检索结果-内蒙古大学图书馆

Artificial intelligence-enabled safety monitoring in Alzheimer's disease clinical trials

The journal of prevention of Alzheimer's disease 2025年第1期12卷 100002-100002页

作者： Jimenez-Maggiora, Gustavo A. Donohue, Michael C. Rafii, Michael S. Raman, Rema Aisen, Paul S. Alzheimer's Therapeutic Research Institute University of Southern California San Diego CA United States Alzheimer's Therapeutic Research Institute University of Southern California San Diego CA United States

BACKGROUND: Investigators conducting clinical trials have an ethical, scientific, and regulatory obligation to protect the safety of trial participants. Traditionally, safety monitoring includes manual review and coding of adverse event data by expert clinicians. OBJECTIVES: Our study explores the use of natural language processing (NLP) and artificial intelligence (AI) methods to streamline and standardize clinician coding of adverse event data in Alzheimer's disease (AD) clinical trials. DESIGN: Our quantitative retrospective study aimed to develop a gold standard AD adverse event data set, evaluate the predictive performance of NLP-based models to classify adverse events, and determine whether automated coding is more efficient, accurate, reliable, and consistent than clinician coding. SETTING: Our study was conducted at the University of Southern California's Alzheimer's Therapeutic Research Institute (ATRI). ATRI serves as the clinical and data coordinating center for the Alzheimer's Clinical Trial Consortium (ACTC). PARTICIPANTS: We collected demographic and adverse event data from eight completed clinical trials in participants (n=1920) with symptomatic AD conducted between 2005 and 2020. MEASUREMENTS: Original expert clinician-confirmed codes were used for all model performance comparisons. F1 score was used as the primary model selection metric. Final classifier performance was evaluated using predictive accuracy. Clinician effort was measured in time to code, review, and confirm coded adverse events. RESULTS: In a sample of 1000 adverse events, AI-based AE coding achieved higher accuracy (∼20% increase in accuracy) and was more cost-effective (∼80% cost reduction) than traditional clinician coding. CONCLUSIONS: Our study results demonstrate how approaches that effectively combine AI and human expertise can improve the efficiency and quality of adverse event coding and clinical trial safety monitoring. Copyright © 2024 The Authors. Published by Elsevier Mas

关键词： Adverse event Alzheimer's disease Artificial intelligence Classification Clinical trial medical coding Safety

来源：评论

学校读者我要写书评

暂无评论

Malnutrition definitions in clinical practice: To be E43 or not to be?

引用

HEALTH INFORMATION MANAGEMENT JOURNAL 2020年第1期49卷 74-79页

作者： Phillips, Wendy Doley, Jennifer Boi, Kelli Morrison Healthcare St George UT 84790 USA Carondelet Hlth Network Tucson AZ USA Intermt Healthcare Provo UT USA

Malnutrition is a disease that imposes a significant healthcare cost burden in the United States, especially when left undiagnosed and untreated for an extended period of time. This article discusses traditional malnutrition diagnostic criteria for adults and why registered dietitian nutritionists and physicians should no longer use these criteria to determine nutrition status. It concludes with the malnutrition clinical characteristics currently accepted in the United States and globally, with implications for practice. Clinical documentation specialists and medical coders can use this information to better interpret medical record documentation and assign the correct International Classification of Diseases, 10th Revision, Clinical Modification codes to the coding abstract.

