Symptoms are known by their companies: towards association guided disease diagnosis assistant.

Over the last few years, dozens of healthcare surveys have shown a shortage of doctors and an alarming doctor-population ratio. With the motivation of assisting doctors and utilizing their time efficiently, automatic disease diagnosis using artificial intelligence is experiencing an ever-growing demand and popularity. Humans are known by the company they keep; similarly, symptoms also exhibit the association property, i.e., one symptom may strongly suggest another symptom's existence/non-existence, and their association provides crucial information about the suffering condition. The work investigates the role of symptom association in symptom investigation and disease diagnosis process. We propose and build a virtual assistant called Association guided Symptom Investigation and Diagnosis Assistant (A-SIDA) using hierarchical reinforcement learning. The proposed A-SIDDA converses with patients and extracts signs and symptoms as per patients' chief complaints and ongoing dialogue context. We infused association-based recommendations and critic into the assistant, which reinforces the assistant for conducting context-aware, symptom-association guided symptom investigation. Following the symptom investigation, the assistant diagnoses a disease based on the extracted signs and symptoms. The assistant then diagnoses a disease based on the extracted signs and symptoms. In addition to diagnosis accuracy, the relevance of inspected symptoms is critical to the usefulness of a diagnosis framework. We also propose a novel evaluation metric called Investigation Relevance Score (IReS), which measures the relevance of symptoms inspected during symptom investigation. The obtained improvements (Diagnosis success rate-5.36%, Dialogue length-1.16, Match rate-2.19%, Disease classifier-6.36%, IReS-0.3501, and Human score-0.66) over state-of-the-art methods firmly establish the crucial role of symptom association that gets uncovered by the virtual agent. Furthermore, we found that the association guided symptom investigation greatly increases human satisfaction, owing to its seamless topic (symptom) transition.

Assessment of the Wettability of Hydrophobic Solid Substrate by Biosurfactant Produced by Bacillus aryabhattai SPS1001.

Characterized biosurfactant produced by Bacillus aryabhattai SPS1001 isolated from crude oil contaminated soil of Haldia Oil Refinery, IOCL, West Bengal, India, was used to evaluate the surface energy and wettability of hydrophobic substrate by sessile drop method. Bacterial cell culture with cells removed was screened for biosurfactant production by drop collapse assay where drop diameter measured was 12.53 ± 0.01 mN/m and 11.79 ± 0.01 mN/m, respectively, on using hydrophobic substrate diesel oil and n-hexadecane in mineral salt medium. Moreover, the surface tension recorded was 24.4 ± 0.02 and 25.9 ± 0.02 mN/m, whereas interfacial tension measured was 0.28 ± 0.02 and 0.35 ± 0.04 mN/m against diesel oil and n-hexadecane, respectively. Additionally, at liquid-solid (silicone oil-coated glass surface) interface, decrease in contact angles of cell culture with cells removed sample (14.02 ± 0.2° and 14.95 ± 0.6°) translated into increase in surface energy of hydrophobic solid surface and quantitatively measured to 23.70 (diesel oil) and 24.57 (n-hexadecane) mN/m, respectively. Presence of biosurfactant in cell culture with cells removed sample plays an important role in lowering contact angle and in deciding the wetting condition of an oil-wet solid (silicone oil-coated) glass surface to water-wet state. Hence, the wetting property of biosurfactant finds applications in various areas such as coating, printing, etc.

Unsupervised gene selection using biological knowledge : application in sample clustering.

BACKGROUND: Classification of biological samples of gene expression data is a basic building block in solving several problems in the field of bioinformatics like cancer and other disease diagnosis and making a proper treatment plan. One big challenge in sample classification is handling large dimensional and redundant gene expression data. To reduce the complexity of handling this high dimensional data, gene/feature selection plays a major role. RESULTS: The current paper explores the use of biological knowledge acquired from Gene Ontology database in selecting the proper subset of genes which can further participate in clustering of samples. The proposed feature selection technique is unsupervised in nature as it does not utilize any class label information in the process of gene selection. At the end, a multi-objective clustering approach is deployed to cluster the available set of samples in the reduced gene space. CONCLUSIONS: Reported results show that consideration of biological knowledge in gene selection technique not only reduces the feature space dimensionality in great extent but also improves the accuracy of sample classification. The obtained reduced gene space is validated using strong biological significance tests. In order to prove the supremacy of our proposed gene selection based sample clustering technique, a thorough comparative analysis has also been performed with state-of-the-art techniques.

