Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification

Machine learning natural language processing for identifying venous thromboembolism: systematic review and meta-analysis

ABSTRACT

Venous thromboembolism (VTE) is a leading cause of preventable in-hospital mortality. Monitoring VTE cases is limited by the challenges of manual medical record review and diagnosis code interpretation. Natural language processing (NLP) can automate the process. Rule-based NLP methods are effective but time consuming. Machine learning (ML)-NLP methods present a promising solution. We conducted a systematic review and meta-analysis of studies published before May 2023 that use ML-NLP to identify VTE diagnoses in the electronic health records. Four reviewers screened all manuscripts, excluding studies that only used a rule-based method. A meta-analysis evaluated the pooled performance of each study's best performing model that evaluated for pulmonary embolism and/or deep vein thrombosis. Pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with confidence interval (CI) were calculated by DerSimonian and Laird method using a random-effects model. Study quality was assessed using an adapted TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) tool. Thirteen studies were included in the systematic review and 8 had data available for meta-analysis. Pooled sensitivity was 0.931 (95% CI, 0.881-0.962), specificity 0.984 (95% CI, 0.967-0.992), PPV 0.910 (95% CI, 0.865-0.941) and NPV 0.985 (95% CI, 0.977-0.990). All studies met at least 13 of the 21 NLP-modified TRIPOD items, demonstrating fair quality. The highest performing models used vectorization rather than bag-of-words and deep-learning techniques such as convolutional neural networks. There was significant heterogeneity in the studies, and only 4 validated their model on an external data set. Further standardization of ML studies can help progress this novel technology toward real-world implementation.

Automated hearing loss type classification based on pure tone audiometry data

Hearing problems are commonly diagnosed with the use of tonal audiometry, which measures a patient's hearing threshold in both air and bone conduction at various frequencies. Results of audiometry tests, usually represented graphically in the form of an audiogram, need to be interpreted by a professional audiologist in order to determine the exact type of hearing loss and administer proper treatment. However, the small number of professionals in the field can severely delay proper diagnosis. The presented work proposes a neural network solution for classification of tonal audiometry data. The solution, based on the Bidirectional Long Short-Term Memory architecture, has been devised and evaluated for classifying audiometry results into four classes, representing normal hearing, conductive hearing loss, mixed hearing loss, and sensorineural hearing loss. The network was trained using 15,046 test results analysed and categorised by professional audiologists. The proposed model achieves 99.33% classification accuracy on datasets outside of training. In clinical application, the model allows general practitioners to independently classify tonal audiometry results for patient referral. In addition, the proposed solution provides audiologists and otolaryngologists with access to an AI decision support system that has the potential to reduce their burden, improve diagnostic accuracy, and minimise human error.

Development and Operationalization of an Automated Workflow for Correlation of Knee MRI and Arthroscopy Findings

OBJECTIVE

In this study, we sought to establish and evaluate an automated workflow to prospectively capture and correlate knee MRI findings with surgical findings in a large medical center.

METHODS

This retrospective analysis included data from patients who had undergone knee MRI followed by arthroscopic knee surgery within 6 months during a 2-year period (2019-2020). Discrete data were automatically extracted from a structured knee MRI report template implementing pick lists. Operative findings were recorded discretely by surgeons using a custom-built web-based telephone application. MRI findings were classified as true-positive, true-negative, false-positive, or false-negative for medial meniscus (MM), lateral meniscus (LM), and anterior cruciate ligament (ACL) tears, with arthroscopy used as the reference standard. An automated dashboard displaying up-to-date concordance and individual and group accuracy was enabled for each radiologist. Manual correlation between MRI and operative reports was performed on a random sample of 10% of cases for comparison with automatically derived values.

RESULTS

Data from 3,187 patients (1,669 male; mean age, 47 years) were analyzed. Automatic correlation was available for 60% of cases, with an overall MRI diagnostic accuracy of 93% (MM, 92%; LM, 89%; ACL, 98%). In cases reviewed manually, the number of cases that could be correlated with surgery was higher (84%). Concordance between automated and manual review was 99% when both were available (MM, 98%; LM, 100%; ACL, 99%).

CONCLUSION

This automated system was able to accurately and continuously assess correlation between imaging and operative findings for a large number of MRI examinations.

A Deep Learning Framework for Predicting Patient Decannulation on Extracorporeal Membrane Oxygenation Devices: Development and Model Analysis Study

BACKGROUND

Venovenous extracorporeal membrane oxygenation (VV-ECMO) is a therapy for patients with refractory respiratory failure. The decision to decannulate someone from extracorporeal membrane oxygenation (ECMO) often involves weaning trials and clinical intuition. To date, there are limited prognostication metrics to guide clinical decision-making to determine which patients will be successfully weaned and decannulated.

OBJECTIVE

This study aims to assist clinicians with the decision to decannulate a patient from ECMO, using Continuous Evaluation of VV-ECMO Outcomes (CEVVO), a deep learning-based model for predicting success of decannulation in patients supported on VV-ECMO. The running metric may be applied daily to categorize patients into high-risk and low-risk groups. Using these data, providers may consider initiating a weaning trial based on their expertise and CEVVO.

METHODS

Data were collected from 118 patients supported with VV-ECMO at the Columbia University Irving Medical Center. Using a long short-term memory-based network, CEVVO is the first model capable of integrating discrete clinical information with continuous data collected from an ECMO device. A total of 12 sets of 5-fold cross validations were conducted to assess the performance, which was measured using the area under the receiver operating characteristic curve (AUROC) and average precision (AP). To translate the predicted values into a clinically useful metric, the model results were calibrated and stratified into risk groups, ranging from 0 (high risk) to 3 (low risk). To further investigate the performance edge of CEVVO, 2 synthetic data sets were generated using Gaussian process regression. The first data set preserved the long-term dependency of the patient data set, whereas the second did not.

RESULTS

CEVVO demonstrated consistently superior classification performance compared with contemporary models (P<.001 and P=.04 compared with the next highest AUROC and AP). Although the model's patient-by-patient predictive power may be too low to be integrated into a clinical setting (AUROC 95% CI 0.6822-0.7055; AP 95% CI 0.8515-0.8682), the patient risk classification system displayed greater potential. When measured at 72 hours, the high-risk group had a successful decannulation rate of 58% (7/12), whereas the low-risk group had a successful decannulation rate of 92% (11/12; P=.04). When measured at 96 hours, the high- and low-risk groups had a successful decannulation rate of 54% (6/11) and 100% (9/9), respectively (P=.01). We hypothesized that the improved performance of CEVVO was owing to its ability to efficiently capture transient temporal patterns. Indeed, CEVVO exhibited improved performance on synthetic data with inherent temporal dependencies (P<.001) compared with logistic regression and a dense neural network.

CONCLUSIONS

The ability to interpret and integrate large data sets is paramount for creating accurate models capable of assisting clinicians in risk stratifying patients supported on VV-ECMO. Our framework may guide future incorporation of CEVVO into more comprehensive intensive care monitoring systems.

A narrative review of deep learning in thyroid imaging: current progress and future prospects

Background and Objective

Deep learning (DL) has contributed substantially to the evolution of image analysis by unlocking increased data and computational power. These DL algorithms have further facilitated the growing trend of implementing precision medicine, particularly in areas of diagnosis and therapy. Thyroid imaging, as a routine means to screening for thyroid diseases on large-scale populations, is a massive data source for the development of DL models. Thyroid disease is a global health problem and involves structural and functional changes. The objective of this study was to evaluate the general rules and future directions of DL networks in thyroid medical image analysis through a review of original articles published between 2018 and 2023.

Methods

We searched for English-language articles published between April 2018 and September 2023 in the databases of PubMed, Web of Science, and Google Scholar. The keywords used in the search included artificial intelligence or DL, thyroid diseases, and thyroid nodule or thyroid carcinoma.

