ABSTRACT
BACKGROUND: As acceptance of artificial intelligence [AI] platforms increases, more patients will consider these tools as sources of information. The ChatGPT architecture utilizes a neural network to process natural language, thus generating responses based on the context of input text. The accuracy and completeness of ChatGPT3.5 in the context of inflammatory bowel disease [IBD] remains unclear. METHODS: In this prospective study, 38 questions worded by IBD patients were inputted into ChatGPT3.5. The following topics were covered: [1] Crohn's disease [CD], ulcerative colitis [UC], and malignancy; [2] maternal medicine; [3] infection and vaccination; and [4] complementary medicine. Responses given by ChatGPT were assessed for accuracy [1-completely incorrect to 5-completely correct] and completeness [3-point Likert scale; range 1-incomplete to 3-complete] by 14 expert gastroenterologists, in comparison with relevant ECCO guidelines. RESULTS: In terms of accuracy, most replies [84.2%] had a median score of ≥4 (interquartile range [IQR]: 2) and a mean score of 3.87 [SD: ±0.6]. For completeness, 34.2% of the replies had a median score of 3 and 55.3% had a median score of between 2 and <3. Overall, the mean rating was 2.24 [SD: ±0.4, median: 2, IQR: 1]. Though groups 3 and 4 had a higher mean for both accuracy and completeness, there was no significant scoring variation between the four question groups [Kruskal-Wallis test p > 0.05]. However, statistical analysis for the different individual questions revealed a significant difference for both accuracy [pâ <â 0.001] and completeness [pâ <â 0.001]. The questions which rated the highest for both accuracy and completeness were related to smoking, while the lowest rating was related to screening for malignancy and vaccinations especially in the context of immunosuppression and family planning. CONCLUSION: This is the first study to demonstrate the capability of an AI-based system to provide accurate and comprehensive answers to real-world patient queries in IBD. AI systems may serve as a useful adjunct for patients, in addition to standard of care in clinics and validated patient information resources. However, responses in specialist areas may deviate from evidence-based guidance and the replies need to give more firm advice.
Subject(s)
Inflammatory Bowel Diseases , Humans , Prospective Studies , Artificial Intelligence , Practice Guidelines as Topic , Vaccination/standards , Complementary Therapies/methods , Colitis, Ulcerative , Crohn Disease , Natural Language Processing , Female , Patient Education as Topic/methods , NeoplasmsABSTRACT
Generative Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, including Question-Answering (QA) and dialogue systems. However, most models are trained on English data and lack strong generalization in providing answers in Chinese. This limitation is especially evident in specialized domains like traditional Chinese medical QA, where performance suffers due to the absence of fine-tuning and high-quality datasets. To address this, we introduce MedChatZH, a dialogue model optimized for Chinese medical QA based on transformer decoder with LLaMA architecture. Continued pre-training on a curated corpus of Chinese medical books is followed by fine-tuning with a carefully selected medical instruction dataset, resulting in MedChatZH outperforming several Chinese dialogue baselines on a real-world medical dialogue dataset. Our model, code, and dataset are publicly available on GitHub (https://github.com/tyang816/MedChatZH) to encourage further research in traditional Chinese medicine and LLMs.