Towards knowledge-infused automated disease diagnosis assistant.

With the advancement of internet communication and telemedicine, people are increasingly turning to the web for various healthcare activities. With an ever-increasing number of diseases and symptoms, diagnosing patients becomes challenging. In this work, we build a diagnosis assistant to assist doctors, which identifies diseases based on patient-doctor interaction. During diagnosis, doctors utilize both symptomatology knowledge and diagnostic experience to identify diseases accurately and efficiently. Inspired by this, we investigate the role of medical knowledge in disease diagnosis through doctor-patient interaction. We propose a two-channel, knowledge-infused, discourse-aware disease diagnosis model (KI-DDI), where the first channel encodes patient-doctor communication using a transformer-based encoder, while the other creates an embedding of symptom-disease using a graph attention network (GAT). In the next stage, the conversation and knowledge graph embeddings are infused together and fed to a deep neural network for disease identification. Furthermore, we first develop an empathetic conversational medical corpus comprising conversations between patients and doctors, annotated with intent and symptoms information. The proposed model demonstrates a significant improvement over the existing state-of-the-art models, establishing the crucial roles of (a) a doctor's effort for additional symptom extraction (in addition to patient self-report) and (b) infusing medical knowledge in identifying diseases effectively. Many times, patients also show their medical conditions, which acts as crucial evidence in diagnosis. Therefore, integrating visual sensory information would represent an effective avenue for enhancing the capabilities of diagnostic assistants.

A multistage framework for respiratory disease detection and assessing severity in chest X-ray images.

Chest Radiography is a non-invasive imaging modality for diagnosing and managing chronic lung disorders, encompassing conditions such as pneumonia, tuberculosis, and COVID-19. While it is crucial for disease localization and severity assessment, existing computer-aided diagnosis (CAD) systems primarily focus on classification tasks, often overlooking these aspects. Additionally, prevalent approaches rely on class activation or saliency maps, providing only a rough localization. This research endeavors to address these limitations by proposing a comprehensive multi-stage framework. Initially, the framework identifies relevant lung areas by filtering out extraneous regions. Subsequently, an advanced fuzzy-based ensemble approach is employed to categorize images into specific classes. In the final stage, the framework identifies infected areas and quantifies the extent of infection in COVID-19 cases, assigning severity scores ranging from 0 to 3 based on the infection's severity. Specifically, COVID-19 images are classified into distinct severity levels, such as mild, moderate, severe, and critical, determined by the modified RALE scoring system. The study utilizes publicly available datasets, surpassing previous state-of-the-art works. Incorporating lung segmentation into the proposed ensemble-based classification approach enhances the overall classification process. This solution can be a valuable alternative for clinicians and radiologists, serving as a secondary reader for chest X-rays, reducing reporting turnaround times, aiding clinical decision-making, and alleviating the workload on hospital staff.

Breast cancer prognosis through the use of multi-modal classifiers: current state of the art and the way forward.

We present a survey of the current state-of-the-art in breast cancer detection and prognosis. We analyze the evolution of Artificial Intelligence-based approaches from using just uni-modal information to multi-modality for detection and how such paradigm shift facilitates the efficacy of detection, consistent with clinical observations. We conclude that interpretable AI-based predictions and ability to handle class imbalance should be considered priority.

Analyzing Effect of Multi-Modality in Predicting Protein-Protein Interactions.

Nowadays, multiple sources of information about proteins are available such as protein sequences, 3D structures, Gene Ontology (GO), etc. Most of the works on protein-protein interaction (PPI) identification had utilized these information about proteins, mainly sequence-based, but individually. The new advances in deep learning techniques allow us to leverage multiple sources/modalities of proteins, which complement each other. Some recent works have shown that multi-modal PPI models perform better than uni-modal approaches. This paper aims to investigate whether the performance of multi-modal PPI models is always consistent or depends on other factors such as dataset distribution, algorithms used to learn features, etc. We have used three modalities for this study: Protein sequence, 3D structure, and GO. Various techniques, including deep learning algorithms, are employed to extract features from multiple sources of proteins. These feature vectors from different modalities are then integrated in several combinations (bi-modal and tri-modal) to predict PPI. To conduct this study, we have used Human and S. cerevisiae PPI datasets. The obtained results demonstrate the potentiality of a multi-modal approach and deep learning techniques in predicting protein interactions. However, the predictive capability of a model for PPI depends on feature extraction methods as well. Also, increasing the modality does not always ensure performance improvement. In this study, the PPI model integrating two modalities outperforms the designed uni-modal and tri-modal PPI models.

