Machine learning and deep learning methods that use omics data for metastasis prediction

Optimizing prediction of metastasis among colorectal cancer patients using machine learning technology

BACKGROUND AND AIM

Colorectal cancer is among the most prevalent and deadliest cancers. Early prediction of metastasis in patients with colorectal cancer is crucial in preventing it from the advanced stages and enhancing the prognosis among these patients. So far, previous studies have been conducted to predict metastasis in colorectal cancer patients using clinical data. The current research attempts to leverage a combination of demographic, lifestyle, nutritional, and clinical factors, such as diagnostic and therapeutical factors, to construct an ML model with more predictive insights and generalizability than previous ones.

MATERIALS AND METHODS

In this retrospective study, we used 1156 CRC patients referred to the Masoud internal clinic in Tehran City from January 2017 to December 2023. The chosen machine learning algorithms, including LightGBM, XG-Boost, random forest, artificial neural network, support vector machine, decision tree, K-Nearest Neighbor and logistic regression, were utilized to establish prediction models for predicting metastasis among colorectal cancer patients. We also assessed features based on the best-performing model to improve clinical usability. To show the generalizability of the established prediction model for predicting CRC metastasis, we leveraged the data of 115 CRC patients from Imam Khomeini Hospital in Sari City. We assessed the predictive ability of LightGBM as the best-performing model based on external data.

RESULTS

The LightGBM model with a PPV of 97.32%, NPV of 84.67%, sensitivity of 83.14%, specificity of 93.14%, accuracy of 88.14%, F1-score of 87.51%, and an AU-ROC of 0.9 [Formula: see text]0.01 obtained satisfactory performance for prediction purposes on this topic. Factors including the history of IBD, family history of CRC, number of lymph nodes involved, fruit intake, and tumor size were considered as more strengthful predictors for metastasis in colorectal cancer and clinical usability. The external validation cohort showed a PPV of 0.8, NPV of 0.85, sensitivity of 0.78, specificity of 0.86, accuracy of 0.834, F1-score of 0.795, and AU-ROC of 0.77[Formula: see text]0.03, demonstrating satisfactory generalizability when leveraging external data from other clinical settings.

CONCLUSION

The current empirical results indicated that LighGBM has predictive competency that can be leveraged by physicians in clinical environments for early prediction of metastasis and enhanced prognosis in patients with colorectal cancer.

CLINICAL TRIAL NUMBER

Not applicable.

Serum Immune-Response Protein Biomarkers Based on Olink Technology for Diagnosis of Ischemic Stroke

The immune response plays a crucial role in the treatment of ischemic stroke (IS). Our primary objective was to explore immune proteins related to stroke and to develop a noninvasive diagnostic panel. We used the high-throughput Olink immunoassay platform to quantitatively measure 92 proteins in the serum of 88 patients with IS and 88 controls. We first selected feature proteins using least absolute shrinkage and selection operator (LASSO), random forest (RF), and support vector machine (SVM), and then modeled them for external validation of IS. In this study, we found that 53 proteins exhibited significant differences in the IS compared to the control group. We selected GLB1, PRDX5, DDX58, and CLEC4C as potential protein biomarkers to differentiate IS from the control group using LASSO, RF, and SVM. The diagnostic model, which included these four proteins, demonstrated excellent performance in validation data sets, achieving an AUC value of 0.899 (95%CI: 0.848-0.950). Our findings offer valuable insights into both the immune response and the diagnosis of IS. These results offer a novel approach to clinical decision-making in the diagnosis and treatment of IS.

Development and validation of a new diagnostic prediction model for NAFLD based on machine learning algorithms in NHANES 2017-2020.3

AIMS

Nonalcoholic fatty liver disease (NAFLD) is a multisystem disease that can trigger the metabolic syndrome. Early prevention and treatment of NAFLD is still a huge challenge for patients and clinicians. The aim of this study was to develop and validate machine learning (ML)-based predictive models. The model with optimal performance would be developed as a set of simple arithmetic tools for predicting the risk of NAFLD individually.

METHODS

Statistical analyses were performed in 2428 individuals extracted from the National Health and Nutrition Examination Survey (NHANES, cycle 2017-2020.3) database. Feature variables were selected by the least absolute shrinkage and selection operator (LASSO) regression. Seven ML algorithms, including logistic regression (LR), decision tree (DT), random forest (RF), extreme gradient boosting (XGB), K-nearest neighbor (KNN), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP), were used to construct models based on the feature variables and evaluate their performance. The model with the best performance was transformed into a diagnostic predictive nomogram (DPN). The DPN was developed into an online calculator and an Excel algorithm tool. Receiver operating characteristic (ROC) curve, decision curve analysis (DCA), and subgroup analyses were used to compare and assess the predictive abilities of the DPN and six existing NAFLD predictive models, including the ZJU index, the hepatic steatosis index (HSI), the triglyceride-glucose index (TyG), the Framingham steatosis index (FSI), the fatty liver index (FLI), and the visceral adiposity index (VAI).

RESULTS

Among the 2428 participants, the prevalence of NAFLD was 47.45%. LASSO regression identified eight variables from 39 variables, including body mass index (BMI), waist circumference (WC), alanine aminotransferase (ALT), triglyceride (TG), diabetes, hypertension, uric acid (UA), and race. Among the models constructed by the seven algorithms mentioned above, the LR-based model performed the best, demonstrating outstanding performance in terms of area under the curve (AUC, 0.823), accuracy (0.754), precision (0.768), specificity (0.804), and positive predictive value (0.768). It was then transformed into the DPN, which was successfully developed as an online calculator and an Excel algorithm tool. The diagnostic accuracy (AUC 0.856, 95% confidence interval (CI) 0.839-0.874, and AUC 0.823, 95% CI 0.793-0.854, respectively) and net clinical benefit of DPN in the training and validation sets were superior to those of the ZJU, HSI, TyG, FSI, FLI, and VAI. The results were maintained in subgroup analyses.

CONCLUSIONS

The LR model based on ML was developed, exhibiting good performance. DPN can be used as an individualized tool for rapid detection of NAFLD.

M-NET: Transforming Single Nucleotide Variations Into Patient Feature Images for the Prediction of Prostate Cancer Metastasis and Identification of Significant Pathways

High-performance prediction of prostate cancer metastasis based on single nucleotide variations remains a challenge. Therefore, we developed a novel biologically informed deep learning framework, named M-NET, for the prediction of prostate cancer metastasis. Within the framework, we transformed single nucleotide variations into patient feature images that are optimal for fitting convolutional neural networks. Moreover, we identified significant pathways associated with the metastatic status. The experimental results showed that M-NET significantly outperformed other comparison methods based on single nucleotide variations, achieving improvements in accuracy, precision, recall, F1-score, area under the receiver operating characteristics curve, and area under the precision-recall curve by 6.3%, 8.4%, 5.1%, 0.070, 0.041, and 0.026, respectively. Furthermore, M-NET identified some important pathways associated with the metastatic status, such as signaling by the hedgehog pathway. In summary, compared with other comparative methods, M-NET exhibited a better performance in the prediction of prostate cancer metastasis.

Investigating factors influencing quality of life in thyroid eye disease: insight from machine learning approaches

Aims

Thyroid eye disease (TED) is an autoimmune orbital disorder that diminishes the quality of life (QOL) in affected individuals. Graves' ophthalmopathy (GO)-QOL questionnaire effectively assesses TED's effect on patients. This study aims to investigate the factors influencing visual functioning (QOL-VF) and physical appearance (QOL-AP) scores in Chinese TED patients using innovative data analysis methods.

Methods

This cross-sectional study included 211 TED patients whose initial visit to our clinic was from July 2022 to March 2023. Patients with previous ophthalmic surgery or concurrent severe diseases were excluded. GO-QOL questionnaires, detailed medical histories and clinical examinations were collected. The distribution of GO-QOL scores was analyzed, and linear regression and machine learning algorithms were utilized.

Results

The median QOL-VF and QOL-AP scores were 64.29 and 62.5, respectively. Multivariate linear regression analysis revealed age (P = 0.013), ocular motility pain (P = 0.012), vertical strabismus (P < 0.001) and diplopia scores as significant predictors for QOL-VF. For QOL-AP, gender (P = 0.013) and clinical activity (P = 0.086) were significant. The XGBoost model demonstrated superior performance, with an R2 of 0.872 and a root mean square error of 11.083. Shapley additive explanations (SHAP) analysis highlighted the importance of vertical strabismus, diplopia score and age in influencing QOL-VF and age, clinical activity and sex in QOL-AP.

Conclusion

TED significantly affects patient QOL. The study highlights the efficacy of XGBoost and SHAP analyses in identifying key factors influencing the QOL in TED patients. Identifying effective interventions and considering specific demographic characteristics are essential to improving the QOL of patients with TED.

Machine learning and artificial intelligence: Enabling the clinical translation of atomic force microscopy-based biomarkers for cancer diagnosis

The influence of biomechanics on cell function has become increasingly defined over recent years. Biomechanical changes are known to affect oncogenesis; however, these effects are not yet fully understood. Atomic force microscopy (AFM) is the gold standard method for measuring tissue mechanics on the micro- or nano-scale. Due to its complexity, however, AFM has yet to become integrated in routine clinical diagnosis. Artificial intelligence (AI) and machine learning (ML) have the potential to make AFM more accessible, principally through automation of analysis. In this review, AFM and its use for the assessment of cell and tissue mechanics in cancer is described. Research relating to the application of artificial intelligence and machine learning in the analysis of AFM topography and force spectroscopy of cancer tissue and cells are reviewed. The application of machine learning and artificial intelligence to AFM has the potential to enable the widespread use of nanoscale morphologic and biomechanical features as diagnostic and prognostic biomarkers in cancer treatment.

