Mutation-based clustering and classification analysis reveals distinctive age groups and age-related biomarkers for glioma

Explainable Machine Learning Models for Brain Diseases: Insights from a Systematic Review

In recent years, Artificial Intelligence (AI) methods, specifically Machine Learning (ML) models, have been providing outstanding results in different areas of knowledge, with the health area being one of its most impactful fields of application. However, to be applied reliably, these models must provide users with clear, simple, and transparent explanations about the medical decision-making process. This systematic review aims to investigate the use and application of explainability in ML models used in brain disease studies. A systematic search was conducted in three major bibliographic databases, Web of Science, Scopus, and PubMed, from January 2014 to December 2023. A total of 133 relevant studies were identified and analyzed out of a total of 682 found in the initial search, in which the explainability of ML models in the medical context was studied, identifying 11 ML models and 12 explainability techniques applied in the study of 20 brain diseases.

Molecular Determinants of Neurocognitive Deficits in Glioma: Based on 2021 WHO Classification

Cognitive impairment is a common feature among patients with diffuse glioma. The objective of the study is to investigate the relationship between preoperative cognitive function and clinical as well as molecular factors, firstly based on the new 2021 World Health Organization's updated classification of central nervous system tumors. A total of 110 diffuse glioma patients enrolled underwent preoperative cognitive assessments using the Mini-Mental State Examination and Montreal Cognitive Assessment. Clinical information was collected from medical records, and gene sequencing was performed to analyze the 18 most influenced genes. The differences in cognitive function between patients with and without glioblastoma were compared under both the 2016 and 2021 WHO classification of tumors of the central nervous system to assess their effect of differentiation on cognition. The study found that age, tumor location, and glioblastoma had significant differences in cognitive function. Several genetic alterations were significantly correlated with cognition. Especially, IDH, CIC, and ATRX are positively correlated with several cognitive domains, while most other genes are negatively correlated. For most focused genes, patients with a low number of genetic alterations tended to have better cognitive function. Our study suggested that, in addition to clinical characteristics such as age, histological type, and tumor location, molecular characteristics play a crucial role in cognitive function. Further research into the mechanisms by which tumors affect brain function is expected to enhance the quality of life for glioma patients. This study highlights the importance of considering both clinical and molecular factors in the management of glioma patients to improve cognitive outcomes.

Unlocking biomedical data sharing: A structured approach with digital twins and artificial intelligence (AI) for open health sciences

Objective

Data sharing promotes the scientific progress. However, not all data can be shared freely due to privacy issues. This work is intended to foster FAIR sharing of sensitive data exemplary in the biomedical domain, via an integrated computational approach for utilizing and enriching individual datasets by scientists without coding experience.

Methods

We present an in silico pipeline for openly sharing controlled materials by generating synthetic data. Additionally, it addresses the issue of inexperience to computational methods in a non-IT-affine domain by making use of a cyberinfrastructure that runs and enables sharing of computational notebooks without the need of local software installation. The use of a digital twin based on cancer datasets serves as exemplary use case for making biomedical data openly available. Quantitative and qualitative validation of model output as well as a study on user experience are conducted.

Results

The metadata approach describes generalizable descriptors for computational models, and outlines how to profit from existing data resources for validating computational models. The use of a virtual lab book cooperatively developed using a cloud-based data management and analysis system functions as showcase enabling easy interaction between users. Qualitative testing revealed a necessity for comprehensive guidelines furthering acceptance by various users.

Conclusion

The introduced framework presents an integrated approach for data generation and interpolating incomplete data, promoting Open Science through reproducibility of results and methods. The system can be expanded from the biomedical to any other domain while future studies integrating an enhanced graphical user interface could increase interdisciplinary applicability.

The underuse of AI in the health sector: Opportunity costs, success stories, risks and recommendations

Purpose

This contribution explores the underuse of artificial intelligence (AI) in the health sector, what this means for practice, and how much the underuse can cost. Attention is drawn to the relevance of an issue that the European Parliament has outlined as a "major threat" in 2020. At its heart is the risk that research and development on trusted AI systems for medicine and digital health will pile up in lab centers without generating further practical relevance. Our analysis highlights why researchers, practitioners and especially policymakers, should pay attention to this phenomenon.