Deviation-support based fuzzy ensemble of multi-modal deep learning classifiers for breast cancer prognosis prediction.

Breast cancer is the fifth leading cause of death in females worldwide. Early detection and treatment are crucial for improving health outcomes and preventing more serious conditions. Analyzing diverse information from multiple sources without errors, particularly with the growing burden of cancer cases, is a daunting task for humans. In this study, our main objective is to improve the accuracy of breast cancer survival prediction using a novel ensemble approach. It is novel due to the consideration of deviation (closeness between predicted classes and actual classes) and support (sparsity between predicted classes and actual classes) of the predicted class with respect to the actual class, a feature lacking in traditional ensembles. The ensemble uses fuzzy integrals on support and deviation scores from base classifiers to calculate aggregated scores while considering how confident or uncertain each classifier is. The proposed ensemble mechanism has been evaluated on a multi-modal breast cancer dataset of breast tumors collected from participants in the METABRIC trial. The proposed architecture proves its efficiency by achieving the accuracy, sensitivity, F1-score, and balanced accuracy of 82.88%, 58.64%, 62.94%, and 74.75% respectively. The obtained results are superior to the performance of individual classifiers and existing ensemble approaches.

Graph-BERT and language model-based framework for protein-protein interaction identification.

Identification of protein-protein interactions (PPI) is among the critical problems in the domain of bioinformatics. Previous studies have utilized different AI-based models for PPI classification with advances in artificial intelligence (AI) techniques. The input to these models is the features extracted from different sources of protein information, mainly sequence-derived features. In this work, we present an AI-based PPI identification model utilizing a PPI network and protein sequences. The PPI network is represented as a graph where each node is a protein pair, and an edge is defined between two nodes if there exists a common protein between these nodes. Each node in a graph has a feature vector. In this work, we have used the language model to extract feature vectors directly from protein sequences. The feature vectors for protein in pairs are concatenated and used as a node feature vector of a PPI network graph. Finally, we have used the Graph-BERT model to encode the PPI network graph with sequence-based features and learn the hidden representation of the feature vector for each node. The next step involves feeding the learned representations of nodes to the fully connected layer, the output of which is fed into the softmax layer to classify the protein interactions. To assess the efficacy of the proposed PPI model, we have performed experiments on several PPI datasets. The experimental results demonstrate that the proposed approach surpasses the existing PPI works and designed baselines in classifying PPI.

Prediction of Protein-Protein Interactions Using Vision Transformer and Language Model.

The knowledge of protein-protein interaction (PPI) helps us to understand proteins' functions, the causes and growth of several diseases, and can aid in designing new drugs. The majority of existing PPI research has relied mainly on sequence-based approaches. With the availability of multi-omics datasets (sequence, 3D structure) and advancements in deep learning techniques, it is feasible to develop a deep multi-modal framework that fuses the features learned from different sources of information to predict PPI. In this work, we propose a multi-modal approach utilizing protein sequence and 3D structure. To extract features from the 3D structure of proteins, we use a pre-trained vision transformer model that has been fine-tuned on the structural representation of proteins. The protein sequence is encoded into a feature vector using a pre-trained language model. The feature vectors extracted from the two modalities are fused and then fed to the neural network classifier to predict the protein interactions. To showcase the effectiveness of the proposed methodology, we conduct experiments on two popular PPI datasets, namely, the human dataset and the S. cerevisiae dataset. Our approach outperforms the existing methodologies to predict PPI, including multi-modal approaches. We also evaluate the contributions of each modality by designing uni-modal baselines. We perform experiments with three modalities as well, having gene ontology as the third modality.

SARS-CoV-2 Detection: Radiology based Multi-modal Multi-task Framework.

