Search

This study aimed to investigate the application of label propagation techniques to propagate labels among photoplethysmogram (PPG) signals, particularly in imbalanced class scenarios and limited data availability scenarios, where clean PPG samples are significantly outnumbered by artifact-contaminated samples. We investigated a dataset comprising PPG recordings from 1571 patients, wherein approximately 82% of the samples were identified as clean, while the remaining 18% were contaminated by artifacts. Our research compares the performance of supervised classifiers, such as conventional classifiers and neural networks (Multi-Layer Perceptron (MLP), Transformers, Fully Convolutional Network (FCN)), with the semi-supervised Label Propagation (LP) algorithm for artifact classification in PPG signals. The results indicate that the LP algorithm achieves a precision of 91%, a recall of 90%, and an F1 score of 90% for the ‘‘artifacts’’ class, showcasing its effectiveness in annotating a medical dataset, even in cases where clean samples are rare. Although the K-Nearest Neighbors (KNN) supervised model demonstrated good results with a precision of 89%, a recall of 95%, and an F1 score of 92%, the semi-supervised algorithm excels in artifact detection. In the case of imbalanced and limited pediatric intensive care environment data, the semi-supervised LP algorithm is promising for artifact detection in PPG signals. The results of this study are important for improving the accuracy of PPG-based health monitoring, particularly in situations in which motion artifacts pose challenges to data interpretation.

Recent research at CHU Sainte Justine's Pediatric Critical Care Unit (PICU) has revealed that traditional machine learning methods, such as semi-supervised label propagation and K-nearest neighbors, outperform Transformer-based models in artifact detection from PPG signals, mainly when data is limited. This study addresses the underutilization of abundant unlabeled data by employing self-supervised learning (SSL) to extract latent features from these data, followed by fine-tuning on labeled data. Our experiments demonstrate that SSL significantly enhances the Transformer model's ability to learn representations, improving its robustness in artifact classification tasks. Among various SSL techniques, including masking, contrastive learning, and DINO (self-distillation with no labels)-contrastive learning exhibited the most stable and superior performance in small PPG datasets. Further, we delve into optimizing contrastive loss functions, which are crucial for contrastive SSL. Inspired by InfoNCE, we introduce a novel contrastive loss function that facilitates smoother training and better convergence, thereby enhancing performance in artifact classification. In summary, this study establishes the efficacy of SSL in leveraging unlabeled data, particularly in enhancing the capabilities of the Transformer model. This approach holds promise for broader applications in PICU environments, where annotated data is often limited., Comment: Under preparation to submit to IEEE for possible publications

This research aims to classify numerical values extracted from medical documents across seven distinct physiological categories, employing CamemBERT-bio. Previous studies suggested that transformer-based models might not perform as well as traditional NLP models in such tasks. To enhance CamemBERT-bio's performances, we introduce two main innovations: integrating keyword embeddings into the model and adopting a number-agnostic strategy by excluding all numerical data from the text. The implementation of label embedding techniques refines the attention mechanisms, while the technique of using a `numerical-blind' dataset aims to bolster context-centric learning. Another key component of our research is determining the criticality of extracted numerical data. To achieve this, we utilized a simple approach that involves verifying if the value falls within the established standard ranges. Our findings are encouraging, showing substantial improvements in the effectiveness of CamemBERT-bio, surpassing conventional methods with an F1 score of 0.89. This represents an over 20\% increase over the 0.73 $F_1$ score of traditional approaches and an over 9\% increase over the 0.82 $F_1$ score of state-of-the-art approaches. All this was achieved despite using small and imbalanced training datasets., Comment: Under the revision. arXiv admin note: substantial text overlap with arXiv:2404.10171

