Natural Language Processing of Radiology Reports to Detect Complications of Ischemic Stroke

Data transformation of unstructured electroencephalography reports by natural language processing: improving data usability for large-scale epilepsy studies

Introduction

Electroencephalography (EEG) is a popular technique that provides neurologists with electrographic insights and clinical interpretations. However, these insights are predominantly presented in unstructured textual formats, which complicates data extraction and analysis. In this study, we introduce a hierarchical algorithm aimed at transforming unstructured EEG reports from pediatric patients diagnosed with epilepsy into structured data using natural language processing (NLP) techniques.

Methods

The proposed algorithm consists of two distinct phases: a deep learning-based text classification followed by a series of rule-based keyword extraction procedures. First, we categorized the EEG reports into two primary groups: normal and abnormal. Thereafter, we systematically identified the key indicators of cerebral dysfunction or seizures, distinguishing between focal and generalized seizures, as well as identifying the epileptiform discharges and their specific anatomical locations. For this study, we retrospectively analyzed a dataset comprising 17,172 EEG reports from 3,423 pediatric patients. Among them, we selected 6,173 normal and 6,173 abnormal reports confirmed by neurologists for algorithm development.

Results

The developed algorithm successfully classified EEG reports into 1,000 normal and 1,000 abnormal reports, and effectively identified the presence of cerebral dysfunction or seizures within these reports. Furthermore, our findings revealed that the algorithm translated abnormal reports into structured tabular data with an accuracy surpassing 98.5% when determining the type of seizures (focal or generalized). Additionally, the accuracy for detecting epileptiform discharges and their respective locations exceeded 88.5%. These outcomes were validated through both internal and external assessments involving 800 reports from two different medical institutions.

Discussion

Our primary focus was to convert EEG reports into structured datasets, diverging from the traditional methods of formulating clinical notes or discharge summaries. We developed a hierarchical and streamlined approach leveraging keyword selections guided by neurologists, which contributed to the exceptional performance of our algorithm. Overall, this methodology enhances data accessibility as well as improves the potential for further research and clinical applications in the field of pediatric epilepsy management.

HELMET: A Hybrid Machine Learning Framework for Real-Time Prediction of Edema Trajectory in Large Middle Cerebral Artery Stroke

Malignant cerebral edema occurs when brain swelling displaces and compresses vital midline structures within the first week of a large middle cerebral artery stroke. Early interventions such as hyperosmolar therapy or surgical decompression may reverse secondary injury but must be administered judiciously. To optimize treatment and reduce secondary damage, clinicians need strategies to frequently and quantitatively assess the trajectory of edema using updated, relevant information. However, existing risk assessment tools are limited by the absence of structured records capturing the evolution of edema and typically estimate risk at a single time point early in the admission, therefore failing to account for changes in variables over the following hours or days. To address this, we developed and validated dynamic machine learning models capable of accurately predicting the severity of midline structure displacement, an established indicator of malignant edema, in real-time. Our models can provide updated estimations as frequently as every hour, using data from structured time-varying patient records, radiographic text, and human-curated neurological characteristics. Our work resulted in two novel multi-class classification models, collectively named Hybrid Ensemble Learning Models for Edema Trajectory (HELMET), predicting the progression of midline shift over 8-hour (HELMET-8) and 24-hour windows (HELMET-24), respectively. HELMET combines transformer-based large language models with supervised ensemble learning, demonstrating the value of merging human expertise and multimodal health records in developing clinical risk scores. Both models were trained on a retrospective cohort of 15,696 observations from 623 patients hospitalized with large middle cerebral artery ischemic stroke and were externally validated using 3,713 observations from 60 patients at a separate hospital system. Our HELMET models are accurate and generalize effectively to diverse populations, achieving a cross-validated mean area under the receiver operating characteristic score of 96.6% in the derivation cohort and 92.5% in the external validation cohort. Moreover, our approach provides a framework for developing hybrid risk prediction models that integrate both human-extracted and algorithm-derived multi-modal inputs. Our work enables accurate estimation of complex, dynamic, and highly specific clinical targets, such as midline shift, in real-time, even when relevant structured information is limited in electronic health record databases.

