Machine learning applications in cancer prognosis and prediction

Predicting breast cancer-specific survival in metaplastic breast cancer patients using machine learning algorithms

Metaplastic breast cancer (MpBC) is a rare and aggressive subtype of breast cancer, with data emerging on prognostic factors and survival prediction. This study aimed to develop machine learning models to predict breast cancer-specific survival (BCSS) in MpBC patients, utilizing a dataset of 160 patients with clinical, pathological, and biological variables. An in-depth variable selection process was carried out using gain ratio and correlation-based methods, resulting in 10 variables for model estimation. Five models (decision tree with bagging; logistic regression; multilayer perceptron; naïve Bayes; and, random forest algorithms) were evaluated using 10-fold cross-validation. Despite the constraints posed by the absence of therapeutic information, the random forest model exhibited the highest performance in predicting BCSS, with an ROC area of 0.808. This study emphasizes the potential of machine learning algorithms in predicting prognosis for complex and heterogeneous cancer subtypes using clinical datasets, and their potential to contribute to patient management. Further research that incorporates additional variables, such as treatment response, and more advanced machine learning techniques will likely enhance the predictive power of MpBC prognostic models.

AUTOSURV: INTERPRETABLE DEEP LEARNING FRAMEWORK FOR CANCER SURVIVAL ANALYSIS INCORPORATING CLINICAL AND MULTI-OMICS DATA

Accurate prognosis for cancer patients can provide critical information for optimizing treatment plans and improving life quality. Combining omics data and demographic/clinical information can offer a more comprehensive view of cancer prognosis than using omics or clinical data alone and can reveal the underlying disease mechanisms at the molecular level. In this study, we developed a novel deep learning framework to extract information from high-dimensional gene expression and miRNA expression data and conduct prognosis prediction for breast cancer and ovarian cancer patients. Our model achieved significantly better prognosis prediction than the conventional Cox Proportional Hazard model and other competitive deep learning approaches in various settings. Moreover, an interpretation approach was applied to tackle the "black-box" nature of deep neural networks and we identified features (i.e., genes, miRNA, demographic/clinical variables) that made important contributions to distinguishing predicted high- and low-risk patients. The identified associations were partially supported by previous studies.

Machine Learning-Based Prediction of Distant Recurrence in Invasive Breast Carcinoma Using Clinicopathological Data: A Cross-Institutional Study

Breast cancer is the most common type of cancer worldwide. Alarmingly, approximately 30% of breast cancer cases result in disease recurrence at distant organs after treatment. Distant recurrence is more common in some subtypes such as invasive breast carcinoma (IBC). While clinicians have utilized several clinicopathological measurements to predict distant recurrences in IBC, no studies have predicted distant recurrences by combining clinicopathological evaluations of IBC tumors pre- and post-therapy with machine learning (ML) models. The goal of our study was to determine whether classification-based ML techniques could predict distant recurrences in IBC patients using key clinicopathological measurements, including pathological staging of the tumor and surrounding lymph nodes assessed both pre- and post-neoadjuvant therapy, response to therapy via standard-of-care imaging, and binary status of adjuvant therapy administered to patients. We trained and tested four clinicopathological ML models using a dataset (144 and 17 patients for training and testing, respectively) from Duke University and validated the best-performing model using an external dataset (8 patients) from Dartmouth Hitchcock Medical Center. The random forest model performed better than the C-support vector classifier, multilayer perceptron, and logistic regression models, yielding AUC values of 1.0 in the testing set and 0.75 in the validation set (p < 0.002) across both institutions, thereby demonstrating the cross-institutional portability and validity of ML models in the field of clinical research in cancer. The top-ranking clinicopathological measurement impacting the prediction of distant recurrences in IBC were identified to be tumor response to neoadjuvant therapy as evaluated via SOC imaging and pathology, which included tumor as well as node staging.

Synergy between imputed genetic pathway and clinical information for predicting recurrence in early stage non-small cell lung cancer

OBJECTIVE

Lung cancer exhibits unpredictable recurrence in low-stage tumors and variable responses to different therapeutic interventions. Predicting relapse in early-stage lung cancer can facilitate precision medicine and improve patient survivability. While existing machine learning models rely on clinical data, incorporating genomic information could enhance their efficiency. This study aims to impute and integrate specific types of genomic data with clinical data to improve the accuracy of machine learning models for predicting relapse in early-stage, non-small cell lung cancer patients.

METHODS

The study utilized a publicly available TCGA lung cancer cohort and imputed genetic pathway scores into the Spanish Lung Cancer Group (SLCG) data, specifically in 1348 early-stage patients. Initially, tumor recurrence was predicted without imputed pathway scores. Subsequently, the SLCG data were augmented with pathway scores imputed from TCGA. The integrative approach aimed to enhance relapse risk prediction performance.

RESULTS

The integrative approach achieved improved relapse risk prediction with the following evaluation metrics: an area under the precision-recall curve (PR-AUC) score of 0.75, an area under the ROC (ROC-AUC) score of 0.80, an F1 score of 0.61, and a Precision of 0.80. The prediction explanation model SHAP (SHapley Additive exPlanations) was employed to explain the machine learning model's predictions.

CONCLUSION

We conclude that our explainable predictive model is a promising tool for oncologists that addresses an unmet clinical need of post-treatment patient stratification based on the relapse risk while also improving the predictive power by incorporating proxy genomic data not available for specific patients.

Predictive overfitting in immunological applications: Pitfalls and solutions

Overfitting describes the phenomenon where a highly predictive model on the training data generalizes poorly to future observations. It is a common concern when applying machine learning techniques to contemporary medical applications, such as predicting vaccination response and disease status in infectious disease or cancer studies. This review examines the causes of overfitting and offers strategies to counteract it, focusing on model complexity reduction, reliable model evaluation, and harnessing data diversity. Through discussion of the underlying mathematical models and illustrative examples using both synthetic data and published real datasets, our objective is to equip analysts and bioinformaticians with the knowledge and tools necessary to detect and mitigate overfitting in their research.

Artificial Intelligence in Head and Neck Cancer: A Systematic Review of Systematic Reviews

INTRODUCTION

Several studies have emphasized the potential of artificial intelligence (AI) and its subfields, such as machine learning (ML), as emerging and feasible approaches to optimize patient care in oncology. As a result, clinicians and decision-makers are faced with a plethora of reviews regarding the state of the art of applications of AI for head and neck cancer (HNC) management. This article provides an analysis of systematic reviews on the current status, and of the limitations of the application of AI/ML as adjunctive decision-making tools in HNC management.

METHODS

Electronic databases (PubMed, Medline via Ovid, Scopus, and Web of Science) were searched from inception until November 30, 2022. The study selection, searching and screening processes, inclusion, and exclusion criteria followed the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. A risk of bias assessment was conducted using a tailored and modified version of the Assessment of Systematic Review (AMSTAR-2) tool and quality assessment using the Risk of Bias in Systematic Reviews (ROBIS) guidelines.

RESULTS

Of the 137 search hits retrieved, 17 fulfilled the inclusion criteria. This analysis of systematic reviews revealed that the application of AI/ML as a decision aid in HNC management can be thematized as follows: (1) detection of precancerous and cancerous lesions within histopathologic slides; (2) prediction of the histopathologic nature of a given lesion from various sources of medical imaging; (3) prognostication; (4) extraction of pathological findings from imaging; and (5) different applications in radiation oncology. In addition, the challenges in implementation of AI/ML models for clinical evaluations include the lack of standardized methodological guidelines for the collection of clinical images, development of these models, reporting of their performance, external validation procedures, and regulatory frameworks.

CONCLUSION

At present, there is a paucity of evidence to suggest the adoption of these models in clinical practice due to the aforementioned limitations. Therefore, this manuscript highlights the need for development of standardized guidelines to facilitate the adoption and implementation of these models in the daily clinical practice. In addition, adequately powered, prospective, randomized controlled trials are urgently needed to further assess the potential of AI/ML models in real-world clinical settings for the management of HNC.

A survival prediction model via interpretable machine learning for patients with oropharyngeal cancer following radiotherapy

PURPOSE

To explore interpretable machine learning (ML) methods, with the hope of adding more prognosis value, for predicting survival for patients with Oropharyngeal-Cancer (OPC).

METHODS

A cohort of 427 OPC patients (Training 341, Test 86) from TCIA database was analyzed. Radiomic features of gross-tumor-volume (GTV) extracted from planning CT using Pyradiomics, and HPV p16 status, etc. patient characteristics were considered as potential predictors. A multi-level dimension reduction algorithm consisting of Least-Absolute-Selection-Operator (Lasso) and Sequential-Floating-Backward-Selection (SFBS) was proposed to effectively remove redundant/irrelevant features. The interpretable model was constructed by quantifying the contribution of each feature to the Extreme-Gradient-Boosting (XGBoost) decision by Shapley-Additive-exPlanations (SHAP) algorithm.