Van Thang Nguyen,1,2,* Hong Duc Pham,2,3,* Van Phan Nguyen Thanh,4 Thanh Dung Le5,6 1Radiology Department, Hai Duong Medical Technical University, Hai Duong, Vietnam; 2Radiology Department, Hanoi Medical University, Hanoi, Vietnam; 3Radiology Department, Saint Paul Hospital, Hanoi, Vietnam; 4Department of Biochemistry, Pham Ngoc Thach University of Medicine, Ho Chi Minh city, Vietnam; 5Radiology Department, Viet Duc University Hospital, Hanoi, Vietnam; 6Department of Radiology, VNU University of Medicine and Pharmacy, Hanoi, Vietnam*These authors contributed equally to this workCorrespondence: Van Phan Nguyen Thanh, Department of biochemistry, Pham Ngoc Thach University of Medicine, 2 Duong Quang Trung Street, Ho Chi Minh city, 700000, Vietnam, Tel +84919691770, Email pnthanhvan@pnt.edu.vnPurpose: This study was conducted to evaluate the results of conservative management of blunt splenic trauma according to the American Association for the Surgery of Trauma-Organ Injury Scale (AAST-OIS) in 2018 by embolization.Methods: This observational study included 50 patients (42 men and 8 women) with splenic injury who underwent multidetector computed tomography (MDCT) and embolization.Results: According to the 2018 AAST-OIS, 27 cases had higher grades than they did according to the 1994 AAST-OIS. The grades of two cases of grade II increased to grade IV; those of 15 cases of grade III increased to grade IV; and four cases of grade IV increased to grade V. As a result, all patients underwent successful splenic embolization and were stable at discharge. No patients required re-embolization or conversion to splenectomy. The mean hospital stay was 11.8± 7 days (range, 6– 44 days), with no difference in length of hospital stay among grades of splenic injury (p > 0.05).Conclusion: Compared with the AAST-OIS 1994, the AAST-OIS 2018 classification is useful in making embolization decisions, regardless of the degree of blunt splenic injury with vascular

When dealing with clinical text classification on a small dataset recent studies have confirmed that a well-tuned multilayer perceptron outperforms other generative classifiers, including deep learning ones. To increase the performance of the neural network classifier, feature selection for the learning representation can effectively be used. However, most feature selection methods only estimate the degree of linear dependency between variables and select the best features based on univariate statistical tests. Furthermore, the sparsity of the feature space involved in the learning representation is ignored. Goal: Our aim is therefore to access an alternative approach to tackle the sparsity by compressing the clinical representation feature space, where limited French clinical notes can also be dealt with effectively. Methods: This study proposed an autoencoder learning algorithm to take advantage of sparsity reduction in clinical note representation. The motivation was to determine how to compress sparse, high- dimensional data by reducing the dimension of the clinical note representation feature space. The classification performance of the classifiers was then evaluated in the trained and compressed feature space. Results: The proposed approach provided overall performance gains of up to 3% for each evaluation. Finally, the classifier achieved a 92% accuracy, 91% recall, 91% precision, and 91% f1-score in detecting the patient’s condition. Furthermore, the compression working mechanism and the autoencoder prediction process were demonstrated by applying the theoretic information bottleneck framework.

Transformer-based models have shown outstanding results in natural language processing but face challenges in applications like classifying small-scale clinical texts, especially with constrained computational resources. This study presents a customized Mixture of Expert (MoE) Transformer models for classifying small-scale French clinical texts at CHU Sainte-Justine Hospital. The MoE-Transformer addresses the dual challenges of effective training with limited data and low-resource computation suitable for in-house hospital use. Despite the success of biomedical pre-trained models such as CamemBERT-bio, DrBERT, and AliBERT, their high computational demands make them impractical for many clinical settings. Our MoE-Transformer model not only outperforms DistillBERT, CamemBERT, FlauBERT, and Transformer models on the same dataset but also achieves impressive results: an accuracy of 87\%, precision of 87\%, recall of 85\%, and F1-score of 86\%. While the MoE-Transformer does not surpass the performance of biomedical pre-trained BERT models, it can be trained at least 190 times faster, offering a viable alternative for settings with limited data and computational resources. Although the MoE-Transformer addresses challenges of generalization gaps and sharp minima, demonstrating some limitations for efficient and accurate clinical text classification, this model still represents a significant advancement in the field. It is particularly valuable for classifying small French clinical narratives within the privacy and constraints of hospital-based computational resources., Comment: Under the revision