Subject(s)
Education, Medical , Medicine, Chinese Traditional , Language , Referral and Consultation , Natural Language Processing , Artificial IntelligenceABSTRACT
AIMS: This study aimed to develop and apply natural language processing (NLP) algorithms to identify recurrent atrial fibrillation (AF) episodes following rhythm control therapy initiation using electronic health records (EHRs). METHODS AND RESULTS: We included adults with new-onset AF who initiated rhythm control therapies (ablation, cardioversion, or antiarrhythmic medication) within two US integrated healthcare delivery systems. A code-based algorithm identified potential AF recurrence using diagnosis and procedure codes. An automated NLP algorithm was developed and validated to capture AF recurrence from electrocardiograms, cardiac monitor reports, and clinical notes. Compared with the reference standard cases confirmed by physicians' adjudication, the F-scores, sensitivity, and specificity were all above 0.90 for the NLP algorithms at both sites. We applied the NLP and code-based algorithms to patients with incident AF (n = 22 970) during the 12 months after initiating rhythm control therapy. Applying the NLP algorithms, the percentages of patients with AF recurrence for sites 1 and 2 were 60.7% and 69.9% (ablation), 64.5% and 73.7% (cardioversion), and 49.6% and 55.5% (antiarrhythmic medication), respectively. In comparison, the percentages of patients with code-identified AF recurrence for sites 1 and 2 were 20.2% and 23.7% for ablation, 25.6% and 28.4% for cardioversion, and 20.0% and 27.5% for antiarrhythmic medication, respectively. CONCLUSION: When compared with a code-based approach alone, this study's high-performing automated NLP method identified significantly more patients with recurrent AF. The NLP algorithms could enable efficient evaluation of treatment effectiveness of AF therapies in large populations and help develop tailored interventions.
Subject(s)
Atrial Fibrillation , Electronic Health Records , Adult , Humans , Atrial Fibrillation/epidemiology , Atrial Fibrillation/therapy , Natural Language Processing , Treatment Outcome , AlgorithmsABSTRACT
OBJECTIVE: To construct an exhaustive Complementary and Integrative Health (CIH) Lexicon (CIHLex) to help better represent the often underrepresented physical and psychological CIH approaches in standard terminologies, and to also apply state-of-the-art natural language processing (NLP) techniques to help recognize them in the biomedical literature. MATERIALS AND METHODS: We constructed the CIHLex by integrating various resources, compiling and integrating data from biomedical literature and relevant sources of knowledge. The Lexicon encompasses 724 unique concepts with 885 corresponding unique terms. We matched these concepts to the Unified Medical Language System (UMLS), and we developed and utilized BERT models comparing their efficiency in CIH named entity recognition to well-established models including MetaMap and CLAMP, as well as the large language model GPT3.5-turbo. RESULTS: Of the 724 unique concepts in CIHLex, 27.2% could be matched to at least one term in the UMLS. About 74.9% of the mapped UMLS Concept Unique Identifiers were categorized as "Therapeutic or Preventive Procedure." Among the models applied to CIH named entity recognition, BLUEBERT delivered the highest macro-average F1-score of 0.91, surpassing other models. CONCLUSION: Our CIHLex significantly augments representation of CIH approaches in biomedical literature. Demonstrating the utility of advanced NLP models, BERT notably excelled in CIH entity recognition. These results highlight promising strategies for enhancing standardization and recognition of CIH terminology in biomedical contexts.
Subject(s)
Algorithms , Unified Medical Language System , Natural Language Processing , LanguageABSTRACT
As dialogue agents become increasingly human-like in their performance, we must develop effective ways to describe their behaviour in high-level terms without falling into the trap of anthropomorphism. Here we foreground the concept of role play. Casting dialogue-agent behaviour in terms of role play allows us to draw on familiar folk psychological terms, without ascribing human characteristics to language models that they in fact lack. Two important cases of dialogue-agent behaviour are addressed this way, namely, (apparent) deception and (apparent) self-awareness.
