Technologies For Cancer Screening Research Articles

Application of AI-assisted Breast Ultrasound Technology in Breast Cancer Screening

To explore the application effect of artificial intelligence-assisted breast screening ultrasound technology in breast cancer screening. Methods 170 suspected breast cancer patients who underwent breast ultrasound examination in our hospital from July 2022 to June 2024 were retrospectively analyzed, and the results of breast biopsy were taken as the gold standard by physician analysis, artificial intelligence analysis, and combined artificial intelligence analysis. To compare the application effect of ultrasonography in breast cancer screening in three ways. Results Among 170 suspected breast cancer patients, 132 were positive, 38 were negative, 113 were true positive, and 29 were true negative. Sensitivity was 85.61%, specificity was 76.32%, consistency was 83.53%, positive predictive value was 92.62%, and negative predictive value was 60.42%. There were 124 true positive cases and 33 true negative cases, the sensitivity was 93.94%, the specificity was 86.84%, the consistency was 92.35%, the positive predictive value was 96.12%, and the negative predictive value was 80.49%. The results showed that 131 cases were true positive, and 37 were true negative. The sensitivity was 99.24%, the specificity was 97.37%, the consistency was 98.82%, the positive predictive value was 99.24%, and the negative predictive value was 97.37%. Taking the results of breast puncture biopsy as the "gold standard," the diagnostic sensitivity, specificity, consistency, positive predictive value, and negative predictive value of physician-combined artificial intelligence analysis were significantly higher than those of physician-only analysis or artificial intelligence analysis. Conclusion The application of AI-assisted breast screening ultrasound technology to breast cancer screening in our hospital not only helps to realize the consistency and accuracy of early identification and diagnosis of breast cancer so that patients can get more accurate treatment but also helps to reduce the workload of radiologists.

Alternative endpoints to mortality in cancer screening trials.

The reliance on mortality endpoints in cancer screening trials is not always compatible with the need to accelerate progress in outcomes for patient and public benefit. Evaluation of novel cancer screening technologies, such as multi-cancer early detection (MCED) tests, could be expedited by using alternative metrics that are measurable earlier than mortality. These include endpoints based on cancer stage at diagnosis, such as reduction in late-stage cancer incidence, and endpoints following cancer diagnosis, such as eligibility for curative therapy. Innovative trial designs with earlier measures that complement cancer mortality are needed to realise the potential benefits of novel screening technologies such as MCEDs more rapidly.

Computer-assisted discrimination of cancerous and pre-cancerous from benign oral lesions based on multispectral autofluorescence imaging endoscopy.

Diagnosis of cancerous and pre-cancerous oral lesions at early stages is critical for the improvement of patient care, to increase survival rates and minimize the invasiveness of tumor resection surgery. Unfortunately, oral precancerous and early-stage cancerous lesions are often difficult to distinguish from oral benign lesions with the existing diagnostic tools used during standard clinical oral examination. In consequence, early diagnosis of oral cancer can be achieved in only about 30% of patients. Therefore, clinical diagnostic technologies for fast, minimally invasive, and accurate oral cancer screening are urgently needed. This study investigated the use of multispectral autofluorescence imaging endoscopy for the automated and noninvasive discrimination of cancerous and precancerous from benign oral epithelial lesions. In vivo multispectral autofluorescence endoscopic images of clinically suspicious oral lesions were acquired from 67 patients undergoing tissue biopsy examination. The imaged lesions were classified as precancerous (n = 4), cancerous (n = 29), and benign (n = 34) lesions based on histopathology diagnosis. Multispectral autofluorescence intensity feature maps were generated for each oral lesion and used to train and optimize support vector machine (SVM) models for automated discrimination of cancerous and precancerous from benign oral lesions. After a leave-one-patient-out cross-validation strategy, an optimized SVM model developed with four multispectral autofluorescence features yielded levels of sensitivity and specificity of 85% and 71%, respectively and overall accuracy of 78% in the discrimination of cancerous/precancerous versus benign oral lesions. This study demonstrates the potentials of a computer-assisted detection system based on multispectral autofluorescence imaging endoscopy for the early detection of cancerous and precancerous oral lesions.

