Screening Paradigm Research Articles

A new paradigm for structural heart disease detection: cost savings of screening with AI-ECG and POCUS

Abstract Background AI-enhanced electrocardiogram (AI-ECG) is a cost-effective tool for left ventricular dysfunction screening. However, its cost-effectiveness for other forms of structural heart disease (SHD) is unknown. While AI-ECG is inexpensive, the relatively low positive predictive value (PPV) of many models can lead to high costs from unnecessary follow-up tests like transthoracic echocardiography (TTE). Therefore, strategies to improve the yield of AI-ECG-based screening are needed. Purpose To evaluate the cost savings of a stepwise approach to SHD screening using AI-ECG followed by point-of-care ultrasound (POCUS) compared to AI-ECG alone. Methods 286 adult outpatients undergoing AI-ECG were randomly selected to undergo same-day POCUS. All participants were required to have a recent TTE, our gold standard for SHD diagnosis, for comparison purposes. We evaluated four SHDs: aortic stenosis, cardiac amyloidosis, hypertrophic cardiomyopathy, and left ventricular dysfunction (defined as left ventricular ejection fraction <50%). The costs of AI-ECG ($75/test) and TTE ($1,305/test) were sourced from Healthcare Bluebook, while the cost of POCUS ($100/test) was independently estimated. We compared the costs of screening with AI-ECG alone to stepwise screening with AI-ECG followed by POCUS. Costs were analyzed for two paradigms: screening for all forms of SHD in parallel and screening for each SHD individually. Results AI-ECG alone identified potential SHD in 125 out of 286 patients. When compared to TTE, only 39 out of 125 were true positives (31% PPV). Among the AI-ECG-positive patients, POCUS demonstrated findings of SHD in 52 out of 125 cases. When compared to TTE, this stepwise approach yielded 32 true positives and 20 false positives (62% PPV). In the parallel screening paradigm, the cost per patient diagnosed with SHD was $4,733 with AI-ECG alone, which decreased to $3,182 with stepwise screening (33% cost savings). For the individual SHD screening paradigm, cost reductions were as follows: aortic stenosis ($18,724 to $6,315, 66% savings), cardiac amyloidosis ($21,023 to $12,230, 42% savings), hypertrophic cardiomyopathy ($9,883 to $6,175, 38% savings), and left ventricular dysfunction ($4,019 to $3,582, 11% savings). Conclusions Stepwise SDH screening with AI-ECG followed by POCUS markedly reduces costs compared to AI-ECG alone. The greatest cost savings for individual SHD screening were observed for aortic stenosis and cardiac amyloidosis, conditions where AI-ECG models have lower PPVs. Parallel screening for multiple SHDs is also less costly than screening for any individual SHD alone. Therefore, a parallel screening approach may maximize SHD detection while minimizing screening costs. Stepwise Screening Approach for SHD SDH Screening Costs

Staged Screening Identifies People with Biomarkers Related to Neuronal Alpha‐Synuclein Disease

ObjectiveRemote identification of individuals with severe hyposmia may enable scalable recruitment of participants with underlying alpha‐synuclein aggregation. We evaluated the performance of a staged screening paradigm using remote smell testing to enrich for abnormal dopamine transporter single‐photon emission computed tomography imaging (DAT‐SPECT) and alpha‐synuclein aggregation.MethodsThe Parkinson's Progression Markers Initiative (PPMI) recruited participants for the prodromal cohort who were 60‐years and older without a Parkinson's disease diagnosis. Participants were invited to complete a University of Pennsylvania Smell Identification Test (UPSIT) independently through an online portal. Hyposmic participants were invited to complete DAT‐SPECT, which determined eligibility for enrollment in longitudinal assessments and further biomarker evaluation including cerebrospinal fluid alpha‐synuclein seed amplification assay (aSynSAA).ResultsAs of January 29, 2024, 49,843 participants were sent an UPSIT and 31,293 (63%) completed it. Of UPSIT completers, 8,301 (27%) scored <15th percentile. Of 1,546 who completed DAT‐SPECT, 1,060 (69%) had DAT‐SPECT binding <100% expected for age and sex. Participants with an UPSIT <10th percentile (n = 1,221) had greater likelihood of low DAT‐SPECT binding compared to participants with an UPSIT in the 10th to 15th percentile (odds ratio, 3.01; 95% confidence interval, 1.85–4.91). Overall, 55% (198/363) of cases with UPSIT <15th percentile and DAT‐SPECT <100% had positive aSynSAA, which increased to 70% (182/260) when selecting for more severe hyposmia (UPSIT <10th percentile).InterpretationRemote screening for hyposmia and reduced DAT‐SPECT binding identifies participants with a high proportion positive aSynSAA. Longitudinal data will be essential to define progression patterns in these individuals to ultimately inform recruitment into disease modification clinical trials. ANN NEUROL 2024