RESULTS

The Lasso-SFBS algorithm proposed in this study finally selected 14 features, and our prediction model achieved an area-under-ROC-curve (AUC) of 0.85 on the test dataset based on this feature set. The ranking of the contribution values calculated by SHAP shows that the top predictors that were most correlated with survival were ECOG performance status, wavelet-LLH_firstorder_Mean, chemotherapy, wavelet-LHL_glcm_InverseVariance, tumor size. Those patients who had chemotherapy, with positive HPV p16 status, and lower ECOG performance status, tended to have higher SHAP scores and longer survival; who had an older age at diagnosis, heavy drinking and smoking pack year history, tended to lower SHAP scores and shorter survival.

CONCLUSION

We demonstrated predictive values of combined patient characteristics and imaging features for the overall survival of OPC patients. The multi-level dimension reduction algorithm can reliably identify the most plausible predictors that are mostly associated with overall survival. The interpretable patient-specific survival prediction model, capturing correlations of each predictor and clinical outcome, was developed to facilitate clinical decision-making for personalized treatment.

Mining Prognostic Biomarkers of Thyroid Cancer Patients Based on the Immune-Related Genes and Development of a Reliable Prognostic Risk Model

PURPOSE

Tumor immunity serves an essential role in the occurrence and development of thyroid cancer (THCA). The aim of this study is to establish an immune-related prognostic model for THCA patients by using immune-related genes (IRGs).

METHODS

Wilcox test was used to screen the differentially expressed immune-related genes (DEIRGs) in THCA and normal tissues, then the DEIRGs related to prognosis were identified using univariate Cox regression analysis. According to The Cancer Genome Atlas (TCGA) cohort, we developed a least absolute shrinkage and selection operator (LASSO) regression prognostic model and performed validation analyses regard to the predictive value of the model in internal (TCGA) and external (International Cancer Genome Consortium) cohorts respectively. Finally, we analyzed the correlation among the prognostic model, clinical variables, and immune cell infiltration.

RESULTS

Eighty-two of 2,498 IRGs were differentially expressed between THCA and normal tissues, and 18 of them were related to prognosis. LASSO Cox regression analysis identified seven DEIRGs with the greatest prognostic value to construct the prognostic model. The risk model showed high predictive value for the survival of THCA in two independent cohorts. The risk score according to the risk model was positively associated with poor survival and the infiltration levels of immune cells, it can evaluate the prognosis of THCA patients independent of any other clinicopathologic feature. The prognostic value and genetic alternations of seven risk genes were evaluated separately.

CONCLUSION

Our study established and verified a dependable prognostic model associated with immune for THCA, both the identified IRGs and immune-related risk model were clinically significant, which is conducive to promoting individualized immunotherapy against THCA.

A Comprehensive Analysis of the Prognostic, Immunological and Diagnostic Role of CCNF in Pan-cancer

Background: Cyclin F (CCNF) represents a pivotal constituent within the family of cell cycle proteins, which also belongs to the F-box protein family and acts as a critical regulatory factor in cell cycle transition. Its heightened expression has been consistently identified across various cancer types, including breast, pancreatic, and colorectal cancer. Nonetheless, a comprehensive exploration of CCNF's involvement in pan-cancer remains lacking. Methods: This study collected transcriptomic data and clinical information from several databases, including The Cancer Genome Atlas (TCGA), Genotype-Tissue Expression (GTEx), and BioGPS detabase. Employing bioinformatics methods, we investigated the potential oncogenic role of CCNF, utilizing various databases such as cBioPortal, Human Protein Atlas (HPA), TIMER2, UALCAN, GEPIA, GSCALite, and CTD detabase. These analyses focused on exploring CCNF expression, prognosis, gene mutations, immune cell infiltration, DNA methylation levels, and targeted chemical drugs across different tumor types. Additionally, we obtained CCNF-related genes from GeneMANIA and GEPIA databases and conducted GO and KEGG enrichment analyses to gain deeper insights into the biological processes associated with CCNF. Furthermore, we validated the differential expression of CCNF in normal human breast cancer and breast cancer cell lines using experimental verification. Results: CCNF exhibited upregulation in the majority of cancer types, demonstrating early diagnostic potential in 15 cancers and prognostic implications for adverse outcomes across numerous malignancies. Furthermore, CCNF was found to be linked with markers of the tumor immune microenvironment in various cancers. Additionally, CCNF expression influenced genetic alterations in pan-cancer. Enrichment analysis revealed that CCNF primarily participates in crucial biological pathways such as the cell cycle, p53 signaling pathway, and cellular senescence pathways. RT-qpcr and WB assays further confirmed that CCNF expression was higher in human cancer cell lines than in normal cell lines. Conclusion: The underlying role and mechanism of CCNF in pan-cancer were elucidated through comprehensive bioinformatics analysis and experimental validation. CCNF holds promise as an invaluable early detection indicator and tumor biomarker, offering potential targets for tumor treatment and prevention.

Machine-learning-based predictions of imprinting quality using ensemble and non-linear regression algorithms

The molecularly imprinted polymers are artificial polymers that, during the synthesis, create specific sites for a definite purpose. These polymers due to their characteristics such as stability, easy of synthesis, reproducibility, reusability, high accuracy, and selectivity have many applications. However, the variety of the functional monomers, templates, solvents, and synthesis conditions like pH, temperature, the rate of stirring, and time, limit the selectivity of imprinting. The Practical optimization of the synthetic conditions has many drawbacks, including chemical compound usage, equipment requirements, and time costs. The use of machine learning (ML) for the prediction of the imprinting factor (IF), which indicates the quality of imprinting is a very interesting idea to overcome these problems. The ML has many advantages, for example a lack of human error, high accuracy, high repeatability, and prediction of a large amount of data in the minimum time. In this research, ML was used to predict the IF using non-linear regression algorithms, including classification and regression tree, support vector regression, and k-nearest neighbors, and ensemble algorithms, like gradient boosting (GB), random forest, and extra trees. The data sets were obtained practically in the laboratory, and inputs, included pH, the type of the template, the type of the monomer, solvent, the distribution coefficient of the MIP (K_MIP), and the distribution coefficient of the non-imprinted polymer (K_NIP). The mutual information feature selection method was used to select the important features affecting the IF. The results showed that the GB algorithm had the best performance in predicting the IF, and using this algorithm, the maximum R² value (R² = 0.871), and the minimum mean absolute error (MAE = - 0.982), and mean square error were obtained (MSE = - 2.303).

Assessment of emerging pretraining strategies in interpretable multimodal deep learning for cancer prognostication

BACKGROUND

Deep learning models can infer cancer patient prognosis from molecular and anatomic pathology information. Recent studies that leveraged information from complementary multimodal data improved prognostication, further illustrating the potential utility of such methods. However, current approaches: 1) do not comprehensively leverage biological and histomorphological relationships and 2) make use of emerging strategies to "pretrain" models (i.e., train models on a slightly orthogonal dataset/modeling objective) which may aid prognostication by reducing the amount of information required for achieving optimal performance. In addition, model interpretation is crucial for facilitating the clinical adoption of deep learning methods by fostering practitioner understanding and trust in the technology.

METHODS

Here, we develop an interpretable multimodal modeling framework that combines DNA methylation, gene expression, and histopathology (i.e., tissue slides) data, and we compare performance of crossmodal pretraining, contrastive learning, and transfer learning versus the standard procedure.

RESULTS

Our models outperform the existing state-of-the-art method (average 11.54% C-index increase), and baseline clinically driven models (average 11.7% C-index increase). Model interpretations elucidate consideration of biologically meaningful factors in making prognosis predictions.

DISCUSSION

Our results demonstrate that the selection of pretraining strategies is crucial for obtaining highly accurate prognostication models, even more so than devising an innovative model architecture, and further emphasize the all-important role of the tumor microenvironment on disease progression.

Spatial Clusters of Cancer Mortality in Brazil: A Machine Learning Modeling Approach

Objectives: Our aim was to test if machine learning algorithms can predict cancer mortality (CM) at an ecological level and use these results to identify statistically significant spatial clusters of excess cancer mortality (eCM). Methods: Age-standardized CM was extracted from the official databases of Brazil. Predictive features included sociodemographic and health coverage variables. Machine learning algorithms were selected and trained with 70% of the data, and the performance was tested with the remaining 30%. Clusters of eCM were identified using SatScan. Additionally, separate analyses were performed for the 10 most frequent cancer types. Results: The gradient boosting trees algorithm presented the highest coefficient of determination (R 2 = 0.66). For total cancer, all algorithms overlapped in the region of Bagé (27% eCM). For esophageal cancer, all algorithms overlapped in west Rio Grande do Sul (48%-96% eCM). The most significant cluster for stomach cancer was in Macapá (82% eCM). The most important variables were the percentage of the white population and residents with computers. Conclusion: We found consistent and well-defined geographic regions in Brazil with significantly higher than expected cancer mortality.

