XL1R-Net: Explainable AI-driven improved L1-regularized deep neural architecture for NSCLC biomarker identification.

BACKGROUND AND OBJECTIVE: Non-small cell lung cancer (NSCLC) exhibits intrinsic molecular heterogeneity, primarily driven by the mutation of specific biomarkers. Identification of these biomarkers would assist not only in distinguishing NSCLC into its major subtypes - Adenocarcinoma and Squamous Cell Carcinoma, but also in developing targeted therapy. Medical practitioners use one or more types of omic data to identify these biomarkers, copy number variation (CNV) being one such type. CNV provides a measure of genomic instability, which is considered a hallmark of carcinoma. However, the CNV data has not received much attention for biomarker identification. This paper aims to identify biomarkers for NSCLC using CNV data. METHODS: An eXplainable AI (XAI)-driven L1-regularized deep learning architecture, XL1R-Net, is proposed that introduces a novel modification of the standard L1-regularized gradient descent algorithm to arrive at an improved deep neural classifier for NSCLC subtyping. Further, XAI-based feature identification has been used to leverage the trained classifier to uncover a set of twenty NCSLC-relevant biomarkers. RESULTS: The identified biomarkers are evaluated based on their classification performance and clinical relevance. Using Multilayer Perceptron (MLP)-based model, a classification accuracy of 84.95% using 10-fold cross-validation is achieved. Moreover, the statistical significance test on the classification performance also revealed the superiority of the MLP model over the competitive machine learning models. Further, the publicly available Drug-Gene Interaction Database reveals twelve of the identified biomarkers as potentially druggable. The K-M Plotter tool was used to verify eighteen of the identified biomarkers with a high probability of predicting NSCLC patients' likelihood of survival. While nine of the identified biomarkers confirm the recent literature, five find mention in the OncoKB Gene List. CONCLUSION: A set of seven novel biomarkers that have not been reported in the literature could be investigated for their potential contribution towards NSCLC therapy. Given NSCLC's genetic diversity, using only one omics data type may not adequately capture the tumor's complexity. Multiomics data and its integration with other sources will be examined in the future to better understand NSCLC heterogeneity.

An explainable AI-driven biomarker discovery framework for Non-Small Cell Lung Cancer classification.

Non-Small Cell Lung Cancer (NSCLC) exhibits intrinsic heterogeneity at the molecular level that aids in distinguishing between its two prominent subtypes - Lung Adenocarcinoma (LUAD) and Lung Squamous Cell Carcinoma (LUSC). This paper proposes a novel explainable AI (XAI)-based deep learning framework to discover a small set of NSCLC biomarkers. The proposed framework comprises three modules - an autoencoder to shrink the input feature space, a feed-forward neural network to classify NSCLC instances into LUAD and LUSC, and a biomarker discovery module that leverages the combined network comprising the autoencoder and the feed-forward neural network. In the biomarker discovery module, XAI methods uncovered a set of 52 relevant biomarkers for NSCLC subtype classification. To evaluate the classification performance of the discovered biomarkers, multiple machine-learning models are constructed using these biomarkers. Using 10-Fold cross-validation, Multilayer Perceptron achieved an accuracy of 95.74% (±1.27) at 95% confidence interval. Further, using Drug-Gene Interaction Database, we observe that 14 of the discovered biomarkers are druggable. In addition, 28 biomarkers aid the prediction of the survivability of the patients. Out of 52 discovered biomarkers, we find that 45 biomarkers have been reported in previous studies on distinguishing between the two NSCLC subtypes. To the best of our knowledge, the remaining seven biomarkers have not yet been reported for NSCLC subtyping and could be further explored for their contribution to targeted therapy of lung cancer.

Using handpicked features in conjunction with ResNet-50 for improved detection of COVID-19 from chest X-ray images.

