding the differences and similarities of the portals. Further, the taxonomy shall support health information managers to more easily define which general type and functionalities of patient portals they need and to select the most suitable solution offered on the market.</p><p><strong>Methods: </strong>We followed the formal taxonomy-building method proposed by Nickerson et al. Based on a literature review, we created a preliminary taxonomy following the conceptional approach of the model. We then evaluated each taxa's appropriateness by analyzing and classifying 17 patient portals offered by software vendors and 11 patient portals offered by health care providers. After each iteration, we examined the achievement of the determined objective and subjective ending conditions.</p><p><strong>Results: </strong>After two conceptional approaches to create our taxonomy, and two empirical approaches to evaluate it, the final taxonomy consists of 20 dimensions and 49 characteristics. To make the taxonomy easy to comprehend, we assigned to the dimensions seven aspects related to patient engagement. These aspects are (1) portal design, (2) management, (3) communication, (4) instruction, (5) self-management, (6) self-determination, and (7) data management. The taxonomy is considered finished and useful after all ending conditions that defined beforehand have been fulfilled. We demonstrated that the taxonomy serves to understand the differences and similarities by comparing patient portals. We call our taxonomy \"Taxonomy of Patient Portals based on Characteristics of Patient Engagement (TOPCOP).\"</p><p><strong>Conclusion: </strong>We developed the first useful taxonomy for health information managers to classify and compare patient portals. The taxonomy is based on characteristics promoting patient engagement. With 20 dimensions and 49 characteristics, our taxonomy is particularly suitable to discriminate among patient portals and can easily be applied to compare portals. The TOPCOP taxonomy enables health information managers to better understand the differences and similarities of patient portals. Further, the taxonomy may help them to define the type and general functionalities needed. But it also supports them in searching and comparing patient portals offered on the market to select the most suitable solution.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 S 01","pages":"e44-e55"},"PeriodicalIF":1.3,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/bb/c4/10-1055-s-0041-1730284.PMC8294937.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39169402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of an Instrument for Assessing the Maturity of Citizens for Consumer Health Informatics in Developing Countries: The Case of Chile, Ghana, and Kosovo.","authors":"Abubakari Yakubu,&nbsp;Fortuna Paloji,&nbsp;Juan Pablo Guerrero Bonnet,&nbsp;Thomas Wetter","doi":"10.1055/s-0041-1731389","DOIUrl":"https://doi.org/10.1055/s-0041-1731389","url":null,"abstract":"<p><strong>Objective: </strong> We aimed to develop a survey instrument to assess the maturity level of consumer health informatics (ConsHI) in low-middle income countries (LMIC).</p><p><strong>Methods: </strong> We deduced items from unified theory of acceptance and use of technology (UTAUT), UTAUT2, patient activation measure (PAM), and ConsHI levels to constitute a pilot instrument. We proposed a total of 78 questions consisting of 14 demographic and 64 related maturity variables using an iterative process. We used a multistage convenient sampling approach to select 351 respondents from all three countries.</p><p><strong>Results: </strong> Our results supported the earlier assertion that mobile devices and technology are standard today than ever, thus confirming that mobile devices have become an essential part of human activities. We used the Wilcoxon Signed-Rank Test (WSRT) and item response theory (IRT) to reduce the ConsHI-related items from 64 to 43. The questionnaire consisted of 10 demographic questions and 43 ConsHI relevant questions on the maturity of citizens for ConsHI in LMIC. Also, the results supported some moderators such as age and gender. Additionally, more demographic items such as marital status, educational level, and location of respondents were validated using IRT and WSRT.</p><p><strong>Conclusion: </strong> We contend that this is the first composite instrument for assessing the maturity of citizens for ConsHI in LMIC. Specifically, it aggregates multiple theoretical models from information systems (UTAUT and UTAUT2) and health (PAM) and the ConsHI level.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 1-02","pages":"62-70"},"PeriodicalIF":1.7,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39164926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Smoothing Corrections for Improving Sample Size Recalculation Rules in Adaptive Group Sequential Study Designs.","authors":"Carolin Herrmann,&nbsp;Geraldine Rauch","doi":"10.1055/s-0040-1721727","DOIUrl":"https://doi.org/10.1055/s-0040-1721727","url":null,"abstract":"<p><strong>Background: </strong>An adequate sample size calculation is essential for designing a successful clinical trial. One way to tackle planning difficulties regarding parameter assumptions required for sample size calculation is to adapt the sample size during the ongoing trial.This can be attained by adaptive group sequential study designs. At a predefined timepoint, the interim effect is tested for significance. Based on the interim test result, the trial is either stopped or continued with the possibility of a sample size recalculation.</p><p><strong>Objectives: </strong>Sample size recalculation rules have different limitations in application like a high variability of the recalculated sample size. Hence, the goal is to provide a tool to counteract this performance limitation.