Subject(s)
Imitative Behavior , Natural Language Processing , Terminology as Topic , Humans , Deception , Self-AssessmentABSTRACT
OBJECTIVE: Apply natural language processing (NLP) to Amazon consumer reviews to identify adverse events (AEs) associated with unapproved over the counter (OTC) homeopathic drugs and compare findings with reports to the US Food and Drug Administration Adverse Event Reporting System (FAERS). MATERIALS AND METHODS: Data were extracted from publicly available Amazon reviews and analyzed using JMP 16 Pro Text Explorer. Topic modeling identified themes. Sentiment analysis (SA) explored consumer perceptions. A machine learning model optimized prediction of AEs in reviews. Reports for the same time interval and product class were obtained from the FAERS public dashboard and analyzed. RESULTS: Homeopathic cough/cold products were the largest category common to both data sources (Amazon = 616, FAERS = 445) and were analyzed further. Oral symptoms and unpleasant taste were described in both datasets. Amazon reviews describing an AE had lower Amazon ratings (X2 = 224.28, P < .0001). The optimal model for predicting AEs was Neural Boosted 5-fold combining topic modeling and Amazon ratings as predictors (mean AUC = 0.927). DISCUSSION: Topic modeling and SA of Amazon reviews provided information about consumers' perceptions and opinions of homeopathic OTC cough and cold products. Amazon ratings appear to be a good indicator of the presence or absence of AEs, and identified events were similar to FAERS. CONCLUSION: Amazon reviews may complement traditional data sources to identify AEs associated with unapproved OTC homeopathic products. This study is the first to use NLP in this context and lays the groundwork for future larger scale efforts.
Subject(s)
Adverse Drug Reaction Reporting Systems , Drug-Related Side Effects and Adverse Reactions , United States , Humans , Natural Language Processing , Software , United States Food and Drug Administration , CoughABSTRACT
BACKGROUND: Kampo medicine is widely used in Japan; however, most physicians and pharmacists have insufficient knowledge and experience in it. Although a chatbot-style system using machine learning and natural language processing has been used in some clinical settings and proven useful, the system developed specifically for the Japanese language using this method has not been validated by research. The purpose of this study is to develop a novel drug information provision system for Kampo medicines using a natural language classifier® (NLC®) based on IBM Watson. METHODS: The target Kampo formulas were 33 formulas listed in the 17th revision of the Japanese Pharmacopoeia. The information included in the system comes from the package inserts of Kampo medicines, Manuals for Management of Individual Serious Adverse Drug Reactions, and data on off-label usage. The system developed in this study classifies questions about the drug information of Kampo formulas input by natural language into preset questions and outputs preset answers for the questions. The system uses morphological analysis, synonym conversion by thesaurus, and NLC®. We fine-tuned the information registered into NLC® and increased the thesaurus. To validate the system, 900 validation questions were provided by six pharmacists who were classified into high or low levels of knowledge and experience of Kampo medicines and three pharmacy students. RESULTS: The precision, recall, and F-measure of the system performance were 0.986, 0.915, and 0.949, respectively. The results were stable even with differences in the amount of expertise of the question authors. CONCLUSIONS: We developed a system using natural language classification that can give appropriate answers to most of the validation questions.
Subject(s)
Medicine, Kampo , Physicians , Humans , Natural Language Processing , Pharmacists , Technology , JapanABSTRACT
PROBLEM: Although holistic review has been used successfully in some residency programs to decrease bias, such review is time-consuming and unsustainable for many programs without initial prescreening. The unstructured qualitative data in residency applications, including notable experiences, letters of recommendation, personal statement, and medical student performance evaluations, require extensive time, resources, and metrics to evaluate; therefore, previous applicant screening relied heavily on quantitative metrics, which can be socioeconomically and racially biased. APPROACH: Using residency applications to the University of Utah internal medicine-pediatrics program from 2015 to 2019, the authors extracted relevant snippets of text from the narrative sections of applications. Expert reviewers annotated these snippets into specific values (academic strength; intellectual curiosity; compassion; communication; work ethic; teamwork; leadership; self-awareness; diversity, equity, and inclusion; professionalism; and adaptability) previously identified as associated with resident success. The authors prospectively applied a machine learning model (MLM) to snippets from applications from 2023, and output was compared with a manual holistic review performed without knowledge of MLM results. OUTCOMES: Overall, the MLM had a sensitivity of 0.64, specificity of 0.97, positive predictive value of 0.62, negative predictive value of 0.97, and F1 score of 0.63. The mean (SD) total number of annotations per application was significantly correlated with invited for interview status (invited: 208.6 [59.1]; not invited: 145.2 [57.2]; P < .001). In addition, 8 of the 10 individual values were significantly predictive of an applicant's invited for interview status. NEXT STEPS: The authors created an MLM that can identify several values important for resident success in internal medicine-pediatrics programs with moderate sensitivity and high specificity. The authors will continue to refine the MLM by increasing the number of annotations, exploring parameter tuning and feature engineering options, and identifying which application sections have the highest correlation with invited for interview status.