Coronaviruses are a family of viruses that majorly cause respiratory disorders in humans. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a new strain of coronavirus that causes the coronavirus disease 2019 (COVID-19). WHO has identified COVID-19 as a pandemic as it has spread across the globe due to its highly contagious nature. For early diagnosis of COVID-19, the reverse transcription-polymerase chain reaction (RT-PCR) test is commonly done. However, it suffers from a high false-negative rate of up to 67% if the test is done during the first five days of exposure. As an alternative, research on the efficacy of deep learning techniques employed in the identification of COVID-19 disease using chest X-ray images is intensely pursued. As pneumonia and COVID-19 exhibit similar/ overlapping symptoms and affect the human lungs, a distinction between the chest X-ray images of pneumonia patients and COVID-19 patients becomes challenging. In this work, we have modeled the COVID-19 classification problem as a multiclass classification problem involving three classes, namely COVID-19, pneumonia, and normal. We have proposed a novel classification framework which combines a set of handpicked features with those obtained from a deep convolutional neural network. The proposed framework comprises of three modules. In the first module, we exploit the strength of transfer learning using ResNet-50 for training the network on a set of preprocessed images and obtain a vector of 2048 features. In the second module, we construct a pool of frequency and texture based 252 handpicked features that are further reduced to a set of 64 features using PCA. Subsequently, these are passed to a feed forward neural network to obtain a set of 16 features. The third module concatenates the features obtained from first and second modules, and passes them to a dense layer followed by the softmax layer to yield the desired classification model. We have used chest X-ray images of COVID-19 patients from four independent publicly available repositories, in addition to images from the Mendeley and Kaggle Chest X-Ray Datasets for pneumonia and normal cases. To establish the efficacy of the proposed model, 10-fold cross-validation is carried out. The model generated an overall classification accuracy of 0.974 ± 0.02 and a sensitivity of 0.987 ± 0.05, 0.963 ± 0.05, and 0.973 ± 0.04 at 95% confidence interval for COVID-19, normal, and pneumonia classes, respectively. To ensure the effectiveness of the proposed model, it was validated using an independent Chest X-ray cohort and an overall classification accuracy of 0.979 was achieved. Comparison of the proposed framework with state-of-the-art methods reveal that the proposed framework outperforms others in terms of accuracy and sensitivity. Since interpretability of results is crucial in the medical domain, the gradient-based localizations are captured using Gradient-weighted Class Activation Mapping (Grad-CAM). In summary, the results obtained are stable over independent cohorts and interpretable using Grad-CAM localizations that serve as clinical evidence.

Clinical and bioavailability studies of sublingually administered atropine sulfate.

INTRODUCTION: The increased use of organophosphorus (OP) pesticides and the ever increasing possibility of terror groups using nerve agents underscore a need to develop effective and safe antidotes against OP poisoning. The objectives of the present study were to develop a novel atropine sulfate (AS) sublingual injection formulation, to create its bioavailability data in humans and to evaluate its suitability for field use with a view to obtain early therapeutic drug concentration in comparison to the conventional intramuscular route that provides a therapeutic peak of 6 to 8 ng/mL in blood at 30 minutes. METHODS: Two milligrams per 0.1 mL of AS was sublingually injected in 6 volunteers, and bioavailability and atropinization signs (blood pressure, pupil diameter, and heart rate) were noted. RESULTS: Human bioavailability curve was created, which was equivalent to 2 mg IM injection in amplitude within 10 minutes and describing a better curve thereafter. Peak plasma concentration of AS occurred at 15 minutes and was 21 ng/mL. Increase in heart rate became extremely significant at 5 minutes (P < .0001) with maximum increase of 62% + or - 6% at 10 minutes after administration. Pupil diameter showed maximal increase of 58% + or - 21% at 15 minutes (P < .01). CONCLUSIONS: Sublingual AS appears to have several advantages over conventional IM route including better bioavailability, rapid onset of action, and early atropinization. It is a safe and efficacious procedure with the potential to become an alternative to conventional IM injection, particularly in case of chemical terrorism scenario where hundreds of victims may require immediate atropinization simultaneously.

Development of atropine sulphate nasal drops and its pharmacokinetic and safety evaluation in healthy human volunteers.

INTRODUCTION: The increased use of organophosphate (OP) insecticides and the ever increasing possibility of terror groups using nerve agents underscore the need to develop effective and safe antidotes against OP poisoning. While intramuscular administration of nerve gas antidotes like atropine sulphate has certain lacunae, intravenous route is neither practical nor feasible in the field conditions for mass casualties. The objective was to develop a novel atropine sulphate nasal drop formulation, evaluate and characterize it using scintigraphy and to carry out safety-efficacy study in human volunteers with a view to obtain early pharmacological effects in comparison to the existing options, particularly the conventional intramuscular route. METHODS: Permeability studies were done using atropine sulphate solution containing variable amount of chitosan. Radiometric method was developed for scintigraphy studies while standard spectroscopy was used for the quantification of atropine sulphate in fluids. Concentration of atropine sulphate in nasal drops to produce therapeutic concentration in blood was calculated. Six volunteers (age range 18-53 years) were administered the formulation delivering 6mg of atropine sulphate each. Bioavailability and atropinization were noted serially. RESULTS: Based on the results of in vitro, human scintigraphy and analytical data, 1% atropine sulphate-0.5% chitosan was chosen as the final nasal formulation. Human bioavailability curve was created which showed that the therapeutic concentration of the drug in blood was reached within 5min with nasal drops suggesting that drug delivery through the nasal route is significantly better than the intramuscular route. Unpaired t-test between the means of baseline value of heart rate and that of each time interval showed that increase in heart rate of all the volunteers became significant at 15min (P<0.01) and extremely significant at 30min (P<0.001). Correlation was evident from 5min (c>0.7). Pupil diameter showed maximal increase at 30min (P<0.01). CONCLUSIONS: This novel product, 1% atropine sulphate-0.5% chitosan nasal drops might be a safe and efficacious emergency treatment of organophosphorous poisoning with several advantages over the present management, including early atropinization and capability of mass treatment in least amount of time.