检索结果-内蒙古大学图书馆

A Unified Review of Deep Learning for Automated medical coding

ACM COMPUTING SURVEYS 2024年第12期56卷 1-41页

作者： Ji, Shaoxiong Li, Xiaobo Sun, Wei Dong, Hang Taalas, Ara Zhang, Yijia Wu, Honghan Pitkaenen, Esa Marttinen, Pekka Aalto Univ Aalto Finland Univ Helsinki Helsinki Finland Dalian Maritime Univ Dalian Peoples R China Katholieke Univ Leuven Leuven Belgium Univ Exeter Exeter England Univ Helsinki Inst Mol Med Finland FIMM HiLIFE Helsinki Finland Terveystalo Healthcare Serv Helsinki Finland Univ Glasgow Sch Hlth & Wellbeing Glasgow Scotland

Automated medical coding, an essential task for healthcare operation and delivery, makes unstructured data manageable by predicting medical codes from clinical documents. Recent advances in deep learning and natural language processing have been widely applied to this task. However, deep learning-based medical coding lacks a unified view of the design of neural network architectures. This review proposes a unified framework to provide a general understanding of the building blocks of medical coding models and summarizes recent advanced models under the proposed framework. Our unified framework decomposes medical coding into four main components, i.e., encoder modules for text feature extraction, mechanisms for building deep encoder architectures, decoder modules for transforming hidden representations into medical codes, and the usage of auxiliary information. Finally, we introduce the benchmarks and real-world usage and discuss key research challenges and future directions.

关键词： medical coding deep learning unified framework

来源：评论

学校读者我要写书评

暂无评论

Exploring Healthcare Guidelines for Successfully Outsourcing Onshore and Offshore medical coding: A Qualitative Review

Exploring Healthcare Guidelines for Successfully Outsourcing...

引用

作者： Weaver, Tammy Colorado Technical University

学位级别：D.M., Doctor of Music/Doctor of Management/Doctor of Medicine/Doctor of Midwifery/Doctor of Medicine

Policies differ because the concerns differ when outsourcing medical coding onshore and offshore. This qualitative exploratory study answers how hospital management successfully incorporates policies to outsource medical coding to third parties. Eight sampled participants include human resources, auditors, medical coders, nurses, managers, directors, and healthcare professionals. The interviews were used to collect participant data. With data analysis and coding, five themes emerged: outsourcing processes, mitigating risk, offshore policies and procedures, percentage of offshore and onshore coding, and offshore and onshore breaches of patient information discovered. With electronic health records, remote opportunities for medical coding continue to be needed to monitor policies when outsourcing patient information. The six themes identified in the study have provided continued concern with maintaining policies in the healthcare management field of medical coding.

关键词： Information outsourcing medical coding Offshore Outsourcing Onshore

来源：评论

学校读者我要写书评

暂无评论

Entropic measures of complexity in a new medical coding system

引用

BMC medical INFORMATICS AND DECISION MAKING 2021年第1期21卷 124-124页

作者： Niyirora, Jerome SUNY Polytech Inst Coll Hlth Sci Utica NY 13502 USA

Background Transitioning from an old medical coding system to a new one can be challenging, especially when the two coding systems are significantly different. The US experienced such a transition in 2015. Objective This research aims to introduce entropic measures to help users prepare for the migration to a new medical coding system by identifying and focusing preparation initiatives on clinical concepts with more likelihood of adoption challenges. Methods Two entropic measures of coding complexity are introduced. The first measure is a function of the variation in the alphabets of new codes. The second measure is based on the possible number of valid representations of an old code. Results A demonstration of how to implement the proposed techniques is carried out using the 2015 mappings between ICD-9-CM and ICD-10-CM/PCS. The significance of the resulting entropic measures is discussed in the context of clinical concepts that were likely to pose challenges regarding documentation, coding errors, and longitudinal data comparisons. Conclusion The proposed entropic techniques are suitable to assess the complexity between any two medical coding systems where mappings or crosswalks exist. The more the entropy, the more likelihood of adoption challenges. Users can utilize the suggested techniques as a guide to prioritize training efforts to improve documentation and increase the chances of accurate coding, code validity, and longitudinal data comparisons.

