Triage Method Research Articles

Cervical screening with self-sampling for postmenopausal women with molecular triage using extended genotyping and methylation.

With the transition from cytology to human papilloma virus (HPV) testing in cervical cancer screening, it is possible to use self-sampling instead of professionally collected samples. Most studies have included women between 20 and 60years age. Here we aimed to study postmenopausal women and investigate whether vaginal self-sampling is equally effective as professional sampling for detection of HSIL and the possibility to use a method for molecular triage directly on the screening sample. Postmenopausal women in Örebro county, Sweden, were invited (n=7835) during 2018-2020 to participate in the study including both professional and self-sampling. In total 2258 women returned both sample types, that were analyzed for HPV followed by triage for cytology, HPV genotyping and methylation and clinical follow-up according to national guidelines. The prevalence of HPV was 3.4% in the professionally collected samples and 12.6% in the self-collected. All women with high-grade squamous intraepithelial lesion (HSIL) were HPV-positive in both professionally and self-collected samples. For self-collected samples, we compared different triage strategies. Cytology was the most efficient strategy. Among the molecular triage methods, the combination of methylation and genotyping was most efficient but resulted in twice as many colposcopy referrals as cytology. In conclusion, HPV self-sampling with molecular triage detects HSIL to the same extent as professional screening with cytological triage. The specificity of molecular triage is, however, unacceptably low, and to avoid overtreatment other triage methods following primary self-sampling need to be developed.

Research progress of DNA methylation in the screening of cervical cancer and precancerous lesions

AbstractCervical cancer is one of the most common malignant tumors that seriously threaten women's health. Persistent infection with high risk human papillomavirus (HPV) is closely related to the progression of cervical cancer. Cervical cancer screening is an effective measure to reduce the incidence and mortality of cervical cancer. The two most common screening strategies are cytology and HPV testing, but they easily lead to missed diagnosis or overdiagnosis. To overcome such limitations, a new triage method needs to be explored. The World Health Organization second edition guideline includes DNA methylation testing as a new method to be evaluated. DNA methylation is a common epigenetic modification and is considered to be closely related to the occurrence and development of tumors. In recent years, many methylated genes have been found to be biomarkers for cervical cancer and precancerous lesions diagnosis. In this paper, we focus on the role and application of host DNA methylation, HPV DNA methylation, as well as combined host and HPV DNA methylation in the screening of cervical cancer and precancerous lesions.

Evaluating PAX1/JAM3 methylation for triage in HPV 16/18-infected women

ObjectiveReferring all women who tested positive for human papillomavirus (HPV) 16/18 to colposcopy may lead to potential over-referral issues. Triage tests based on cytology results face challenges in achieving accurate diagnoses. Our study aims to assess the clinical effectiveness of PAX1/JAM3 methylation (CISCER) test as a triage method for HPV 16/18-positive women.MethodsFrom November 2021 to December 2022, a total of 334 women who tested positive for HPV 16/18 and were referred to colposcopy at The Second Affiliated Hospital of Zhejiang University School of Medicine were studied. The clinical utility of the CISCER test, cytology, and the combination of CISCER with cytology as potential triage tests was compared.ResultsWe observed a significant increase in the methylation levels of PAX1 gene and JAM3 gene in women with cervical intraepithelial neoplasia (CIN) grade 2 or severe (CIN2+). The CISCER test demonstrated superior triage performance over cytology, even when used in combination with cytology, showing a high sensitivity of 89.0% (95% confidence interval [CI] 82.9–95.1%) and specificity of 95.3% (95% CI 92.6–98.0%). It achieved an area under the curve of 0.921 (95% CI 0.877–0.966) and an odds ratio of 164.02 (95% CI 68.64–391.95). The immediate CIN2+ risk based on positive CISCER results would be 89.0% (95% CI 80.8–94.1%), with an estimated average of 1.12 referrals needed to detect one CIN2+ case. Moreover, CISCER triaging successfully identified all cancer patients and did not miss any CIN3+ cases among women aged ≥ 30.ConclusionsThe PAX1/JAM3 methylation detection exhibited excellent accuracy in identifying cervical precancerous lesions in HPV 16/18-positive women and could be considered as a triage tool to reduce excessive referrals for colposcopy and overtreatment.

