Utility of Machine Learning, Natural Language Processing, and Artificial Intelligence in Predicting Hospital Readmissions After Orthopaedic Surgery: A Systematic Review and Meta-Analysis.

BACKGROUND: Numerous applications and strategies have been utilized to help assess the trends and patterns of readmissions after orthopaedic surgery in an attempt to extrapolate possible risk factors and causative agents. The aim of this work is to systematically summarize the available literature on the extent to which natural language processing, machine learning, and artificial intelligence (AI) can help improve the predictability of hospital readmissions after orthopaedic and spine surgeries. METHODS: This is a systematic review and meta-analysis. PubMed, Embase and Google Scholar were searched, up until August 30, 2023, for studies that explore the use of AI, natural language processing, and machine learning tools for the prediction of readmission rates after orthopedic procedures. Data regarding surgery type, patient population, readmission outcomes, advanced models utilized, comparison methods, predictor sets, the inclusion of perioperative predictors, validation method, size of training and testing sample, accuracy, and receiver operating characteristics (C-statistic), among other factors, were extracted and assessed. RESULTS: A total of 26 studies were included in our final dataset. The overall summary C-statistic showed a mean of 0.71 across all models, indicating a reasonable level of predictiveness. A total of 15 articles (57%) were attributed to the spine, making it the most commonly explored orthopaedic field in our study. When comparing accuracy of prediction models between different fields, models predicting readmissions after hip/knee arthroplasty procedures had a higher prediction accuracy (mean C-statistic = 0.79) than spine (mean C-statistic = 0.7) and shoulder (mean C-statistic = 0.67). In addition, models that used single institution data, and those that included intraoperative and/or postoperative outcomes, had a higher mean C-statistic than those utilizing other data sources, and that include only preoperative predictors. According to the Prediction model Risk of Bias Assessment Tool, the majority of the articles in our study had a high risk of bias. CONCLUSION: AI tools perform reasonably well in predicting readmissions after orthopaedic procedures. Future work should focus on standardizing study methodologies and designs, and improving the data analysis process, in an attempt to produce more reliable and tangible results. LEVEL OF EVIDENCE: Level III. See Instructions for Authors for a complete description of levels of evidence.

Automated Extraction of Patient-Centered Outcomes After Breast Cancer Treatment: An Open-Source Large Language Model-Based Toolkit.

PURPOSE: Patient-centered outcomes (PCOs) are pivotal in cancer treatment, as they directly reflect patients' quality of life. Although multiple studies suggest that factors affecting breast cancer-related morbidity and survival are influenced by treatment side effects and adherence to long-term treatment, such data are generally only available on a smaller scale or from a single center. The primary challenge with collecting these data is that the outcomes are captured as free text in clinical narratives written by clinicians. MATERIALS AND METHODS: Given the complexity of PCO documentation in these narratives, computerized methods are necessary to unlock the wealth of information buried in unstructured text notes that often document PCOs. Inspired by the success of large language models (LLMs), we examined the adaptability of three LLMs, GPT-2, BioGPT, and PMC-LLaMA, on PCO tasks across three institutions, Mayo Clinic, Emory University Hospital, and Stanford University. We developed an open-source framework for fine-tuning LLM that can directly extract the five different categories of PCO from the clinic notes. RESULTS: We found that these LLMs without fine-tuning (zero-shot) struggle with challenging PCO extraction tasks, displaying almost random performance, even with some task-specific examples (few-shot learning). The performance of our fine-tuned, task-specific models is notably superior compared with their non-fine-tuned LLM models. Moreover, the fine-tuned GPT-2 model has demonstrated a significantly better performance than the other two larger LLMs. CONCLUSION: Our discovery indicates that although LLMs serve as effective general-purpose models for tasks across various domains, they require fine-tuning when applied to the clinician domain. Our proposed approach has the potential to lead more efficient, adaptable models for PCO information extraction, reducing reliance on extensive computational resources while still delivering superior performance for specific tasks.

Self-Administered Interventions Based on Natural Language Processing Models for Reducing Depressive and Anxiety Symptoms: Systematic Review and Meta-Analysis.