Key Content and Findings

The computer vision tasks of DL in thyroid imaging included classification, segmentation, and detection. The current applications of DL in clinical workflow were found to mainly include management of thyroid nodules/carcinoma, risk evaluation of thyroid cancer metastasis, and discrimination of functional thyroid diseases.

Conclusions

DL is expected to enhance the quality of thyroid images and provide greater precision in the assessment of thyroid images. Specifically, DL can increase the diagnostic accuracy of thyroid diseases and better inform clinical decision-making.

Medical image analysis using deep learning algorithms

In the field of medical image analysis within deep learning (DL), the importance of employing advanced DL techniques cannot be overstated. DL has achieved impressive results in various areas, making it particularly noteworthy for medical image analysis in healthcare. The integration of DL with medical image analysis enables real-time analysis of vast and intricate datasets, yielding insights that significantly enhance healthcare outcomes and operational efficiency in the industry. This extensive review of existing literature conducts a thorough examination of the most recent deep learning (DL) approaches designed to address the difficulties faced in medical healthcare, particularly focusing on the use of deep learning algorithms in medical image analysis. Falling all the investigated papers into five different categories in terms of their techniques, we have assessed them according to some critical parameters. Through a systematic categorization of state-of-the-art DL techniques, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), Long Short-term Memory (LSTM) models, and hybrid models, this study explores their underlying principles, advantages, limitations, methodologies, simulation environments, and datasets. Based on our results, Python was the most frequent programming language used for implementing the proposed methods in the investigated papers. Notably, the majority of the scrutinized papers were published in 2021, underscoring the contemporaneous nature of the research. Moreover, this review accentuates the forefront advancements in DL techniques and their practical applications within the realm of medical image analysis, while simultaneously addressing the challenges that hinder the widespread implementation of DL in image analysis within the medical healthcare domains. These discerned insights serve as compelling impetuses for future studies aimed at the progressive advancement of image analysis in medical healthcare research. The evaluation metrics employed across the reviewed articles encompass a broad spectrum of features, encompassing accuracy, sensitivity, specificity, F-score, robustness, computational complexity, and generalizability.

Depression prediction based on LassoNet-RNN model: A longitudinal study

Depression has become a widespread health concern today. Understanding the influencing factors can promote human mental health as well as provide a basis for exploring preventive measures. Combining LassoNet with recurrent neural network (RNN), this study constructed a screening model ,LassoNet-RNN, for identifying influencing factors of individual depression. Based on multi-wave surveys of China Health and Retirement Longitudinal Study (CHARLS) dataset (11,661 observations), we analyzed the multivariate time series data and recognized 27 characteristic variables selected from four perspectives: demographics, health-related risk factors, household economic status, and living environment. Additionally, the importance rankings of the characteristic variables were obtained. These results offered insightful recommendations for theoretical developments and practical decision making in public health.

Role of artificial intelligence and machine learning in the diagnosis of cerebrovascular disease

Introduction

Cerebrovascular diseases are known to cause significant morbidity and mortality to the general population. In patients with cerebrovascular disease, prompt clinical evaluation and radiographic interpretation are both essential in optimizing clinical management and in triaging patients for critical and potentially life-saving neurosurgical interventions. With recent advancements in the domains of artificial intelligence (AI) and machine learning (ML), many AI and ML algorithms have been developed to further optimize the diagnosis and subsequent management of cerebrovascular disease. Despite such advances, further studies are needed to substantively evaluate both the diagnostic accuracy and feasibility of these techniques for their application in clinical practice. This review aims to analyze the current use of AI and MI algorithms in the diagnosis of, and clinical decision making for cerebrovascular disease, and to discuss both the feasibility and future applications of utilizing such algorithms.

Methods

We review the use of AI and ML algorithms to assist clinicians in the diagnosis and management of ischemic stroke, hemorrhagic stroke, intracranial aneurysms, and arteriovenous malformations (AVMs). After identifying the most widely used algorithms, we provide a detailed analysis of the accuracy and effectiveness of these algorithms in practice.

Results

The incorporation of AI and ML algorithms for cerebrovascular patients has demonstrated improvements in time to detection of intracranial pathologies such as intracerebral hemorrhage (ICH) and infarcts. For ischemic and hemorrhagic strokes, commercial AI software platforms such as RapidAI and Viz.AI have bene implemented into routine clinical practice at many stroke centers to expedite the detection of infarcts and ICH, respectively. Such algorithms and neural networks have also been analyzed for use in prognostication for such cerebrovascular pathologies. These include predicting outcomes for ischemic stroke patients, hematoma expansion, risk of aneurysm rupture, bleeding of AVMs, and in predicting outcomes following interventions such as risk of occlusion for various endovascular devices. Preliminary analyses have yielded promising sensitivities when AI and ML are used in concert with imaging modalities and a multidisciplinary team of health care providers.

Conclusion

The implementation of AI and ML algorithms to supplement clinical practice has conferred a high degree of accuracy, efficiency, and expedited detection in the clinical and radiographic evaluation and management of ischemic and hemorrhagic strokes, AVMs, and aneurysms. Such algorithms have been explored for further purposes of prognostication for these conditions, with promising preliminary results. Further studies should evaluate the longitudinal implementation of such techniques into hospital networks and residency programs to supplement clinical practice, and the extent to which these techniques improve patient care and clinical outcomes in the long-term.

Transformer versus traditional natural language processing: how much data is enough for automated radiology report classification?

OBJECTIVES

Current state-of-the-art natural language processing (NLP) techniques use transformer deep-learning architectures, which depend on large training datasets. We hypothesized that traditional NLP techniques may outperform transformers for smaller radiology report datasets.

METHODS

We compared the performance of BioBERT, a deep-learning-based transformer model pre-trained on biomedical text, and three traditional machine-learning models (gradient boosted tree, random forest, and logistic regression) on seven classification tasks given free-text radiology reports. Tasks included detection of appendicitis, diverticulitis, bowel obstruction, and enteritis/colitis on abdomen/pelvis CT reports, ischemic infarct on brain CT/MRI reports, and medial and lateral meniscus tears on knee MRI reports (7,204 total annotated reports). The performance of NLP models on held-out test sets was compared after training using the full training set, and 2.5%, 10%, 25%, 50%, and 75% random subsets of the training data.

RESULTS

In all tested classification tasks, BioBERT performed poorly at smaller training sample sizes compared to non-deep-learning NLP models. Specifically, BioBERT required training on approximately 1,000 reports to perform similarly or better than non-deep-learning models. At around 1,250 to 1,500 training samples, the testing performance for all models began to plateau, where additional training data yielded minimal performance gain.

CONCLUSIONS

With larger sample sizes, transformer NLP models achieved superior performance in radiology report binary classification tasks. However, with smaller sizes (<1000) and more imbalanced training data, traditional NLP techniques performed better.

ADVANCES IN KNOWLEDGE

Our benchmarks can help guide clinical NLP researchers in selecting machine-learning models according to their dataset characteristics.

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.

Accurate Prediction of Sudden Cardiac Death Based on Heart Rate Variability Analysis Using Convolutional Neural Network

Sudden cardiac death (SCD) is a significant global health issue that affects individuals with and without a history of heart disease. Early identification of SCD risk factors is crucial in reducing mortality rates. This study aims to utilize electrocardiogram (ECG) tools, specifically focusing on heart rate variability (HRV), to detect early SCD risk factors. In this study, we expand the comparison group dataset to include five groups: Normal Sinus Rhythm (NSR), coronary artery disease (CAD), Congestive Heart Failure (CHF), Ventricular Tachycardia (VT), and SCD. ECG signals were recorded for 30 min and segmented into 5 min intervals, following the recommended HRV feature analysis guidelines. We introduce an innovative approach to HRV signal analysis by utilizing Convolutional Neural Networks (CNN). The CNN model was optimized by tuning hyperparameters such as the number of layers, learning rate, and batch size, significantly impacting the prediction accuracy. The findings demonstrate that the HRV approach, in conjunction with linear features and the DL method, achieved a higher accuracy rate, averaging 99.30%, reaching 97% sensitivity, 99.60% specificity, and 97.87% precision. Future research should focus on further exploring and refining DL methods in the context of HRV analysis to improve SCD prediction.

