1
|
Osman M, Cooper R, Sayer AA, Witham MD. The use of natural language processing for the identification of ageing syndromes including sarcopenia, frailty and falls in electronic healthcare records: a systematic review. Age Ageing 2024; 53:afae135. [PMID: 38970549 PMCID: PMC11227113 DOI: 10.1093/ageing/afae135] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Indexed: 07/08/2024] Open
Abstract
BACKGROUND Recording and coding of ageing syndromes in hospital records is known to be suboptimal. Natural Language Processing algorithms may be useful to identify diagnoses in electronic healthcare records to improve the recording and coding of these ageing syndromes, but the feasibility and diagnostic accuracy of such algorithms are unclear. METHODS We conducted a systematic review according to a predefined protocol and in line with Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. Searches were run from the inception of each database to the end of September 2023 in PubMed, Medline, Embase, CINAHL, ACM digital library, IEEE Xplore and Scopus. Eligible studies were identified via independent review of search results by two coauthors and data extracted from each study to identify the computational method, source of text, testing strategy and performance metrics. Data were synthesised narratively by ageing syndrome and computational method in line with the Studies Without Meta-analysis guidelines. RESULTS From 1030 titles screened, 22 studies were eligible for inclusion. One study focussed on identifying sarcopenia, one frailty, twelve falls, five delirium, five dementia and four incontinence. Sensitivity (57.1%-100%) of algorithms compared with a reference standard was reported in 20 studies, and specificity (84.0%-100%) was reported in only 12 studies. Study design quality was variable with results relevant to diagnostic accuracy not always reported, and few studies undertaking external validation of algorithms. CONCLUSIONS Current evidence suggests that Natural Language Processing algorithms can identify ageing syndromes in electronic health records. However, algorithms require testing in rigorously designed diagnostic accuracy studies with appropriate metrics reported.
Collapse
Affiliation(s)
- Mo Osman
- AGE Research Group, Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, UK
- NIHR Newcastle Biomedical Research Centre, Newcastle upon Tyne NHS Foundation Trust, Cumbria Northumberland Tyne and Wear NHS Foundation Trust and Newcastle University, Newcastle upon Tyne, UK
| | - Rachel Cooper
- AGE Research Group, Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, UK
- NIHR Newcastle Biomedical Research Centre, Newcastle upon Tyne NHS Foundation Trust, Cumbria Northumberland Tyne and Wear NHS Foundation Trust and Newcastle University, Newcastle upon Tyne, UK
| | - Avan A Sayer
- AGE Research Group, Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, UK
- NIHR Newcastle Biomedical Research Centre, Newcastle upon Tyne NHS Foundation Trust, Cumbria Northumberland Tyne and Wear NHS Foundation Trust and Newcastle University, Newcastle upon Tyne, UK
| | - Miles D Witham
- AGE Research Group, Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, UK
- NIHR Newcastle Biomedical Research Centre, Newcastle upon Tyne NHS Foundation Trust, Cumbria Northumberland Tyne and Wear NHS Foundation Trust and Newcastle University, Newcastle upon Tyne, UK
| |
Collapse
|
2
|
Wang H, Alanis N, Haygood L, Swoboda TK, Hoot N, Phillips D, Knowles H, Stinson SA, Mehta P, Sambamoorthi U. Using natural language processing in emergency medicine health service research: A systematic review and meta-analysis. Acad Emerg Med 2024; 31:696-706. [PMID: 38757352 PMCID: PMC11246236 DOI: 10.1111/acem.14937] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2024] [Revised: 04/15/2024] [Accepted: 04/17/2024] [Indexed: 05/18/2024]
Abstract
OBJECTIVES Natural language processing (NLP) represents one of the adjunct technologies within artificial intelligence and machine learning, creating structure out of unstructured data. This study aims to assess the performance of employing NLP to identify and categorize unstructured data within the emergency medicine (EM) setting. METHODS We systematically searched publications related to EM research and NLP across databases including MEDLINE, Embase, Scopus, CENTRAL, and ProQuest Dissertations & Theses Global. Independent reviewers screened, reviewed, and evaluated article quality and bias. NLP usage was categorized into syndromic surveillance, radiologic interpretation, and identification of specific diseases/events/syndromes, with respective sensitivity analysis reported. Performance metrics for NLP usage were calculated and the overall area under the summary of receiver operating characteristic curve (SROC) was determined. RESULTS A total of 27 studies underwent meta-analysis. Findings indicated an overall mean sensitivity (recall) of 82%-87%, specificity of 95%, with the area under the SROC at 0.96 (95% CI 0.94-0.98). Optimal performance using NLP was observed in radiologic interpretation, demonstrating an overall mean sensitivity of 93% and specificity of 96%. CONCLUSIONS Our analysis revealed a generally favorable performance accuracy in using NLP within EM research, particularly in the realm of radiologic interpretation. Consequently, we advocate for the adoption of NLP-based research to augment EM health care management.
