A Study on the Robustness and Stability of Explainable Deep Learning in an Imbalanced Setting: The Exploration of the Conformational Space of G Protein-Coupled Receptors.

G-protein coupled receptors (GPCRs) are transmembrane proteins that transmit signals from the extracellular environment to the inside of the cells. Their ability to adopt various conformational states, which influence their function, makes them crucial in pharmacoproteomic studies. While many drugs target specific GPCR states to exert their effects-thereby regulating the protein's activity-unraveling the activation pathway remains challenging due to the multitude of intermediate transformations occurring throughout this process, and intrinsically influencing the dynamics of the receptors. In this context, computational modeling, particularly molecular dynamics (MD) simulations, may offer valuable insights into the dynamics and energetics of GPCR transformations, especially when combined with machine learning (ML) methods and techniques for achieving model interpretability for knowledge generation. The current study builds upon previous work in which the layer relevance propagation (LRP) technique was employed to interpret the predictions in a multi-class classification problem concerning the conformational states of the ß2-adrenergic (ß2AR) receptor from MD simulations. Here, we address the challenges posed by class imbalance and extend previous analyses by evaluating the robustness and stability of deep learning (DL)-based predictions under different imbalance mitigation techniques. By meticulously evaluating explainability and imbalance strategies, we aim to produce reliable and robust insights.

Early pseudoprogression and progression lesions in glioblastoma patients are both metabolically heterogeneous.

The standard treatment in glioblastoma includes maximal safe resection followed by concomitant radiotherapy plus chemotherapy and adjuvant temozolomide. The first follow-up study to evaluate treatment response is performed 1 month after concomitant treatment, when contrast-enhancing regions may appear that can correspond to true progression or pseudoprogression. We retrospectively evaluated 31 consecutive patients at the first follow-up after concomitant treatment to check whether the metabolic pattern assessed with multivoxel MRS was predictive of treatment response 2 months later. We extracted the underlying metabolic patterns of the contrast-enhancing regions with a blind-source separation method and mapped them over the reference images. Pattern heterogeneity was calculated using entropy, and association between patterns and outcomes was measured with Cramér's V. We identified three distinct metabolic patterns-proliferative, necrotic, and responsive, which were associated with status 2 months later. Individually, 70% of the patients showed metabolically heterogeneous patterns in the contrast-enhancing regions. Metabolic heterogeneity was not related to the regions' size and only stable patients were less heterogeneous than the rest. Contrast-enhancing regions are also metabolically heterogeneous 1 month after concomitant treatment. This could explain the reported difficulty in finding robust pseudoprogression biomarkers.

Advances in the Use of Deep Learning for the Analysis of Magnetic Resonance Image in Neuro-Oncology.

Machine Learning is entering a phase of maturity, but its medical applications still lag behind in terms of practical use. The field of oncological radiology (and neuro-oncology in particular) is at the forefront of these developments, now boosted by the success of Deep-Learning methods for the analysis of medical images. This paper reviews in detail some of the most recent advances in the use of Deep Learning in this field, from the broader topic of the development of Machine-Learning-based analytical pipelines to specific instantiations of the use of Deep Learning in neuro-oncology; the latter including its use in the groundbreaking field of ultra-low field magnetic resonance imaging.

Is Generative Artificial Intelligence the Next Step Toward a Personalized Hemodialysis?

ABSTRACT Artificial intelligence (AI) generative models driven by the integration of AI and natural language processing technologies, such as OpenAI's chatbot generative pre-trained transformer large language model (LLM), are receiving much public attention and have the potential to transform personalized medicine. Dialysis patients are highly dependent on technology and their treatment generates a challenging large volume of data that has to be analyzed for knowledge extraction. We argue that, by integrating the data acquired from hemodialysis treatments with the powerful conversational capabilities of LLMs, nephrologists could personalize treatments adapted to patients' lifestyles and preferences. We also argue that this new conversational AI integrated with a personalized patient-computer interface will enhance patients' engagement and self-care by providing them with a more personalized experience. However, generative AI models require continuous and accurate updates of data, and expert supervision and must address potential biases and limitations. Dialysis patients can also benefit from other new emerging technologies such as Digital Twins with which patients' care can also be addressed from a personalized medicine perspective. In this paper, we will revise LLMs potential strengths in terms of their contribution to personalized medicine, and, in particular, their potential impact, and limitations in nephrology. Nephrologists' collaboration with AI academia and companies, to develop algorithms and models that are more transparent, understandable, and trustworthy, will be crucial for the next generation of dialysis patients. The combination of technology, patient-specific data, and AI should contribute to create a more personalized and interactive dialysis process, improving patients' quality of life.

