Towards automated classification of intensive care nursing narratives (original) (raw)
Related papers
Detecting of a Patient's Condition From Clinical Narratives Using Natural Language Representation
IEEE Open Journal of Engineering in Medicine and Biology
The rapid progress in clinical data management systems and artificial intelligence approaches enable the era of personalized medicine. Intensive care units (ICUs) are ideal clinical research environments for such development because they collect many clinical data and are highly computerized. Goal: We designed a retrospective clinical study on a prospective ICU database using clinical natural language to help in the early diagnosis of heart failure in critically ill children. Methods: The methodology consisted of empirical experiments of a learning algorithm to learn the hidden interpretation and presentation of the French clinical note data. This study included 1386 patients' clinical notes with 5444 single lines of notes. There were 1941 positive cases (36% of total) and 3503 negative cases classified by two independent physicians using a standardized approach. Results: The multilayer perceptron neural network outperforms other discriminative and generative classifiers. Consequently, the proposed framework yields an overall classification performance with 89% accuracy, 88% recall, and 89% precision. Conclusions: This study successfully applied learning representation and machine learning algorithms to detect heart failure in a single French institution from clinical natural language. Further work is needed to use the same methodology in other languages and institutions.
Enormous amount of unstructured electronic health record are invaluable for the medical research in finding the relationship between the patient's disease and the final diagnosis. How to use computer automatically dig up these information has long been a hot spot. To get the relationship between the clinical outcomes and free text writing by nurse, we developed an automatic categorization system process natural language nursing record based on vector space model. 210 cases of electronic nursing records, which were diagnosed as pancreatitis, were induced in this study. We filtered the restricted corpus for acute pancreatitis classification by information gain (information gain. IG), and construct a text classification system based on Partial least squares discrimination algorithm (PLS-DA) and vector support machine (VSM). PLS loading value analysis found that there are 20 terms can be used to classify medical record text. Our innovative machine-learning algorithm effectively classified free texts of nurse care records associated with normal and acute pancreatitis diagnoses, after training on pre-classified test sets by PLS. This automatic identification technology focus in large-scale medical document may provide important clues to study the acute pancreatitis and other important common disease.
Relevance Ranking of Intensive Care Nursing Narratives
Lecture Notes in Computer Science, 2006
Current computer-based patient records provide many capabilities to assist nurses' work in intensive care units, but the possibilities to utilize existing free-text documentation are limited without the appropriate tools. To ease this limitation, we present an adaptation of the Regularized Least-Squares (RLS) algorithm for ranking pieces of nursing notes with respect to their relevance to breathing, blood circulation, and pain. We assessed the ranking results by using Kendall's τ b as a measure of association between the output of the RLS algorithm and the desired ranking. The values of τ b were 0.62, 0.69, and 0.44 for breathing, blood circulation, and pain, respectively. These values indicate that a machine learning approach can successfully be used to rank nursing notes, and encourage further research on the use of ranking techniques when developing intelligent tools for the utilization of nursing narratives.
Journal of the American Medical Informatics Association, 2019
Objective This study focuses on the task of automatically assigning standardized (topical) subject headings to free-text sentences in clinical nursing notes. The underlying motivation is to support nurses when they document patient care by developing a computer system that can assist in incorporating suitable subject headings that reflect the documented topics. Central in this study is performance evaluation of several text classification methods to assess the feasibility of developing such a system. Materials and Methods Seven text classification methods are evaluated using a corpus of approximately 0.5 million nursing notes (5.5 million sentences) with 676 unique headings extracted from a Finnish university hospital. Several of these methods are based on artificial neural networks. Evaluation is first done in an automatic manner for all methods, then a manual error analysis is done on a sample. Results We find that a method based on a bidirectional long short-term memory network p...
ArXiv, 2021
The purpose of the study presented herein is to develop a machine learning algorithm based on natural language processing that automatically detects whether a patient has a “cardiac failure” or “healthy” condition by using physician notes in Research Data Warehouse at CHU Sainte-Justine Hospital. First, a word representation learning technique was employed by using bag-of-word (BoW), term frequency–inverse document frequency (TF-IDF), and neural word embeddings (word2vec). Each representation technique aims to retain the words’ semantic and syntactic analysis in critical care data. It helps to enrich the mutual information for the word representation and leads to an advantage for further appropriate analysis steps. Second, a machine learning classifier was used to detect the patient’s condition for either cardiac failure or stable patient through the created word representation vector space from the previous step. This machine learning approach is based on a supervised binary classi...