This study aimed to investigate the application of label propagation techniques to propagate labels among photoplethysmogram (PPG) signals, particularly in imbalanced class scenarios and limited data availability scenarios, where clean PPG samples are significantly outnumbered by artifact-contaminated samples. We investigated a dataset comprising PPG recordings from 1571 patients, wherein approximately 82% of the samples were identified as clean, while the remaining 18% were contaminated by artifacts. Our research compares the performance of supervised classifiers, such as conventional classifiers and neural networks (Multi-Layer Perceptron (MLP), Transformers, Fully Convolutional Network (FCN)), with the semi-supervised Label Propagation (LP) algorithm for artifact classification in PPG signals. The results indicate that the LP algorithm achieves a precision of 91%, a recall of 90%, and an F1 score of 90% for the "artifacts" class, showcasing its effectiveness in annotating a medical dataset, even in cases where clean samples are rare. Although the K-Nearest Neighbors (KNN) supervised model demonstrated good results with a precision of 89%, a recall of 95%, and an F1 score of 92%, the semi-supervised algorithm excels in artifact detection. In the case of imbalanced and limited pediatric intensive care environment data, the semi-supervised LP algorithm is promising for artifact detection in PPG signals. The results of this study are important for improving the accuracy of PPG-based health monitoring, particularly in situations in which motion artifacts pose challenges to data interpretation, Comment: Under preparation to submit to IEEE for possible publications

When dealing with clinical text classification on a small dataset recent studies have confirmed that a well-tuned multilayer perceptron outperforms other generative classifiers, including deep learning ones. To increase the performance of the neural network classifier, feature selection for the learning representation can effectively be used. However, most feature selection methods only estimate the degree of linear dependency between variables and select the best features based on univariate statistical tests. Furthermore, the sparsity of the feature space involved in the learning representation is ignored. Goal: Our aim is therefore to access an alternative approach to tackle the sparsity by compressing the clinical representation feature space, where limited French clinical notes can also be dealt with effectively. Methods: This study proposed an autoencoder learning algorithm to take advantage of sparsity reduction in clinical note representation. The motivation was to determine how to compress sparse, high-dimensional data by reducing the dimension of the clinical note representation feature space. The classification performance of the classifiers was then evaluated in the trained and compressed feature space. Results: The proposed approach provided overall performance gains of up to 3% for each evaluation. Finally, the classifier achieved a 92% accuracy, 91% recall, 91% precision, and 91% f1-score in detecting the patient's condition. Furthermore, the compression working mechanism and the autoencoder prediction process were demonstrated by applying the theoretic information bottleneck framework., Comment: Submitted to IEEE journal for review

The rapid progress in clinical data management systems and artificial intelligence approaches enable the era of personalized medicine. Intensive care units (ICUs) are ideal clinical research environments for such development because they collect many clinical data and are highly computerized. Goal: We designed a retrospective clinical study on a prospective ICU database using clinical natural language to help in the early diagnosis of heart failure in critically ill children. Methods: The methodology consisted of empirical experiments of a learning algorithm to learn the hidden interpretation and presentation of the French clinical note data. This study included 1386 patients’ clinical notes with 5444 single lines of notes. There were 1941 positive cases (36% of total) and 3503 negative cases classified by two independent physicians using a standardized approach. Results: The multilayer perceptron neural network outperforms other discriminative and generative classifiers. Consequently, the proposed framework yields an overall classification performance with 89% accuracy, 88% recall, and 89% precision. Conclusions: This study successfully applied learning representation and ma- chine learning algorithms to detect heart failure in a single French institution from clinical natural language. Further work is needed to use the same methodology in other languages and institutions.

The purpose of the study presented herein is to develop a machine learning algorithm based on natural language processing that automatically detects whether a patient has a cardiac failure or a healthy condition by using physician notes in Research Data Warehouse at CHU Sainte Justine Hospital. First, a word representation learning technique was employed by using bag-of-word (BoW), term frequency inverse document frequency (TFIDF), and neural word embeddings (word2vec). Each representation technique aims to retain the words semantic and syntactic analysis in critical care data. It helps to enrich the mutual information for the word representation and leads to an advantage for further appropriate analysis steps. Second, a machine learning classifier was used to detect the patients condition for either cardiac failure or stable patient through the created word representation vector space from the previous step. This machine learning approach is based on a supervised binary classification algorithm, including logistic regression (LR), Gaussian Naive-Bayes (GaussianNB), and multilayer perceptron neural network (MLPNN). Technically, it mainly optimizes the empirical loss during training the classifiers. As a result, an automatic learning algorithm would be accomplished to draw a high classification performance, including accuracy (acc), precision (pre), recall (rec), and F1 score (f1). The results show that the combination of TFIDF and MLPNN always outperformed other combinations with all overall performance. In the case without any feature selection, the proposed framework yielded an overall classification performance with acc, pre, rec, and f1 of 84% and 82%, 85%, and 83%, respectively. Significantly, if the feature selection was well applied, the overall performance would finally improve up to 4% for each evaluation., Comment: Submitted to 2021 34th IEEE International Symposium on Computer-Based Medical Systems (CBMS)