Design and implementation of a radiomic-driven intelligent dental hospital diversion system utilizing multilabel imaging data

BackgroundWith the increasing burden of dental diseases and the limited availability of healthcare resources, traditional triage methods are inadequate in efficiently utilizing healthcare resources and meeting patient needs. The aim of this study is to develop an advanced triage system that combines oral radiomics and biological multi-omics data, which enables accurate departmental referral of patients by automatically interpreting biological information in oral X-ray images.MethodsUsing a multi-label learning algorithm, we analyzed multi-omics data from 3,942 patients with oral diseases from three cohorts between July 1, 2023 and August 18, 2023, and continuously monitored classification accuracy (ACC) metrics.ResultsIn the test cohort and external validation cohort, we used the DenseNet121 model to analyze the multi-omics data and achieved classification accuracies of 0.80 and 0.82, respectively.ConclusionsThe main contribution of this study is to propose a new treatment process that incorporates biological multi-omics data, which reduces the workload of physicians while providing timely and accurate medical care to patients. Through comparative experiments, we demonstrate that the process is more efficient than existing processes. In addition, this intelligent triage system demonstrates high prediction accuracy in practical applications, providing new ideas and methods for biological multi-omics research.

TRIAGE: an R package for regulatory gene analysis.

Regulatory genes are critical determinants of cellular responses in development and disease, but standard RNA sequencing (RNA-seq) analysis workflows, such as differential expression analysis, have significant limitations in revealing the regulatory basis of cell identity and function. To address this challenge, we present the TRIAGE R package, a toolkit specifically designed to analyze regulatory elements in both bulk and single-cell RNA-seq datasets. The package is built upon TRIAGE methods, which leverage consortium-level H3K27me3 data to enrich for cell-type-specific regulatory regions. It facilitates the construction of efficient and adaptable pipelines for transcriptomic data analysis and visualization, with a focus on revealing regulatory gene networks. We demonstrate the utility of the TRIAGE R package using three independent transcriptomic datasets, showcasing its integration into standard analysis workflows for examining regulatory mechanisms across diverse biological contexts. The TRIAGE R package is available on GitHub at https://github.com/palpant-comp/TRIAGE_R_Package.

Impact of knowledge of HPV positivity on cervical cytology performance in latin america.

Cervical cytology is recommended by WHO as a triage option in HPV-based cervical cancer screening programmes. We assessed the performance of cytology to detect CIN3+ without and with knowledge of HPV positivity. Women were screened with cytology and HPV across ESTAMPA study centres in Latin America. Screen-positives were referred to colposcopy with biopsy and treatment as needed. Cytology was initially interpreted without knowing HPV results. A subset of cytologies from HPV-positive women were re-interpreted at the same laboratories, with knowledge of HPV status, blinded to previous cytology and histological diagnosis. Performance indicators for cytology to detect CIN3+ without and with knowledge of HPV positivity were estimated. A total of 4,087 women were included, of which 490 had histologically confirmed CIN3 + (455 CIN3 and 35 cancers). Cytology sensitivity without knowledge of HPV positivity for CIN3+ was 47.2% (95% CI: 42.5-51.9), whereas with knowledge of HPV positivity, the sensitivity was higher (58.9%, 95% CI: 54.2-63.5), p < .0001. The specificity without knowledge of HPV was 89.4% (95% CI: 88.2-90.5), while with knowledge of HPV positivity was 78.9% (95% CI: 77.4-80.4), p < .0001. Performance estimates varied by study centre for cytology without knowing the HPV positivity, (range from 32.8% to 61.5% for sensitivity; range 80.7% to 98.6% for specificity). Similarly, performance varied with knowledge of HPV positivity (36.1% to 93.4% for sensitivity; 39.6% to 98.6% for specificity). The increase in sensitivity of cytology with HPV knowledge was limited and highly variable, reinforcing the need for alternative triage methods to support cervical cancer elimination goals.

