Generating Medical Assessments Using a Neural Network Model: Algorithm Development and Validation. Hu, B., Bajracharya, A., & Yu, H. JMIR Medical Informatics, 8(1):e14971, 2020. Company: JMIR Medical Informatics Distributor: JMIR Medical Informatics Institution: JMIR Medical Informatics Label: JMIR Medical Informatics Publisher: JMIR Publications Inc., Toronto, Canada![Generating Medical Assessments Using a Neural Network Model: Algorithm Development and Validation [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Background: Since its inception, artificial intelligence has aimed to use computers to help make clinical diagnoses. Evidence-based medical reasoning is important for patient care. Inferring clinical diagnoses is a crucial step during the patient encounter. Previous works mainly used expert systems or machine learning–based methods to predict the International Classification of Diseases - Clinical Modification codes based on electronic health records. We report an alternative approach: inference of clinical diagnoses from patients’ reported symptoms and physicians’ clinical observations. Objective: We aimed to report a natural language processing system for generating medical assessments based on patient information described in the electronic health record (EHR) notes. Methods: We processed EHR notes into the Subjective, Objective, Assessment, and Plan sections. We trained a neural network model for medical assessment generation (N2MAG). Our N2MAG is an innovative deep neural model that uses the Subjective and Objective sections of an EHR note to automatically generate an “expert-like” assessment of the patient. N2MAG can be trained in an end-to-end fashion and does not require feature engineering and external knowledge resources. Results: We evaluated N2MAG and the baseline models both quantitatively and qualitatively. Evaluated by both the Recall-Oriented Understudy for Gisting Evaluation metrics and domain experts, our results show that N2MAG outperformed the existing state-of-the-art baseline models. Conclusions: N2MAG could generate a medical assessment from the Subject and Objective section descriptions in EHR notes. Future work will assess its potential for providing clinical decision support. [JMIR Med Inform 2020;8(1):e14971]
@article{hu_generating_2020,
title = {Generating {Medical} {Assessments} {Using} a {Neural} {Network} {Model}: {Algorithm} {Development} and {Validation}},
volume = {8},
copyright = {Unless stated otherwise, all articles are open-access distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work (},
shorttitle = {Generating {Medical} {Assessments} {Using} a {Neural} {Network} {Model}},
url = {https://medinform.jmir.org/2020/1/e14971/},
doi = {10.2196/14971},
abstract = {Background: Since its inception, artificial intelligence has aimed to use computers to help make clinical diagnoses. Evidence-based medical reasoning is important for patient care. Inferring clinical diagnoses is a crucial step during the patient encounter. Previous works mainly used expert systems or machine learning–based methods to predict the International Classification of Diseases - Clinical Modification codes based on electronic health records. We report an alternative approach: inference of clinical diagnoses from patients’ reported symptoms and physicians’ clinical observations.
Objective: We aimed to report a natural language processing system for generating medical assessments based on patient information described in the electronic health record (EHR) notes.
Methods: We processed EHR notes into the Subjective, Objective, Assessment, and Plan sections. We trained a neural network model for medical assessment generation (N2MAG). Our N2MAG is an innovative deep neural model that uses the Subjective and Objective sections of an EHR note to automatically generate an “expert-like” assessment of the patient. N2MAG can be trained in an end-to-end fashion and does not require feature engineering and external knowledge resources.
Results: We evaluated N2MAG and the baseline models both quantitatively and qualitatively. Evaluated by both the Recall-Oriented Understudy for Gisting Evaluation metrics and domain experts, our results show that N2MAG outperformed the existing state-of-the-art baseline models.
Conclusions: N2MAG could generate a medical assessment from the Subject and Objective section descriptions in EHR notes. Future work will assess its potential for providing clinical decision support.