GPCR molecular dynamics forecasting using recurrent neural networks.

G protein-coupled receptors (GPCRs) are a large superfamily of cell membrane proteins that play an important physiological role as transmitters of extracellular signals. Signal transmission through the cell membrane depends on conformational changes in the transmembrane region of the receptor, which makes the investigation of the dynamics in these regions particularly relevant. Molecular dynamics (MD) simulations provide a wealth of data about the structure, dynamics, and physiological function of biological macromolecules by modelling the interactions between their atomic constituents. In this study, a Recurrent and Convolutional Neural Network (RNN) model, namely Long Short-Term Memory (LSTM), is used to predict the dynamics of two GPCR states and three specific simulations of each one, through their activation path and focussing on specific receptor regions. Active and inactive states of the GPCRs are analysed in six scenarios involving APO, Full Agonist (BI 167107) and Partial Inverse Agonist (carazolol) of the receptor. Four Machine Learning models with increasing complexity in terms of neural network architecture are evaluated, and their results discussed. The best method achieves an overall RMSD lower than 0.139 Å and the transmembrane helices are the regions showing the minimum prediction errors and minimum relative movements of the protein.

Is generative artificial intelligence the next step toward a personalized hemodialysis?

Artificial intelligence (AI) generative models driven by the integration of AI and natural language processing technologies, such as OpenAI's chatbot generative pre-trained transformer large language model (LLM), are receiving much public attention and have the potential to transform personalized medicine. Dialysis patients are highly dependent on technology and their treatment generates a challenging large volume of data that has to be analyzed for knowledge extraction. We argue that, by integrating the data acquired from hemodialysis treatments with the powerful conversational capabilities of LLMs, nephrologists could personalize treatments adapted to patients' lifestyles and preferences. We also argue that this new conversational AI integrated with a personalized patient-computer interface will enhance patients' engagement and self-care by providing them with a more personalized experience. However, generative AI models require continuous and accurate updates of data, and expert supervision and must address potential biases and limitations. Dialysis patients can also benefit from other new emerging technologies such as Digital Twins with which patients' care can also be addressed from a personalized medicine perspective. In this paper, we will revise LLMs potential strengths in terms of their contribution to personalized medicine, and, in particular, their potential impact, and limitations in nephrology. Nephrologists' collaboration with AI academia and companies, to develop algorithms and models that are more transparent, understandable, and trustworthy, will be crucial for the next generation of dialysis patients. The combination of technology, patient-specific data, and AI should contribute to create a more personalized and interactive dialysis process, improving patients' quality of life.

A comparison of non-negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors.

Magnetic resonance spectroscopy (MRS) is an MR technique that provides information about the biochemistry of tissues in a noninvasive way. MRS has been widely used for the study of brain tumors, both preoperatively and during follow-up. In this study, we investigated the performance of a range of variants of unsupervised matrix factorization methods of the non-negative matrix underapproximation (NMU) family, namely, sparse NMU, global NMU, and recursive NMU, and compared them with convex non-negative matrix factorization (C-NMF), which has previously shown a good performance on brain tumor diagnostic support problems using MRS data. The purpose of the investigation was 2-fold: first, to ascertain the differences among the sources extracted by these methods; and second, to compare the influence of each method in the diagnostic accuracy of the classification of brain tumors, using them as feature extractors. We discovered that, first, NMU variants found meaningful sources in terms of biological interpretability, but representing parts of the spectrum, in contrast to C-NMF; and second, that NMU methods achieved better classification accuracy than C-NMF for the classification tasks when one class was not meningioma.

Using Single-Voxel Magnetic Resonance Spectroscopy Data Acquired at 1.5T to Classify Multivoxel Data at 3T: A Proof-of-Concept Study.