Estimating the incremental population health impact of a multi-cancer early detection (MCED) test to complement existing screening among elevated risk populations with multiple cancer risk factors: a mathematical modeling study

BackgroundThe added benefits of a multi-cancer early detection (MCED) test among individuals with multiple risk factors will help policy decision-makers allocate limited healthcare resources. This study sought to estimate the population health implications of adding an MCED test to standard-of-care (SOC) cancer screening tests among individuals aged 50–79 years with additional cancer risk factors (i.e., tobacco use, family history of cancer, and/or obesity).MethodsA mathematical model was developed to assess the potential screening efficiency of an MCED test in addition to current guideline-recommended screenings. Among the US population of 107 million adults aged 50–79 years, the size of, and cancer risk among specific subgroups (i.e., smokers, obese individuals, those with a family history of cancer) as well as the general population were estimated from the literature. Published estimates of screening uptake and/or performance were used to model the number of cancers detected by SOC screening alone, and the number of incremental cancers that could be detected by an MCED test. Screening efficiency outcomes included the true-positive:false-positive (TP:FP) ratio, diagnostic yield (DY), and cancer detection rate (CDR). Sensitivity analyses were conducted by varying the values of key parameters.ResultsAmong all subgroups, the TP:FP ratios were higher with an MCED test than with SOC screening alone, and higher than in the general population, suggesting improved screening efficiency with an MCED test. The estimated TP:FP ratios were 1:43.3 (SOC)/1:1.1 (MCED), 1:40.4/1:0.8, 1:36.9/1:0.5 among former, ever, and current smokers, respectively, 1:38.3/1:0.9 (those with a family history of cancer), and 1:39.3/1:1.1 (obese individuals). Among the general population, the TP:FP ratios were 1:43.5/1:1.1. Across all subpopulations, the DY and CDR increased by up to threefold with an MCED test, when compared to SOC screening alone, with up to 75% of cancers detected with an MCED test lacking a screening paradigm. These results were robust in sensitivity analyses.ConclusionsAdding an MCED test could improve screening efficiency among individuals with multiple risk factors, as well as the general population.

Does Colonoscopy as a First Screening Test Still Make Sense?-Counterpoint.

Colonoscopy has been widely regarded as the gold standard for its high diagnostic accuracy and preventive potential. However, its invasive nature, high cost, and suboptimal participation rates limit its utility at the population level. Non-invasive screening tests, notably the fecal immunochemical test (FIT) and multitarget stool DNA tests, present promising alternatives that may improve screening participation and reduce barriers to participation. Among these, FIT has demonstrated a consistent advantage in enhancing participation, which subsequently contributes to better long-term outcomes in CRC prevention. FIT-based two-step screening offers several practical advantages, including cost-effectiveness, non-invasiveness, and greater flexibility. Moreover, the quantitative nature of FIT allows for adjustable sensitivity thresholds and the ability of risk stratification, making it adaptable across diverse populations and scenarios. Through serial testing, FIT can increase cumulative detection rates over time. This approach facilitates the identification of high-risk individuals, allowing for more judicious use of colonoscopy resources and reducing unnecessary invasive procedures, especially among low-risk populations. Notably, evidence indicates that participation to FIT-based screening is consistently higher than to colonoscopy, which enhances the detection of early-stage cancers and advanced adenomas in the long run. Given the constraints of limited endoscopic capacity, the aging population, and the recent lowering of the recommended screening age due to the rising incidence of early-onset CRC, FIT emerges as a practical, flexible solution. The role of two-step FIT screening in improving participation and enabling risk-stratified, personalized approaches to CRC prevention is pivotal, advocating for its expanded integration into future screening paradigms.

Arrhythmogenic Cardiomyopathy: Towards Genotype Based Diagnoses and Management.