Orchestrating information across tissues via a novel multitask GAT framework to improve quantitative gene regulation relation modeling for survival analysis

Survival analysis is critical to cancer prognosis estimation. High-throughput technologies facilitate the increase in the dimension of genic features, but the number of clinical samples in cohorts is relatively small due to various reasons, including difficulties in participant recruitment and high data-generation costs. Transcriptome is one of the most abundantly available OMIC (referring to the high-throughput data, including genomic, transcriptomic, proteomic and epigenomic) data types. This study introduced a multitask graph attention network (GAT) framework DQSurv for the survival analysis task. We first used a large dataset of healthy tissue samples to pretrain the GAT-based HealthModel for the quantitative measurement of the gene regulatory relations. The multitask survival analysis framework DQSurv used the idea of transfer learning to initiate the GAT model with the pretrained HealthModel and further fine-tuned this model using two tasks i.e. the main task of survival analysis and the auxiliary task of gene expression prediction. This refined GAT was denoted as DiseaseModel. We fused the original transcriptomic features with the difference vector between the latent features encoded by the HealthModel and DiseaseModel for the final task of survival analysis. The proposed DQSurv model stably outperformed the existing models for the survival analysis of 10 benchmark cancer types and an independent dataset. The ablation study also supported the necessity of the main modules. We released the codes and the pretrained HealthModel to facilitate the feature encodings and survival analysis of transcriptome-based future studies, especially on small datasets. The model and the code are available at http://www.healthinformaticslab.org/supp/.

Single-Cell Analysis and Classification according to Multiplexed Proteins via Microdroplet-Based Self-Driven Magnetic Surface-Enhanced Raman Spectroscopy Platforms Assisted with Machine Learning Algorithms

A microdroplet-based surface-enhanced Raman spectroscopy (microdroplet SERS) platform was constructed to envelop individual cells in microdroplets, followed by the SERS detection of their extracellular vesicle-proteins (EV-proteins) via the in-drop immunoassays by use of immunomagnetic beads (iMBs) and immuno-SERS tags (iSERS tags). A unique phenomenon is found that iMBs can start a spontaneous reorientation on the probed cell surface based on the electrostatic force-driven interfacial aggregation effect, which leads EV-proteins and iSERS tags to be gathered from a liquid phase to a cell membrane interface and significantly improves SERS sensitivity to the single-cell analysis level due to the formation of numbers of SERS hotspots. Three EV-proteins from two breast cancer cell lines were collected and further analyzed by machine learning algorithmic tools, which will be helpful for a deeper understanding of breast cancer subtypes from the view of EV-proteins.

A Framework for Prediction of Oncogenomic Progression Aiding Personalized Treatment of Gastric Cancer

Mutations in genes can alter their DNA patterns, and by recognizing these mutations, many carcinomas can be diagnosed in the progression stages. The human body contains many hidden and enigmatic features that humankind has not yet fully understood. A total of 7539 neoplasm cases were reported from 1 January 2021 to 31 December 2021. Of these, 3156 were seen in males (41.9%) and 4383 (58.1%) in female patients. Several machine learning and deep learning frameworks are already implemented to detect mutations, but these techniques lack generalized datasets and need to be optimized for better results. Deep learning-based neural networks provide the computational power to calculate the complex structures of gastric carcinoma-driven gene mutations. This study proposes deep learning approaches such as long and short-term memory, gated recurrent units and bi-LSTM to help in identifying the progression of gastric carcinoma in an optimized manner. This study includes 61 carcinogenic driver genes whose mutations can cause gastric cancer. The mutation information was downloaded from intOGen.org and normal gene sequences were downloaded from asia.ensembl.org, as explained in the data collection section. The proposed deep learning models are validated using the self-consistency test (SCT), 10-fold cross-validation test (FCVT), and independent set test (IST); the IST prediction metrics of accuracy, sensitivity, specificity, MCC and AUC of LSTM, Bi-LSTM, and GRU are 97.18%, 98.35%, 96.01%, 0.94, 0.98; 99.46%, 98.93%, 100%, 0.989, 1.00; 99.46%, 98.93%, 100%, 0.989 and 1.00, respectively.

Exploring the Role of Circulating Cell-Free RNA in the Development of Colorectal Cancer

Circulating tumor RNA (ctRNA) has recently emerged as a novel and attractive liquid biomarker. CtRNA is capable of providing important information about the expression of a variety of target genes noninvasively, without the need for biopsies, through the use of circulating RNA sequencing. The overexpression of cancer-specific transcripts increases the tumor-derived RNA signal, which overcomes limitations due to low quantities of circulating tumor DNA (ctDNA). The purpose of this work is to present an up-to-date review of current knowledge regarding ctRNAs and their status as biomarkers to address the diagnosis, prognosis, prediction, and drug resistance of colorectal cancer. The final section of the article discusses the practical aspects involved in analyzing plasma ctRNA, including storage and isolation, detection technologies, and their limitations in clinical applications.

Enhancing Health and Public Health through Machine Learning: Decision Support for Smarter Choices

In recent years, the integration of Machine Learning (ML) techniques in the field of healthcare and public health has emerged as a powerful tool for improving decision-making processes [...].

Deep Learning Approaches for Glioblastoma Prognosis in Resource-Limited Settings: A Study Using Basic Patient Demographic, Clinical, and Surgical Inputs

BACKGROUND

Glioblastoma (GBM) is the most common brain tumor in the United States, with an annual incidence rate of 3.21 per 100,000. It is the most aggressive type of diffuse glioma and has a median survival of months after treatment. This study aims to assess the accuracy of different novel deep learning models trained on a set of simple clinical, demographic, and surgical variables to assist in clinical practice, even in areas with constrained health care infrastructure.

METHODS

Our study included 37,095 patients with GBM from the SEER (Surveillance Epidemiology and End Results) database. All predictors were based on demographic, clinicopathologic, and treatment information of the cases. Our outcomes of interest were months of survival and vital status. Concordance index (C-index) and integrated Brier scores (IBS) were used to evaluate the performance of the models.

RESULTS

The patient characteristics and the statistical analyses were consistent with the epidemiologic literature. The models C-index and IBS ranged from 0.6743 to 0.6918 and from 0.0934 to 0.1034, respectively. Probabilistic matrix factorization (0.6918), multitask logistic regression (0.6916), and logistic hazard (0.6916) had the highest C-index scores. The models with the lowest IBS were the probabilistic matrix factorization (0.0934), multitask logistic regression (0.0935), and logistic hazard (0.0936). These models had an accuracy (1-IBS) of 90.66%; 90.65%, and 90.64%, respectively. The deep learning algorithms were deployed on an interactive Web-based tool for practical use available via https://glioblastoma-survanalysis.herokuapp.com/.

CONCLUSIONS

Novel deep learning algorithms can better predict GBM prognosis than do baseline methods and can lead to more personalized patient care regardless of extensive electronic health record availability.

Use of machine learning to predict bladder cancer survival outcomes: a systematic literature review

INTRODUCTION

The objective of this systematic review is to summarize the use of machine learning (ML) in predicting overall survival (OS) in patients with bladder cancer.

METHODS

Search terms for bladder cancer, ML algorithms, and mortality were used to identify studies in PubMed and Web of Science as of February 2022. Notable inclusion/exclusion criteria contained the inclusion of studies that utilized patient-level datasets and exclusion of primary gene expression-related dataset studies. Study quality and bias were assessed using the International Journal of Medical Informatics (IJMEDI) checklist.

RESULTS

Of the 14 included studies, the most common algorithms were artificial neural networks (n = 8) and logistic regression (n = 4). Nine articles described missing data handling, with five articles removing patients with missing data entirely. With respect to feature selection, the most common sociodemographic variables were age (n = 9), gender (n = 9), and smoking status (n = 3), with clinical variables most commonly including tumor stage (n = 8), grade (n = 7), and lymph node involvement (n = 6). Most studies (n = 10) were of medium IJMEDI quality, with common areas of improvement being the descriptions of data preparation and deployment.

CONCLUSIONS

ML holds promise for optimizing bladder cancer care through accurate OS predictions, but challenges related to data processing, feature selection, and data source quality must be resolved to develop robust models. While this review is limited by its inability to compare models across studies, this systematic review will inform decision-making by various stakeholders to improve understanding of ML-based OS prediction in bladder cancer and foster interpretability of future models.

Utilizing Graph Neural Networks for Breast Cancer Prognosis Prediction with High-dimensional Genomic Data

An accurate prediction of breast cancer is essential to help physicians make appropriate treatment recommendations to reduce the chance of excessive treatment, avoiding unnecessary anxiety for patients. Cancer prognosis is highly related to patients' genomic features, which are high-dimensional in nature. In this study, we utilize a systems biology feature selector for dimension reduction to select 20 prognostic biomarkers that are considered closely related to breast cancer prognosis from the high dimensional RNA Sequencing (RNA-Seq) data. Furthermore, we establish a graph neural network (GNN) and a multi-layer perception (MLP) graph-level readout method to better extract the underlying gene interactions from the corresponding gene interaction network (GIN). With the help of GINs, the model performs the best among all baseline models, especially in the area under the precision-recall curve (AUPRC) by as large as 23%. The results demonstrate that our approach using GNNs can successfully extract high-dimensional and complicated interactions within genomic data.

