Machine Learning Protocols in Early Cancer Detection Based on Liquid Biopsy: A Survey

Advancing precision medicine in hepatocellular carcinoma: current challenges and future directions in liquid biopsy, immune microenvironment, single nucleotide polymorphisms, and conversion therapy

Hepatocellular carcinoma (HCC) remains a health concern characterized by heterogeneity and high mortality. Surgical resection, radiofrequency ablation, trans-arterial chemoembolization, and liver transplantation offer potentially curative treatments for early-stage disease, but recurrence remains high. Most patients present with advanced-stage HCC, where locoregional therapies are less effective, and systemic treatments-primarily multi-kinase inhibitors and immune checkpoint inhibitors-often yield limited responses. Precision medicine aims to tailor therapy to molecular and genetic profiles, yet its adoption in HCC is hindered by inter-/intra-tumoral heterogeneity and limited biopsy availability. Advances in molecular diagnostics support reintroducing tissue sampling to better characterize genetic, epigenetic, and immunological features. Liquid biopsy offers a minimally invasive method for capturing real-time tumor evolution, overcoming spatial and temporal heterogeneity. Artificial intelligence and machine learning are revolutionizing biomarker discovery, risk stratification, and treatment planning by integrating multi-omics data. Immunological factors such as tumor-infiltrating lymphocytes, natural killer cells, macrophages, and fibroblasts have emerged as determinants of HCC progression and treatment response. Conversion therapy-combining systemic agents with locoregional treatments-has showndemonstrated promise in downstaging unresectable HCC. Ongoing efforts to refine biomarker-driven approaches and optimize multi-modality regimens underscore precision medicine's potential to improve outcomes. PubMed (January 2002-February 2025) was searched for relevant studies.

Smart nanomedicines powered by artificial intelligence: a breakthrough in lung cancer diagnosis and treatment

Lung cancer remains one of the leading causes of cancer-related mortality worldwide, primarily due to challenges in early detection, suboptimal therapeutic efficacy, and severe adverse effects associated with conventional treatments. The convergence of nanotechnology and artificial intelligence (AI) offers transformative potential in precision oncology, enabling innovative solutions for lung cancer diagnosis and therapy. Intelligent nanomedicines facilitate targeted drug delivery, enhanced imaging, and theranostic applications, while AI-driven models harness big biomedical data to optimize nanomedicine design, functionality, and clinical application. This review explores the synergistic integration of AI and nanotechnology in lung cancer care, highlighting recent advancements, key challenges, and future directions for clinical translation. Ethical considerations, including data standardization and privacy concerns, are also addressed, providing a comprehensive roadmap to overcome current barriers and advance the adoption of AI-driven intelligent nanomedicines in precision oncology. This synthesis underscores the critical role of emerging technologies in revolutionizing lung cancer management.

Unveiling the impact of corticosteroid therapy on liquid biopsy-detected cell-free DNA levels in meningioma and glioblastoma patients

The liquid biopsy era has brought several possibilities to improve precision in patient care. Among the different sources of analytes, the cfDNA has been explored as a possible disease indicator, especially in cancer. Intracranial tumors still represent a challenge for liquid biopsy due to the blood-brain barrier being able to restrain both the migrating tumor cells and the liberation of cfDNA into the blood circulation. The aim of this work was to compare the differences between the cfDNA concentration in the plasma from patients with central nervous system tumors, and for this we analyzed a cohort of 188 individuals with glioblastoma (N = 57), brain metastasis (N = 15), meningioma (N = 90) and schwannoma (N = 26). Plasma samples were obtained immediately before tumor excision, and the cfDNA was isolated from the samples and quantified. The results showed that cfDNA plasma levels vary according to the tumors analyzed, with glioblastoma and brain metastasis presenting higher median levels of cfDNA than meningiomas and schwannomas. In addition, corticosteroid treatment resulted in higher cfDNA levels in meningioma and glioblastoma patients and vasogenic brain edema resulted in higher cfDNA levels only in meningioma patients. We hypothesize that cfDNA evaluation might have clinical monitoring value and that other clinical variables, such as corticosteroid used, should be considered during the liquid biopsy clinical evaluation of intracranial tumors.

