Accurate Screening Tool Research Articles

Comparison of the sensitivity and specificity of commercial anti-dengue virus IgG tests to identify persons eligible for dengue vaccination.

The Advisory Committee on Immunization Practices (ACIP) has set forth recommendations that dengue pre-vaccination screening tests must exhibit at least 98% specificity and 75% sensitivity. Our research rigorously assesses the performance of various commercial tests against these benchmarks using well-characterized specimens from Puerto Rico. The findings from our study are particularly relevant given FDA approval and ACIP recommendation of Sanofi Pasteur's Dengvaxia vaccine, highlighting the need for accurate pre-vaccination screening tools.

Validating the Fluctuating Mental Status Evaluation in Neurocritically Ill Patients With Acute Stroke.

Neurocritically ill patients are at high risk for developing delirium, which can worsen the long-term outcomes of this vulnerable population. However, existing delirium assessment tools do not account for neurologic deficits that often interfere with conventional testing and are therefore unreliable in neurocritically ill patients. We aimed to determine the accuracy and predictive validity of the Fluctuating Mental Status Evaluation (FMSE), a novel delirium screening tool developed specifically for neurocritically ill patients. Prospective validation study. Neurocritical care unit at an academic medical center. One hundred thirty-nine neurocritically ill stroke patients (mean age, 63.9 [sd, 15.9], median National Institutes of Health Stroke Scale score 11 [interquartile range, 2-17]). None. Expert raters performed daily Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition-based delirium assessments, while paired FMSE assessments were performed by trained clinicians. We analyzed 717 total noncomatose days of paired assessments, of which 52% (n = 373) were rated by experts as days with delirium; 53% of subjects were delirious during one or more days. Compared with expert ratings, the overall accuracy of the FMSE was high (area under the curve [AUC], 0.85; 95% CI, 0.82-0.87). FMSE scores greater than or equal to 1 had 86% sensitivity and 74% specificity on a per-assessment basis, while scores greater than or equal to 2 had 70% sensitivity and 88% specificity. Accuracy remained high in patients with aphasia (FMSE ≥ 1: 82% sensitivity, 64% specificity; FMSE ≥ 2: 64% sensitivity, 84% specificity) and those with decreased arousal (FMSE ≥ 1: 87% sensitivity, 77% specificity; FMSE ≥ 2: 71% sensitivity, 90% specificity). Positive FMSE assessments also had excellent accuracy when predicting functional outcomes at discharge (AUC, 0.86 [95% CI, 0.79-0.93]) and 3 months (AUC, 0.85 [95% CI, 0.78-0.92]). In this validation study, we found that the FMSE was an accurate delirium screening tool in neurocritically ill stroke patients. FMSE scores greater than or equal to 1 indicate "possible" delirium and should be used when prioritizing sensitivity, whereas scores greater than or equal to 2 indicate "probable" delirium and should be used when prioritizing specificity.

A-251 Simplification of Molecular Diagnostics for Sexually Transmitted Infection Point-of-Care Testing