Subject(s)
Internship and Residency , Humans , Child , Natural Language Processing , Internal Medicine/education , Professionalism , CommunicationABSTRACT
There is widespread use of dietary supplements, some prescribed but many taken without a physician's guidance. There are many potential interactions between supplements and both over-the-counter and prescription medications in ways that are unknown to patients. Structured medical records do not adequately document supplement use; however, unstructured clinical notes often contain extra information on supplements. We studied a group of 377 patients from three healthcare facilities and developed a natural language processing (NLP) tool to detect supplement use. Using surveys of these patients, we investigated the correlation between self-reported supplement use and NLP extractions from the clinical notes. Our model achieved an F1 score of 0.914 for detecting all supplements. Individual supplement detection had a variable correlation with survey responses, ranging from an F1 of 0.83 for calcium to an F1 of 0.39 for folic acid. Our study demonstrated good NLP performance while also finding that self-reported supplement use is not always consistent with the documented use in clinical records.
Subject(s)
Electronic Health Records , Natural Language Processing , Humans , Dietary Supplements , Self ReportABSTRACT
During the production and processing of tea, harmful substances are often introduced. However, they have never been systematically integrated, and it is impossible to understand the harmful substances that may be introduced during tea production and their related relationships when searching for papers. To address these issues, a database on tea risk substances and their research relationships was constructed. These data were correlated by knowledge mapping techniques, and a Neo4j graph database centered on tea risk substance research was constructed, containing 4189 nodes and 9400 correlations (e.g. research category-PMID, risk substance category-PMID, and risk substance-PMID). This is the first knowledge-based graph database that is specifically designed for integrating and analyzing risk substances in tea and related research, containing nine main types of tea risk substances (including a comprehensive discussion of inclusion pollutants, heavy metals, pesticides, environmental pollutants, mycotoxins, microorganisms, radioactive isotopes, plant growth regulators, and others) and six types of tea research papers (including reviews, safety evaluations/risk assessments, prevention and control measures, detection methods, residual/pollution situations, and data analysis/data measurement). It is an essential reference for exploring the causes of the formation of risk substances in tea and the safety standards of tea in the future. Database URL http://trsrd.wpengxs.cn.
Subject(s)
Natural Language Processing , Pattern Recognition, Automated , Databases, Factual , Knowledge , TeaABSTRACT
BACKGROUND: Musculoskeletal pain is common in the Veterans Health Administration (VHA), and there is growing national use of chiropractic services within the VHA. Rapid expansion requires scalable and autonomous solutions, such as natural language processing (NLP), to monitor care quality. Previous work has defined indicators of pain care quality that represent essential elements of guideline-concordant, comprehensive pain assessment, treatment planning, and reassessment. OBJECTIVE: Our purpose was to identify pain care quality indicators and assess patterns across different clinic visit types using NLP on VHA chiropractic clinic documentation. METHODS: Notes from ambulatory or in-hospital chiropractic care visits from October 1, 2018 to September 30, 2019 for patients in the Women Veterans Cohort Study were included in the corpus, with visits identified as consultation visits and/or evaluation and management (E&M) visits. Descriptive statistics of pain care quality indicator classes were calculated and compared across visit types. RESULTS: There were 11,752 patients who received any chiropractic care during FY2019, with 63,812 notes included in the corpus. Consultation notes had more than twice the total number of annotations per note (87.9) as follow-up visit notes (34.7). The mean number of total classes documented per note across the entire corpus was 9.4 (standard deviation [SD] = 1.5). More total indicator classes were documented during consultation visits with (mean = 14.8, SD = 0.9) or without E&M (mean = 13.9, SD = 1.2) compared to follow-up visits with (mean = 9.1, SD = 1.4) or without E&M (mean = 8.6, SD = 1.5). Co-occurrence of pain care quality indicators describing pain assessment was high. CONCLUSION: VHA chiropractors frequently document pain care quality indicators, identifiable using NLP, with variability across different visit types.
