Machine Learning Models for the Identification of Prognostic and Predictive Cancer Biomarkers: A Systematic Review

Development of an equation to predict delta bilirubin levels using machine learning

OBJECTIVE

Delta bilirubin (albumin-covalently bound bilirubin) may provide important clinical utility in identifying impaired hepatic excretion of conjugated bilirubin, but it cannot be measured in real-time for diagnostic purposes in clinical laboratories.

METHODS

A total of 210 samples were collected, and their delta bilirubin levels were measured four times using high-performance liquid chromatography. Data collected included age, sex, diagnosis code, delta bilirubin, total bilirubin, direct bilirubin, total protein, albumin, globulin, aspartate aminotransferase, alanine transaminase, alkaline phosphatase, gamma-glutamyl transferase, lactate dehydrogenase, hemoglobin, serum hemolysis value, hemolysis index, icterus value (Iv), icterus index (Ii), lipemia value (Lv), and lipemia index. To conduct feature selection and identify the optimal combination of variables, linear regression machine learning was performed 1,000 times.

RESULTS

The selected variables were total bilirubin, direct bilirubin, total protein, albumin, hemoglobin, Iv, Ii, and Lv. The best predictive performance for high delta bilirubin concentrations was achieved with the combination of albumin-direct bilirubin-hemoglobin-Iv-Lv. The final equation composed of these variables was as follows: delta bilirubin = 0.35 × Iv + 0.05 × Lv - 0.23 × direct bilirubin - 0.05 × hemoglobin - 0.04 × albumin + 0.10.

CONCLUSION

The equation established in this study is practical and can be easily applied in real-time in clinical laboratories.

Pioneering noninvasive colorectal cancer detection with an AI-enhanced breath volatilomics platform

Background: The sensitivity and specificity of current breath biomarkers are often inadequate for effective cancer screening, particularly in colorectal cancer (CRC). While a few exhaled biomarkers in CRC exhibit high specificity, they lack the requisite sensitivity for early-stage detection, thereby limiting improvements in patient survival rates. Methods: In this study, we developed an advanced Mass Spectrometry-based volatilomics platform, complemented by an enhanced breath sampler. The platform integrates artificial intelligence (AI)-assisted algorithms to detect multiple volatile organic compounds (VOCs) biomarkers in human breath. Subsequently, we applied this platform to analyze 364 clinical CRC and normal exhaled samples. Results: The diagnostic signatures, including 2-methyl, octane, and butyric acid, generated by the platform effectively discriminated CRC patients from normal controls with high sensitivity (89.7%), specificity (86.8%), and accuracy (AUC = 0.91). Furthermore, the metastatic signature correctly identified over 50% of metastatic patients who tested negative for carcinoembryonic antigen (CEA). Fecal validation indicated that elevated breath biomarkers correlated with an inflammatory response guided by Bacteroides fragilis in CRC. Conclusion: This study introduces a sophisticated AI-aided Mass Spectrometry-based platform capable of identifying novel and feasible breath biomarkers for early-stage CRC detection. The promising results position the platform as an efficient noninvasive screening test for clinical applications, offering potential advancements in early detection and improved survival rates for CRC patients.

Potential role of lncRNA LOXL1-AS1 in human cancer development: a narrative review

Background and Objective

Long non-coding RNAs (lncRNAs) are a group of non-coding RNAs consisting of more than 200 nucleotides that are widely involved in various physiological and pathobiological processes in the body. LncRNA plays a crucial role in tumorigenesis and development with its unique functions, such as playing a role in a variety of biological processes of malignant tumors as a cancer-promoting factor or a cancer-suppressor factor. Lysyl oxidase-like protein 1-antisense RNA1 (LOXL1-AS1) is a novel functional lncRNA recently reported. This article reviews the current findings on the role of LOXL1-AS1 in cancer, and discusses the potential clinical significance and application prospects, in order to provide a theoretical basis and reference for the clinical diagnosis, treatment and screening of prognostic markers for malignant tumors.

Methods

The PubMed and Embase databases were searched using the keywords "cancer" or "tumor" or "neoplasm" and "LOXL1-AS1" for publications from 2018 to the present. The English literature was searched, with a focus on relevant articles. These articles validated the role and mechanism of LOXL1-AS1 in different cancers.