OligoM-Cancer: A multidimensional information platform for deep phenotyping of heterogenous oligometastatic cancer

Patients with oligometastatic cancer (OMC) exhibit better response to local therapeutic interventions and a more treatable tendency than those with polymetastatic cancers. However, studies on OMC are limited and lack effective integration for systematic comparison and personalized application, and the diagnosis and precise treatment of OMC remain controversial. The application of large language models in medicine remains challenging because of the requirement of high-quality medical data. Moreover, these models must be enhanced using precise domain-specific knowledge. Therefore, we developed the OligoM-Cancer platform (http://oligo.sysbio.org.cn), pioneering knowledge curation that depicts various aspects of oligometastases spectrum, including markers, diagnosis, prognosis, and therapy choices. A user-friendly website was developed using HTML, FLASK, MySQL, Bootstrap, Echarts, and JavaScript. This platform encompasses comprehensive knowledge and evidence of phenotypes and their associated factors. With 4059 items of literature retrieved, OligoM-Cancer includes 1345 valid publications and 393 OMC-associated factors. Additionally, the included clinical assistance tools enhance the interpretability and credibility of clinical translational practice. OligoM-Cancer facilitates knowledge-guided modeling for deep phenotyping of OMC and potentially assists large language models in supporting specialised oligometastasis applications, thereby enhancing their generalization and reliability.

A fatty acid metabolism-related genes model for predicting the prognosis and immunotherapy effect of lung adenocarcinoma

ObjectiveLung adenocarcinoma (LUAD) is a common and highly heterogeneous malignancy cancer with increasing morbidity and mortality. Dysregulation of fatty acid metabolism (FAM) has been identified as a key regulator of LUAD progression. Our purpose was to establish a risk model of FAM-related genes to provide a reference for the prognosis prediction of LUAD.MethodsFirstly, we screened FAM-related differentially expressed genes (DEGs) based on the Cancer Genome Atlas (TCGA) database, and identified the prognostic signatures by Cox-regression analysis. The least absolute shrinkage and selection operator algorithm (LASSO) was used to obtain the formula for risk model. And the analysis of Gene Expression Omnibus (GEO) dataset used to verify. Nomogram was produced for individualized prediction in clinical treatment. Immune cell function and drug sensitivity analysis used to screen potential therapeutic drugs.ResultsPatients in low-risk had better overall survival (OS). High-risk patients exhibit higher TMB and lower TIDE scores, and they are more likely to benefit from immunotherapy. The analysis of GEO verified that risk model has a high prediction accuracy.ConclusionThe risk model based on 17 FAM-related DEGs is of great value in predicting the prognosis of LUAD, and these prognostic signatures may be potential therapeutic targets for LUAD.

Artificial intelligence in skeletal metastasis imaging

In the field of metastatic skeletal oncology imaging, the role of artificial intelligence (AI) is becoming more prominent. Bone metastasis typically indicates the terminal stage of various malignant neoplasms. Once identified, it necessitates a comprehensive revision of the initial treatment regime, and palliative care is often the only resort. Given the gravity of the condition, the diagnosis of bone metastasis should be approached with utmost caution. AI techniques are being evaluated for their efficacy in a range of tasks within medical imaging, including object detection, disease classification, region segmentation, and prognosis prediction in medical imaging. These methods offer a standardized solution to the frequently subjective challenge of image interpretation.This subjectivity is most desirable in bone metastasis imaging. This review describes the basic imaging modalities of bone metastasis imaging, along with the recent developments and current applications of AI in the respective imaging studies. These concrete examples emphasize the importance of using computer-aided systems in the clinical setting. The review culminates with an examination of the current limitations and prospects of AI in the realm of bone metastasis imaging. To establish the credibility of AI in this domain, further research efforts are required to enhance the reproducibility and attain robust level of empirical support.

OmicsFootPrint: a framework to integrate and interpret multi-omics data using circular images and deep neural networks

The OmicsFootPrint framework addresses the need for advanced multi-omics data analysis methodologies by transforming data into intuitive two-dimensional circular images and facilitating the interpretation of complex diseases. Utilizing deep neural networks and incorporating the SHapley Additive exPlanations algorithm, the framework enhances model interpretability. Tested with The Cancer Genome Atlas data, OmicsFootPrint effectively classified lung and breast cancer subtypes, achieving high area under the curve (AUC) scores-0.98 ± 0.02 for lung cancer subtype differentiation and 0.83 ± 0.07 for breast cancer PAM50 subtypes, and successfully distinguished between invasive lobular and ductal carcinomas in breast cancer, showcasing its robustness. It also demonstrated notable performance in predicting drug responses in cancer cell lines, with a median AUC of 0.74, surpassing nine existing methods. Furthermore, its effectiveness persists even with reduced training sample sizes. OmicsFootPrint marks an enhancement in multi-omics research, offering a novel, efficient and interpretable approach that contributes to a deeper understanding of disease mechanisms.

Association analysis of gut microbiota with LDL-C metabolism and microbial pathogenicity in colorectal cancer patients

BACKGROUND

Colorectal cancer (CRC) is the most common gastrointestinal malignancy worldwide, with obesity-induced lipid metabolism disorders playing a crucial role in its progression. A complex connection exists between gut microbiota and the development of intestinal tumors through the microbiota metabolite pathway. Metabolic disorders frequently alter the gut microbiome, impairing immune and cellular functions and hastening cancer progression.

METHODS

This study thoroughly examined the gut microbiota through 16S rRNA sequencing of fecal samples from 181 CRC patients, integrating preoperative Low-density lipoprotein cholesterol (LDL-C) levels and RNA sequencing data. The study includes a comparison of microbial diversity, differential microbiological analysis, exploration of the associations between microbiota, tumor microenvironment immune cells, and immune genes, enrichment analysis of potential biological functions of microbe-related host genes, and the prediction of LDL-C status through microorganisms.

RESULTS

The analysis revealed that differences in α and β diversity indices of intestinal microbiota in CRC patients were not statistically significant across different LDL-C metabolic states. Patients exhibited varying LDL-C metabolic conditions, leading to a bifurcation of their gut microbiota into two distinct clusters. Patients with LDL-C metabolic irregularities had higher concentrations of twelve gut microbiota, which were linked to various immune cells and immune-related genes, influencing tumor immunity. Under normal LDL-C metabolic conditions, the protective microorganism Anaerostipes_caccae was significantly negatively correlated with the GO Biological Process pathway involved in the negative regulation of the unfolded protein response in the endoplasmic reticulum. Both XGBoost and MLP models, developed using differential gut microbiota, could forecast LDL-C levels in CRC patients biologically.

CONCLUSIONS

The intestinal microbiota in CRC patients influences the LDL-C metabolic status. With elevated LDL-C levels, gut microbiota can regulate the function of immune cells and gene expression within the tumor microenvironment, affecting cancer-related pathways and promoting CRC progression. LDL-C and its associated gut microbiota could provide non-invasive markers for clinical evaluation and treatment of CRC patients.

Identification of metabolic biomarkers in idiopathic pulmonary arterial hypertension using targeted metabolomics and bioinformatics analysis

Pulmonary arterial hypertension (PAH) is a life-threatening disease with a poor prognosis, and metabolic abnormalities play a critical role in its development. This study used metabolomics, machine learning algorithms and bioinformatics to screen for potential metabolic biomarkers associated with the diagnosis of PAH. In this study, plasma samples were collected from 17 patients diagnosed with idiopathic pulmonary arterial hypertension (IPAH) and 20 healthy controls. Plasma metabolomic profiling was performed by high-performance liquid chromatography-mass spectrometry. Gene profiles of PAH patients were obtained from the GEO database. Key differentially expressed metabolites (DEMs) and metabolism-related genes were subsequently identified using machine learning algorithms. Twenty differential plasma metabolites associated with IPAH were identified (VIP score > 1 and p < 0 0.05), and enrichment analysis revealed the arginine biosynthesis pathway as the most altered pathway. Using machine learning models, including least absolute shrinkage and selection operator (LASSO), random forest (RF) and support vector machine (SVM), we extracted key metabolites that correlated with clinical phenotypes. Our results suggested that five metabolites, kynurenine, homoserine, tryptophan, AMP, and spermine, are potential biomarkers for IPAH. Bioinformatics analysis also identified 3 metabolism-related genes, MAPK6, SLC7A11 and CDC42BPA, that are strongly correlated with pulmonary hypertension, demonstrating strong predictive power and clinical relevance. Our findings revealed some key genes associated with metabolism in PH, and provided crucial information about complex metabolic reprogramming signals and may lead to the identification of useful metabolic biomarkers for the diagnosis of PAH.

Machine Learning for Dynamic Prognostication of Patients With Hepatocellular Carcinoma Using Time-Series Data: Survival Path Versus Dynamic-DeepHit HCC Model

Objectives

Patients with intermediate or advanced hepatocellular carcinoma (HCC) require repeated disease monitoring, prognosis assessment and treatment planning. In 2018, a novel machine learning methodology "survival path" (SP) was developed to facilitate dynamic prognosis prediction and treatment planning. One year after, a deep learning approach called Dynamic Deephit was developed. The performance of the two state-of-art models in dynamic prognostication have not been compared.