BACKGROUND: The introduction of natural language processing (NLP) technologies has significantly enhanced the potential of self-administered interventions for treating anxiety and depression by improving human-computer interactions. Although these advances, particularly in complex models such as generative artificial intelligence (AI), are highly promising, robust evidence validating the effectiveness of the interventions remains sparse. OBJECTIVE: The aim of this study was to determine whether self-administered interventions based on NLP models can reduce depressive and anxiety symptoms. METHODS: We conducted a systematic review and meta-analysis. We searched Web of Science, Scopus, MEDLINE, PsycINFO, IEEE Xplore, Embase, and Cochrane Library from inception to November 3, 2023. We included studies with participants of any age diagnosed with depression or anxiety through professional consultation or validated psychometric instruments. Interventions had to be self-administered and based on NLP models, with passive or active comparators. Outcomes measured included depressive and anxiety symptom scores. We included randomized controlled trials and quasi-experimental studies but excluded narrative, systematic, and scoping reviews. Data extraction was performed independently by pairs of authors using a predefined form. Meta-analysis was conducted using standardized mean differences (SMDs) and random effects models to account for heterogeneity. RESULTS: In all, 21 articles were selected for review, of which 76% (16/21) were included in the meta-analysis for each outcome. Most of the studies (16/21, 76%) were recent (2020-2023), with interventions being mostly AI-based NLP models (11/21, 52%); most (19/21, 90%) delivered some form of therapy (primarily cognitive behavioral therapy: 16/19, 84%). The overall meta-analysis showed that self-administered interventions based on NLP models were significantly more effective in reducing both depressive (SMD 0.819, 95% CI 0.389-1.250; P<.001) and anxiety (SMD 0.272, 95% CI 0.116-0.428; P=.001) symptoms compared to various control conditions. Subgroup analysis indicated that AI-based NLP models were effective in reducing depressive symptoms (SMD 0.821, 95% CI 0.207-1.436; P<.001) compared to pooled control conditions. Rule-based NLP models showed effectiveness in reducing both depressive (SMD 0.854, 95% CI 0.172-1.537; P=.01) and anxiety (SMD 0.347, 95% CI 0.116-0.578; P=.003) symptoms. The meta-regression showed no significant association between participants' mean age and treatment outcomes (all P>.05). Although the findings were positive, the overall certainty of evidence was very low, mainly due to a high risk of bias, heterogeneity, and potential publication bias. CONCLUSIONS: Our findings support the effectiveness of self-administered NLP-based interventions in alleviating depressive and anxiety symptoms, highlighting their potential to increase accessibility to, and reduce costs in, mental health care. Although the results were encouraging, the certainty of evidence was low, underscoring the need for further high-quality randomized controlled trials and studies examining implementation and usability. These interventions could become valuable components of public health strategies to address mental health issues. TRIAL REGISTRATION: PROSPERO International Prospective Register of Systematic Reviews CRD42023472120; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023472120.

Development and Validation of a Natural Language Processing Algorithm for Extracting Clinical and Pathological Features of Breast Cancer From Pathology Reports.

PURPOSE: Electronic health records (EHRs) are valuable information repositories that offer insights for enhancing clinical research on breast cancer (BC) using real-world data. The objective of this study was to develop a natural language processing (NLP) model specifically designed to extract structured data from BC pathology reports written in natural language. METHODS: During the initial phase, the algorithm's development cohort comprised 193 pathology reports from 116 patients with BC from 2012 to 2016. A rule-based NLP algorithm was applied to extract 26 variables for analysis and was compared with the manual extraction of data performed by both a data entry specialist and an oncologist. Following the first approach, the data set was expanded to include 513 reports, and a Named Entity Recognition (NER)-NLP model was trained and evaluated using K-fold cross-validation. RESULTS: The first approach led to a concordance analysis, which revealed an 82.9% agreement between the algorithm and the oncologist, whereas the concordance between the data entry specialist and the oncologist was 90.8%. The second training approach introduced the definition of an NER-NLP model, in which the accuracy showed remarkable potential (97.8%). Notably, the model demonstrated remarkable performance, especially for parameters such as estrogen receptor, progesterone receptor, human epidermal growth factor receptor 2, and Ki-67 (F1-score 1.0). CONCLUSION: The present study aligns with the rapidly evolving field of artificial intelligence (AI) applications in oncology, seeking to expedite the development of complex cancer databases and registries. The results of the model are currently undergoing postprocessing procedures to organize the data into tabular structures, facilitating their utilization in real-world clinical and research endeavors.