关键词： medical coding Mapping Complexity Entropy

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Natural Language Processing Application for Prediction of medical Case coding Complexity: Algorithm Development and Validation

引用

JMIR medical INFORMATICS 2023年 11卷 e38150页

作者： Xu, He Ayu Maccari, Bernard Guillain, Herve Herzen, Julien Agri, Fabio Raisaro, Jean Louis Lausanne Univ Hosp Biomed Data Sci Ctr Lausanne Switzerland Unit8 SA Lausanne Switzerland Publ Hlth Solut Ltd Promasens Switzerland Lausanne Univ Hosp Dept Adm & Finance Lausanne Switzerland Lausanne Univ Hosp Dept Visceral Surg Lausanne Switzerland Lausanne Univ Hosp Biomed Data Sci Ctr CHUV Ctr Hosp Univ Vaudois Rue Bugnon 21 CH-1011 Lausanne Switzerland

Background: medical coding is the process that converts clinical documentation into standard medical codes. Codes are used for several key purposes in a hospital (eg, insurance reimbursement and performance analysis);therefore, their optimization is crucial. With the rapid growth of natural language processing technologies, several solutions based on artificial intelligence have been proposed to aid in medical coding by automatically suggesting relevant codes for clinical documents. However, their effectiveness is still limited to simple cases, and it is not yet clear how much value they can bring in improving coding efficiency and accuracy. Objective: This study aimed to bring more efficiency to the coding process to improve the selection of codes by medical coders. To achieve this, we developed an innovative multimodal machine learning-based solution that, instead of predicting codes, detects the degree of coding complexity before coding is performed. The notion of coding complexity was used to better dispatch work among medical coders to eventually minimize errors and improve ***: To train and evaluate our approach, we collected 2060 cases rated by coders in terms of coding complexity from 1 (simplest) to 4 (most complex). We asked 2 expert coders to rate 3.01% (62/2060) of the cases as the gold standard. The agreements between experts were used as benchmarks for model evaluation. A case contains both clinical text and patient metadata from the hospital electronic health record. We extracted both text features and metadata features, then concatenated and fed them into several machine learning models. Finally, we selected 2 models. The first used cross-validated training on 1751 cases and testing on 309 cases aiming to assess the predictive power of the proposed approach and its generalizability. The second model was trained on 1998 cases and tested on the gold standard to validate the best model performance against human ***: Our fir

关键词： medical coding natural language processing NLP complexity prediction prediction decision support machine learning model clinical decision support application multimodal modeling coding algorithm documentation health record electronic health record EHR development

来源：评论

学校读者我要写书评

暂无评论

The Magic of Semantic Enrichment and NLP for medical coding 16th

The Magic of Semantic Enrichment and NLP for Medical Coding

引用

16th International Extended Semantic Web Conference (ESWC)

作者： Garcia-Santa, Nuria San Miguel, Beatriz Ugai, Takanori Fujitsu Labs Europe Madrid 28224 Spain Fujitsu Labs Ltd Nakahara Ku 4-1-1 Kamikodanaka Kawasaki Kanagawa 2118588 Japan

ISBN: (纸本)9783030323271;9783030323264

Artificial Intelligence technologies are every day more present in the medical domain. Several healthcare activities that were entirely done manually by experts in the past, now are reaching a high level of automatization thanks to a satisfactory integration between these technologies and the medical professionals. This is the case of the medical coding process, consisting on the annotation of clinical notes (free-text narrative reports) to standard medical classifications in order to align this information with the patients' records. This paper presents a combination of NLP and semantic enrichment techniques to generate an extended Biomedical Knowledge Graph in order to be exploited in the development of our automatic medical coding solution.