Natural Language Processing for Clinical Laboratory Data Repository Systems: Implementation and Evaluation for Respiratory Viruses

BACKGROUND

With the growing volume and complexity of laboratory repositories, it has become tedious to parse unstructured data into structured and tabulated formats for secondary uses such as decision support, quality assurance, and outcome analysis. However, advances in natural language processing (NLP) approaches have enabled efficient and automated extraction of clinically meaningful medical concepts from unstructured reports.

OBJECTIVE

In this study, we aimed to determine the feasibility of using the NLP model for information extraction as an alternative approach to a time-consuming and operationally resource-intensive handcrafted rule-based tool. Therefore, we sought to develop and evaluate a deep learning-based NLP model to derive knowledge and extract information from text-based laboratory reports sourced from a provincial laboratory repository system.

METHODS

The NLP model, a hierarchical multilabel classifier, was trained on a corpus of laboratory reports covering testing for 14 different respiratory viruses and viral subtypes. The corpus includes 87,500 unique laboratory reports annotated by 8 subject matter experts (SMEs). The classification task involved assigning the laboratory reports to labels at 2 levels: 24 fine-grained labels in level 1 and 6 coarse-grained labels in level 2. A "label" also refers to the status of a specific virus or strain being tested or detected (eg, influenza A is detected). The model's performance stability and variation were analyzed across all labels in the classification task. Additionally, the model's generalizability was evaluated internally and externally on various test sets.

RESULTS

Overall, the NLP model performed well on internal, out-of-time (pre-COVID-19), and external (different laboratories) test sets with microaveraged F1-scores >94% across all classes. Higher precision and recall scores with less variability were observed for the internal and pre-COVID-19 test sets. As expected, the model's performance varied across categories and virus types due to the imbalanced nature of the corpus and sample sizes per class. There were intrinsically fewer classes of viruses being detected than those tested; therefore, the model's performance (lowest F1-score of 57%) was noticeably lower in the detected cases.

CONCLUSIONS

We demonstrated that deep learning-based NLP models are promising solutions for information extraction from text-based laboratory reports. These approaches enable scalable, timely, and practical access to high-quality and encoded laboratory data if integrated into laboratory information system repositories.

Comprehensive evaluation of machine learning algorithms for predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability

Introduction

Perinatal women tend to have difficulties with sleep along with autonomic characteristics. This study aimed to identify a machine learning algorithm capable of achieving high accuracy in predicting sleep-wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability (HRV).

Methods

Nine HRV indicators (features) and sleep-wake conditions of 154 pregnant women were measured for 1 week, from the 23rd to the 32nd weeks of pregnancy. Ten machine learning and three deep learning methods were applied to predict three types of sleep-wake conditions (wake, shallow sleep, and deep sleep). In addition, the prediction of four conditions, in which the wake conditions before and after sleep were differentiated-shallow sleep, deep sleep, and the two types of wake conditions-was also tested.

Results and Discussion

In the test for predicting three types of sleep-wake conditions, most of the algorithms, except for Naïve Bayes, showed higher areas under the curve (AUCs; 0.82-0.88) and accuracy (0.78-0.81). The test using four types of sleep-wake conditions with differentiation between the wake conditions before and after sleep also resulted in successful prediction by the gated recurrent unit with the highest AUC (0.86) and accuracy (0.79). Among the nine features, seven made major contributions to predicting sleep-wake conditions. Among the seven features, "the number of interval differences of successive RR intervals greater than 50 ms (NN50)" and "the proportion dividing NN50 by the total number of RR intervals (pNN50)" were useful to predict sleep-wake conditions unique to pregnancy. These findings suggest alterations in the vagal tone system specific to pregnancy.

Ophthalmology Operation Note Encoding with Open-Source Machine Learning and Natural Language Processing

INTRODUCTION

Accurate assignment of procedural codes has important medico-legal, academic, and economic purposes for healthcare providers. Procedural coding requires accurate documentation and exhaustive manual labour to interpret complex operation notes. Ophthalmology operation notes are highly specialised making the process time-consuming and challenging to implement. This study aimed to develop natural language processing (NLP) models trained by medical professionals to assign procedural codes based on the surgical report. The automation and accuracy of these models can reduce burden on healthcare providers and generate reimbursements that reflect the operation performed.

METHODS

A retrospective analysis of ophthalmological operation notes from two metropolitan hospitals over a 12-month period was conducted. Procedural codes according to the Medicare Benefits Schedule (MBS) were applied. XGBoost, decision tree, Bidirectional Encoder Representations from Transformers (BERT) and logistic regression models were developed for classification experiments. Experiments involved both multi-label and binary classification, and the best performing model was used on the holdout test dataset.

RESULTS

There were 1,000 operation notes included in the study. Following manual review, the five most common procedures were cataract surgery (374 cases), vitrectomy (298 cases), laser therapy (149 cases), trabeculectomy (56 cases), and intravitreal injections (49 cases). Across the entire dataset, current coding was correct in 53.9% of cases. The BERT model had the highest classification accuracy (88.0%) in the multi-label classification on these five procedures. The total reimbursement achieved by the machine learning algorithm was $184,689.45 ($923.45 per case) compared with the gold standard of $214,527.50 ($1,072.64 per case).

CONCLUSION

Our study demonstrates accurate classification of ophthalmic operation notes into MBS coding categories with NLP technology. Combining human and machine-led approaches involves using NLP to screen operation notes to code procedures, with human review for further scrutiny. This technology can allow the assignment of correct MBS codes with greater accuracy. Further research and application in this area can facilitate accurate logging of unit activity, leading to reimbursements for healthcare providers. Increased accuracy of procedural coding can play an important role in training and education, study of disease epidemiology and improve research ways to optimise patient outcomes.

Facial expression recognition using lightweight deep learning modeling

Facial expression is a type of communication and is useful in many areas of computer vision, including intelligent visual surveillance, human-robot interaction and human behavior analysis. A deep learning approach is presented to classify happy, sad, angry, fearful, contemptuous, surprised and disgusted expressions. Accurate detection and classification of human facial expression is a critical task in image processing due to the inconsistencies amid the complexity, including change in illumination, occlusion, noise and the over-fitting problem. A stacked sparse auto-encoder for facial expression recognition (SSAE-FER) is used for unsupervised pre-training and supervised fine-tuning. SSAE-FER automatically extracts features from input images, and the softmax classifier is used to classify the expressions. Our method achieved an accuracy of 92.50% on the JAFFE dataset and 99.30% on the CK+ dataset. SSAE-FER performs well compared to the other comparative methods in the same domain.

Contextual Embeddings-Based Web Page Categorization Using the Fine-Tune BERT Model

The World Wide Web has revolutionized the way we live, causing the number of web pages to increase exponentially. The web provides access to a tremendous amount of information, so it is difficult for internet users to locate accurate and useful information on the web. In order to categorize pages accurately based on the queries of users, methods of categorizing web pages need to be developed. The text content of web pages plays a significant role in the categorization of web pages. If a word’s position is altered within a sentence, causing a change in the interpretation of that sentence, this phenomenon is called polysemy. In web page categorization, the polysemy property causes ambiguity and is referred to as the polysemy problem. This paper proposes a fine-tuned model to solve the polysemy problem, using contextual embeddings created by the symmetry multi-head encoder layer of the Bidirectional Encoder Representations from Transformers (BERT). The effectiveness of the proposed model was evaluated by using the benchmark datasets for web page categorization, i.e., WebKB and DMOZ. Furthermore, the experiment series also fine-tuned the proposed model’s hyperparameters to achieve 96.00% and 84.00% F1-Scores, respectively, demonstrating the proposed model’s importance compared to baseline approaches based on machine learning and deep learning.