Collapse
Affiliation(s)
- Hao Wang
- Department of Emergency Medicine, JPS Health Network, 1500 S. Main St., Fort Worth, TX 76104
| | - Naomi Alanis
- Department of Emergency Medicine, JPS Health Network, 1500 S. Main St., Fort Worth, TX 76104
| | - Laura Haygood
- Health Sciences Librarian for Public Health, Brown University, 69 Brown St., Providence, RI 02912
| | - Thomas K. Swoboda
- Department of Emergency Medicine, The Valley Health System, Touro University Nevada School of Osteopathic Medicine, 657 N. Town Center Drive, Las Vegas, NV 89144
| | - Nathan Hoot
- Department of Emergency Medicine, JPS Health Network, 1500 S. Main St., Fort Worth, TX 76104
| | - Daniel Phillips
- Department of Emergency Medicine, JPS Health Network, 1500 S. Main St., Fort Worth, TX 76104
| | - Heidi Knowles
- Department of Emergency Medicine, JPS Health Network, 1500 S. Main St., Fort Worth, TX 76104
| | - Sara Ann Stinson
- Mary Couts Burnett Library, Burnett School of Medicine at Texas Christian University, 2800 S. University Dr., Fort Worth, TX 76109
| | - Prachi Mehta
- Department of Emergency Medicine, JPS Health Network, 1500 S. Main St., Fort Worth, TX 76104
| | - Usha Sambamoorthi
- College of Pharmacy, University of North Texas Health Science Center, 3500 Camp Bowie Blvd, Fort Worth, TX 76107
| |
Collapse
|
3
|
Pillai M, Blumke TL, Studnia J, Wang Y, Veigulis ZP, Ware AD, Hoover PJ, Carroll IR, Humphreys K, Osborne TF, Asch SM, Hernandez-Boussard T, Curtin CM. Improving postsurgical fall detection for older Americans using LLM-driven analysis of clinical narratives. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.06.25.24309480. [PMID: 38978655 PMCID: PMC11230313 DOI: 10.1101/2024.06.25.24309480] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/10/2024]
Abstract
Postsurgical falls have significant patient and societal implications but remain challenging to identify and track. Detecting postsurgical falls is crucial to improve patient care for older adults and reduce healthcare costs. Large language models (LLMs) offer a promising solution for reliable and automated fall detection using unstructured data in clinical notes. We tested several LLM prompting approaches to postsurgical fall detection in two different healthcare systems with three open-source LLMs. The Mixtral-8×7B zero-shot had the best performance at Stanford Health Care (PPV = 0.81, recall = 0.67) and the Veterans Health Administration (PPV = 0.93, recall = 0.94). These results demonstrate that LLMs can detect falls with little to no guidance and lay groundwork for applications of LLMs in fall prediction and prevention across many different settings.