2020
BackgroundIn Chile, a patient needing a specialty consultation or surgery has to first be referred by a general practitioner, then placed on a waiting list. The Explicit Health Guarantees (GES in Spanish) ensure, by law, the maximum time to solve an important set of health problems. Usually, a health professional manually verifies if each referral, written in natural language, corresponds or not to a GES-covered disease. An error in this classification is catastrophic for patients, as it puts them on a non-prioritized waiting list, characterized by prolonged waiting times. MethodsTo support the manual process, we developed and deployed a system that automatically classifies referrals as GES-covered or not using historical data. Our system is based on word embeddings specially trained for clinical text produced in Chile. We used a vector representation of the reason for referral and patient's age as features for training machine learning models using human-labeled historical data...
Journal of Biomedical Semantics
Background: Up to 35% of nurses' working time is spent on care documentation. We describe the evaluation of a system aimed at assisting nurses in documenting patient care and potentially reducing the documentation workload. Our goal is to enable nurses to write or dictate nursing notes in a narrative manner without having to manually structure their text under subject headings. In the current care classification standard used in the targeted hospital, there are more than 500 subject headings to choose from, making it challenging and time consuming for nurses to use. Methods: The task of the presented system is to automatically group sentences into paragraphs and assign subject headings. For classification the system relies on a neural network-based text classification model. The nursing notes are initially classified on sentence level. Subsequently coherent paragraphs are constructed from related sentences. Results: Based on a manual evaluation conducted by a group of three domain experts, we find that in about 69% of the paragraphs formed by the system the topics of the sentences are coherent and the assigned paragraph headings correctly describe the topics. We also show that the use of a paragraph merging step reduces the number of paragraphs produced by 23% without affecting the performance of the system.
Representing critical care data using the clinical care classification
AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, 2005
Concept-oriented terminologies require the user to combine terms, making them awkward for their direct use as a documentation tool. Therefore, classification systems are needed to serve as interface terminologies between the user and the reference terminology used to organize the computer database system. Whether nursing classification systems provide sufficient granularity to adequately capture nursing practice is controversial. In addition, no nursing classification systems have been designed specifically for or evaluated in the critical care setting. The purpose of this study was to evaluate the ability of the Clinical Care Classification (CCC) to represent data in an intensive care setting and to provide recommendations for the expansion of this classification for its use in critical care documentation.
Amia Annual Symposium Proceedings Amia Symposium Amia Symposium, 2010
This study investigates the feasibility of using structured data (age, gender, and medical condition), and unstructured medical notes on classification accuracy for resuscitation code status. Data was extracted from the MIMICII database. Natural language processing (NLP) was used to evaluate the social section of the nurses’ progress notes. BoosTexter was used to predict the code-status using notes, age, gender, and Simplified Acute Physiology Score (SAPS). The relative impact of features was analyzed by feature ablation. Unstructured notes were the greatest single indicator of code status. The addition of text to medical condition features increased classification accuracy significantly (p<0.001.) N-gram frequency was analyzed. Gender differences were noted across all code-statuses, with women always more frequent (e.g. wife>husband.) Logistic regression on structured features was used determine gender bias or ageism. Evidence of bias was found; both females (OR=1.45) and patients over age 70 (OR=3.72) were more likely to be Do-Not-Resuscitate (DNR).
Unlocking the Power of Clinical Notes: Natural Language Processing in Healthcare
Acta Scientific Medical Sciences, 2024
Electronic Health Records (EHRs) have become the backbone of modern healthcare, providing a comprehensive record of a patient's medical journey. However, a significant portion of this data resides in clinical notes, predominantly consist of unstructured text. While valuable for consumption by medical professionals, this format presents challenges for traditional data analysis methods. Natural Language Processing (NLP) offers a powerful solution to structure the information presented and unlock the potential of clinical notes. This paper explores the application of NLP tasks within the healthcare domain, specifically focusing on EHR data. We delve into the NLP pipeline, which allows us to differentiate between essential upstream tasks like tokenization and downstream tasks like named entity recognition (NER) and relation extraction. We showcase how NLP can extract crucial clinical information through these tasks and also emphasize the importance of de-identification for maintaining patient privacy. A major challenge in NLP for healthcare is the limited availability of labeled clinical data. We discuss this bottleneck and explore potential solutions like active learning and transfer learning. Finally, the paper highlights the transformative potential of NLP in healthcare data processing and paves the way for future advancements in this dynamic field.