Abstract Background HPV-caused cancers contribute to a large disease burden, accounting for 5% of all cancers. It is estimated that over 700,000 people develop HPV-related cancers each year with the majority being cervical cancer. The burden of this disease is disproportionately carried by low-income countries with the highest rates of HPV cervical infections primarily found in sub-Saharan Africa, Latin America, Eastern Europe, and South-East Asia. Many regions in low-resource countries lack adequate access to sensitive point-of-care screening tools, preventing timely diagnosis and treatment. Current low-cost methods, such as Pap smears and visual inspection using acetic acid suffer from low sensitivity, specificity, and reproducibility which limit their effectiveness as a screening modality. Many countries use nucleic acid amplification tests (NAATs) to identify key HPV infections which may progress towards cervical cancer. However, the expenditure for NAAT-capable equipment and reagents are cost-prohibitive for rural and underserved communities. To reduce screening barriers, we developed an isothermal HPV molecular test that can detect all 14 cancer-causing HPV strains using a novel amplification methodology combined with G-quadruplex DNAzyme colorimetric detection. Methods We developed a novel isothermal amplification technique that is related to loop-mediated isothermal amplification (LAMP) but uses modified looped primers to enable exponential amplification at 60°C for 1 hour. The modified primers only require two binding sites compared to 4-6 in LAMP. To detect the amplified products, we used G-quadruplex peroxidase-like DNAzyme probes which reduce ABTS to produce a visually interpreted result. Analytical validation evaluated the method’s limit of detection, specificity, and accuracy. As proof of concept in a relevant matrix, clinical cervical brushings collected ThinPrep Pap media were tested with the new method and compared to an FDA-approved reference qPCR test. Results Repeated experiments demonstrate that the lowest detectable HPV DNA concentration was approximately 1000 genomic copies/µL with no amplification with other pathogens. As proof of concept, the comparison to the reference standard demonstrated high accuracy. Conclusions The application of our assay is intended as a near-patient screening tool with further evaluation by a clinician for confirmation. With an accurate and rapid screening tool, we envision low-resource regions across the world will have the tools to rapidly detect and treat cervical cancers in their early stages.

Deep Learning Methods for Chest X-Ray Imaging-Based COVID-19 Pneumonia Detection

The COVID-19 pandemic currently underway has highlighted a need for fast and accurate screening tools to help identify the disease, particularly in resource-poor settings. In this paper, a deep convolutional neural network (CNN) model is proposed for the automatic detection of COVID-19 pneumonia using chest X-ray images that helps in reducing the cost and processing time compared to traditional testing procedures. It uses several deep-structured medical image data types and improvement of the deep learning model architecture to achieve good diagnostic accuracy. Our hybrid CNN architecture integrates VGG-16 for feature extraction and ResNet-50 for pattern complexity assessment in detecting fine changes characteristic of COVID-19 pneumonia. Our dataset for this study is a collection of few thousands labelled chest X-ray images categorized in three classes, which are COVID-19, viral pneumonia and healthy cases. More advanced data preprocessing methods such as normalized, augmentation, and filtered noise has also been carried out which enhances in the model performance. We have high accuracy, recall, and good F1-score in the experimental results proving model robustness are applicable in real-world clinical scenarios. These research results speak to the importance of AI for improving diagnosis workflows, especially in fast-to-deploy large scale scenarios needed during a pandemic to cope with healthcare burdens.

Automatic retinal image analysis methods using colour fundus images for screening glaucomatous optic neuropathy

ObjectivesTrain an automatic retinal image analysis (ARIA) method to screen glaucomatous optic neuropathy (GON) on non-mydriatic retinal images labelled with the additional results of optical coherence tomography (OCT) and assess...

Tracheal Ultrasound for Diagnosis of Tracheal Cartilaginous Sleeve in Patients with Syndromic Craniosynostosis.

The aim of this study was to assess the utility of ultrasound (US) imaging for diagnosis of abnormal tracheal morphology, such as tracheal cartilaginous sleeves (TCS), in patients with syndromic craniosynostosis (SC). Age-matched cohort study. Tertiary pediatric hospital. Two age-matched cohorts were identified: patients with SC and known TCS based upon airway endoscopy and normal controls without tracheal pathology. Enrolled patients underwent awake US of the neck which were randomized and reviewed by blinded pediatric radiologists and rated on presence or absence of normal tracheal cartilage morphology and visualization or nonvisualization of a tracheostomy tube. Fisher's exact test was used to assess pooled data. Fleiss' Kappa (κ) was calculated to assess inter-rater reliability. Ten patients were included in each cohort. Control patients were gender and age-matched to TCS patients with a mean difference of 3.7 months (±3.9 months). Across all raters, cartilage type was correctly identified in 93% (95% confidence interval [CI]: 84%-98%) and tracheostomy visualization in 97% (95% CI: 89%-99%). The sensitivity and specificity for detection of abnormal cartilage pathology was 87% and 100%, respectively. Inter-rater reliability for cartilage assessment was κ = 0.88 (95% CI: 0.67-1.00, P < .05) and 0.83 (95% CI: 0.58-1.00, P < .05) for tracheostomy presence. This study demonstrated that tracheal US is a feasible, accurate screening tool for TCS, and can be successfully performed non-sedated in patients up to 18 years of age, both with and without tracheostomy tubes in place.