The global community is still grappling with the SARS-CoV-2 pandemic, declared by the World Health Organization in March 2020. Radiology is an important screening method for the early detection of SARS-CoV-2. Doctors typically recommend that patients undergo one of the radiology procedures during the early stages of diagnosis. Recent research has focused on developing deep learning-based architectures that use either X-Rays or CT-Scans, but not both. This paper presents a multi-modal, multi-task learning framework that uses either the X-Rays or CT-Scans to identify SARS-CoV-2 patients. The framework employs a shared feature embedding that utilizes common information from both X-Rays and CT-Scans, as well as task-specific feature embeddings that are independent of the type of chest screening. The shared and task-specific embeddings are combined to obtain the final classification results, which have been shown to have an accuracy of 98.23% and 98.83% in detecting SARS-CoV-2 using X-Rays and CT-Scans, respectively.

COVID-19 and cyberbullying: deep ensemble model to identify cyberbullying from code-switched languages during the pandemic.

It has been declared by the World Health Organization (WHO) the novel coronavirus a global pandemic due to an exponential spread in COVID-19 in the past months reaching over 100 million cases and resulting in approximately 3 million deaths worldwide. Amid this pandemic, identification of cyberbullying has become a more evolving area of research over posts or comments in social media platforms. In multilingual societies like India, code-switched texts comprise the majority of the Internet. Identifying the online bullying of the code-switched user is bit challenging than monolingual cases. As a first step towards enabling the development of approaches for cyberbullying detection, we developed a new code-switched dataset, collected from Twitter utterances annotated with binary labels. To demonstrate the utility of the proposed dataset, we build different machine learning (Support Vector Machine & Logistic Regression) and deep learning (Multilayer Perceptron, Convolution Neural Network, BiLSTM, BERT) algorithms to detect cyberbullying of English-Hindi (En-Hi) code-switched text. Our proposed model integrates different hand-crafted features and is enriched by sequential and semantic patterns generated by different state-of-the-art deep neural network models. Initial experimental results of the proposed deep ensemble model on our code-switched data reveal that our approach yields state-of-the-art results, i.e., 0.93 in terms of macro-averaged F1 score. The dataset and codes of the present study will be made publicly available on the paper's companion repository [https://github.com/95sayanta/COVID-19-and-Cyberbullying].

Machine Learning-Mediated Ultrasensitive Detection of Citrinin and Associated Mycotoxins in Real Food Samples Discerned from a Photoluminescent Carbon Dot Barcode Array.

Economically viable remote sensing of foodborne contaminants using minimalistic chemical reagents and simultaneous automation calls for a concrete integration of a chemical detection strategy with artificial intelligence. In a first of its kind, we report the ultrasensitive detection of citrinin and associated mycotoxins like aflatoxin B1 and ochratoxin A using an Alizarin Red S (ARS) and cystamine-derived carbon dot (CD) that aptly amalgamate with machine learning algorithms for automation. The photoluminescence response of the CD as a function of various solvents and pH is used to generate array channels that are further modulated in the presence of the mycotoxins whose digital images were acquired to determine pixelation, essentially creating a barcode. The barcode was fed to machine learning algorithms that actualize and intertwine convoluted databases, demonstrating Extreme Gradient Boosting (XGBoost) as the optimized model out of eight algorithms tested. Spiked samples of wheat, rice, gram, maize, coffee, and milk were used to evaluate the testing model where an exemplary accuracy of 100% even at 10 pmol of mycotoxin concentration was achieved. Most importantly, the coexistence of mycotoxins could also be detected through the CD array and XGBoost synergy hinting toward a broader scope of the developed methodology for smart detection of foodborne contaminants.

Proposal of SVM Utility Kernel for Breast Cancer Survival Estimation.

The advancement of medical research in the field of cancer prognosis and diagnosis using various modalities has put oncologists under tremendous stress. The complexity and heterogeneity involved in multiple modalities and their significantly varied clinical outcomes make it difficult to analyze the disease and provide the correct treatment. Breast cancer is the major concern among all cancers worldwide, specifically for females. To help oncologists and cancer patients, research for breast cancer survival estimation has been proposed. It ranges from complex deep neural networks to simple and interpretable architectures. We propose a utility kernel for a support vector machine (SVM) in this article. It is a simple yet powerful function, which performs better than other popular machine learning algorithms and deep neural networks in the task of breast cancer survival prediction using the TCGA-BRCA dataset. This study validates the proposed utility kernel using four different modalities (gene expression, copy number variation, clinical, and histopathological tissue images) and their multi-modal combinations. The SVM based on our utility kernel empirically proves its efficacy by achieving the highest value on various performance measures, whereas advanced deep neural networks fail to train on small and highly imbalanced breast cancer data.