A novel machine learning model for breast cancer detection using mammogram images.

The most fatal disease affecting women worldwide now is breast cancer. Early detection of breast cancer enhances the likelihood of a full recovery and lowers mortality. Based on medical imaging, researchers from all around the world are developing breast cancer screening technologies. Due to their rapid progress, deep learning algorithms have caught the interest of many in the field of medical imaging. This research proposes a novel method in mammogram image feature extraction with classification and optimization using machine learning in breast cancer detection. The input image has been processed for noise removal, smoothening, and normalization. The input image features were extracted using probabilistic principal component analysis for detecting the presence of tumors in mammogram images. The extracted tumor region is classified using the Naïve Bayes classifier and transfer integrated convolution neural networks. The classified output has been optimized using firefly binary grey optimization and metaheuristic moth flame lion optimization. The experimental analysis has been carried out in terms of different parameters based on datasets. The proposed framework used an ensemble model for breast cancer that made use of the proposed Bayes + FBGO and TCNN + MMFLO classifier and optimizer for diverse mammography image datasets. The INbreast dataset was evaluated using the proposed Bayes + FBGO and TCNN + MMFLO classifiers, which achieved 95% and 98% accuracy, respectively.

Perspectives on clinical adoption barriers to blood-based multi-cancer early detection tests across stakeholders.

e13574 Background: Current United States Preventive Services Task Force (USPSTF) recommendations include routine screening for breast, cervical, colorectal, and lung cancer; however, two out of every three cancer cases occur in other indications leading to diagnosis in advanced stages of the disease and higher likelihood of mortality. Current recommended cancer screening and early detection tests also face several hurdles hindering equitable access in a real-world setting. Blood-based MCED tests can impact cancer screening and early detection by monitoring for multiple different cancer types at once via a blood draw that can detect cancers in multiple indications, including indications where screening is not performed routinely today. Given their nascency, the role of blood-based MCED tests in clinical practice is currently undefined. To help facilitate the appropriate integration of MCED tests into patient care, it is important to understand the perspectives of stakeholders on the anticipated challenges to implementation. Methods: We conducted three separate double-blinded surveys in July 2023 of representative cohorts of U.S. Healthcare providers (HCPs) (n=238) that are or act as primary care providers (general practitioners and obstetrics and gynecologists (OB-GYNs)), payers (n=40), and patients (n=116), to evaluate the current cancer screening and early detection landscape and gather perspectives on barriers to implementation of new cancer screening technologies, including blood-based MCED tests. Results: Of the surveyed HCPs and payers, >90% and 100% respectively reported to be aware of MCED tests. However, <10% of HCPs reported having ordered an MCED test and 80% of payers had not yet evaluated an MCED test for coverage under their plan at the time of the survey. The survey results indicated that there is broad agreement on the value proposition that blood-based MCED tests would improve patient outcomes with earlier intervention. Despite this recognition, the survey highlighted that there is limited use today due to the perceived lack of clinical accuracy and utility data, high out-of-pocket patient costs, and lack of payer coverage. Conclusions: To overcome the hurdles for future widespread adoption of blood-based MCED tests, increased investment in data generation, education, and implementation of logistical support for HCPs will be critical. Initiatives include collaborations between stakeholders to generate near-term clinical utility data, equipping HCPs with the ability to educate patients on test accuracy, and seamlessly integrating the testing process into the patient visit workflow. The findings of this study can help build understanding of the anticipated barriers and inform strategies to alleviate them and build a foundation for clinical adoption of blood-based MCED tests.