Methods

We trained and tested the SP and Dynamic DeepHit models in a large cohort of 2511 HCC patients using time-series data. The time-series data were converted into data of time slices, with an interval of three months. The time-dependent c-index for OS at given prediction time (t = 1, 6, 12, 18 months) and evaluation time (∆t = 3, 6, 9, 12, 18, 24, 36, 48 months) were compared.

Results

The comparison between SP model and Dynamic DeepHit-HCC model showed the latter had significant better performance at the time of initial admission. The time-dependent c-index of Dynamic DeepHit-HCC model gradually decreased with the extension of time (from 0.756 to 0.639 in the training set; from 0.787 to 0.661 in internal testing set; from 0.725 to 0.668 in multicenter testing set); while the time-dependent c-index of SP model displayed an increased trend (from 0.665 to 0.748 in the training set; from 0.608 to 0.743 in internal testing set; from 0.643 to 0.720 in multicenter testing set). When the prediction time comes to 6 months or later since initial treatment, the survival path model outperformed the dynamic DeepHit model at late evaluation times (∆t > 12 months).

Conclusions

This research highlighted the unique strengths of both models. The SP model had advantage in long term prediction while the Dynamic DeepHit-HCC model had advantages in prediction at near time points. Fine selection of models is needed in dealing with different scenarios.

Interpretable machine learning based on CT-derived extracellular volume fraction to predict pathological grading of hepatocellular carcinoma

PURPOSE

To develop a non-invasive auxiliary assessment method based on CT-derived extracellular volume (ECV) to predict the pathological grading (PG) of hepatocellular carcinoma (HCC).

METHODS

The study retrospectively analyzed 238 patients who underwent HCC resection surgery between January 2013 and April 2023. Six machine learning algorithms were employed to construct predictive models for HCC PG: logistic regression, extreme gradient boosting, Light Gradient Boosting Machine (LightGBM), random forest, adaptive boosting, and Gaussian naive Bayes. Model performance was evaluated using receiver operating characteristic curve analysis, including area under the curve (AUC), sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and F1 score. Calibration plots were used for visual evaluation of model calibration. Clinical decision curve analysis was performed to assess potential clinical utility by calculating net benefit.

RESULTS

166 patients from Hospital A were allocated to the training set, while 72 patients from Hospital B (constituting 30.25% of the total sample) were assigned to the test set. The model achieved an AUC of 1.000 (95%CI: 1.000-1.000) in the training set and 0.927 (95%CI: 0.837-0.999) in the validation set, respectively. Ultimately, the model achieved an AUC of 0.909 (95%CI: 0.837-0.980) in the test set, with an accuracy of 0.778, sensitivity of 0.906, specificity of 0.789, negative predictive value of 0.556, and F1 score of 0.908.

CONCLUSION

This study successfully developed and validated a non-invasive auxiliary assessment method based on CT-derived ECV to predict the HCC PG, providing important supplementary information for clinical decision-making.

Early detection of pancreatic cancer by comprehensive serum miRNA sequencing with automated machine learning

BACKGROUND

Pancreatic cancer is often diagnosed at advanced stages, and early-stage diagnosis of pancreatic cancer is difficult because of nonspecific symptoms and lack of available biomarkers.

METHODS

We performed comprehensive serum miRNA sequencing of 212 pancreatic cancer patient samples from 14 hospitals and 213 non-cancerous healthy control samples. We randomly classified the pancreatic cancer and control samples into two cohorts: a training cohort (N = 185) and a validation cohort (N = 240). We created ensemble models that combined automated machine learning with 100 highly expressed miRNAs and their combination with CA19-9 and validated the performance of the models in the independent validation cohort.

RESULTS

The diagnostic model with the combination of the 100 highly expressed miRNAs and CA19-9 could discriminate pancreatic cancer from non-cancer healthy control with high accuracy (area under the curve (AUC), 0.99; sensitivity, 90%; specificity, 98%). We validated high diagnostic accuracy in an independent asymptomatic early-stage (stage 0-I) pancreatic cancer cohort (AUC:0.97; sensitivity, 67%; specificity, 98%).

CONCLUSIONS

We demonstrate that the 100 highly expressed miRNAs and their combination with CA19-9 could be biomarkers for the specific and early detection of pancreatic cancer.

Comparing Regularized Logistic Regression and Stochastic Gradient Descent in Predicting Drug-Gene Interactions of Inhibitors of Apoptosis Proteins in Periodontitis

OBJECTIVE

Periodontitis, characterized by inflammation linked to apoptosis dysregulation, underscores the role of inhibitors of apoptosis proteins (IAPs) like survivin and cIAP1, implicated in disease progression and treatment resistance across various conditions. Our study aims to analyze the prediction of drug-gene interactions by machine learning techniques, combining regularized logistic regression and stochastic gradient descent (SGD) for efficient classification.

METHODS

Data from Probes-Drugs.org on IAP-based drug-protein interactions underwent rigorous annotation and outlier removal. A data robot tool trained machine learning models, regularized logistic regression and SGD (https://app.datarobot.com/new). Network analysis employed Cytoscape to construct and analyze the IAP network, identifying key hub nodes crucial in periodontitis pathogenesis.

RESULTS

The constructed IAP network comprised 376 nodes and 556 edges, revealing intricate drug-gene interactions with an average of 2957 neighbors per node. Ten hub nodes were identified as pivotal in regulating biological processes specific to periodontitis, suggesting their potential as therapeutic targets and biomarkers. Predictive models demonstrated high accuracy, with gradient descent achieving 93% and regularized logistic regression achieving 92% in identifying drug-gene interactions within the IAP network.

CONCLUSIONS

These findings highlight the utility of computational methods in elucidating molecular mechanisms underlying periodontitis, offering insights into potential therapeutic strategies targeting IAP-related pathways. Future research should focus on validating hub genes experimentally and integrating multi-omics data to advance precision medicine approaches in periodontitis treatment.

Research progress on machine algorithm prediction of liver cancer prognosis after intervention therapy

The treatment for liver cancer has transitioned from traditional surgical resection to interventional therapies, which have become increasingly popular among patients due to their minimally invasive nature and significant local efficacy. However, with advancements in treatment technologies, accurately assessing patient response and predicting long-term survival has become a crucial research topic. Over the past decade, machine algorithms have made remarkable progress in the medical field, particularly in hepatology and prognosis studies of hepatocellular carcinoma (HCC). Machine algorithms, including deep learning and machine learning, can identify prognostic patterns and trends by analyzing vast amounts of clinical data. Despite significant advancements, several issues remain unresolved in the prognosis prediction of liver cancer using machine algorithms. Key challenges and main controversies include effectively integrating multi-source clinical data to improve prediction accuracy, addressing data privacy and ethical concerns, and enhancing the transparency and interpretability of machine algorithm decision-making processes. This paper aims to systematically review and analyze the current applications and potential of machine algorithms in predicting the prognosis of patients undergoing interventional therapy for liver cancer, providing theoretical and empirical support for future research and clinical practice.

Metabolomic profiling of dengue infection: unraveling molecular signatures by LC-MS/MS and machine learning models

BACKGROUND & OBJECTIVE

The progression of dengue fever to severe dengue (SD) is a major public health concern that impairs the capacity of the medical system to predict and treat dengue patients. Hence, the present study used a metabolomic approach integrated with machine models to identify differentially expressed metabolites in patients with SD compared to nonsevere patients and healthy controls.

METHODS

Comprehensively, the plasma was collected at different clinical phases during dengue without warning signs (DWOW, N = 10), dengue with warning signs (DWW, N = 10), and SD (N = 10) at different stages [i.e., day of admission (DOA), day of defervescence (DOD), and day of convalescent (DOC)] in comparison to healthy control (HC). The samples were subjected to LC‒ESI‒MS/MS to identify metabolites. Statistical and machine learning analyses were performed using R and Python language. Further, biomarker, pathway and correlation analysis was performed to identify potential predictors of dengue.

RESULTS & CONCLUSION

A total of 423 metabolites were identified in all the study groups. Paired and unpaired t-tests revealed 14 highly differentially expressed metabolites between and across the dengue groups, with four metabolites (shikimic acid, ureidosuccinic acid, propionyl carnitine, and alpha-tocopherol) showing significant differences compared to HC. Furthermore, biomarker (ROC) analysis revealed 11 potential molecules with a significant AUC value of 1 that could serve as potential biomarkers for identifying different dengue clinical stages that are beneficial for predicting dengue disease outcomes. The logistic regression model revealed that S-adenosylhomocysteine, hypotaurine, and shikimic acid metabolites could be beneficial indicators for predicting severe dengue, with an accuracy and AUC of 0.75. The data showed that dengue infection is related to lipid metabolism, oxidative stress, inflammation, metabolomic adaptation, and virus manipulation. Moreover, the biomarkers had a significant correlation with biochemical parameters like platelet count, and hematocrit. These results shed some light on host-derived small-molecule biomarkers that are associated with dengue severity and novel insights into metabolomics mechanisms interlinked with disease severity.

Prognosis of colorectal cancer, prognostic index of immunogenic cell death associated genes in response to immunotherapy, and potential therapeutic effects of ferroptosis inducers

Introduction

This study leverages bioinformatics and medical big data to integrate datasets from the Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA), providing a comprehensive overview of immunogenic cell death (ICD)-related gene expression in colorectal cancer (CRC). The research aims to elucidate the molecular pathways and gene networks associated with ICD in CRC, with a focus on the therapeutic potential of cell death inducers, including ferroptosis agents, and their implications for precision medicine.