Methods

The paper examines the ways in which governments and public agencies are addressing the underuse of AI. As governments and international organizations often acknowledge the limitations of their own initiatives, the contribution explores the causes of the current issues and suggests ways to improve initiatives for digital health.

Results

Recommendations address the development of standards, models of regulatory governance, assessment of the opportunity costs of underuse of technology, and the urgency of the problem.

Conclusions

The exponential pace of AI advances and innovations makes the risks of underuse of AI increasingly threatening.

Graphical Abstract

Prognostic Indicators for H3K27M-Mutant Diffuse Midline Glioma: A Population-Based Retrospective Surveillance, Epidemiology, and End Results Database Analysis

BACKGROUND

Diffuse midline glioma with histone H3K27M mutation (H3K27M DMG) is a recently recognized World Health Organization grade IV glioma with a dismal prognosis. Despite maximal treatment, this high-grade glioma exhibits an estimated median survival of 9-12 months. However, little is known with regards to prognostic risk factors for overall survival (OS) for patients with this malignant tumor. The aim of the present study is to characterize risk factors influencing survival in H3K27M DMG.

METHODS

This is a population-based retrospective study of survival in patients with H3K27M DMG. The Surveillance, Epidemiology, and End Results database was examined from the years 2018 to 2019 and data from 137 patients were collected. Basic demographics, tumor site, and treatments regimens were retrieved. Univariate and multivariable analyses were conducted to assess for factors associated with OS. Nomograms were built based on the results of the multivariable analyses.

RESULTS

Median OS of the entire cohort was 13 months. Patients with infratentorial H3K27M DMG exhibited worse OS compared to their supratentorial counterparts. Any form of radiation treatment resulted in a significantly improved OS. Most combination treatments significantly improved OS with the exception of the surgery plus chemotherapy group. The combination of surgery and radiation had the greatest impact on OS.

CONCLUSIONS

Overall, the infratentorial location of H3K27M DMG portends a worse prognosis compared to their supratentorial counterparts. The combination of surgery and radiation had the greatest impact on OS. These data highlight the survival benefit in utilizing a multimodal treatment approach for H3K27M DMG.

A Risk Signature Consisting of Eight m6A Methylation Regulators Predicts the Prognosis of Glioma

Glioma progression seriously correlates to the epigenetic context. This study aims to identify glioma subtypes by clustering analysis of patients using the multi-omics data of N6-methyladenosine (m6A) methylation regulators and to construct a risk signature for investigating the role of m6A methylation regulators in the prognosis of glioma. Multi-omics data of glioma and normal control tissues were obtained through The Cancer Genome Atlas (TCGA) database. The clustering analysis of multi-omics data of patients was conducted using the R package iClusterPlus software. The risk model was constructed by univariate and multivariate Cox analysis, and the glioma expression data and related clinical data were obtained by Chinese Glioma Genome Atlas (CGGA) datasets to verify the risk model. By analyzing the glioma data in TCGA, we found that the risk signature could be constructed according to the eight genes with m6A methylation modification function, including ALKBH5, HNRNPA2B1, IGF2BP2, IGF2BP3, RBM15, WTAP, YTHDF1, and YTHDF2. Meanwhile, we found that IGF2BP2 and IGF2BP3 were highly expressed in glioma subtypes with high-risk scores and closely related to the prognosis of glioma patients. m6A methylation regulators, especially IGF2BP2 and IGF2BP3, play important roles in the malignant progression of glioma. The risk signature constructed by eight m6A methylation regulators can predict the prognosis of glioma. IGF2BP2 and IGF2BP3 may be the key regulatory factors of m6A methylation regulators involved in the occurrence and development of glioma, and can serve as molecular markers for the prognosis of glioma.

An update on the molecular biology of glioblastoma, with clinical implications and progress in its treatment