Classification of Patients' Judgments of Their Physicians in Web-Based Written Reviews Using Natural Language Processing: Algorithm Development and Validation.

BACKGROUND: Patients increasingly rely on web-based physician reviews to choose a physician and share their experiences. However, the unstructured text of these written reviews presents a challenge for researchers seeking to make inferences about patients' judgments. Methods previously used to identify patient judgments within reviews, such as hand-coding and dictionary-based approaches, have posed limitations to sample size and classification accuracy. Advanced natural language processing methods can help overcome these limitations and promote further analysis of physician reviews on these popular platforms. OBJECTIVE: This study aims to train, test, and validate an advanced natural language processing algorithm for classifying the presence and valence of 2 dimensions of patient judgments in web-based physician reviews: interpersonal manner and technical competence. METHODS: We sampled 345,053 reviews for 167,150 physicians across the United States from Healthgrades.com, a commercial web-based physician rating and review website. We hand-coded 2000 written reviews and used those reviews to train and test a transformer classification algorithm called the Robustly Optimized BERT (Bidirectional Encoder Representations from Transformers) Pretraining Approach (RoBERTa). The 2 fine-tuned models coded the reviews for the presence and positive or negative valence of patients' interpersonal manner or technical competence judgments of their physicians. We evaluated the performance of the 2 models against 200 hand-coded reviews and validated the models using the full sample of 345,053 RoBERTa-coded reviews. RESULTS: The interpersonal manner model was 90% accurate with precision of 0.89, recall of 0.90, and weighted F1-score of 0.89. The technical competence model was 90% accurate with precision of 0.91, recall of 0.90, and weighted F1-score of 0.90. Positive-valence judgments were associated with higher review star ratings whereas negative-valence judgments were associated with lower star ratings. Analysis of the data by review rating and physician gender corresponded with findings in prior literature. CONCLUSIONS: Our 2 classification models coded interpersonal manner and technical competence judgments with high precision, recall, and accuracy. These models were validated using review star ratings and results from previous research. RoBERTa can accurately classify unstructured, web-based review text at scale. Future work could explore the use of this algorithm with other textual data, such as social media posts and electronic health records.

GPT-4 as an X data annotator: Unraveling its performance on a stance classification task.

Data annotation in NLP is a costly and time-consuming task, traditionally handled by human experts who require extensive training to enhance the task-related background knowledge. Besides, labeling social media texts is particularly challenging due to their brevity, informality, creativity, and varying human perceptions regarding the sociocultural context of the world. With the emergence of GPT models and their proficiency in various NLP tasks, this study aims to establish a performance baseline for GPT-4 as a social media text annotator. To achieve this, we employ our own dataset of tweets, expertly labeled for stance detection with full inter-rater agreement among three annotators. We experiment with three techniques: Zero-shot, Few-shot, and Zero-shot with Chain-of-Thoughts to create prompts for the labeling task. We utilize four training sets constructed with different label sets, including human labels, to fine-tune transformer-based large language models and various combinations of traditional machine learning models with embeddings for stance classification. Finally, all fine-tuned models undergo evaluation using a common testing set with human-generated labels. We use the results from models trained on human labels as the benchmark to assess GPT-4's potential as an annotator across the three prompting techniques. Based on the experimental findings, GPT-4 achieves comparable results through the Few-shot and Zero-shot Chain-of-Thoughts prompting methods. However, none of these labeling techniques surpass the top three models fine-tuned on human labels. Moreover, we introduce the Zero-shot Chain-of-Thoughts as an effective strategy for aspect-based social media text labeling, which performs better than the standard Zero-shot and yields results similar to the high-performing yet expensive Few-shot approach.

Supporting the working life exposome: Annotating occupational exposure for enhanced literature search.