Subject(s)
Chiropractic , Humans , Female , Quality Indicators, Health Care , Veterans Health , Natural Language Processing , Cohort Studies , Quality of Health Care , PainABSTRACT
OBJECTIVE: We propose a system, quEHRy, to retrieve precise, interpretable answers to natural language questions from structured data in electronic health records (EHRs). MATERIALS AND METHODS: We develop/synthesize the main components of quEHRy: concept normalization (MetaMap), time frame classification (new), semantic parsing (existing), visualization with question understanding (new), and query module for FHIR mapping/processing (new). We evaluate quEHRy on 2 clinical question answering (QA) datasets. We evaluate each component separately as well as holistically to gain deeper insights. We also conduct a thorough error analysis for a crucial subcomponent, medical concept normalization. RESULTS: Using gold concepts, the precision of quEHRy is 98.33% and 90.91% for the 2 datasets, while the overall accuracy was 97.41% and 87.75%. Precision was 94.03% and 87.79% even after employing an automated medical concept extraction system (MetaMap). Most incorrectly predicted medical concepts were broader in nature than gold-annotated concepts (representative of the ones present in EHRs), eg, Diabetes versus Diabetes Mellitus, Non-Insulin-Dependent. DISCUSSION: The primary performance barrier to deployment of the system is due to errors in medical concept extraction (a component not studied in this article), which affects the downstream generation of correct logical structures. This indicates the need to build QA-specific clinical concept normalizers that understand EHR context to extract the "relevant" medical concepts from questions. CONCLUSION: We present an end-to-end QA system that allows information access from EHRs using natural language and returns an exact, verifiable answer. Our proposed system is high-precision and interpretable, checking off the requirements for clinical use.
Subject(s)
Electronic Health Records , Natural Language Processing , Semantics , Access to Information , GoldABSTRACT
PROBLEM: Reviewing residency application narrative components is time intensive and has contributed to nearly half of applications not receiving holistic review. The authors developed a natural language processing (NLP)-based tool to automate review of applicants' narrative experience entries and predict interview invitation. APPROACH: Experience entries (n = 188,500) were extracted from 6,403 residency applications across 3 application cycles (2017-2019) at 1 internal medicine program, combined at the applicant level, and paired with the interview invitation decision (n = 1,224 invitations). NLP identified important words (or word pairs) with term frequency-inverse document frequency, which were used to predict interview invitation using logistic regression with L1 regularization. Terms remaining in the model were analyzed thematically. Logistic regression models were also built using structured application data and a combination of NLP and structured data. Model performance was evaluated on never-before-seen data using area under the receiver operating characteristic and precision-recall curves (AUROC, AUPRC). OUTCOMES: The NLP model had an AUROC of 0.80 (vs chance decision of 0.50) and AUPRC of 0.49 (vs chance decision of 0.19), showing moderate predictive strength. Phrases indicating active leadership, research, or work in social justice and health disparities were associated with interview invitation. The model's detection of these key selection factors demonstrated face validity. Adding structured data to the model significantly improved prediction (AUROC 0.92, AUPRC 0.73), as expected given reliance on such metrics for interview invitation. NEXT STEPS: This model represents a first step in using NLP-based artificial intelligence tools to promote holistic residency application review. The authors are assessing the practical utility of using this model to identify applicants screened out using traditional metrics. Generalizability must be determined through model retraining and evaluation at other programs. Work is ongoing to thwart model "gaming," improve prediction, and remove unwanted biases introduced during model training.