Structural Analysis and Classification of Low-Molecular-Weight Hyaluronic Acid by Near-Infrared Spectroscopy: A Comparison between Traditional Machine Learning and Deep Learning

Confusing low-molecular-weight hyaluronic acid (LMWHA) from acid degradation and enzymatic hydrolysis (named LMWHA-A and LMWHA-E, respectively) will lead to health hazards and commercial risks. The purpose of this work is to analyze the structural differences between LMWHA-A and LMWHA-E, and then achieve a fast and accurate classification based on near-infrared (NIR) spectroscopy and machine learning. First, we combined nuclear magnetic resonance (NMR), Fourier transform infrared (FTIR) spectroscopy, two-dimensional correlated NIR spectroscopy (2DCOS), and aquaphotomics to analyze the structural differences between LMWHA-A and LMWHA-E. Second, we compared the dimensionality reduction methods including principal component analysis (PCA), kernel PCA (KPCA), and t-distributed stochastic neighbor embedding (t-SNE). Finally, the differences in classification effect of traditional machine learning methods including partial least squares-discriminant analysis (PLS-DA), support vector classification (SVC), and random forest (RF) as well as deep learning methods including one-dimensional convolutional neural network (1D-CNN) and long short-term memory (LSTM) were compared. The results showed that genetic algorithm (GA)-SVC and RF were the best performers in traditional machine learning, but their highest accuracy in the test dataset was 90%, while the accuracy of 1D-CNN and LSTM models in the training dataset and test dataset classification was 100%. The results of this study show that compared with traditional machine learning, the deep learning models were better for the classification of LMWHA-A and LMWHA-E. Our research provides a new methodological reference for the rapid and accurate classification of biological macromolecules.

Next Generation Infectious Diseases Monitoring Gages via Incremental Federated Learning: Current Trends and Future Possibilities

Infectious diseases are always alarming for the survival of human life and are a key concern in the public health domain. Therefore, early diagnosis of these infectious diseases is a high demand for modern-era healthcare systems. Novel general infectious diseases such as coronavirus are infectious diseases that cause millions of human deaths across the globe in 2020. Therefore, early, robust recognition of general infectious diseases is the desirable requirement of modern intelligent healthcare systems. This systematic study is designed under Kitchenham guidelines and sets different RQs (research questions) for robust recognition of general infectious diseases. From 2018 to 2021, four electronic databases, IEEE, ACM, Springer, and ScienceDirect, are used for the extraction of research work. These extracted studies delivered different schemes for the accurate recognition of general infectious diseases through different machine learning techniques with the inclusion of deep learning and federated learning models. A framework is also introduced to share the process of detection of infectious diseases by using machine learning models. After the filtration process, 21 studies are extracted and mapped to defined RQs. In the future, early diagnosis of infectious diseases will be possible through wearable health monitoring cages. Moreover, these gages will help to reduce the time and death rate by detection of severe diseases at starting stage.

Systematic review of content analysis algorithms based on deep neural networks

Today according to social media, the internet, Etc. Data is rapidly produced and occupies a large space in systems that have resulted in enormous data warehouses; the progress in information technology has significantly increased the speed and ease of data flow.text mining is one of the most important methods for extracting a useful model through extracting and adapting knowledge from data sets. However, many studies have been conducted based on the usage of deep learning for text processing and text mining issues.The idea and method of text mining are one of the fields that seek to extract useful information from unstructured textual data that is used very today. Deep learning and machine learning techniques in classification and text mining and their type are discussed in this paper as well. Neural networks of various kinds, namely, ANN, RNN, CNN, and LSTM, are the subject of study to select the best technique. In this study, we conducted a Systematic Literature Review to extract and associate the algorithms and features that have been used in this area. Based on our search criteria, we retrieved 130 relevant studies from electronic databases between 1997 and 2021; we have selected 43 studies for further analysis using inclusion and exclusion criteria in Section 3.2. According to this study, hybrid LSTM is the most widely used deep learning algorithm in these studies, and SVM in machine learning method high accuracy in result shown.

Convolutional Neural Network for Predicting Thyroid Cancer Based on Ultrasound Elastography Image of Perinodular Region

We aimed to develop deep learning models based on perinodular regions' shear-wave elastography (SWE) images and ultrasound (US) images of thyroid nodules (TNs) and determine their performances in predicting thyroid cancer. A total of 1747 American College of Radiology Thyroid Imaging Reporting & Data System 4 (TR4) thyroid nodules (TNs) in 1582 patients were included in this retrospective study. US images, SWE images, and 2 quantitative SWE parameters (maximum elasticity of TNs; 5-point average maximum elasticity of TNs) were obtained. Based on US and SWE images of TNs and perinodular tissue, respectively, 7 single-image convolutional neural networks (CNN) models [US, internal SWE, 0.5 mm SWE, 1.0 mm SWE, 1.5 mm SWE, 2.0 mm SWE of perinodular tissue, and whole SWE region of interest (ROI) image] and another 6 fusional-image CNN models (US + internal SWE, US + 0.5 mm SWE, US + 1.0 mm SWE, US + 1.5 mm SWE, US + 2.0 mm SWE, US + ROI SWE) were established using RestNet18. All of the CNN models and quantitative SWE parameters were built on a training cohort (1247 TNs) and evaluated on a validation cohort (500 TNs). In predicting thyroid cancer, US + 2.0 mm SWE image CNN model obtained the highest area under the curve in 10 mm < TNs ≤ 20 mm (0.95 for training; 0.92 for validation) and TNs > 20 mm (0.95 for training; 0.92 for validation), while US + 1.0 mm SWE image CNN model obtained the highest area under the curve in TNs ≤ 10 mm (0.95 for training; 0.92 for validation). The CNN models based on the fusion of SWE segmentation images and US images improve the radiological diagnostic accuracy of thyroid cancer.

Automatic text classification of actionable radiology reports of tinnitus patients using bidirectional encoder representations from transformer (BERT) and in-domain pre-training (IDPT)

Background

Given the increasing number of people suffering from tinnitus, the accurate categorization of patients with actionable reports is attractive in assisting clinical decision making. However, this process requires experienced physicians and significant human labor. Natural language processing (NLP) has shown great potential in big data analytics of medical texts; yet, its application to domain-specific analysis of radiology reports is limited.

Objective

The aim of this study is to propose a novel approach in classifying actionable radiology reports of tinnitus patients using bidirectional encoder representations from transformer BERT-based models and evaluate the benefits of in domain pre-training (IDPT) along with a sequence adaptation strategy.

Methods

A total of 5864 temporal bone computed tomography(CT) reports are labeled by two experienced radiologists as follows: (1) normal findings without notable lesions; (2) notable lesions but uncorrelated to tinnitus; and (3) at least one lesion considered as potential cause of tinnitus. We then constructed a framework consisting of deep learning (DL) neural networks and self-supervised BERT models. A tinnitus domain-specific corpus is used to pre-train the BERT model to further improve its embedding weights. In addition, we conducted an experiment to evaluate multiple groups of max sequence length settings in BERT to reduce the excessive quantity of calculations. After a comprehensive comparison of all metrics, we determined the most promising approach through the performance comparison of F1-scores and AUC values.

