检索结果-内蒙古大学图书馆

Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval

作者： Xiaorui Jiang Kulsoom Khan Sumithra Thinakara Vasantha Sajjad Haider Information School The University of Sheffield Sheffield United Kingdom Department of Computer Science Institute of Business Administration Karachi Pakistan Coventry University Coventry United Kingdom

来源：评论

学校读者我要写书评

暂无评论

The Hospital Data Project - Comparing hospital activity within Europe

引用

EUROPEAN JOURNAL OF PUBLIC HEALTH 2003年第3S期13卷 73-79页

作者： Magee, HF Dept Hlth & Children Dublin 2 Ireland

Background: The ability to measure and compare hospital activity between EU member states is important for policy, planning, financing and assessment of population health. Earlier initiatives in this area have been largely directed at standardising high-level indicator definitions without proper account of differences in health systems and health information systems. The Hospital Data Project (HDP) develops a methodology for improved comparability of hospital inpatient and day case activity data across Europe and produces a pilot common data set. All EU members, Iceland and the World Health Organisation are participants. Methods: The approach comprises a detailed inventory of patient-level hospital data, identification of common areas, specification of data transformations and production of pilot data sets and metadata in a common format. An expert group developed a new diagnosis shortlist based on icd-10. The project takes account of current work in the area of health care and morbidity indictors and applies the functional specification of health systems developed by the OECD. Results: Seventeen countries have submitted data and metadata in the common format for a single year. Data on inpatients and day cases are classified by age, gender, diagnosis and type of admission. Numbers of hospital discharges, mean and median lengths of stay and population rates are reported. Test data on selected hospital procedures has also been collected. The full data set contains approximately 500,000 records, and software has been designed to facilitate validation and use. Conclusion: Results to date are promising. It is a first step in a complex area, and further work is required to extend and refine this approach.

关键词： EU Health monitoring programme health systems hospital activity data icd coding

来源：评论

学校读者我要写书评

暂无评论

Can GPT-3.5 generate and code discharge summaries?

引用

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION 2024年第10期31卷 2284-2293页

作者： Falis, Matus Gema, Aryo Pradipta Dong, Hang Daines, Luke Basetti, Siddharth Holder, Michael Penfold, Rose S. Birch, Alexandra Alex, Beatrice Univ Edinburgh Sch Informat 10 Crichton St Edinburgh EH8 9AB Scotland Univ Exeter Dept Comp Sci Exeter EX4 4QF England Univ Edinburgh Usher Inst Ctr Med Informat Edinburgh EH16 4UX Scotland Natl Hlth Serv Highland Dept Res Dev & Innovat Inverness IV2 3JH Scotland Univ Edinburgh Usher Inst Ctr Populat Hlth Sci Edinburgh EH16 4UX Scotland Univ Edinburgh Usher Inst Ageing & Hlth Edinburgh EH16 4UX Scotland Univ Edinburgh Adv Care Res Ctr Edinburgh EH16 4UX Scotland Univ Edinburgh Edinburgh Futures Inst Edinburgh EH3 9EF Scotland Univ Edinburgh Sch Literatures Languages & Cultures Edinburgh EH8 9LH Scotland

Objectives The aim of this study was to investigate GPT-3.5 in generating and coding medical documents with International Classification of Diseases (icd)-10 codes for data augmentation on low-resource *** and Methods Employing GPT-3.5 we generated and coded 9606 discharge summaries based on lists of icd-10 code descriptions of patients with infrequent (or generation) codes within the MIMIC-IV dataset. Combined with the baseline training set, this formed an augmented training set. Neural coding models were trained on baseline and augmented data and evaluated on an MIMIC-IV test set. We report micro- and macro-F1 scores on the full codeset, generation codes, and their families. Weak Hierarchical Confusion Matrices determined within-family and outside-of-family coding errors in the latter codesets. The coding performance of GPT-3.5 was evaluated on prompt-guided self-generated data and real MIMIC-IV data. Clinicians evaluated the clinical acceptability of the generated *** Data augmentation results in slightly lower overall model performance but improves performance for the generation candidate codes and their families, including 1 absent from the baseline training data. Augmented models display lower out-of-family error rates. GPT-3.5 identifies icd-10 codes by their prompted descriptions but underperforms on real data. Evaluators highlight the correctness of generated concepts while suffering in variety, supporting information, and *** and Conclusion While GPT-3.5 alone given our prompt setting is unsuitable for icd-10 coding, it supports data augmentation for training neural models. Augmentation positively affects generation code families but mainly benefits codes with existing examples. Augmentation reduces out-of-family errors. Documents generated by GPT-3.5 state prompted concepts correctly but lack variety, and authenticity in narratives.