Natural language processing in the intensive care unit: A scoping review

Objectives

Natural language processing (NLP) is a branch of artificial intelligence focused on enabling computers to interpret and analyse text-based data. The intensive care specialty is known to generate large volumes of data, including free-text, however, NLP applications are not commonly used either in critical care clinical research or quality improvement projects. This review aims to provide an overview of how NLP has been used in the intensive care specialty and promote an understanding of NLP's potential future clinical applications.

Design

Scoping review.

Data sources

A systematic search was developed with an information specialist and deployed on the PubMed electronic journal database. Results were restricted to the last 10 years to ensure currency.

Review methods

Screening and data extraction were undertaken by two independent reviewers, with any disagreements resolved by a third. Given the heterogeneity of the eligible articles, a narrative synthesis was conducted.

Results

Eighty-seven eligible articles were included in the review. The most common type (n = 24) were studies that used NLP-derived features to predict clinical outcomes, most commonly mortality (n = 16). Next were articles that used NLP to identify a specific concept (n = 23), including sepsis, family visitation and mental health disorders. Most studies only described the development and internal validation of their algorithm (n = 79), and only one reported the implementation of an algorithm in a clinical setting.

Conclusions

Natural language processing has been used for a variety of purposes in the ICU context. Increasing awareness of these techniques amongst clinicians may lead to more clinically relevant algorithms being developed and implemented.

Miller Fisher's Rules and Digital Health: The Best of Both Worlds

BACKGROUND

Professor Fisher's legacy, defined by meticulous observation, curiosity, and profound knowledge, has established a foundational cornerstone in medical practice. However, the advent of automated algorithms and artificial intelligence (AI) in medicine raises questions about the applicability of Fisher's principles in this era. Our objective was to propose adaptations to these enduring rules, addressing the challenges and leveraging the opportunities presented by digital health.

SUMMARY

The adapted rules we propose advocate for the harmonious integration of traditional bedside manners with contemporary technological advancements. The judicious use of advanced devices for patient examination, recording, and sharing, while upholding patient confidentiality, is pivotal in modern practice and academic research. Additionally, the strategic employment of AI tools at the bedside, to aid in diagnosis and hypothesis generation, underscores their role as valued complements to clinical reasoning. These adapted rules emphasize the importance of continual learning from experience, literature, and colleagues, and stress the necessity for a critical approach toward AI-derived information, which further consolidates clinical skills. These aspects underscore the perpetual relevance of Professor Fisher's rules, advocating not for their replacement but for their evolution. Thus, a balanced methodology that adeptly utilizes the strengths of AI and digital tools, while steadfastly maintaining the core humanistic values, arises as essential in the modern practice of medicine.

KEY MESSAGES

A commitment between traditional medical wisdom and modern technological capabilities may enhance medical practice and patient care. This represents the future of medicine - a resolute commitment to progress and technology, while preserving the essence of medical humanities.

Data Extraction from Free-Text Reports on Mechanical Thrombectomy in Acute Ischemic Stroke Using ChatGPT: A Retrospective Analysis

Background Procedural details of mechanical thrombectomy in patients with ischemic stroke are important predictors of clinical outcome and are collected for prospective studies or national stroke registries. To date, these data are collected manually by human readers, a labor-intensive task that is prone to errors. Purpose To evaluate the use of the large language models (LLMs) GPT-4 and GPT-3.5 to extract data from neuroradiology reports on mechanical thrombectomy in patients with ischemic stroke. Materials and Methods This retrospective study included consecutive reports from patients with ischemic stroke who underwent mechanical thrombectomy between November 2022 and September 2023 at institution 1 and between September 2016 and December 2019 at institution 2. A set of 20 reports was used to optimize the prompt, and the ability of the LLMs to extract procedural data from the reports was compared using the McNemar test. Data manually extracted by an interventional neuroradiologist served as the reference standard. Results A total of 100 internal reports from 100 patients (mean age, 74.7 years ± 13.2 [SD]; 53 female) and 30 external reports from 30 patients (mean age, 72.7 years ± 13.5; 18 male) were included. All reports were successfully processed by GPT-4 and GPT-3.5. Of 2800 data entries, 2631 (94.0% [95% CI: 93.0, 94.8]; range per category, 61%-100%) data points were correctly extracted by GPT-4 without the need for further postprocessing. With 1788 of 2800 correct data entries, GPT-3.5 produced fewer correct data entries than did GPT-4 (63.9% [95% CI: 62.0, 65.6]; range per category, 14%-99%; P < .001). For the external reports, GPT-4 extracted 760 of 840 (90.5% [95% CI: 88.3, 92.4]) correct data entries, while GPT-3.5 extracted 539 of 840 (64.2% [95% CI: 60.8, 67.4]; P < .001). Conclusion Compared with GPT-3.5, GPT-4 more frequently extracted correct procedural data from free-text reports on mechanical thrombectomy performed in patients with ischemic stroke. © RSNA, 2024 Supplemental material is available for this article.