An individual's likelihood of developing non-communicable diseases is often influenced by the types, intensities and duration of exposures at work. Job exposure matrices provide exposure estimates associated with different occupations. However, due to their time-consuming expert curation process, job exposure matrices currently cover only a subset of possible workplace exposures and may not be regularly updated. Scientific literature articles describing exposure studies provide important supporting evidence for developing and updating job exposure matrices, since they report on exposures in a variety of occupational scenarios. However, the constant growth of scientific literature is increasing the challenges of efficiently identifying relevant articles and important content within them. Natural language processing methods emulate the human process of reading and understanding texts, but in a fraction of the time. Such methods can increase the efficiency of both finding relevant documents and pinpointing specific information within them, which could streamline the process of developing and updating job exposure matrices. Named entity recognition is a fundamental natural language processing method for language understanding, which automatically identifies mentions of domain-specific concepts (named entities) in documents, e.g., exposures, occupations and job tasks. State-of-the-art machine learning models typically use evidence from an annotated corpus, i.e., a set of documents in which named entities are manually marked up (annotated) by experts, to learn how to detect named entities automatically in new documents. We have developed a novel annotated corpus of scientific articles to support machine learning based named entity recognition relevant to occupational substance exposures. Through incremental refinements to the annotation process, we demonstrate that expert annotators can attain high levels of agreement, and that the corpus can be used to train high-performance named entity recognition models. The corpus thus constitutes an important foundation for the wider development of natural language processing tools to support the study of occupational exposures.

Deep-Transfer-Learning-Based Natural Language Processing of Serial Free-Text Computed Tomography Reports for Predicting Survival of Patients With Pancreatic Cancer.

PURPOSE: To explore the predictive potential of serial computed tomography (CT) radiology reports for pancreatic cancer survival using natural language processing (NLP). METHODS: Deep-transfer-learning-based NLP models were retrospectively trained and tested with serial, free-text CT reports, and survival information of consecutive patients diagnosed with pancreatic cancer in a Korean tertiary hospital was extracted. Randomly selected patients with pancreatic cancer and their serial CT reports from an independent tertiary hospital in the United States were included in the external testing data set. The concordance index (c-index) of predicted survival and actual survival, and area under the receiver operating characteristic curve (AUROC) for predicting 1-year survival were calculated. RESULTS: Between January 2004 and June 2021, 2,677 patients with 12,255 CT reports and 670 patients with 3,058 CT reports were allocated to training and internal testing data sets, respectively. ClinicalBERT (Bidirectional Encoder Representations from Transformers) model trained on the single, first CT reports showed a c-index of 0.653 and AUROC of 0.722 in predicting the overall survival of patients with pancreatic cancer. ClinicalBERT trained on up to 15 consecutive reports from the initial report showed an improved c-index of 0.811 and AUROC of 0.911. On the external testing set with 273 patients with 1,947 CT reports, the AUROC was 0.888, indicating the generalizability of our model. Further analyses showed our model's contextual interpretation beyond specific phrases. CONCLUSION: Deep-transfer-learning-based NLP model of serial CT reports can predict the survival of patients with pancreatic cancer. Clinical decisions can be supported by the developed model, with survival information extracted solely from serial radiology reports.

Enhancing Postmarketing Surveillance of Medical Products With Large Language Models.

Importance: The Sentinel System is a key component of the US Food and Drug Administration (FDA) postmarketing safety surveillance commitment and uses clinical health care data to conduct analyses to inform drug labeling and safety communications, FDA advisory committee meetings, and other regulatory decisions. However, observational data are frequently deemed insufficient for reliable evaluation of safety concerns owing to limitations in underlying data or methodology. Advances in large language models (LLMs) provide new opportunities to address some of these limitations. However, careful consideration is necessary for how and where LLMs can be effectively deployed for these purposes. Observations: LLMs may provide new avenues to support signal-identification activities to identify novel adverse event signals from narrative text of electronic health records. These algorithms may be used to support epidemiologic investigations examining the causal relationship between exposure to a medical product and an adverse event through development of probabilistic phenotyping of health outcomes of interest and extraction of information related to important confounding factors. LLMs may perform like traditional natural language processing tools by annotating text with controlled vocabularies with additional tailored training activities. LLMs offer opportunities for enhancing information extraction from adverse event reports, medical literature, and other biomedical knowledge sources. There are several challenges that must be considered when leveraging LLMs for postmarket surveillance. Prompt engineering is needed to ensure that LLM-extracted associations are accurate and specific. LLMs require extensive infrastructure to use, which many health care systems lack, and this can impact diversity, equity, and inclusion, and result in obscuring significant adverse event patterns in some populations. LLMs are known to generate nonfactual statements, which could lead to false positive signals and downstream evaluation activities by the FDA and other entities, incurring substantial cost. Conclusions and Relevance: LLMs represent a novel paradigm that may facilitate generation of information to support medical product postmarket surveillance activities that have not been possible. However, additional work is required to ensure LLMs can be used in a fair and equitable manner, minimize false positive findings, and support the necessary rigor of signal detection needed for regulatory activities.