AutoCancer as an automated multimodal framework for early cancer detection

Current studies in early cancer detection based on liquid biopsy data often rely on off-the-shelf models and face challenges with heterogeneous data, as well as manually designed data preprocessing pipelines with different parameter settings. To address those challenges, we present AutoCancer, an automated, multimodal, and interpretable transformer-based framework. This framework integrates feature selection, neural architecture search, and hyperparameter optimization into a unified optimization problem with Bayesian optimization. Comprehensive experiments demonstrate that AutoCancer achieves accurate performance in specific cancer types and pan-cancer analysis, outperforming existing methods across three cohorts. We further demonstrated the interpretability of AutoCancer by identifying key gene mutations associated with non-small cell lung cancer to pinpoint crucial factors at different stages and subtypes. The robustness of AutoCancer, coupled with its strong interpretability, underscores its potential for clinical applications in early cancer detection.

Constructing diagnostic signature of serum microRNAs using machine learning for early pan-cancer detection

BACKGROUND

Cancer is a major public health concern and the second leading cause of death worldwide. Various studies have reported the use of serum microRNAs (miRNAs) as non-invasive biomarkers for cancer detection. However, large-scale pan-cancer studies based on serum miRNAs have been relatively scarce.

METHODS

An optimized machine learning workflow, combining least absolute shrinkage and selection operator (LASSO) analyses, recursive feature elimination (RFE), and fourteen kinds of machine learning algorithms, was use to screen out candidate miRNAs from 2540 serum miRNAs and constructed a potent diagnostic signature (Cancer-related Serum miRNA Signatures) for pan-cancer detection, based on a serum miRNA expression dataset of 38,223 samples.

RESULT

Cancer-related Serum miRNA Signatures performed well in pan-cancer detection with an area under curve (AUC) of 0.999, 94.51% sensitivity, and 99.49% specificity in the external validation cohort, and represented an acceptable diagnostic performance for identifying early-stage tumors. Furthermore, the ability of multi-classification of tumors by serum miRNAs in pancreatic, colorectal, and biliary tract cancers was lower than that in other cancers, which showed accuracies of 59%, 58.5%, and 28.9%, respectively, indicating that the difference in serum miRNA expression profiles among a small number of tumor subtypes was not as significant as that between cancer samples and non-cancer controls.

CONCLUSION

We have developed a serum miRNA signature using machine learning that may be a cost-effective risk tool for pan-cancer detection. Our findings will benefit not only the predictive diagnosis of cancer but also a preventive and more personalized screening plan.

Liquid biopsy into the clinics: Current evidence and future perspectives

As precision oncology has become a major part of the treatment landscape in oncology, liquid biopsies have developed as a particularly powerful tool as it surmounts several limitations of traditional tissue biopsies. These biopsies involve most commonly the isolation of circulating extracellular nucleic acids, including cell-free DNA (cfDNA) and circulating tumor DNA (ctDNA), as well as circulating tumor cells (CTCs), typically from blood. The clinical applications of liquid biopsies are diverse, encompassing the initial diagnosis and cancer detection, the application as a tool for prognostication in early and advanced tumor settings, the identification of potentially actionable alterations, the monitoring of response and resistance under systemic therapy and the detection of resistance mechanisms, the differentiation of distinct immune checkpoint blockade response patterns through serial samples, the prediction of immune checkpoint blockade responses based on initial liquid biopsy characteristics and the assessment of tumor heterogeneity. Moreover, molecular relapse monitoring in early-stage cancers and the personalization of adjuvant or additive therapy via MRD have become a major field of research in recent years. Compared to tissue biopsies, liquid biopsies are less invasive and can be collected serially, offering real-time molecular insights. Furthermore, liquid biopsies may allow for a more holistic evaluation of a patient's disease, as they assess material from all tumor sites and can theoretically reflect tumor heterogeneity. Furthermore, quicker turnaround-time also constitutes an advantage of liquid biopsies. Disadvantages or hurdles include the challenge of detecting low amounts of tumor deposits in peripheral blood or other fluids and the potential of different amounts tumor-shedding from different metastatic sites, as well as potentially false-positive from clonal hematopoietic mutations of indeterminate potential (CHIP) mutations. The clinical utility of liquid biopsies still must be validated in most settings and further research has to be done. Clinal trials including alternate bodily fluids and leveraging AI-technology are expected to revolutionize the field of liquid biopsies.