Arrhythmogenic cardiomyopathy (ACM) is a genetically heterogeneous inherited cardiomyopathy with an estimated prevalence of 1:5000-10 000 that predisposes patients to life-threatening ventricular arrhythmias (VA) and sudden cardiac death (SCD). ACM diagnostic criteria and risk prediction models, particularly for arrhythmogenic right ventricular cardiomyopathy (ARVC), the most common form of ACM, are typically genotype-agnostic, but numerous studies have established clinically meaningful genotype-phenotype associations. Early signs of ACM onset differ by genotype indicating the need for genotype-specific diagnostic criteria and family screening paradigms. Likewise, risk factors for SCD vary by genetic subtype, indicating that genotype-specific guidelines for management are also warranted. Of particular importance, genotype-specific therapeutic approaches are being developed. Results from a randomized controlled trial for flecainide use in ARVC patients are currently pending. Research in a plakophilin-2-deficient mouse model suggests this antiarrhythmic drug may be particularly useful for patients with likely pathogenic or pathogenic (LP/P) PKP2 variants. Additionally, the first gene therapy clinical trials in ARVC patients harboring LP/P PKP2 variants are currently underway. This review aims to provide clinicians caring for ACM patients with an up-to-date overview of the current literature in genotype-specific natural history of disease and management of ACM patients and describe scientific advances that have led to upcoming clinical trials.

Multi-Component, Time-Course screening to develop combination cancer therapies based on synergistic toxicity

Clinical trials in cancer are ideally built on a foundation of sound mechanistic rationale and well-validated drug activity in relevant disease models. The screening of approved and investigational drugs in cell-based phenotypic assays can provide evidence of drug activity, but alternative screening paradigms are needed to develop and optimize multidrug combination regimens. Here, we utilize in vitro screening outcomes across a panel of lymphoma cell lines to dissect the activity of four small-molecule drugs (Venetoclax, Ibrutinib, Prednisolone, and Lenalidomide) currently under investigation within ongoing clinical trials in lymphoma. Data from multiple concentration ranges and time points show that synergistic drug combinations promote apoptosis and cytotoxicity responses at concentrations and time points that are consistent with in vivo drug exposures. To fully map the interaction landscape of these agents in relevant cell models, we developed an in vitro assay format that facilitated time-course evaluations involving concurrent multidrug exposure which further highlighted rapid, synergistic apoptosis induction as a central engine for the activity of this multicomponent targeted therapy. In addition to several instances of exceptional drug+drug synergy, the genetically similar diffuse large B cell lymphoma models also displayed substantial heterogeneity in the degree of synergism between drug pairs. A parallel survey of chemotherapies exhibited limited combination benefit, supporting recent findings that multicomponent chemotherapy outcomes are driven by individual drug activity. Collectively, these data demonstrate how in vitro drug screening data can identify multidrug combinations that exploit drug synergy to overcome the functional diversity of human malignancies.

An Ensemble Deep Learning Algorithm for Structural Heart Disease Screening Using Electrocardiographic Images: PRESENT SHD.

Identifying structural heart diseases (SHDs) early can change the course of the disease, but their diagnosis requires cardiac imaging, which is limited in accessibility. To leverage images of 12-lead ECGs for automated detection and prediction of multiple SHDs using an ensemble deep learning approach. We developed a series of convolutional neural network models for detecting a range of individual SHDs from images of ECGs with SHDs defined by transthoracic echocardiograms (TTEs) performed within 30 days of the ECG at the Yale New Haven Hospital (YNHH). SHDs were defined based on TTEs with LV ejection fraction <40%, moderate-to-severe left-sided valvular disease (aortic/mitral stenosis or regurgitation), or severe left ventricular hypertrophy (IVSd > 1.5cm and diastolic dysfunction). We developed an ensemble XGBoost model, PRESENT-SHD, as a composite screen across all SHDs. We validated PRESENT-SHD at 4 US hospitals and a prospective population-based cohort study, the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), with concurrent protocolized ECGs and TTEs. We also used PRESENT-SHD for risk stratification of new-onset SHD or heart failure (HF) in clinical cohorts and the population-based UK Biobank (UKB). The models were developed using 261,228 ECGs from 93,693 YNHH patients and evaluated on a single ECG from 11,023 individuals at YNHH (19% with SHD), 44,591 across external hospitals (20-27% with SHD), and 3,014 in the ELSA-Brasil (3% with SHD). In the held-out test set, PRESENT-SHD demonstrated an AUROC of 0.886 (0.877-894), sensitivity of 90%, and specificity of 66%. At hospital-based sites, PRESENT-SHD had AUROCs ranging from 0.854-0.900, with sensitivities and specificities of 93-96% and 51-56%, respectively. The model generalized well to ELSA-Brasil (AUROC, 0.853 [0.811-0.897], sensitivity 88%, specificity 62%). PRESENT-SHD performance was consistent across demographic subgroups and novel ECG formats. A positive PRESENT-SHD screen portended a 2- to 4-fold higher risk of new-onset SHD/HF, independent of demographics, comorbidities, and the competing risk of death across clinical sites and UKB, with high predictive discrimination. We developed and validated PRESENT-SHD, an AI-ECG tool identifying a range of SHD using images of 12-lead ECGs, representing a robust, scalable, and accessible modality for automated SHD screening and risk stratification.