Glioblastoma multiforme (GBM) is the most aggressive and common malignant primary brain tumor. Patients with GBM often have poor prognoses, with a median survival of ∼15 months. Enhanced understanding of the molecular biology of central nervous system tumors has led to modifications in their classifications, the most recent of which classified these tumors into new categories and made some changes in their nomenclature and grading system. This review aims to give a panoramic view of the last 3 years' findings in glioblastoma characterization, its heterogeneity, and current advances in its treatment. Several molecular parameters have been used to achieve an accurate and personalized characterization of glioblastoma in patients, including epigenetic, genetic, transcriptomic and metabolic features, as well as age- and sex-related patterns and the involvement of several noncoding RNAs in glioblastoma progression. Astrocyte-like neural stem cells and outer radial glial-like cells from the subventricular zone have been proposed as agents involved in GBM of IDH-wildtype origin, but this remains controversial. Glioblastoma metabolism is characterized by upregulation of the PI3K/Akt/mTOR signaling pathway, promotion of the glycolytic flux, maintenance of lipid storage, and other features. This metabolism also contributes to glioblastoma's resistance to conventional therapies. Tumor heterogeneity, a hallmark of GBM, has been shown to affect the genetic expression, modulation of metabolic pathways, and immune system evasion. GBM's aggressive invasion potential is modulated by cell-to-cell crosstalk within the tumor microenvironment and altered expressions of specific genes, such as ANXA2, GBP2, FN1, PHIP, and GLUT3. Nevertheless, the rising number of active clinical trials illustrates the efforts to identify new targets and drugs to treat this malignancy. Immunotherapy is still relevant for research purposes, given the amount of ongoing clinical trials based on this strategy to treat GBM, and neoantigen and nucleic acid-based vaccines are gaining importance due to their antitumoral activity by inducing the immune response. Furthermore, there are clinical trials focused on the PI3K/Akt/mTOR axis, angiogenesis, and tumor heterogeneity for developing molecular-targeted therapies against GBM. Other strategies, such as nanodelivery and computational models, may improve the drug pharmacokinetics and the prognosis of patients with GBM.

Machine learning analysis of TCGA cancer data

In recent years, machine learning (ML) researchers have changed their focus towards biological problems that are difficult to analyse with standard approaches. Large initiatives such as The Cancer Genome Atlas (TCGA) have allowed the use of omic data for the training of these algorithms. In order to study the state of the art, this review is provided to cover the main works that have used ML with TCGA data. Firstly, the principal discoveries made by the TCGA consortium are presented. Once these bases have been established, we begin with the main objective of this study, the identification and discussion of those works that have used the TCGA data for the training of different ML approaches. After a review of more than 100 different papers, it has been possible to make a classification according to following three pillars: the type of tumour, the type of algorithm and the predicted biological problem. One of the conclusions drawn in this work shows a high density of studies based on two major algorithms: Random Forest and Support Vector Machines. We also observe the rise in the use of deep artificial neural networks. It is worth emphasizing, the increase of integrative models of multi-omic data analysis. The different biological conditions are a consequence of molecular homeostasis, driven by both protein coding regions, regulatory elements and the surrounding environment. It is notable that a large number of works make use of genetic expression data, which has been found to be the preferred method by researchers when training the different models. The biological problems addressed have been classified into five types: prognosis prediction, tumour subtypes, microsatellite instability (MSI), immunological aspects and certain pathways of interest. A clear trend was detected in the prediction of these conditions according to the type of tumour. That is the reason for which a greater number of works have focused on the BRCA cohort, while specific works for survival, for example, were centred on the GBM cohort, due to its large number of events. Throughout this review, it will be possible to go in depth into the works and the methodologies used to study TCGA cancer data. Finally, it is intended that this work will serve as a basis for future research in this field of study.

Transcriptomic Landscape of Lower Grade Glioma Based on Age-Related Non-Silent Somatic Mutations

Glioma accounts for 80% of all malignant brain tumours and is the most common adult primary brain tumour. Age is an important factor affecting the development of cancer, as somatic mutations accumulate with age. Here, we aimed to analyse the significance of age-dependent non-silent somatic mutations in glioma prognosis. Histological tumour grade depends on age at diagnosis in patients with IDH1, TP53, ATRX, and EGFR mutations. Age of patients with wild-type IDH1 and EGFR increased with increase in tumour grade, while the age of patients with IDH1 or EGFR mutation remained constant. However, the age of patients with EGFR mutation was higher than that of patients with IDH1 mutation. The hierarchical clustering of patients was dominantly separated by IDH1 and EGFR mutations. Furthermore, patients with IDH1 mutation were dominantly separated by TP53 and ATRX double mutation and its double wild-type counterpart. The age of patients with ATRX and TP53 mutation was lower than that of patients with wild-type ATRX and TP53. Patients with the double mutation showed poorer prognosis than those with the double wild type genotype. Unlike IDH1 mutant, IDH1 wild-type showed upregulation of expression of epithelial mesenchymal transition associated genes.