Cervical cancer screening: efficacy of PAX1 and JAM3 methylation assay in the triage of atypical squamous cell of undetermined significance (ASC-US)

BackgroundAtypical squamous cells of undetermined significance (ASC-US) often present diagnostic challenges with cytology-based results, leading to potential underdiagnosis or overdiagnosis. An effective triage method is essential for managing these cases to reduce unnecessary referrals and treatment.MethodsA total of 322 women diagnosed with ASC-US were tested for HPV-DNA and the PAX1 and JAM3 methylation (PAX1m/JAM3m) test in the study.ResultsMethylation levels of PAX1 and JAM3 were significantly elevated in cervical lesions classified as CIN2 or more severe lesions (CIN2+). The methylation assay demonstrated a sensitivity of 83.8% and a specificity of 95.8%, outperforming HPV-DNA testing in differentiating high-grade cervical lesions among women with ASC-US. Moreover, PAX1m/JAM3m testing significantly reduced the colposcopy referral rate for further diagnostic procedures in high-risk HPV-positive women by 79.5%.ConclusionsPAX1m/JAM3m testing shows promise as a reliable supplemental method to HPV-DNA testing for the triage of women with cytologic ASC-US. In addition, the molecular triage based on the CISCER assay or single PAX1 or JAM3 methylation, had better effects in the women with non-HPV16/18 group. This approach could potentially minimize overtreatment and unnecessary referrals in clinical practice, enhancing patient management and resource utilization.

A Novel Anthropometric Phantom for Rapid Radiological Triage: A Quick Sort Triage Solution.

Rapidly identifying individuals who have received internal radiation exposure above action guidelines is crucial for mitigating health risks and addressing public concerns immediately following a radiological event involving the dispersal of radioactive materials. This study describes a novel triage method using a conventional Geiger-Mueller (GM) detector to select those individuals from the large group of persons who may have received an intake of radioactive material at levels corresponding to one Clinical Decision Guide (CDG). The triage method involves placing a portable GM detector against the lower anterior torso of a sitting person as they bend over to surround the detector with their body. The response of the GM detector is evaluated using a new, specially designed anthropometric phantom that simulates combined tissues of the lower thorax and gastrointestinal (GI) tract and is fabricated with a tissue substitute material that matches the overall radiological properties of human tissue present in this body region. The phantom has four separate layers of tissue substitute material with ports to accommodate a single GM detector at the center and one or more sealed radioactive sources that can be arranged to characterize the detector response for a variety of source distributions, including a "hot spot." In this study, the response of a Ludlum Model 133-4 GM detector was evaluated using sealed sources of 232Th and 137Cs to determine the measurement efficiency for a quantity of activity present in the abdomen within a few hours post-intake equivalent to 1 CDG. Results demonstrate that the Quick Sort triage procedure using a single GM detector placed against the abdomen of a person can reliably detect internal deposition resulting from an intake equivalent to 1 CDG for 232Th or a significantly lower activity of 137Cs within a few hours following a radiological incident. The evaluation was performed over a wide range of photon energies, so the Quick Sort triage procedure is expected to be suitable for most fission products distributed uniformly within the abdomen or as a single "hot spot."

ChatGPT provides safe responses to post-operative concerns following total joint arthroplasty

Introduction: Postoperative triage is a considerable financial and time burden following total joint arthroplasty (TJA). An ideal post-operative triage method would be equally as safe as triage nurses, but more cost-effective and time-efficient. Therefore, this study aimed to see if ChatGPT could serve as a safe and effective method of postoperative triage in responding to patient concerns following TJA. Methods: A list of ten potential concerns from post-operative arthroplasty patients was compiled ranging from “How much walking can I do?” to “My leg is throbbing and red, and I’m having trouble breathing. What should I do?”. These concerns were presented to trained orthopaedic triage nurses (n=3) and ChatGPT (Version 3.5). The generated responses were rated blindly by three fellowship-trained orthopaedic surgeons specializing in adult reconstruction using Likert scales ranging from 1-5 for safety and completeness (1 being highly unsafe/incomplete; 5 being highly safe/complete). The average scores were calculated for each prompt and are presented as mean±standard deviation. Results: There was no significant difference in average safety scores between ChatGPT responses (4.2±0.5) and those of triage nurses (4.3±0.4) (P=0.68). Similarly, there was no significant difference in completeness scores between ChatGPT responses (3.9±0.8) and those of triage nurses (4.0±0.6) (P=0.67). Furthermore, there were no significant differences in safety or completeness between ChatGPT and triage nurses for any of the individual prompts (all P values &gt;0.05). Conclusions: Postoperative triage is a critical component of perioperative care but represents a substantial time and cost burden. This preliminary study highlights the promising opportunity for future use of AI-enabled chatbots to provide instantaneous, safe, and complete responses to postoperative patient concerns.