Imprints of vector field non-standard couplings on solar neutrino flux

Regarding the proximity of dark energy scale and neutrino mass, one can get new insight into the probe signatures of vector field dark energy component on neutrino flavor conversion. A vector field is assumed to be conformally coupled to various matter components through a screening paradigm. We show how the oscillation probabilities evolve differently with a finite-size matter density like the Sun for different values of relevant model parameters. Considering existing neutrino flavor conversion data, we point out how this non-standard coupling affects neutrino fluxes, and also, we compute the discrepancy in the total flux of solar electron-neutrinos.

Challenging the American College of Obstetricians and Gynecologists' Clinical Practice Update on Screening for Pre-existing Diabetes and Early Gestational Diabetes.

A recent American College of Obstetricians and Gynecologists Clinical Practice Update continues to recommend targeted (as opposed to universal) screening for pregestational diabetes, no longer recommends screening for early gestational diabetes mellitus (GDM), and provides updated guidelines for immediate postpartum testing for diabetes in patients with GDM. Here, we present data that the targeted screening paradigm, which has repeatedly been shown to fail in practice because of its complexity, no longer makes sense in the context of the high and rising prevalence of diabetes and diabetic risk factors, and we argue that the time has come for universal early pregnancy screening for pregestational diabetes. Furthermore, the recommendation against early screening for GDM is based on 2021 U.S. Preventive Services Task Force guidance, which in turn is based almost entirely on a single underpowered study that excluded individuals at highest risk and does not account for more recent research showing benefits of early diagnosis and treatment. Universal early pregnancy screening for pregestational diabetes may also help to identify patients at risk who will benefit from early GDM diagnosis and treatment and may provide rationale for prioritizing postpartum diabetes testing.

An adaptable, fit-for-purpose screening approach with high-throughput capability to determine speed of action and stage specificity of anti-malarial compounds.

A revamped in vitro compound identification and activity profiling approach is required to meet the large unmet need for new anti-malarial drugs to combat parasite drug resistance. Although compound hit identification utilizing high-throughput screening of large compound libraries is well established, the ability to rapidly prioritize such large numbers for further development is limited. Determining the speed of action of anti-malarial drug candidates is a vital component of malaria drug discovery, which currently occurs predominantly in lead optimization and development. This is due in part to the capacity of current methods which have low throughput due to the complexity and labor intensity of the approaches. Here, we provide an adaptable screening paradigm utilizing automated high content imaging, including the development of an automated schizont maturation assay, which collectively can identify anti-malarial compounds, classify activity into fast and slow acting, and provide an indication of the parasite stage specificity, with high-throughput capability. By frontloading these critical biological parameters much earlier in the drug discovery pipeline, it has the potential to reduce lead compound attrition rates later in the development process. The capability of the approach in its alternative formats is demonstrated using three Medicines for Malaria Venture open access compound "boxes," namely Pathogen Box (malaria set-125 compounds), Global Health Priority Box [Malaria Box 2 (80 compounds) and zoonotic neglected diseases (80 compounds)], and the Pandemic Response Box (400 compounds). From a total of 685 compounds tested, 79 were identified as having fast ring-stage-specific activity comparable to that of artemisinin and therefore of high priority for further consideration and development.