Insights Into the Patient Experience of Hormone Therapy for Early Breast Cancer Treatment Using Patient Forum Discussions and Natural Language Processing.

PURPOSE: Understanding the real-world experience of patients with early breast cancer (eBC) is imperative for optimizing outcomes and evolving patient care. However, there is a lack of patient-level data, hindering clinical development. This social listening study was performed to understand patient insights into symptoms and impacts of hormone therapy (HT) for eBC using posts from patient forums on breastcancer.org to inform future clinical research. METHODS: Natural language processing (NLP) and machine learning techniques were used to identify themes related to eBC from a sample of 500,000 posts. After relevant data selection, 362,074 eBC posts were retained for further analysis of symptoms and impacts related to HT, as well as insights into symptom severity, pain locations, and symptom management using exercise and yoga. RESULTS: Overall, 32 symptoms and nine impacts had significant associations with ≥one HT. Hot flush (relative risk [RR], 6.70 [95% CI, 3.36 to 13.36]), arthralgia (RR, 6.67 [95% CI, 3.53 to 12.59]), weight increased (RR, 4.83 [95% CI, 3.20 to 7.28]), mood swings (RR, 7.36 [95% CI, 5.75 to 9.42]), insomnia (RR, 4.76 [95% CI, 3.14 to 7.22]), and depression (RR, 3.05 [95% CI, 1.71 to 5.44]) demonstrated the strongest associations. Severe headache, dizziness, back pain, and muscle spasms showed significant associations with ≥one HT despite their low overall prevalence in eBC posts. CONCLUSION: The social listening approach allowed the identification of real-world insights from posts specific to eBC HT from a large-scale online breast cancer forum that captured experiences from a uniquely diverse group of patients. Using NLP has a potential to scale analysis of patient feedback and reveal actionable insights into patient experiences of treatment that can inform the development of future therapies and improve the care of patients with eBC.

Overview of computational methods in taphonomy based on the combination of bibliometric analysis and natural language.

Artificial intelligence tools are new in taphonomy and are growing fast. They are being used mainly to investigate bone surface marks. In order to investigate this subject, a bibliometric study was made to understand the growing rate of this intersectional field, the future, and gaps in the field until now. From Scopus and Google Scholar metadata, graphs were made to describe the data, and inferential statistics were made by regression with the Ordinary Least Squares method. Exploratory analysis with word clouds, topic modeling, and natural language processing with Latent Dirichlet Allocation as a method were also made using the entire corpus from the papers. From the first register until 2023, we found eight articles in Scopus and 32 in Google Scholar; the majority of the studies and the most cited were from Spain. The studies are growing fast from 2016 to 2018, and the regression shows that growth can be maintained in the coming years. Exploratory analysis shows the most frequent words are marks, models, data, and bone. Topic modeling shows that the studies are highly concentrated on similar problems and the tools to solve them, revealing that there is much more to explore with computational tools in taphonomy and paleontology as well.

Artificial intelligence and headache.

BACKGROUND AND METHODS: In this narrative review, we introduce key artificial intelligence (AI) and machine learning (ML) concepts, aimed at headache clinicians and researchers. Thereafter, we thoroughly review the use of AI in headache, based on a comprehensive literature search across PubMed, Embase and IEEExplore. Finally, we discuss limitations, as well as ethical and political perspectives. RESULTS: We identified six main research topics. First, natural language processing can be used to effectively extract and systematize unstructured headache research data, such as from electronic health records. Second, the most common application of ML is for classification of headache disorders, typically based on clinical record data, or neuroimaging data, with accuracies ranging from around 60% to well over 90%. Third, ML is used for prediction of headache disease trajectories. Fourth, ML shows promise in forecasting of headaches using self-reported data such as triggers and premonitory symptoms, data from wearable sensors and external data. Fifth and sixth, ML can be used for prediction of treatment responses and inference of treatment effects, respectively, aiming to optimize and individualize headache management. CONCLUSIONS: The potential uses of AI and ML in headache are broad, but, at present, many studies suffer from poor reporting and lack out-of-sample evaluation, and most models are not validated in a clinical setting.