Advances in Machine Learning Processing of Big Data from Disease Diagnosis Sensors

Exploring accurate, noninvasive, and inexpensive disease diagnostic sensors is a critical task in the fields of chemistry, biology, and medicine. The complexity of biological systems and the explosive growth of biomarker data have driven machine learning to become a powerful tool for mining and processing big data from disease diagnosis sensors. With the development of bioinformatics and artificial intelligence (AI), machine learning models formed by data mining have been able to guide more sensitive and accurate molecular computing. This review presents an overview of big data collection approaches and fundamental machine learning algorithms and discusses recent advances in machine learning and molecular computational disease diagnostic sensors. More specifically, we highlight existing modular workflows and key opportunities and challenges for machine learning to achieve disease diagnosis through big data mining.

Liquid biopsy: New opportunities for precision medicine in hepatocellular carcinoma care

Liquid biopsy, specifically the analysis of circulating tumor DNA (ctDNA), offers a non-invasive approach for hepatocellular carcinoma (HCC) diagnosis and management. However, its implementation in the clinical setting is difficult due to challenges such as low ctDNA yield and difficulty in understanding the mutation signals from background noise. This review highlights the crucial role of artificial intelligence (AI) in addressing these limitations and in improving discoveries in the field of liquid biopsy for HCC care. Combining AI with liquid biopsy data can offer a promising future for the discovery of novel biomarkers and an AI-powered clinical decision support system (CDSS) can turn liquid biopsy into an important tool for personalized management of HCC. Despite the current challenges, the integration of AI shows promise to significantly improve patient outcomes and revolutionize the field of oncology.

Circulating cell-free DNA as a diagnostic and prognostic marker for cervical cancer

Circulating cell-free DNA (cfDNA) is a promising tool for liquid biopsy-based tests. cfDNA has been reported to help in the diagnosis, quantification of minimal residual disease, prognosis, and identification of mutations conferring resistance in various types of cancers. Cervical cancer is the fourth most common cancer among women worldwide. High-risk human papillomavirus (hr-HPV) infections have been associated with almost all cervical cancers. Lack of HPV vaccines in national vaccination programs and irregular screening strategies in nations with low or moderate levels of human development index have led to cervical cancer becoming the second leading cause of cancer mortality in women. As HPV integration and overexpression of E6/E7 oncoprotein are crucial steps in the development of cancer, HPV cfDNA could potentially be used as a specific biomarker for the detection of cervical cancer. Many studies have used HPV cfDNA and other gene mutations or mRNA expression profiles for diagnosis and disease surveillance in patients with cervical cancer at various stages of disease progression. In this review we present an overview of different studies discussing the utility of cfDNA in cervical cancer and summarize the evidence supporting its potential use in diagnosis and treatment monitoring.

Artificial intelligence in salivary biomarker discovery and validation for oral diseases

Salivary biomarkers can improve the efficacy, efficiency, and timeliness of oral and maxillofacial disease diagnosis and monitoring. Oral and maxillofacial conditions in which salivary biomarkers have been utilized for disease-related outcomes include periodontal diseases, dental caries, oral cancer, temporomandibular joint dysfunction, and salivary gland diseases. However, given the equivocal accuracy of salivary biomarkers during validation, incorporating contemporary analytical techniques for biomarker selection and operationalization from the abundant multi-omics data available may help improve biomarker performance. Artificial intelligence represents one such advanced approach that may optimize the potential of salivary biomarkers to diagnose and manage oral and maxillofacial diseases. Therefore, this review summarized the role and current application of techniques based on artificial intelligence for salivary biomarker discovery and validation in oral and maxillofacial diseases.

Development of a blood-based extracellular vesicle classifier for detection of early-stage pancreatic ductal adenocarcinoma

BACKGROUND

Pancreatic ductal adenocarcinoma (PDAC) has an overall 5-year survival rate of just 12.5% and thus is among the leading causes of cancer deaths. When detected at early stages, PDAC survival rates improve substantially. Testing high-risk patients can increase early-stage cancer detection; however, currently available liquid biopsy approaches lack high sensitivity and may not be easily accessible.

