Technology For Early Detection Research Articles

Seeing and believing: behavioural insights from implementing an artificial intelligence-enabled stethoscope in primary care

Abstract Background • Early detection and treatment of cardiovascular disease (CVD) improves survival, quality of life and health economic outcomes (1) • Despite evidence of effectiveness, health systems fail to implement technologies for early detection of CVD sustainably, limiting their public health impact (2). This challenge may limit the full potential of artificial intelligence (AI) in healthcare (3). • An AI-enabled stethoscope can detect reduced left ventricular ejection fraction (LVEF), atrial fibrillation (AF) and structural cardiac murmurs during fifteen seconds of conventional cardiac examination (4) • The determinants of uptake, sustained use and clinical impact of implementing the AI-stethoscope in primary care are unknown. Purpose • To implement the AI-stethoscope in a UK primary care system • To measure rates of utilisation and their association with potential disease detection • To characterise the adoption patterns of an AI technology in primary care Methods • TRICORDER is a cluster randomised controlled trial and implementation study. • Clinicians in the intervention arm receive in-person training in use of the AI-stethoscope and are remunerated for this training time. • Clinicians using the AI-stethoscope in routine care are supported by a clinical guideline and data privacy approvals from the regional health service executive board. • GP practices are not remunerated for using the AI-stethoscope • Anonymised utilisation and AI disease detection rates were extracted from the manufacturer’s cloud database from 31st October 2023 to 25th February 2024. We performed linear regression to characterise use over time. Results • 59 practices were randomised and onboarded to the intervention arm between 31st October and 3rd December 2023, all using the stethoscope at least once, for a total of 1,555 unique patient examinations (3,253 total recordings), over a median of 90 days. • The mean (±SD) number of recordings per practice per week was 5.45 (±5.68). • There were 32 practices with utilisation data for at least 12 weeks. There was a weakly positive utilisation trend (r = 0.042; P= >0.05, Figure 1A), with no significant difference in rates of utilisation at 4, 8 and 12 weeks (Figure 1B). • There were 159 (4.88%), 89 (2.74%) and 102 (3.13%) abnormal AI flags for reduced LVEF, AF and structural murmurs, respectively. • We characterised three groups by patterns of use (Table 1). There were no significant differences between mean rates of abnormal AI findings between groups (ANOVA p = 0.43). Conclusions • Implementation of an AI-stethoscope in primary care is feasible and was associated with stable utilisation. • The proportion of abnormal AI findings are consistent with modelled detection gap of the target conditions in the UK, and would not consequentially overwhelm downstream health services. •The proportion of abnormal AI findings did not significantly differ between low and high-utilisation groups.Table 1Figure 1

A Triple-Mismatch Differentiating assay exploiting activation and trans cleavage of CRISPR-Cas12a for mutation detection with ultra specificity and sensitivity

Liquid biopsy technology is non-invasive and convenient, and is currently an emerging technology for cancer screening. Among them, clustered regularly interspaced short palindromic repeats (CRISPR)-CRISPR associated protein 12a (Cas12a) based nucleic acid detection technology has the advantages of high sensitivity, rapidity, and easy operation. However, CRISPR-Cas12a does not discriminate single-base mismatches of targets well enough to meet the needs of clinical detection. Herein, we developed the Triple-Mismatch Differentiating (TMD) assay. This assay amplified the small thermodynamic difference in mismatches at one site at the level of CRISPR-Cas12a activation to a significant thermodynamic difference at three sites at both the level of CRISPR-Cas12a activation and trans-cleavage, which greatly improves the ability of CRISPR-Cas12a to discriminate between base mismatches. Our manipulation greatly improved the specificity of the CRISPR-Cas12a system while maintaining its inherent sensitivity and simplicity, increasing the detection limit to 0.0001%. When testing samples from pancreatic cancer patients, our results were highly consistent with NGS sequencing results. We believe that the TMD assay will provide a new technology for early cancer detection and will be widely used in the clinical practice.

