Early-stage Detection Research Articles

A rigorous multi-laboratory study of known PDAC biomarkers identifies increased sensitivity and specificity over CA19-9 alone

A blood test that enables surveillance for early-stage pancreatic ductal adenocarcinoma (PDAC) is an urgent need. Independent laboratories have reported PDAC biomarkers that could improve biomarker performance over CA19-9 alone, but the performance of the previously reported biomarkers in combination is not known. Therefore, we conducted a coordinated case/control study across multiple laboratories using common sets of blinded training and validation samples (132 and 295 plasma samples, respectively) from PDAC patients and non-PDAC control subjects representing conditions under which surveillance occurs. We analyzed the training set to identify candidate biomarker combination panels using biomarkers across laboratories, and we applied the fixed panels to the validation set. The panels identified in the training set, CA19-9 with CA199.STRA, LRG1, TIMP-1, TGM2, THSP2, ANG, and MUC16.STRA, achieved consistent performance in the validation set. The panel of CA19-9 with the glycan biomarker CA199.STRA improved sensitivity from 0.44 with 0.98 specificity for CA19-9 alone to 0.71 with 0.98 specificity (p < 0.001, 1000-fold bootstrap). Similarly, CA19-9 combined with the protein biomarker LRG1 and CA199.STRA improved specificity from 0.16 with 0.94 sensitivity for CA19-9 to 0.65 with 0.89 sensitivity (p < 0.001, 1000-fold bootstrap). We further validated significantly improved performance using biomarker panels that did not include CA19-9. This study establishes the effectiveness of a coordinated study of previously discovered biomarkers and identified panels of those biomarkers that significantly increased the sensitivity and specificity of early-stage PDAC detection in a rigorous validation trial.

Smart and autonomous monitoring of cracking in concrete structures with PZT sensor array-based hybrid sensing

Detecting microcracks in concrete structures is crucial for maintaining structural integrity; however, current methods often lack the precision, objectivity, and sensitivity needed for early-stage detection and monitoring. This study introduces a pioneering hybrid sensing approach that combines coherent and incoherent ultrasonic wave fields with surface-mounted PZT-based sensors, significantly advancing the state-of-the-art. The sensors are positioned at specified locations on a notched concrete beam and operated in the actuator-receiver (AR) mode, allowing for the manipulation of fracture width at the notch to achieve distinct degrees of damage. By evaluating the ultrasonic waves received from various AR configurations, we developed robust damage indices: the attenuation factor and diffusivity ratio. These indices provide objective metrics for evaluating the degree of damage, addressing the limitations of existing techniques. Key results demonstrate that the attenuation factor can detect crack widths as small as 10 µm at a 120 kHz frequency, surpassing traditional methods. Nevertheless, its sensitivity diminishes if the crack width exceeds 100 µm. Additionally, the diffusivity ratio remains sensitive to cracks beyond 200 µm and shows a substantial 40 % decrease even for non-visible fractures, offering a comprehensive assessment of fracture propagation. These advancements not only enhance early detection and monitoring precision but also offer a deeper understanding of fracture mechanics, paving the way for improved structural health monitoring and maintenance strategies.

A HybridOpt approach for early Alzheimer’s Disease diagnostics with Ant Lion Optimizer (ALO)

Alzheimer disease is a neurological disorder that affects the elderly, caused by abnormal protein buildup in the brain. It leads to difficulties such as financial mismanagement, disorientation, behavioral changes, and repetitive speech. The existing methods use traditional features to detect the early signs of AD with low detection accuracy. The potential features have to be identified that represent best the patterns associated with alzheimers. Feature selection using ant lion optimization resolves the issue by using complementarty information from hybrid features. The proposed HybridOpt pipeling for AD diagnosis combines the high level and low level features for early stage detection The objective of this work is to select efficient features from different deep networks, such as AlexNet, Googlenet, VGG16, ResNet, Efficient, DenseNet, and traditional texture features. Ant Lion Optimization is used to select the best feature among the deep network and traditional texture feature groups. Extensive experimentation on two highly challenging datasets called the Alzheimer’s disease neuroimage dataset and KAGGLE reveals that the proposed HybridOpt pipeline achieves an accuracy of 99% and 98.1% respectively.