Methods

We conducted differential expression analysis and utilized advanced bioinformatic techniques to analyze ICD-related gene expression in CRC tissues. Unsupervised consensus clustering was applied to categorize CRC patients into distinct ICD-associated subtypes, followed by an in-depth immune microenvironment analysis and single-cell RNA sequencing to investigate immune responses and cell infiltration patterns. Experimental validation was performed to assess the impact of cell death inducers on ICD gene expression and their interaction with ferroptosis inducers in combination with other clinical drugs.

Results

Distinct ICD gene expression profiles were identified in CRC tissues, revealing molecular pathways and intricate gene networks. Unsupervised consensus clustering refined the CRC cohort into unique ICD-associated subtypes, each characterized by distinct clinical and immunological features. Immune microenvironment analysis and single-cell RNA sequencing revealed significant variations in immune responses and cell infiltration patterns across these subtypes. Experimental validation confirmed that cell death inducers directly affect ICD gene expression, highlighting their therapeutic potential. Additionally, combinatorial therapies with ferroptosis inducers and clinical drugs were shown to influence drug sensitivity and resistance in CRC.

Discussion

Our findings underscore the importance of ICD-related genes in CRC prognosis and therapeutic targeting. The study provides actionable insights into the efficacy of cell death-inducing therapies, particularly ferroptosis inducers, and their regulatory mechanisms in CRC. These discoveries support the development of precision medicine strategies targeting ICD genes and offer valuable guidance for translating these therapies into clinical practice, with the potential to enhance CRC treatment outcomes and patient survival.

Construction of an artificial neural network diagnostic model and investigation of immune cell infiltration characteristics for idiopathic pulmonary fibrosis

BACKGROUND

Idiopathic pulmonary fibrosis (IPF) is a severe lung condition, and finding better ways to diagnose and treat the disease is crucial for improving patient outcomes. Our study sought to develop an artificial neural network (ANN) model for IPF and determine the immune cell types that differed between the IPF and control groups.

METHODS

From the Gene Expression Omnibus (GEO) database, we first obtained IPF microarray datasets. To conduct protein-protein interaction (PPI) networks and enrichment analyses, differentially expressed genes (DEGs) were screened between tissues of patients with IPF and tissues of controls. Afterward, we identified the important feature genes associated with IPF using random forest (RF) analysis, and then constructed and validated a prediction ANN mode. In addition, the proportions of immune cells were quantified using cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT) analysis, which was performed on microarray datasets based on gene expression profiling.

RESULTS

A total of 11 downregulated and 36 upregulated DEGs were identified. PPI networks and enrichment analyses were carried out; the immune system and extracellular matrix were the subjects of the enrichments. Using RF analysis, the significant feature genes LRRC17, COMP, ASPN, CRTAC1, POSTN, COL3A1, PEBP4, IL13RA2, and CA4 were identified. The nine feature gene scores were integrated into the ANN to develop a diagnostic prediction model. The receiver operating characteristic (ROC) curves demonstrated the strong diagnostic ability of the ANN in predicting IPF in the training and testing sets. An analysis of IPF tissues in comparison to normal tissues revealed a reduction in the infiltration of natural killer cells resting, monocytes, macrophages M0, and neutrophils; conversely, the infiltration of T cells CD4 memory resting, mast cells, and macrophages M0 increased.

CONCLUSION

LRRC17, COMP, ASPN, CRTAC1, POSTN, COL3A1, PEBP4, IL13RA2, and CA4 were determined as key feature genes for IPF. The nine feature genes in the ANN model will be extremely important for diagnosing IPF. It may be possible to use differentiated immune cells from IPF samples in comparison to normal samples as targets for immunotherapy in patients with IPF.

From Lipid Signatures to Cellular Responses: Unraveling the Complexity of Melanoma and Furthering Its Diagnosis and Treatment

Recent advancements in mass spectrometry have significantly enhanced our understanding of complex lipid profiles, opening new avenues for oncological diagnostics. This review highlights the importance of lipidomics in the comprehension of certain metabolic pathways and its potential for the detection and characterization of various cancers, in particular melanoma. Through detailed case studies, we demonstrate how lipidomic analysis has led to significant breakthroughs in the identification and understanding of cancer types and its potential for detecting unique biomarkers that are instrumental in its diagnosis. Additionally, this review addresses the technical challenges and future perspectives of these methodologies, including their potential expansion and refinement for clinical applications. The discussion underscores the critical role of lipidomic profiling in advancing cancer diagnostics, proposing a new paradigm in how we approach this devastating disease, with particular emphasis on its application in comparative oncology.

Data mining and machine learning in HIV infection risk research: An overview and recommendations

In the contemporary era, the applications of data mining and machine learning have permeated extensively into medical research, significantly contributing to areas such as HIV studies. By reviewing 38 articles published in the past 15 years, the study presents a roadmap based on seven different aspects, utilizing various machine learning techniques for both novice researchers and experienced researchers seeking to comprehend the current state of the art in this area. While traditional regression modeling techniques have been commonly used, researchers are increasingly adopting more advanced fully supervised machine learning and deep learning techniques, which often outperform the traditional methods in predictive performance. Additionally, the study identifies nine new open research issues and outlines possible future research plans to enhance the outcomes of HIV infection risk research. This review is expected to be an insightful guide for researchers, illuminating current practices and suggesting advancements in the field.

Exploring the Roles of Key Mediators IKBKE and HSPA1A in Alzheimer's Disease and Hepatocellular Carcinoma through Bioinformatics Analysis

Recent studies have hinted at a potential link between Alzheimer's Disease (AD) and cancer. Thus, our study focused on finding genes common to AD and Liver Hepatocellular Carcinoma (LIHC), assessing their promise as diagnostic indicators and guiding future treatment approaches for both conditions. Our research utilized a broad methodology, including differential gene expression analysis, Weighted Gene Co-expression Network Analysis (WGCNA), gene enrichment analysis, Receiver Operating Characteristic (ROC) curves, and Kaplan-Meier plots, supplemented with immunohistochemistry data from the Human Protein Atlas (HPA) and machine learning techniques, to identify critical genes and significant pathways shared between AD and LIHC. Through differential gene expression analysis, WGCNA, and machine learning methods, we identified nine key genes associated with AD, which served as entry points for LIHC analysis. Subsequent analyses revealed IKBKE and HSPA1A as shared pivotal genes in patients with AD and LIHC, suggesting these genes as potential targets for intervention in both conditions. Our study indicates that IKBKE and HSPA1A could influence the onset and progression of AD and LIHC by modulating the infiltration levels of immune cells. This lays a foundation for future research into targeted therapies based on their shared mechanisms.

TMO-Net: an explainable pretrained multi-omics model for multi-task learning in oncology

Cancer is a complex disease composing systemic alterations in multiple scales. In this study, we develop the Tumor Multi-Omics pre-trained Network (TMO-Net) that integrates multi-omics pan-cancer datasets for model pre-training, facilitating cross-omics interactions and enabling joint representation learning and incomplete omics inference. This model enhances multi-omics sample representation and empowers various downstream oncology tasks with incomplete multi-omics datasets. By employing interpretable learning, we characterize the contributions of distinct omics features to clinical outcomes. The TMO-Net model serves as a versatile framework for cross-modal multi-omics learning in oncology, paving the way for tumor omics-specific foundation models.

Artificial Intelligence in Point-of-Care Biosensing: Challenges and Opportunities

The integration of artificial intelligence (AI) into point-of-care (POC) biosensing has the potential to revolutionize diagnostic methodologies by offering rapid, accurate, and accessible health assessment directly at the patient level. This review paper explores the transformative impact of AI technologies on POC biosensing, emphasizing recent computational advancements, ongoing challenges, and future prospects in the field. We provide an overview of core biosensing technologies and their use at the POC, highlighting ongoing issues and challenges that may be solved with AI. We follow with an overview of AI methodologies that can be applied to biosensing, including machine learning algorithms, neural networks, and data processing frameworks that facilitate real-time analytical decision-making. We explore the applications of AI at each stage of the biosensor development process, highlighting the diverse opportunities beyond simple data analysis procedures. We include a thorough analysis of outstanding challenges in the field of AI-assisted biosensing, focusing on the technical and ethical challenges regarding the widespread adoption of these technologies, such as data security, algorithmic bias, and regulatory compliance. Through this review, we aim to emphasize the role of AI in advancing POC biosensing and inform researchers, clinicians, and policymakers about the potential of these technologies in reshaping global healthcare landscapes.