The rapid progress in clinical data management systems and artificial intelligence approaches enable the era of personalized medicine. Intensive care units (ICUs) are the ideal clinical research environment for such development because they collect many clinical data and are highly computerized environments. We designed a retrospective clinical study on a prospective ICU database using clinical natural language to help in the early diagnosis of heart failure in critically ill children. The methodology consisted of empirical experiments of a learning algorithm to learn the hidden interpretation and presentation of the French clinical note data. This study included 1386 patients' clinical notes with 5444 single lines of notes. There were 1941 positive cases (36 % of total) and 3503 negative cases classified by two independent physicians using a standardized approach. The multilayer perceptron neural network outperforms other discriminative and generative classifiers. Consequently, the proposed framework yields an overall classification performance with 89 % accuracy, 88 % recall, and 89 % precision. This study successfully applied learning representation and machine learning algorithms to detect heart failure from clinical natural language in a single French institution. Further work is needed to use the same methodology in other institutions and other languages., Comment: Accepted for publication in IEEE Open Journal of Engineering in Medicine and Biology. arXiv admin note: text overlap with arXiv:2104.03934

In recent years, Generative Adversarial Networks (GANs) have shown substantial progress in modeling complex distributions of data. These networks have received tremendous attention since they can generate implicit probabilistic models that produce realistic data using a stochastic procedure. While such models have proven highly effective in diverse scenarios, they require a large set of fully-observed training samples. In many applications access to such samples are difficult or even impractical and only noisy or partial observations of the desired distribution is available. Recent research has tried to address the problem of incompletely observed samples to recover the distribution of the data. \citep{zhu2017unpaired} and \citep{yeh2016semantic} proposed methods to solve ill-posed inverse problem using cycle-consistency and latent-space mappings in adversarial networks, respectively. \citep{bora2017compressed} and \citep{kabkab2018task} have applied similar adversarial approaches to the problem of compressed sensing. In this work, we focus on a new variant of GAN models called AmbientGAN, which incorporates a measurement process (e.g. adding noise, data removal and projection) into the GAN training. While in the standard GAN, the discriminator distinguishes a generated image from a real image, in AmbientGAN model the discriminator has to separate a real measurement from a simulated measurement of a generated image. The results shown by \citep{bora2018ambientgan} are quite promising for the problem of incomplete data, and have potentially important implications for generative approaches to compressed sensing and ill-posed problems., Comment: This work was submitted as final project for the course IFT6135: Representation Learning - A Deep Learning Course, University of Montreal, Winter 2018

Ce travail de thèse concerne la préparation, la réactivité, la chimie de coordination et l'utilisation de ligands amidines N-phosphorées en catalyse de Suzuki-Miyaura. Dans un premier temps, nous avons développé la synthèse d'une nouvelle famille de ligands monodentes et bidentes N-phosphino formamidines (R' = H) et N-phosphino amidines (R' =/ H) R"2N-C(R')=N-PR2. Nous avons ensuite mené la première étude systématique de la réactivité de ces composés vis-à-vis d'acides de Brönsted et de Lewis. Des calculs théoriques ont permis de rationaliser nos résultats expérimentaux. Enfin, nous avons étudié la chimie de coordination des ligands monodentes et bidentes amidines N-phosphorées avec différents précurseurs métalliques de palladium(II) et nous avons démontré le potentiel de ces ligands en catalyse de Suzuki-Miyaura dans la réaction entre l'acide boronique et le p-bromoanisole en présence de palladium(II)., This thesis deals with the preparation, the reactivity, the coordination chemistry and the use of N-phosphorus amidine ligands in the Suzuki-Miyaura catalytic reaction. First, we have developped a straightforward synthesis of a new family of monodentate and bidentate ligands, the N-phosphinoformamidines (R' = H) and the N-phosphinoamidines (R' =/ H) R"2N-C(R')=N-PR2. Then, an unprecedented study regarding the reactivity of these compounds towards Brönsted et Lewis acids was carried out. Theoretical calculations enabled us to rationalize our experimental results. Finally, the coordination chemistry of these monodentate and bidentate ligands, N-phosphorus amidines, with various palladium(II) precursors was studied and we have showed the potential of our ligands in the catalytic Suzuki-Miyaura coupling reaction between boronic acid and p-bromoanisol in the presence of palladium(II).