Breast cancer survival prognosis using the graph convolutional network with Choquet fuzzy integral.

Breast cancer is the most prevalent kind of cancer among women and there is a need for a reliable algorithm to predict its prognosis. Previous studies focused on using gene expression data to build predictive models. However, recent advancements have made multi-omics cancer data sets (gene expression, copy number alteration, etc.) accessible. This has acted as the motivation for the creation of a novel model that utilizes a graph convolutional network (GCN) and Choquet fuzzy ensemble, incorporating multi-omics and clinical data retrieved from the publicly available METABRIC Database. In this study, graphs have been used to extract structural information, and a Choquet Fuzzy Ensemble with Logistic Regression, Random Forest, and Support Vector Machine as base classifiers has been employed to classify breast cancer patients as short-term or long-term survivors. The model has been run using all possible combinations of gene expression, copy number alteration, and clinical modality, and the results have been reported. Furthermore, a comparison has been made between the obtained results and different baseline models and state-of-the-art to demonstrate the efficacy of the proposed model in terms of different metrics. The results of this model based on Accuracy, Matthews correlation coefficient, Precision, Sensitivity, Specificity, Balanced Accuracy, and F1-Measure are 0.820, 0.528, 0.630, 0.666, 0.871, 0.769, and 0.647, respectively.

Improving the robustness and stability of a machine learning model for breast cancer prognosis through the use of multi-modal classifiers.

Breast cancer is a deadly disease with a high mortality rate among PAN cancers. The advancements in biomedical information retrieval techniques have been beneficial in developing early prognosis and diagnosis systems for cancer patients. These systems provide the oncologist with plenty of information from several modalities to make the correct and feasible treatment plan for breast cancer patients and protect them from unnecessary therapies and their toxic side effects. The cancer patient's related information can be collected using various modalities like clinical, copy number variation, DNA-methylation, microRNA sequencing, gene expression, and histopathological whole slide images. High dimensionality and heterogeneity in these modalities demand the development of some intelligent systems to understand related features to the prognosis and diagnosis of diseases and make correct predictions. In this work, we have studied some end-to-end systems having two main components : (a) dimensionality reduction techniques applied to original features from different modalities and (b) classification techniques applied to the fusion of reduced feature vectors from different modalities for automatic predictions of breast cancer patients into two categories: short-time and long-time survivors. Principal component analysis (PCA) and variational auto-encoders (VAEs) are used as the dimensionality reduction techniques, followed by support vector machines (SVM) or random forest as the machine learning classifiers. The study utilizes raw, PCA, and VAE extracted features of the TCGA-BRCA dataset from six different modalities as input to the machine learning classifiers. We conclude this study by suggesting that adding more modalities to the classifiers provides complementary information to the classifier and increases the stability and robustness of the classifiers. In this study, the multimodal classifiers have not been validated on primary data prospectively.

Assessment of Driver's Stress using Multimodal Biosignals and Regularized Deep Kernel Learning.

In this work, we classify the stress state of car drivers using multimodal physiological signals and regularized deep kernel learning. Using a driving simulator in a controlled environment, we acquire electrocardiography (ECG), electrodermal activity (EDA), photoplethysmography (PPG), and respiration rate (RESP) from N = 10 healthy drivers in experiments of 25min duration with different stress states (5min resting, 10min driving, 10min driving + answering cognitive questions). We manually remove unusable segments and approximately 4h of data remain. Multimodal time and frequency features are extracted and employed to regularized deep kernel machine learning based on a fusion framework. Task-specific representations of different physiological signals are combined using intermediate fusion. Subsequently, the fused multimodal features are fed a support vector machine (SVM) and a random forest (RF) for stress classification. The experimental results show that the proposed approach can discriminate between stress states. The combination of PPG and ECG using RF as classifier yields the highest F1-score of 0.97 in the test set. PPG only and RF yield a maximum F1-score of 0.90. Furthermore, subject-specific cross-validation improves performance. ECG and PPG signals are reliable in classifying the stress state of a car driver. In summary, the proposed framework could be extended to real-time stress state assessment in driving conditions.