Drug evaluation platform based on non-destructive and real-time in situ organoid fate state monitoring by graphene field-effect transistor

3D organoid models have been widely used in drug evaluation because they effectively mimic physiological conditions and cell–cell interactions. However, current organoid-based drug evaluation heavily relies on invasive methods like qRT-PCR and immunofluorescence quantification, which disrupts the organoid’s structure and physiological function during the evaluation process. Therefore, it is urgent to develop a non-destructive drug evaluation platform to continuously monitor organoid fate. Here, a non-destructive and real-time in situ platform based on field effect transistor sensor (NDRS-FET) was developed to monitor organoid fate and obtained accurate drug evaluation by conducting the dynamic models. Using liver organoid as the model, the transition kinetics of liver organoid fate in response to candidate drug compounds were recorded by the NDRS-FET platform. OSM, FH1 and BG45 were successfully identified as effective regulators of liver organoid fate. Compared to traditional methods, the NDRS-FET platform could not only accurately capture the drug effect on organoid in real time, but also reduce the intergroup deviation among samples, providing more accurate and reliable tool for drug development and screening.

Measuring Social Frailty: A Scoping Review of Available Scales and Tools.

Social frailty is an emerging concept characterized by state of vulnerability due to the lack or absence of social resources that enable health and well-being, particularly among older people. However, there is no consensus on how to accurately measure and assess social frailty, given the broad coverage of social dimensions affecting older individuals. This scoping review aimed to identify the existing tools and scales used to measure social frailty in older people. A scoping review methodology was employed. Articles published between January 2014 and April 2024 were searched in 6 electronic databases: PubMed, PsycINFO, ProQuest, Scopus, SocIndex, and CINAHL. The scoping review followed a 5-stage process by Arksey and O'Malley and adhered to the guidelines provided by Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews. Nine social frailty tools were identified across the 58 papers included in this review. The individual question item commonly used in the scales were classified into main categories based on their conceptual characteristics and intentions. The most common individual questionnaire constructs used to measure social frailty included financial status, social resources, social behaviors and activities, and sense of purpose. The reviewed tools varied in terms of their robustness and the process of scale development. Our review suggested the development of a standardized, psychometrically tested, and accurate screening tool to screen social frailty status. An accurate social frailty assessment can inform the development of useful interventions, which also has implications in preventing the development of physical frailty.

Simultaneous targeting and monitoring of free antigen and in-situ membrane antigen in prostate cancer cells via an aggregation-induced emission-based bifunctional probe

The precise clinical diagnosis of prostate cancer still presents inherent challenges, and usually a monitoring of multiple biomarkers is required. In this study, a new aggregation-induced emission (AIE)-based bifunctional strategy was developed for the simultaneous detection of prostate cancer-specific in situ membrane antigens (PSMA) and free antigens (PSA). First, a bifunctional fluorescent probe with double sensing sites (a PSA-specific sensing site and a PSMA-targeted ligand) was constructed. In the presence of PSA, it specifically binds to the PSA-specific sensing site of the probe, resulting in the restoration of the fluorescence signal, enabling linear sensing of PSA. For the detection of PSMA, the PSMA-targeted ligand modified on the probe can specifically recognize PSMA, inducing the aggregation of the AIE material and resulting in an enhanced fluorescence signal. Moreover, a liposome-based artificial cell was developed to simulate the real prostate cancer cell, and it was used to investigate the feasibility of monitoring the two types of antigens. Utilizing this bifunctional fluorescent strategy, a dual-analysis of free serum antigen biomarker of PSA and in-situ membrane antigen of PSMA was achieved. The assay exhibited a wide linearity range for PSA detection from 0.0001 to 0.1 μg/mL, with a low limit of detection (LOD) of 6.18 pg/mL. For PSMA, the obtained LOD is 8.79 pg/mL, with a linearity range from 0.0001 to 0.1 μg/mL. This strategy allows us to simultaneously assess the levels of two types of biomarkers in living human prostatic cancer cells, providing a highly accurate and selective tool for early screening and monitoring of prostatic cancer.