Intelligent system based on multiple networks for accurate ovarian tumor semantic segmentation

Ovarian tumors, especially malignant ones, represent a global concern, with increased prevalence in recent years. More accurate medical support systems are urgently needed to support medical staff in obtaining an efficient ovarian tumors diagnosis since detection in early stages could lead to immediately applying appropriate treatment, and implicitly improving the survival rate. The current paper aims to demonstrate that more accurate systems could be designed by combining different convolutional neural networks using different custom combination approaches and by selecting the appropriate networks to be involved in the ensemble model to achieve the best performance metrics. It is essential to understand if combining all experimented networks or only the best-performing ones could always lead to the most effective results or not. The current paper is structured in three main phases. The first step is to propose the individual networks involved in the experiments. Five DeepLab-V3+ networks with different encoders (ResNet-18, ResNet-50, MobileNet-V2, InceptionResNet-V2, and Xception) were used. In the second step, the paper proposes a custom algorithm to combine multiple individual semantic segmentation networks, while the last step describes the iterative selection approach for selecting all individual networks to be combined so that the most accurate ensemble is obtained. The system performing semantic segmentation for different types of ovarian tumors, covering both benign and malignant ones, achieved 91.18 % Intersection over union (IoU), thus overperforming all individual networks. The proposed method could be extended so that more powerful deep learning models could be used.

103P Epigenetic regulated genes enhanced fragmentomics-based model for early-stage lung cancer detection

103P Epigenetic regulated genes enhanced fragmentomics-based model for early-stage lung cancer detection

1180P An integrated metabolomics-based platform for early-stage detection of multiple cancers

1180P An integrated metabolomics-based platform for early-stage detection of multiple cancers

A CRITICAL APPRAISAL OF ASTHISAMHARAKADI CHOORNA IN THE MANAGEMENT OF ASTHIKSHAYA WITH REFERENCE TO OSTEOPENIA AND OSTEOPOROSIS

Osteoporosis is the most common bone disease, representing a major public health issue. Osteopenia &amp; Osteoporosis characterize a spectrum of conditions that present with decreased bone mass and disrupted bone microarchitecture. According to Ayurveda, Asthikshaya (diminution of bone) and Asthisoushirya (porosity of bone) are the two conditions which allies with osteopenia and osteoporosis. Asthikshaya and Asthisoushirya consequently lead to high susceptibility of Asthibhagna (fracture). This bone loss is preventable through adequate nutrition, physical activity and appropriate treatment protocols. Detection and prevention in early stages is essential as it may cause burden at individual and socioeconomic level. Ayurveda provides several therapeutic approaches to remodel the depleted or degenerated tissues. Oral administration of Oushadha yogas (medicinal formulations) is one of the highly accepted therapeutic modality. Asthisamharakadi choorna is one such polyherbal formulation which is mentioned in Chakradatta in the context of Bhagna Chikitsa. The review aims to ascertain the pharmacological effects of ingredients of Asthisamharakadi choorna and to propose its probable mode of action in Asthikshaya (osteopenia). The detailed review of the formulation and its constituents was carried from several Ayurvedic classical texts and published research articles. This review presents a detailed understanding on anti-oxidant, anti-inflammatory and osteoblastogenesis activity of phytoconstituents of Asthisamharakadi choorna. It enables to comprehend the bone remodelling and stabilizing effect of phytoconstituents present in each ingredient of Asthisamharakadi choorna. The pharmacological appraisal of the formulation encourages the clinical employability of Asthisamharakadi choorna for the prevention and management of Asthikshaya or Asthisoushirya, osteopenia and osteoporosis.