METHODS

Extracellular vesicles (EVs) were isolated from blood plasma that was collected from a training set of 650 patients (105 PDAC stages I and II, 545 controls). EV proteins were analyzed using a machine learning approach to determine which were the most informative to develop a classifier for early-stage PDAC. The classifier was tested on a validation cohort of 113 patients (30 PDAC stages I and II, 83 controls).

RESULTS

The training set demonstrates an AUC of 0.971 (95% CI = 0.953-0.986) with 93.3% sensitivity (95% CI: 86.9-96.7) at 91.0% specificity (95% CI: 88.3-93.1). The trained classifier is validated using an independent cohort (30 stage I and II cases, 83 controls) and achieves a sensitivity of 90.0% and a specificity of 92.8%.

CONCLUSIONS

Liquid biopsy using EVs may provide unique or complementary information that improves early PDAC and other cancer detection. EV protein determinations herein demonstrate that the AC Electrokinetics (ACE) method of EV enrichment provides early-stage detection of cancer distinct from normal or pancreatitis controls.

Liquid biopsies for cancer: From bench to clinic

Over the past two decades, liquid biopsy has been increasingly used as a supplement, or even, a replacement to the traditional biopsy in clinical oncological practice, due to its noninvasive and early detectable properties. The detections can be based on a variety of features extracted from tumor‑derived entities, such as quantitative alterations, genetic changes, and epigenetic aberrations, and so on. So far, the clinical applications of cancer liquid biopsy mainly aimed at two aspects, prediction (early diagnosis, prognosis and recurrent evaluation, therapeutic response monitoring, etc.) and intervention. In spite of the rapid development and great contributions achieved, cancer liquid biopsy is still a field under investigation and deserves more clinical practice. To better open up future work, here we systematically reviewed and compared the latest progress of the most widely recognized circulating components, including circulating tumor cells, cell-free circulating DNA, noncoding RNA, and nucleosomes, from their discovery histories to clinical values. According to the features applied, we particularly divided the contents into two parts, beyond epigenetics and epigenetic-based. The latter was considered as the highlight along with a brief overview of the advances in both experimental and bioinformatic approaches, due to its unique advantages and relatively lack of documentation.

Is There a Role for Machine Learning in Liquid Biopsy for Brain Tumors? A Systematic Review

The paucity of studies available in the literature on brain tumors demonstrates that liquid biopsy (LB) is not currently applied for central nervous system (CNS) cancers. The purpose of this systematic review focused on the application of machine learning (ML) to LB for brain tumors to provide practical guidance for neurosurgeons to understand the state-of-the-art practices and open challenges. The herein presented study was conducted in accordance with the PRISMA-P (preferred reporting items for systematic review and meta-analysis protocols) guidelines. An online literature search was launched on PubMed/Medline, Scopus, and Web of Science databases using the following query: "((Liquid biopsy) AND (Glioblastoma OR Brain tumor) AND (Machine learning OR Artificial Intelligence))". The last database search was conducted in April 2023. Upon the full-text review, 14 articles were included in the study. These were then divided into two subgroups: those dealing with applications of machine learning to liquid biopsy in the field of brain tumors, which is the main aim of this review (n = 8); and those dealing with applications of machine learning to liquid biopsy in the diagnosis of other tumors (n = 6). Although studies on the application of ML to LB in the field of brain tumors are still in their infancy, the rapid development of new techniques, as evidenced by the increase in publications on the subject in the past two years, may in the future allow for rapid, accurate, and noninvasive analysis of tumor data. Thus making it possible to identify key features in the LB samples that are associated with the presence of a brain tumor. These features could then be used by doctors for disease monitoring and treatment planning.