Digital Measures to Decipher Forest Fires a Comparative Study of the Moroccan and American Experiences

Objectives: The study analyzed the digital measures in forest fire management in Morocco and the United States, comparing of the fire management methods in each country. The goal was to enhance the policies and strategies used in Morocco and to further integrate the Moroccan approach with the American experience. Methods: The study relied on the descriptive-analytical approach to describe the digital measures adopted in both Morocco and the United States for extinguishing forest fires. The comparative approach was also used to compare the experiences of both countries in combating forest fires and explore how Morocco can benefit from American expertise. Results: The study results indicate that both Morocco and the United States use digital technology for early detection of forest fires. However, Morocco faces challenges such as funding shortages, inadequate technical infrastructure, and the need for firefighter training. Meanwhile, the U.S. employs advanced technologies, including satellites, drones, and ground-based thermal sensors, and benefits from integrated information management systems and artificial intelligence. Despite this, the U.S. also encounters challenges related to coordinating efforts among different agencies. In comparison, the U.S. has significantly higher levels of funding and technical support, allowing for the use of more advanced technologies. Therefore, Morocco could benefit from the American experience in several ways, including improving technical infrastructure, training firefighting teams, using integrated information management systems, and exchanging expertise and knowledge.. Conclusions: These results reflect the importance of digital technology in enhancing the effectiveness of forest fire response and highlight Morocco's potential to benefit from the United States' experience to address this environmental issue more effectively.

Accelerating Progress to Reduce the Cancer Burden through Prevention and Control in the US.

Improvements in cancer prevention and control are poised to be main contributors in reducing the burden of cancer in the US. We quantify top opportunities to accelerate progress using projected life years gained (LYG) and deaths averted as measures. We project that over the next 25 years, realistic gains from tobacco control can contribute 0.4 to 17 million additional LYG per intervention and 8.4 million additional LYG from improving uptake of screening programs over the lifetime of 25 annual cohorts. Additional opportunities include addressing modifiable risk factors (excess weight, alcohol consumption), improving methods to prevent or treat oncogenic infections, and reducing cancer health disparities. Investment is needed in the pipeline of new preventive agents and technologies for early detection to continue progress. There is also a need for additional research to improve the access to and uptake of existing and emerging interventions for cancer prevention and control and to address health disparities. These gains are undeniably within our power to realize for the US population.

Advanced Tuberculosis Detection System for Preserving Public Health

Tuberculosis is a major public health threat that requires efficient and early detection technologies. Challenges associated with real-world implementation include information variability, model availability, and operations in different clinical circumstances. In this paper, we introduce a Crow Search Driven Tuned Logistic Regression (CS-TLR) tuberculosis identification system to sustain early identification of the disease and increase the levels of diagnostic accuracy to help sustain public health. The model attempts to enhance the overall prediction performance of logistic regression by optimizing its parameters by using CSA's optimization capability. We gathered the Kaggle dataset with a variety of clinical and demographic characteristics of tuberculosis patients. We evaluate the performance of the suggested method employing standard parameters including AUC (90.5%), precision (89.9%), recall (90.1%), and F1-score (89.7%). The findings suggest that it could be an important public health surveillance tool by enabling early diagnosis and treatment of TB.

Policy brief Belgian EBCP mirror group ‘prevention’ and ‘early detection & screening’ in cancer

The availability and linkage of comprehensive data on cancer mortality, incidence, screening and vaccination (HPV/HB) are essential for monitoring the process and impact of all screening and vaccination programmes, and to generate evidence to improve prevention policies. Linkage of data registries will allow better exploitation of real-world data. Simplification of data sharing for epidemiological research is of utmost importance. Human, as well as technical/technological and legal/regulatory barriers need to be tackled in Belgium to aid actors involved in screening, to facilitate organised linkage of data. Rapid advances in technologies for early detection and screening for a broad range of cancer types provide significant opportunities. Such tests are not yet ready for adoption in screening programmes. Emerging evidence should be monitored to ensure that promising innovations can transition to implementation studies in a timely manner. More and sustained research is needed to generate the necessary scientific relevance for new screening techniques in relevant cancer types.

Development of a Maintenance System for Low Voltage Electricity Distribution Networks

This research focuses on important efforts to ensure the availability and reliability of electricity supply through the design and implementation of effective systems for monitoring and maintaining low voltage electricity distribution networks. The methods used in this research include analysis of maintenance needs, development of software for network monitoring, and integration of sensor technology for early detection of disturbances. The developed system aims to increase maintenance efficiency by providing real-time information about network conditions, enabling preventive action before disruptions occur. In addition, this system is also designed to reduce downtime and maintenance costs, as well as increase the reliability of electricity supply for customers. The research results show that implementing advanced sensor technology and monitoring software can significantly improve response to disruptions and minimize the impact on customer service. Thus, this system not only increases operational efficiency but also provides long-term benefits in maintaining the stability and reliability of electricity supply.

