Applying deep neural networks to unstructured text notes in electronic medical records for phenotyping youth depression.
Ontology highlight
ABSTRACT:
SUBMITTER: Geraci J
PROVIDER: S-EPMC5566092 | biostudies-other | 2017 Jul
REPOSITORIES: biostudies-other
Similar Datasets
Project description:BackgroundA cancer diagnosis is a source of psychological and emotional stress, which are often maintained for sustained periods of time that may lead to depressive disorders. Depression is one of the most common psychological conditions in patients with cancer. According to the Global Cancer Observatory, breast and colorectal cancers are the most prevalent cancers in both sexes and across all age groups in Spain.ObjectiveThis study aimed to compare the prevalence of depression in patients before and after the diagnosis of breast or colorectal cancer, as well as to assess the usefulness of the analysis of free-text clinical notes in 2 languages (Spanish or Catalan) for detecting depression in combination with encoded diagnoses.MethodsWe carried out an analysis of the electronic health records from a general hospital by considering the different sources of clinical information related to depression in patients with breast and colorectal cancer. This analysis included ICD-9-CM (International Classification of Diseases, Ninth Revision, Clinical Modification) diagnosis codes and unstructured information extracted by mining free-text clinical notes via natural language processing tools based on Systematized Nomenclature of Medicine Clinical Terms that mentions symptoms and drugs used for the treatment of depression.ResultsWe observed that the percentage of patients diagnosed with depressive disorders significantly increased after cancer diagnosis in the 2 types of cancer considered-breast and colorectal cancers. We managed to identify a higher number of patients with depression by mining free-text clinical notes than the group selected exclusively on ICD-9-CM codes, increasing the number of patients diagnosed with depression by 34.8% (441/1269). In addition, the number of patients with depression who received chemotherapy was higher than those who did not receive this treatment, with significant differences (P<.001).ConclusionsThis study provides new clinical evidence of the depression-cancer comorbidity and supports the use of natural language processing for extracting and analyzing free-text clinical notes from electronic health records, contributing to the identification of additional clinical data that complements those provided by coded data to improve the management of these patients.
| S-EPMC9315897 | biostudies-literature
Project description:ObjectiveTo evaluate the phenotyping performance of three major electronic health record (EHR) components: International Classification of Disease (ICD) diagnosis codes, primary notes, and specific medications.Materials and methodsWe conducted the evaluation using de-identified Vanderbilt EHR data. We preselected ten diseases: atrial fibrillation, Alzheimer's disease, breast cancer, gout, human immunodeficiency virus infection, multiple sclerosis, Parkinson's disease, rheumatoid arthritis, and types 1 and 2 diabetes mellitus. For each disease, patients were classified into seven categories based on the presence of evidence in diagnosis codes, primary notes, and specific medications. Twenty-five patients per disease category (a total number of 175 patients for each disease, 1750 patients for all ten diseases) were randomly selected for manual chart review. Review results were used to estimate the positive predictive value (PPV), sensitivity, andF-score for each EHR component alone and in combination.ResultsThe PPVs of single components were inconsistent and inadequate for accurately phenotyping (0.06-0.71). Using two or more ICD codes improved the average PPV to 0.84. We observed a more stable and higher accuracy when using at least two components (mean ± standard deviation: 0.91 ± 0.08). Primary notes offered the best sensitivity (0.77). The sensitivity of ICD codes was 0.67. Again, two or more components provided a reasonably high and stable sensitivity (0.59 ± 0.16). Overall, the best performance (Fscore: 0.70 ± 0.12) was achieved by using two or more components. Although the overall performance of using ICD codes (0.67 ± 0.14) was only slightly lower than using two or more components, its PPV (0.71 ± 0.13) is substantially worse (0.91 ± 0.08).ConclusionMultiple EHR components provide a more consistent and higher performance than a single one for the selected phenotypes. We suggest considering multiple EHR components for future phenotyping design in order to obtain an ideal result.