关键词： Semantic enrichment Natural Language Processing (NLP) Knowledge graphs Word embeddings medical coding

来源：评论

学校读者我要写书评

暂无评论

The role of artificial intelligence in enhancing CPT coding accuracy for aesthetic plastic surgery: Insight into large language models

引用

JOURNAL OF PLASTIC RECONSTRUCTIVE AND AESTHETIC SURGERY 2025年 103卷 226-228页

作者： Isch, Emily L. Sambangi, Abhijeet Somers, Sydney Self, D. Mitchell Kim, David Mcmahon, Heather Newman, Andrew Jenkins, Matthew Thomas Jefferson Univ Dept Surg Div Plast Surg Philadelphia PA 19107 USA Thomas Jefferson Univ Sidney Kimmel Med Coll Philadelphia PA 19107 USA Thomas Jefferson Univ Dept Neurosurg Philadelphia PA 19107 USA Jefferson Hosp Neurosci Philadelphia PA 19107 USA

来源：评论

学校读者我要写书评

暂无评论

Automatic ICD-10 coding: Natural language processing for German MRI reports

引用

RADIOLOGIE 2024年第10期64卷 793-800页

作者： Mittermeier, Andreas Assenmacher, Matthias Schachtner, Balthasar Grosu, Sergio Dakovic, Vladana Kandratovich, Viktar Sabel, Bastian Ingrisch, Michael LMU Munchen Klin & Poliklin Radiol LMU Klinikum Munich Germany LMU Munchen Inst Stat Munich Germany Munich Ctr Machine Learning MCML Munich Germany

Background: The medical coding of radiology reports is essential for a good quality of care and correct billing, but at the same time a complex and error-prone task. Objective: To assess the performance of natural language processing (NLP) for ICD-10 coding of German radiology reports using fine tuning of suitable language models. Material and methods: This retrospective study included all magnetic resonance imaging (MRI) radiology reports acquired at our institution between 2010 and 2020. The codes on discharge ICD-10 were matched to the corresponding reports to construct a dataset for multiclass classification. Fine tuning of GermanBERT and flanT5 was carried out on the total dataset (ds(total)) containing 1035 different ICD-10 codes and 2 reduced subsets containing the 100 (ds(100)) and 50 (ds(50)) most frequent codes. The performance of the model was assessed using top-k accuracy for k = 1, 3 and 5. In an ablation study both models were trained on the accompanying metadata and the radiology report alone. Results: The total dataset consisted of 100,672 radiology reports, the reduced subsets ds(100) of 68,103 and ds(50) of 52,293 reports. The performance of the model increased when several of the best predictions of the model were taken into consideration, when the number of target classes was reduced and the metadata were combined with the report. The flanT5 outperformed GermanBERT across all datasets and metrics and was is suited as a medical coding assistant, achieving a top 3 accuracy of nearly 70% in the real-world dataset ds(total). Conclusion: Finely tuned language models can reliably predict ICD-10 codes of German magnetic resonance imaging (MRI) radiology reports across various settings. As a coding assistant flanT5 can guide medical coders to make informed decisions and potentially reduce the workload.

关键词： Radiology reports Language models Natural language processing Artificial intelligence medical coding Radiology reports Language models Natural language processing Artificial intelligence medical coding

来源：评论

学校读者我要写书评

暂无评论

Friend or Foe? Teaming Between Artificial Intelligence and Workers with Variation in Experience

引用

MANAGEMENT SCIENCE 2024年第9期70卷 5753-5775页

作者： Wang, Weiguang Gao, Guodong (Gordon) Agarwal, Ritu Univ Rochester Simon Business Sch Rochester NY 14627 USA Johns Hopkins Univ Carey Business Sch Baltimore MD 21202 USA

As artificial intelligence (AI) applications become more pervasive, it is critical to understand how knowledge workers with different levels and types of experience can team with AI for productivity gains. We focus on the influence of two major types of human work experience (narrow experience based on the specific task volume and broad experience based on seniority) on the human-AI team dynamics. We developed an AI solution for medical chart coding in a publicly traded company and conducted a field study among the knowledge workers. Based on a detailed analysis performed at the medical chart level, we find evidence that AI benefits workers with greater task-based experience, but senior workers gain less from AI than their junior colleagues. Further investigation reveals that the relatively lower productivity lift from AI is not a result of seniority per se but lower trust in AI, likely triggered by the senior workers' broader job responsibilities. This study provides new empirical insights into the differential roles of worker experience in the collaborative dynamics between AI and knowledge workers, which have important societal and business implications.