关键词： icd coding data augmentation large language model clinical text generation evaluation by clinicians

来源：评论

学校读者我要写书评

暂无评论

Patient safety indicators from a spine surgery perspective: the importance of a specialty specific clinician working with the documentation team and the impact to your hospital

引用

SPINE JOURNAL 2022年第10期22卷 1595-1600页

作者： Buza, John A. Carreon, Leah Y. Steele, Portia A. Nazar, Ryan G. Glassman, Steven D. Gum, Jeffrey L. Norton Leatherman Spine Ctr 210 E Gray St Suite 900 Louisville KY 40202 USA Norton Healthcare Care Management 234 East Gray StSuite 364 Louisville KY USA

BACKGROUND CONTEXT: The Hospital Acquired Conditions (HAC) Reduction Program sup-ports the Centers for Medicare and Medicaid Services (CMS) effort to prevent harm to patients by providing a financial incentive to reduce HACs. HAC scores are impacted by Patient Safety Indica -tors (PSIs), potentially preventable hospital-related events associated with harmful patient out-comes. PSIs are identified using International Classification of Diseases (icd) coding;however, icd coding does not always reflect the patient's true medical course. PURPOSE: To evaluate the efficacy of and costs savings associated with a clinical documentation review process in tandem with clinician collaboration in identifying incorrectly generated PSIs. STUDY DESIGN: Retrospective chart *** PATIENT SAMPLE: All patients undergoing spine surgery at a single multi-surgeon tertiary spine center. OUTCOME MEASURES: Occurrence of PSI. METHODS: Over two 11-month periods, all PSIs attributable to spine surgery were determined. The number and type of spine related PSIs were compared before (Control) and after the implementation of a specialty specific clinical review (Intervention) to identify incorrectly generated PSIs. The financial impact of this intervention was calculated in the form of an annual cost savings to our hospital system. RESULTS: During the Control phase, 61 PSIs were reported in 3368 spine cases, representing a total of 3.6 PSIs/month. During Intervention phase, 26 PSIs in 4,482 spine cases, resulting in a statistically significant decrease of 1.5 PSIs per month. The percentage of PSIs across all surgical cases attributable to spine surgery had a statistically significant decrease during the Intervention period compared to the Control period (16% vs. 10%, p=.034), resulting in the avoidance of a 1% CMS cost reduction, an annual cost saving of approximately $3-4 million dollars per year. CONCLUSIONS: The implementation of a clinical documentation review process with clinician colla

关键词： Centers for Medicare and Medicaid Clinical reviewer coding Cost savings Documentation Hospital acquired conditions icd coding Patient safety indicator Reimbursement Review process

来源：评论

学校读者我要写书评

暂无评论

Underestimated prevalence of heart failure in hospital inpatients: a comparison of icd codes and discharge letter information

引用

CLINICAL RESEARCH IN CARDIOLOGY 2018年第9期107卷 778-787页

作者： Kaspar, Mathias Fette, Georg Gueder, Guelmisal Seidlmayer, Lea Ertl, Maximilian Dietrich, Georg Greger, Helmut Puppe, Frank Stoerk, Stefan Wurzburg Univ Hosp CHFC Dept Internal Med 1 Schwarzenberg 15 D-97078 Wurzburg Germany Univ Wurzburg Chair Comp Sci 6 Wurzburg Germany Wurzburg Univ Hosp Serv Ctr Med Informat Wurzburg Germany

Heart failure is the predominant cause of hospitalization and amongst the leading causes of death in Germany. However, accurate estimates of prevalence and incidence are lacking. Reported figures originating from different information sources are compromised by factors like economic reasons or documentation quality. We implemented a clinical data warehouse that integrates various information sources (structured parameters, plain text, data extracted by natural language processing) and enables reliable approximations to the real number of heart failure patients. Performance of icd-based diagnosis in detecting heart failure was compared across the years 2000-2015 with (a) advanced definitions based on algorithms that integrate various sources of the hospital information system, and (b) a physician-based reference standard. Applying these methods for detecting heart failure in inpatients revealed that relying on icd codes resulted in a marked underestimation of the true prevalence of heart failure, ranging from 44% in the validation dataset to 55% (single year) and 31% (all years) in the overall analysis. Percentages changed over the years, indicating secular changes in coding practice and efficiency. Performance was markedly improved using search and permutation algorithms from the initial expert-specified query (F1 score of 81%) to the computer-optimized query (F1 score of 86%) or, alternatively, optimizing precision or sensitivity depending on the search objective. Estimating prevalence of heart failure using icd codes as the sole data source yielded unreliable results. Diagnostic accuracy was markedly improved using dedicated search algorithms. Our approach may be transferred to other hospital information systems.