Genetic and lifestyle factors for breast cancer risk assessment in Southeast China

BACKGROUND

Despite the rising incidence and mortality of breast cancer among women in China, there are currently few predictive models for breast cancer in the Chinese population and with low accuracy. This study aimed to identify major genetic and life-style risk factors in a Chinese population for potential application in risk assessment models.

METHODS

A case-control study in southeast China was conducted including 1321 breast cancer patients and 2045 controls during 2013-2016, in which the data were randomly divided into a training set and a test set on a 7:3 scale. The association between genetic and life-style factors and breast cancer was examined using logistic regression models. Using AUC curves, we also compared the performance of the logistic model to machine learning models, namely LASSO regression model and support vector machine (SVM), and the scores calculated from CKB, Gail and Tyrer-Cuzick models in the test set.

RESULTS

Among all factors considered, the best model was achieved when polygenetic risk score, lifestyle, and reproductive factors were considered jointly in the logistic regression model (AUC = 0.73; 95% CI: 0.70-0.77). The models created in this study performed better than those using scores calculated from the CKB, Gail, and Tyrer-Cuzick models. However, the logistic model and machine learning models did not significantly differ from one another.

CONCLUSION

In summary, we have found genetic and lifestyle risk predictors for breast cancer with moderate discrimination, which might provide reference for breast cancer screening in southeast China. Further population-based studies are needed to validate the model for future applications in personalized breast cancer screening programs.

GAN-based data augmentation for transcriptomics: survey and comparative assessment

MOTIVATION

Transcriptomics data are becoming more accessible due to high-throughput and less costly sequencing methods. However, data scarcity prevents exploiting deep learning models' full predictive power for phenotypes prediction. Artificially enhancing the training sets, namely data augmentation, is suggested as a regularization strategy. Data augmentation corresponds to label-invariant transformations of the training set (e.g. geometric transformations on images and syntax parsing on text data). Such transformations are, unfortunately, unknown in the transcriptomic field. Therefore, deep generative models such as generative adversarial networks (GANs) have been proposed to generate additional samples. In this article, we analyze GAN-based data augmentation strategies with respect to performance indicators and the classification of cancer phenotypes.

RESULTS

This work highlights a significant boost in binary and multiclass classification performances due to augmentation strategies. Without augmentation, training a classifier on only 50 RNA-seq samples yields an accuracy of, respectively, 94% and 70% for binary and tissue classification. In comparison, we achieved 98% and 94% of accuracy when adding 1000 augmented samples. Richer architectures and more expensive training of the GAN return better augmentation performances and generated data quality overall. Further analysis of the generated data shows that several performance indicators are needed to assess its quality correctly.

AVAILABILITY AND IMPLEMENTATION

All data used for this research are publicly available and comes from The Cancer Genome Atlas. Reproducible code is available on the GitLab repository: https://forge.ibisc.univ-evry.fr/alacan/GANs-for-transcriptomics.

AttOmics: attention-based architecture for diagnosis and prognosis from omics data

MOTIVATION

The increasing availability of high-throughput omics data allows for considering a new medicine centered on individual patients. Precision medicine relies on exploiting these high-throughput data with machine-learning models, especially the ones based on deep-learning approaches, to improve diagnosis. Due to the high-dimensional small-sample nature of omics data, current deep-learning models end up with many parameters and have to be fitted with a limited training set. Furthermore, interactions between molecular entities inside an omics profile are not patient specific but are the same for all patients.

RESULTS

In this article, we propose AttOmics, a new deep-learning architecture based on the self-attention mechanism. First, we decompose each omics profile into a set of groups, where each group contains related features. Then, by applying the self-attention mechanism to the set of groups, we can capture the different interactions specific to a patient. The results of different experiments carried out in this article show that our model can accurately predict the phenotype of a patient with fewer parameters than deep neural networks. Visualizing the attention maps can provide new insights into the essential groups for a particular phenotype.

AVAILABILITY AND IMPLEMENTATION

The code and data are available at https://forge.ibisc.univ-evry.fr/abeaude/AttOmics. TCGA data can be downloaded from the Genomic Data Commons Data Portal.

Cancer survival prediction by learning comprehensive deep feature representation for multiple types of genetic data

BACKGROUND

Cancer is one of the leading death causes around the world. Accurate prediction of its survival time is significant, which can help clinicians make appropriate therapeutic schemes. Cancer data can be characterized by varied molecular features, clinical behaviors and morphological appearances. However, the cancer heterogeneity problem usually makes patient samples with different risks (i.e., short and long survival time) inseparable, thereby causing unsatisfactory prediction results. Clinical studies have shown that genetic data tends to contain more molecular biomarkers associated with cancer, and hence integrating multi-type genetic data may be a feasible way to deal with cancer heterogeneity. Although multi-type gene data have been used in the existing work, how to learn more effective features for cancer survival prediction has not been well studied.

RESULTS

To this end, we propose a deep learning approach to reduce the negative impact of cancer heterogeneity and improve the cancer survival prediction effect. It represents each type of genetic data as the shared and specific features, which can capture the consensus and complementary information among all types of data. We collect mRNA expression, DNA methylation and microRNA expression data for four cancers to conduct experiments.

CONCLUSIONS

Experimental results demonstrate that our approach substantially outperforms established integrative methods and is effective for cancer survival prediction.

AVAILABILITY AND IMPLEMENTATION

https://github.com/githyr/ComprehensiveSurvival .

Identifying miRNA biomarkers for breast cancer and ovarian cancer: a text mining perspective

BACKGROUND

microRNA (miRNAs) are small, non-coding RNAs that mediate post-transcriptional gene silencing. Numerous studies have demonstrated the critical role of miRNAs in the development of breast cancer and ovarian cancer. To reduce potential bias from individual studies, a more comprehensive approach of exploring miRNAs in cancer research is essential. This study aims to explore the role of miRNAs in the development of breast cancer and ovarian cancer.

METHODS

Abstracts of the publications were tokenized and the biomedical terms (miRNA, gene, disease, species) were identified and extracted for vectorization. Predictive analyses were conducted with four machine learning models: K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Random Forest (RF), and Naïve Bayes. Both holdout validation and cross-validation were utilized. Feature importance will be identified for miRNA-cancer networks construction.

RESULTS

We found that miR-182 is highly specific to female cancers. miR-182 targets different genes in regulating breast cancer and ovarian cancer. Naïve Bayes provided a promising prediction model for breast cancer and ovarian cancer with miRNAs and genes combination, with an accuracy score greater than 60%. Feature importance identified miR-155 and miR-199 are critical for breast cancer and ovarian cancer prediction, with miR-155 being highly related to breast cancer, whereas miR-199 being more associated with ovarian cancer.

CONCLUSION

Our approach effectively identified potential miRNA biomarkers associated with breast cancer and ovarian cancer, providing a solid foundation for generating novel research hypotheses and guiding future experimental studies.

Role of Histone Deacetylases in the Pathogenesis of Salivary Gland Tumors and Therapeutic Targeting Options

Salivary gland tumors (SGTs) comprise a rare and heterogenous category of benign/malignant neoplasms with progressively increasing knowledge of the molecular mechanisms underpinning their pathogenesis, poor prognosis, and therapeutic treatment efficacy. Emerging data are pointing toward an interplay of genetic and epigenetic factors contributing to their heterogeneity and diverse clinical phenotypes. Post-translational histone modifications such as histone acetylation/deacetylation have been shown to actively participate in the pathobiology of SGTs, further suggesting that histone deacetylating factors (HDACs), selective or pan-HDAC inhibitors (HDACis), might present effective treatment options for these neoplasms. Herein, we describe the molecular and epigenetic mechanisms underlying the pathology of the different types of SGTs, focusing on histone acetylation/deacetylation effects on gene expression as well as the progress of HDACis in SGT therapy and the current status of relevant clinical trials.

The value of machine learning for prognosis prediction of diphenhydramine exposure: National analysis of 50,000 patients in the United States

Background

Diphenhydramine (DPH) is an antihistamine medication that in overdose can result in anticholinergic symptoms and serious complications, including arrhythmia and coma. We aimed to compare the value of various machine learning (ML) models, including light gradient boosting machine (LGBM), logistic regression (LR), and random forest (RF), in the outcome prediction of DPH poisoning.

Materials and Methods

We used the National Poison Data System database and included all of the human exposures of DPH from January 01, 2017 to December 31, 2017, and excluded those cases with missing information, duplicated cases, and those who reported co-ingestion. Data were split into training and test datasets, and three ML models were compared. We developed confusion matrices for each, and standard performance metrics were calculated.