Differences in influencing mechanism of clinicians’ adoption behavior for liver cancer screening technology between the leading and subordinate hospitals within medical consortiums

BackgroundMedical consortiums have been extensively established to facilitate the integration of health resources and bridge the technical gap among member institutions. However, some commonly appropriate technologies remain stagnant in subordinate hospitals, although they have been routinely applied in leading hospitals. Besides, the mechanism underlying differences in clinicians’ adoption behavior at different levels of institutions was unknown. Therefore, this study aimed to investigate the differences in influencing mechanisms of clinicians’ hepatic contrast-enhanced ultrasound technology (CEUS) utilization behavior between leading and subordinate hospitals within medical consortiums, thus providing clues for expanding effective and appropriate technologies within integrated care systems.MethodsA self-designed scale was developed based on the theory of planned behavior (TPB). A multistage sampling method was applied to investigate clinicians who were aware of CEUS and worked in liver disease-related departments within the sampled medical institutions. The final sample size was 289. AMOS 24.0 software was used to construct multi-group structural equation modeling (SEM) to validate the hypotheses and determine the mechanism of hepatic CEUS utilization.ResultsIt revealed that behavioral intention significantly influenced adoption behavior, regardless of whether it was in leading hospitals or subordinate hospitals (β = 0.283, p < 0.001). Furthermore, behavioral attitude (β = 0.361, p < 0.001) and perceived behavioral control (β = 0.582, p < 0.001) exerted significant effects on adoption behavior through behavioral intention. However, in leading hospitals, subjective norm had a significant positive effect on behavioral intention (β = 0.183, p < 0.01), while it had a significant negative impact on behavioral intention in the subordinate hospitals (β = -0.348, p < 0.01).ConclusionTo effectively translate the adoption intention into actual behavior, it is recommended to elucidate the demand and facilitators involved in the process of health technology adoption across leading and subordinate hospitals. Additionally, bolstering technical support and knowledge dissemination within subordinate hospitals while harnessing the influential role of key individuals can further enhance this transformative process.

Worm-Based Diagnosis Combining Microfluidics toward Early Cancer Screening.

Early cancer diagnosis increases therapy efficiency and saves huge medical costs. Traditional blood-based cancer markers and endoscopy procedures demonstrate limited capability in the diagnosis. Reliable, non-invasive, and cost-effective methods are in high demand across the world. Worm-based diagnosis, utilizing the chemosensory neuronal system of C. elegans, emerges as a non-invasive approach for early cancer diagnosis with high sensitivity. It facilitates effectiveness in large-scale cancer screening for the foreseeable future. Here, we review the progress of a unique route of early cancer diagnosis based on the chemosensory neuronal system of C. elegans. We first introduce the basic procedures of the chemotaxis assay of C. elegans: synchronization, behavior assay, immobilization, and counting. Then, we review the progress of each procedure and the various cancer types for which this method has achieved early diagnosis. For each procedure, we list examples of microfluidics technologies that have improved the automation, throughput, and efficiency of each step or module. Finally, we envision that microfluidics technologies combined with the chemotaxis assay of C. elegans can lead to an automated, cost-effective, non-invasive early cancer screening technology, with the development of more mature microfluidic modules as well as systematic integration of functional modules.

Application of different methods for cervical cancer detection

Cervical cancer remains a widespread and challenging malignancy that affects women worldwide and poses significant clinical and public health issues. Since it is difficult to find early cervical lesions in the patient's own state, it is very important to apply appropriate and effective detection and screening for cervical cancer and precancerous lesions. This research investigates the development of cervical cancer and the various subtypes of HPV, which are the primary cause of cervical lesions. Combined with the investigation of the three most common clinical screening methods, including liquid-based thin-layer cell assay (TCT), human papillomavirus detection (HPV) and colposcopy detection operating methods and screening standards, data were used to comprehensively analyze the accuracy, sensitivity and specificity of single or combined screening of the three detection methods. This research examines various methods and technologies for cervical cancer screening, with the goal of determining their clinical effectiveness in detecting cervical lesions. Based on screening data, the results are positive and the methods are deemed suitable for early diagnosis of the condition. It is recommended that these screening tools be utilized in a clinical setting.