Comprehensive serum glycopeptide spectra analysis to identify early-stage epithelial ovarian cancer

Epithelial ovarian cancer (EOC) is widely recognized as the most lethal gynecological malignancy; however, its early-stage detection remains a considerable clinical challenge. To address this, we have introduced a new method, named Comprehensive Serum Glycopeptide Spectral Analysis (CSGSA), which detects early-stage cancer by combining glycan alterations in serum glycoproteins with tumor markers. We detected 1712 glycopeptides using liquid chromatography–mass spectrometry from the sera obtained from 564 patients with EOC and 1149 controls across 13 institutions. Furthermore, we used a convolutional neural network to analyze the expression patterns of the glycopeptides and tumor markers. Using this approach, we successfully differentiated early-stage EOC (Stage I) from non-EOC, with an area under the curve (AUC) of 0.924 in receiver operating characteristic (ROC) analysis. This method markedly outperforms conventional tumor markers, including cancer antigen 125 (CA125, 0.842) and human epididymis protein 4 (HE4, 0.717). Notably, our method exhibited remarkable efficacy in differentiating early-stage ovarian clear cell carcinoma from endometrioma, achieving a ROC-AUC of 0.808, outperforming CA125 (0.538) and HE4 (0.557). Our study presents a promising breakthrough in the early detection of EOC through the innovative CSGSA method. The integration of glycan alterations with cancer-related tumor markers has demonstrated exceptional diagnostic potential.

Ultrasensitive electrochemiluminescence biosensor constructed by luminol-diazonium ion functionalized Au/MXene nanocomposites for early stage detection of disease in human

MicroRNAs (miRNAs) are important biomarkers for tracking occurrence and development of many diseases, therefore, the reliable, sensitive, fast and accurate detection of miRNAs plays an extremely critical role in clinic diagnosis and treatment of early stage diseases. Herein, we developed ultrasensitive electrochemiluminescence (ECL) biosensor constructed by luminol-diazonium ion functionalized Au/MXene nanocomposites for early stage detection of kidney disease in human. The synergistic effect of MXene and Au nanoparticles significantly enhanced the ECL emission of luminol up to 6.9-fold due to their shortened electron transfer distance and excellent catalytic performance. The loading efficiency of luminol on MXene could be as high as ∼7 %, enabling the enrichment of luminol on MXene nanosheets. The enhanced ECL signal and excessive loading of luminol allowed the Au-MXene-luminol as an excellent ECL labeling agent, which was further developed for the determination of miRNA-377 according to the sandwich-like assay. The as-developed miRNA-377 biosensor had ultrahigh sensitivity, wide linear range (from ∼50 aM to ∼1 nM), low limit of detection (∼13.2 aM) and high selectivity (∼82.6 %) for highly homologous miRNA with mismatched single-bases. The ultrasensitive ECL biosensor was successfully applied to determine miRNA-377 in the serum samples of early stage kidney patients, which were well consistent with the clinic standard of quantitative real-time polymerase chain reaction method. The ultrasensitive ECL-labeling biosensor with high selectivity is very promising for universally screening any kinds of biomarkers with corresponding specific targets.

Machine learning-based acoustic emission technique for corrosion-induced damage monitoring in reinforced concrete structures

Early-stage detection of corrosion in reinforcement embedded inside concrete, generally considered as the major problem in structures under extreme marine environments, can help to schedule timely maintenance/repair and to avoid any catastrophic failure. However, quantitative evaluation of the degree of deterioration, especially at a very early stage, i.e., before its appearance on the surface, is extremely difficult due to the complex process in heterogeneous material. This study aims to characterize the critical damage stages in reinforced concrete specimens under accelerated conditions using the Acoustic emission (AE) damage quantification methods supported by machine learning (ML) techniques. The stages of corrosion-induced damage are predicted by a two-step predictive model that involve both regression and classification tasks. Three supervised regression models — support vector regression (SVR), relevance vector machine (RVM) and kernel ridge regression (KRR) —are first adopted to evaluate the amount of current. Then the output from regression model is given as an input to the classification problem to predict the discrete class label output. Characterized damage stages are validated based on mass loss and crack width measurements. The results show that the corrosion initiation (at day 3) and crack formation (at day 7) can be determined from the sudden change in acoustic parameters. Further, a double layer (supervised-unsupervised) model is proposed which is found be more effective in correctly detecting the progression of damage. The findings indicate that the proposed approach that combines corrosion detection by analysing AE signals with ML technique can accurately and robustly predict corrosion severity.

