Filters








1,561 Hits in 7.0 sec

Automating the Assignment of Diagnosis Codes to Patient Encounters Using Example-based and Machine Learning Techniques

S. V. S. Pakhomov, J. D. Buntrock, C. G. Chute
2006 JAMIA Journal of the American Medical Informatics Association  
Codes with the highest certainty are generated by matching the diagnostic text to frequent examples in a database of 22 million manually coded entries.  ...  Methods: We have developed an automated coding system designed to assign codes to clinical diagnoses. The system uses the notion of certainty to recommend subsequent processing.  ...  ICD-10 is the most current edition and is used for mortality coding world-wide; ICD-9CM (Clinically Modified) is usually used for billing in the United States.  ... 
doi:10.1197/jamia.m2077 pmid:16799125 pmcid:PMC1561792 fatcat:zoy47ohdmvcy7afjuhuj4ozbou

Towards Automated ICD Coding Using Deep Learning [article]

Haoran Shi, Pengtao Xie, Zhiting Hu, Ming Zhang, Eric P. Xing
2017 arXiv   pre-print
can automatically assign ICD diagnostic codes given written diagnosis.  ...  Considering the complicated and dedicated process to assign correct codes to each patient admission based on overall diagnosis, we propose a hierarchical deep learning model with attention mechanism which  ...  Acknowledgements The authors thank Devendra Singh Sachan for his sharing of pre-trained word vectors. Author contributions statement H.S. and P.X. conceived and designed the study.  ... 
arXiv:1711.04075v3 fatcat:wsipm67ipvdddfa44ko2cnfwbu

Explainable Prediction of Medical Codes With Knowledge Graphs

Fei Teng, Wei Yang, Li Chen, LuFei Huang, Qiang Xu
2020 Frontiers in Bioengineering and Biotechnology  
Adversarial learning is used to generate the adversarial samples to reconcile the writing styles of doctor.  ...  Based on the above considerations, the knowledge graph and attention mechanism were expanded into medical code prediction to improve interpretability.  ...  ACKNOWLEDGMENTS We would like to thank the Beth Israel Deaconess Medical Center for providing data support. We would also like to thank the reviewers for their insightful comments.  ... 
doi:10.3389/fbioe.2020.00867 pmid:32923430 pmcid:PMC7456905 fatcat:cftvof2urnbwxjwuluc2qxkovm

A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summaries [article]

Rajvir Kaur, Jeewani Anupama Ginige, Oliver Obst
2021 arXiv   pre-print
This systematic literature review provides a comprehensive overview of automated clinical coding systems that utilises appropriate NLP, ML and DL methods and techniques to assign ICD codes to discharge  ...  coding of clinical narratives and to assist human coders to assign clinical codes more accurately and efficiently.  ...  -10-AM and ACHI codes, and 1 study [86] used ICD-10-PCS, 1 study [95] converted ICD-9-CM codes to ICD-10-CM codes an using online resource before assigning them to discharge summaries.  ... 
arXiv:2107.10652v1 fatcat:5tyrtj5y4zgslbfwcm3hyztr2q

DiLBERT: Cheap Embeddings for Disease Related Medical NLP

Kevin Roitero, Beatrice Portelli, Mihai Horia Popescu, Vincenzo Della Mea
2021 IEEE Access  
Usually, text is also coded using appropriate terminologies and classifications. The act of coding is time consuming and prone to mistakes.  ...  Consequently, there is increasing demand for clinical text mining tools to help coding.  ...  We thank the anonymous reviewers for providing insightful comments which helped to improve the overall quality of the paper.  ... 
doi:10.1109/access.2021.3131386 fatcat:dckasazw4bcq3b4mnc3ex56wda

Automated coding of diagnoses--three methods compared

P Franz, A Zaiss, S Schulz, U Hahn, R Klar
2000 Proceedings. AMIA Symposium  
In response to emerging needs for computer-supported tools we examined three methods for automated coding of German-language free-text diagnosis phrases.  ...  We compared a language-independent lexicon-free n-gram approach with one which uses a dictionary of medical morphemes and refines the query by a mapping to SNOMED codes.  ...  RESULTS The results of the assignment of the correct ICD-9 codes to free-text discharge diagnoses are given in Table 1.  ... 
pmid:11079883 pmcid:PMC2243719 fatcat:gxkqob57lbhu3myh7bwjwigpui

A hybrid approach to determining modification of clinical diagnoses

Sergeui Pakhomov, Christopher G Chute
2006 AMIA Annual Symposium Proceedings  
In this paper we present a hybrid rule-based and machine learning technique for automatic determination of whether a diagnosis is confirmed, probable or represents a history of a disorder.  ...  The rule-based stage was able to classify 86% of test instances with an accuracy of 98.7%.  ...  ICD-10 is the most current edition and is used for mortality coding world-wide; ICD-9CM (Clinically Modified) is usually used for billing in the United States.  ... 
pmid:17238413 pmcid:PMC1839348 fatcat:z2ebiazwevh4rfujojtmxi3fbu

A Comparison of Deep Learning Methods for ICD Coding of Clinical Records

Elias Moons, Aditya Khanna, Abbas Akkasi, Marie-Francine Moens
2020 Applied Sciences  
In this survey, we discuss the task of automatically classifying medical documents into the taxonomy of the International Classification of Diseases (ICD), by the use of deep neural networks.  ...  All methods and their combinations are evaluated on two publicly available datasets that represent ICD-9 and ICD-10 coding, respectively.  ...  The documents are in free text format, which is automatically translated to English from Spanish, and they are manually labeled with ICD-10 codes by healthcare professionals.  ... 
doi:10.3390/app10155262 fatcat:oonzdpnitfdrzbuoh6fgwhrkma