关键词： Data warehouse Information extraction icd coding Heart failure Electronic health records

来源：评论

学校读者我要写书评

暂无评论

An explainable CNN approach for medical codes prediction from clinical text

引用

BMC MEDICAL INFORMATICS AND DECISION MAKING 2021年第SUPPL 9期21卷 256-256页

作者： Hu, Shuyuan Teng, Fei Huang, Lufei Yan, Jun Zhang, Haibo Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu Peoples R China Third Peoples Hosp Chengdu Chengdu Peoples R China Yidu Cloud Beijing Technol Co Ltd AI Lab Beijing Peoples R China Univ Otago Dept Comp Sci Dunedin New Zealand

Background Clinical notes are unstructured text documents generated by clinicians during patient encounters, generally are annotated with International Classification of Diseases (icd) codes, which give formatted information about the diagnosis and treatment. icd code has shown its potentials in many fields, but manual coding is labor-intensive and error-prone, lead to researches of automatic coding. Two specific challenges of this task are (1) given an annotated clinical notes, the reasons behind specific diagnoses and treatments are implicit;(2) explainability is important for practical automatic coding method, the method should not only explain its prediction output but also have explainable internal mechanics. This study aims to develop an explainable CNN approach to address these two challenges. Method Our key idea is that for the automatic icd coding task, the presence of informative snippets in the clinical text that correlated with each code plays an important role in the prediction of codes, and an informative snippet can be considered as a local and low-level feature. We infer that there exists a correspondence between a convolution filter and a local and low-level feature. Base on the inference, we come up with the Shallow and Wide Attention convolutional Mechanism (SWAM) to improve the CNN-based models' ability to learn local and low-level features for each label. Results We evaluate our approach on MIMIC-III, an open-access dataset of ICU medical records. Our approach substantially outperforms previous results on top-50 medical code prediction on MIMIC-III dataset, the precision of the worst-performing 10% labels in previous works is increased from 0% to 53% on average. We attribute this improvement to SWAM, by which the wide architecture with attention mechanism gives the model ability to more extensively learn the unique features of different codes, and we prove it by an ablation experiment. Besides, we perform manual analysis of the performance imbal

关键词： icd coding Machine learning Attention mechanism Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Death Certification Errors and the Effect on Mortality Statistics

引用

PUBLIC HEALTH REPORTS 2017年第6期132卷 669-675页

作者： McGivern, Lauri Shulman, Leanne Carney, Jan K. Shapiro, Steven Bundock, Elizabeth Vermont Dept Hlth Off Chief Med Examiner 111 Colchester AveBaird 1 Burlington VT 05401 USA Univ Vermont Robert Larner MD Coll Med Burlington VT USA

Objective: Errors in cause and manner of death on death certificates are common and affect families, mortality statistics, and public health research. The primary objective of this study was to characterize errors in the cause and manner of death on death certificates completed by non-Medical Examiners. A secondary objective was to determine the effects of errors on national mortality statistics. Methods: We retrospectively compared 601 death certificates completed between July 1, 2015, and January 31, 2016, from the Vermont Electronic Death Registration System with clinical summaries from medical records. Medical Examiners, blinded to original certificates, reviewed summaries, generated mock certificates, and compared mock certificates with original certificates. They then graded errors using a scale from 1 to 4 (higher numbers indicated increased impact on interpretation of the cause) to determine the prevalence of minor and major errors. They also compared International Classification of Diseases, 10th Revision (icd-10) codes on original certificates with those on mock certificates. Results: Of 601 original death certificates, 319 (53%) had errors;305 (51%) had major errors;and 59 (10%) had minor errors. We found no significant differences by certifier type (physician vs nonphysician). We did find significant differences in major errors in place of death (P < .001). Certificates for deaths occurring in hospitals were more likely to have major errors than certificates for deaths occurring at a private residence (59% vs 39%, P < .001). A total of 580 (93%) death certificates had a change in icd-10 codes between the original and mock certificates, of which 348 (60%) had a change in the underlying cause-of-death code. Conclusions: Error rates on death certificates in Vermont are high and extend to icd-10 coding, thereby affecting national mortality statistics. Surveillance and certifier education must expand beyond local and state efforts. Simplifying and standardizi

关键词： death certificate errors mortality statistics icd coding cause of death

来源：评论

学校读者我要写书评

暂无评论

Hospital morbidity data for determining spread of disease at diagnosis for colorectal cancer: A validation study