Applications of Natural Language Processing for the Management of Stroke Disorders: Scoping Review

BACKGROUND

Recent advances in natural language processing (NLP) have heightened the interest of the medical community in its application to health care in general, in particular to stroke, a medical emergency of great impact. In this rapidly evolving context, it is necessary to learn and understand the experience already accumulated by the medical and scientific community.

OBJECTIVE

The aim of this scoping review was to explore the studies conducted in the last 10 years using NLP to assist the management of stroke emergencies so as to gain insight on the state of the art, its main contexts of application, and the software tools that are used.

METHODS

Data were extracted from Scopus and Medline through PubMed, using the keywords "natural language processing" and "stroke." Primary research questions were related to the phases, contexts, and types of textual data used in the studies. Secondary research questions were related to the numerical and statistical methods and the software used to process the data. The extracted data were structured in tables and their relative frequencies were calculated. The relationships between categories were analyzed through multiple correspondence analysis.

RESULTS

Twenty-nine papers were included in the review, with the majority being cohort studies of ischemic stroke published in the last 2 years. The majority of papers focused on the use of NLP to assist in the diagnostic phase, followed by the outcome prognosis, using text data from diagnostic reports and in many cases annotations on medical images. The most frequent approach was based on general machine learning techniques applied to the results of relatively simple NLP methods with the support of ontologies and standard vocabularies. Although smaller in number, there has been an increasing body of studies using deep learning techniques on numerical and vectorized representations of the texts obtained with more sophisticated NLP tools.

CONCLUSIONS

Studies focused on NLP applied to stroke show specific trends that can be compared to the more general application of artificial intelligence to stroke. The purpose of using NLP is often to improve processes in a clinical context rather than to assist in the rehabilitation process. The state of the art in NLP is represented by deep learning architectures, among which Bidirectional Encoder Representations from Transformers has been found to be especially widely used in the medical field in general, and for stroke in particular, with an increasing focus on the processing of annotations on medical images.

Artificial Intelligence to Improve Patient Understanding of Radiology Reports

Diagnostic imaging reports are generally written with a target audience of other providers. As a result, the reports are written with medical jargon and technical detail to ensure accurate communication. With implementation of the 21st Century Cures Act, patients have greater and quicker access to their imaging reports, but these reports are still written above the comprehension level of the average patient. Consequently, many patients have requested reports to be conveyed in language accessible to them. Numerous studies have shown that improving patient understanding of their condition results in better outcomes, so driving comprehension of imaging reports is essential. Summary statements, second reports, and the inclusion of the radiologist's phone number have been proposed, but these solutions have implications for radiologist workflow. Artificial intelligence (AI) has the potential to simplify imaging reports without significant disruptions. Many AI technologies have been applied to radiology reports in the past for various clinical and research purposes, but patient focused solutions have largely been ignored. New natural language processing technologies and large language models (LLMs) have the potential to improve patient understanding of their imaging reports. However, LLMs are a nascent technology and significant research is required before LLM-driven report simplification is used in patient care.

Machine Learning in Clinical Trials: A Primer with Applications to Neurology

We reviewed foundational concepts in artificial intelligence (AI) and machine learning (ML) and discussed ways in which these methodologies may be employed to enhance progress in clinical trials and research, with particular attention to applications in the design, conduct, and interpretation of clinical trials for neurologic diseases. We discussed ways in which ML may help to accelerate the pace of subject recruitment, provide realistic simulation of medical interventions, and enhance remote trial administration via novel digital biomarkers and therapeutics. Lastly, we provide a brief overview of the technical, administrative, and regulatory challenges that must be addressed as ML achieves greater integration into clinical trial workflows.