</p><p><strong>Methods: </strong>Sample size recalculation rules can be interpreted as functions of the observed interim effect. Often, a \"jump\" from the first stage's sample size to the maximal sample size at a rather arbitrarily chosen interim effect size is implemented and the curve decreases monotonically afterwards. This jump is one reason for a high variability of the sample size. In this work, we investigate how the shape of the recalculation function can be improved by implementing a smoother increase of the sample size. The design options are evaluated by means of Monte Carlo simulations. Evaluation criteria are univariate performance measures such as the conditional power and sample size as well as a conditional performance score which combines these components.</p><p><strong>Results: </strong>We demonstrate that smoothing corrections can reduce variability in conditional power and sample size as well as they increase the performance with respect to a recently published conditional performance score for medium and large standardized effect sizes.</p><p><strong>Conclusion: </strong>Based on the simulation study, we present a tool that is easily implemented to improve sample size recalculation rules. The approach can be combined with existing sample size recalculation rules described in the literature.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 1-02","pages":"1-8"},"PeriodicalIF":1.7,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1055/s-0040-1721727","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"25417773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Why Is the Electronic Health Record So Challenging for Research and Clinical Care?","authors":"John H Holmes,&nbsp;James Beinlich,&nbsp;Mary R Boland,&nbsp;Kathryn H Bowles,&nbsp;Yong Chen,&nbsp;Tessa S Cook,&nbsp;George Demiris,&nbsp;Michael Draugelis,&nbsp;Laura Fluharty,&nbsp;Peter E Gabriel,&nbsp;Robert Grundmeier,&nbsp;C William Hanson,&nbsp;Daniel S Herman,&nbsp;Blanca E Himes,&nbsp;Rebecca A Hubbard,&nbsp;Charles E Kahn,&nbsp;Dokyoon Kim,&nbsp;Ross Koppel,&nbsp;Qi Long,&nbsp;Nebojsa Mirkovic,&nbsp;Jeffrey S Morris,&nbsp;Danielle L Mowery,&nbsp;Marylyn D Ritchie,&nbsp;Ryan Urbanowicz,&nbsp;Jason H Moore","doi":"10.1055/s-0041-1731784","DOIUrl":"https://doi.org/10.1055/s-0041-1731784","url":null,"abstract":"<p><strong>Background: </strong> The electronic health record (EHR) has become increasingly ubiquitous. At the same time, health professionals have been turning to this resource for access to data that is needed for the delivery of health care and for clinical research. There is little doubt that the EHR has made both of these functions easier than earlier days when we relied on paper-based clinical records. Coupled with modern database and data warehouse systems, high-speed networks, and the ability to share clinical data with others are large number of challenges that arguably limit the optimal use of the EHR OBJECTIVES:  Our goal was to provide an exhaustive reference for those who use the EHR in clinical and research contexts, but also for health information systems professionals as they design, implement, and maintain EHR systems.</p><p><strong>Methods: </strong> This study includes a panel of 24 biomedical informatics researchers, information technology professionals, and clinicians, all of whom have extensive experience in design, implementation, and maintenance of EHR systems, or in using the EHR as clinicians or researchers. All members of the panel are affiliated with Penn Medicine at the University of Pennsylvania and have experience with a variety of different EHR platforms and systems and how they have evolved over time.</p><p><strong>Results: </strong> Each of the authors has shared their knowledge and experience in using the EHR in a suite of 20 short essays, each representing a specific challenge and classified according to a functional hierarchy of interlocking facets such as usability and usefulness, data quality, standards, governance, data integration, clinical care, and clinical research.</p><p><strong>Conclusion: </strong> We provide here a set of perspectives on the challenges posed by the EHR to clinical and research users.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 1-02","pages":"32-48"},"PeriodicalIF":1.7,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9295893/pdf/nihms-1819708.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39200478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of Not Structurable Oncological Study Eligibility Criteria for Improved Patient-Trial Matching.","authors":"Julia Dieter,&nbsp;Friederike Dominick,&nbsp;Alexander Knurr,&nbsp;Janko Ahlbrandt,&nbsp;Frank Ückert","doi":"10.1055/s-0041-1724107","DOIUrl":"https://doi.org/10.1055/s-0041-1724107","url":null,"abstract":"<p><strong>Background: </strong> Higher enrolment rates of cancer patients into clinical trials are necessary to increase cancer survival. As a prerequisite, an improved semiautomated matching of patient characteristics with clinical trial eligibility criteria is needed. This is based on the computer interpretability, i.e., structurability of eligibility criteria texts. To increase structurability, the common content, phrasing, and structuring problems of oncological eligibility criteria need to be better understood.</p><p><strong>Objectives: </strong> We aimed to identify oncological eligibility criteria that were not possible to be structured by our manual approach and categorize them by the underlying structuring problem. Our results shall contribute to improved criteria phrasing in the future as a prerequisite for increased structurability.</p><p><strong>Methods: </strong> The inclusion and exclusion criteria of 159 oncological studies from the Clinical Trial Information System of the National Center for Tumor Diseases Heidelberg were manually structured and grouped into content-related subcategories. Criteria identified as not structurable were analyzed further and manually categorized by the underlying structuring problem.