Abstract 6075: Most cancer deaths are unaddressed by current screening paradigms

Abstract Cancer is the leading cause of death at ages ≤80 in the US. To understand the burden of cancer death potentially addressable by new or improved screening approaches, we estimated the proportion of US cancer deaths without recommended guideline-based screening, especially after accounting for lung cancer screening eligibility and adherence. Using 2018-2019 mortality data from the National Center for Health Statistics and published estimates of the proportion of screening-eligible lung cancer patients, we estimated that 31.4% of nearly 600,000 annual cancer deaths were from colorectal, female breast, cervical, and smoking-eligible lung cancers (Table). Further accounting for adherence to lung cancer screening guidelines reduced the estimated proportion of screened cancer deaths to 17.4%; thus, 82.6% of cancer deaths may not be addressed by current guideline-based screening. Among the cancers not covered by guideline-based screening are uncommon cancer types, which (as defined by the National Cancer Institute) comprised 30.4% of cancer deaths. According to incidence-based mortality data from Surveillance, Epidemiology, and End Results registries, 24.7% of all cancer deaths were from stage 4 cancer types without guideline-based screening. These estimates, based on population data without patient-level information on mode of diagnosis, almost certainly underestimate the percentage of cancer deaths missed by currently available screening efforts. The large proportion of cancer deaths unaddressed by guideline-based screening represents a vast opportunity for new cancer screening technologies that are safe, effective, accessible, and affordable to enable earlier detection and successful treatment of the full spectrum of cancer types that contribute to the overall cancer burden. Table. Deaths from cancer by primary type in 2018-2019, US National Center for Health Statistics, with eligibility for and adherence to guideline-based low-dose computed tomography screening for lung cancer All cancer types Lung Colon/rectum Breast (female) Uterine cervix Total screened % of all All cancer deaths 1,198,854 281,681 104,059 84,745 8,290 478,775 39.9% Eligible for screening based on smoking (63.7% of lung)* 179,431 104,059 84,745 8,290 376,525 31.4% Adherent to smoking-guideline-based screening (6.6% of lung)† 11,842 104,059 84,745 8,290 208,936 17.4% *Modeled estimate of proportion of lung cancer patients eligible for screening (Landy et al. 2023). †Lung cancer screening receipt from 2019 American College of Radiology Lung Cancer Screening Registry (Fedewa et al. 2022). Citation Format: Ellen T. Chang, Anuraag Kansal, Earl A. Hubbell, Graham A. Colditz, Allison W. Kurian, Christina A. Clarke. Most cancer deaths are unaddressed by current screening paradigms [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6075.

Auto-BCS: A Hybrid System for Real-Time Breast Cancer Screening from Pathological Images.

Breast cancer is recognized as a prominent cause of cancer-related mortality among women globally, emphasizing the critical need for early diagnosis resulting improvement in survival rates. Current breast cancer diagnostic procedures depend on manual assessments of pathological images by medical professionals. However, in remote or underserved regions, the scarcity of expert healthcare resources often compromised the diagnostic accuracy. Machine learning holds great promise for early detection, yet existing breast cancer screening algorithms are frequently characterized by significant computational demands, rendering them unsuitable for deployment on low-processing-power mobile devices. In this paper, a real-time automated system "Auto-BCS" is introduced that significantly enhances the efficiency of early breast cancer screening. The system is structured into three distinct phases. In the initial phase, images undergo a pre-processing stage aimed at noise reduction. Subsequently, feature extraction is carried out using a lightweight and optimized deep learning model followed by extreme gradient boosting classifier, strategically employed to optimize the overall performance and prevent overfitting in the deep learning model. The system's performance is gauged through essential metrics, including accuracy, precision, recall, F1 score, and inference time. Comparative evaluations against state-of-the-art algorithms affirm that Auto-BCS outperforms existing models, excelling in both efficiency and processing speed. Computational efficiency is prioritized by Auto-BCS, making it particularly adaptable to low-processing-power mobile devices. Comparative assessments confirm the superior performance of Auto-BCS, signifying its potential to advance breast cancer screening technology.

Primary Human Papillomavirus Testing and Other New Technologies for Cervical Cancer Screening

(Abstracted from Obstet Gynecol 2023;142(5):1036–1043) Cervical cancer screening has saved millions of lives over the past 7 decades. Never-screened or underscreened women currently account for more than half of all cervical cancer cases in the United States.