引用

ASIA-PACIFIC JOURNAL OF CLINICAL ONCOLOGY 2012年第3期8卷 E17-E22页

作者： Thompson, Bridie Lumley, John Coory, Michael Queensland Hlth Patient Safety & Qual Improvement Serv Brisbane Qld Australia Univ Queensland Sch Populat Hlth Brisbane Qld Australia Wesley Hosp Brisbane Qld Australia Royal Childrens Hosp Murdoch Childrens Res Inst Melbourne Vic Australia

Aims: There is currently no routine collection of cancer stages in population-based data in Australia. This study evaluates the accuracy of International classification of diseases (icd) codes for secondary neoplasms recorded in hospital morbidity data to assign spread of disease at diagnosis for colorectal cancer. Methods: The reference (gold) standard was the Australian clinicopathological stage (ACPS) documented by a treating colorectal surgeon and derived from histopathology and clinical findings. To allow comparison with stages derived from the hospital morbidity data (HMD), ACPS was mapped to the spread of disease (local, regional and distant). Sensitivity, specificity and positive-predictive values were calculated to compare the accuracy of stage derived from HMD. Results: Data from both the reference standard and HMD were available for 499 patients. HMD slightly overestimated patients with local disease (62.3 vs 56.9%). There was a corresponding underestimation of regional and distant spread of disease. While sensitivity for regional and distant disease was moderate (66.4 and 71.4%, respectively), specificity was high (92.7 and 96.6%, respectively). Conclusion: icd codes for secondary neoplasms in HMD are limited in their utility for determining the spread of disease for colorectal cancer. Clinicians need to ensure that clinical coders are provided with enough information to accurately code for spread of disease. We recommend reporting histopathology in a synoptic format which includes background information on the presence or absence of distant metastasis and the tumor node metastasis stage.

关键词： colorectal epidemiology icd coding pathology stage

来源：评论

学校读者我要写书评

暂无评论

Assessing the Accuracy of Emergency Department International Classification of Diseases coding

引用

JACC-HEART FAILURE 2015年第5期3卷 392-394页

作者： Storrow, Alan B. Collins, Sean P. Vanderbilt Univ Dept Emergency Med Nashville TN 37232 USA

来源：评论

学校读者我要写书评

暂无评论

The Need for Standardized Nomenclature in Electronic Documentation of Female Genital Cutting in Health Records

引用

JOURNAL OF IMMIGRANT AND MINORITY HEALTH 2024年第4期26卷 667-673页

作者： Creger, Jae Abdikeir, Kalthum Kaczmarczik, Kyra Chaisson, Nicole Johnson-Agbakwu, Crista E. Robinson, Beatrice Bean E. Connor, Jennifer Jo Univ Minnesota Dept Family Med & Community Hlth Med Sch Minneapolis MN USA Univ Minnesota Sch Nursing Minneapolis MN USA Univ Minnesota Med Sch Minneapolis MN USA UMass Chan Med Sch Div Prevent & Behav Med Populat & Quantitat Hlth Sci Worcester MA USA UMass Mem Hlth Worcester MA USA Univ Minnesota Eli Coleman Inst Sexual & Gender Hlth Dept Family Med & Community Hlth Med Sch 1300 South Second StSuite 180 Minneapolis MN 55454 USA

To evaluate the quality of Electronic Health Record (EHR) documentation practices of Female Genital Cutting (FGC) by medical providers. A retrospective chart review study of 99 patient encounter notes within the University of Minnesota health system (inclusive of 40 hospitals and clinics) was conducted. Extracted data included but was not limited to patient demographics, reason for patient visit, icd code used in note, and provider description of FGC anatomy. Data was entered into REDCAP and categorized according to descriptive statistics. Out of 99 encounters, 45% used the unspecified code for FGC. The most common reason for patient visits was sexual pain, though many notes contained several reasons for the visit regarding reproductive, urological, or sexual concerns. 56% of visits discussed deinfibulation. 11 different terms for FGC were used, with "female circumcision" being the most common. 14 different terms for deinfibulation were found within 64 notes. 42% of encounters included a description of introitus size in the anatomical description, and only 38% of these provided a metric measurement. This study found significant variation in the quality of FGC documentation practices. Medical providers often used the unspecified FGC code, subjective and/or seemingly inaccurate descriptions of FGC/anatomy, and several different terms for both FGC and deinfibulation. Clearly, more education is needed in clinical training programs to (1) identify FGC type, (2) use the corresponding icd code, and (3) use specific, objective descriptions (including presence/absence of structures and infibulation status).

关键词： Female genital cutting Medical documentation icd coding Sexual pain

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：