Biomarker Reproducibility Challenge: A Review of Non-Nucleotide Biomarker Discovery Protocols from Body Fluids in Breast Cancer Diagnosis

Breast cancer has now become the most commonly diagnosed cancer, accounting for one in eight cancer diagnoses worldwide. Non-invasive diagnostic biomarkers and associated tests are superlative candidates to complement or improve current approaches for screening, early diagnosis, or prognosis of breast cancer. Biomarkers detected from body fluids such as blood (serum/plasma), urine, saliva, nipple aspiration fluid, and tears can detect breast cancer at its early stages in a minimally invasive way. The advancements in high-throughput molecular profiling (omics) technologies have opened an unprecedented opportunity for unbiased biomarker detection. However, the irreproducibility of biomarkers and discrepancies of reported markers have remained a major roadblock to clinical implementation, demanding the investigation of contributing factors and the development of standardised biomarker discovery pipelines. A typical biomarker discovery workflow includes pre-analytical, analytical, and post-analytical phases, from sample collection to model development. Variations introduced during these steps impact the data quality and the reproducibility of the findings. Here, we present a comprehensive review of methodological variations in biomarker discovery studies in breast cancer, with a focus on non-nucleotide biomarkers (i.e., proteins, lipids, and metabolites), highlighting the pre-analytical to post-analytical variables, which may affect the accurate identification of biomarkers from body fluids.

A cardiologist's guide to machine learning in cardiovascular disease prognosis prediction

A modern-day physician is faced with a vast abundance of clinical and scientific data, by far surpassing the capabilities of the human mind. Until the last decade, advances in data availability have not been accompanied by analytical approaches. The advent of machine learning (ML) algorithms might improve the interpretation of complex data and should help to translate the near endless amount of data into clinical decision-making. ML has become part of our everyday practice and might even further change modern-day medicine. It is important to acknowledge the role of ML in prognosis prediction of cardiovascular disease. The present review aims on preparing the modern physician and researcher for the challenges that ML might bring, explaining basic concepts but also caveats that might arise when using these methods. Further, a brief overview of current established classical and emerging concepts of ML disease prediction in the fields of omics, imaging and basic science is presented.

Tailored point-of-care biosensors for liquid biopsy in the field of oncology

In the field of cancer detection, technologies to analyze tumors using biomarkers circulating in fluids such as blood have developed rapidly based on liquid biopsy. A proactive approach to early cancer detection can lead to more effective treatments with minimal side effects and better long-term patient survival. However, early detection of cancer is hindered by the existing limitations of conventional cancer diagnostic methods. To enable early diagnosis and regular monitoring and improve automation, the development of integrated point-of-care (POC) and biosensors is needed. This is expected to fundamentally change the diagnosis, management, and monitoring of response to treatment of cancer. POC-based techniques will provide a way to avoid complications that occur after invasive tissue biopsy, such as bleeding, infection, and pain. The aim of this study is to provide a comprehensive view of biosensors and their clinical relevance in oncology for the detection of biomarkers with liquid biopsies of proteins, miRNA, ctDNA, exosomes, and cancer cells. The preceding discussion also illustrates the changing landscape of liquid biopsy-based cancer diagnosis through nanomaterials, machine learning, artificial intelligence, wearable devices, and sensors, many of which apply POC design principles. With the advent of sensitive, selective, and timely detection of cancer, we see the field of POC technology for cancer detection and treatment undergoing a positive paradigm shift in the foreseeable future.

COL10A1 allows stratification of invasiveness of colon cancer and associates to extracellular matrix and immune cell enrichment in the tumor parenchyma

BACKGROUND

Treatment options for metastatic colorectal cancer (CRC) are mostly ineffective. We present new evidence that tumor tissue collagen type X alpha 1 (COL10A1) is a relevant candidate biomarker to improve this dilemma.

METHODS

Several public databases had been screened to observe COL10A1 expression in transcriptome levels with cell lines and tissues. Protein interactions and alignment to changes in clinical parameters and immune cell invasion were performed, too. We also used algorithms to build a novel COL10A1-related immunomodulator signature. Various wet-lab experiments were conducted to quantify COL10A1 protein and transcript expression levels in disease and control cell models.

RESULTS

COL10A1 mRNA levels in tumor material is clinical and molecular prognostic, featuring upregulation compared to non-cancer tissue, increase with histomorphological malignancy grading of the tumor, elevation in tumors that invade perineural areas, or lymph node invasion. Transcriptomic alignment noted a strong positive correlation of COL10A1 with transcriptomic signature of cancer-associated fibroblasts (CAFs) and populations of the immune compartment, namely, B cells and macrophages. We verified those findings in functional assays showing that COL10A1 are decreased in CRC cells compared to fibroblasts, with strongest signal in the cell supernatant of the cells.