Improved Control System for Digital Imaging Elasto-Tomography Breast Cancer Screening

Breast cancer is the most recognised form of cancer in New Zealand women. Early treatment is a key factor in the long-term outcome of the disease. Robust screening methods are an essential component to help early diagnoses. Common screening methods include mammography and physical examination. Both methods have significant downsides including discomfort and exposure to radiation. Digital Imaging Elasto-Tomography (DIET) is a new breast cancer screening technology. Screening involves women lying prone on the machine, while sinewaves of known amplitude and frequency are applied to the breast at the nipple. Images are taken at multiple phases of the sinewave as the breast is vibrated. These images are processed to determine the surface motion and consequently the tissue properties of the breast, which is then used to distinguish tumours from healthy tissue. A prototype of this machine has been designed and used on breast phantoms and in clinical trials.A known issue with the prototype is noise in the actuation system. This creates vibration in the rest of the machine and impacts the quality of the oscillation imparted to the breast. A possible solution isolates the actuator from the machine by using damping feet. The motion of the feet was measured using an extra Linear Variable Differential Transformer (LVDT) sensor. Feedback control for the actuation was provided by the combination of this sensor and the original one. The results of these changes were compared to using a single sensor for feedback.The vibration of the feet reduced the overall amplitude of the actuator when in operation. This reduction was accounted for when two sensors were used for feedback. The Signal to Noise Ratio (SNR) was used to quantify the quality of the actuation. At 20 Hz the SNR was 22.7 and 22.0 using one and two sensors respectively. At 50 Hz the SNR improved to 39.9 and 38.6 for one and two sensors respectively. The impact of the reduced range of motion could be seen in the surface motion reconstruction of the breast phantom. The new control scheme reduced the vibration transferred to the rest of the machine and improved the amplitude accuracy. Potential changes to the software implementation of the control system may further improve the quality of the output.

Primary Human Papillomavirus Testing and Other New Technologies for Cervical Cancer Screening.

Cervical cancer screening has saved the lives of millions in regions where routine gynecologic care is readily accessible. As screening continues to evolve away from cervical cytology to primary human papillomavirus (HPV) testing, robust prospective cohort data have allowed for precise risk stratification and improved our ability to identify those at greatest risk of high-grade dysplasia and decrease unnecessary diagnostic procedures. New technologies such as p16/Ki-67 dual stain testing and HPV methylation panels, which offer comparable performance to co-testing and can be developed into high-throughput workflows, could lead to a fully molecular Pap test. Self-sampling in the United States, where the initial screen can be done in the home, in conjunction with new screening technologies, may decrease the existing hurdles of routine cervical cancer screening. Implementation barriers include issues with workflow, workforce, and cost. These need to be addressed to achieve an improved and more equitable cervical cancer screening program in the United States.

Factors That Determine Multiple Primary Cancers in the Adult Population in the United States.

Cancer is a major public health problem worldwide and a leading cause of death in the United States. Multiple primary cancers mean that an individual has more than one cancer in the same or a different organ but does not include instances of metastasis of initial primary cancer. Several factors such as genetics, for example, BRCA1 gene mutations, may predict multiple primary cancers. Factors such as the age at first cancer diagnosis may determine the outcome of multiple primary cancers. This study aims to determine factors that determine multiple primary cancers among the adult population in the United States. Methods: This study uses data from the Behavioral Risk Factor Surveillance System 2021 dataset. The study included all individuals recently diagnosed with cancer (sample size = 9806). All age groups were included in this study. Measures included the outcome variable number of cancers and a major independent variable: age at first cancer diagnosis. Covariates included race, sex, smoking status, and cancer treatment. Descriptive, bivariate, and multivariate logistic regressions were conducted using a statistical analysis system. It was hypothesized that individuals with age at first diagnosis of cancer at a younger age have higher odds of having multiple primary cancers as compared to individuals diagnosed at an older age. Results:The age group of 50-64 years had the highest percentage of only one cancer type (35.87%) and of two or more cancers (35.46%). A majority of females had two or more cancers (53.52%) as compared to males (47.48%). The majority of participants with only one cancer type (80.59%) and two or more cancers (88.61%) were of White non-Hispanic ethnicity. At the multivariate level,the age group under 18 years had 9.4% higher odds of having two or more cancers compared to the age group of 18-29 years (adjusted OR (AOR)=1.094, 95%CI=1.026-1.166; p-value=0.0057). The age group 65 years and above had 11.6% lower odds of having multiple primary cancers as compared to the age group of 18-29 years (AOR=0.884; 95%CI=0.859-0910; p-value=<0.0001). The Black non-Hispanic group had 73.8% lower odds of having multiple primary cancers as compared to White non-Hispanic respondents (AOR= 0.262; 95%CI = 0.228-0.301; p-value = <0.0001).Hispanic respondents had 59.8% lower odds of having two or more cancers as compared to the White non-Hispanicgroup (AOR= 0.402; 95%CI=0.390-0.413; p-value=<0.0001). Current smokers had 9.7% higher odds of having multiple cancers as compared to individuals who never smoked (AOR = 1.097; 95%CI=1.066-1.129; p-value=<0.0001). Former smokers had 24.2% higher odds of having multiple cancers as compared to individuals who never smoked (AOR=1.242; 95%CI=1.224-1.261; p-value=<0.0001). Individuals who were currently on treatment had 2.676 higher odds of having two or more cancers as compared to individuals not on treatment (AOR=2.676; 95%CI=2.629-2.724; p-value=<0.0001). Conclusion: Multiple primary cancers have been on the increase recently following advancements in anticancer therapy and cancer screening and diagnosis technology. It is important that studies that aim to demonstrate risk factors and predictors of multiple primary cancers such as the age at first diagnosis, smoking status, and cancer treatment are encouraged among public health specialists.