</p><p><strong>Results: </strong> The structuring of criteria resulted in 4,742 smallest meaningful components (SMCs) distributed across seven main categories (Diagnosis, Therapy, Laboratory, Study, Findings, Demographics, and Lifestyle, Others). A proportion of 645 SMCs (13.60%) was not possible to be structured due to content- and structure-related issues. Of these, a subset of 415 SMCs (64.34%) was considered not remediable, as supplementary medical knowledge would have been needed or the linkage among the sentence components was too complex. The main category \"Diagnosis and Study\" contained these two subcategories to the largest parts and thus were the least structurable. In the inclusion criteria, reasons for lacking structurability varied, while missing supplementary medical knowledge was the largest factor within the exclusion criteria.</p><p><strong>Conclusion: </strong> Our results suggest that further improvement of eligibility criterion phrasing only marginally contributes to increased structurability. Instead, physician-based confirmation of the matching results and the exclusion of factors harming the patient or biasing the study is needed.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 1-02","pages":"9-20"},"PeriodicalIF":1.7,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1055/s-0041-1724107","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38901452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MAGICPL: A Generic Process Description Language for Distributed Pseudonymization Scenarios.","authors":"Galina Tremper,&nbsp;Torben Brenner,&nbsp;Florian Stampe,&nbsp;Andreas Borg,&nbsp;Martin Bialke,&nbsp;David Croft,&nbsp;Esther Schmidt,&nbsp;Martin Lablans","doi":"10.1055/s-0041-1731387","DOIUrl":"https://doi.org/10.1055/s-0041-1731387","url":null,"abstract":"<p><strong>Objectives: </strong> Pseudonymization is an important aspect of projects dealing with sensitive patient data. Most projects build their own specialized, hard-coded, solutions. However, these overlap in many aspects of their functionality. As any re-implementation binds resources, we would like to propose a solution that facilitates and encourages the reuse of existing components.</p><p><strong>Methods: </strong> We analyzed already-established data protection concepts to gain an insight into their common features and the ways in which their components were linked together. We found that we could represent these pseudonymization processes with a simple descriptive language, which we have called MAGICPL, plus a relatively small set of components. We designed MAGICPL as an XML-based language, to make it human-readable and accessible to nonprogrammers. Additionally, a prototype implementation of the components was written in Java. MAGICPL makes it possible to reference the components using their class names, making it easy to extend or exchange the component set. Furthermore, there is a simple HTTP application programming interface (API) that runs the tasks and allows other systems to communicate with the pseudonymization process.</p><p><strong>Results: </strong> MAGICPL has been used in at least three projects, including the re-implementation of the pseudonymization process of the German Cancer Consortium, clinical data flows in a large-scale translational research network (National Network Genomic Medicine), and for our own institute's pseudonymization service.</p><p><strong>Conclusions: </strong> Putting our solution into productive use at both our own institute and at our partner sites facilitated a reduction in the time and effort required to build pseudonymization pipelines in medical research.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 1-02","pages":"21-31"},"PeriodicalIF":1.7,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39084872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semi-automated Conversion of Clinical Trial Legacy Data into CDISC SDTM Standards Format Using Supervised Machine Learning.","authors":"Takuma Oda,&nbsp;Shih-Wei Chiu,&nbsp;Takuhiro Yamaguchi","doi":"10.1055/s-0041-1731388","DOIUrl":"https://doi.org/10.1055/s-0041-1731388","url":null,"abstract":"<p><strong>Objective: </strong> This study aimed to develop a semi-automated process to convert legacy data into clinical data interchange standards consortium (CDISC) study data tabulation model (SDTM) format by combining human verification and three methods: data normalization; feature extraction by distributed representation of dataset names, variable names, and variable labels; and supervised machine learning.</p><p><strong>Materials and methods: </strong> Variable labels, dataset names, variable names, and values of legacy data were used as machine learning features. Because most of these data are string data, they had been converted to a distributed representation to make them usable as machine learning features. For this purpose, we utilized the following methods for distributed representation: Gestalt pattern matching, cosine similarity after vectorization by Doc2vec, and vectorization by Doc2vec. In this study, we examined five algorithms-namely decision tree, random forest, gradient boosting, neural network, and an ensemble that combines the four algorithms-to identify the one that could generate the best prediction model.</p><p><strong>Results: </strong> The accuracy rate was highest for the neural network, and the distribution of prediction probabilities also showed a split between the correct and incorrect distributions. By combining human verification and the three methods, we were able to semi-automatically convert legacy data into the CDISC SDTM format.</p><p><strong>Conclusion: </strong> By combining human verification and the three methods, we have successfully developed a semi-automated process to convert legacy data into the CDISC SDTM format; this process is more efficient than the conventional fully manual process.</p>","PeriodicalId":49822,"journal":{"name":"Methods of Information in Medicine","volume":"60 1-02","pages":"49-61"},"PeriodicalIF":1.7,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39164925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}