Reduced graphene oxide based ultrasensitive resistive sensor for detection of CA125

Early-stage detection of any cancer significantly improves the survival rates by enabling clinicians to design simpler and more effective treatment options, leading to a cure or remission. Early diagnosis of ovarian cancer, the leading cause of gynaecological cancer related mortalities, relies heavily on accurate detection of the serum biomarker CA125. This work presents a simple rGO/monoclonal antibody (mAB)/bovine serum albumin (BSA) based 2-port resistive sensor for CA125. The binding of mAB on rGO was confirmed by atomic force microscopy which showed increase in thickness of the device from 1.4 nm to approximately 40–60 nm after the mAB anchored on the device. FESEM further confirmed the morphologies of rGO, rGO/mAB, and rGO/mAB/CA125. The sensor exhibited impressive response ranging from 1.28% to 113.4% for 1 pg/mL to 300 ng/mL CA125. Notably, the rGO/mAB/BSA sensor displayed high selectivity towards CA125 and a readout circuit was designed, assembled, and tested with the sensors to get a portable device for detecting CA125. The developed sensors were tested with 9 clinical samples and were found to be determining the CA125 concentration accurately.

OS IMPACTOS DAS TÉCNICAS DE RASTREIO DE CA DE PULMÃO E SEU IMPACTO NA MORTALIDADE NA POPULAÇÃO TABAGISTA

To present the theme of the impacts of lung cancer screening and its impact on mortality in the smoking population. Lung cancer is the neoplasm with the highest incidence and mortality in the world. Its natural history is characterized by rapid progression and late diagnosis, which limits therapeutic options and causes low patient survival. The objective of this work is to reflect on the possibilities of increasing the number of early diagnoses in order to decrease mortality and improve survival for lung cancer. The follow-up of lung cancer with low-dose computed tomography (LDCT), for example, has been shown in the National Lung Screening Trial (NLST) and NELSON studies to increase the number of early stage diagnoses and reduce lung cancer mortality by over 20%. Screening measures have shown to be favorable for asymptomatic patients at high risk of neoplasia, contributing to a favorable prognosis. LDCT is the main screening tool, with higher sensitivity in the early detection of lung neoplasia and stage I cancer compared to chest X-ray screening. In this article, we compare the results established in each study in order to reflect on the need for investment in lung cancer screening.

Nonlinear progression during the occult transition establishes cancer lethality.

Cancer screening is based upon a linear model of neoplastic growth and malignant progression. Yet, historical observations suggest that malignant progression is uncoupled from growth which may explain the paradoxical increase in early-stage breast cancer detection without a dramatic reduction in metastatic burden. Here we lineage trace millions of genetically transformed field cells and thousands of screen detectable and symptomatic tumors using a cancer rainbow mouse model of HER2+ breast cancer. Transition rates from field cell to screen detectable tumor and then to symptomatic tumors were estimated from a dynamical model of tumor development. Field cells are orders of magnitude less likely to transition to a screen detectable tumor than the subsequent transition of a screen detectable tumor to a symptomatic tumor. Our model supports a critical occult transition in tumor development during which time a transformed cell becomes a bona fide neoplasm. Lineage tracing and test-by-transplantation reveals that nonlinear progression during or prior to the occult transition gives rise to nascent lethal cancers at screen detection. Simulations illustrate how occult transition rates are a critical determinant of tumor growth and malignancy in the lifetime of a host. Our data provides direct experimental evidence that cancers can deviate from the predictable linear progression model foundational to current screening paradigms.