The aggregate value of cancer screenings in the United States: full potential value and value considering adherence

BackgroundAlthough cancer mortality has been decreasing since 1991, many cancers are still not detected until later stages with poorer outcomes. Screening for early-stage cancer can save lives because treatments are generally more effective at earlier than later stages of disease. Evidence of the aggregate benefits of guideline-recommended single-site cancer screenings has been limited. This article assesses the benefits in terms of life-years gained and associated value from major cancer screening technologies in the United States.MethodsA mathematical model was built to estimate the aggregate benefits of screenings for breast, colorectal, cervical, and lung cancer over time since the start of US Preventive Services Task Force (USPSTF) recommendations. For each type, the full potential benefits under perfect adherence and the benefits considering reported adherence rates were estimated. The effectiveness of each screening technology was abstracted from published literature on the life-years gained per screened individual. The number of individuals eligible for screening per year was estimated using US Census data matched to the USPSTF recommendations, which changed over time. Adherence rates to screening protocols were based on the National Health Interview Survey results with extrapolation.ResultsSince initial USPSTF recommendations, up to 417 million people were eligible for cancer screening. Assuming perfect adherence to screening recommendations, the life-years gained from screenings are estimated to be 15.5–21.3 million (2.2–4.9, 1.4–3.6, 11.4–12.3, and 0.5 million for breast, colorectal, cervical, and lung cancer, respectively). At reported adherence rates, combined screening has saved 12.2–16.2 million life-years since the introduction of USPSTF recommendations, ~ 75% of potential with perfect adherence. These benefits translate into a value of $8.2-$11.3 trillion at full potential and $6.5-$8.6 trillion considering current adherence. Therefore, single-site screening could have saved an additional 3.2–5.1 million life-years, equating to $1.7-$2.7 trillion, with perfect adherence.ConclusionsAlthough gaps persist between the full potential benefit and benefits considering adherence, existing cancer screening technologies have offered significant value to the US population. Technologies and policy interventions that can improve adherence and/or expand the number of cancer types tested will provide significantly more value and save significantly more patient lives.

Impact of perceived ease of use, organizational support mechanism, and industry competitive pressure on physicians' use of liver cancer screening technology in medical alliances.