Collapse
Affiliation(s)
- Malvika Pillai
- Veterans Affairs Palo Alto Health Care System, Palo Alto, California, USA
- Department of Medicine (Biomedical Informatics), Stanford University, Stanford, CA, USA
| | - Terri L Blumke
- National Center for Collaborative Healthcare Innovation, Palo Alto VA Healthcare System, Palo Alto, CA, USA
| | - Joachim Studnia
- Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA, USA
| | - Yuqing Wang
- Department of Medicine (Biomedical Informatics), Stanford University, Stanford, CA, USA
| | | | - Anna D Ware
- National Center for Collaborative Healthcare Innovation, Palo Alto VA Healthcare System, Palo Alto, CA, USA
| | - Peter J Hoover
- National Center for Collaborative Healthcare Innovation, Palo Alto VA Healthcare System, Palo Alto, CA, USA
| | - Ian R Carroll
- Department of Anesthesiology, Stanford University School of Medicine, Stanford, CA, USA
| | - Keith Humphreys
- Department of Psychiatry and the Behavioral Sciences, Stanford University, Stanford, CA USA
| | - Thomas F Osborne
- National Center for Collaborative Healthcare Innovation, Palo Alto VA Healthcare System, Palo Alto, CA, USA
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA
| | - Steven M Asch
- Veterans Affairs Palo Alto Health Care System, Palo Alto, California, USA
- Division of Primary Care and Population Health, Stanford University School of Medicine, Stanford, CA, USA
| | | | - Catherine M Curtin
- Veterans Affairs Palo Alto Health Care System, Palo Alto, California, USA
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA
| |
Collapse
|
4
|
Spalding WM, Bertoia ML, Bulik CM, Seeger JD. Treatment characteristics among patients with binge-eating disorder: an electronic health records analysis. Postgrad Med 2023; 135:254-264. [PMID: 35037815 DOI: 10.1080/00325481.2021.2018255] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Abstract
OBJECTIVES Treatment for adults diagnosed with binge-eating disorder (BED) includes psychotherapy and/or pharmacotherapy and aims to reduce the frequency of binge-eating episodes and disordered eating, improve metabolic-related issues and reduce weight, and address mood symptoms. Data describing real-world treatment patterns are lacking; therefore, this study aims to characterize real-world treatment patterns among patients with BED. METHODS This retrospective study identified adult patients with BED using natural language processing of clinical notes from the Optum electronic health record database from 2009 to 2015. Treatment patterns were examined during the 12 months preceding the BED recognition date and during a follow-up period after BED recognition (1-3 years for most patients). RESULTS Among 1042 patients, 384 were categorized as the BED cohort and 658, who met less stringent criteria, were categorized as probable BED. In the BED cohort, mean ± SD age was 45.2 ± 13.4 years and 81.8% were women (probable BED, 45.9 ± 12.8 years, 80.2%). A greater percentage of patients in the BED cohort were prescribed pharmacotherapy (70.6% [probable BED, 66.9%]) than received/discussed psychotherapy (53.1% [probable BED, 39.2%]) at baseline. In the BED cohort, 54.4% of patients were prescribed antidepressants (probable BED, 52.4%), 25.3% stimulants (probable BED, 20.1%), and 34.4% nonspecific psychotherapy (probable BED, 24.6%) at baseline, with no substantive differences observed during follow-up. Low percentages of patients in the BED cohort received/discussed cognitive behavioral therapy at baseline (12.5% [probable BED, 9.0%) or during follow-up (13.0% [probable BED, 8.8%). Among patients with ≥1 psychotherapy visit, the mean ± SD number of visits in the BED cohort was 1.2 ± 5.9 at baseline (probable BED, 1.7 ± 7.3) and 2.2 ± 7.7 during follow-up (probable BED, 2.6 ± 7.7). CONCLUSION This cohort of patients with BED was treated more frequently with pharmacotherapy than psychotherapy. These data may help inform strategies for reducing differences between real-world treatment patterns and evidence-based recommendations.
Collapse
Affiliation(s)
| | | | - Cynthia M Bulik
- Department of Psychiatry, University of North Carolina School of Medicine, Chapel Hill, NC, USA
- Department of Nutrition, Gillings School of Global Public Health, University of North Carolina, Chapel Hill, NC, USA
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden
| | | |
Collapse
|
5
|
Stortenbeker I, Salm L, Olde Hartman T, Stommel W, Das E, van Dulmen S. Coding linguistic elements in clinical interactions: a step-by-step guide for analyzing communication form. BMC Med Res Methodol 2022; 22:191. [PMID: 35820827 PMCID: PMC9277943 DOI: 10.1186/s12874-022-01647-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2022] [Accepted: 05/31/2022] [Indexed: 05/31/2023] Open
Abstract
Background The quality of communication between healthcare professionals (HCPs) and patients affects health outcomes. Different coding systems have been developed to unravel the interaction. Most schemes consist of predefined categories that quantify the content of communication (the what). Though the form (the how) of the interaction is equally important, protocols that systematically code variations in form are lacking. Patterns of form and how they may differ between groups therefore remain unnoticed. To fill this gap, we present CLECI, Coding Linguistic Elements in Clinical Interactions, a protocol for the development of a quantitative codebook analyzing communication form in medical interactions. Methods Analyzing with a CLECI codebook is a four-step process, i.e. preparation, codebook development, (double-)coding, and analysis and report. Core activities within these phases are research question formulation, data collection, selection of utterances, iterative deductive and inductive category refinement, reliability testing, coding, analysis, and reporting. Results and conclusion We present step-by-step instructions for a CLECI analysis and illustrate this process in a case study. We highlight theoretical and practical issues as well as the iterative codebook development which combines theory-based and data-driven coding. Theory-based codes assess how relevant linguistic elements occur in natural interactions, whereas codes derived from the data accommodate linguistic elements to real-life interactions and contribute to theory-building. This combined approach increases research validity, enhances theory, and adjusts to fit naturally occurring data. CLECI will facilitate the study of communication form in clinical interactions and other institutional settings. Supplementary Information The online version contains supplementary material available at 10.1186/s12874-022-01647-0.