| S-EPMC4954637 | biostudies-literature
Project description:BackgroundElectronic health records are invaluable for medical research, but much of the information is recorded as unstructured free text which is time-consuming to review manually.AimTo develop an algorithm to identify relevant free texts automatically based on labelled examples.MethodsWe developed a novel machine learning algorithm, the 'Semi-supervised Set Covering Machine' (S3CM), and tested its ability to detect the presence of coronary angiogram results and ovarian cancer diagnoses in free text in the General Practice Research Database. For training the algorithm, we used texts classified as positive and negative according to their associated Read diagnostic codes, rather than by manual annotation. We evaluated the precision (positive predictive value) and recall (sensitivity) of S3CM in classifying unlabelled texts against the gold standard of manual review. We compared the performance of S3CM with the Transductive Vector Support Machine (TVSM), the original fully-supervised Set Covering Machine (SCM) and our 'Freetext Matching Algorithm' natural language processor.ResultsOnly 60% of texts with Read codes for angiogram actually contained angiogram results. However, the S3CM algorithm achieved 87% recall with 64% precision on detecting coronary angiogram results, outperforming the fully-supervised SCM (recall 78%, precision 60%) and TSVM (recall 2%, precision 3%). For ovarian cancer diagnoses, S3CM had higher recall than the other algorithms tested (86%). The Freetext Matching Algorithm had better precision than S3CM (85% versus 74%) but lower recall (62%).ConclusionsOur novel S3CM machine learning algorithm effectively detected free texts in primary care records associated with angiogram results and ovarian cancer diagnoses, after training on pre-classified test sets. It should be easy to adapt to other disease areas as it does not rely on linguistic rules, but needs further testing in other electronic health record datasets.
| S-EPMC3261909 | biostudies-literature
Project description:Integration of detailed phenotype information with genetic data is well established to facilitate accurate diagnosis of hereditary disorders. As a rich source of phenotype information, electronic health records (EHRs) promise to empower diagnostic variant interpretation. However, how to accurately and efficiently extract phenotypes from heterogeneous EHR narratives remains a challenge. Here, we present EHR-Phenolyzer, a high-throughput EHR framework for extracting and analyzing phenotypes. EHR-Phenolyzer extracts and normalizes Human Phenotype Ontology (HPO) concepts from EHR narratives and then prioritizes genes with causal variants on the basis of the HPO-coded phenotype manifestations. We assessed EHR-Phenolyzer on 28 pediatric individuals with confirmed diagnoses of monogenic diseases and found that the genes with causal variants were ranked among the top 100 genes selected by EHR-Phenolyzer for 16/28 individuals (p < 2.2 × 10-16), supporting the value of phenotype-driven gene prioritization in diagnostic sequence interpretation. To assess the generalizability, we replicated this finding on an independent EHR dataset of ten individuals with a positive diagnosis from a different institution. We then assessed the broader utility by examining two additional EHR datasets, including 31 individuals who were suspected of having a Mendelian disease and underwent different types of genetic testing and 20 individuals with positive diagnoses of specific Mendelian etiologies of chronic kidney disease from exome sequencing. Finally, through several retrospective case studies, we demonstrated how combined analyses of genotype data and deep phenotype data from EHRs can expedite genetic diagnoses. In summary, EHR-Phenolyzer leverages EHR narratives to automate phenotype-driven analysis of clinical exomes or genomes, facilitating the broader implementation of genomic medicine.
| S-EPMC6035281 | biostudies-literature
Project description:BackgroundElectronic health records (EHRs) in unstructured formats are valuable sources of information for research in both the clinical and biomedical domains. However, before such records can be used for research purposes, sensitive health information (SHI) must be removed in several cases to protect patient privacy. Rule-based and machine learning-based methods have been shown to be effective in deidentification. However, very few studies investigated the combination of transformer-based language models and rules.ObjectiveThe objective of this study is to develop a hybrid deidentification pipeline for Australian EHR text notes using rules and transformers. The study also aims to investigate the impact of pretrained word embedding and transformer-based language models.MethodsIn this study, we present a hybrid deidentification pipeline called OpenDeID, which is developed using an Australian multicenter EHR-based corpus called OpenDeID Corpus. The OpenDeID corpus consists of 2100 pathology reports with 38,414 SHI entities from 1833 patients. The OpenDeID pipeline incorporates a hybrid approach of associative rules, supervised deep learning, and pretrained language models.ResultsThe OpenDeID achieved a best F1-score of 0.9659 by fine-tuning the Discharge Summary BioBERT model and incorporating various preprocessing and postprocessing rules. The OpenDeID pipeline has been deployed at a large tertiary teaching hospital and has processed over 8000 unstructured EHR text notes in real time.ConclusionsThe OpenDeID pipeline is a hybrid deidentification pipeline to deidentify SHI entities in unstructured EHR text notes. The pipeline has been evaluated on a large multicenter corpus. External validation will be undertaken as part of our future work to evaluate the effectiveness of the OpenDeID pipeline.