Photoacoustic imaging of a cyanine dye targeting bacterial infection

The development of a non-invasive infection-specific diagnostic probe holds the potential to vastly improve early-stage detection of infection, enabling precise therapeutic intervention and potentially reducing the incidence of antibiotic resistance. Towards this goal, a commercially available bacteria-targeting Zinc(II)-dipicolylamine (ZnDPA)-derived fluorophore, PSVue794, was assessed as a photoacoustic (PA) imaging probe (PIP). A radiolabeled version of the dye, [99mTc]Tc-PSVue794, was developed to facilitate quantitative biodistribution studies beyond optical imaging methods, which showed a target-to-non-target ratio of 10.1 ± 1.1, 12 h post-injection. The ability of the PIP to differentiate between bacterial infection, sterile inflammation, and healthy tissue in a mouse model, was then evaluated via PA imaging. The PA signal in sites of sterile inflammation (0.062 ± 0.012 a.u.) was not statistically different from that of the background (0.058 ± 0.006 a.u.). In contrast, high PA signal was detected at sites of bacterial infection (0.176 ± 0.011 a.u.) as compared to background (0.081 ± 0.04 a.u., where P ≤ 0.03). This work demonstrates the potential of utilizing established fluorophores towards PAI and utilizing PAI as a modality in the distinction of bacterial infection from sites of sterile inflammation.

ZnS/MXene/CdS heterostructure modified electrode for ultrasensitive miRNA-21 assay with signal amplified photoelectrochemical strategy

The early-stage detection of microRNA (miRNA) holds significant value for clinical diagnosis of tumor. In this study, a highly sensitive miRNA detection platform is developed using a photoelectrochemical sensing system based on layer-by-layer (LBL) assembled ZnS/MXene/CdS (ZMC) heterostructure electrode. By incorporating ultrathin and highly conductive MXene, the ZMC electrode exhibits robust photocurrent signals upon exposure to light. The electrode is further modified HS-H1 DNA via disulfide bonds.With the help of auxiliary H2 DNA, a target miRNA-21 triggered catalytic hairpin assembly (CHA) amplification reaction is realized on the electrode surface through complementary base pairing. Then, manganese porphyrin (MnPP) is introduced to the formed double-stranded DNA after CHA reaction to catalyze the conversion of 4-chloro-1-naphthol (4-CN) to benzo-4-chloro-hexanedione (4-CD) precipitate in the presence of hydrogen peroxide, which leads to a significant decrease in photocurrent signals. As a result, the sensor demonstrates a reliable linear correlation in miRNA-21 detection with detection limits as low as 0.36 fM. The recoveries of miRNA-21 in human serum samples ranged from 98.27 % to 101.35 % with RSD values below 3.67 % suggest the reliability and practicality of this method. Therefore it shows great potential for the construction and application of highly sensitive photoelectrochemical biosensors in clinical sample detection.

Discrimination of Lung Cancer and Benign Lung Diseases Using BALF Exosome DNA Methylation Profile.

Benign lung diseases are common and often do not require specific treatment, but they pose challenges in the distinguishing of them from lung cancer during low-dose computed tomography (LDCT). This study presents a comprehensive methylation analysis using real-time PCR for minimally invasive diagnoses of lung cancer via employing BALF exosome DNA. A panel of seven epigenetic biomarkers was identified, exhibiting specific methylation patterns in lung cancer BALF exosome DNA. This panel achieved an area under the curve (AUC) of 0.97, with sensitivity and specificity rates of 88.24% and 97.14%, respectively. Each biomarker showed significantly higher mean methylation levels (MMLs) in both non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC) compared to non-cancer groups, with fold changes from 1.7 to 13.36. The MMLs of the biomarkers were found to be moderately elevated with increasing patient age and smoking history, regardless of sex. A strong correlation was found between the MMLs and NSCLC stage progression, with detection sensitivities of 79% for early stages and 92% for advanced stages. In the validation cohort, the model demonstrated an AUC of 0.95, with 94% sensitivity and specificity. Sensitivity for early-stage NSCLC detection improved from 88.00% to 92.00% when smoking history was included as an additional risk factor.