Reinforcing personalized persuasion in task-oriented virtual sales assistant.

PURPOSE: Existing task-oriented virtual agents can assist users with simple tasks like ticket booking, hotel reservations, etc. effectively and with high confidence. These virtual assistants, however, assume specific, predictable end-user behavior, such as predefined/servable objectives, which results in conversation failures in challenging situations, such as when goals are unavailable. METHODOLOGY: Inspired by the practice and its efficacy, we propose an end-to-end framework for task-oriented persuasive dialogue generation that combines pre-training and reinforcement learning for generating context-aware persuasive responses. We utilize four novel rewards to improve consistency and repetitiveness in generated responses. Additionally, a meta-learning strategy has also been utilized to make the model parameters better for domain adaptation. Furthermore, we also curate a personalized persuasive dialogue (PPD) corpus, which contains utterance-level intent, slot, sentiment, and persuasion strategy annotation. FINDINGS: The obtained results and detailed analysis firmly establish the effectiveness of the proposed persuasive virtual assistant over traditional task-oriented virtual assistants. The proposed framework considerably increases the quality of dialogue generation in terms of consistency and repetitiveness. Additionally, our experiment with a few shot and zero-shot settings proves that our meta-learned model learns to quickly adopt new domains with a few or even zero no. of training epochs. It outperforms the non-meta-learning-based approaches keeping the base model constant. ORIGINALITY: To the best of our knowledge, this is the first effort to improve a task-oriented virtual agent's persuasiveness and domain adaptation.

Multi-Modal Classification for Human Breast Cancer Prognosis Prediction: Proposal of Deep-Learning Based Stacked Ensemble Model.

Breast Cancer is a highly aggressive type of cancer generally formed in the cells of the breast. Despite significant advances in the treatment of primary breast cancer in the last decade, there is a dire need to attempt of an accurate predictive model for breast cancer prognosis prediction. Researchers from various disciplines are working together to develop methods to save people from this fatal disease. A good predictive model can help in correct prognosis prediction of breast cancer. This accurate prediction can have several benefits like detection of cancer in the early stage, spare patients from getting unnecessary treatment and medical expenses related to it. Previous works rely mostly on uni-modal data (selected gene expression)for predictive model design. In recent years, however, multi-modal cancer data sets have become available (gene expression, copy number alteration and clinical). Motivated by the enhancement of deep-learning based models, in the current study, we propose to use some deep-learning based predictive models in a stacked ensemble framework to improve the prognosis prediction of breast cancer from available multi-modal data sets. One of the unique advantages of the proposed approach lies in the architecture of the model. It is a two-stage model. Stage one uses a convolutional neural network for feature extraction, while stage two uses the extracted features as input to the stack-based ensemble model. The predictive performance evaluated using different performance measures shows that this model produces better result than already existing approaches. This model results in AUC value of 0.93 and accuracy of 90.2 percent at medium stringency level (Specificity = 95 percent and threshold = 0.45). Keras 2.2.1, along with Tensorflow 1.12, is used for implementing the source code of the model. The source code can be downloaded from Github: https://github.com/nikhilaryan92/BreastCancer.

Generative Incomplete Multi-View Prognosis Predictor for Breast Cancer: GIMPP.

In today's digital world, we are equipped with modern computer-based data collection sources and feature extraction methods. It enhances the availability of the multi-view data and corresponding researches. Multi-view prediction models form a mainstream research direction in the healthcare and bioinformatics domain. While these models are designed with the assumption that there is no missing data for any views, in the real world, certain views of the data are often not having the same number of samples, resulting in the incomplete multi-view dataset. The studies performed over these datasets are termed incomplete multi-view clustering or prediction. Here, we develop a two-stage generative incomplete multi-view prediction model named GIMPP to address the missing view problem of breast cancer prognosis prediction by explicitly generating the missing data. The first stage incorporates the multi-view encoder networks and the bi-modal attention scheme to learn common latent space representations by leveraging complementary knowledge between different views. The second stage generates missing view data using view-specific generative adversarial networks conditioned on the shared representations and encoded features given by other views. Experimental results on TCGA-BRCA and METABRIC datasets proves the usefulness of the developed method over the state-of-the-art methods.