Collapse
Affiliation(s)
- Inge Stortenbeker
- Centre for Language Studies, Radboud University, Nijmegen, the Netherlands.
| | - Lisa Salm
- Centre for Language Studies, Radboud University, Nijmegen, the Netherlands
| | - Tim Olde Hartman
- Radboud university medical center, Radboud Institute for Health Sciences, Department of Primary and Community Care, Nijmegen, the Netherlands
| | - Wyke Stommel
- Centre for Language Studies, Radboud University, Nijmegen, the Netherlands
| | - Enny Das
- Centre for Language Studies, Radboud University, Nijmegen, the Netherlands
| | - Sandra van Dulmen
- Radboud university medical center, Radboud Institute for Health Sciences, Department of Primary and Community Care, Nijmegen, the Netherlands.,NIVEL (Netherlands institute for health services research), Utrecht, the Netherlands.,Faculty of Caring Science, University of Borås, Borås, Sweden
| |
Collapse
|
6
|
Fu S, Thorsteinsdottir B, Zhang X, Lopes GS, Pagali SR, LeBrasseur NK, Wen A, Liu H, Rocca WA, Olson JE, Sauver JS, Sohn S. A hybrid model to identify fall occurrence from electronic health records. Int J Med Inform 2022; 162:104736. [PMID: 35316697 PMCID: PMC9448825 DOI: 10.1016/j.ijmedinf.2022.104736] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/18/2021] [Revised: 01/29/2022] [Accepted: 03/04/2022] [Indexed: 12/14/2022]
Abstract
INTRODUCTION Falls are a leading cause of unintentional injury in the elderly. Electronic health records (EHRs) offer the unique opportunity to develop models that can identify fall events. However, identifying fall events in clinical notes requires advanced natural language processing (NLP) to simultaneously address multiple issues because the word "fall" is a typical homonym. METHODS We implemented a context-aware language model, Bidirectional Encoder Representations from Transformers (BERT) to identify falls from the EHR text and further fused the BERT model into a hybrid architecture coupled with post-hoc heuristic rules to enhance the performance. The models were evaluated on real world EHR data and were compared to conventional rule-based and deep learning models (CNN and Bi-LSTM). To better understand the ability of each approach to identify falls, we further categorize fall-related concepts (i.e., risk of fall, prevention of fall, homonym) and performed a detailed error analysis. RESULTS The hybrid model achieved the highest f1-score on sentence (0.971), document (0.985), and patient (0.954) level. At the sentence level (basic data unit in the model), the hybrid model had 0.954, 1.000, 0.988, and 0.999 in sensitivity, specificity, positive predictive value, and negative predictive value, respectively. The error analysis showed that that machine learning-based approaches demonstrated higher performance than a rule-based approach in challenging cases that required contextual understanding. The context-aware language model (BERT) slightly outperformed the word embedding approach trained on Bi-LSTM. No single model yielded the best performance for all fall-related semantic categories. CONCLUSION A context-aware language model (BERT) was able to identify challenging fall events that requires context understanding in EHR free text. The hybrid model combined with post-hoc rules allowed a custom fix on the BERT outcomes and further improved the performance of fall detection.