关键词： clinical coding electronic clinical documentation financial management hospital healthcare health information management malnutrition nutrition assessment malnutrition coding clinical coding medical coding nutrition diagnosis

来源：评论

学校读者我要写书评

暂无评论

Use of the ICD-10 vision codes to study ocular conditions in Medicare beneficiaries with stroke

引用

BMC HEALTH SERVICES RESEARCH 2020年第1期20卷 628-628页

作者： Hreha, Kimberly P. Fisher, Steve R. Reistetter, Timothy A. Ottenbacher, Kenneth Haas, Allen Li, Chih-Ying Ehrlich, Joshua R. Whitaker, Diane B. Whitson, Heather E. Univ Texas Med Branch Div Rehabil Sci Sch Hlth Profess 301 Univ Blvd Galveston TX 77555 USA Univ Texas Med Branch Sch Hlth Profess Phys Therapy Dept 301 Univ Blvd Galveston TX 77555 USA Univ Texas San Antonio Sch Hlth Profess Dept Occupat Therapy 7703 Floyd Curl Dr San Antonio TX 78229 USA Univ Texas Med Branch Dept Prevent Med & Populat Hlth 301 Univ Blvd Galveston TX 77555 USA Univ Texas Med Branch Occupat Therapy Dept Sch Hlth Profess 301 Univ Blvd Galveston TX 77555 USA Univ Michigan Kellogg Eye Ctr Dept Ophthalmol & Visual Sci 100 Wall St Ann Arbor MI 48105 USA Duke Univ Dept Ophthalmol Sch Med 2351 Erwin Rd Durham NC 27705 USA Duke Univ Sch Med Dept Med Durham NC 27706 USA Duke Univ Sch Med Ctr Study Aging & Human Dis Durham NC USA Durham VA Med Ctr Geriatr Res Educ & Clin Ctr 8 Searle Ctr Dr Durham NC 27710 USA

Background Ocular conditions are common following stroke and frequently occur in combination with pre-existing ophthalmologic disease. The Medicare International Statistical Classification of Diseases and Related Health Problems (ICD-10) coding system for identifying vision related health conditions provides a much higher level of detail for coding these complex scenarios than the previous ICD-9 system. While this new coding system has advantages for clinical care and billing, the degree to which providers and researchers are utilizing the expanded code structure is unknown. The purpose of this study was to describe the use of ICD-10 vision codes in a large cohort of stroke survivors. Methods Retrospective cohort design to study national 100% Medicare claims files from 2015 through 2017. Descriptive data analyses were conducted using all available ICD-10 vision codes for beneficiaries who had an acute care stay because of a new stroke. The outcome of interest was >= 1 ICD-10 visual code recorded in the claims chart. Results The cohort (n = 269,314) was mostly female (57.1%) with ischemic stroke (87.8%). Approximately 15% were coded as having one or more ocular condition. Unspecified glaucoma was the most frequently used code among men (2.83%), those over 85+ (4.80%) and black beneficiaries (4.12%). Multiple vision codes were used in few patients (0.6%). Less than 3% of those in the oldest group (85+ years) had two or more vision codes in their claims. Conclusions Ocular comorbidity was present in a portion of this cohort of stroke survivors, however the vision codes used to describe impairments in this population were few and lacked specificity. Future studies should compare ophthalmic examination results with billing codes to characterize the type and frequency of ocular comorbidity. It important to understand how the use of ICD-10 vision codes impacts clinical decision making, recovery, and outcomes.

关键词： Vision Impairment Ocular conditions Stroke Comorbidity medical coding

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Automatic Encoding of French Electronic medical Records: Is More Data Better ? 30

Machine Learning for Automatic Encoding of French Electronic...

引用

30th medical Informatics Europe (MIE) Conference

作者： Gobeill, Julien Ruch, Patrick Meyer, Rodolphe Swiss Inst Bioinformat SIB Text Min Grp Geneva Switzerland HES So HEG Informat Sci Geneva Switzerland Univ Hospitals Geneva HUG Informat Syst Dept Geneva Switzerland

ISBN: (纸本)9781643680835;9781643680828

The encoding of Electronic medical Records is a complex and time-consuming task. We report on a machine learning model for proposing diagnoses and procedures codes, from a large realistic dataset of 245 000 electronic medical records at the University Hospitals of Geneva. Our study particularly focuses on the impact of training data quantity on the model's performances. We show that the performances of the models do not increase while encoded instances from previous years are exploited for learning data. Furthermore, supervised models are shown to be highly perishable: we show a potential drop in performances of around -10% per year. Consequently, great and constant care must be exercised for designing and updating the content of such knowledge bases exploited by machine learning.