Results

In the first experiment, the BERT finetune model achieved a more promising result (AUC-0.868, F1-0.760) compared with that of the Word2Vec-based models(AUC-0.767, F1-0.733) on validation data. In the second experiment, the BERT in-domain pre-training model (AUC-0.948, F1-0.841) performed significantly better than the BERT based model(AUC-0.868, F1-0.760). Additionally, in the variants of BERT fine-tuning models, Mengzi achieved the highest AUC of 0.878 (F1-0.764). Finally, we found that the BERT max-sequence-length of 128 tokens achieved an AUC of 0.866 (F1-0.736), which is almost equal to the BERT max-sequence-length of 512 tokens (AUC-0.868,F1-0.760).

Conclusion

In conclusion, we developed a reliable BERT-based framework for tinnitus diagnosis from Chinese radiology reports, along with a sequence adaptation strategy to reduce computational resources while maintaining accuracy. The findings could provide a reference for NLP development in Chinese radiology reports.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01946-y.

A comparative study on deep learning models for text classification of unstructured medical notes with various levels of class imbalance

BACKGROUND

Discharge 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.

METHODS

In 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).

RESULTS

The 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.

CONCLUSIONS

For 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.

Leakage Current Sensor and Neural Network for MOA Monitoring

Metal-oxide arrester (MOA) has been widely used in electric power systems. The leakage current monitoring of MOA can not only detect the MOA's running state continuously and intelligently but also reduce the unexpected outage of the equipment, which is also beneficial to the stability of the grid. The MOA loses its protection function due to various faults caused by excessive leakage current in actual running. This article studies the monitoring method of MOA based on leakage current sensor and back propagation (BP) neural network. At first, we design a novel leakage current sensor to acquire the leakage current of MOA. Then, the leakage current measurement of MOA based on harmonic analysis is proposed. Finally, the strong training ability of the BP neural network is used to train some key parameters that can reflect the aging of MOA so as to monitor the MOA state. The experimental results show that the leakage current acquired from the simulation is close to the actual leakage current that needs to be measured. It is also shown that the proposed method has good anti-interference and can effectively monitor the aging of MOA. Through the training of the BP neural network, the experiments prove that the training method in this article is superior to other neural network training methods obviously.

Automatic detection of actionable findings and communication mentions in radiology reports using natural language processing

OBJECTIVES

To develop and validate classifiers for automatic detection of actionable findings and documentation of nonroutine communication in routinely delivered radiology reports.

METHODS

Two radiologists annotated all actionable findings and communication mentions in a training set of 1,306 radiology reports and a test set of 1,000 reports randomly selected from the electronic health record system of a large tertiary hospital. Various feature sets were constructed based on the impression section of the reports using different preprocessing steps (stemming, removal of stop words, negations, and previously known or stable findings) and n-grams. Random forest classifiers were trained to detect actionable findings, and a decision-rule classifier was trained to find communication mentions. Classifier performance was evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity.

RESULTS

On the training set, the actionable finding classifier with the highest cross-validated performance was obtained for a feature set of unigrams, after stemming and removal of negated, known, and stable findings. On the test set, this classifier achieved an AUC of 0.876 (95% CI 0.854-0.898). The classifier for communication detection was trained after negation removal, using unigrams as features. The resultant decision rule had a sensitivity of 0.841 (95% CI 0.706-0.921) and specificity of 0.990 (95% CI 0.981-0.994) on the test set.

CONCLUSIONS

Automatic detection of actionable findings and subsequent communication in routinely delivered radiology reports is possible. This can serve quality control purposes and may alert radiologists to the presence of actionable findings during reporting.

KEY POINTS

• Classifiers were developed for automatic detection of the broad spectrum of actionable findings and subsequent communication mentions in routinely delivered radiology reports. • Straightforward report preprocessing and simple feature sets can produce well-performing classifiers. • The resultant classifiers show good performance for detection of actionable findings and excellent performance for detection of communication mentions.

Multi-label annotation of text reports from computed tomography of the chest, abdomen, and pelvis using deep learning

Background

There is progress to be made in building artificially intelligent systems to detect abnormalities that are not only accurate but can handle the true breadth of findings that radiologists encounter in body (chest, abdomen, and pelvis) computed tomography (CT). Currently, the major bottleneck for developing multi-disease classifiers is a lack of manually annotated data. The purpose of this work was to develop high throughput multi-label annotators for body CT reports that can be applied across a variety of abnormalities, organs, and disease states thereby mitigating the need for human annotation.

Methods

We used a dictionary approach to develop rule-based algorithms (RBA) for extraction of disease labels from radiology text reports. We targeted three organ systems (lungs/pleura, liver/gallbladder, kidneys/ureters) with four diseases per system based on their prevalence in our dataset. To expand the algorithms beyond pre-defined keywords, attention-guided recurrent neural networks (RNN) were trained using the RBA-extracted labels to classify reports as being positive for one or more diseases or normal for each organ system. Alternative effects on disease classification performance were evaluated using random initialization or pre-trained embedding as well as different sizes of training datasets. The RBA was tested on a subset of 2158 manually labeled reports and performance was reported as accuracy and F-score. The RNN was tested against a test set of 48,758 reports labeled by RBA and performance was reported as area under the receiver operating characteristic curve (AUC), with 95% CIs calculated using the DeLong method.

Results

Manual validation of the RBA confirmed 91–99% accuracy across the 15 different labels. Our models extracted disease labels from 261,229 radiology reports of 112,501 unique subjects. Pre-trained models outperformed random initialization across all diseases. As the training dataset size was reduced, performance was robust except for a few diseases with a relatively small number of cases. Pre-trained classification AUCs reached > 0.95 for all four disease outcomes and normality across all three organ systems.

Conclusions

Our label-extracting pipeline was able to encompass a variety of cases and diseases in body CT reports by generalizing beyond strict rules with exceptional accuracy. The method described can be easily adapted to enable automated labeling of hospital-scale medical data sets for training image-based disease classifiers.

Automated Radiology-Arthroscopy Correlation of Knee Meniscal Tears Using Natural Language Processing Algorithms

RATIONALE AND OBJECTIVES

Train and apply natural language processing (NLP) algorithms for automated radiology-arthroscopy correlation of meniscal tears.

MATERIALS AND METHODS

In this retrospective single-institution study, we trained supervised machine learning models (logistic regression, support vector machine, and random forest) to detect medial or lateral meniscus tears on free-text MRI reports. We trained and evaluated model performances with cross-validation using 3593 manually annotated knee MRI reports. To assess radiology-arthroscopy correlation, we then randomly partitioned this dataset 80:20 for training and testing, where 108 test set MRIs were followed by knee arthroscopy within 1 year. These free-text arthroscopy reports were also manually annotated. The NLP algorithms trained on the knee MRI training dataset were then evaluated on the MRI and arthroscopy report test datasets. We assessed radiology-arthroscopy agreement using the ensembled NLP-extracted findings versus manually annotated findings.

RESULTS

The NLP models showed high cross-validation performance for meniscal tear detection on knee MRI reports (medial meniscus F1 scores 0.93-0.94, lateral meniscus F1 scores 0.86-0.88). When these algorithms were evaluated on arthroscopy reports, despite never training on arthroscopy reports, performance was similar, though higher with model ensembling (medial meniscus F1 score 0.97, lateral meniscus F1 score 0.99). However, ensembling did not improve performance on knee MRI reports. In the radiology-arthroscopy test set, the ensembled NLP models were able to detect mismatches between MRI and arthroscopy reports with sensitivity 79% and specificity 87%.

CONCLUSION

Radiology-arthroscopy correlation can be automated for knee meniscal tears using NLP algorithms, which shows promise for education and quality improvement.