Subject(s)
Internship and Residency , Humans , Natural Language Processing , Artificial Intelligence , Personnel Selection , LeadershipABSTRACT
PURPOSE: Imaging reports in oncology provide critical information about the disease evolution that should be timely shared to tailor the clinical decision making and care coordination of patients with advanced cancer. However, tumor response stays unstructured in free-text and underexploited. Natural language processing (NLP) methods can help provide this critical information into the electronic health records (EHR) in real time to assist health care workers. METHODS: A rule-based algorithm was developed using SAS tools to automatically extract and categorize tumor response within progression or no progression categories. 2,970 magnetic resonance imaging, computed tomography scan, and positron emission tomography French reports were extracted from the EHR of a large comprehensive cancer center to build a 2,637-document training set and a 603-document validation set. The model was also tested on 189 imaging reports from 46 different radiology centers. A tumor dashboard was created in the EHR using the Timeline tool of the vis.js javascript library. RESULTS: An NLP methodology was applied to create an ontology of radiographic terms defining tumor response, mapping text to five main concepts, and application decision rules on the basis of clinical practice RECIST guidelines. The model achieved an overall accuracy of 0.88 (ranging from 0.87 to 0.94), with similar performance on both progression and no progression classification. The overall accuracy was 0.82 on reports from different radiology centers. Data were visualized and organized in a dynamic tumor response timeline. This tool was deployed successfully at our institution both retrospectively and prospectively as part of an automatic pipeline to screen reports and classify tumor response in real time for all metastatic patients. CONCLUSION: Our approach provides an NLP-based framework to structure and classify tumor response from the EHR and integrate tumor response classification into the clinical oncology workflow.
Subject(s)
Neoplasms , Radiology , Humans , Retrospective Studies , Natural Language Processing , Workflow , Neoplasms/diagnostic imaging , Neoplasms/therapy , Medical OncologyABSTRACT
Patients advise their peers on how to cope with their illness in daily life on online support groups. To date, no efforts have been made to automatically extract recommended coping strategies from online patient discussion groups. We introduce this new task, which poses a number of challenges including complex, long entities, a large long-tailed label space, and cross-document relations. We present an initial ontology for coping strategies as a starting point for future research on coping strategies, and the first end-to-end pipeline for extracting coping strategies for side effects. We also compared two possible computational solutions for this novel and highly challenging task; multi-label classification and named entity recognition (NER) with entity linking (EL). We evaluated our methods on the discussion forum from the Facebook group of the worldwide patient support organization 'GIST support international' (GSI); GIST support international donated the data to us. We found that coping strategy extraction is difficult and both methods attain limited performance (measured with F1 score) on held out test sets; multi-label classification outperforms NER+EL (F1=0.220 vs F1=0.155). An inspection of the multi-label classification output revealed that for some of the incorrect predictions, the reference label is close to the predicted label in the ontology (e.g. the predicted label 'juice' instead of the more specific reference label 'grapefruit juice'). Performance increased to F1=0.498 when we evaluated at a coarser level of the ontology. We conclude that our pipeline can be used in a semi-automatic setting, in interaction with domain experts to discover coping strategies for side effects from a patient forum. For example, we found that patients recommend ginger tea for nausea and magnesium and potassium supplements for cramps. This information can be used as input for patient surveys or clinical studies.
Subject(s)
Drug-Related Side Effects and Adverse Reactions , Gastrointestinal Stromal Tumors , Social Media , Humans , Natural Language ProcessingABSTRACT
STUDY OBJECTIVE: Patients undergoing diagnostic imaging studies in the emergency department (ED) commonly have incidental findings, which may represent unrecognized serious medical conditions, including cancer. Recognition of incidental findings frequently relies on manual review of textual radiology reports and can be overlooked in a busy clinical environment. Our study aimed to develop and validate a supervised machine learning model using natural language processing to automate the recognition of incidental findings in radiology reports of patients discharged from the ED. METHODS: We performed a retrospective analysis of computed tomography (CT) reports from trauma patients discharged home across an integrated health system in 2019. Two independent annotators manually labeled CT reports for the presence of an incidental finding as a reference standard. We used regular expressions to derive and validate a random forest model using open-source and machine learning software. Final model performance was assessed across different ED types. RESULTS: The study CT reports were divided into derivation (690 reports) and validation (282 reports) sets, with a prevalence of incidental findings of 22.3%, and 22.7%, respectively. The random forest model had an area under the curve of 0.88 (95% confidence interval [CI], 0.84 to 0.92) on the derivation set and 0.92 (95% CI, 0.88 to 0.96) on the validation set. The final model was found to have a sensitivity of 92.2%, a specificity of 79.4%, and a negative predictive value of 97.2%. Similarly, strong model performance was found when stratified to a dedicated trauma center, high-volume, and low-volume community EDs. CONCLUSION: Machine learning and natural language processing can classify incidental findings in CT reports of ED patients with high sensitivity and high negative predictive value across a broad range of ED settings. These findings suggest the utility of natural language processing in automating the review of free-text reports to identify incidental findings and may facilitate interventions to improve timely follow-up.