Improving the quality of Persian clinical text with a novel spelling correction system.

BACKGROUND: The accuracy of spelling in Electronic Health Records (EHRs) is a critical factor for efficient clinical care, research, and ensuring patient safety. The Persian language, with its abundant vocabulary and complex characteristics, poses unique challenges for real-word error correction. This research aimed to develop an innovative approach for detecting and correcting spelling errors in Persian clinical text. METHODS: Our strategy employs a state-of-the-art pre-trained model that has been meticulously fine-tuned specifically for the task of spelling correction in the Persian clinical domain. This model is complemented by an innovative orthographic similarity matching algorithm, PERTO, which uses visual similarity of characters for ranking correction candidates. RESULTS: The evaluation of our approach demonstrated its robustness and precision in detecting and rectifying word errors in Persian clinical text. In terms of non-word error correction, our model achieved an F1-Score of 90.0% when the PERTO algorithm was employed. For real-word error detection, our model demonstrated its highest performance, achieving an F1-Score of 90.6%. Furthermore, the model reached its highest F1-Score of 91.5% for real-word error correction when the PERTO algorithm was employed. CONCLUSIONS: Despite certain limitations, our method represents a substantial advancement in the field of spelling error detection and correction for Persian clinical text. By effectively addressing the unique challenges posed by the Persian language, our approach paves the way for more accurate and efficient clinical documentation, contributing to improved patient care and safety. Future research could explore its use in other areas of the Persian medical domain, enhancing its impact and utility.

An improved data augmentation approach and its application in medical named entity recognition.

Performing data augmentation in medical named entity recognition (NER) is crucial due to the unique challenges posed by this field. Medical data is characterized by high acquisition costs, specialized terminology, imbalanced distributions, and limited training resources. These factors make achieving high performance in medical NER particularly difficult. Data augmentation methods help to mitigate these issues by generating additional training samples, thus balancing data distribution, enriching the training dataset, and improving model generalization. This paper proposes two data augmentation methods-Contextual Random Replacement based on Word2Vec Augmentation (CRR) and Targeted Entity Random Replacement Augmentation (TER)-aimed at addressing the scarcity and imbalance of data in the medical domain. When combined with a deep learning-based Chinese NER model, these methods can significantly enhance performance and recognition accuracy under limited resources. Experimental results demonstrate that both augmentation methods effectively improve the recognition capability of medical named entities. Specifically, the BERT-BiLSTM-CRF model achieved the highest F1 score of 83.587%, representing a 1.49% increase over the baseline model. This validates the importance and effectiveness of data augmentation in medical NER.

Research on entity relation extraction for Chinese medical text.

Currently, the primary challenges in entity relation extraction are the existence of overlapping relations and cascading errors. In addressing these issues, both CasRel and TPLinker have demonstrated their competitiveness. This study aims to explore the application of these two models in the context of entity relation extraction from Chinese medical text. We evaluate the performance of these models using the publicly available dataset CMeIE and further enhance their capabilities through the incorporation of pre-trained models that are tailored to the specific characteristics of the text. The experimental findings demonstrate that the TPLinker model exhibits a heightened and consistent boosting effect compared to CasRel, while also attaining superior performance through the utilization of advanced pre-trained models. Notably, the MacBERT + TPLinker combination emerges as the optimal choice, surpassing the benchmark model by 12.45% and outperforming the leading model ERNIE-Health 3.0 in the CBLUE challenge by 2.31%.

Natural Language Processing Accurately Differentiates Cancer Symptom Information in Electronic Health Record Narratives.