Key Content and Findings

LOXL1-AS1 is a recently reported novel lncRNA, which is abnormally expressed and upregulated in more than ten cancers, and is positively correlated with adverse clinical features and poor prognosis in cancer patients. LOXL1-AS1 competently binds to a variety of microRNAs to regulate the expression of downstream target genes and regulate related signaling pathways, including proliferation, migration, invasion and inhibition of malignant biological behaviors such as apoptosis.

Conclusions

LOXL1-AS1 is expected to become a novel biomarker for cancer diagnosis and treatment, with great potential as an independent prognostic indicator.

Immunotherapy for lung cancer

Immune checkpoint blockers have transformed non-small-cell lung cancer treatment, but they can lead to autoimmune and inflammatory side effects, leading to the concurrent use of immunosuppressive treatments. In this analysis, we delve into the potential of antibodies checkpoint blockade, focusing on CTLA-4 inhibition using ipilimumab, as a groundbreaking cancer immunotherapy. We also concentrate on the role of biomarkers, particularly PD-L1 activity and mutation significance, in predicting the response to programmed cell death protein 1 blockage and the prevalence of side effects associated with immune-related side effects. In describing the patterns of cancer response to immunotherapy, we underline the limitations of response assessment criteria like RECIST and World Health Organization. We also stress the necessity of ongoing studies and clinical trials, standardized guidelines, and additional research to improve response assessment in the era of immunotherapy.

Navigating the Future: A Comprehensive Review of Artificial Intelligence Applications in Gastrointestinal Cancer

This comprehensive review explores the transformative role of artificial intelligence (AI) in the realm of gastrointestinal cancer. Gastrointestinal cancers present unique challenges, necessitating precise diagnostic tools and personalized treatment strategies. Leveraging AI, particularly machine learning and deep learning algorithms, has demonstrated remarkable potential in revolutionizing early detection, treatment planning, prognosis, and drug development. The analysis of current research and technological advancements underscores the capacity of AI to unravel intricate patterns within extensive datasets, providing actionable insights that enhance diagnostic accuracy and treatment efficacy. The transformative impact of AI on the landscape of gastrointestinal cancer is emphasized, signaling a paradigm shift towards more precise and targeted cancer care. The conclusion emphasizes the need for sustained research efforts and collaborative initiatives among AI researchers, healthcare professionals, and policymakers. By fostering interdisciplinary collaboration, we can navigate the evolving field of gastrointestinal cancer care, embracing the potential of AI to improve patient outcomes and contribute to a more effective and personalized approach to cancer management.

A Comprehensive Review of Current Trends in the Diagnosis and Treatment of Ovarian Germ Cell Tumors

Ovarian germ cell tumors constitute a rare and intricate spectrum of neoplasms characterized by diverse histological subtypes. This comprehensive review elucidates the classification, diagnosis, treatment, prognosis, and unique challenges associated with these tumors. The classification is rooted in histological attributes, with principal subtypes encompassing dysgerminoma, immature teratoma, yolk sac tumor (endodermal sinus tumor), choriocarcinoma, and mixed germ cell tumors. Each subtype bears distinct characteristics and clinical implications, necessitating precise diagnosis and tailored therapeutic strategies. Diagnosis hinges upon recognizing the broad clinical presentation, employing imaging techniques (such as ultrasound and MRI), evaluating tumor markers (alpha-fetoprotein and beta-human chorionic gonadotropin), and conducting histopathological examinations where necessary. Staging, primarily utilizing the International Federation of Gynecology and Obstetrics (FIGO) system, is pivotal in determining the extent of disease, guiding treatment choices, and facilitating prognostic assessment. Treatment modalities encompass surgery, chemotherapy (including standard regimens and emerging therapies), radiation therapy, targeted therapies, and immunotherapy. Prognosis is influenced by histological subtype, tumor stage, patient age, surgical success, response to chemotherapy, and tumor markers, while predictive biomarkers are continually emerging. Despite advances in treatment, ovarian germ cell tumors pose distinct challenges, including late diagnosis, treatment-related side effects, and the enigma of chemoresistance. An integral aspect of comprehensive care is supportive strategies to manage symptoms and offer psychological and emotional support. This review accentuates the vital role of early diagnosis and multidisciplinary care in optimizing outcomes. Future research directions and evolving clinical practices are explored in these intricate and distinctive malignancies, highlighting the dynamic landscape of ovarian germ cell tumors.