Subject(s)
Natural Language Processing , Radiology , Humans , Retrospective Studies , Patient Discharge , Machine Learning , Emergency Service, Hospital , Incidental FindingsABSTRACT
We sought to determine whether machine learning and natural language processing (NLP) applied to electronic medical records could improve performance of automated health-care claims-based algorithms to identify anaphylaxis events using data on 516 patients with outpatient, emergency department, or inpatient anaphylaxis diagnosis codes during 2015-2019 in 2 integrated health-care institutions in the Northwest United States. We used one site's manually reviewed gold-standard outcomes data for model development and the other's for external validation based on cross-validated area under the receiver operating characteristic curve (AUC), positive predictive value (PPV), and sensitivity. In the development site 154 (64%) of 239 potential events met adjudication criteria for anaphylaxis compared with 180 (65%) of 277 in the validation site. Logistic regression models using only structured claims data achieved a cross-validated AUC of 0.58 (95% CI: 0.54, 0.63). Machine learning improved cross-validated AUC to 0.62 (0.58, 0.66); incorporating NLP-derived covariates further increased cross-validated AUCs to 0.70 (0.66, 0.75) in development and 0.67 (0.63, 0.71) in external validation data. A classification threshold with cross-validated PPV of 79% and cross-validated sensitivity of 66% in development data had cross-validated PPV of 78% and cross-validated sensitivity of 56% in external data. Machine learning and NLP-derived data improved identification of validated anaphylaxis events.
Subject(s)
Anaphylaxis , Natural Language Processing , Humans , Anaphylaxis/diagnosis , Anaphylaxis/epidemiology , Machine Learning , Algorithms , Emergency Service, Hospital , Electronic Health RecordsABSTRACT
BACKGROUND: Natural language processing (NLP) of unstructured text from electronic medical records (EMR) can improve the characterization of COVID-19 signs and symptoms, but large-scale studies demonstrating the real-world application and validation of NLP for this purpose are limited. OBJECTIVE: The aim of this paper is to assess the contribution of NLP when identifying COVID-19 signs and symptoms from EMR. METHODS: This study was conducted in Kaiser Permanente Southern California, a large integrated health care system using data from all patients with positive SARS-CoV-2 laboratory tests from March 2020 to May 2021. An NLP algorithm was developed to extract free text from EMR on 12 established signs and symptoms of COVID-19, including fever, cough, headache, fatigue, dyspnea, chills, sore throat, myalgia, anosmia, diarrhea, vomiting or nausea, and abdominal pain. The proportion of patients reporting each symptom and the corresponding onset dates were described before and after supplementing structured EMR data with NLP-extracted signs and symptoms. A random sample of 100 chart-reviewed and adjudicated SARS-CoV-2-positive cases were used to validate the algorithm performance. RESULTS: A total of 359,938 patients (mean age 40.4 [SD 19.2] years; 191,630/359,938, 53% female) with confirmed SARS-CoV-2 infection were identified over the study period. The most common signs and symptoms identified through NLP-supplemented analyses were cough (220,631/359,938, 61%), fever (185,618/359,938, 52%), myalgia (153,042/359,938, 43%), and headache (144,705/359,938, 40%). The NLP algorithm identified an additional 55,568 (15%) symptomatic cases that were previously defined as asymptomatic using structured data alone. The proportion of additional cases with each selected symptom identified in NLP-supplemented analysis varied across the selected symptoms, from 29% (63,742/220,631) of all records for cough to 64% (38,884/60,865) of all records with nausea or vomiting. Of the 295,305 symptomatic patients, the median time from symptom onset to testing was 3 days using structured data alone, whereas the NLP algorithm identified signs or symptoms approximately 1 day earlier. When validated against chart-reviewed cases, the NLP algorithm successfully identified signs and symptoms with consistently high sensitivity (ranging from 87% to 100%) and specificity (94% to 100%). CONCLUSIONS: These findings demonstrate that NLP can identify and characterize a broad set of COVID-19 signs and symptoms from unstructured EMR data with enhanced detail and timeliness compared with structured data alone.