IoT Based Smart Monitoring of Patients' with Acute Heart Failure

The prediction of heart failure survivors is a challenging task and helps medical professionals to make the right decisions about patients. Expertise and experience of medical professionals are required to care for heart failure patients. Machine Learning models can help with understanding symptoms of cardiac disease. However, manual feature engineering is challenging and requires expertise to select the appropriate technique. This study proposes a smart healthcare framework using the Internet-of-Things (IoT) and cloud technologies that improve heart failure patients’ survival prediction without considering manual feature engineering. The smart IoT-based framework monitors patients on the basis of real-time data and provides timely, effective, and quality healthcare services to heart failure patients. The proposed model also investigates deep learning models in classifying heart failure patients as alive or deceased. The framework employs IoT-based sensors to obtain signals and send them to the cloud web server for processing. These signals are further processed by deep learning models to determine the state of patients. Patients’ health records and processing results are shared with a medical professional who will provide emergency help if required. The dataset used in this study contains 13 features and was attained from the UCI repository known as Heart Failure Clinical Records. The experimental results revealed that the CNN model is superior to other deep learning and machine learning models with a 0.9289 accuracy value.

Citation Context Analysis Using Combined Feature Embedding and Deep Convolutional Neural Network Model

Citation creates a link between citing and the cited author, and the frequency of citation has been regarded as the basic element to measure the impact of research and knowledge-based achievements. Citation frequency has been widely used to calculate the impact factor, H index, i10 index, etc., of authors and journals. However, for a fair evaluation, the qualitative aspect should be considered along with the quantitative measures. The sentiments expressed in citation play an important role in evaluating the quality of the research because the citation may be used to indicate appreciation, criticism, or a basis for carrying on research. In-text citation analysis is a challenging task, despite the use of machine learning models and automatic sentiment annotation. Additionally, the use of deep learning models and word embedding is not studied very well. This study performs several experiments with machine learning and deep learning models using fastText, fastText subword, global vectors, and their blending for word representation to perform in-text sentiment analysis. A dimensionality reduction technique called principal component analysis (PCA) is utilized to reduce the feature vectors before passing them to the classifier. Additionally, a customized convolutional neural network (CNN) is presented to obtain higher classification accuracy. Results suggest that the deep learning CNN coupled with fastText word embedding produces the best results in terms of accuracy, precision, recall, and F1 measure.

A Fusion NLP Model for the Inference of Standardized Thyroid Nodule Malignancy Scores from Radiology Report Text

Radiology reports are a rich resource for advancing deep learning applications for medical images, facilitating the generation of large-scale annotated image databases. Although the ambiguity and subtlety of natural language poses a significant challenge to information extraction from radiology reports. Thyroid Imaging Reporting and Data Systems (TI-RADS) has been proposed as a system to standardize ultrasound imaging reports for thyroid cancer screening and diagnosis, through the implementation of structured templates and a standardized thyroid nodule malignancy risk scoring system; however there remains significant variation in radiologist practice when it comes to diagnostic thyroid ultrasound interpretation and reporting. In this work, we propose a computerized approach using a contextual embedding and fusion strategy for the large-scale inference of TI-RADS final assessment categories from narrative ultrasound (US) reports. The proposed model has achieved high accuracy on an internal data set, and high performance scores on an external validation dataset.

Sense understanding of text conversation using temporal convolution neural network

This paper proposes a model which uses Spatio Temporal features for real-time sense understanding of a text conversation. The proposed model uses CNN along with the concept of LSTM to create a new Spatio temporal cell. Furthermore, the proposed model is used to classify the sentences into eight senses. The model achieved an F-Score around 0.984 on sense classification. Additionally, the efficiency and capabilities of the model are also tested on a standard IMDB sentiment classification dataset. On the IMDB dataset, the model gave an accuracy of 89.27. The experimental results show that the proposed model works better than a CNN model, a Bi-LSTM model, and a combination of CNN & LSTM model in terms of a number of parameters and execution time.

Association Mining of Near Misses in Hydropower Engineering Construction Based on Convolutional Neural Network Text Classification

Accidents of various types in the construction of hydropower engineering projects occur frequently, which leads to significant numbers of casualties and economic losses. Identifying and eliminating near misses are a significant means of preventing accidents. Mining near-miss data can provide valuable information on how to mitigate and control hazards. However, most of the data generated in the construction of hydropower engineering projects are semi-structured text data without unified standard expression, so data association analysis is time-consuming and labor-intensive. Thus, an artificial intelligence (AI) automatic classification method based on a convolutional neural network (CNN) is adopted to obtain structured data on near-miss locations and near-miss types from safety records. The apriori algorithm is used to further mine the associations between “locations” and “types” by scanning structured data. The association results are visualized using a network diagram. A Sankey diagram is used to reveal the information flow of near-miss specific objects using the “location ⟶ type” strong association rule. The proposed method combines text classification, association rules, and the Sankey diagrams and provides a novel approach for mining semi-structured text. Moreover, the method is proven to be useful and efficient for exploring near-miss distribution laws in hydropower engineering construction to reduce the possibility of accidents and efficiently improve the safety level of hydropower engineering construction sites.

Predicting pulmonary embolism among hospitalized patients with machine learning algorithms

Background

Objective

Materials and Methods

Results

Conclusions

The Influencing Legal and Factors of Migrant Children's Educational Integration Based on Convolutional Neural Network

This research aims to analyze the influencing factors of migrant children's education integration based on the convolutional neural network (CNN) algorithm. The attention mechanism, LSTM, and GRU are introduced based on the CNN algorithm, to establish an ALGCNN model for text classification. Film and television review data set (MR), Stanford sentiment data set (SST), and news opinion data set (MPQA) are used to analyze the classification accuracy, loss value, Hamming loss (HL), precision (Pre), recall (Re), and micro-F1 (F1) of the ALGCNN model. Then, on the big data platform, data in the Comprehensive Management System of Floating Population and Rental Housing, Student Status Information Management System, and Student Information Management System of Beijing city are taken as samples. The ALGCNN model is used to classify and compare related data. It is found that in the MR, STT, and MPQA data sets, the classification accuracy and loss value of the ALGCNN model are better than other algorithms. HL is the lowest (15.2 ± 1.38%), the Pre is second only to the BERT algorithm, and the Re and F1 are both higher than other algorithms. From 2015 to 2019, the number of migrant children in different grades of elementary school shows a gradual increase. Among migrant children, the number of migrant children from other counties in this province is evidently higher than the number of migrant children from other provinces. Among children of migrant workers, the number of immigrants from other counties in this province is also notably higher than the number of immigrants from other provinces. With the gradual increase in the years, the proportion of township-level expenses shows a gradual decrease, whereas the proportion of district and county-level expenses shows a gradual increase. Moreover, the accuracy of the ALGCNN model in migrant children and local children data classification is 98.6 and 98.9%, respectively. The proportion of migrant children in the first and second grades of a primary school in Beijing city is obviously higher than that of local children (p < 0.05). The average final score of local children was greatly higher than that of migrant children (p < 0.05), whereas the scores of migrant children's listening methods, learning skills, and learning environment adaptability are lower, which shows that an effective text classification model (ALGCNN) is established based on the CNN algorithm. In short, the children's education costs, listening methods, learning skills, and learning environment adaptability are the main factors affecting migrant children's educational integration, and this work provides a reference for the analysis of migrant children's educational integration.

Classification of Multiple Diseases on Body CT Scans Using Weakly Supervised Deep Learning

PURPOSE

To design multidisease classifiers for body CT scans for three different organ systems using automatically extracted labels from radiology text reports.

MATERIALS AND METHODS

This retrospective study included a total of 12 092 patients (mean age, 57 years ± 18 [standard deviation]; 6172 women) for model development and testing. Rule-based algorithms were used to extract 19 225 disease labels from 13 667 body CT scans performed between 2012 and 2017. Using a three-dimensional DenseVNet, three organ systems were segmented: lungs and pleura, liver and gallbladder, and kidneys and ureters. For each organ system, a three-dimensional convolutional neural network classified each as no apparent disease or for the presence of four common diseases, for a total of 15 different labels across all three models. Testing was performed on a subset of 2158 CT volumes relative to 2875 manually derived reference labels from 2133 patients (mean age, 58 years ± 18; 1079 women). Performance was reported as area under the receiver operating characteristic curve (AUC), with 95% CIs calculated using the DeLong method.