RNA sequencing-based approaches to identifying disulfidptosis-related diagnostic clusters and immune landscapes in osteoporosis

Disulfidptosis, a newly recognized cell death triggered by disulfide stress, has garnered attention for its potential role in osteoporosis (OP) pathogenesis. Although sulfide-related proteins are reported to regulate the balance of bone metabolism in OP, the precise involvement of disulfidptosis regulators remains elusive. Herein, leveraging the GSE56815 dataset, we conducted an analysis to delineate disulfidptosis-associated diagnostic clusters and immune landscapes in OP. Subsequently, vertebral bone tissues obtained from OP patients and controls were subjected to RNA sequencing (RNA-seq) for the validation of key disulfidptosis gene expression. Our analysis unveiled seven significant disulfidptosis regulators, including FLNA, ACTB, PRDX1, SLC7A11, NUBPL, OXSM, and RAC1, distinguishing OP samples from controls. Furthermore, employing a random forest model, we identified four diagnostic disulfidptosis regulators including FLNA, SLC7A11, NUBPL, and RAC1 potentially predictive of OP risk. A nomogram model integrating these four regulators was constructed and validated using the GSE35956 dataset, demonstrating promising utility in clinical decision-making, as affirmed by decision curve analysis. Subsequent consensus clustering analysis stratified OP samples into two different disulfidptosis subgroups (clusters A and B) using significant disulfidptosis regulators, with cluster B exhibiting higher disulfidptosis scores and implicating monocyte immunity, closely linked to osteoclastogenesis. Notably, RNA-seq analysis corroborated the expression patterns of two disulfidptosis modulators, PRDX1 and OXSM, consistent with bioinformatics predictions. Collectively, our study sheds light on disulfidptosis patterns, offering potential markers and immunotherapeutic avenues for future OP management.

OmicsFootPrint: a framework to integrate and interpret multi-omics data using circular images and deep neural networks

The OmicsFootPrint framework addresses the need for advanced multi-omics data analysis methodologies by transforming data into intuitive two-dimensional circular images and facilitating the interpretation of complex diseases. Utilizing Deep Neural Networks and incorporating the SHapley Additive exPlanations (SHAP) algorithm, the framework enhances model interpretability. Tested with The Cancer Genome Atlas (TCGA) data, OmicsFootPrint effectively classified lung and breast cancer subtypes, achieving high Area Under Curve (AUC) scores - 0.98±0.02 for lung cancer subtype differentiation, 0.83±0.07 for breast cancer PAM50 subtypes, and successfully distinguishe between invasive lobular and ductal carcinomas in breast cancer, showcasing its robustness. It also demonstrated notable performance in predicting drug responses in cancer cell lines, with a median AUC of 0.74, surpassing existing algorithms. Furthermore, its effectiveness persists even with reduced training sample sizes. OmicsFootPrint marks an enhancement in multi-omics research, offering a novel, efficient, and interpretable approach that contributes to a deeper understanding of disease mechanisms.

Predicting intensive care unit-acquired weakness: A multilayer perceptron neural network approach

In this editorial, we comment on the article by Wang and Long, published in a recent issue of the World Journal of Clinical Cases. The article addresses the challenge of predicting intensive care unit-acquired weakness (ICUAW), a neuromuscular disorder affecting critically ill patients, by employing a novel processing strategy based on repeated machine learning. The editorial presents a dataset comprising clinical, demographic, and laboratory variables from intensive care unit (ICU) patients and employs a multilayer perceptron neural network model to predict ICUAW. The authors also performed a feature importance analysis to identify the most relevant risk factors for ICUAW. This editorial contributes to the growing body of literature on predictive modeling in critical care, offering insights into the potential of machine learning approaches to improve patient outcomes and guide clinical decision-making in the ICU setting.

Validating core therapeutic targets for osteoporosis treatment based on integrating network pharmacology and informatics

OBJECTIVE

Our goal was to find metabolism-related lncRNAs that were associated with osteoporosis (OP) and construct a model for predicting OP progression using these lncRNAs.

METHODS

The GEO database was employed to obtain gene expression profiles. The WGCNA technique and differential expression analysis were used to identify hypoxia-related lncRNAs. A Lasso regression model was applied to select 25 hypoxia-related genes, from which a classification model was created. Its robust classification performance was confirmed with an area under the ROC curve close to 1, as verified on the validation set. Concurrently, we constructed a ceRNA network based on these genes to unveil potential regulatory processes. Biologically active compounds of STZYD were identified using the Traditional Chinese Medicine System Pharmacology Database and Analysis Platform (TCMSP) database. BATMAN was used to identify its targets, and we obtained OP-related genes from Malacards and DisGeNET, followed by identifying intersection genes with metabolism-related genes. A pharmacological network was then constructed based on the intersecting genes. The pharmacological network was further integrated with the ceRNA network, resulting in the creation of a comprehensive network that encompasses herb-active components, pathways, lncRNAs, miRNAs, and targets. Expression levels of hypoxia-related lncRNAs in mononuclear cells isolated from peripheral blood of OP and normal patients were subsequently validated using quantitative real-time PCR (qRT-PCR). Protein levels of RUNX2 were determined through a western blot assay.

RESULTS

CBFB, GLO1, NFKB2 and PIK3CA were identified as central therapeutic targets, and ADD3-AS1, DTX2P1-UPK3BP1-PMS2P11, TTTY1B, ZNNT1 and LINC00623 were identified as core lncRNAs.

CONCLUSIONS

Our work uncovers a possible therapeutic mechanism for STZYD, providing a potential therapeutic target for OP. In addition, a prediction model of metabolism-related lncRNAs of OP progression was constructed to provide a reference for the diagnosis of OP patients.

Metal ion stimulation-related gene signatures correlate with clinical and immunologic characteristics of glioma

Background

Environmental factors serve as one of the important pathogenic factors for gliomas. Yet people focus only on the effect of electromagnetic radiation on its pathogenicity, while metals in the environment are neglected. This study aimed to investigate the relationship between metal ion stimulation and the clinical characteristics and immune status of GM patients.

Methods

Firstly, mRNA expression profiles of GM patients and normal subjects were obtained from Chinese GM Genome Atlas (CGGA) and Gene Expression Omnibus (GEO) to identify differentially expressed metal ion stimulation-related genes(DEMISGs). Secondly, two molecular subtypes were identified and validated based on these DEMISGs using consensus clustering. Diagnostic and prognostic models for GM were constructed after screening these features based on machine learning. Finally, supervised classification and unsupervised clustering were combined to classify and predict the grade of GM based on SHAP values.

Results

GM patients are divided into two different response states to metal ion stimulation, M1 and M2, which are related to the grade and IDH status of the GM. Six genes with diagnostic value were obtained: SLC30A3, CRHBP, SYT13, DLG2, CDK1, and WNT5A. The AUC in the external validation set was higher than 0.90. The SHAP value improves the performance of classification prediction.

Conclusion

The gene features associated with metal ion stimulation are related to the clinical and immune characteristics of transgenic patients. XGboost/LightGBM Kmeans has a higher classification prediction accuracy in predicting glioma grades compared to using purely supervised classification techniques.

Natural variables separate the endemic areas of Clonorchis sinensis and Opisthorchis viverrini along a continuous, straight zone in Southeast Asia

BACKGROUND

Clonorchiasis and opisthorchiasis, caused by the liver flukes Clonorchis sinensis and Opisthorchis viverrini respectively, represent significant neglected tropical diseases (NTDs) in Asia. The co-existence of these pathogens in overlapping regions complicates effective disease control strategies. This study aimed to clarify the distribution and interaction of these diseases within Southeast Asia.

METHODS

We systematically collated occurrence records of human clonorchiasis (n = 1809) and opisthorchiasis (n = 731) across the Southeast Asia countries. Utilizing species distribution models incorporating environmental and climatic data, coupled machine learning algorithms with boosted regression trees, we predicted and distinguished endemic areas for each fluke species. Machine learning techniques, including geospatial analysis, were employed to delineate the boundaries between these flukes.

RESULTS

Our analysis revealed that the endemic range of C. sinensis and O. viverrini in Southeast Asia primarily spans across part of China, Vietnam, Thailand, Laos, and Cambodia. During the period from 2000 to 2018, we identified C. sinensis infections in 84 distinct locations, predominantly in southern China (Guangxi Zhuang Autonomous Region) and northern Vietnam. In a stark contrast, O. viverrini was more widely distributed, with infections documented in 721 locations across Thailand, Laos, Cambodia, and Vietnam. Critical environmental determinants were quantitatively analyzed, revealing annual mean temperatures ranging between 14 and 20 °C in clonorchiasis-endemic areas and 24-30 °C in opisthorchiasis regions (P < 0.05). The machine learning model effectively mapped a distinct demarcation zone, demonstrating a clear separation between the endemic areas of these two liver flukes with AUC from 0.9 to1. The study in Vietnam delineates the coexistence and geographical boundaries of C. sinensis and O. viverrini, revealing distinct endemic zones and a transitional area where both liver fluke species overlap.

CONCLUSIONS

Our findings highlight the critical role of specific climatic and environmental factors in influencing the geographical distribution of C. sinensis and O. viverrini. This spatial delineation offers valuable insights for integrated surveillance and control strategies, particularly in regions with sympatric transmission. The results underscore the need for tailored interventions, considering regional epidemiological variations. Future collaborations integrating eco-epidemiology, molecular epidemiology, and parasitology are essential to further elucidate the complex interplay of liver fluke distributions in Asia.

A personalized probabilistic approach to ovarian cancer diagnostics

OBJECTIVE

The identification/development of a machine learning-based classifier that utilizes metabolic profiles of serum samples to accurately identify individuals with ovarian cancer.

METHODS

Serum samples collected from 431 ovarian cancer patients and 133 normal women at four geographic locations were analyzed by mass spectrometry. Reliable metabolites were identified using recursive feature elimination coupled with repeated cross-validation and used to develop a consensus classifier able to distinguish cancer from non-cancer. The probabilities assigned to individuals by the model were used to create a clinical tool that assigns a likelihood that an individual patient sample is cancer or normal.

RESULTS

Our consensus classification model is able to distinguish cancer from control samples with 93% accuracy. The frequency distribution of individual patient scores was used to develop a clinical tool that assigns a likelihood that an individual patient does or does not have cancer.