Results

Our study population included 53,761 patients with DPH exposure. The most common reasons for exposure, outcome, chronicity of exposure, and formulation were captured. Our results showed that the average precision-recall area under the curve (AUC) of 0.84. LGBM and RF had the highest performance (average AUC of 0.91), followed by LR (average AUC of 0.90). The specificity of the models was 87.0% in the testing groups. The precision of models was 75.0%. Recall (sensitivity) of models ranged between 73% and 75% with an F1 score of 75.0%. The overall accuracy of LGBM, LR, and RF models in the test dataset was 74.8%, 74.0%, and 75.1%, respectively. In total, just 1.1% of patients (mostly those with major outcomes) received physostigmine.

Conclusion

Our study demonstrates the application of ML in the prediction of DPH poisoning.

Machine Learning Approach for the Prediction of Age-Specific Probability of SCA3 and DRPLA by Survival Curve Analysis

Background and Objectives

As the number of repeats in the expansion increases, polyglutamine diseases tend to show at a younger age. From this relationship, attempts have been made to predict age at onset by parametric survival analysis. However, a method for a more accurate prediction has been desirable. In this study, we examined 2 methods for survival analysis using machine learning and 6 conventional methods for parametric survival analysis of spinocerebellar ataxia (SCA)3 and dentatorubral-pallidoluysian atrophy (DRPLA).

Methods

We compared the performance of 2 machine learning methods of survival analysis (random survival forest [RSF] and DeepSurv) and 6 methods of parametric survival analysis (Weibull, exponential, Gaussian, logistic, loglogistic, and log Gaussian). Training and evaluation were performed using the leave-one-out cross-validation method, and evaluation criteria included root mean squared error (RMSE), mean absolute error (MAE), and the integrated Brier score. The latter was used as the primary end point, and the survival analysis model yielding the best result was used to predict the asymptomatic probability.

Results

Among the models examined, the RSF and DeepSurv machine learning methods had a higher prediction accuracy than the parametric methods of survival analysis. For both SCA3 and DRPLA, RSF had a higher accuracy than DeepSurv for the assessment of RMSE (SCA3: 7.37, DRPLA: 10.78), MAE (SCA3: 5.52, DRPLA: 8.17), and the integrated Brier score (SCA3: 0.05, DRPLA: 0.077). Using RSF, we determined the age-specific probability distribution of age at onset based on CAG repeat size and current age.

Discussion

In this study, we have demonstrated the superiority of machine learning methods for predicting age at onset of SCA3 and DRPLA using survival analysis. Such accurate prediction of onset will be useful for genetic counseling of carriers and for devising methods to verify the effects of interventions for unaffected individuals.

Machine learning for predicting survival of colorectal cancer patients

Colorectal cancer is one of the most incident types of cancer in the world, with almost 2 million new cases annually. In Brazil, the scenery is the same, around 41 thousand new cases were estimated in the last 3 years. This increase in cases further intensifies the interest and importance of studies related to the topic, especially using new approaches. The use of machine learning algorithms for cancer studies has grown in recent years, and they can provide important information to medicine, in addition to making predictions based on the data. In this study, five different classifications were performed, considering patients' survival. Data were extracted from Hospital Based Cancer Registries of São Paulo, which is coordinated by Fundação Oncocentro de São Paulo, containing patients with colorectal cancer from São Paulo state, Brazil, treated between 2000 and 2021. The machine learning models used provided us the predictions and the most important features for each one of the algorithms of the studies. Using part of the dataset to validate our models, the results of the predictors were around 77% of accuracy, with AUC close to 0.86, and the most important column was the clinical staging in all of them.

Skin Cancer Classification Using Deep Spiking Neural Network

Skin cancer is one of the primary causes of death globally, and experts diagnose it by visual inspection, which can be inaccurate. The need for developing a computer-aided method to aid dermatologists in diagnosing skin cancer is highlighted by the fact that early identification can lower the number of deaths caused by skin malignancies. Among computer-aided techniques, deep learning is the most popular for identifying cancer from skin lesion images. Due to their power-efficient behavior, spiking neural networks are attractive deep neural networks for hardware implementation. We employed deep spiking neural networks using the surrogate gradient descent method to classify 3670 melanoma and 3323 non-melanoma images from the ISIC 2019 dataset. We achieved an accuracy of 89.57% and an F1 score of 90.07% using the proposed spiking VGG-13 model, which is higher than the VGG-13 and AlexNet using less trainable parameters.

Biomarkers as Biomedical Bioindicators: Approaches and Techniques for the Detection, Analysis, and Validation of Novel Biomarkers of Diseases

A biomarker is any measurable biological moiety that can be assessed and measured as a potential index of either normal or abnormal pathophysiology or pharmacological responses to some treatment regimen. Every tissue in the body has a distinct biomolecular make-up, which is known as its biomarkers, which possess particular features, viz., the levels or activities (the ability of a gene or protein to carry out a particular body function) of a gene, protein, or other biomolecules. A biomarker refers to some feature that can be objectively quantified by various biochemical samples and evaluates the exposure of an organism to normal or pathological procedures or their response to some drug interventions. An in-depth and comprehensive realization of the significance of these biomarkers becomes quite important for the efficient diagnosis of diseases and for providing the appropriate directions in case of multiple drug choices being presently available, which can benefit any patient. Presently, advancements in omics technologies have opened up new possibilities to obtain novel biomarkers of different types, employing genomic strategies, epigenetics, metabolomics, transcriptomics, lipid-based analysis, protein studies, etc. Particular biomarkers for specific diseases, their prognostic capabilities, and responses to therapeutic paradigms have been applied for screening of various normal healthy, as well as diseased, tissue or serum samples, and act as appreciable tools in pharmacology and therapeutics, etc. In this review, we have summarized various biomarker types, their classification, and monitoring and detection methods and strategies. Various analytical techniques and approaches of biomarkers have also been described along with various clinically applicable biomarker sensing techniques which have been developed in the recent past. A section has also been dedicated to the latest trends in the formulation and designing of nanotechnology-based biomarker sensing and detection developments in this field.

Hematologic Cancer Detection Using White Blood Cancerous Cells Empowered with Transfer Learning and Image Processing

Lymphoma and leukemia are fatal syndromes of cancer that cause other diseases and affect all types of age groups including male and female, and disastrous and fatal blood cancer causes an increased savvier death ratio. Both lymphoma and leukemia are associated with the damage and rise of immature lymphocytes, monocytes, neutrophils, and eosinophil cells. So, in the health sector, the early prediction and treatment of blood cancer is a major issue for survival rates. Nowadays, there are various manual techniques to analyze and predict blood cancer using the microscopic medical reports of white blood cell images, which is very steady for prediction and causes a major ratio of deaths. Manual prediction and analysis of eosinophils, lymphocytes, monocytes, and neutrophils are very difficult and time-consuming. In previous studies, they used numerous deep learning and machine learning techniques to predict blood cancer, but there are still some limitations in these studies. So, in this article, we propose a model of deep learning empowered with transfer learning and indulge in image processing techniques to improve the prediction results. The proposed transfer learning model empowered with image processing incorporates different levels of prediction, analysis, and learning procedures and employs different learning criteria like learning rate and epochs. The proposed model used numerous transfer learning models with varying parameters for each model and cloud techniques to choose the best prediction model, and the proposed model used an extensive set of performance techniques and procedures to predict the white blood cells which cause cancer to incorporate image processing techniques. So, after extensive procedures of AlexNet, MobileNet, and ResNet with both image processing and without image processing techniques with numerous learning criteria, the stochastic gradient descent momentum incorporated with AlexNet is outperformed with the highest prediction accuracy of 97.3% and the misclassification rate is 2.7% with image processing technique. The proposed model gives good results and can be applied for smart diagnosing of blood cancer using eosinophils, lymphocytes, monocytes, and neutrophils.

Predicting second breast cancer among women with primary breast cancer using machine learning algorithms, a population-based observational study

Breast cancer survivors often experience recurrence or a second primary cancer. We developed an automated approach to predict the occurrence of any second breast cancer (SBC) using patient-level data and explored the generalizability of the models with an external validation data source. Breast cancer patients from the cancer registry of Zurich, Zug, Schaffhausen, Schwyz (N = 3213; training dataset) and the cancer registry of Ticino (N = 1073; external validation dataset), diagnosed between 2010 and 2018, were used for model training and validation, respectively. Machine learning (ML) methods, namely a feed-forward neural network (ANN), logistic regression, and extreme gradient boosting (XGB) were employed for classification. The best-performing model was selected based on the receiver operating characteristic (ROC) curve. Key characteristics contributing to a high SBC risk were identified. SBC was diagnosed in 6% of all cases. The most important features for SBC prediction were age at incidence, year of birth, stage, and extent of the pathological primary tumor. The ANN model had the highest area under the ROC curve with 0.78 (95% confidence interval [CI] 0.750.82) in the training data and 0.70 (95% CI 0.61-0.79) in the external validation data. Investigating the generalizability of different ML algorithms, we found that the ANN generalized better than the other models on the external validation data. This research is a first step towards the development of an automated tool that could assist clinicians in the identification of women at high risk of developing an SBC and potentially preventing it.