Capsule Endoscopy for the Risk Stratification and Management of Acute Upper Gastrointestinal Bleeding in Emergency Departments: A Systematic Review on Triage, Risk Stratification, and Management.

Gastrointestinal bleeding is a common occurrence in emergency departments. The standard of care for it is an esophagogastroduodenoscopy within 24 hours to diagnose and potentially treat the bleeding. Several tools and pre-endoscopic risk assessment scores are used to help evaluate and manage upper gastrointestinal bleeding. Additionally, capsule endoscopy providesanon-invasive method to visualize thegastrointestinal tract and identify lesions. The aim of this review was to explore the role of capsule endoscopy in thetriage, stratification, and management of upper gastrointestinal bleeding patients in the emergency department. Four databases, PubMed, Scopus, Embase, and the Cochrane Library, were searched using keywords related to capsule endoscopy and gastrointestinal bleeding in the emergency department. Studies were included if they assessed the use of capsule endoscopy in emergency settings for managing upper gastrointestinal bleeding. After screening titles, abstracts, and full texts and reviewing bibliographies for relevant articles, data on study design, participant demographics, capsule endoscopy procedure description, and outcomes were collected into a pre-designed spreadsheet. The review focused on the triage, risk stratification, management impact, and safety of capsule endoscopy. The literature search identified 712 records, with 37 studies screened for full-text review, resulting in nine studies included in the review. These studies involved 634 patients and primarily compared capsule endoscopy with standard care in emergency settings. Capsule endoscopy demonstrated potential advantages, including improved identification of high-risk lesions and reduced hospital admissions. Capsule endoscopy effectively detected bleeding and reduced the need for invasive procedures compared to standard practices. Capsule endoscopy also had lower costs relative to traditional triaging methods. The use of capsule endoscopy in the risk stratification and management of upper gastrointestinal bleeding in emergency settings is promising. Its high diagnostic accuracy can enhance patient outcomes by enabling timely and precise diagnosis, reducing the need for invasive procedures. Future research should focus on larger randomized trials to validate capsule endoscopy's efficacy and explore its cost-effectiveness.

A novel triage framework for emergency department based on machine learning paradigm

AbstractEmergency departments, crucial in managing patient emergencies, are often challenged by overcrowding and diagnostic errors during triage—the process that assesses the urgency of patients' conditions. Traditional triage systems, heavily dependent on human judgement, are prone to errors like under‐triage, where severe conditions are missed, delaying treatment, and over‐triage, where less severe conditions are overly prioritized, causing unnecessary resource use and morbidity. This thesis presents a novel multi‐model machine‐learning framework designed to enhance triage accuracy by evaluating multiple medical conditions concurrently, including chronic illnesses like heart disease. The framework employs various machine‐learning techniques—such as logistic regression, support vector machines, random forests, deep neural networks, and decision trees—to analyze different medical conditions in two comprehensive phases. In the first phase, patients' conditions are categorized, and a multi‐tiered analysis using multiple classifiers refines the assessment by considering probabilistic outcomes from each classifier. The second phase synthesizes these insights into a unified and precise triage decision, distinguishing between patients who require critical care and those needing less urgent hospitalization. This integration of diverse machine learning models allows for a fused and precise triage decision, overcoming traditional triage systems' limitations that usually focus on single conditions and rely on isolated model predictions. A hybrid feature selection method is also utilized to identify critical predictors, enhancing the decision‐making process. The framework is validated through a specially curated dataset that simulates multiple triage scenarios, evaluated by medical experts for efficacy. Comparative analysis with traditional triage methods demonstrates significant improvements in decision accuracy, as evidenced by higher area under curve (AUC) values—0.95 for critical care and 0.90 for hospitalization. The implementation of this data‐driven approach substantially reduces human error, boosts operational efficiency, and aids medical staff in making rapid, informed decisions. This research represents a significant advancement in emergency medical care, illustrating the benefits of integrating sophisticated machine learning techniques to improve patient outcomes and resource management.