“Mammograms are kind of my pacifier”: The cultural context of women's preference for annual mammograms in a risk-based screening cohort

Population genetic testing and risk-based screening have the potential to shift how we determine risk and screen for breast cancer. While much attention has been paid to the experiences of individuals who may be at elevated risk for breast cancer, less is known about how those at average risk make decisions about their health. Through qualitative interviews with 30 participants, we explore how those enrolled in a risk-based screening trial who are determined to be at average risk for breast cancer make screening decisions. We consider how the social context of breast health, known as ‘pink ribbon culture,’ and the pervasiveness of annual mammography as the standard of care make risk-based screening less acceptable for many participants. Risk-based screening paradigms assume that individuals will assess their risk quantitatively based on the risk models that are used. Yet, our findings demonstrate that social and cultural factors influence decision-making surrounding breast cancer screening, an important consideration when implementing risk-based screening programs. We will begin to address a gap in knowledge about how women who are told they are average risk after risk-based screening (most of the population) and recommended to screen less than annually make screening decisions.

Genomic-Based Early Detection Screening: A Literature Review of Prospective Trials and Emerging Strategies for Gastrointestinal Cancers.

Numerous genomic-based early detection screening tests are being developed. These tests have the potential to revolutionize current single-organ screening paradigms, especially in gastrointestinal cancers. In this review, we underscore the performance of these genomic-based early detection tests based on prospective clinical trials. Moreover, we discuss a professional advancement for gastroenterologists in the diagnostic assessment of individuals who are cancer signal positive.

Writing direction influences the spatial representations of past- and future-tense forms: Evidence from eye tracking.

The present study tests the hypothesis that the directionality of reading habits (left-to-right or right-to-left) impacts individuals' representation of nonspatial events. Using the blank screen paradigm, we examine whether eye movements reflect culture-specific spatial biases in processing temporal information, specifically, grammatical tense in Russian and Hebrew. Sixty-two native speakers of Russian (a language with a left-to-right reading and writing system) and 62 native speakers of Hebrew (a language with a right-to-left reading and writing system) listened to verbs in the past or future tense while their spontaneous gaze positions were recorded. Following the verb, a visual spatial probe appeared in one of the five locations of the screen, and participants responded manually to indicate its position. While participants' response latencies to the spatial probe revealed no significant effects, their gaze positions along the horizontal axis for past- and future-tensed verbs aligned with the reading and writing direction in their language. These results provide novel evidence that eye movements during auditory processing of grammatical tense are influenced by culturally specific reading and writing conventions, shifting leftward or rightward on the horizontal plane depending on the stimuli's time reference (past or future) and the participants' language (Russian or Hebrew). This spatial bias indicates a common underlying cognitive mechanism that uses spatial dimensions to represent temporal constructs.

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.

Shifting the Cancer Screening Paradigm: Developing a Multi-Biomarker Class Approach to Multi-Cancer Early Detection Testing.

Guideline-recommended screening programs exist for only a few cancer types. Although all these programs are understood to lead to reductions in cancer-related mortality, standard-of-care screening tests vary in accuracy, adherence and effectiveness. Recent advances in high-throughput technologies and machine learning have facilitated the development of blood-based multi-cancer cancer early detection (MCED) tests. MCED tests are positioned to be complementary to standard-of-care screening and they may broaden screening availability, especially for individuals who are not adherent with current screening programs and for individuals who may harbor cancers with no available screening options. In this article, we outline some key features that should be considered for study design and MCED test development, provide an example of the developmental pathway undertaken for an emerging multi-biomarker class MCED test and propose a clinical algorithm for an imaging-based diagnostic resolution strategy following MCED testing.

Detectability of Breast Cancer Through Inverse Heat Transfer Modeling Using Patient-Specific Surface Temperatures

Abstract Breast cancer in women is a prevalent disease which takes over 680,000 lives each year worldwide. Early detection of breast cancer through screening has played a significant role in reducing the mortality rates. The current screening paradigm has shown the difficulties in detecting cancers for patients with dense breasts, small and deep tumors, and cancer types that are difficult to visualize. Infrared imaging (IRI) aided by advanced thermal analysis of the breast has shown great promise in detecting cancer using surface temperatures effected by a metabolically active and highly perfused tumor region. We previously developed an inverse heat transfer approach to detect the presence and absence of breast cancer using IRI, called the IRI-Numerical Engine. It was validated with 23 biopsy-proven breast cancer patients irrespective of breast density and cancer type at various tumor depths (0.95 cm to 5.45 cm from the breast surface). The current work is aimed to obtain the detectability limit of the IRI-Numerical Engine by testing the capability of detecting 10-20 mm tumors at various depths in patient-specific digital breast models. In addition, a study on the effect of tumor size, tumor location, breast shape, and breast size on the surface temperatures of patient-specific models was conducted to verify that an IR camera could capture these surface temperature distributions. The algorithm was able to detect the presence of a tumor at various depths, and deep tumors are detectable given the appropriate thermal sensitive IR camera.