Gastric Cancer Biomarker Candidates Identified by Machine Learning and Integrative Bioinformatics: Toward Personalized Medicine

Gastric cancer (GC) is among the leading causes of cancer-related deaths worldwide. The discovery of robust diagnostic biomarkers for GC remains a challenge. This study sought to identify biomarker candidates for GC by integrating machine learning (ML) and bioinformatics approaches. Transcriptome profiles of patients with GC were analyzed to identify differentially expressed genes between the tumor and adjacent normal tissues. Subsequently, we constructed protein-protein interaction networks so as to find the significant hub genes. Along with the bioinformatics integration of ML methods such as support vector machine, the recursive feature elimination was used to select the most informative genes. The analysis unraveled 160 significant genes, with 88 upregulated and 72 downregulated, 10 hub genes, and 12 features from the variable selection method. The integrated analyses found that EXO1, DTL, KIF14, and TRIP13 genes are significant and poised as potential diagnostic biomarkers in relation to GC. The receiver operating characteristic curve analysis found KIF14 and TRIP13 are strongly associated with diagnosis of GC. We suggest KIF14 and TRIP13 are considered as biomarker candidates that might potentially inform future research on diagnosis, prognosis, or therapeutic targets for GC. These findings collectively offer new future possibilities for precision/personalized medicine research and development for patients with GC.

Detection and Classification of Histopathological Breast Images Using a Fusion of CNN Frameworks

Breast cancer is responsible for the deaths of thousands of women each year. The diagnosis of breast cancer (BC) frequently makes the use of several imaging techniques. On the other hand, incorrect identification might occasionally result in unnecessary therapy and diagnosis. Therefore, the accurate identification of breast cancer can save a significant number of patients from undergoing unnecessary surgery and biopsy procedures. As a result of recent developments in the field, the performance of deep learning systems used for medical image processing has showed significant benefits. Deep learning (DL) models have found widespread use for the aim of extracting important features from histopathologic BC images. This has helped to improve the classification performance and has assisted in the automation of the process. In recent times, both convolutional neural networks (CNNs) and hybrid models of deep learning-based approaches have demonstrated impressive performance. In this research, three different types of CNN models are proposed: a straightforward CNN model (1-CNN), a fusion CNN model (2-CNN), and a three CNN model (3-CNN). The findings of the experiment demonstrate that the techniques based on the 3-CNN algorithm performed the best in terms of accuracy (90.10%), recall (89.90%), precision (89.80%), and f1-Score (89.90%). In conclusion, the CNN-based approaches that have been developed are contrasted with more modern machine learning and deep learning models. The application of CNN-based methods has resulted in a significant increase in the accuracy of the BC classification.

Modeling the survival of colorectal cancer patients based on colonoscopic features in a feature ensemble vision transformer

The prognosis of patients with colorectal cancer (CRC) mostly relies on the classic tumor node metastasis (TNM) staging classification. A more accurate and convenient prediction model would provide a better prognosis and assist in treatment. From May 2014 to December 2017, patients who underwent an operation for CRC were enrolled. The proposed feature ensemble vision transformer (FEViT) used ensemble classifiers to benefit the combinations of relevant colonoscopy features from the pretrained vision transformer and clinical features, including sex, age, family history of CRC, and tumor location, to establish the prognostic model. A total of 1729 colonoscopy images were enrolled in the current retrospective study. For the prediction of patient survival, FEViT achieved an accuracy of 94 % with an area under the receiver operating characteristic curve of 0.93, which was better than the TNM staging classification (90 %, 0.83) in the experiment. FEViT reduced the limited receptive field and gradient disappearance in the conventional convolutional neural network and was a relatively effective and efficient procedure. The promising accuracy of FEViT in modeling survival makes the prognosis of CRC patients more predictable and practical.

Accurate and non-destructive monitoring of mold contamination in foodstuffs based on whole-cell biosensor array coupling with machine-learning prediction models

Mold contamination in foodstuffs causes huge economic losses, quality deterioration and mycotoxin production. Thus, non-destructive and accurate monitoring of mold occurrence in foodstuffs is highly required. We proposed a novel whole-cell biosensor array to monitor pre-mold events in foodstuffs. Firstly, 3 volatile markers ethyl propionate, 1-methyl-1 H-pyrrole and 2,3-butanediol were identified from pre-mold peanuts using gas chromatography-mass spectrometry. Together with other 3 frequently-reported volatiles from Aspergillus flavus infection, the volatiles at subinhibitory concentrations induced significant but differential response patterns from 14 stress-responsive Escherichia coli promoters. Subsequently, a whole-cell biosensor array based on the 14 promoters was constructed after whole-cell immobilization in calcium alginate. To discriminate the response patterns of the whole-cell biosensor array to mold-contaminated foodstuffs, optimal classifiers were determined by comparing 6 machine-learning algorithms. 100 % accuracy was achieved to discriminate healthy from moldy peanuts and maize, and 95 % and 98 % accuracy in discriminating pre-mold stages for infected peanuts and maize, based on random forest classifiers. 83 % accuracy was obtained to separate moldy peanuts from moldy maize by sparse partial least square determination analysis. The results demonstrated high accuracy and practicality of our method based on a whole-cell biosensor array coupling with machine-learning classifiers for mold monitoring in foodstuffs.

Deep learning-extracted CT imaging phenotypes predict response to total resection in colorectal cancer

BACKGROUND

Deep learning surpasses many traditional methods for many vision tasks, allowing the transformation of hierarchical features into more abstract, high-level features.

PURPOSE

To evaluate the prognostic value of preoperative computed tomography (CT) image texture features and deep learning self-learning high-throughput features (SHF) on postoperative overall survival in the treatment of patients with colorectal cancer (CRC).

MATERIAL AND METHODS

The dataset consisted of 810 enrolled patients with CRC confirmed from 10 November 2011 to 10 February 2018. In contrast, SHF extracted by deep learning with multi-task training mechanism and texture features were extracted from the CT with tumor volume region of interest, respectively, and combined with the Cox proportional hazard (CoxPH) model for initial validation to obtain a RAD score to classify patients into high- and low-risk groups. The SHF stability was further validated in combination with Neural Multi-Task Logistic Regression (N-MTLR) model. The overall recognition ability and accuracy of CoxPH and N-MTLR model were evaluated by C-index and Integrated Brier Score (IBS).

RESULTS

SHF had a more significant degree of differentiation than texture features. The result is (SHF vs. texture features: C-index: 0.884 vs. 0.611; IBS: 0.025 vs. 0.073) in the CoxPH model, and (SHF vs. texture features: C-index: 0.861 vs. 0.630; IBS: 0.024 vs. 0.065) in N-MTLR.

CONCLUSION

SHF is superior to texture features and has potential application for the preoperative prediction of the individualized treatment of CRC.

Development of prediction models for one-year brain tumour survival using machine learning: a comparison of accuracy and interpretability

BACKGROUND AND OBJECTIVE

Prediction of survival in patients diagnosed with a brain tumour is challenging because of heterogeneous tumour behaviours and treatment response. Advances in machine learning have led to the development of clinical prognostic models, but due to the lack of model interpretability, integration into clinical practice is almost non-existent. In this retrospective study, we compare five classification models with varying degrees of interpretability for the prediction of brain tumour survival greater than one year following diagnosis.

METHODS

1028 patients aged ≥16 years with a brain tumour diagnosis between April 2012 and April 2020 were included in our study. Three intrinsically interpretable 'glass box' classifiers (Bayesian Rule Lists [BRL], Explainable Boosting Machine [EBM], and Logistic Regression [LR]), and two 'black box' classifiers (Random Forest [RF] and Support Vector Machine [SVM]) were trained on electronic patients records for the prediction of one-year survival. All models were evaluated using balanced accuracy (BAC), F1-score, sensitivity, specificity, and receiver operating characteristics. Black box model interpretability and misclassified predictions were quantified using SHapley Additive exPlanations (SHAP) values and model feature importance was evaluated by clinical experts.

RESULTS

The RF model achieved the highest BAC of 78.9%, closely followed by SVM (77.7%), LR (77.5%) and EBM (77.1%). Across all models, age, diagnosis (tumour type), functional features, and first treatment were top contributors to the prediction of one year survival. We used EBM and SHAP to explain model misclassifications and investigated the role of feature interactions in prognosis.

CONCLUSION

Interpretable models are a natural choice for the domain of predictive medicine. Intrinsically interpretable models, such as EBMs, may provide an advantage over traditional clinical assessment of brain tumour prognosis by weighting potential risk factors and their interactions that may be unknown to clinicians. An agreement between model predictions and clinical knowledge is essential for establishing trust in the models decision making process, as well as trust that the model will make accurate predictions when applied to new data.