The hidden pandemic: surgical wound complications and the use of technology for early detection and prevention

The global volume of surgery is considerable and growing. It was estimated that 312.9 million surgical procedures were performed in 2012, which represented a 33.6% increase over 8 years. Despite advances in surgical technique, infection control practices and wound care, surgical wound complications such as surgical site infection and surgical wound dehiscence are unwanted outcome following surgery.

Trends and frontiers in signal amplification for aptamer-based tumor detection: A bibliometric analysis.

Malignant tumors are one of the leading causes of death worldwide, imposing a substantial economic and social burden. Early detection is the key to improving cure rates and reducing mortality rates, which requires the development of sensitive early detection technologies. Signal amplification techniques play a crucial role in aptamer-based early detection of tumors and are increasingly garnering attention from researchers. To investigate the current research status, developmental trajectories, and hotspots in signal amplification for aptamer-based tumor detection through bibliometric analysis. English publications pertaining to signal amplification in aptamer-based tumor detection were retrieved from the Web of Science Core Collection database. VOSviewer and CiteSpace software were employed to analyze various information within this field, including countries, institutions, authors, co-cited authors, journals, co-cited journals, cited references, and keywords. A total of 757 publications were included in this study. China accounted for 85.47% of all publications, with Nanjing University (China) emerging as the institution with the highest publication output. The most influential authors and journals were Hasanzadeh M. from Iran and "Biosensors and Bioelectronics", respectively. Exosomes and carcinoembryonic antigen (CEA) stood out as the most researched tumor-related molecules. Currently, the predominant signal amplification technique, nanomaterial, and signal transduction method were identified as hybridization chain reactions, gold nanoparticles, and electrochemical methods, respectively. Over the past 3 years, exosomes, CEA, electrochemical biosensors, and nanosheets have emerged as research hotspots, exhibiting a robust burst of intensity. This study is the first bibliometric analysis of literature on signal amplification in aptamer-based tumor detection and elucidates the current status, hotspots, and prospective research directions within this realm. Additionally, it provides an important reference for researchers.

Application of CRISPR Technology for Early Detection of Lung Cancer

Application of CRISPR Technology for Early Detection of Lung Cancer

Early multi-parameter detection study of lithium-ion batteries based on the ratio of blue to infrared light and gas concentration

As the use of lithium-ion batteries in energy storage and transportation grows, the number of fires and explosions caused by battery thermal runaway increases, emphasizing the vital need for enhanced early detection technology. Existing research does not clarify the effect of airflow environment and detection location on battery smoke flow and detection effectiveness. The purpose of this study is to illuminate the environmental effects on battery smoke diffusion, allowing for the selection of more appropriate detection parameters while also improving detection sensitivity and robustness. Here, the investigation focuses on the smoke characteristics of 18650 LiFePO4 (LFP) batteries, using the ratio of blue to infrared light and concentrations of CO and H2. Additionally, a detrending algorithm was developed to interpret smoke signals, and the smoke characteristics of batteries in different states of diffusion after thermal runaway occurred at different states of charge (SOC) were further investigated. It is shown that the smoke signal values processed by the detrending algorithm are more suitable for smoke detection in thermal runaway batteries. Using smoke and fugitive gas growth rate parameters, the results show that airflow interference is important in promoting smoke diffusion. Notably, the ambient state and the SOC of the battery have a greater influence on the maximum concentration of CO compared to H2. The linear equations and the addition of the environmental influence parameter DR imply that H2 is a better choice as the primary gas parameter for identifying battery runaway. The airflow disruption reduced the smoke response time by around 40 % while having minimal influence on gas diffusion. This study establishes a theoretical foundation for optimizing battery operating environments and gives practical guidelines for the use of multi-parameter monitoring and early detection of lithium-ion batteries. Furthermore, this study improves the safe management and protection of lithium batteries in their application.

Time-to-diagnosis and peri-diagnostic healthcare utilization between screen- and non-screen detected cancers: Evidence from SEER-Medicare.