RESULTS

Manual validation of the extracted labels confirmed 91%-99% accuracy across the 15 different labels. AUCs for lungs and pleura labels were as follows: atelectasis, 0.77 (95% CI: 0.74, 0.81); nodule, 0.65 (95% CI: 0.61, 0.69); emphysema, 0.89 (95% CI: 0.86, 0.92); effusion, 0.97 (95% CI: 0.96, 0.98); and no apparent disease, 0.89 (95% CI: 0.87, 0.91). AUCs for liver and gallbladder were as follows: hepatobiliary calcification, 0.62 (95% CI: 0.56, 0.67); lesion, 0.73 (95% CI: 0.69, 0.77); dilation, 0.87 (95% CI: 0.84, 0.90); fatty, 0.89 (95% CI: 0.86, 0.92); and no apparent disease, 0.82 (95% CI: 0.78, 0.85). AUCs for kidneys and ureters were as follows: stone, 0.83 (95% CI: 0.79, 0.87); atrophy, 0.92 (95% CI: 0.89, 0.94); lesion, 0.68 (95% CI: 0.64, 0.72); cyst, 0.70 (95% CI: 0.66, 0.73); and no apparent disease, 0.79 (95% CI: 0.75, 0.83).

CONCLUSION

Weakly supervised deep learning models were able to classify diverse diseases in multiple organ systems from CT scans.Keywords: CT, Diagnosis/Classification/Application Domain, Semisupervised Learning, Whole-Body Imaging© RSNA, 2022.

Automatic Diagnosis Labeling of Cardiovascular MRI by Using Semisupervised Natural Language Processing of Text Reports

PURPOSE

To assess whether the semisupervised natural language processing (NLP) of text from clinical radiology reports could provide useful automated diagnosis categorization for ground truth labeling to overcome manual labeling bottlenecks in the machine learning pipeline.

MATERIALS AND METHODS

In this retrospective study, 1503 text cardiac MRI reports from 2016 to 2019 were manually annotated for five diagnoses by clinicians: normal, dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy, myocardial infarction (MI), and myocarditis. A semisupervised method that uses bidirectional encoder representations from transformers (BERT) pretrained on 1.14 million scientific publications was fine-tuned by using the manually extracted labels, with a report dataset split into groups of 801 for training, 302 for validation, and 400 for testing. The model's performance was compared with two traditional NLP models: a rule-based model and a support vector machine (SVM) model. The models' F1 scores and receiver operating characteristic curves were used to analyze performance.

RESULTS

After 15 epochs, the F1 scores on the test set of 400 reports were as follows: normal, 84%; DCM, 79%; hypertrophic cardiomyopathy, 86%; MI, 91%; and myocarditis, 86%. The pooled F1 score and area under the receiver operating curve were 86% and 0.96, respectively. On the same test set, the BERT model had a higher performance than the rule-based model (F1 score, 42%) and SVM model (F1 score, 82%). Diagnosis categories classified by using the BERT model performed the labeling of 1000 MR images in 0.2 second.

CONCLUSION

The developed model used labels extracted from radiology reports to provide automated diagnosis categorization of MR images with a high level of performance.Keywords: Semisupervised Learning, Diagnosis/Classification/Application Domain, Named Entity Recognition, MRI Supplemental material is available for this article. © RSNA, 2021.

An application for classifying perceptions on my health bank in Taiwan using convolutional neural networks and web-based computerized adaptive testing: A development and usability study

BACKGROUND

The classification of a respondent's opinions online into positive and negative classes using a minimal number of questions is gradually changing and helps turn techniques into practices. A survey incorporating convolutional neural networks (CNNs) into web-based computerized adaptive testing (CAT) was used to collect perceptions on My Health Bank (MHB) from users in Taiwan. This study designed an online module to accurately and efficiently turn a respondent's perceptions into positive and negative classes using CNNs and web-based CAT.

METHODS

In all, 640 patients, family members, and caregivers with ages ranging from 20 to 70 years who were registered MHB users were invited to complete a 3-domain, 26-item, 5-category questionnaire asking about their perceptions on MHB (PMHB26) in 2019. The CNN algorithm and k-means clustering were used for dividing respondents into 2 classes of unsatisfied and satisfied classes and building a PMHB26 predictive model to estimate parameters. Exploratory factor analysis, the Rasch model, and descriptive statistics were used to examine the demographic characteristics and PMHB26 factors that were suitable for use in CNNs and Rasch multidimensional CAT (MCAT). An application was then designed to classify MHB perceptions.

RESULTS

We found that 3 construct factors were extracted from PMHB26. The reliability of PMHB26 for each subscale beyond 0.94 was evident based on internal consistency and stability in the data. We further found the following: the accuracy of PMHB26 with CNN yields a higher accuracy rate (0.98) with an area under the curve of 0.98 (95% confidence interval, 0.97-0.99) based on the 391 returned questionnaires; and for the efficiency, approximately one-third of the items were not necessary to answer in reducing the respondents' burdens using Rasch MCAT.

CONCLUSIONS

The PMHB26 CNN model, combined with the Rasch online MCAT, is recommended for improving the accuracy and efficiency of classifying patients' perceptions of MHB utility. An application developed for helping respondents self-assess the MHB cocreation of value can be applied to other surveys in the future.

Neural networks applied to 12-lead electrocardiograms predict body mass index, visceral adiposity and concurrent cardiometabolic ill-health

Background

Obesity is associated with electrophysiological remodeling, which manifests as detectable changes on the surface electrocardiogram (ECG).

Objective

To develop neural networks (NN) to predict body mass index (BMI) from ECGs and test the hypothesis that discrepancies between NN-predicted BMI and measured BMI are indicative of underlying adiposity and/or concurrent cardiometabolic ill-health.

Methods

NN models were developed using 36,856 12-lead resting ECGs from the UK Biobank. Two architectures were developed for continuous and categorical BMI estimation (normal weight [BMI <25 kg/m²] vs overweight/obese [BMI ≥25 kg/m²]). Models for male and female participants were trained and tested separately. For each sex, data were randomly divided into 4 folds, and models were evaluated in a leave-1-fold-out manner.

Results

ECGs were available for 17,807 male and 19,049 female participants (mean ages: 61 ± 7 and 63 ± 8 years; mean BMI 26 ± 5 kg/m² and 27 ± 4 kg/m², respectively). NN models detected overweight/obese individuals with average accuracies of 75% and 73% for male and female subjects, respectively. The magnitudes of difference between NN-predicted BMI and actual BMI were significantly correlated with visceral adipose tissue volumes. Concurrent hypertension, diabetes, dyslipidemia, and/or coronary heart disease explained false-positive classifications (ie, calculated BMI <25 kg/m² misclassified as ≥25 kg/m² by NN model, P < .001).

Conclusion

NN models applied to 12-lead ECGs predict BMI with a reasonable degree of accuracy. Discrepancies between NN-predicted and calculated BMI may be indicative of underlying visceral adiposity and concomitant cardiometabolic perturbation, which could be used to identify individuals at risk of cardiometabolic disease.

Haze Prediction Model Using Deep Recurrent Neural Network

In recent years, haze pollution is frequent, which seriously affects daily life and production process. The main factors to measure the degree of smoke pollution are the concentrations of PM2.5 and PM10. Therefore, it is of great significance to study the prediction of PM2.5/PM10 concentration. Since PM2.5 and PM10 concentration data are time series, their time characteristics should be considered in their prediction. However, the traditional neural network is limited by its own structure and has some weakness in processing time related data. Recurrent neural network is a kind of network specially used for sequence data modeling, that is, the current output of the sequence is correlated with the historical output. In this paper, a haze prediction model is established based on a deep recurrent neural network. We obtained air pollution data in Chengdu from the China Air Quality Online Monitoring and Analysis Platform, and conducted experiments based on these data. The results show that the new method can predict smog more effectively and accurately, and can be used for social and economic purposes.