An overview of machine learning methods in enabling IoMT-based epileptic seizure detection

The healthcare industry is rapidly automating, in large part because of the Internet of Things (IoT). The sector of the IoT devoted to medical research is sometimes called the Internet of Medical Things (IoMT). Data collecting and processing are the fundamental components of all IoMT applications. Machine learning (ML) algorithms must be included into IoMT immediately due to the vast quantity of data involved in healthcare and the value that precise forecasts have. In today's world, together, IoMT, cloud services, and ML techniques have become effective tools for solving many problems in the healthcare sector, such as epileptic seizure monitoring and detection. One of the biggest hazards to people's lives is epilepsy, a lethal neurological condition that has become a global issue. To prevent the deaths of thousands of epileptic patients each year, there is a critical necessity for an effective method for detecting epileptic seizures at their earliest stage. Numerous medical procedures, including epileptic monitoring, diagnosis, and other procedures, may be carried out remotely with the use of IoMT, which will reduce healthcare expenses and improve services. This article seeks to act as both a collection and a review of the different cutting-edge ML applications for epilepsy detection that are presently being combined with IoMT.

A multi-view co-training network for semi-supervised medical image-based prognostic prediction

Prognostic prediction has long been a hotspot in disease analysis and management, and the development of image-based prognostic prediction models has significant clinical implications for current personalized treatment strategies. The main challenge in prognostic prediction is to model a regression problem based on censored observations, and semi-supervised learning has the potential to play an important role in improving the utilization efficiency of censored data. However, there are yet few effective semi-supervised paradigms to be applied. In this paper, we propose a semi-supervised co-training deep neural network incorporating a support vector regression layer for survival time estimation (Co-DeepSVS) that improves the efficiency in utilizing censored data for prognostic prediction. First, we introduce a support vector regression layer in deep neural networks to deal with censored data and directly predict survival time, and more importantly to calculate the labeling confidence of each case. Then, we apply a semi-supervised multi-view co-training framework to achieve accurate prognostic prediction, where labeling confidence estimation with prior knowledge of pseudo time is conducted for each view. Experimental results demonstrate that the proposed Co-DeepSVS has a promising prognostic ability and surpasses most widely used methods on a multi-phase CT dataset. Besides, the introduction of SVR layer makes the model more robust in the presence of follow-up bias.

Prognostic Models Using Machine Learning Algorithms and Treatment Outcomes of Occult Breast Cancer Patients

BACKGROUND

Occult breast cancer (OBC) is an uncommon malignant tumor and the prognosis and treatment of OBC remain controversial. Currently, there exists no accurate prognostic clinical model for OBC, and the treatment outcomes of chemotherapy and surgery in its different molecular subtypes are still unknown.

METHODS

The SEER database provided the data used for this study's analysis (2010-2019). To identify the prognostic variables for patients with ODC, we conducted Cox regression analysis and constructed prognostic models using six machine learning algorithms to predict overall survival (OS) of OBC patients. A series of validation methods, including calibration curve and area under the curve (AUC value) of receiver operating characteristic curve (ROC) were employed to validate the accuracy and reliability of the logistic regression (LR) models. The effectiveness of clinical application of the predictive models was validated using decision curve analysis (DCA). We also investigated the role of chemotherapy and surgery in OBC patients with different molecular subtypes, with the help of K-M survival analysis as well as propensity score matching, and these results were further validated by subgroup Cox analysis.

RESULTS

The LR models performed best, with high precision and applicability, and they were proved to predict the OS of OBC patients in the most accurate manner (test set: 1-year AUC = 0.851, 3-year AUC = 0.790 and 5-year survival AUC = 0.824). Interestingly, we found that the N1 and N2 stage OBC patients had more favorable prognosis than N0 stage patients, but the N3 stage was similar to the N0 stage (OS: N0 vs. N1, HR = 0.6602, 95%CI 0.4568-0.9542, p < 0.05; N0 vs. N2, HR = 0.4716, 95%CI 0.2351-0.9464, p < 0.05; N0 vs. N3, HR = 0.96, 95%CI 0.6176-1.5844, p = 0.96). Patients aged >80 and distant metastases were also independent prognostic factors for OBC. In terms of treatment, our multivariate Cox regression analysis discovered that surgery and radiotherapy were both independent protective variables for OBC patients, but chemotherapy was not. We also found that chemotherapy significantly improved both OS and breast cancer-specific survival (BCSS) only in the HR-/HER2+ molecular subtype (OS: HR = 0.15, 95%CI 0.037-0.57, p < 0.01; BCSS: HR = 0.027, 95%CI 0.027-0.81, p < 0.05). However, surgery could help only the HR-/HER2+ and HR+/HER2- subtypes improve prognosis.

CONCLUSIONS

We analyzed the clinical features and prognostic factors of OBC patients; meanwhile, machine learning prognostic models with high precision and applicability were constructed to predict their overall survival. The treatment results in different molecular subtypes suggested that primary surgery might improve the survival of HR+/HER2- and HR-/HER2+ subtypes, however, only the HR-/HER2+ subtype could benefit from chemotherapy. The necessity of surgery and chemotherapy needs to be carefully considered for OBC patients with other subtypes.

Comprehensive circulating microRNA profile as a supersensitive biomarker for early-stage lung cancer screening

PURPOSE

 Less-invasive early diagnosis of lung cancer is essential for improving patient survival rates. The purpose of this study is to demonstrate that serum comprehensive miRNA profile is high sensitive biomarker to early-stage lung cancer in direct comparison to the conventional blood biomarker using next-generation sequencing (NGS) technology combined with automated machine learning (AutoML).

METHODS

We first evaluated the reproducibility of our measurement system using Pearson's correlation coefficients between samples derived from a single pooled RNA sample. To generate comprehensive miRNA profile, we performed NGS analysis of miRNAs in 262 serum samples. Among the discovery set (57 patients with lung cancer and 57 healthy controls), 1123 miRNA-based diagnostic models for lung cancer detection were constructed and screened using AutoML technology. The diagnostic faculty of the best performance model was evaluated by inspecting the validation samples (74 patients with lung cancer and 74 healthy controls).

RESULTS

The Pearson's correlation coefficients between samples derived from the pooled RNA sample ≥ 0.98. In the validation analysis, the best model showed a high AUC score (0.98) and a high sensitivity for early stage lung cancer (85.7%, n = 28). Furthermore, in comparison to carcinoembryonic antigen (CEA), a conventional blood biomarker for adenocarcinoma, the miRNA-based model showed higher sensitivity for early-stage lung adenocarcinoma (CEA, 27.8%, n = 18; miRNA-based model, 77.8%, n = 18).

CONCLUSION

The miRNA-based diagnostic model showed a high sensitivity for lung cancer, including early-stage disease. Our study provides the experimental evidence that serum comprehensive miRNA profile can be a highly sensitive blood biomarker for early-stage lung cancer.

Machine-learning predicts time-series prognosis factors in metastatic prostate cancer patients treated with androgen deprivation therapy

Machine learning technology is expected to support diagnosis and prognosis prediction in medicine. We used machine learning to construct a new prognostic prediction model for prostate cancer patients based on longitudinal data obtained from age at diagnosis, peripheral blood and urine tests of 340 prostate cancer patients. Random survival forest (RSF) and survival tree were used for machine learning. In the time-series prognostic prediction model for metastatic prostate cancer patients, the RSF model showed better prediction accuracy than the conventional Cox proportional hazards model for almost all time periods of progression-free survival (PFS), overall survival (OS) and cancer-specific survival (CSS). Based on the RSF model, we created a clinically applicable prognostic prediction model using survival trees for OS and CSS by combining the values of lactate dehydrogenase (LDH) before starting treatment and alkaline phosphatase (ALP) at 120 days after treatment. Machine learning provides useful information for predicting the prognosis of metastatic prostate cancer prior to treatment intervention by considering the nonlinear and combined impacts of multiple features. The addition of data after the start of treatment would allow for more precise prognostic risk assessment of patients and would be beneficial for subsequent treatment selection.