关键词： medical coding machine learning text mining

来源：评论

学校读者我要写书评

暂无评论

Blind coding Academies: A Proposed Method for Overcoming Accessibility Barriers for Individuals Who are Blind or Severely Visually Impaired

引用

JOURNAL OF VISUAL IMPAIRMENT & BLINDNESS 2019年第4期113卷 387-393页

作者： Candela, Anthony R. 3015 Riverdale Ave Apartment 5H Bronx NY 10463 USA

The article discusses the development of blind coding academies to provide a structure to prepare students who are blind or severely visually impaired to overcome or mitigate barriers. Topics mentioned include the benefits of attending a blind coding academy, accessibility barriers faced by youths and adults who are blind or severely visually impaired, and the need for coders who are visually impaired to communicate well with fellow team members.

关键词： COMPUTER software COMPUTERS CURRICULA (Courses of study) GOAL (Psychology) INFORMATION science LABOR market TEACHING aids VISION disorders TEACHING methods medical coding

来源：评论

学校读者我要写书评

暂无评论

Neural transfer learning for assigning diagnosis codes to EMRs

引用

ARTIFICIAL INTELLIGENCE IN MEDICINE 2019年 96卷 116-122页

作者： Rios, Anthony Kavuluru, Ramakanth Univ Kentucky Dept Comp Sci Lexington KY USA Univ Kentucky Div Biomed Informat Dept Internal Med Lexington KY 40506 USA

Objective: Electronic medical records (EMRs) are manually annotated by healthcare professionals and specialized medical coders with a standardized set of alphanumeric diagnosis and procedure codes, specifically from the International Classification of Diseases (ICD). Annotating EMRs with ICD codes is important for medical billing and downstream epidemiological studies. However, manually annotating EMRs is both time-consuming and error prone. In this paper, we explore the use of convolutional neural networks (CNNs) for automatic ICD coding. Because many codes occur infrequently, CNN performance is inhibited. Therefore, we propose supplementing EMR data with PubMed indexed biomedical research abstracts through neural transfer learning. Materials and methods: Transfer learning is the process of "transferring" knowledge acquired from one task (the source task) to a different (target) task. For the source task, we train a CNN to predict medical subject headings (MeSH) using 1.6 million PubMed indexed biomedical abstracts. For the target task, we train a CNN on 71,463 real-world EMRs collected from the University of Kentucky (UKY) medical center to predict ICD diagnosis codes. We introduce a simple, yet effective, transfer learning methodology which avoids forgetting knowledge gained from the source task. Results: Compared to our prior work using EMRs from the UKY medical center, we improve both the micro and macro F-scores by more than 8%. Likewise, compared to other transfer learning methods, our approach results in nearly 2% improvement in macro F-score. Conclusion: We show that transfer learning can improve CNN performance for EMR coding in the presence of data sparsity issues. Furthermore, we find that our proposed transfer learning approach outperforms other methods with respect to macro F-score. Finally, we analyze how transfer learning impacts codes with respect to code frequency. We find that we achieve greater improvement on infrequent codes compared to improvem

关键词： medical coding Convolutional neural networks Transfer learning Multi-label classification

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of spatial neglect and rehabilitation access for stroke survivors

引用

Cogent gerontology 2024年第1期3卷 2375706页

作者： Corey Morrow Holden Gasque Michelle Woodbury Eyad Almallouhi Annie Simpson Kit Simpson Division of Occupational Therapy Medical University of South Carolina Charleston SC USA.