CONCLUSIONS

An integrative approach using metabolomic profiles and machine learning-based classifiers has been employed to develop a clinical tool that assigns a probability that an individual patient does or does not have ovarian cancer. This personalized/probabilistic approach to cancer diagnostics is more clinically informative and accurate than traditional binary (yes/no) tests and represents a promising new direction in the early detection of ovarian cancer.

The Development and Evaluation of a Prediction Model for Kidney Transplant-Based Pneumocystis carinii Pneumonia Patients Based on Hematological Indicators

BACKGROUND

This study aimed to develop a simple predictive model for early identification of the risk of adverse outcomes in kidney transplant-associated Pneumocystis carinii pneumonia (PCP) patients.

METHODS

This study encompassed 103 patients diagnosed with PCP, who received treatment at our hospital between 2018 and 2023. Among these participants, 20 were categorized as suffering from severe PCP, and, regrettably, 13 among them succumbed. Through the application of machine learning techniques and multivariate logistic regression analysis, two pivotal variables were discerned and subsequently integrated into a nomogram. The efficacy of the model was assessed via receiver operating characteristic (ROC) curves and calibration curves. Additionally, decision curve analysis (DCA) and a clinical impact curve (CIC) were employed to evaluate the clinical utility of the model. The Kaplan-Meier (KM) survival curves were utilized to ascertain the model's aptitude for risk stratification.

RESULTS

Hematological markers, namely Procalcitonin (PCT) and C-reactive protein (CRP)-to-albumin ratio (CAR), were identified through machine learning and multivariate logistic regression. These variables were subsequently utilized to formulate a predictive model, presented in the form of a nomogram. The ROC curve exhibited commendable predictive accuracy in both internal validation (AUC = 0.861) and external validation (AUC = 0.896). Within a specific threshold probability range, both DCA and CIC demonstrated notable performance. Moreover, the KM survival curve further substantiated the nomogram's efficacy in risk stratification.

CONCLUSIONS

Based on hematological parameters, especially CAR and PCT, a simple nomogram was established to stratify prognostic risk in patients with renal transplant-related PCP.

Machine Learning-Based Breast Tumor Ultrasound Radiomics for Pre-operative Prediction of Axillary Sentinel Lymph Node Metastasis Burden in Early-Stage Invasive Breast Cancer

OBJECTIVE

The aim of the work described here was to assess the application of ultrasound (US) radiomics with machine learning (ML) classifiers to the prediction of axillary sentinel lymph node metastasis (SLNM) burden in early-stage invasive breast cancer (IBC).

METHODS

In this study, 278 early-stage IBC patients with at least one SLNM (195 in the training set and 83 in the test set) were studied at our institution. Pathologic SLNM burden was used as the reference standard. The US radiomics features of breast tumors were extracted by using 3D-Slicer and PyRadiomics software. Four ML classifiers-linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF) and decision tree (DT)-were used to construct radiomics models for the prediction of SLNM burden. The combined clinicopathologic-radiomics models were also assessed with respect to sensitivity, specificity, accuracy and areas under the curve (AUCs).

RESULTS

Among the US radiomics models, the SVM classifier achieved better predictive performance with an AUC of 0.920 compared with RF (AUC = 0.874), LDA (AUC = 0.835) and DT (AUC = 0.800) in the test set. The clinicopathologic model had low efficacy, with AUCs of 0.678 and 0.710 in the training and test sets, respectively. The combined clinicopathologic (C) factors and SVM classifier (C + SVM) model improved the predictive ability with an AUC of 0.934, sensitivity of 86.7%, specificity of 89.9% and accuracy of 91.0% in the test set.

CONCLUSION

ML-based US radiomics analysis, as a novel and promising predictive tool, is conducive to a precise clinical treatment strategy.

Combined measurement of serum zinc with PSA ameliorates prostate cancer screening efficiency via support vector machine algorithms

Background

Early screening of prostate cancer (PCa) is pivotal but challenging in the clinical scenario due to the phenomena of false positivity or false negativity of some serological evaluations, e.g. PSA testing. Decline of serum Zn2+ levels in PCa patients reportedly plays a crucial role in early screening of PCa. Accordingly, we combined 4 indices comprising the serum levels of total PSA (tPSA), free PSA (fPSA), Zn2+ and demographic information (especially age) in order to ameliorate the efficacies of PCa screening with support vector machine (SVM) algorithms.

Methods

A total of 858 male patients with prostate disorders and 345 healthy male controls were enrolled. Patients' data included 4 variables and serum Zn2+ was quantified via a self-invented Zn2+ responsive AIE-based fluorescent probe as previously published. tPSA and fPSA were routinely determined by a chemiluminescent method. Mathematical simulations were conducted to establish a SVM model for the combined diagnostics with the four variables. Moreover, ROC and its characteristic AUC were also employed to evaluate the classification efficacy of the model. Sigmoid function was utilized to estimate corresponding probabilities of classifying the clinical subjects as per 5 grades, which were incorporated into our established prostate index (PI) stratification system.

Results

In SVM model, the mean AUC of the ROC with the quartet of variables was approximately 84% for PCa diagnosis, whereas the mean AUC of the ROCs with tPSA, fPSA, [Zn2+] or age alone was 64%, 62%, 55% and 59%, respectively. We further established an integrated prostate index (PI) stratification system with 5 grades and a software package to support clinicians in predicting PCa, with the accuracy of our risk stratification system being 83.3%, 91.6% and 83.3% in predicting normal, benign and PCa cases in corresponding groups. Follow-up findings especially MRI results and PI-RADS scores supported the reliability of this stratification platform as well.

Conclusion

Findings from our present study demonstrated that index combination via SVM algorithms may well facilitate clinicians in early differential screening of PCa. Meanwhile, our established PI stratification system based on SVM model and Sigmoid function provided substantial accuracy in preclinical risk prediction of developing prostate cancer.

Preoperative CT-based deep learning radiomics model to predict lymph node metastasis and patient prognosis in bladder cancer: a two-center study

OBJECTIVE

To establish a model for predicting lymph node metastasis in bladder cancer (BCa) patients.

METHODS

We retroactively enrolled 239 patients who underwent three-phase CT and resection for BCa in two centers (training set, n = 185; external test set, n = 54). We reviewed the clinical characteristics and CT features to identify significant predictors to construct a clinical model. We extracted the hand-crafted radiomics features and deep learning features of the lesions. We used the Minimum Redundancy Maximum Relevance algorithm and the least absolute shrinkage and selection operator logistic regression algorithm to screen features. We used nine classifiers to establish the radiomics machine learning signatures. To compensate for the uneven distribution of the data, we used the synthetic minority over-sampling technique to retrain each machine-learning classifier. We constructed the combined model using the top-performing radiomics signature and clinical model, and finally presented as a nomogram. We evaluated the combined model's performance using the area under the receiver operating characteristic, accuracy, calibration curves, and decision curve analysis. We used the Kaplan-Meier survival curve to analyze the prognosis of BCa patients.

RESULTS

The combined model incorporating radiomics signature and clinical model achieved an area under the receiver operating characteristic of 0.834 (95% CI: 0.659-1.000) for the external test set. The calibration curves and decision curve analysis demonstrated exceptional calibration and promising clinical use. The combined model showed good risk stratification performance for progression-free survival.

CONCLUSION

The proposed CT-based combined model is effective and reliable for predicting lymph node status of BCa patients preoperatively.

CRITICAL RELEVANCE STATEMENT

Bladder cancer is a type of urogenital cancer that has a high morbidity and mortality rate. Lymph node metastasis is an independent risk factor for death in bladder cancer patients. This study aimed to investigate the performance of a deep learning radiomics model for preoperatively predicting lymph node metastasis in bladder cancer patients.

KEY POINTS

• Conventional imaging is not sufficiently accurate to determine lymph node status. • Deep learning radiomics model accurately predicted bladder cancer lymph node metastasis. • The proposed method showed satisfactory patient risk stratification for progression-free survival.

CAT Bridge: an efficient toolkit for gene-metabolite association mining from multiomics data

BACKGROUND

With advancements in sequencing and mass spectrometry technologies, multiomics data can now be easily acquired for understanding complex biological systems. Nevertheless, substantial challenges remain in determining the association between gene-metabolite pairs due to the nonlinear and multifactorial interactions within cellular networks. The complexity arises from the interplay of multiple genes and metabolites, often involving feedback loops and time-dependent regulatory mechanisms that are not easily captured by traditional analysis methods.

FINDINGS

Here, we introduce Compounds And Transcripts Bridge (abbreviated as CAT Bridge, available at https://catbridge.work), a free user-friendly platform for longitudinal multiomics analysis to efficiently identify transcripts associated with metabolites using time-series omics data. To evaluate the association of gene-metabolite pairs, CAT Bridge is a pioneering work benchmarking a set of statistical methods spanning causality estimation and correlation coefficient calculation for multiomics analysis. Additionally, CAT Bridge features an artificial intelligence agent to assist users interpreting the association results.

CONCLUSIONS

We applied CAT Bridge to experimentally obtained Capsicum chinense (chili pepper) and public human and Escherichia coli time-series transcriptome and metabolome datasets. CAT Bridge successfully identified genes involved in the biosynthesis of capsaicin in C. chinense. Furthermore, case study results showed that the convergent cross-mapping method outperforms traditional approaches in longitudinal multiomics analyses. CAT Bridge simplifies access to various established methods for longitudinal multiomics analysis and enables researchers to swiftly identify associated gene-metabolite pairs for further validation.