Evaluation of Matrix Metalloproteases by Artificial Intelligence Techniques in Negative Biopsies as New Diagnostic Strategy in Prostate Cancer

Usually, after an abnormal level of serum prostate-specific antigen (PSA) or digital rectal exam, men undergo a prostate needle biopsy. However, the traditional sextant technique misses 15-46% of cancers. At present, there are problems regarding disease diagnosis/prognosis, especially in patients' classification, because the information to be handled is complex and challenging to process. Matrix metalloproteases (MMPs) have high expression by prostate cancer (PCa) compared with benign prostate tissues. To assess the possible contribution to the diagnosis of PCa, we evaluated the expression of several MMPs in prostate tissues before and after PCa diagnosis using machine learning, classifiers, and supervised algorithms. A retrospective study was conducted on 29 patients diagnosed with PCa with previous benign needle biopsies, 45 patients with benign prostatic hyperplasia (BHP), and 18 patients with high-grade prostatic intraepithelial neoplasia (HGPIN). An immunohistochemical study was performed on tissue samples from tumor and non-tumor areas using specific antibodies against MMP -2, 9, 11, and 13, and the tissue inhibitor of MMPs -3 (TIMP-3), and the protein expression by different cell types was analyzed to which several automatic learning techniques have been applied. Compared with BHP or HGPIN specimens, epithelial cells (ECs) and fibroblasts from benign prostate biopsies before the diagnosis of PCa showed a significantly higher expression of MMPs and TIMP-3. Machine learning techniques provide a differentiable classification between these patients, with greater than 95% accuracy, considering ECs, being slightly lower when considering fibroblasts. In addition, evolutionary changes were found in paired tissues from benign biopsy to prostatectomy specimens in the same patient. Thus, ECs from the tumor zone from prostatectomy showed higher expressions of MMPs and TIMP-3 compared to ECs of the corresponding zone from the benign biopsy. Similar differences were found for expressions of MMP-9 and TIMP-3, between fibroblasts from these zones. The classifiers have determined that patients with benign prostate biopsies before the diagnosis of PCa showed a high MMPs/TIMP-3 expression by ECs, so in the zone without future cancer development as in the zone with future tumor, compared with biopsy samples from patients with BPH or HGPIN. Expression of MMP -2, 9, 11, and 13, and TIMP-3 phenotypically define ECs associated with future tumor development. Also, the results suggest that MMPs/TIMPs expression in biopsy tissues may reflect evolutionary changes from prostate benign tissues to PCa. Thus, these findings in combination with other parameters might contribute to improving the suspicion of PCa diagnosis.

Optimizing prognostic factors of five-year survival in gastric cancer patients using feature selection techniques with machine learning algorithms: a comparative study

BACKGROUND

Gastric cancer is the most common malignant tumor worldwide and a leading cause of cancer deaths. This neoplasm has a poor prognosis and heterogeneous outcomes. Survivability prediction may help select the best treatment plan based on an individual's prognosis. Numerous clinical and pathological features are generally used in predicting gastric cancer survival, and their influence on the survival of this cancer has not been fully elucidated. Moreover, the five-year survivability prognosis performances of feature selection methods with machine learning (ML) classifiers for gastric cancer have not been fully benchmarked. Therefore, we adopted several well-known feature selection methods and ML classifiers together to determine the best-paired feature selection-classifier for this purpose.

METHODS

This was a retrospective study on a dataset of 974 patients diagnosed with gastric cancer in the Ayatollah Talleghani Hospital, Abadan, Iran. First, four feature selection algorithms, including Relief, Boruta, least absolute shrinkage and selection operator (LASSO), and minimum redundancy maximum relevance (mRMR) were used to select a set of relevant features that are very informative for five-year survival prediction in gastric cancer patients. Then, each feature set was fed to three classifiers: XG Boost (XGB), hist gradient boosting (HGB), and support vector machine (SVM) to develop predictive models. Finally, paired feature selection-classifier methods were evaluated to select the best-paired method using the area under the curve (AUC), accuracy, sensitivity, specificity, and f1-score metrics.

RESULTS

The LASSO feature selection algorithm combined with the XG Boost classifier achieved an accuracy of 89.10%, a specificity of 87.15%, a sensitivity of 89.42%, an AUC of 89.37%, and an f1-score of 90.8%. Tumor stage, history of other cancers, lymphatic invasion, tumor site, type of treatment, body weight, histological type, and addiction were identified as the most significant factors affecting gastric cancer survival.

CONCLUSIONS

This study proved the worth of the paired feature selection-classifier to identify the best path that could augment the five-year survival prediction in gastric cancer patients. Our results were better than those of previous studies, both in terms of the time required to form the models and the performance measurement criteria of the algorithms. These findings may be very promising and can, therefore, inform clinical decision-making and shed light on future studies.

Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer

Established prognostic tests based on limited numbers of transcripts can identify high-risk breast cancer patients yet are approved only for individuals presenting with specific clinical features or disease characteristics. Deep learning algorithms could hold potential for stratifying patient cohorts based on full transcriptome data, yet the development of robust classifiers is hampered by the number of variables in omics datasets typically far exceeding the number of patients. To overcome this hurdle, we propose a classifier based on a data augmentation pipeline consisting of a Wasserstein generative adversarial network (GAN) with gradient penalty and an embedded auxiliary classifier to obtain a trained GAN discriminator (T-GAN-D). Applied to 1244 patients of the METABRIC breast cancer cohort, this classifier outperformed established breast cancer biomarkers in separating low- from high-risk patients (disease specific death, progression or relapse within 10 years from initial diagnosis). Importantly, the T-GAN-D also performed across independent, merged transcriptome datasets (METABRIC and TCGA-BRCA cohorts), and merging data improved overall patient stratification. In conclusion, the reiterative GAN-based training process allowed generating a robust classifier capable of stratifying low- vs high-risk patients based on full transcriptome data and across independent and heterogeneous breast cancer cohorts.

Utility of artificial intelligence to identify antihyperglycemic agents poisoning in the USA: introducing a practical web application using National Poison Data System (NPDS)

Clinical effects of antihyperglycemic agents poisoning may overlap each other. So, distinguishing exposure to these pharmaceutical drugs may take work. This study examined the application of machine learning techniques in identifying antihyperglycemic agent exposure using the national poisoning database in the USA. In this study, the data of single exposure due to Biguanides and Sulfonylureas (n=6183) was requested from the National Poison Data System (NPDS) for 2014-2018. We have tried five machine learning models (random forest classifier, k-nearest neighbors, Xgboost classifier, logistic regression, neural network Keras). For the multiclass classification modeling, we have divided the dataset into two parts: train (75%) and test (25%). The performance metrics used were accuracy, specificity, precision, recall, and F1-score. The algorithms used to get the classification results of different models to diagnose antihyperglycemic agents were very accurate. The accuracy of our model in determining these two antihyperglycemic agents was 91-93%. The precision-recall curve showed average precision of 0.91, 0.97, 0.97, and 0.98 for k-nearest neighbors, logistic regression, random forest, and XGB, respectively. The logistic regression, random forest, and XGB had the highest AUC (AUC=0.97) among both biguanides and sulfonylureas groups. The negative predictive values (NPV) for all the models were between 89 and 93%. We introduced a practical web application to help physicians distinguish between these agents. Despite variations in accuracy among the different types of algorithms used, all of them could accurately determine the specific exposure to biguanides and sulfonylureas retrospectively. Machine learning can distinguish antihyperglycemic agents, which may be useful for physicians without any background in medical toxicology. Besides, Our suggested ML-based Web application might help physicians in their diagnosis.

Mechanistic modeling of metastatic relapse in early breast cancer to investigate the biological impact of prognostic biomarkers

BACKGROUND AND OBJECTIVE

Estimating the risk of metastatic relapse is a major challenge to decide adjuvant treatment options in early-stage breast cancer (eBC). To date, distant metastasis-free survival (DMFS) analysis mainly relies on classical, agnostic, statistical models (e.g., Cox regression). Instead, we propose here to derive mechanistic models of DMFS.

METHODS

The present series consisted of eBC patients who did not receive adjuvant systemic therapy from three datasets, composed respectively of 692 (Bergonié Institute), 591 (Paoli-Calmettes Institute, IPC), and 163 (Public Hospital Marseille, AP-HM) patients with routine clinical annotations. The last dataset also contained expression of three non-routine biomarkers. Our mechanistic model of DMFS relies on two mathematical parameters that represent growth (α) and dissemination (μ). We identified their population distributions using mixed-effects modeling. Critically, we propose a novel variable selection procedure allowing to: (i) identify the association of biological parameters with either α, μ or both, and (ii) generate an optimal candidate model for DMFS prediction.

RESULTS

We found that Ki67 and Thymidine Kinase-1 were associated with α, and nodal status and Plasminogen Activator Inhibitor-1 with μ. The predictive performances of the model were excellent in calibration but moderate in discrimination, with c-indices of 0.72 (95% CI [0.48, 0.95], AP-HM), 0.63 ([0.44, 0.83], Bergonié) and 0.60 (95% CI [0.54, 0.80], IPC).

CONCLUSIONS

Overall, we demonstrate that our novel method combining mechanistic and advanced statistical modeling is able to unravel the biological roles of clinicopathological parameters from DMFS data.

Predicting mechanical properties of silk from its amino acid sequences via machine learning

The silk fiber is increasingly being sought for its superior mechanical properties, biocompatibility, and eco-friendliness, making it promising as a base material for various applications. One of the characteristics of protein fibers, such as silk, is that their mechanical properties are significantly dependent on the amino acid sequence. Numerous studies have been conducted to determine the specific relationship between the amino acid sequence of silk and its mechanical properties. Still, the relationship between the amino acid sequence of silk and its mechanical properties is yet to be clarified. Other fields have adopted machine learning (ML) to establish a relationship between the inputs, such as the ratio of different input material compositions and the resulting mechanical properties. We have proposed a method to convert the amino acid sequence into numerical values for input and succeeded in predicting the mechanical properties of silk from its amino acid sequences. Our study sheds light on predicting mechanical properties of silk fiber from respective amino acid sequences.