Spatial neglect in stroke survivors is associated with a decrease in quality of life. This disorder occurs in 20-80% of stroke survivors and up to 1/3 of stroke survivors will continue to experience chronic impairment. Occupational therapists are uniquely qualified to treat stroke survivors with spatial neglect due to their holistic approach but access to therapy is limited. Diagnostic coding is used to help determine appropriate reimbursement and continuation of care including rehabilitation services. The objectives of this study were to 1) identify the prevalence of diagnostic coding for spatial neglect in stroke survivors, and 2) identify the prevalence and types of rehabilitation for patients with diagnostic coding for spatial neglect. We completed a retrospective cohort analysis using 2018 and 2019 5% Medicare Limited Data Sets from the Centers for Medicare and Medicaid Services. We extracted all ischemic stroke survivors and stratified them by the presence of a secondary diagnostic code indicating spatial neglect. Rehabilitation Current Procedural Terminology codes were used to identify stroke survivors who received rehabilitation. Despite recommendations from clinical practice, only 4.9% had a diagnostic code for spatial neglect. Of those formally diagnosed, only 2.3% received outpatient occupational therapy after being discharged from acute care.

关键词： I10 Spatial neglect diagnosis medical coding occupational therapy stroke

来源：评论

学校读者我要写书评

暂无评论

Automated Billing Code Retrieval from MRI Scanner Log Data

引用

JOURNAL OF DIGITAL IMAGING 2019年第6期32卷 1103-1111页

作者： Denck, Jonas Landschuetz, Wilfried Nairz, Knud Heverhagen, Johannes T. Maier, Andreas Rothgang, Eva Tech Univ Appl Sci Amberg Weiden Inst Med Engn Weiden Germany Friedrich Alexander Univ Erlangen Nurnberg Dept Comp Sci Pattern Recognit Lab Erlangen Germany Siemens Healthineers Erlangen Germany Univ Bern Dept Diagnost Intervent & Pediat Radiol Inselspital Bern Switzerland

Although the level of digitalization and automation steadily increases in radiology, billing coding for magnetic resonance imaging (MRI) exams in the radiology department is still based on manual input from the technologist. After the exam completion, the technologist enters the corresponding exam codes that are associated with billing codes in the radiology information system. Moreover, additional billing codes are added or removed, depending on the performed procedure. This workflow is time-consuming and we showed that billing codes reported by the technologists contain errors. The coding workflow can benefit from an automated system, and thus a prediction model for automated assignment of billing codes for MRI exams based on MRI log data is developed in this work. To the best of our knowledge, it is the first attempt to focus on the prediction of billing codes from modality log data. MRI log data provide a variety of information, including the set of executed MR sequences, MR scanner table movements, and given a contrast medium. MR sequence names are standardized using a heuristic approach and incorporated into the features for the prediction. The prediction model is trained on 9754 MRI exams and tested on 1 month of log data (423 MRI exams) from two MRI scanners of the radiology site for the Swiss medical tariffication system Tarmed. The developed model, an ensemble of classifier chains with multilayer perceptron as a base classifier, predicts medical billing codes for MRI exams with a micro-averaged F1-score of 97.8% (recall 98.1%, precision 97.5%). Manual coding reaches a micro-averaged F1-score of 98.1% (recall 97.4%, precision 98.8%). Thus, the performance of automated coding is close to human performance. Integrated into the clinical environment, this work has the potential to free the technologist from a non-value adding an administrative task, therefore enhance the MRI workflow, and prevent coding errors.

关键词： Machine learning Magnetic resonance imaging medical coding Reimbursement Workflow enhancement

来源：评论

学校读者我要写书评

暂无评论

Exploiting hierarchy in medical concept embedding

引用

JAMIA OPEN 2021年第1期4卷 ooab022页

作者： Finch, Anthony Crowell, Alexander Bhatia, Mamta Parameshwarappa, Pooja Chang, Yung-Chieh Martinez, Jose Horberg, Michael Kaiser Permanente Midatlantic Permanente Med Grp 2101 E Jefferson St Rockville MD 20852 USA Kaiser Permanente Midatlantic Permanente Res Inst 2101 E Jefferson St Rockville MD 20852 USA