Using machine learning approach for screening metastatic biomarkers in colorectal cancer and predictive modeling with experimental validation

Colorectal cancer (CRC) liver metastasis accounts for the majority of fatalities associated with CRC. Early detection of metastasis is crucial for improving patient outcomes but can be delayed due to a lack of symptoms. In this research, we aimed to investigate CRC metastasis-related biomarkers by employing a machine learning (ML) approach and experimental validation. The gene expression profile of CRC patients with liver metastasis was obtained using the GSE41568 dataset, and the differentially expressed genes between primary and metastatic samples were screened. Subsequently, we carried out feature selection to identify the most relevant DEGs using LASSO and Penalized-SVM methods. DEGs commonly selected by these methods were selected for further analysis. Finally, the experimental validation was done through qRT-PCR. 11 genes were commonly selected by LASSO and P-SVM algorithms, among which seven had prognostic value in colorectal cancer. It was found that the expression of the MMP3 gene decreases in stage IV of colorectal cancer compared to other stages (P value < 0.01). Also, the expression level of the WNT11 gene was observed to increase significantly in this stage (P value < 0.001). It was also found that the expression of WNT5a, TNFSF11, and MMP3 is significantly lower, and the expression level of WNT11 is significantly higher in liver metastasis samples compared to primary tumors. In summary, this study has identified a set of potential biomarkers for CRC metastasis using ML algorithms. The findings of this research may provide new insights into identifying biomarkers for CRC metastasis and may potentially lay the groundwork for innovative therapeutic strategies for treatment of this disease.

Potential Associations between Vascular Biology and Hodgkin's Lymphoma: An Overview

Hodgkin's lymphoma (HL) is a lymphatic neoplasm typically found in the cervical lymph nodes. The disease is multifactorial, and in recent years, the relationships between various vascular molecules have been explored in the field of vascular biology. The connection between vascular biology and HL is intricate and the roles of several pathways remain unclear. This review summarizes the cellular and molecular relationships between vascular biology and HL. Proteins associated with various functions in vascular biology, including cytokines (TNF-α, IL-1, IL-13, and IL-21), chemokines (CXCL10, CXCL12, and CCL21), adhesion molecules (ELAM-1/VCAM-1), and growth factors (BDNF/NT-3, platelet-derived growth factor receptor-α), have been linked to tumor activity. Notable tumor activities include the induction of paracrine activation of NF-kB-dependent pathways, upregulation of adhesion molecule regulation, genome amplification, and effective loss of antigen presentation mediated by MHC-II. Preclinical study models, primarily those using cell culture, have been optimized for HL. Animal models, particularly mice, are also used as alternatives to complex biological systems, with studies primarily focusing on the physiopathogenic evaluation of the disease. These biomolecules warrant further study because they may shed light on obscure pathways and serve as targets for prevention and/or treatment interventions.

Enhancing head and neck tumor management with artificial intelligence: Integration and perspectives

Head and neck tumors (HNTs) constitute a multifaceted ensemble of pathologies that primarily involve regions such as the oral cavity, pharynx, and nasal cavity. The intricate anatomical structure of these regions poses considerable challenges to efficacious treatment strategies. Despite the availability of myriad treatment modalities, the overall therapeutic efficacy for HNTs continues to remain subdued. In recent years, the deployment of artificial intelligence (AI) in healthcare practices has garnered noteworthy attention. AI modalities, inclusive of machine learning (ML), neural networks (NNs), and deep learning (DL), when amalgamated into the holistic management of HNTs, promise to augment the precision, safety, and efficacy of treatment regimens. The integration of AI within HNT management is intricately intertwined with domains such as medical imaging, bioinformatics, and medical robotics. This article intends to scrutinize the cutting-edge advancements and prospective applications of AI in the realm of HNTs, elucidating AI's indispensable role in prevention, diagnosis, treatment, prognostication, research, and inter-sectoral integration. The overarching objective is to stimulate scholarly discourse and invigorate insights among medical practitioners and researchers to propel further exploration, thereby facilitating superior therapeutic alternatives for patients.