Factors affecting the accuracy of prehospital triage application and prehospital scene time in simulated mass casualty incidents

BackgroundThe contemporary management of mass casualty incidents (MCIs) relies on the effective application of predetermined, dedicated response plans based on current best evidence. Currently, there is limited evidence regarding the factors influencing the accuracy of first responders (FRs) in applying the START protocol and the associated prehospital times during the response to MCIs. The objective of this study was to investigate factors affecting FRs’ accuracy in performing prehospital triage in a series of simulated mass casualty exercises. Secondly, we assessed factors affecting triage-to-scene exit time in the same series of exercises.MethodsThis retrospective study focused on simulated casualties in a series of simulated MCIs Full Scale Exercises. START triage was the triage method of choice. For each Full-Scale Exercise (FSEx), collected data included exercise and casualty-related information, simulated casualty vital parameters, simulated casualty anatomic lesions, scenario management times, and responder experience.ResultsAmong the 1090 casualties included in the primary analysis, 912 (83.6%) were correctly triaged, 137 (12.6%) were overtriaged, and 41 (3.7%) were undertriaged. The multinomial regression model indicated that increasing heart rate (RRR = 1.012, p = 0.008), H-AIS (RRR = 1.532, p < 0.001), and thorax AIS (T-AIS) (RRR = 1.344, p = 0.007), and lower ISS (RRR = 0.957, p = 0.042) were independently associated with overtriage. Undertriage was significantly associated with increasing systolic blood pressure (RRR = 1.013, p = 0.005), AVPU class (RRR = 3.104 per class increase), and A-AIS (RRR = 1.290, p = 0.035). The model investigating the factors associated with triage-to-scene departure time showed that the assigned prehospital triage code red (TR = 0.841, p = 0.002), expert providers (TR = 0.909, p = 0.015), and higher peripheral oxygen saturation (TR = 0.998, p < 0.001) were associated with a reduction in triage-to-scene departure time. Conversely, increasing ISS was associated with a longer triage-to-scene departure time (TR = 1.004, 0.017).ConclusionsUnderstanding the predictors influencing triage and scene management decision-making by healthcare professionals responding to a mass casualty may facilitate the development of tailored training pathways regarding mass casualty triage and scene management.

Improving Triage Accuracy in Prehospital Emergency Telemedicine: Scoping Review of Machine Learning-Enhanced Approaches.