Collapse
Affiliation(s)
- Sunyang Fu
- Department of AI and Informatics, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA; University of Minnesota, Minneapolis, MN 55455, USA
| | | | - Xin Zhang
- Department of Medicine, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Guilherme S Lopes
- Department of Quantitative Health Sciences, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Sandeep R Pagali
- Department of Medicine, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Nathan K LeBrasseur
- Department of Physical Medicine & Rehabilitation, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA; Department of Physiology & Biomedical Engineering, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Andrew Wen
- Department of AI and Informatics, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Hongfang Liu
- Department of AI and Informatics, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Walter A Rocca
- Department of Quantitative Health Sciences, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA; Department of Neurology, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA; Women's Health Research Center, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Janet E Olson
- Department of Quantitative Health Sciences, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Jennifer St Sauver
- Department of Quantitative Health Sciences, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA
| | - Sunghwan Sohn
- Department of AI and Informatics, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA.
| |
Collapse
|
7
|
Taylor RA, Fiellin D, D’Onofrio G, Venkatesh A. Identifying opioid-related electronic health record phenotypes for emergency care research and surveillance: An expert consensus driven concept mapping process. Subst Abuse 2022; 43:841-847. [DOI: 10.1080/08897077.2021.1975864] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Affiliation(s)
- R. Andrew Taylor
- Department of Emergency Medicine, Yale University School of Medicine, New Haven, CT, USA
| | - David Fiellin
- Department of Medicine, Yale University School of Medicine, New Haven, CT, USA
| | - Gail D’Onofrio
- Department of Emergency Medicine, Yale University School of Medicine, New Haven, CT, USA
| | - Arjun Venkatesh
- Department of Emergency Medicine, Yale University School of Medicine, New Haven, CT, USA
| |
Collapse
|
8
|
Dedhia PH, Chen K, Song Y, LaRose E, Imbus JR, Peissig PL, Mendonca EA, Schneider DF. Ambiguous and Incomplete: Natural Language Processing Reveals Problematic Reporting Styles in Thyroid Ultrasound Reports. Methods Inf Med 2022; 61:11-18. [PMID: 34991173 DOI: 10.1055/s-0041-1740493] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Abstract
OBJECTIVE Natural language processing (NLP) systems convert unstructured text into analyzable data. Here, we describe the performance measures of NLP to capture granular details on nodules from thyroid ultrasound (US) reports and reveal critical issues with reporting language. METHODS We iteratively developed NLP tools using clinical Text Analysis and Knowledge Extraction System (cTAKES) and thyroid US reports from 2007 to 2013. We incorporated nine nodule features for NLP extraction. Next, we evaluated the precision, recall, and accuracy of our NLP tools using a separate set of US reports from an academic medical center (A) and a regional health care system (B) during the same period. Two physicians manually annotated each test-set report. A third physician then adjudicated discrepancies. The adjudicated "gold standard" was then used to evaluate NLP performance on the test-set. RESULTS A total of 243 thyroid US reports contained 6,405 data elements. Inter-annotator agreement for all elements was 91.3%. Compared with the gold standard, overall recall of the NLP tool was 90%. NLP recall for thyroid lobe or isthmus characteristics was: laterality 96% and size 95%. NLP accuracy for nodule characteristics was: laterality 92%, size 92%, calcifications 76%, vascularity 65%, echogenicity 62%, contents 76%, and borders 40%. NLP recall for presence or absence of lymphadenopathy was 61%. Reporting style accounted for 18% errors. For example, the word "heterogeneous" interchangeably referred to nodule contents or echogenicity. While nodule dimensions and laterality were often described, US reports only described contents, echogenicity, vascularity, calcifications, borders, and lymphadenopathy, 46, 41, 17, 15, 9, and 41% of the time, respectively. Most nodule characteristics were equally likely to be described at hospital A compared with hospital B. CONCLUSIONS NLP can automate extraction of critical information from thyroid US reports. However, ambiguous and incomplete reporting language hinders performance of NLP systems regardless of institutional setting. Standardized or synoptic thyroid US reports could improve NLP performance.