In vivo magnetic resonance spectroscopy (MRS) has two modalities, single-voxel (SV) and multivoxel (MV), in which one or more contiguous grids of SVs are acquired. PURPOSE: To test whether MV grids can be classified with models trained with SV. METHODS: Retrospective study. Training dataset: Multicenter multiformat SV INTERPRET, 1.5T. Testing dataset: MV eTumour, 3T. Two classification tasks were completed: 3-class (meningioma vs. aggressive vs. normal) and 4-class (meningioma vs. low-grade glioma vs. aggressive vs. normal). Five different methods were tested for feature selection. The classification was implemented using linear discriminant analysis (LDA), random forest, and support vector machines. The evaluation was completed with balanced error rate (BER) and area under the curve (AUC) on both sets. The accuracy in class prediction was calculated by developing a solid tumor index (STI) and segmentation accuracy with the Dice score. RESULTS: The best method was sequential forward feature selection combined with LDA, with AUCs = 0.95 (meningioma), 0.89 (aggressive), 0.82 (low-grade glioma), and 0.82 (normal). STI was 66% (4-class task) and 71% (3-class task) because two cases failed completely and two more had suboptimal STI as defined by us. DISCUSSION: The reasons for failure in the classification of the MV test set were related to the presence of artifacts.

AI-Based Glioma Grading for a Trustworthy Diagnosis: An Analytical Pipeline for Improved Reliability.

Glioma is the most common type of tumor in humans originating in the brain. According to the World Health Organization, gliomas can be graded on a four-stage scale, ranging from the most benign to the most malignant. The grading of these tumors from image information is a far from trivial task for radiologists and one in which they could be assisted by machine-learning-based decision support. However, the machine learning analytical pipeline is also fraught with perils stemming from different sources, such as inadvertent data leakage, adequacy of 2D image sampling, or classifier assessment biases. In this paper, we analyze a glioma database sourced from multiple datasets using a simple classifier, aiming to obtain a reliable tumor grading and, on the way, we provide a few guidelines to ensure such reliability. Our results reveal that by focusing on the tumor region of interest and using data augmentation techniques we significantly enhanced the accuracy and confidence in tumor classifications. Evaluation on an independent test set resulted in an AUC-ROC of 0.932 in the discrimination of low-grade gliomas from high-grade gliomas, and an AUC-ROC of 0.893 in the classification of grades 2, 3, and 4. The study also highlights the importance of providing, beyond generic classification performance, measures of how reliable and trustworthy the model's output is, thus assessing the model's certainty and robustness.

Layer-Wise Relevance Analysis for Motif Recognition in the Activation Pathway of the ß2-Adrenergic GPCR Receptor.

G-protein-coupled receptors (GPCRs) are cell membrane proteins of relevance as therapeutic targets, and are associated to the development of treatments for illnesses such as diabetes, Alzheimer's, or even cancer. Therefore, comprehending the underlying mechanisms of the receptor functional properties is of particular interest in pharmacoproteomics and in disease therapy at large. Their interaction with ligands elicits multiple molecular rearrangements all along their structure, inducing activation pathways that distinctly influence the cell response. In this work, we studied GPCR signaling pathways from molecular dynamics simulations as they provide rich information about the dynamic nature of the receptors. We focused on studying the molecular properties of the receptors using deep-learning-based methods. In particular, we designed and trained a one-dimensional convolution neural network and illustrated its use in a classification of conformational states: active, intermediate, or inactive, of the ß2-adrenergic receptor when bound to the full agonist BI-167107. Through a novel explainability-oriented investigation of the prediction results, we were able to identify and assess the contribution of individual motifs (residues) influencing a particular activation pathway. Consequently, we contribute a methodology that assists in the elucidation of the underlying mechanisms of receptor activation-deactivation.

Radiomics-Based Assessment of OCT Angiography Images for Diabetic Retinopathy Diagnosis.