[JMIR Med Inform 2020;8(1):e14971]},
language = {en},
number = {1},
urldate = {2020-04-07},
journal = {JMIR Medical Informatics},
author = {Hu, Baotian and Bajracharya, Adarsha and Yu, Hong},
year = {2020},
pmid = {31939742 PMCID: PMC7006435},
note = {Company: JMIR Medical Informatics
Distributor: JMIR Medical Informatics
Institution: JMIR Medical Informatics
Label: JMIR Medical Informatics
Publisher: JMIR Publications Inc., Toronto, Canada},
pages = {e14971},
}
Downloads: 0
{"_id":"QZEsETDRdL3J3QYEg","bibbaseid":"hu-bajracharya-yu-generatingmedicalassessmentsusinganeuralnetworkmodelalgorithmdevelopmentandvalidation-2020","author_short":["Hu, B.","Bajracharya, A.","Yu, H."],"bibdata":{"bibtype":"article","type":"article","title":"Generating Medical Assessments Using a Neural Network Model: Algorithm Development and Validation","volume":"8","copyright":"Unless stated otherwise, all articles are open-access distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work (","shorttitle":"Generating Medical Assessments Using a Neural Network Model","url":"https://medinform.jmir.org/2020/1/e14971/","doi":"10.2196/14971","abstract":"Background: Since its inception, artificial intelligence has aimed to use computers to help make clinical diagnoses. Evidence-based medical reasoning is important for patient care. Inferring clinical diagnoses is a crucial step during the patient encounter. Previous works mainly used expert systems or machine learning–based methods to predict the International Classification of Diseases - Clinical Modification codes based on electronic health records. We report an alternative approach: inference of clinical diagnoses from patients’ reported symptoms and physicians’ clinical observations. Objective: We aimed to report a natural language processing system for generating medical assessments based on patient information described in the electronic health record (EHR) notes. Methods: We processed EHR notes into the Subjective, Objective, Assessment, and Plan sections. We trained a neural network model for medical assessment generation (N2MAG). Our N2MAG is an innovative deep neural model that uses the Subjective and Objective sections of an EHR note to automatically generate an “expert-like” assessment of the patient. N2MAG can be trained in an end-to-end fashion and does not require feature engineering and external knowledge resources. Results: We evaluated N2MAG and the baseline models both quantitatively and qualitatively. Evaluated by both the Recall-Oriented Understudy for Gisting Evaluation metrics and domain experts, our results show that N2MAG outperformed the existing state-of-the-art baseline models. Conclusions: N2MAG could generate a medical assessment from the Subject and Objective section descriptions in EHR notes. Future work will assess its potential for providing clinical decision support. [JMIR Med Inform 2020;8(1):e14971]","language":"en","number":"1","urldate":"2020-04-07","journal":"JMIR Medical Informatics","author":[{"propositions":[],"lastnames":["Hu"],"firstnames":["Baotian"],"suffixes":[]},{"propositions":[],"lastnames":["Bajracharya"],"firstnames":["Adarsha"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]}],"year":"2020","pmid":"31939742 PMCID: PMC7006435","note":"Company: JMIR Medical Informatics Distributor: JMIR Medical Informatics Institution: JMIR Medical Informatics Label: JMIR Medical Informatics Publisher: JMIR Publications Inc., Toronto, Canada","pages":"e14971","bibtex":"@article{hu_generating_2020,\n\ttitle = {Generating {Medical} {Assessments} {Using} a {Neural} {Network} {Model}: {Algorithm} {Development} and {Validation}},\n\tvolume = {8},\n\tcopyright = {Unless stated otherwise, all articles are open-access distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work (},\n\tshorttitle = {Generating {Medical} {Assessments} {Using} a {Neural} {Network} {Model}},\n\turl = {https://medinform.jmir.org/2020/1/e14971/},\n\tdoi = {10.2196/14971},\n\tabstract = {Background: Since its inception, artificial intelligence has aimed to use computers to help make clinical diagnoses. Evidence-based medical reasoning is important for patient care. Inferring clinical diagnoses is a crucial step during the patient encounter. Previous works mainly used expert systems or machine learning–based methods to predict the International Classification of Diseases - Clinical Modification codes based on electronic health records. We report an alternative approach: inference of clinical diagnoses from patients’ reported symptoms and physicians’ clinical observations.\n Objective: We aimed to report a natural language processing system for generating medical assessments based on patient information described in the electronic health record (EHR) notes.\n Methods: We processed EHR notes into the Subjective, Objective, Assessment, and Plan sections. We trained a neural network model for medical assessment generation (N2MAG). Our N2MAG is an innovative deep neural model that uses the Subjective and Objective sections of an EHR note to automatically generate an “expert-like” assessment of the patient. N2MAG can be trained in an end-to-end fashion and does not require feature engineering and external knowledge resources.\n Results: We evaluated N2MAG and the baseline models both quantitatively and qualitatively. Evaluated by both the Recall-Oriented Understudy for Gisting Evaluation metrics and domain experts, our results show that N2MAG outperformed the existing state-of-the-art baseline models.\n Conclusions: N2MAG could generate a medical assessment from the Subject and Objective section descriptions in EHR notes. Future work will assess its potential for providing clinical decision support.\n [JMIR Med Inform 2020;8(1):e14971]},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2020-04-07},\n\tjournal = {JMIR Medical Informatics},\n\tauthor = {Hu, Baotian and Bajracharya, Adarsha and Yu, Hong},\n\tyear = {2020},\n\tpmid = {31939742 PMCID: PMC7006435},\n\tnote = {Company: JMIR Medical Informatics\nDistributor: JMIR Medical Informatics\nInstitution: JMIR Medical Informatics\nLabel: JMIR Medical Informatics\nPublisher: JMIR Publications Inc., Toronto, Canada},\n\tpages = {e14971},\n}\n\n","author_short":["Hu, B.","Bajracharya, A.","Yu, H."],"key":"hu_generating_2020","id":"hu_generating_2020","bibbaseid":"hu-bajracharya-yu-generatingmedicalassessmentsusinganeuralnetworkmodelalgorithmdevelopmentandvalidation-2020","role":"author","urls":{"Paper":"https://medinform.jmir.org/2020/1/e14971/"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"http://fenway.cs.uml.edu/papers/pubs-all.bib","dataSources":["TqaA9miSB65nRfS5H"],"keywords":[],"search_terms":["generating","medical","assessments","using","neural","network","model","algorithm","development","validation","hu","bajracharya","yu"],"title":"Generating Medical Assessments Using a Neural Network Model: Algorithm Development and Validation","year":2020}