Objective: To construct and publicly release a set of medical concept embeddings for codes following the ICD10 coding standard which explicitly incorporate hierarchical information from medical codes into the embedding formulation. Materials and Methods: We trained concept embeddings using several new extensions to the Word2Vec algorithm using a dataset of approximately 600,000 patients from a major integrated healthcare organization in the Mid-Atlantic US. Our concept embeddings included additional entities to account for the medical categories assigned to codes by the Clinical Classification Software Revised (CCSR) dataset. We compare these results to sets of publicly released pretrained embeddings and alternative training methodologies. Results: We found that Word2Vec models which included hierarchical data outperformed ordinary Word2Vec alternatives on tasks which compared naive clusters to canonical ones provided by CCSR. Our Skip-Gram model with both codes and categories achieved 61.4% normalized mutual information with canonical labels in comparison to 57.5% with traditional Skip-Gram. In models operating on two different outcomes, we found that including hierarchical embedding data improved classification performance 96.2% of the time. When controlling for all other variables, we found that co-training embeddings improved classification performance 66.7% of the time. We found that all models outperformed our competitive benchmarks. Discussion: We found significant evidence that our proposed algorithms can express the hierarchical structure of medical codes more fully than ordinary Word2Vec models, and that this improvement carries forward into classification tasks. As part of this publication, we have released several sets of pretrained medical concept embeddings using the ICD-10 standard which significantly outperform other well-known pretrained vectors on our tested outcomes.

关键词： concept embedding medical coding ICD-10

来源：评论

学校读者我要写书评

暂无评论

Patients' Needs of Religion/Spirituality Integration in Two Mental Health Clinics in the Netherlands

引用

ISSUES IN MENTAL HEALTH NURSING 2019年第1期40卷 41-49页

作者： Amerongen-Meeuse, Joke C. van Nieuw Schaap-Jonker, Hanneke Hennipman-Herweijer, Christina Anbeek, Christa Braam, Arjan W. Univ Humanist Studies Dept Globalizat & Dialogue Studies Kromme Nieuwegracht 29 NL-3512 HD Utrecht Netherlands Ctr Res & Innovat Christian Mental Hlth Care Eleo Amersfoort Netherlands Eleos Mental Hlth Care Bosch En Duin Netherlands Free Univ Amsterdam Dept Relig & Theol Amsterdam Netherlands Altrecht Mental Hlth Care Dept Emergency Psychiat Utrecht Netherlands Altrecht Mental Hlth Care Dept Residency Training Utrecht Netherlands

Introduction: In the last decades, the attention for religion/spirituality (R/S) in mental health care (MHC) has considerably increased. However, patients' preferences concerning R/S in treatment have not often been investigated. The aim of this study was to find out how patients in clinical multidisciplinary MHC want R/S to be addressed in their care. Methods: Thirty-five semi-structured interviews were carried out between September 2015 and July 2016 among patients in a secular and a Christian MHC in the Netherlands. Qualitative inductive content analysis was performed, using Atlas Ti. Results: Patients appreciated (1) individual R/S conversations between patients and care team members (mainly nurses), (2) a familiar R/S environment, (3) a special R/S program and (4) contact with their R/S network. Patients varied in their presentation of R/S care needs from (a) explicit, mostly in the Christian MHC, to (b) implicit, predominantly in the secular MHC, or showed (c) hidden R/S care needs. A non-acute stage of the illness and R/S affinity of the mental health professionals, were classified as possible conditions for addressing R/S.

关键词： MENTAL illness treatment PSYCHIATRIC hospitals CHRISTIANITY CONTENT analysis HEALTH care teams INTERVIEWING RESEARCH methodology medical personnel & patient PSYCHOTHERAPY patients RESEARCH funding SPIRITUALITY QUALITATIVE research JUDGMENT sampling PATIENTS' attitudes medical coding DESCRIPTIVE statistics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：