Purpose: To evaluate the diagnostic accuracy of machine learning (ML) techniques applied to radiomic features extracted from OCT and OCT angiography (OCTA) images for diabetes mellitus (DM), diabetic retinopathy (DR), and referable DR (R-DR) diagnosis. Design: Cross-sectional analysis of a retinal image dataset from a previous prospective OCTA study (ClinicalTrials.govNCT03422965). Participants: Patients with type 1 DM and controls included in the progenitor study. Methods: Radiomic features were extracted from fundus retinographies, OCT, and OCTA images in each study eye. Logistic regression, linear discriminant analysis, support vector classifier (SVC)-linear, SVC-radial basis function, and random forest models were created to evaluate their diagnostic accuracy for DM, DR, and R-DR diagnosis in all image types. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC) mean and standard deviation for each ML model and each individual and combined image types. Results: A dataset of 726 eyes (439 individuals) were included. For DM diagnosis, the greatest AUC was observed for OCT (0.82, 0.03). For DR detection, the greatest AUC was observed for OCTA (0.77, 0.03), especially in the 3 × 3 mm superficial capillary plexus OCTA scan (0.76, 0.04). For R-DR diagnosis, the greatest AUC was observed for OCTA (0.87, 0.12) and the deep capillary plexus OCTA scan (0.86, 0.08). The addition of clinical variables (age, sex, etc.) improved most models AUC for DM, DR and R-DR diagnosis. The performance of the models was similar in unilateral and bilateral eyes image datasets. Conclusions: Radiomics extracted from OCT and OCTA images allow identification of patients with DM, DR, and R-DR using standard ML classifiers. OCT was the best test for DM diagnosis, OCTA for DR and R-DR diagnosis and the addition of clinical variables improved most models. This pioneer study demonstrates that radiomics-based ML techniques applied to OCT and OCTA images may be an option for DR screening in patients with type 1 DM. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Extraction of artefactual MRS patterns from a large database using non-negative matrix factorization.

Despite the success of automated pattern recognition methods in problems of human brain tumor diagnostic classification, limited attention has been paid to the issue of automated data quality assessment in the field of MRS for neuro-oncology. Beyond some early attempts to address this issue, the current standard in practice is MRS quality control through human (expert-based) assessment. One aspect of automatic quality control is the problem of detecting artefacts in MRS data. Artefacts, whose variety has already been reviewed in some detail and some of which may even escape human quality control, have a negative influence in pattern recognition methods attempting to assist tumor characterization. The automatic detection of MRS artefacts should be beneficial for radiology as it guarantees more reliable tumor characterizations, as well as the development of more robust pattern recognition-based tumor classifiers and more trustable MRS data processing and analysis pipelines. Feature extraction methods have previously been used to help distinguishing between good and bad quality spectra to apply subsequent supervised pattern recognition techniques. In this study, we apply feature extraction differently and use a variant of a method for blind source separation, namely Convex Non-Negative Matrix Factorization, to unveil MRS signal sources in a completely unsupervised way. We hypothesize that, while most sources will correspond to the different tumor patterns, some of them will reflect signal artefacts. The experimental work reported in this paper, analyzing a combined short and long echo time 1 H-MRS database of more than 2000 spectra acquired at 1.5T and corresponding to different tumor types and other anomalous masses, provides a first proof of concept that points to the possible validity of this approach.

Machine Learning for Clinical Decision-Making: Challenges and Opportunities in Cardiovascular Imaging.

The use of machine learning (ML) approaches to target clinical problems is called to revolutionize clinical decision-making in cardiology. The success of these tools is dependent on the understanding of the intrinsic processes being used during the conventional pathway by which clinicians make decisions. In a parallelism with this pathway, ML can have an impact at four levels: for data acquisition, predominantly by extracting standardized, high-quality information with the smallest possible learning curve; for feature extraction, by discharging healthcare practitioners from performing tedious measurements on raw data; for interpretation, by digesting complex, heterogeneous data in order to augment the understanding of the patient status; and for decision support, by leveraging the previous steps to predict clinical outcomes, response to treatment or to recommend a specific intervention. This paper discusses the state-of-the-art, as well as the current clinical status and challenges associated with the two later tasks of interpretation and decision support, together with the challenges related to the learning process, the auditability/traceability, the system infrastructure and the integration within clinical processes in cardiovascular imaging.

Leveraging Data Science for a Personalized Haemodialysis.