Prehospital telemedicine triage systems combined with machine learning (ML) methods have the potential to improve triage accuracy and safely redirect low-acuity patients from attending the emergency department. However, research in prehospital settings is limited but needed; emergency department overcrowding and adverse patient outcomes are increasingly common. In this scoping review, we sought to characterize the existing methods for ML-enhanced telemedicine emergency triage. In order to support future research, we aimed to delineate what data sources, predictors, labels, ML models, and performance metrics were used, and in which telemedicine triage systems these methods were applied. A scoping review was conducted, querying multiple databases (MEDLINE, PubMed, Scopus, and IEEE Xplore) through February 24, 2023, to identify potential ML-enhanced methods, and for those eligible, relevant study characteristics were extracted, including prehospital triage setting, types of predictors, ground truth labeling method, ML models used, and performance metrics. Inclusion criteria were restricted to the triage of emergency telemedicine services using ML methods on an undifferentiated (disease nonspecific) population. Only primary research studies in English were considered. Furthermore, only those studies using data collected remotely (as opposed to derived from physical assessments) were included. In order to limit bias, we exclusively included articles identified through our predefined search criteria and had 3 researchers (DR, JS, and KS) independently screen the resulting studies. We conducted a narrative synthesis of findings to establish a knowledge base in this domain and identify potential gaps to be addressed in forthcoming ML-enhanced methods. A total of 165 unique records were screened for eligibility and 15 were included in the review. Most studies applied ML methods during emergency medical dispatch (7/15, 47%) or used chatbot applications (5/15, 33%). Patient demographics and health status variables were the most common predictors, with a notable absence of social variables. Frequently used ML models included support vector machines and tree-based methods. ML-enhanced models typically outperformed conventional triage algorithms, and we found a wide range of methods used to establish ground truth labels. This scoping review observed heterogeneity in dataset size, predictors, clinical setting (triage process), and reported performance metrics. Standard structured predictors, including age, sex, and comorbidities, across articles suggest the importance of these inputs; however, there was a notable absence of other potentially useful data, including medications, social variables, and health system exposure. Ground truth labeling practices should be reported in a standard fashion as the true model performance hinges on these labels. This review calls for future work to form a standardized framework, thereby supporting consistent reporting and performance comparisons across ML-enhanced prehospital triage systems.

HPV 16/18 E7 oncoprotein detection as a promising triage strategy for HPV 16/18-positive patients: A prospective multicenter study with a 2-year follow up.

To explore the effectiveness of HPV 16/18 E7 oncoprotein in detecting high-grade cervical intraepithelial neoplasia (CIN) and predicting disease outcomes in HPV 16/18-positive patients. The present study was a cross-sectional study with a 2-year follow up. We collected 915 cervical exfoliated cell samples from patients who tested positive for HPV 16/18 in gynecologic clinics of three tertiary hospitals in Beijing from March 2021 to October 2022 for HPV 16/18 E7 oncoprotein testing. Subsequently, 2-year follow up of 408 patients with baseline histologic CIN1 or below were used to investigate the predictive role of HPV 16/18 E7 oncoprotein in determining HPV persistent infection and disease progression. The positivity rate of the HPV 16/18 E7 oncoprotein assay was 42.06% (249/592) in the inflammation/CIN 1 group and 85.45% (277/324) in the CIN2+ group. For CIN2+ detection, using the HPV 16/18 E7 oncoprotein assay combined with HPV 16/18 testing, the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 85.45%, 57.94%, 52.57%, and 87.95%, respectively. During the 2-year follow up, the sensitivity, specificity, PPV, and NPV for predicting persistent HPV infection were 48.44%, 58.21%, 34.64%, and 71.18% in the baseline inflammation and CIN1 group. As a triage method for high-grade CIN screening in HPV 16/18-positive patients, HPV 16/18 E7 oncoprotein demonstrated a relatively high NPV, making it suitable for clinical use in triaging HPV 16/18-positive cases and potentially reducing the colposcopic referral rate. HPV 16/18 E7 oncoprotein exhibited a preferably predictive value in determining HPV infection outcomes and disease progression.

A review of criticality dosimetry at the Y-12 National Security Complex and practical importance of dose accuracy in emergency response

A nuclear criticality results in the emission of both neutron and gamma radiation and can produce doses to personnel near the event that exceed 0.1 Gy (10 rad). The primary purpose of nuclear accident dosimetry is to rapidly identify affected personnel in need of prompt medical treatment and to reassure personnel who have been only minimally exposed. While accurate dosimetry is desired, it must be recognized that dose determinations made from whole-body dosimeters or simple triage methods are very rough estimates and contain significant uncertainties. Even when accounting for factors like varying neutron energy spectra, mean photon energies, body orientation within the radiation field, and transient effects on dosimeter response, etc., the end value is a dosimetric quantity defined for very specific radiological conditions and determined within a simple phantom usually at a single depth. Of more importance is the biological response to the radiation, which will vary by person and can be affected by the individual's radiation sensitivity, age, gender, mass, and underlying health conditions. The overall biological, person-specific response to a given dose cannot be precisely determined except by patient symptom observation and individual biological dosimetry (e.g. chromosome analysis, lymphocyte ratios, etc.). This work describes and discusses the criticality accident dosimetry program at the Y-12 National Security Complex, a United States Department of Energy National Nuclear Security Administration facility. The primary goals of the Y-12 accident dosimetry program are, among others, the rapid identification of significantly exposed persons, prompt routing of exposed workers for medical evaluation and treatment, and the ultimate processing of dosimeters to assign doses to personnel.