| S-EPMC10733816 | biostudies-literature
Project description:Background: Deep Phenotyping is the precise and comprehensive analysis of phenotypic features in which the individual components of the phenotype are observed and described. In UK mental health clinical practice, most clinically relevant information is recorded as free text in the Electronic Health Record, and offers a granularity of information beyond what is expressed in most medical knowledge bases. The SNOMED CT nomenclature potentially offers the means to model such information at scale, yet given a sufficiently large body of clinical text collected over many years, it is difficult to identify the language that clinicians favour to express concepts. Methods: By utilising a large corpus of healthcare data, we sought to make use of semantic modelling and clustering techniques to represent the relationship between the clinical vocabulary of internationally recognised SMI symptoms and the preferred language used by clinicians within a care setting. We explore how such models can be used for discovering novel vocabulary relevant to the task of phenotyping Serious Mental Illness (SMI) with only a small amount of prior knowledge. Results: 20 403 terms were derived and curated via a two stage methodology. The list was reduced to 557 putative concepts based on eliminating redundant information content. These were then organised into 9 distinct categories pertaining to different aspects of psychiatric assessment. 235 concepts were found to be expressions of putative clinical significance. Of these, 53 were identified having novel synonymy with existing SNOMED CT concepts. 106 had no mapping to SNOMED CT. Conclusions: We demonstrate a scalable approach to discovering new concepts of SMI symptomatology based on real-world clinical observation. Such approaches may offer the opportunity to consider broader manifestations of SMI symptomatology than is typically assessed via current diagnostic frameworks, and create the potential for enhancing nomenclatures such as SNOMED CT based on real-world expressions.
| S-EPMC5968362 | biostudies-literature
Project description:BackgroundDischarge medical notes written by physicians contain important information about the health condition of patients. Many deep learning algorithms have been successfully applied to extract important information from unstructured medical notes data that can entail subsequent actionable results in the medical domain. This study aims to explore the model performance of various deep learning algorithms in text classification tasks on medical notes with respect to different disease class imbalance scenarios.MethodsIn this study, we employed seven artificial intelligence models, a CNN (Convolutional Neural Network), a Transformer encoder, a pretrained BERT (Bidirectional Encoder Representations from Transformers), and four typical sequence neural networks models, namely, RNN (Recurrent Neural Network), GRU (Gated Recurrent Unit), LSTM (Long Short-Term Memory), and Bi-LSTM (Bi-directional Long Short-Term Memory) to classify the presence or absence of 16 disease conditions from patients' discharge summary notes. We analyzed this question as a composition of 16 binary separate classification problems. The model performance of the seven models on each of the 16 datasets with various levels of imbalance between classes were compared in terms of AUC-ROC (Area Under the Curve of the Receiver Operating Characteristic), AUC-PR (Area Under the Curve of Precision and Recall), F1 Score, and Balanced Accuracy as well as the training time. The model performances were also compared in combination with different word embedding approaches (GloVe, BioWordVec, and no pre-trained word embeddings).ResultsThe analyses of these 16 binary classification problems showed that the Transformer encoder model performs the best in nearly all scenarios. In addition, when the disease prevalence is close to or greater than 50%, the Convolutional Neural Network model achieved a comparable performance to the Transformer encoder, and its training time was 17.6% shorter than the second fastest model, 91.3% shorter than the Transformer encoder, and 94.7% shorter than the pre-trained BERT-Base model. The BioWordVec embeddings slightly improved the performance of the Bi-LSTM model in most disease prevalence scenarios, while the CNN model performed better without pre-trained word embeddings. In addition, the training time was significantly reduced with the GloVe embeddings for all models.ConclusionsFor classification tasks on medical notes, Transformer encoders are the best choice if the computation resource is not an issue. Otherwise, when the classes are relatively balanced, CNNs are a leading candidate because of their competitive performance and computational efficiency.