CONCLUSION

COL10A1 abundance in CRC tissue predicts metastatic and immunogenic properties of the disease. COL10A1 transcription may mediate tumor cell interaction with its stromal microenvironment.

Significance of ZEB2 in the immune microenvironment of colon cancer

Background: ZEB2 is a protein-coding gene that is differentially expressed in tumors and can regulate the growth of tumor cells. This study investigated the specific regulatory mechanism of ZEB2 in COAD, a common cancer with high rates of morbidity and mortality.

Methods: Multi-omics panoramic display of expression and function of ZEB2 in colon cancer. R software was used to study the expression of ZEB2 in 33 types of cancer. Furthermore, RT-PCR was used to detect the expression of ZEB2 in colon cancers and para-cancer tissues, as well as in colon cancer cells and normal cells. The ssGSEA was then used to explore the relationship between ZEB2 and immune cells, with UALCAN, EWAS and MEXPRESS applied to explore the methylation of ZEB2. The relationship between immunomodulators and chemokines (or receptors) based on expression data, copy number data, methylation data, and mutation data of ZEB2 was investigated using TISIDB. Finally, a protein interaction network of ZEB2 was constructed, and GO and KEGG analyses were performed on the differentially expressed genes.

Results: ZEB2 is downregulated in most cancers, including COAD. The infiltration of the immune cells NK CD56 and Th17 cells was negatively correlated with ZEB2 expression, while the other 22 cells were positively correlated with ZEB2 expression. The DNA methylation of ZEB2 and the methylation of the ZEB2 protein on the EWAS website increased significantly. Analysis of the methylation levels and ZEB2 expression revealed that only the DNA methylation level and the expression of ZEB2 were significantly negatively correlated. The tumor-infiltrating lymphocytes positively correlated with the expression of ZEB2 but negatively correlated with the methylation of ZEB2. The same trend was observed for immunomodulators, chemokines, and receptors. The network showed that the protein performed certain biological functions, thereby affecting disease symptoms.

Conclusion: These findings provide evidence that ZEB2-based therapy may represent a powerful treatment strategy for COAD.

Liquid biopsies for early diagnosis of brain tumours: in silico mathematical biomarker modelling

Brain tumours are the biggest cancer killer in those under 40 and reduce life expectancy more than any other cancer. Blood-based liquid biopsies may aid early diagnosis, prediction and prognosis for brain tumours. It remains unclear whether known blood-based biomarkers, such as glial fibrillary acidic protein (GFAP), have the required sensitivity and selectivity. We have developed a novel in silico model which can be used to assess and compare blood-based liquid biopsies. We focused on GFAP, a putative biomarker for astrocytic tumours and glioblastoma multi-formes (GBMs). In silico modelling was paired with experimental measurement of cell GFAP concentrations and used to predict the tumour volumes and identify key parameters which limit detection. The average GBM volumes of 449 patients at Leeds Teaching Hospitals NHS Trust were also measured and used as a benchmark. Our model predicts that the currently proposed GFAP threshold of 0.12 ng ml-1 may not be suitable for early detection of GBMs, but that lower thresholds may be used. We found that the levels of GFAP in the blood are related to tumour characteristics, such as vasculature damage and rate of necrosis, which are biological markers of tumour aggressiveness. We also demonstrate how these models could be used to provide clinical insight.

Mini-review: Recent advances in post-translational modification site prediction based on deep learning

Post-translational modifications (PTMs) are closely linked to numerous diseases, playing a significant role in regulating protein structures, activities, and functions. Therefore, the identification of PTMs is crucial for understanding the mechanisms of cell biology and diseases therapy. Compared to traditional machine learning methods, the deep learning approaches for PTM prediction provide accurate and rapid screening, guiding the downstream wet experiments to leverage the screened information for focused studies. In this paper, we reviewed the recent works in deep learning to identify phosphorylation, acetylation, ubiquitination, and other PTM types. In addition, we summarized PTM databases and discussed future directions with critical insights.