Subject(s)
COVID-19 , Humans , Female , Adult , Male , SARS-CoV-2 , Natural Language Processing , Myalgia , Cough/etiology , Headache/etiology , Fever/etiologyABSTRACT
Autistic spectrum disorder (ASD) is one of the most complex groups of neurobehavioral and developmental conditions. The reason is the presence of three different impaired domains, such as social interaction, communication, and restricted repetitive behaviors. Some children with ASD may not be able to communicate using language or speech. Many experts propose that continued therapy in the form of software training in this area might help to bring improvement. In this work, we propose a design of software speech therapy system for ASD. We combined different devices, technologies, and features with techniques of home rehabilitation. We used TensorFlow for Image Classification, ArKit for Text-to-Speech, Cloud Database, Binary Search, Natural Language Processing, Dataset of Sentences, and Dataset of Images with two different Operating Systems designed for Smart Mobile devices in daily life. This software is a combination of different Deep Learning Technologies and makes Human-Computer Interaction Therapy very easy to conduct. In addition, we explain the way these were connected and put to work together. Additionally, we explain in detail the architecture of software and how each component works together as an integrated Therapy System. Finally, it allows the patient with ASD to perform the therapy anytime and everywhere, as well as transmitting information to a medical specialist.
Subject(s)
Autism Spectrum Disorder , Child Development Disorders, Pervasive , Autism Spectrum Disorder/therapy , Child , Humans , Language , Linguistics , Natural Language ProcessingABSTRACT
PURPOSE: Although BRCA1/2 testing in ovarian cancer improves outcomes, it is vastly underutilized. Scalable approaches are urgently needed to improve genomically guided care. METHODS: We developed a Natural Language Processing (NLP) pipeline to extract electronic medical record information to identify recipients of BRCA testing. We applied the NLP pipeline to assess testing status in 308 patients with ovarian cancer receiving care at a National Cancer Institute Comprehensive Cancer Center (main campus [MC] and five affiliated clinical network sites [CNS]) from 2017 to 2019. We compared characteristics between (1) patients who had/had not received testing and (2) testing utilization by site. RESULTS: We found high uptake of BRCA testing (approximately 78%) from 2017 to 2019 with no significant differences between the MC and CNS. We observed an increase in testing over time (67%-85%), higher uptake of testing among younger patients (mean age tested = 61 years v untested = 65 years, P = .01), and higher testing among Hispanic (84%) compared with White, Non-Hispanic (78%), and Asian (75%) patients (P = .006). Documentation of referral for an internal genetics consultation for BRCA pathogenic variant carriers was higher at the MC compared with the CNS (94% v 31%). CONCLUSION: We were able to successfully use a novel NLP pipeline to assess use of BRCA testing among patients with ovarian cancer. Despite relatively high levels of BRCA testing at our institution, 22% of patients had no documentation of genetic testing and documentation of referral to genetics among BRCA carriers in the CNS was low. Given success of the NLP pipeline, such an informatics-based approach holds promise as a scalable solution to identify gaps in genetic testing to ensure optimal treatment interventions in a timely manner.