11135 Background: Cancer screening programs can improve outcomes and may reduce treatment cost and utilization by shifting cancers to earlier, more curable stages at diagnosis (Dx). Few studies have evaluated the impact of screening on outcomes prior to diagnosis. Such information is needed to better understand the potential impact of newer blood-based multicancer early detection technologies. Methods: We conducted a retrospective cohort study using SEER cancer registry data linked with Medicare claims. Patients with a breast cancer (BC) or colorectal cancer (CRC) Dx between 2010-2019 were included if they were 65-74 years old at Dx, continuously enrolled in Medicare Parts A&B, had a Charlson Comorbidity Index of ≤2, and no cancer for ≥12 months prior to Dx. Those enrolled in an HMO or with high genetic risk for BC (in BC cohort) were excluded. Patients were assigned to screening groups prior to Dx; screening was defined as ≥1 screening procedure in the 6 months prior to Dx using CPT/HCPCS codes. Screening included FIT/FOBT, sigmoidoscopy, colonoscopy, CT colonography, mt-sDNA (CRC), and mammography (BC). Screened and not screened groups were compared for statistical significance using chi-squared for categorical variables, Wilcoxon rank-sum test for continuous variables. Results: Screening procedures were more prevalent in the BC cohort (68%) than the CRC cohort (44%) (table). Both screened subgroups (vs non-screened subgroups) had significantly lower proportions of patients diagnosed at stage 4 (2% vs 10% BC, 16% vs 27% CRC) and shorter times from first screening or imaging procedure to confirmed diagnosis (BC: 33 vs 227 days, CRC: 14 vs 29 days). Screened patients in both cancer cohorts had a similar number of average procedures prior to treatment initiation as non-screened (BC: 4.8 vs 4.2, CRC: 3.3 vs 3.3 respectively, including screening procedures). Conclusions: Individuals diagnosed with BC and CRC through screening exhibit earlier stage diagnoses and shorter intervals to diagnosis. Novel screening technologies such as MCED tests can potentially improve peri-diagnostic outcomes in cancers lacking existing or widely adopted screening methods. [Table: see text]

Mobile Diagnostic Clinics.

This article reviews the revolutionary impact of emerging technologies and artificial intelligence (AI) in reshaping modern healthcare systems, with a particular focus on the implementation of mobile diagnostic clinics. It presents an insightful analysis of the current healthcare challenges, including the shortage of healthcare workers, financial constraints, and the limitations of traditional clinics in continual patient monitoring. The concept of "Mobile Diagnostic Clinics" is introduced as a transformative approach where healthcare delivery is made accessible through the incorporation of advanced technologies. This approach is a response to the impending shortfall of medical professionals and the financial and operational burdens conventional clinics face. The proposed mobile diagnostic clinics utilize digital health tools and AI to provide a wide range of services, from everyday screenings to diagnosis and continual monitoring, facilitating remote and personalized care. The article delves into the potential of nanotechnology in diagnostics, AI's role in enhancing predictive analytics, diagnostic accuracy, and the customization of care. Furthermore, the article discusses the importance of continual, noninvasive monitoring technologies for early disease detection and the role of clinical decision support systems (CDSSs) in personalizing treatment guidance. It also addresses the challenges and ethical concerns of implementing these advanced technologies, including data privacy, integration with existing healthcare infrastructure, and the need for transparent and bias-free AI systems.

DNA methylation markers in esophageal cancer.

Esophageal cancer (EC) is a prevalent malignancy characterized by a low 5-year survival rate, primarily attributed to delayed diagnosis and limited therapeutic options. Currently, early detection of EC heavily relies on endoscopy and pathological examination, which pose challenges due to their invasiveness and high costs, leading to low patient compliance. The detection of DNA methylation offers a non-endoscopic, cost-effective, and secure approach that holds promising prospects for early EC detection. To identify improved methylation markers for early EC detection, we conducted a comprehensive review of relevant literature, summarized the performance of DNA methylation markers based on different input samples and analytical methods in EC early detection and screening. This review reveals that blood cell free DNA methylation-based method is an effective non-invasive method for early detection of EC, although there is still a need to improve its sensitivity and specificity. Another highly sensitive and specific non-endoscopic approach for early detection of EC is the esophageal exfoliated cells based-DNA methylation analysis. However, while there are substantial studies in esophageal adenocarcinoma, further more validation is required in esophageal squamous cell carcinoma. In conclusion, DNA methylation detection holds significant potential as an early detection and screening technology for EC.