Extracellular Vesicle-Based Multianalyte Liquid Biopsy as a Diagnostic for Cancer

Liquid biopsy is the analysis of materials shed by tumors into circulation, such as circulating tumor cells, nucleic acids, and extracellular vesicles (EVs), for the diagnosis and management of cancer. These assays have rapidly evolved with recent FDA approvals of single biomarkers in patients with advanced metastatic disease. However, they have lacked sensitivity or specificity as a diagnostic in early-stage cancer, primarily due to low concentrations in circulating plasma. EVs, membrane-enclosed nanoscale vesicles shed by tumor and other cells into circulation, are a promising liquid biopsy analyte owing to their protein and nucleic acid cargoes carried from their mother cells, their surface proteins specific to their cells of origin, and their higher concentrations over other noninvasive biomarkers across disease stages. Recently, the combination of EVs with non-EV biomarkers has driven improvements in sensitivity and accuracy; this has been fueled by the use of machine learning (ML) to algorithmically identify and combine multiple biomarkers into a composite biomarker for clinical prediction. This review presents an analysis of EV isolation methods, surveys approaches for and issues with using ML in multianalyte EV datasets, and describes best practices for bringing multianalyte liquid biopsy to clinical implementation. Expected final online publication date for the Annual Review of Biomedical Data Science, Volume 5 is August 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Risk Factor Analysis for Predicting the Onset of Rotator Cuff Calcific Tendinitis Based on Artificial Intelligence

Background

Symptomatic rotator cuff calcific tendinitis (RCCT) is a common shoulder disorder, and approaches combined with artificial intelligence greatly facilitate the development of clinical practice. Current scarce knowledge of the onset suggests that clinicians may need to explore this disease thoroughly.

Methods

Clinical data were retrospectively collected from subjects diagnosed with RCCT at our institution within the period 2008 to 2020. A standardized questionnaire related to shoulder symptoms was completed in all cases, and standardized radiographs of both shoulders were extracted using a human-computer interactive electronic medical system (EMS) to clarify the clinical diagnosis of symptomatic RCCT. Based on the exclusion of asymptomatic subjects, risk factors in the baseline characteristics significantly associated with the onset of symptomatic RCCT were assessed via stepwise logistic regression analysis.

Results

Of the 1,967 consecutive subjects referred to our academic institution for shoulder discomfort, 237 were diagnosed with symptomatic RCCT (12.05%). The proportion of women and the prevalence of clinical comorbidities were significantly higher in the RCCT cohort than those in the non-RCCT cohort. Stepwise logistic regression analysis confirmed that female gender, hyperlipidemia, diabetes mellitus, and hypothyroidism were independent risk factors for the entire cohort. Stratified by gender, the study found a partial overlap of risk factors contributing to morbidity in men and women. Diagnosis of hyperlipidemia, diabetes mellitus, and hypothyroidism in male cases and diabetes mellitus in female cases were significantly associated with symptomatic RCCT.

Conclusion

Independent predictors of symptomatic RCCT are female, hyperlipidemia, diabetes mellitus, and hypothyroidism. Men diagnosed with hyperlipidemia, diabetes mellitus, and hypothyroidism are at high risk for symptomatic RCCT, while more medical attention is required for women with diabetes mellitus. Artificial intelligence offers pioneering innovations in the diagnosis and treatment of musculoskeletal disorders, and careful assessment through individualized risk stratification can help predict onset and targeted early stage treatment.

Early-stage multi-cancer detection using an extracellular vesicle protein-based blood test

Background

Detecting cancer at early stages significantly increases patient survival rates. Because lethal solid tumors often produce few symptoms before progressing to advanced, metastatic disease, diagnosis frequently occurs when surgical resection is no longer curative. One promising approach to detect early-stage, curable cancers uses biomarkers present in circulating extracellular vesicles (EVs). To explore the feasibility of this approach, we developed an EV-based blood biomarker classifier from EV protein profiles to detect stages I and II pancreatic, ovarian, and bladder cancer.

Methods

Utilizing an alternating current electrokinetics (ACE) platform to purify EVs from plasma, we use multi-marker EV-protein measurements to develop a machine learning algorithm that can discriminate cancer cases from controls. The ACE isolation method requires small sample volumes, and the streamlined process permits integration into high-throughput workflows.