| S-EPMC9250736 | biostudies-literature
Project description:BackgroundStatins are widely prescribed cholesterol-lowering medications in the US, but their clinical benefits can be diminished by statin-associated muscle symptoms (SAMS), leading to discontinuation. In this study, we aimed to develop and validate a pharmacological SAMS clinical phenotyping algorithm using electronic health records (EHRs) data from Minnesota Fairview.MethodsWe retrieved structured and unstructured EHR data of statin users and manually ascertained a gold standard set of SAMS cases and controls using the SAMS-CI tool from clinical notes in 200 patients. We developed machine learning algorithms and rule-based algorithms that incorporated various criteria, including ICD codes, statin allergy, creatine kinase elevation, and keyword mentions in clinical notes. We applied the best performing algorithm to the statin cohort to identify SAMS.ResultsWe identified 16,889 patients who started statins in the Fairview EHR system from 2010-2020. The combined rule-based (CRB) algorithm, which utilized both clinical notes and structured data criteria, achieved similar performance compared to machine learning algorithms with a precision of 0.85, recall of 0.71, and F1 score of 0.77 against the gold standard set. Applying the CRB algorithm to the statin cohort, we identified the pharmacological SAMS prevalence to be 1.9% and selective risk factors which included female gender, coronary artery disease, hypothyroidism, use of immunosuppressants or fibrates.ConclusionOur study developed and validated a simple pharmacological SAMS phenotyping algorithm that can be used to create SAMS case/control cohort for further analysis such as developing SAMS risk prediction model.
| S-EPMC10197715 | biostudies-literature
Project description:Alzheimer's Disease (AD) is a neurodegenerative disorder that is still not fully understood. Sex modifies AD vulnerability, but the reasons for this are largely unknown. We utilize two independent electronic medical record (EMR) systems across 44,288 patients to perform deep clinical phenotyping and network analysis to gain insight into clinical characteristics and sex-specific clinical associations in AD. Embeddings and network representation of patient diagnoses demonstrate greater comorbidity interactions in AD in comparison to matched controls. Enrichment analysis identifies multiple known and new diagnostic, medication, and lab result associations across the whole cohort and in a sex-stratified analysis. With this data-driven method of phenotyping, we can represent AD complexity and generate hypotheses of clinical factors that can be followed-up for further diagnostic and predictive analyses, mechanistic understanding, or drug repurposing and therapeutic approaches.
| S-EPMC8814236 | biostudies-literature
Project description:BackgroundElectronic health records are invaluable for medical research, but much information is stored as free text rather than in a coded form. For example, in the UK General Practice Research Database (GPRD), causes of death and test results are sometimes recorded only in free text. Free text can be difficult to use for research if it requires time-consuming manual review. Our aim was to develop an automated method for extracting coded information from free text in electronic patient records.MethodsWe reviewed the electronic patient records in GPRD of a random sample of 3310 patients who died in 2001, to identify the cause of death. We developed a computer program called the Freetext Matching Algorithm (FMA) to map diagnoses in text to the Read Clinical Terminology. The program uses lookup tables of synonyms and phrase patterns to identify diagnoses, dates and selected test results. We tested it on two random samples of free text from GPRD (1000 texts associated with death in 2001, and 1000 general texts from cases and controls in a coronary artery disease study), comparing the output to the U.S. National Library of Medicine's MetaMap program and the gold standard of manual review.ResultsAmong 3310 patients registered in the GPRD who died in 2001, the cause of death was recorded in coded form in 38.1% of patients, and in the free text alone in 19.4%. On the 1000 texts associated with death, FMA coded 683 of the 735 positive diagnoses, with precision (positive predictive value) 98.4% (95% confidence interval (CI) 97.2, 99.2) and recall (sensitivity) 92.9% (95% CI 90.8, 94.7). On the general sample, FMA detected 346 of the 447 positive diagnoses, with precision 91.5% (95% CI 88.3, 94.1) and recall 77.4% (95% CI 73.2, 81.2), which was similar to MetaMap.ConclusionsWe have developed an algorithm to extract coded information from free text in GP records with good precision. It may facilitate research using free text in electronic patient records, particularly for extracting the cause of death.
| S-EPMC3483188 | biostudies-literature