Leveraging AI and Machine Learning to Develop and Evaluate a Contextualized User-Friendly Cough Audio Classifier for Detecting Respiratory Diseases: Protocol for a Diagnostic Study in Rural Tanzania.

Respiratory diseases, including active tuberculosis (TB), asthma, and chronic obstructive pulmonary disease (COPD), constitute substantial global health challenges, necessitating timely and accurate diagnosis for effective treatment and management. This research seeks to develop and evaluate a noninvasive user-friendly artificial intelligence (AI)-powered cough audio classifier for detecting these respiratory conditions in rural Tanzania. This is a nonexperimental cross-sectional research with the primary objective of collection and analysis of cough sounds from patients with active TB, asthma, and COPD in outpatient clinics to generate and evaluate a noninvasive cough audio classifier. Specialized cough sound recording devices, designed to be nonintrusive and user-friendly, will facilitate the collection of diverse cough sound samples from patients attending outpatient clinics in 20 health care facilities in the Shinyanga region. The collected cough sound data will undergo rigorous analysis, using advanced AI signal processing and machine learning techniques. By comparing acoustic features and patterns associated with TB, asthma, and COPD, a robust algorithm capable of automated disease discrimination will be generated facilitating the development of a smartphone-based cough sound classifier. The classifier will be evaluated against the calculated reference standards including clinical assessments, sputum smear, GeneXpert, chest x-ray, culture and sensitivity, spirometry and peak expiratory flow, and sensitivity and predictive values. This research represents a vital step toward enhancing the diagnostic capabilities available in outpatient clinics, with the potential to revolutionize the field of respiratory disease diagnosis. Findings from the 4 phases of the study will be presented as descriptions supported by relevant images, tables, and figures. The anticipated outcome of this research is the creation of a reliable, noninvasive diagnostic cough classifier that empowers health care professionals and patients themselves to identify and differentiate these respiratory diseases based on cough sound patterns. Cough sound classifiers use advanced technology for early detection and management of respiratory conditions, offering a less invasive and more efficient alternative to traditional diagnostics. This technology promises to ease public health burdens, improve patient outcomes, and enhance health care access in under-resourced areas, potentially transforming respiratory disease management globally. PRR1-10.2196/54388.

Nanobiosensors: A powerful Technology for Early Detection of Plant Parasitic Nematodes

Nanobiosensors: A powerful Technology for Early Detection of Plant Parasitic Nematodes

Non-invasive biomarkers for detecting progression toward hypovolemic cardiovascular instability in a lower body negative pressure model

Occult hemorrhages after trauma can be present insidiously, and if not detected early enough can result in patient death. This study evaluated a hemorrhage model on 18 human subjects, comparing the performance of traditional vital signs to multiple off-the-shelf non-invasive biomarkers. A validated lower body negative pressure (LBNP) model was used to induce progression towards hypovolemic cardiovascular instability. Traditional vital signs included mean arterial pressure (MAP), electrocardiography (ECG), plethysmography (Pleth), and the test systems utilized electrical impedance via commercial electrical impedance tomography (EIT) and multifrequency electrical impedance spectroscopy (EIS) devices. Absolute and relative metrics were used to evaluate the performance in addition to machine learning-based modeling. Relative EIT-based metrics measured on the thorax outperformed vital sign metrics (MAP, ECG, and Pleth) achieving an area-under-the-curve (AUC) of 0.99 (CI 0.95–1.00, 100% sensitivity, 87.5% specificity) at the smallest LBNP change (0–15 mmHg). The best vital sign metric (MAP) at this LBNP change yielded an AUC of 0.6 (CI 0.38–0.79, 100% sensitivity, 25% specificity). Out-of-sample predictive performance from machine learning models were strong, especially when combining signals from multiple technologies simultaneously. EIT, alone or in machine learning-based combination, appears promising as a technology for early detection of progression toward hemodynamic instability.