Transformers for Clinical Coding in Spanish

Guillermo Lopez-Garcia, Jose M. Jerez, Nuria Ribelles, Emilio Alba, Francisco J. Veredas
2021 IEEE Access  
Thus, given a clinical free text written in specialized natural Spanish language, the tasks CodiEsp-D and CodiEsp-P consisted of assigning to the text a list of CIE-10-ES diagnostic and procedural codes  ...  [22] compared algorithms based on binary outputs, groups of subsets and extreme classification (eXtreme Multilabel Text Classification, or XMTC) to assign CIE-10-ES codes to clinical texts from hospital  ... 
doi:10.1109/access.2021.3080085 fatcat:y3qh3udqjrfxdfa7xdi2olmzjm

Natural Language Processing to Detect Cognitive Concerns in Electronic Health Records Using Deep Learning [article]

Zhuoqiao Hong, Colin G. Magdamo, Yi-han Sheu, Prathamesh Mohite, Ayush Noori, Elissa M. Ye, Wendong Ge, Haoqi Sun, Laura Brenner, Gregory Robbins, Shibani Mukerji, Sahar Zafar (+7 others)
2020 arXiv   pre-print
Automated mining of these notes presents a potential opportunity to label patients with cognitive concerns who could benefit from an evaluation or be referred to specialist care.  ...  In order to identify patients with cognitive concerns in electronic medical records, we applied natural language processing (NLP) algorithms and compared model performance to a baseline model that used  ...  concern (ICD 9 codes: 290.X, 294.X, 331.X, 780.93; ICD 10 codes: G30.X and G31.X).  ... 
arXiv:2011.06489v1 fatcat:rmrbtp57tnefpbnskbq2pzs7he

Active learning for medical code assignment [article]

Martha Dais Ferreira, Michal Malyska, Nicola Sahar, Riccardo Miotto, Fernando Paulovich, Evangelos Milios
2021 arXiv   pre-print
In this context, we apply a set of well-known AL methods to help automatically assign ICD-9 codes on the MIMIC-III dataset.  ...  Machine Learning (ML) is widely used to automatically extract meaningful information from Electronic Health Records (EHR) to support operational, clinical, and financial decision-making.  ...  In this scenario, the goal is automatically to assign the ICD-9 (the Ninth Revision of International Classification of Diseases) codes based on the content of the notes.  ... 
arXiv:2104.05741v1 fatcat:lqzs5q5oxneubhlj3k3cnb7ara

Extreme multi-label ICD classification: sensitivity to hospital service and time

Alberto Blanco, Alicia Perez, Arantza Casillas
2020 IEEE Access  
In 2019 [25] the task explored the automatic assignment of ICD-10 codes to non-technical summaries of animal experimentation in German.  ...  In 2017 [24] the task goal was to automatically assign ICD-10 codes to English and French death certificates. In 2018 [18] the task focused on French, Hungarian and Italian texts.  ... 
doi:10.1109/access.2020.3029429 fatcat:ac7gpztegnexpcgqzouz5pie5y

FasTag: Automatic text classification of unstructured medical narratives

Guhan Ram Venkataraman, Arturo Lopez Pineda, Oliver J. Bear Don't Walk IV, Ashley M. Zehnder, Sandeep Ayyar, Rodney L. Page, Carlos D. Bustamante, Manuel A. Rivas, Simon Clegg
2020 PLoS ONE  
In this retrospective study, we aimed to automate the assignment of top-level International Classification of Diseases version 9 (ICD-9) codes to clinical records from human and veterinary data stores  ...  We also investigated whether transforming the data using MetaMap Lite, a clinical natural language processing tool, affected classification performance.  ...  Kanagawa for her valuable support in editing this manuscript and Devin Johnson, DVM, MS, for her contribution to clinical coding and comparison with coding from the MetaMap tool.  ... 
doi:10.1371/journal.pone.0234647 pmid:32569327 fatcat:66wcqhitxfhdnpokdydoa2n6hq

Pre-training A Neural Language Model Improves The Sample Efficiency of an Emergency Room Classification Model [article]

Binbin Xu and Cédric Gil-Jardiné and Frantz Thiessard and Eric Tellier and Marta Avalos and Emmanuel Lagarde
2021 arXiv   pre-print
To build a French national electronic injury surveillance system based on emergency room visits, we aim to develop a coding system to classify their causes from clinical notes in free-text.  ...  Results show that the number of data required to achieve a ginve level of performance (AUC>0.95) was reduced by a factor of 10 when applying pre-training.  ...  We leveraged the fact that the traumatic/non-traumatic cause of the ER visit could be easily derived from available diagnostic codes (ICD-10) already assigned by clinicians at patient's hospitalization  ... 
arXiv:1909.01136v5 fatcat:wlyfiit5jbgzrgrxyt6zf4k7g4

Modeling Diagnostic Label Correlation for Automatic ICD Coding [article]

Shang-Chi Tsai, Chao-Wei Huang, Yun-Nung Chen
2021 arXiv   pre-print
To address this problem, we propose a two-stage framework to improve automatic ICD coding by capturing the label correlation.  ...  The source code of this project is available at https://github.com/MiuLab/ICD-Correlation.  ...  The associated diagnostic codes from the International Classification of Diseases (ICD) represent diagnostic and procedural information of the visit.  ... 
arXiv:2106.12800v1 fatcat:ejzatbw6yve7jmukn67bkmudky
« Previous Showing results 1 — 15 out of 1,561 results