Results

In this case-control pilot study, comparison of 139 pathologically confirmed stage I and II cancer cases representing pancreatic, ovarian, or bladder patients against 184 control subjects yields an area under the curve (AUC) of 0.95 (95% CI: 0.92 to 0.97), with sensitivity of 71.2% (95% CI: 63.2 to 78.1) at 99.5% (97.0 to 99.9) specificity. Sensitivity is similar at both early stages [stage I: 70.5% (60.2 to 79.0) and stage II: 72.5% (59.1 to 82.9)]. Detection of stage I cancer reaches 95.5% in pancreatic, 74.4% in ovarian (73.1% in Stage IA) and 43.8% in bladder cancer.

Conclusions

This work demonstrates that an EV-based, multi-cancer test has potential clinical value for early cancer detection and warrants future expanded studies involving prospective cohorts with multi-year follow-up.

Finding cancer early can make treatment easier and improve odds of survival. However, many tumors go unnoticed until they have grown large enough to cause symptoms. While scans can detect tumors earlier, routine full-body imaging is impractical for population screening. New cancer detection methods being explored are based on observations that tumors release tiny particles called extracellular vesicles (EVs) into the bloodstream, containing proteins from the tumor. Here, we used a method to purify EVs from patients’ blood followed by a method to detect tumor proteins in the EVs. Our method quickly and accurately detected early-stage pancreatic, ovarian, or bladder cancer. With further testing, this method may provide a useful screening tool for clinicians to detect cancers at an earlier stage.

Hinestrosa et al. describe the early-stage detection of cancer using biomarkers present in circulating extracellular vesicles purified via an alternating current electrokinetics platform. They show, in a case-control study, that 95.7% of pancreatic, 75.0% of ovarian and 43.8% of bladder stage I and II cancers can be detected.

Liquid Biopsy and Artificial Intelligence as Tools to Detect Signatures of Colorectal Malignancies: A Modern Approach in Patient's Stratification

Colorectal cancer (CRC) is the second most frequently diagnosed type of cancer and a major worldwide public health concern. Despite the global efforts in the development of modern therapeutic strategies, CRC prognosis is strongly correlated with the stage of the disease at diagnosis. Early detection of CRC has a huge impact in decreasing mortality while pre-lesion detection significantly reduces the incidence of the pathology. Even though the management of CRC patients is based on robust diagnostic methods such as serum tumor markers analysis, colonoscopy, histopathological analysis of tumor tissue, and imaging methods (computer tomography or magnetic resonance), these strategies still have many limitations and do not fully satisfy clinical needs due to their lack of sensitivity and/or specificity. Therefore, improvements of the current practice would substantially impact the management of CRC patients. In this view, liquid biopsy is a promising approach that could help clinicians screen for disease, stratify patients to the best treatment, and monitor treatment response and resistance mechanisms in the tumor in a regular and minimally invasive manner. Liquid biopsies allow the detection and analysis of different tumor-derived circulating markers such as cell-free nucleic acids (cfNA), circulating tumor cells (CTCs), and extracellular vesicles (EVs) in the bloodstream. The major advantage of this approach is its ability to trace and monitor the molecular profile of the patient's tumor and to predict personalized treatment in real-time. On the other hand, the prospective use of artificial intelligence (AI) in medicine holds great promise in oncology, for the diagnosis, treatment, and prognosis prediction of disease. AI has two main branches in the medical field: (i) a virtual branch that includes medical imaging, clinical assisted diagnosis, and treatment, as well as drug research, and (ii) a physical branch that includes surgical robots. This review summarizes findings relevant to liquid biopsy and AI in CRC for better management and stratification of CRC patients.

Liquid Biopsy as a Prognostic and Theranostic Tool for the Management of Pancreatic Ductal Adenocarcinoma

Pancreatic ductal adenocarcinomas (PDAC) represent one of the deadliest cancers worldwide. Survival is still low due to diagnosis at an advanced stage and resistance to treatment. Herein, we review the main types of liquid biopsy able to help in both prognosis and adaptation of treatments.