SwarmDeepSurv: swarm intelligence advances deep survival network for prognostic radiomics signatures in four solid cancers

Survival models exist to study relationships between biomarkers and treatment effects. Deep learning-powered survival models supersede the classical Cox proportional hazards (CoxPH) model, but substantial performance drops were observed on high-dimensional features because of irrelevant/redundant information. To fill this gap, we proposed SwarmDeepSurv by integrating swarm intelligence algorithms with the deep survival model. Furthermore, four objective functions were designed to optimize prognostic prediction while regularizing selected feature numbers. When testing on multicenter sets (n = 1,058) of four different cancer types, SwarmDeepSurv was less prone to overfitting and achieved optimal patient risk stratification compared with popular survival modeling algorithms. Strikingly, SwarmDeepSurv selected different features compared with classical feature selection algorithms, including the least absolute shrinkage and selection operator (LASSO), with nearly no feature overlapping across these models. Taken together, SwarmDeepSurv offers an alternative approach to model relationships between radiomics features and survival endpoints, which can further extend to study other input data types including genomics.

Chemo Markers as Biomarkers in Septic Shock: A Comprehensive Review of Their Utility and Clinical Applications

Sepsis is a life-threatening condition characterized by a dysregulated host response to infection, often leading to septic shock. Early diagnosis and prompt intervention are crucial for improving patient outcomes. Chemo markers, which are measurable biological substances associated with the pathophysiology of septic shock, have emerged as potential biomarkers for the identification, risk stratification, and management of this condition. This comprehensive review aims to thoroughly evaluate the utility and clinical applications of chemo markers in septic shock. The review begins by discussing the criteria for ideal chemo markers, including specificity, sensitivity, dynamic range, stability, non-invasiveness, and prognostic value. These characteristics ensure accurate diagnosis, early detection, effective monitoring, and prediction of clinical outcomes. Furthermore, the review explores the role of chemo markers in monitoring treatment response and disease progression, highlighting their ability to serve as objective indicators for assessing the effectiveness of interventions and making timely adjustments in management strategies. Moreover, the prognostic value of chemo markers in predicting outcomes is discussed, emphasizing their association with mortality, hospital stays, and the development of complications. Integration of chemo markers into prognostic models or scoring systems enhances risk stratification and informs therapeutic decisions. The review also delves into recent advances in chemo marker research and technology, emphasizing the potential for discovering novel chemo markers with enhanced diagnostic and prognostic capabilities. It highlights the use of high-throughput proteomics, genomics, and transcriptomics in identifying specific molecular signatures associated with septic shock. This contributes to a deeper understanding of the complex immune and inflammatory responses involved. In conclusion, chemo markers have emerged as valuable biomarkers in septic shock, offering potential utility in diagnosis, risk stratification, treatment monitoring, and prediction of outcomes. Continued research, validation, and integration into clinical practice are necessary to fully realize their potential in improving patient care and outcomes in septic shock.

Identification and validation of m6A-GPI signatures as a novel prognostic model for colorectal cancer

In order to develop an N6-methyladenosine-related gene prognostic index (m6A-GPI) that can predict the prognosis in colorectal cancer (CRC), we obtained m6A-related differentially expressed genes (DEGs) based on The Cancer Genome Atlas (TCGA) and m6Avar database, seven genes were screened by weighted gene co-expression network analysis (WGCNA) and least absolute shrinkage and selection operator (LASSO) analysis. Then, m6A-GPI was constructed based on the risk score. Survival analysis indicated that patients in the lower m6A-GPI group have more prolonged disease-free survival (DFS), and different clinical characteristic groups (tumor site and stage) also showed differential risk scores. In the analysis of the molecular characteristics, the risk score is positively associated with homologous recombination defects (HRD), copy number alterations (CNA), and the mRNA expression-based stemness index (mRNAsi). In addition, m6A-GPI also plays an essential role in tumor immune cell infiltration. The immune cell infiltration in the low m6A-GPI group is significantly higher in CRC. Moreover, we found that CIITA, one of the genes in m6A-GPI was up-regulated in CRC tissues based on real-time RT-PCR and Western blot. m6A-GPI is a promising prognostic biomarker that can be used to distinguish the prognosis of CRC patients in CRC.

New Actions on Actionable Mutations in Lung Cancers

Actionable mutations refer to DNA alterations that, if detected, would be expected to affect patients' response to treatments [...].