Liver cancer is one of the malignant tumors worldwide, while the prevention and control situation is grim at present, and the diffusion of its early screening technology still faces some challenges. This study aims to investigate the influencing mechanism of perceived ease of use, organizational support mechanism, and industry competitive pressure on hepatic early screening technologies use by physicians, so as to promote the wider use of corresponding technologies. Under the theoretical guidance of technology-organization-environment framework and mindsponge theory, this study took hepatic contrast-enhanced ultrasound as an example, and conducted a cross-sectional questionnaire by randomly selecting physicians from Fujian and Jiangxi provinces in China with a high and low incidence of liver cancer, respectively. Structural equation modeling was used to determine the correlation among perceived ease of use, organizational support mechanism, and industry competitive pressure, as well as their impact on the physicians' behavior toward contrast-enhanced ultrasound use. The hypothesis model fits well with the data (χ2/df = 1.863, GFI = 0.937, AGFI = 0.908, RMSEA = 0.054, NFI = 0.959, IFI = 0.980, CFI = 0.980). Under technology-organization-environment framework, the perceived ease of use (β = 0.171, p < 0.05), organizational support mechanism (β = 0.423, p < 0.01), industry competitive pressure (β = 0.159, p < 0.05) significantly influenced physicians' use of hepatic contrast-enhanced ultrasound. Besides, perceived ease of use and organizational support mechanism (β = 0.216, p < 0.01), perceived ease of use and industry competitive pressure (β = 0.671, p < 0.01), organizational support mechanism and industry competitive pressure (β = 0.330, p < 0.01) were all associated significantly. From the lens of information processing (mindsponge theory) and technology-organization-environment framework, this study clarified the social and psychological influencing mechanism of perceived ease of use, organizational support mechanism, and industry competitive pressure on physicians' use of hepatic contrast-enhanced ultrasound. The results will directly propose recommendations for expanding hepatic contrast-enhanced ultrasound utilization and indirectly promoting other appropriate and effective health technologies diffusion within the integrated health system.

A panel of seven protein tumour markers for effective and affordable multi-cancer early detection by artificial intelligence.

155 Background: Cancer early detection aims at reducing cancer deaths. Unfortunately, many established cancer screening technologies are not suitable for use in low- and middle-income countries (LMICs) due to cost, complexity, and dependency on extensive medical infrastructure. Methods: Nearly 10,000 participants [1959 cancer cases (containing more than nine common cancer types) and 7423 non-cancer cases] were divided into one training and two independent validation cohorts. One tube of peripheral blood samples was collected from each participant and quantified using a panel of seven selected protein tumour markers (PTMs) by a common clinical electrochemiluminescence immunoassay analyser. An algorithm named OncoSeek was established using artificial intelligence (AI) to distinguish cancer from non-cancer cases by calculating the probability of cancer (POC) index based on the quantification results of the seven PTMs and clinical information including sex and age of the subjects, and to predict the possible affected tissue of origin (TOO) for those who have been detected with cancer signal. Results: The conventional clinical method relied only on a single threshold for each PTM which would make a big problem when combining the results of those markers, the false positive rate would accumulate as the number of markers increased. Nevertheless, OncoSeek was empowered by AI technology to significantly reduce the false positive rate, increasing the specificity from 56·9% [95% confidence interval (CI): 55·8% to 58·0%] to 92·9% (95% CI: 92·3% to 93·5%). In all cancer types, the overall sensitivity of the OncoSeek test was 51·7% (95% CI: 49·4% to 53·9%). And the performance was generally consistent in the training and the two validation cohorts. The sensitivities ranged from 37·1% to 77·6% for the detection of the nine common cancer types (breast, colorectum, liver, lung, lymphoma, oesophagus, ovary, pancreas, and stomach), which account for ~59·2% of global cancer deaths annually. Furthermore, it has shown excellent sensitivity in several high-mortality cancer types for which there are lacking routine screening tests in the clinic, such as the sensitivity of pancreatic cancer was 77·6% (95% CI: 69·3% to 84·6%). The overall accuracy of TOO prediction in the true positives was 66·8%, which could assist the clinical diagnostic workup. Conclusions: OncoSeek significantly outperforms the conventional clinical method, representing a novel blood-based test for multi-cancer early detection (MCED) which is a non-invasive, easy, efficient, and robust approach. Moreover, the accuracy of TOO facilitates the follow-up diagnostic workup and this method is affordable (less than $25) and accessible requiring nothing more than a blood draw at the screening sites, which makes it acceptable and sustainable in LMICs.