Early fire detection technology based on improved transformers in aircraft cargo compartments

The implementation of early and accurate detection of aircraft cargo compartment fire is of great significance to ensure flight safety. The current airborne fire detection technology mostly relies on single-parameter smoke detection using infrared light. This often results in a high false alarm rate in complex air transportation environments. The traditional deep learning model struggles to effectively address the issue of long-term dependency in multivariate fire information. This paper proposes a multi-technology collaborative fire detection method based on an improved transformers model. Dual-wavelength optical sensors, flue gas analyzers, and other equipment are used to carry out multi-technology collaborative detection methods and characterize various feature dimensions of fire to improve detection accuracy. The improved Transformer model which integrates the self-attention mechanism and position encoding mechanism is applied to the problem of long-time series modeling of fire information from a global perspective, which effectively solves the problem of gradient disappearance and gradient explosion in traditional RNN (recurrent neural network) and CNN (convolutional neural network). Two different multi-head self-attention mechanisms are used to classify and model multivariate fire information, respectively, which solves the problem of confusing time series modeling and classification modeling in dealing with multivariate classification tasks by a single attention mechanism. Finally, the output results of the two models are fused through the gate mechanism. The research results show that, compared with the traditional single-feature detection technology, the multi-technology collaborative fire detection method can better capture fire information. Compared with the traditional deep learning model, the multivariate fire prediction model constructed by the improved Transformer can better detect fires, and the accuracy rate is 0.995.

Advances in Sensor-Based Detection and Machine Learning for Osteoporosis: A Comprehensive Survey of Diagnostic Techniques

Abstract: One of the biggest challenges in the field of healthcare is the early identification of bone diseases. The increasing demand for diagnostic services often overwhelms current approaches, leading to increased healthcare costs, delayed identification, and patient discontent. To solve this problem, an Osteoporosis Early Detection System incorporating Biosensors and Machine Learning via the Internet of Things (IoT) is desperately needed. Osteoporosis difficulties and increased health risks are similar to congestion challenges that they might arise from delayed diagnosis. The scarcity of adequate technologies for early osteoporosis detection hinders effective healthcare delivery, especially in areas where the condition is more prevalent or during screenings that need quick identification. In order to enable prompt identification and notify medical professionals for preventive action, certain healthcare institutions have started including biosensors that can track changes in bone density. The development of these technologies could revolutionize the early diagnosis and treatment of osteoporosis and lessen the effects of the condition on patient’s health outcomes.

Reliability of udder infrared thermography as a non-invasive technology for early detection of sub-clinical mastitis in Sahiwal (Bos indicus) cows under semi-intensive production system

The present study focused on Sahiwal cows, a prominent milch breed in tropical India, to correlate udder temperature with physiological markers of stress and inflammation during subclinical mastitis (SCM). The primary goal was to assess the potential of udder infrared thermography for the early detection of SCM under the semi-intensive production. Cows were categorized based on milk somatic cell counts (SCC), with healthy (H) cows having SCC <2 × 105 cells/mL and no history of mastitis, and cows with subclinical mastitis (SCM) and initial stages of clinical mastitis (CM) having quarter milk SCC of 2–5 × 105 and >5 × 105 cells/mL, respectively. Firstly, udder thermograms were analysed for udder skin surface temperature (USST), teat skin surface temperature (TSST), and teat apex temperature (TAT) using Fluke software to determine the optimal site for temperature measurement during intramammary infection. Secondly, milk samples were collected for automatic estimation of compositional changes, electrical conductivity, and pH. Thirdly, milk whey was separated for quantifying stress and inflammatory indicators, including cortisol, prolactin, and acute-phase proteins (APPs): milk amyloid A and milk haptoglobin using bovine-specific ELISA kits. Significant increases (p < 0.01) in USST, TSST, TAT, cortisol, and APPs were observed in SCM and CM compared to healthy cows, while prolactin levels decreased (p < 0.01). The correlation matrix revealed strong positive correlations of SCC with USST (r = 0.84, p < 0.01). In ROC analysis, USST demonstrated cut-off values of 37.74 and 39.58 °C, with accuracy (p < 0.05) of 98% for SCM and 95% for CM, surpassing both TAT and TSST. Therefore, the combination of these non-invasive methods increases the reliability and accuracy of infrared thermography for early detection of SCM, providing valuable insights for the development of a protocol for routine screening and udder health monitoring in indigenous dairy cows.