Development and validation of a clinical prediction model for glioma grade using machine learning

BACKGROUND

Histopathological evaluation is currently the gold standard for grading gliomas; however, this technique is invasive.

OBJECTIVE

This study aimed to develop and validate a diagnostic prediction model for glioma by employing multiple machine learning algorithms to identify risk factors associated with high-grade glioma, facilitating the prediction of glioma grading.

METHODS

Data from 1114 eligible glioma patients were obtained from The Cancer Genome Atlas (TCGA) database, which was divided into a training set (n= 781) and a test set (n= 333). Fifty machine learning algorithms were employed, and the optimal algorithm was selected to construct a prediction model. The performance of the machine learning prediction model was compared to the clinical prediction model in terms of discrimination, calibration, and clinical validity to assess the performance of the prediction model.

RESULTS

The area under the curve (AUC) values of the machine learning prediction models (training set: 0.870 vs. 0.740, test set: 0.863 vs. 0.718) were significantly improved from the clinical prediction models. Furthermore, significant improvement in discrimination was observed for the Integrated Discrimination Improvement (IDI) (training set: 0.230, test set: 0.270) and Net Reclassification Index (NRI) (training set: 0.170, test set: 0.170) from the clinical prognostic model. Both models showed a high goodness of fit and an increased net benefit.

CONCLUSION

A strong prediction accuracy model can be developed using machine learning algorithms to screen for high-grade glioma risk predictors, which can serve as a non-invasive prediction tool for preoperative diagnostic grading of glioma.

MTTLm6A: A multi-task transfer learning approach for base-resolution mRNA m6A site prediction based on an improved transformer

N6-methyladenosine (m6A) is a crucial RNA modification involved in various biological activities. Computational methods have been developed for the detection of m6A sites in Saccharomyces cerevisiae at base-resolution due to their cost-effectiveness and efficiency. However, the generalization of these methods has been hindered by limited base-resolution datasets. Additionally, RMBase contains a vast number of low-resolution m6A sites for Saccharomyces cerevisiae, and base-resolution sites are often inferred from these low-resolution results through post-calibration. We propose MTTLm6A, a multi-task transfer learning approach for base-resolution mRNA m6A site prediction based on an improved transformer. First, the RNA sequences are encoded by using one-hot encoding. Then, we construct a multi-task model that combines a convolutional neural network with a multi-head-attention deep framework. This model not only detects low-resolution m6A sites, it also assigns reasonable probabilities to the predicted sites. Finally, we employ transfer learning to predict base-resolution m6A sites based on the low-resolution m6A sites. Experimental results on Saccharomyces cerevisiae m6A and Homo sapiens m1A data demonstrate that MTTLm6A respectively achieved area under the receiver operating characteristic (AUROC) values of 77.13% and 92.9%, outperforming the state-of-the-art models. At the same time, it shows that the model has strong generalization ability. To enhance user convenience, we have made a user-friendly web server for MTTLm6A publicly available at http://47.242.23.141/MTTLm6A/index.php.

Extensive prediction of drug response in mutation-subtype-specific LUAD with machine learning approach

Background

Lung cancer is the most prevalent cancer diagnosis and the leading cause of cancer death worldwide. Therapeutic failure in lung cancer (LUAD) is heavily influenced by drug resistance. This challenge stems from the diverse cell populations within the tumor, each having unique genetic, epigenetic, and phenotypic profiles. Such variations lead to varied therapeutic responses, thereby contributing to tumor relapse and disease progression.

Methods

The Genomics of Drug Sensitivity in Cancer (GDSC) database was used in this investigation to obtain the mRNA expression dataset, genomic mutation profile, and drug sensitivity information of NSCLS. Machine Learning (ML) methods, including Random Forest (RF), Artificial Neurol Network (ANN), and Support Vector Machine (SVM), were used to predict the response status of each compound based on the mRNA and mutation characteristics determined using statistical methods. The most suitable method for each drug was proposed by comparing the prediction accuracy of different ML methods, and the selected mRNA and mutation characteristics were identified as molecular features for the drug-responsive cancer subtype. Finally, the prognostic influence of molecular features on the mutational subtype of LUAD in publicly available datasets.

Results

Our analyses yielded 1,564 gene features and 45 mutational features for 46 drugs. Applying the ML approach to predict the drug response for each medication revealed an upstanding performance for SVM in predicting Afuresertib drug response (area under the curve [AUC] 0.875) using CIT, GAS2L3, STAG3L3, ATP2B4-mut, and IL15RA-mut as molecular features. Furthermore, the ANN algorithm using 9 mRNA characteristics demonstrated the highest prediction performance (AUC 0.780) in Gefitinib with CCL23-mut.

Conclusion

This work extensively investigated the mRNA and mutation signatures associated with drug response in LUAD using a machine-learning approach and proposed a priority algorithm to predict drug response for different drugs.

Construction of 11 metabolic-related lncRNAs to predict the prognosis in lung adenocarcinoma

OBJECTIVE

To explore the metabolism-related lncRNAs in the tumorigenesis of lung adenocarcinoma.

METHODS

The transcriptome data and clinical information about lung adenocarcinoma patients were acquired in TCGA (The Cancer Genome Atlas). Metabolism-related genes were from the GSEA (Gene Set Enrichment Analysis) database. Through differential expression analysis and Pearson correlation analysis, lncRNAs about lung adenocarcinoma metabolism were identified. The samples were separated into the training and validation sets in the proportion of 2:1. The prognostic lncRNAs were determined by univariate Cox regression analysis and LASSO (Least absolute shrinkage and selection operator) regression. A risk model was built using Multivariate Cox regression analysis, evaluated by the internal validation data. The model prediction ability was assessed by subgroup analysis. The Nomogram was constructed by combining clinical indicators with independent prognostic significance and risk scores. C-index, calibration curve, DCA (Decision Curve Analysis) clinical decision and ROC (Receiver Operating Characteristic Curve) curves were obtained to assess the prediction ability of the model. Based on the CIBERSORT analysis, the correlation between lncRNAs and tumor infiltrating lymphocytes was obtained.

RESULTS

From 497 lung adenocarcinoma and 54 paracancerous samples, 233 metabolic-related and 11 prognostic-related lncRNAs were further screened. According to the findings of the survival study, the low-risk group had a greater OS (Overall survival) than the high-risk group. ROC analysis indicated AUC (Area Under Curve) value was 0.726. Then, a nomogram with T, N stage and risk ratings was developed according to COX regression analysis. The C-index was 0.743, and the AUC values of 3- and 5-year survival were 0.741 and 0.775, respectively. The above results suggested the nomogram had a good prediction ability. The results based on the CIBERSORT algorithm demonstrated the lncRNAs used to construct the model had a strong correlation with the polarization of immune cells.

CONCLUSIONS

The study identified 11 metabolic-related lncRNAs for lung adenocarcinoma prognosis, on which basis a prognostic risk scoring model was created. This model may have a good predictive potential for lung adenocarcinoma.

Machine learning algorithms for a novel cuproptosis-related gene signature of diagnostic and immune infiltration in endometriosis

Endometriosis (EMT) is an aggressive disease of the reproductive system, also called "benign cancer". However, effective treatments for EMT are still lacking in clinical practice. Interestingly, immune infiltration is significantly involved in EMT pathogenesis. Currently, no studies have shown the involvement of cuproptosis-related genes (CRGs) in regulating immune infiltration in EMT. This study identified three CRGs such as GLS, NFE2L2, and PDHA1, associated with EMT using machine learning algorithms. These three CRGs were upregulated in the endometrium of patients with moderate/severe EMT and downregulated in patients with infertility. Single sample genomic enrichment analysis (ssGSEA) revealed that these CRGs were closely correlated with autoimmune diseases such as systemic lupus erythematosus. Furthermore, these CRGs were correlated with immune cells such as eosinophils, natural killer cells, and macrophages. Therefore, profiling patients based on these genes aid in a more accurate diagnosis of EMT progression. The mRNA and protein expression levels of GLS, NFE2L2 and PDHA1 were validated by qRT-PCR and WB studies in EMT samples. These findings provide a new idea for the pathology and treatment of endometriosis, suggesting that CRGs such as GLS, NFE2L2 and PDHA1 may play a key role in the occurrence and development of endometriosis.

An Explainable AI Approach for Breast Cancer Metastasis Prediction Based on Clinicopathological Data

OBJECTIVE

Breast Cancer is the most prevalent cancer and the first cause of cancer deaths among women worldwide. In 90% of the cases, mortality is related to distant metastasis. Computer-aided prognosis systems using machine learning models have been widely used to predict breast cancer metastasis. Despite that, these systems still face several challenges. First, the models are generally biased toward the majority class due to datasets unbalance. Second, their increased complexity is associated with decreased interpretability which causes clinicians to distrust their prognosis.

METHODS

To tackle these issues, we have proposed an explainable approach for predicting breast cancer metastasis using clinicopathological data. Our approach is based on cost-sensitive CatBoost classifier and utilises LIME explainer to provide patient-level explanations.