A panel of seven protein tumour markers for effective and affordable multi-cancer early detection by artificial intelligence: a large-scale and multicentre case–control study

A panel of seven protein tumour markers for effective and affordable multi-cancer early detection by artificial intelligence: a large-scale and multicentre case–control study

Metabolic insights into tumor pathogenesis: Unveiling pan‐cancer metabolism and the potential of untargeted metabolomics

AbstractMetabolic dysregulation is a hallmark of cancer, underpinning diverse aggressive behaviors such as uncontrolled proliferation, immune evasion, and metastasis. Despite the potential of tumor metabolites as biomarkers, their utility has been hampered by metabolic heterogeneity. Exploring cancer metabolism aims to discern shared metabolic pathways and have a better understanding the metabolic heterogeneity of tumors. This approach offers a holistic view of cancer metabolism, facilitating the identification of multicancer‐relevant metabolic targets and the development of more broadly effective therapeutics. In this review, we present a comprehensive overview of the current landscape of cancer metabolism and its prospective applications in cancer diagnosis and prognosis. We delineate common metabolic aberrations observed across a spectrum of cancer types and elucidate the unique metabolic signatures characterizing the six leading causes of cancer‐related mortality. Furthermore, we survey the utilization of untargeted metabolomics and single‐cell technologies in cancer screening, diagnosis, and prognosis, while also spotlighting available data resources for pan‐cancer metabolomics analyses. Throughout this discussion, we tackle prevailing research challenges and propose strategies aimed at enhancing cancer management. Our objective is to furnish valuable insights that can inform and guide future research endeavors in the dynamic realm of cancer metabolism.

A panel of seven protein tumor markers for multi-cancer early detection by artificial intelligence.

3067 Background: Early cancer detection is key to reducing cancer deaths. Unfortunately, many established cancer screening technologies are not suitable for use in low- and middle-income countries due to expenses, complexity, and dependency on extensive medical infrastructure. Therefore, a simple, affordable, efficient multi-cancer early detection test is a major unmet need. Methods: This study enrolled nearly 10,000 participants (1959 cancer cases and 7423 non-cancer cases) containing more than nine common cancer types. One tube of peripheral blood samples was collected from each participant and quantified a panel of seven selected protein tumor markers (PTMs) by a clinical common electrochemiluminescence immunoassay analyzer. A protein assay named OncoSeek was established using artificial intelligence to distinguish cancer from non-cancer cases by calculating the probability of cancer (POC) index based on the quantification results of 7 PTMs and clinical information including gender and age of the subjects. Then using another model to predict the possible affected tissue of origin (TOO) who has been detected with cancer signal. Results: In this study, we found that the conventional clinical method relied only on a single threshold for each protein tumor marker which would make a big problem that was when combining the result of those markers, the false positive rate would accumulate as the number of tests increased. Nevertheless, OncoSeek was empowered by artificial intelligence technology to significantly reduce the false positive rate, increasing the specificity from 56.9% (95% confidence interval (CI): 55.8% to 58.0%) to 92.9% (95% CI: 92.3% to 93.5%). In all cancer types sensitivity of the OncoSeek test was 51.7% (95% CI: 49.4% to 53.9%). The sensitivities ranged from 37.1% to 77.6% for the detection of the nine common cancer types (breast, colorectum, esophagus, liver, lung, lymphoma, ovary, pancreas, stomach), which account for ~59.2% of global cancer deaths annually. Furthermore, it has shown excellent sensitivity in several high-mortality cancer types for which there are a lack of routine screening tests in the clinic, such as the sensitivity of pancreatic cancer was 77.6% (95% CI: 69.3% to 84.6%). The overall accuracy of tissue of origin (TOO) prediction in true positives was 66.8%, which reduced the clinical diagnostic workup. Conclusions: In summary, this study supported that OncoSeek significantly outperforms the conventional clinical method, representing a novel blood-based test for multi-cancer early detection which is a non-invasive, easier, and efficient approach. Moreover, the accuracy of TOO of it which facilitates the follow-up diagnostic workup. As well as this method is affordable (the cost of the test is less than $25) and requires nothing more than a blood draw at the screening sites, which makes it more practical in low- and middle-income countries.