关键词： artificial intelligence human-AI teaming worker experience productivity healthcare medical coding

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hospital Reimbursement Through a Pediatric Surgery Resident Orientation Program: A Focus on Accurate Diagnosis Code Documentation for Acute Appendicitis

引用

JOURNAL OF PEDIATRIC SURGERY 2025年第1期60卷 161919-161919页

作者： Cordaro, Owen Vaughn, Cortnie Osei, Hector Georger, Miranda L'Huillier, Joseph C. Woodward, John M. Bittner, Krystle Harmon, Carroll M. Vali, Kaveh Ben Ham III, P. SUNY Buffalo Jacobs Sch Med & Biomed Sci Buffalo NY USA John R Oishei Childrens Hosp Div Pediat Surg Buffalo NY USA SUNY Buffalo DEPT SURG BUFFALO NY USA John R Oishei Childrens Hosp Dept Finance Buffalo NY USA

Background: The usage of specific ICD-10 diagnosis codes significantly influences hospital reimbursement compared to non-specific codes. This study hypothesized that a formal orientation program for pediatric surgery residents would enhance the selection of accurate and specific diagnosis codes for acute appendicitis such as K35.30 for "Acute appendicitis with localized peritonitis" rather than K35.80 for "Unspecified acute appendicitis," thereby improving hospital reimbursement. Methods: We implemented a comprehensive orientation for pediatric surgery residents at our institution in late 2020, a component of which emphasized the importance of having specific ICD-10 diagnosis codes. We conducted a retrospective analysis of laparoscopic appendectomy billing data for pediatric patients, comparing the use of specific versus unspecified diagnosis codes and associated hospital reimbursement rates before (2020) and after (2022) the program's initiation. Patients without payment were excluded. Statistical significance was determined by a two-tailed p-value of <= 0.05. Results: Analysis of 267 patient records showed a significant increase in the use of the specific diagnosis code (K35.30) from 3.6% in 2020 to 87.5% in 2022 (p < 0.0001). Adjusted for inflation and billing changes, mean hospital reimbursement per case increased by $661 (from $4414 to $5,075, p = 0.027), totaling an additional $84,616 in 2022, just for a single subset of appendicitis patients. Conclusions: A targeted resident orientation program significantly improves the use of specific ICD-10 codes for acute appendicitis, leading to increased hospital reimbursement. Such programs represent a valuable approach for enhancing the financial outcomes of pediatric surgical care while reinforcing the importance of accurate medical documentation. Study Design: Retrospective. Level of Evidence: III. (c) 2024 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar tech

关键词： medical coding Reimbursement Appendicitis Surgical education Resident orientation Resident education

来源：评论

学校读者我要写书评

暂无评论

How do hospitals respond to payment unbundling for diagnostic imaging of suspected cancer patients?

引用

HEALTH ECONOMICS 2024年第5期33卷 823-843页

作者： Hayes, Helen Stokes, Jonathan Sutton, Matt Meacock, Rachel Off Hlth Econ OHE London England Univ Manchester Ctr Primary Care & Hlth Serv Res Sch Hlth Sci Hlth Org Policy & Econ HOPE Manchester England Univ Glasgow Sch Hlth & Wellbeing MRC CSO Social & Publ Hlth Sci Unit Glasgow City Scotland Monash Univ Ctr Hlth Econ Melbourne Vic Australia

Payments for some diagnostic scans undertaken in outpatient settings were unbundled from Diagnosis Related Group based payments in England in April 2013 to address under-provision. Unbundled scans attracted additional payments of between 45 pound and 748 pound directly following the reform. We examined the effect on utilization of these scans for patients with suspected cancer. We also explored whether any detected effects represented real increases in use of scans or better coding of activity. We applied difference-in-differences regression to patient-level data from Hospital Episodes Statistics for 180 NHS hospital Trusts in England, between April 2010 and March 2018. We also explored heterogeneity in recorded use of scans before and after the unbundling at hospital Trust-level. Use of scans increased by 0.137 scans per patient following unbundling, a 134% relative increase. This increased annual national provider payments by 79.2 pound million. Over 15% of scans recorded after the unbundling were at providers that previously recorded no scans, suggesting some of the observed increase in activity reflected previous under-coding. Hospitals recorded substantial increases in diagnostic imaging for suspected cancer in response to payment unbundling. Results suggest that the reform also encouraged improvements in recording, so the real increase in testing is likely lower than detected.

关键词： cancer Diagnosis Related Groups (DRGs) diagnostic imaging medical coding payment methods

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：