BACKGROUND: The 2019 Science for Dialysis Meeting at Bellvitge University Hospital was devoted to the challenges and opportunities posed by the use of data science to facilitate precision and personalized medicine in nephrology, and to describe new approaches and technologies. The meeting included separate sections for issues in data collection and data analysis. As part of data collection, we presented the institutional ARGOS e-health project, which provides a common model for the standardization of clinical practice. We also pay specific attention to the way in which randomized controlled trials offer data that may be critical to decision-making in the real world. The opportunities of open source software (OSS) for data science in clinical practice were also discussed. SUMMARY: Precision medicine aims to provide the right treatment for the right patients at the right time and is deeply connected to data science. Dialysis patients are highly dependent on technology to live, and their treatment generates a huge volume of data that has to be analysed. Data science has emerged as a tool to provide an integrated approach to data collection, storage, cleaning, processing, analysis, and interpretation from potentially large volumes of information. This is meant to be a perspective article about data science based on the experience of the experts invited to the Science for Dialysis Meeting and provides an up-to-date perspective of the potential of data science in kidney disease and dialysis. KEY MESSAGES: Healthcare is quickly becoming data-dependent, and data science is a discipline that holds the promise of contributing to the development of personalized medicine, although nephrology still lags behind in this process. The key idea is to ensure that data will guide medical decisions based on individual patient characteristics rather than on averages over a whole population usually based on randomized controlled trials that excluded kidney disease patients. Furthermore, there is increasing interest in obtaining data about the effectiveness of available treatments in current patient care based on pragmatic clinical trials. The use of data science in this context is becoming increasingly feasible in part thanks to the swift developments in OSS.

Unraveling response to temozolomide in preclinical GL261 glioblastoma with MRI/MRSI using radiomics and signal source extraction.

Glioblastoma is the most frequent aggressive primary brain tumor amongst human adults. Its standard treatment involves chemotherapy, for which the drug temozolomide is a common choice. These are heterogeneous and variable tumors which might benefit from personalized, data-based therapy strategies, and for which there is room for improvement in therapy response follow-up, investigated with preclinical models. This study addresses a preclinical question that involves distinguishing between treated and control (untreated) mice bearing glioblastoma, using machine learning techniques, from magnetic resonance-based data in two modalities: MRI and MRSI. It aims to go beyond the comparison of methods for such discrimination to provide an analytical pipeline that could be used in subsequent human studies. This analytical pipeline is meant to be a usable and interpretable tool for the radiology expert in the hope that such interpretation helps revealing new insights about the problem itself. For that, we propose coupling source extraction-based and radiomics-based data transformations with feature selection. Special attention is paid to the generation of radiologist-friendly visual nosological representations of the analyzed tumors.

Societal Issues Concerning the Application of Artificial Intelligence in Medicine.

BACKGROUND: Medicine is becoming an increasingly data-centred discipline and, beyond classical statistical approaches, artificial intelligence (AI) and, in particular, machine learning (ML) are attracting much interest for the analysis of medical data. It has been argued that AI is experiencing a fast process of commodification. This characterization correctly reflects the current process of industrialization of AI and its reach into society. Therefore, societal issues related to the use of AI and ML should not be ignored any longer and certainly not in the medical domain. These societal issues may take many forms, but they all entail the design of models from a human-centred perspective, incorporating human-relevant requirements and constraints. In this brief paper, we discuss a number of specific issues affecting the use of AI and ML in medicine, such as fairness, privacy and anonymity, explainability and interpretability, but also some broader societal issues, such as ethics and legislation. We reckon that all of these are relevant aspects to consider in order to achieve the objective of fostering acceptance of AI- and ML-based technologies, as well as to comply with an evolving legislation concerning the impact of digital technologies on ethically and privacy sensitive matters. Our specific goal here is to reflect on how all these topics affect medical applications of AI and ML. This paper includes some of the contents of the "2nd Meeting of Science and Dialysis: Artificial Intelligence," organized in the Bellvitge University Hospital, Barcelona, Spain. SUMMARY AND KEY MESSAGES: AI and ML are attracting much interest from the medical community as key approaches to knowledge extraction from data. These approaches are increasingly colonizing ambits of social impact, such as medicine and healthcare. Issues of social relevance with an impact on medicine and healthcare include (although they are not limited to) fairness, explainability, privacy, ethics and legislation.