Multisource Data Framework for Prehospital Emergency Triage in Real-Time IoMT-Based Telemedicine Systems

Background and ObjectiveThe Internet of Medical Things (IoMT) has revolutionized telemedicine by enabling the remote monitoring and management of patient care. Nevertheless, the process of regeneration presents the difficulty of effectively prioritizing the information of emergency patients in light of the extensive amount of data generated by several integrated health care devices. The main goal of this study is to be improving the procedure of prioritizing emergency patients by implementing the Real-time Triage Optimization Framework (RTOF), an innovative method that utilizes diverse data from the Internet of Medical Things (IoMT). MethodsThe study’s methodology utilized a variety of Internet of Medical Things (IoMT) data, such as sensor data and texts derived from electronic medical records. Tier 1 supplies sensor and textual data, and Tier 3 imports textual data from electronic medical records. We employed our methodologies to handle and examine data from a sample of 100,000 patients afflicted with hypertension and heart disease, employing artificial intelligence algorithms. We utilized five machine-learning algorithms to enhance the accuracy of triage. ResultsThe RTOF approach has remarkable efficacy in a simulated telemedicine environment, with a triage accuracy rate of 98%. The Random Forest algorithm exhibited superior performance compared to the other approaches under scrutiny. The performance characteristics attained were an accuracy rate of 98%, a precision rate of 99%, a sensitivity rate of 98%, and a specificity rate of 100%. The findings show a significant improvement compared to the present triage methods. ConclusionsThe efficiency of RTOF surpasses that of existing triage frameworks, showcasing its significant ability to enhance the quality and efficacy of telemedicine solutions. This work showcases substantial enhancements compared to existing triage approaches, while also providing a scalable approach to tackle hospital congestion and optimize resource allocation in real-time. The results of our study emphasize the capacity of RTOF to mitigate hospital overcrowding, expedite medical intervention, and enable the creation of adaptable telemedicine networks. This study highlights potential avenues for further investigation into the integration of the Internet of Medical Things (IoMT) with machine learning to develop cutting-edge medical technologies.

Identify, screen and treat via electronic pathway: a semiautomated approach to retriaging a liver clinic waitlist.

Long specialist outpatient waiting lists are a source of clinical risk. Triage assignment is based on subjective assessment of referrals and fails to account for dynamic changes in disease status while patients await clinical review. To pilot an innovative triage method using a trifold approach to conduct noninvasive assessment of fibrosis and to determine the feasibility of reflex hepatitis C virus (HCV) polymerase chain reaction (PCR) testing. A total of 1006 patients awaiting an initial liver clinic appointment at a tertiary Australian hospital were sent a short message service (SMS) requesting a blood test be completed. The first 60 patients received an SMS only, and the subsequent 946 patients also received a phone call from a Liver Care Guide (LCG), a nonclinician employed to increase patient engagement. Liver fibrosis assessment through noninvasive testing was performed using an aspartate aminotransferase to platelet ratio index (APRI) and fibrosis-4 (FIB4) score. Patients with an APRI ≥1, FIB4 ≥3.25 or positive HCV PCR were retriaged to Category 1. Four hundred ninety (49%) patients completed testing and 40 (4%) were triaged to Category 1. Subanalyses demonstrated increased response rates with LCG input (P = 0.012). Retriaged patients had been on the waitlist for a median of 216 days, exceeding initial category recommendations. This study successfully implemented a semiautomated strategy that prioritises patients with probable advanced liver disease or active HCV, demonstrating enhanced patient engagement with LCG support. It highlights the burden of patients referred for specialist care and the need for innovative strategies for monitoring and objective risk stratification.