Collapse
Affiliation(s)
- Priya H Dedhia
- Department of Surgery, Division of Surgical Oncology, Ohio State University Comprehensive Cancer Center and Ohio State University Wexner Medical Center, Columbus, Ohio, United States
| | - Kallie Chen
- Department of Surgery, Division of Endocrine Surgery, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, United States
| | - Yiqiang Song
- Department of Biostatistics and Medical Informatics, Department of Pediatrics, University of Wisconsin-Madison, Madison, Wisconsin, United States
| | - Eric LaRose
- Center for Precision Medicine Research, Marshfield Clinic Research Institute, Marshfield Clinic Health System, Marshfield, Wisconsin, United States
| | - Joseph R Imbus
- Department of Surgery, Division of Endocrine Surgery, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, United States
| | - Peggy L Peissig
- Center for Precision Medicine Research, Marshfield Clinic Research Institute, Marshfield Clinic Health System, Marshfield, Wisconsin, United States
| | - Eneida A Mendonca
- Department of Biostatistics and Medical Informatics, Department of Pediatrics, University of Wisconsin-Madison, Madison, Wisconsin, United States.,Department of Pediatrics, Department of Biostatistics and Health Data Sciences, Indiana University, Indianapolis, Indiana, United States
| | - David F Schneider
- Department of Surgery, Division of Endocrine Surgery, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, United States
| |
Collapse
|
9
|
Tohira H, Finn J, Ball S, Brink D, Buzzacott P. Machine learning and natural language processing to identify falls in electronic patient care records from ambulance attendances. Inform Health Soc Care 2021; 47:403-413. [PMID: 34965817 DOI: 10.1080/17538157.2021.2019038] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Abstract
We derived machine learning models utilizing features generated by natural language processing (NLP) of free-text data from an ambulance services provider to identify fall cases. The data comprised samples of electronic patient care records care records (ePCRs) from St John Western Australia (WA), the sole ambulance services provider in most of WA. We manually labeled fall cases by reviewing the free-text summary. The models used features including case characteristics (e.g., age) and text frequency-inverse document frequency (tf-idf) of each word of the free-text generated by NLP. Support vector machine (SVM) and random forest were used as classifiers. We compared the performance of the models against the manual identification of falls by recall, precision, and F-measure. A total of 9,447 cases (1%) were randomly sampled, of which 1,648 (17%) were labeled as fall. The best model was an SVM model using case characteristics and tf-idf's of the first 100 words of free-text, with recall of 0.84, precision of 0.86, and F-measure of 0.85. This performance was better than an SVM model with only case characteristics. Machine-learning models incorporated with features generated by NLP improved the performance of classifying fall cases compared with models without such features. Scope remains for further improvement.
Collapse
Affiliation(s)
- Hideo Tohira
- Prehospital, Resuscitation and Emergency Care Research Unit, Curtin School of Nursing, Curtin University, Perth, Australia.,Discipline of Emergency Medicine, Medical School, The University of Western Australia, Perth, Australia
| | - Judith Finn
- Prehospital, Resuscitation and Emergency Care Research Unit, Curtin School of Nursing, Curtin University, Perth, Australia.,Discipline of Emergency Medicine, Medical School, The University of Western Australia, Perth, Australia.,Ambulance Operation, St John Western Australia, Belmont, Australia.,School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia
| | - Stephen Ball
- Prehospital, Resuscitation and Emergency Care Research Unit, Curtin School of Nursing, Curtin University, Perth, Australia.,Ambulance Operation, St John Western Australia, Belmont, Australia
| | - Deon Brink
- Ambulance Operation, St John Western Australia, Belmont, Australia
| | - Peter Buzzacott
- Prehospital, Resuscitation and Emergency Care Research Unit, Curtin School of Nursing, Curtin University, Perth, Australia
| |
Collapse
|
10
|
Chen KJ, Dedhia PH, Imbus JR, Schneider DF. Thyroid Ultrasound Reports: Will the Thyroid Imaging, Reporting, and Data System Improve Natural Language Processing Capture of Critical Thyroid Nodule Features? J Surg Res 2020; 256:557-563. [PMID: 32799005 PMCID: PMC8102071 DOI: 10.1016/j.jss.2020.07.015] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2020] [Revised: 06/29/2020] [Accepted: 07/11/2020] [Indexed: 02/06/2023]