PURPOSE: Identifying cancer symptoms in electronic health record (EHR) narratives is feasible with natural language processing (NLP). However, more efficient NLP systems are needed to detect various symptoms and distinguish observed symptoms from negated symptoms and medication-related side effects. We evaluated the accuracy of NLP in (1) detecting 14 symptom groups (ie, pain, fatigue, swelling, depressed mood, anxiety, nausea/vomiting, pruritus, headache, shortness of breath, constipation, numbness/tingling, decreased appetite, impaired memory, disturbed sleep) and (2) distinguishing observed symptoms in EHR narratives among patients with cancer. METHODS: We extracted 902,508 notes for 11,784 unique patients diagnosed with cancer and developed a gold standard corpus of 1,112 notes labeled for presence or absence of 14 symptom groups. We trained an embeddings-augmented NLP system integrating human and machine intelligence and conventional machine learning algorithms. NLP metrics were calculated on a gold standard corpus subset for testing. RESULTS: The interannotator agreement for labeling the gold standard corpus was excellent at 92%. The embeddings-augmented NLP model achieved the best performance (F1 score = 0.877). The highest NLP accuracy was observed in pruritus (F1 score = 0.937) while the lowest accuracy was in swelling (F1 score = 0.787). After classifying the entire data set with embeddings-augmented NLP, we found that 41% of the notes included symptom documentation. Pain was the most documented symptom (29% of all notes) while impaired memory was the least documented (0.7% of all notes). CONCLUSION: We illustrated the feasibility of detecting 14 symptom groups in EHR narratives and showed that an embeddings-augmented NLP system outperforms conventional machine learning algorithms in detecting symptom information and differentiating observed symptoms from negated symptoms and medication-related side effects.

ICDXML: enhancing ICD coding with probabilistic label trees and dynamic semantic representations.

Accurately assigning standardized diagnosis and procedure codes from clinical text is crucial for healthcare applications. However, this remains challenging due to the complexity of medical language. This paper proposes a novel model that incorporates extreme multi-label classification tasks to enhance International Classification of Diseases (ICD) coding. The model utilizes deformable convolutional neural networks to fuse representations from hidden layer outputs of pre-trained language models and external medical knowledge embeddings fused using a multimodal approach to provide rich semantic encodings for each code. A probabilistic label tree is constructed based on the hierarchical structure existing in ICD labels to incorporate ontological relationships between ICD codes and enable structured output prediction. Experiments on medical code prediction on the MIMIC-III database demonstrate competitive performance, highlighting the benefits of this technique for robust clinical code assignment.

Knowledge Base Prototype Creating with Using Interdisciplinary Metathesaurus.

This article presents our experience in development an ontological model can be used in clinical decision support systems (CDSS) creating. We have used the largest international biomedical terminological metathesaurus the Unified Medical Language System (UMLS) as the basis of our model. This metathesaurus has been adapted into Russian using an automated hybrid translation system with expert control. The product we have created was named as the National Unified Terminological System (NUTS). We have added more than 33 million scientific and clinical relationships between NUTS terms, extracted from the texts of scientific articles and electronic health records. We have also computed weights for each relationship, standardized their values and created symptom checker in preliminary diagnostics based on this. We expect, that the NUTS allow solving task of named entity recognition (NER) and increasing terms interoperability in different CDSS.

Development of Unified Terminological System Based on UMLS: Experience and Perspectives.

This article presents experience in construction the National Unified Terminological System (NUTS) with an ontological structure based on international Unified Medical Language System (UMLS). UMLS has been adapted and enriched with formulations from national directories, relationships, extracted from the texts of scientific articles and electronic health records, and weight coefficients.

Protocol for a Validation Study of an Ontology of Administrable Dose Forms of Medicinal Products.

Administrable dose form can be obtained after (no-)transformation from pharmaceutical dose form. Building on the creation of a small ontology of 428 pharmaceutical dose forms from EDQM to support alignment with other dose form ontologies (SNOMED-CT, RxNorm), the present study is focused on a simple ontology of 308 administrable dose forms, 27 Intended Sites and an intermediary level of 65 dose form groupers. The ontology was created after 432 pharmaceutical dose forms, 65 combined pharmaceutical dose forms and 73 combined terms were linked by EDQM to administrable dose forms during the UNICOM project. The article describes these resources, the resulting ontology, the differences between its top-level concepts and the source's. It presents the protocol for a validation study through expert review, as a preparation for use case studies.