VolGPT: Evaluation on triaging ransomware process in memory forensics with Large Language Model

In the face of the harm that ransomware can inflict upon users’ computers, the imperative to efficiently and accurately triage its processes within memory forensics becomes increasingly crucial. However, ransomware perpetrators employ sophisticated techniques, such as process masquerading, to evade detection and analysis. In response to these challenges, we propose a novel ransomware triage method leveraging a Large Language Model (LLM) in conjunction with the Volatility framework, the de-facto standard in memory forensics. We conducted experiments on memory dumps infected by five different ransomware families, utilizing LLM-based approaches. Through extensive experiments, our method named volGPT demonstrated high accuracy in identifying ransomware-related processes within memory dumps. Additionally, our approach exhibited greater efficiency and provided more comprehensive explanations during ransomware triage than other state-of-the-art methods.

Screening outcome of HPV-vaccinated women: Data from the Danish Trial23 cohort study.

Danish women-who were HPV-vaccinated as girls-are now reaching an age where they are invited to cervical cancer screening. Because of their expected lower cervical cancer risk, we must reassess our screening strategies. We analyzed Danish HPV-vaccinated women's outcomes after the first screening test at age 23. Our study was embedded in Danish routine cytology-based screening. We conducted an observational study and included women born in 1994, offered the 4-valent HPV vaccine at age 14, and subsequently invited to screening at age 23. Cervical cytology was used for diagnostics and clinical management. Residual material was HPV tested with Cobas® 4800/6800. The most severe histology diagnosis within 795 days of screening was found through linkage with the Danish National Pathology Register. We calculated the number of women undergoing follow-up (repeated testing and/or colposcopy) per detected cervical intraepithelial neoplasia (CIN2+). A total of 6021 women were screened; 92% were HPV-vaccinated; 12% had abnormal cytology; 35% were high-risk HPV-positive, including 0.9% HPV16/18 positive, and 20% had follow-up. In women that were cytology-abnormal and HPV-positive (Cyt+/HPV+), 610 (98.5%) had been followed up, and 138 CIN2+ cases were diagnosed, resulting in 4.4 (95% CI 3.9-5.2) women undergoing follow-up per detected CIN2+. In contrast to recommendations, 182 (12.2%) cytology-normal and HPV-positive (Cyt-/HPV+) women were followed up within 795 days, and 8 CIN2+ cases were found, resulting in 22.8 (95% CI 13.3-59.3) women undergoing follow-up per detected CIN2+. Overall, HPV prevalence was high in HPV-vaccinated women, but HPV16/18 had largely disappeared. In the large group of cytology-normal and HPV-positive women, 23 had been followed up per detected CIN2+ case. Our data indicated that primary HPV screening of young HPV-vaccinated women would require very effective triage methods to avoid an excessive follow-up burden. Trial registration number: NCT0304955.

Accuracy of nurse-based Cipto Triage Method in the emergency department

Background The Cipto Triage Method (CTM) is a method developed in Indonesia for assessing the clinical acuity of emergency department patients. To evaluate the accuracy of the CTM, this study compared triage decisions using the CTM performed by nurses to the triage decisions performed by emergency medical officers (EMO). Methods This cross-sectional diagnostic study was performed in a single-centre referral hospital in Jakarta, Indonesia. Adult patients who attended the emergency department (ED) met the inclusion criteria. Trauma cases, pregnancy, and psychiatric disorders were excluded. All eligible patients underwent triage assessment based on CTM by a triage nurse and were then referred to the ED treatment zone for triage assessment performed by an EMO. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and likelihood ratio were calculated. Results Between April and July 2022, 902 participants were randomly selected. The overall accuracy of the triage assessment of the index test was 84.7%, and the PPV of resuscitation and urgent triage was very good (90.5% and 84.5%, respectively). In the non-urgent category, the PPV was acceptable (72%), but the NPV was very good (92.2%). Conclusions Nurse-based triage assessment using CTM in the ED had very good accuracy in determining clinical acuity.