High-sensitive multi-cancers early detection for 8 cancer types by cell-free DNA targeted methylation sequencing: A retrospective cohort study.

3043 Background: Early screening effectively reduces mortality associated with cancer. Currently, most cancers lack effective screening paradigms. We developed blood-based multi-cancers early detection (MCED) and cancer signal origin (CSO) approaches in 8 types of cancers including esophageal, stomach, colorectal, pancreatic, liver, lung, breast and ovarian cancer. Methods: DNA methylation data generated based on GM-seq by public and internal whole genome methylation data. Based on these data, a panel of 155,362 CpG sites spanning the 2.0M genome was constructed and validated. We enrolled a case-control cohort of 746 participants (522 cancers, 224 non-cancers) for MCED model development. cell-free DNA (cfDNA) was isolated from 10 ml peripheral blood from each participant. A targeted methylation sequencing of cfDNA in plasma baseline was established using 224 non-cancers blood samples for 8 types of cancers. Finally, we developed a MCED model named AMBER for distinguishing cancer from non-cancer individuals. Results: DNA methylation data were from 8 types of cancers (cancer tissues: n=812, adjacent/normal tissues: n=416, cancer peripheral bloods: n=624, normal peripheral bloods: n=503) in internal and Infinium Human Methylation 450K array (cancer tissues: n=5000+, adjacent/normal tissues: n=1000+) from public data. 224 non-cancer individuals (healthy: n=196, cancer benign: n=28, male: female, 54.3%: 45.7%) were collected as control, while 522 cancer patients (male: female, 50.0%: 50.0%, stage I 26.9%, II 21.1%) from esophageal (n=56, stage I: n=10), stomach (n=47, stage I: n=11), colorectal (n=72, stage I: n=16), pancreatic (n=64, stage I: n=16), liver (n=69, stage I: n=22), lung (n=103, stage I: n=46), breast (n=41) and ovarian cancer (n=70, stage I: n=17). AMBER showed 99.1% specificity and total sensitivity 77.2% (95% confidence interval (CI): 73.4% to 80.7%). Of them, 56.8% (95% CI: 48.2% to 65.2%) of all stage I cases were detected, 70.6% (95% CI: 61.2% to 79.0%) for stage II, 84.5% (95% CI: 77.6% to 89.9%) for stage III, and 96.7% (95% CI: 91.8% to 99.1%) for stage IV. Strikingly, for stage I cancers, the sensitivity of esophageal, stomach, colorectal, pancreatic, liver, lung and ovarian cancer were 80.0%, 63.6%, 43.8%, 62.5%, 86.4%, 30.4% and 82.4% respectively. The sensitivity of esophageal, stomach, colorectal, pancreatic, liver, lung, breast and ovarian cancer reached 91.1%, 76.6%, 75.0%, 78.1%, 94.2%, 55.3%, 65.9% and 90.0%. For CSO model, the accuracy of TPO1 and TPO2 was 78.9% (95% CI: 74.6% to 82.8%) and 89.1% (95% CI: 85.6% to 92.0%). Conclusions: Our MCED tests demonstrated superior performance in detecting 8 types of cancers, especially early cancer screening, by utilizing cfDNA methylation information. It suggests the model can complement lack of multi-cancers early detection.

Current Challenges of Methylation-Based Liquid Biopsies in Cancer Diagnostics.

In current clinical practice, effective cancer testing and screening paradigms are limited to specific types of cancer, exhibiting varying efficiency, acceptance, and adherence. Cell-free DNA (cfDNA) methylation profiling holds promise in providing information about the presence of malignity regardless of its type and location while leveraging blood-based liquid biopsies as a method to obtain analytical samples. However, technical difficulties, costs and challenges resulting from biological variations, tumor heterogeneity, and exogenous factors persist. This method exploits the mechanisms behind cfDNA release but faces issues like fragmentation, low concentrations, and high background noise. This review explores cfDNA methylation's origins, means of detection, and profiling for cancer diagnostics. The critical evaluation of currently available multi-cancer early detection methods (MCEDs) as well as tests targeting single genes, emphasizing their potential and limits to refine strategies for early cancer detection, are explained. The current methodology limitations, workflows, comparisons of clinically approved liquid biopsy-based methylation tests for cancer, their utilization in companion diagnostics as well as the biological limitations of the epigenetics approach are discussed, aiming to help healthcare providers as well as researchers to orient themselves in this increasingly complex and evolving field of diagnostics.