RESULTS

We used a public dataset of 716 breast cancer patients to assess our approach. The results demonstrate the superiority of cost-sensitive CatBoost in precision (76.5%), recall (79.5%), and f1-score (77%) over classical and boosting models. The LIME explainer was used to quantify the impact of patient and treatment characteristics on breast cancer metastasis, revealing that they have different impacts ranging from high impact like the non-use of adjuvant chemotherapy, and moderate impact including carcinoma with medullary features histological type, to low impact like oral contraception use. The code is available at https://github.com/IkramMaouche/CS-CatBoost Conclusion: Our approach serves as a first step toward introducing more efficient and explainable computer-aided prognosis systems for breast cancer metastasis prediction.

SIGNIFICANCE

This approach could help clinicians understand the factors behind metastasis and assist them in proposing more patient-specific therapeutic decisions.

Beneficial or detrimental: Recruiting more types of benign cases for cancer diagnosis based on salivary glycopatterns

With the advantages of convenient, painless and non-invasive collection, saliva holds great promise as a valuable biomarker source for cancer detection, pathological assessment and therapeutic monitoring. Salivary glycopatterns have shown significant potential for cancer screening in recent years. However, the understanding of benign lesions at non-cancerous sites in cancer diagnosis has been overlooked. Clarifying the influence of benign lesions on salivary glycopatterns and cancer screening is crucial for advancing the development of salivary glycopattern-based diagnostics. In this study, 2885 samples were analyzed using lectin microarrays to identify variations in salivary glycopatterns according to the number, location, and type of lesions. By utilizing our previously published data of tumor-associated salivary glycopatterns, the performance of machine learning algorithm for cancer screening was investigated to evaluate the effect of adding benign disease cases to the control group. The results demonstrated that both the location and number of lesions had discernible effects on salivary glycopatterns. And it was also revealed that incorporating a broad range of benign diseases into the controls improved the classifier's performance in distinguishing cancer cases from controls. This finding holds guiding significance for enhancing salivary glycopattern-based cancer screening and facilitates their practical implementation in clinical settings.

Prediction of lymph node metastasis of lung squamous cell carcinoma by machine learning algorithm classifiers

BACKGROUND

Lymph node metastasis (LNM) is an essential factor affecting the prognosis of patients with lung squamous cell carcinoma (LUSC), as well as a critical consideration for the choice of treatment strategy. Exploring effective methods for predicting LNM in LUSC may benefit clinical decision making.

MATERIALS AND METHODS

We used data collected from the Surveillance, Epidemiology, and End Results (SEER) database to develop machine learning algorithm classifiers, including boosted trees (BTs), based on the primary clinical parameters of patients to predict LNM in LUSC. Training on a large-sample training cohort (n = 8,063) allowed for the construction of several concise classifiers for LNM prediction in LUSC, which were then validated using test and in-house cohorts (n = 2,017 and 57, respectively).

RESULTS

The six classifiers established in this research enabled distinction between patients with and without LNM. Among these classifiers, the BT classifier was the top performer, with accuracy, F1 scores, precision, recall, sensitivity, and specificity values of 0.654, 0.621, 0.654, 0.592, 0.592, and 0.711, respectively. The precision recall (PR) and receiver operating characteristic (ROC) (with area under the curve = 0.714) curves also supported this result, which was validated by the in-house cohort. Notably, the tumor stage was a critical factor in determining LNM in patients with LUSC.

CONCLUSIONS

The use of classifiers, especially the BT classifier, may serve as a useful tool for improving clinical precision and individualized treatment of patients with LUSC.

A deep learning model predicts the presence of diverse cancer types using circulating tumor cells

Circulating tumor cells (CTCs) are cancer cells that detach from the primary tumor and intravasate into the bloodstream. Thus, non-invasive liquid biopsies are being used to analyze CTC-expressed genes to identify potential cancer biomarkers. In this regard, several studies have used gene expression changes in blood to predict the presence of CTC and, consequently, cancer. However, the CTC mRNA data has not been used to develop a generic approach that indicates the presence of multiple cancer types. In this study, we developed such a generic approach. Briefly, we designed two computational workflows, one using the raw mRNA data and deep learning (DL) and the other exploiting five hub gene ranking algorithms (Degree, Maximum Neighborhood Component, Betweenness Centrality, Closeness Centrality, and Stress Centrality) with machine learning (ML). Both workflows aim to determine the top genes that best distinguish cancer types based on the CTC mRNA data. We demonstrate that our automated, robust DL framework (DNNraw) more accurately indicates the presence of multiple cancer types using the CTC gene expression data than multiple ML approaches. The DL approach achieved average precision of 0.9652, recall of 0.9640, f1-score of 0.9638 and overall accuracy of 0.9640. Furthermore, since we designed multiple approaches, we also provide a bioinformatics analysis of the gene commonly identified as top-ranked by the different methods. To our knowledge, this is the first study wherein a generic approach has been developed to predict the presence of multiple cancer types using raw CTC mRNA data, as opposed to other models that require a feature selection step.

Role of arachidonic acid metabolism in intervertebral disc degeneration: identification of potential biomarkers and therapeutic targets via multi-omics analysis and artificial intelligence strategies

BACKGROUND

Intervertebral disc degeneration (IVDD) is widely recognized as the primary etiological factor underlying low back pain, often necessitating surgical intervention as the sole recourse in severe cases. The metabolic pathway of arachidonic acid (AA), a pivotal regulator of inflammatory responses, influences the development and progression of IVDD.

METHODS

Initially, a comparative analysis was conducted to investigate the relationship between AA expression patterns and different stages of IVDD using single-cell sequencing (scRNA-seq) data. Additionally, three machine learning methods (LASSO, random forest, and support vector machine recursive feature elimination) were employed to identify hub genes associated with IVDD. Subsequently, a novel artificial intelligence prediction model was developed for IVDD based on an artificial neural network algorithm and validated using an independent dataset. The identified hub genes were further subjected to functional enrichment, immune infiltration, and Connectivity Map analysis. Moreover, external validation was performed using flow cytometry and real-time reverse transcription polymerase chain reaction analysis.

RESULTS

Both scRNA-seq and bulk RNA-seq data revealed a positive correlation between the severity of IVDD and the AA metabolic pathway. They also revealed increased AA metabolic activity in macrophages and neutrophils, as well as enhanced intercellular communication with nucleus pulposus cells. Utilizing advanced machine learning algorithms, five hub genes (AKR1C3, ALOX5, CYP2B6, EPHX2, and PLB1) were identified, and an incipient diagnostic model was developed with an AUC of 0.961 in the training cohort and 0.72 in the validation cohort. An in-depth exploration of the functionality of these hub genes revealed their notable association with inflammatory responses and immune cell infiltration. Lastly, AH6809 was found to delay IVDD by inhibiting AKR1C3.

CONCLUSIONS

This study offers comprehensive insights into potential biomarkers and small molecules associated with the early pathogenesis of IVDD. The identified biomarkers and the developed integrated diagnostic model hold great promise in predicting the onset of early IVDD. AH6809 was established as a therapeutic target for AKR1C3 in the treatment of IVDD, as evidenced by computer simulations and biological experiments.

Machine Learning Techniques to Predict Timeliness of Care among Lung Cancer Patients

Delays in the assessment, management, and treatment of lung cancer patients may adversely impact prognosis and survival. This study is the first to use machine learning techniques to predict the quality and timeliness of care among lung cancer patients, utilising data from the Victorian Lung Cancer Registry (VLCR) between 2011 and 2022, in Victoria, Australia. Predictor variables included demographic, clinical, hospital, and geographical socio-economic indices. Machine learning methods such as random forests, k-nearest neighbour, neural networks, and support vector machines were implemented and evaluated using 20% out-of-sample cross validations via the area under the curve (AUC). Optimal model parameters were selected based on 10-fold cross validation. There were 11,602 patients included in the analysis. Evaluated quality indicators included, primarily, overall proportion achieving "time from referral date to diagnosis date ≤ 28 days" and proportion achieving "time from diagnosis date to first treatment date (any intent) ≤ 14 days". Results showed that the support vector machine learning methods performed well, followed by nearest neighbour, based on out-of-sample AUCs of 0.89 (in-sample = 0.99) and 0.85 (in-sample = 0.99) for the first indicator, respectively. These models can be implemented in the registry databases to help healthcare workers identify patients who may not meet these indicators prospectively and enable timely interventions.

Identification of Breast Cancer Metastasis Markers from Gene Expression Profiles Using Machine Learning Approaches

Cancer metastasis accounts for approximately 90% of cancer deaths, and elucidating markers in metastasis is the first step in its prevention. To characterize metastasis marker genes (MGs) of breast cancer, XGBoost models that classify metastasis status were trained with gene expression profiles from TCGA. Then, a metastasis score (MS) was assigned to each gene by calculating the inner product between the feature importance and the AUC performance of the models. As a result, 54, 202, and 357 genes with the highest MS were characterized as MGs by empirical p-value cutoffs of 0.001, 0.005, and 0.01, respectively. The three sets of MGs were compared with those from existing metastasis marker databases, which provided significant results in most comparisons (p-value < 0.05). They were also significantly enriched in biological processes associated with breast cancer metastasis. The three MGs, SPPL2C, KRT23, and RGS7, showed highly significant results (p-value < 0.01) in the survival analysis. The MGs that could not be identified by statistical analysis (e.g., GOLM1, ELAVL1, UBP1, and AZGP1), as well as the MGs with the highest MS (e.g., ZNF676, FAM163B, LDOC2, IRF1, and STK40), were verified via the literature. Additionally, we checked how close the MGs were to each other in the protein-protein interaction networks. We expect that the characterized markers will help understand and prevent breast cancer metastasis.