Deep Learning for the Detection and Classification of Diabetic Retinopathy Stages

The incidence of diabetic retinopathy (DR), a complication of diabetes leading to severe vision impairment and potential blindness, has surged worldwide in recent years. This condition is considered one of the leading causes of vision loss. To improve diagnostic accuracy for DR and reduce the burden on healthcare professionals, artificial intelligence (AI) methods are increasingly implemented in medical institutions. AI-based models, in particular, are integrating more algorithms to enhance the performance of existing neural network architectures that are commercially used for DR detection. However, these neural network models still exhibit limitations, such as the need for high computational power and lower accuracy in detecting early DR stages. To overcome these challenges, developing more advanced machine learning models for precise DR detection and classification of DR stages is essential, as it would aid ophthalmologists in making accurate diagnoses. This article reviews current research on the use of deep learning in diagnosing and classifying DR and related diseases, as well as the challenges ophthalmologists face in detecting this condition and potential solutions for early-stage DR detection. This review provides information on modern approaches to DR detection using deep learning applications and discusses the issues and limitations in this area.

Artificial intelligence for early-stage detection of chronic kidney disease

Early-stage detection of chronic kidney disease (CKD) is crucial in research to enable timely intervention, enhance understanding of disease progression, reduce healthcare costs and support public health initiatives. The traditional approaches on early-stage chronic kidney disease detection often suffer from slow convergence and not integrate advanced technologies, impacting their effectiveness. Additionally, security and privacy concerns related to patient data are ineffectively addressed. To overcome these issues, this research incorporates novel optimized artificial intelligence-based approaches. The main aim is to enhance detection process through enhanced hybrid mud ring network (EHMRN), a novel detection technique combining light gradient boosting machine and MobileNet, involving extensive data collection, including a large dataset of 100,000 instances. The introduced network is optimized through the mud ring optimization to attain enhanced performance. Incorporating spark ensures secure cloud-based storage, enhancing privacy and compliance with healthcare data regulations. This approach represents a significant advancement in primary stage detection more effectively and promptly. The results show that the introduced approach outperforms traditional approaches in terms of accuracy (99.96%), F1-score (99.91%), precision (100%), specificity (99.98%), recall (100%) and execution time (0.09 s).

Evaluation of machine learning and deep learning methods for early detection of internet of things botnets

The internet of things (IoT) represents a rapidly expanding sector within computing, facilitating the interconnection of myriad smart devices autonomously. However, the complex interplay of IoT systems and their interdisciplinary nature has presented novel security concerns (e.g. privacy risks, device vulnerabilities, Botnets). In response, there has been a growing reliance on machine learning and deep learning methodologies to transition from conventional connectivity-centric IoT security paradigms to intelligence-driven security frameworks. This paper undertakes a comprehensive comparative analysis of recent advancements in the creation of IoT botnets. It introduces a novel taxonomy of attacks structured around the attack life-cycle, aiming to enhance the understanding and mitigation of IoT botnet threats. Furthermore, the paper surveys contemporary techniques employed for early-stage detection of IoT botnets, with a primary emphasis on machine learning and deep learning approaches. This elucidates the current landscape of the issue, existing mitigation strategies, and potential avenues for future research.

Screening and Surveillance of Colorectal Cancer: A Review of the Literature.

Colorectal cancer (CRC) has the highest mortality rate among men and is the second highest among women under fifty, with incidence and mortality rates rising in younger populations. Studies indicate that up to one-third of patients diagnosed before fifty have a family history or genetic factors, highlighting the need for earlier screening. Contrariwise, diagnosis in healthy subjects through screening strategies enables early-stage detection of the tumor and better clinical outcomes. In recent years, mortality rates of CRC in Western countries have been on a steady decline, which is largely attributed to widespread screening programs and advancements in treatment modalities. Indeed, early detection through screening significantly improves prognosis, with stark differences in survival rates between localized and metastatic disease. This article aims to provide a comprehensive review of the existing literature, delving into the performance and efficacy of various CRC screening strategies. It navigates through available screening tools, evaluating their efficacy and cost-effectiveness. The discussion extends to delineating target populations for screening, emphasizing the importance of tailored approaches for individuals at heightened risk.