Physio-omics? Robotic development, software engineering, and machine learning for high throughput, whole animal physiology assays as a path to disease mechanism and drug discovery

Measurement and analysis of cardio-respiratory function in animal models is essential for our understanding of functional and disease mechanisms that pave the way for human therapeutics and treatments. However, physiological phenotyping in conscious animals is often an onerous process requiring significant observer time, attention, and manual effort while being susceptible to bias and variability that ultimately limits the kinds of questions that can be asked and answered. Once data is collected, comprehensive and accurate analysis is challenging as it often requires either the use of expensive commercial software(s) with limited flexibility to meet the investigator’s needs or lab developed scripts that are often arduous and require specialized skills to utilize, resulting in incremental insights. Here we present an overview of our high throughput physiology assessment and analysis pipeline for interrogating disease mechanisms and enabling drug discovery in congenital cardio-respiratory disorders such as the lethal sudden infant death syndrome (SIDS). We first developed a closed loop robotic platform for automated neonate cardio-respiratory experiments (Looper) that enables automated interventional studies (i.e. hypoxic induction or drug application) based on real-time physiological feedback during the experiment. We show that deployment of multiple Looper platforms in parallel enables an order of magnitude increase in data collection for a single observer over a single workday and is highly scalable to achieve yet greater outputs. When combined with well designed genetically engineered or other disease mouse models, large scale genetic, molecular, and cellular mechanistic insights and drug discovery become feasible through physiological screening paradigms. Next, we developed an open-sourced cardio-respiratory assessment software tool (Breathe Easy) that enables facile deep interrogation of terabytes of data in a high throughput fashion while offering extensive customization capabilities to allow for unique case by case analysis by more skilled users. Breathe Easy output offers near publication ready graphical outputs with significance markings and statistical tables for rapid presentation of results through manuscripts and web-publishing. Lastly, we will present our early work leveraging our robotic and software pipeline to build an analytical machine learning framework that can predict cardio-respiratory failure (death) with high temporal specificity (more than 10 min out) in our SIDS like assay and our efforts to utilize the trained algorithms for 1) real-time prediction, feedback, and intervention application in our SIDS like assays on the Looper platform to screen small molecules for novel therapeutics; 2) elucidating unique physiological mechanisms through comparative training in distinct SIDS models; and 3) determining the potential for these machine learning approaches to be used in human polysomnographic recordings to identify at risk infants. R01HL161142, R01HL130249. This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Efficient screening of pharmacological broad-spectrum anti-cancer peptides utilizing advanced bidirectional Encoder representation from Transformers strategy

In the vanguard of oncological advancement, this investigation delineates the integration of deep learning paradigms to refine the screening process for Anticancer Peptides (ACPs), epitomizing a new frontier in broad-spectrum oncolytic therapeutics renowned for their targeted antitumor efficacy and specificity. Conventional methodologies for ACP identification are marred by prohibitive time and financial exigencies, representing a formidable impediment to the evolution of precision oncology. In response, our research heralds the development of a groundbreaking screening apparatus that marries Natural Language Processing (NLP) with the Pseudo Amino Acid Composition (PseAAC) technique, thereby inaugurating a comprehensive ACP compendium for the extraction of quintessential primary and secondary structural attributes. This innovative methodological approach is augmented by an optimized BERT model, meticulously calibrated for ACP detection, which conspicuously surpasses existing BERT variants and traditional machine learning algorithms in both accuracy and selectivity. Subjected to rigorous validation via five-fold cross-validation and external assessment, our model exhibited exemplary performance, boasting an average Area Under the Curve (AUC) of 0.9726 and an F1 score of 0.9385, with external validation further affirming its prowess (AUC of 0.9848 and F1 of 0.9371). These findings vividly underscore the method's unparalleled efficacy and prospective utility in the precise identification and prognostication of ACPs, significantly ameliorating the financial and temporal burdens traditionally associated with ACP research and development. Ergo, this pioneering screening paradigm promises to catalyze the discovery and clinical application of ACPs, constituting a seminal stride towards the realization of more efficacious and economically viable precision oncology interventions.