Machine learning predictive models for acute pancreatitis: A systematic review

INTRODUCTION

Acute pancreatitis (AP) is a common clinical pancreatic disease. Patients with different severity levels have different clinical outcomes. With the advantages of algorithms, machine learning (ML) has gradually emerged in the field of disease prediction, assisting doctors in decision-making.

METHODS

A systematic review was conducted using the PubMed, Web of Science, Scopus, and Embase databases, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Publication time was limited from inception to 29 May 2021. Studies that have used ML to establish predictive tools for AP were eligible for inclusion. Quality assessment of the included studies was conducted in accordance with the IJMEDI checklist.

RESULTS

In this systematic review, 24 of 2,913 articles, with a total of 8,327 patients and 47 models, were included. The studies could be divided into five categories: 10 studies (42%) reported severity prediction; 10 studies (42%), complication prediction; 3 studies (13%), mortality prediction; 2 studies (8%), recurrence prediction; and 2 studies (8%), surgery timing prediction. ML showed great accuracy in several prediction tasks. However, most of the included studies were retrospective in nature, conducted at a single centre, based on database data, and lacked external validation. According to the IJMEDI checklist and our scoring criteria, two studies were considered to be of high quality. Most studies had an obvious bias in the quality of data preparation, validation, and deployment dimensions.

CONCLUSION

In the prediction tasks for AP, ML has shown great potential in assisting decision-making. However, the existing studies still have some deficiencies in the process of model construction. Future studies need to optimize the deficiencies and further evaluate the comparability of the ML systems and model performance, so as to consequently develop high-quality ML-based models that can be used in clinical practice.

Basic Artificial Intelligence Techniques: Natural Language Processing of Radiology Reports

Natural language processing (NLP) is a subfield of computer science and linguistics that can be applied to extract meaningful information from radiology reports. Symbolic NLP is rule based and well suited to problems that can be explicitly defined by a set of rules. Statistical NLP is better situated to problems that cannot be well defined and requires annotated or labeled examples from which machine learning algorithms can infer the rules. Both symbolic and statistical NLP have found success in a variety of radiology use cases. More recently, deep learning approaches, including transformers, have gained traction and demonstrated good performance.

Semantic Features with Contextual Knowledge-Based Web Page Categorization Using the GloVe Model and Stacked BiLSTM

Internet technologies are emerging very fast nowadays, due to which web pages are generated exponentially. Web page categorization is required for searching and exploring relevant web pages based on users’ queries and is a tedious task. The majority of web page categorization techniques ignore semantic features and the contextual knowledge of the web page. This paper proposes a web page categorization method that categorizes web pages based on semantic features and contextual knowledge. Initially, the GloVe model is applied to capture the semantic features of the web pages. Thereafter, a Stacked Bidirectional long short-term memory (BiLSTM) with symmetric structure is applied to extract the contextual and latent symmetry information from the semantic features for web page categorization. The performance of the proposed model has been evaluated on the publicly available WebKB dataset. The proposed model shows superiority over the existing state-of-the-art machine learning and deep learning methods.

Fully-channel regional attention network for disease-location recognition with tongue images

OBJECTIVE

Using the deep learning model to realize tongue image-based disease location recognition and focus on solving two problems: 1. The ability of the general convolution network to model detailed regional tongue features is weak; 2. Ignoring the group relationship between convolution channels, which caused the high redundancy of the model.

METHODS

To enhance the convolutional neural networks. In this paper, a stochastic region pooling method is proposed to gain detailed regional features. Also, an inner-imaging channel relationship modeling method is proposed to model multi-region relations on all channels. Moreover, we combine it with the spatial attention mechanism.

RESULTS

The tongue image dataset with the clinical disease-location label is established. Abundant experiments are carried out on it. The experimental results show that the proposed method can effectively model the regional details of tongue image and improve the performance of disease location recognition.

CONCLUSION

In this paper, we construct the tongue image dataset with disease-location labels to mine the relationship between tongue images and disease locations. A novel fully-channel regional attention network is proposed to model the local detail tongue features and improve the modeling efficiency.

SIGNIFICANCE

The applications of deep learning in tongue image disease-location recognition and the proposed innovative models have guiding significance for other assistant diagnostic tasks. The proposed model provides an example of efficient modeling of detailed tongue features, which is of great guiding significance for other auxiliary diagnosis applications.

Deep Learning for Classifying Physical Activities from Accelerometer Data

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the two models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from eight volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides accurate performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. The results indicate that our method provides the medical doctors and trainers a promising way to track and understand a patient’s physical activities precisely for better treatment.

Automatic Prediction of Recurrence of Major Cardiovascular Events: A Text Mining Study Using Chest X-Ray Reports

Methods

We used EHR data of patients included in the Second Manifestations of ARTerial disease (SMART) study. We propose a deep learning-based multimodal architecture for our text mining pipeline that integrates neural text representation with preprocessed clinical predictors for the prediction of recurrence of major cardiovascular events in cardiovascular patients. Text preprocessing, including cleaning and stemming, was first applied to filter out the unwanted texts from X-ray radiology reports. Thereafter, text representation methods were used to numerically represent unstructured radiology reports with vectors. Subsequently, these text representation methods were added to prediction models to assess their clinical relevance. In this step, we applied logistic regression, support vector machine (SVM), multilayer perceptron neural network, convolutional neural network, long short-term memory (LSTM), and bidirectional LSTM deep neural network (BiLSTM).

Results

We performed various experiments to evaluate the added value of the text in the prediction of major cardiovascular events. The two main scenarios were the integration of radiology reports (1) with classical clinical predictors and (2) with only age and sex in the case of unavailable clinical predictors. In total, data of 5603 patients were used with 5-fold cross-validation to train the models. In the first scenario, the multimodal BiLSTM (MI-BiLSTM) model achieved an area under the curve (AUC) of 84.7%, misclassification rate of 14.3%, and F1 score of 83.8%. In this scenario, the SVM model, trained on clinical variables and bag-of-words representation, achieved the lowest misclassification rate of 12.2%. In the case of unavailable clinical predictors, the MI-BiLSTM model trained on radiology reports and demographic (age and sex) variables reached an AUC, F1 score, and misclassification rate of 74.5%, 70.8%, and 20.4%, respectively.

Conclusions

Using the case study of routine care chest X-ray radiology reports, we demonstrated the clinical relevance of integrating text features and classical predictors in our text mining pipeline for cardiovascular risk prediction. The MI-BiLSTM model with word embedding representation appeared to have a desirable performance when trained on text data integrated with the clinical variables from the SMART study. Our results mined from chest X-ray reports showed that models using text data in addition to laboratory values outperform those using only known clinical predictors.

An Integrated Compensation Method for the Force Disturbance of a Six-Axis Force Sensor in Complex Manufacturing Scenarios

As one of the key components for active compliance control and human–robot collaboration, a six-axis force sensor is often used for a robot to obtain contact forces. However, a significant problem is the distortion between the contact forces and the data conveyed by the six-axis force sensor because of its zero drift, system error, and gravity of robot end-effector. To eliminate the above disturbances, an integrated compensation method is proposed, which uses a deep learning network and the least squares method to realize the zero-point prediction and tool load identification, respectively. After that, the proposed method can automatically complete compensation for the six-axis force sensor in complex manufacturing scenarios. Additionally, the experimental results demonstrate that the proposed method can provide effective and robust compensation for force disturbance and achieve high measurement accuracy.