Abstract
BACKGROUND Critical thyroid nodule features are contained in unstructured ultrasound (US) reports. The Thyroid Imaging, Reporting, and Data System (TI-RADS) uses five key features to risk stratify nodules and recommend appropriate intervention. This study aims to analyze the quality of US reporting and the potential benefit of Natural Language Processing (NLP) systems in efficiently capturing TI-RADS features from text reports. MATERIALS AND METHOD This retrospective study used free-text thyroid US reports from an academic center (A) and community hospital (B). Physicians created "gold standard" annotations by manually extracting TI-RADS features and clinical recommendations from reports to determine how often they were included. Similar annotations were created using an automated NLP system and compared with the gold standard. RESULTS Two hundred eighty-two reports contained 409 nodules at least 1-cm in maximum diameter. The gold standard identified three nodules (0.7%) which contained enough information to calculate a complete TI-RADS score. Shape was described most often (92.7% of nodules), whereas margins were described least often (11%). A median number of two TI-RADS features are reported per nodule. The NLP system was significantly less accurate than the gold standard in capturing echogenicity (27.5%) and margins (58.9%). One hundred eight nodule reports (26.4%) included clinical management recommendations, which were included more often at site A than B (33.9 versus 17%, P < 0.05). CONCLUSIONS These results suggest a gap between current US reporting styles and those needed to implement TI-RADS and achieve NLP accuracy. Synoptic reporting should prompt more complete thyroid US reporting, improved recommendations for intervention, and better NLP performance.
Collapse
Affiliation(s)
- Kallie J Chen
- Division of Endocrine Surgery at University of Wisconsin School of Medicine and Public Health, Department of Surgery, Madison, Wisconsin.
| | - Priya H Dedhia
- Division of Endocrine Surgery at University of Wisconsin School of Medicine and Public Health, Department of Surgery, Madison, Wisconsin
| | - Joseph R Imbus
- Division of Endocrine Surgery at University of Wisconsin School of Medicine and Public Health, Department of Surgery, Madison, Wisconsin
| | - David F Schneider
- Division of Endocrine Surgery at University of Wisconsin School of Medicine and Public Health, Department of Surgery, Madison, Wisconsin
| |
Collapse
|
11
|
Patterson BW, Jacobsohn GC, Maru AP, Venkatesh AK, Smith MA, Shah MN, Mendonça EA. RESEARCHComparing Strategies for Identifying Falls in Older Adult Emergency Department Visits Using EHR Data. J Am Geriatr Soc 2020; 68:2965-2967. [PMID: 32951200 DOI: 10.1111/jgs.16831] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2020] [Revised: 08/18/2020] [Accepted: 08/21/2020] [Indexed: 11/29/2022]
Affiliation(s)
- Brian W Patterson
- BerbeeWalsh Department of Emergency Medicine, University of Wisconsin-Madison School of Medicine and Public Health, Madison, Wisconsin.,Health Innovation Program, University of Wisconsin-Madison, Madison, Wisconsin.,Department of Industrial and Systems Engineering, Department of Biostatistics and Medical Informatics, University of Wisconsin, Madison, Wisconsin
| | - Gwen Costa Jacobsohn
- BerbeeWalsh Department of Emergency Medicine, University of Wisconsin-Madison School of Medicine and Public Health, Madison, Wisconsin
| | - Apoorva P Maru
- BerbeeWalsh Department of Emergency Medicine, University of Wisconsin-Madison School of Medicine and Public Health, Madison, Wisconsin
| | - Arjun K Venkatesh
- Department of Emergency Medicine and Center for Outcomes Research and Evaluation, Yale University School of Medicine, New Haven, Connecticut
| | - Maureen A Smith
- Health Innovation Program, University of Wisconsin-Madison, Madison, Wisconsin
| | - Manish N Shah
- BerbeeWalsh Department of Emergency Medicine, University of Wisconsin-Madison School of Medicine and Public Health, Madison, Wisconsin.,Division of Geriatrics and Gerontology, Department of Medicine, University of Wisconsin-Madison School of Medicine and Public Health, Madison, Wisconsin.,Department of Population Health Sciences, University of Wisconsin-Madison School of Medicine and Public Health, Madison, Wisconsin
| | - Eneida A Mendonça
- Department of Pediatrics and Biostatistics, Indiana University School of Medicine, Indianapolis, Indiana.,Regenstrief Institute, Indianapolis, Indiana
| |
Collapse
|