An ML-based decision support system for reliable diagnosis of ovarian cancer by leveraging explainable AI

Ovarian cancer (OC) is one of the most prevalent types of cancer in women. Early and accurate diagnosis is crucial for the survival of the patients. However, the majority of women are diagnosed in advanced stages due to the lack of effective biomarkers and accurate screening tools. While previous studies sought a common biomarker, our study suggests different biomarkers for the premenopausal and postmenopausal populations. This can provide a new perspective in the search for novel predictors for the effective diagnosis of OC. Genetic algorithm has been utilized to identify the most significant biomarkers. The XGBoost classifier is then trained on the selected features and high ROC-AUC scores of 0.864 and 0.911 have been obtained for the premenopausal and postmenopausal populations, respectively. Lack of explainability is one major limitation of current AI systems. The stochastic nature of the ML algorithms raises concerns about the reliability of the system as it is difficult to interpret the reasons behind the decisions. To increase the trustworthiness and accountability of the diagnostic system as well as to provide transparency and explanations behind the predictions, explainable AI has been incorporated into the ML framework. SHAP is employed to quantify the contributions of the selected biomarkers and determine the most discriminative features. Merging SHAP with the ML models enables clinicians to investigate individual decisions made by the model and gain insights into the factors leading to that prediction. Thus, a hybrid decision support system has been established that can eliminate the bottlenecks caused by the black-box nature of the ML algorithms providing a safe and trustworthy AI tool. The diagnostic accuracy obtained from the proposed system outperforms the existing methods as well as the state-of-the-art ROMA algorithm by a substantial margin which signifies its potential to be an effective tool in the differential diagnosis of OC.

Docking Score ML: Target-Specific Machine Learning Models Improving Docking-Based Virtual Screening in 155 Targets.

In drug discovery, molecular docking methods face challenges in accurately predicting energy. Scoring functions used in molecular docking often fail to simulate complex protein-ligand interactions fully and accurately leading to biases and inaccuracies in virtual screening and target predictions. We introduce the "Docking Score ML", developed from an analysis of over 200,000 docked complexes from 155 known targets for cancer treatments. The scoring functions used are founded on bioactivity data sourced from ChEMBL and have been fine-tuned using both supervised machine learning and deep learning techniques. We validated our approach extensively using multiple data sets such as validation of selectivity mechanism, the DUDE, DUD-AD, and LIT-PCBA data sets, and performed a multitarget analysis on drugs like sunitinib. To enhance prediction accuracy, feature fusion techniques were explored. By merging the capabilities of the Graph Convolutional Network (GCN) with multiple docking functions, our results indicated a clear superiority of our methodologies over conventional approaches. These advantages demonstrate that Docking Score ML is an efficient and accurate tool for virtual screening and reverse docking.

Optimizing ankle-brachial index measurement for peripheral arterial disease screening in mobile clinics

ObjectiveMultidisciplinary mobile clinics (MMCs) provide a robust venue to provide health care access and peripheral arterial disease (PAD) screening to underserved populations. The ankle-brachial index (ABI) can facilitate PAD diagnosis; however, traditional supine ABI measurements may be challenging technically in a mobile outreach clinic with limited infrastructure, whereas seated ABI offers technical ease. In this study, the usefulness and feasibility of performing supine ABI, seated ABI, and seated ABI with a calculation to account for seated hydrostatic pressure (seated-adjusted ABI) were compared in a mobile outreach setting. MethodsProspective data were collected from patients at five independent MMCs focused on diabetic foot and PAD screening with ABI for underserved communities. Three techniques were used to measure the ABI: seated ABI, seated-adjusted ABI using a formula to account for hydrostatic ankle pressure, and traditional supine ABI using a foldable massage table that is 5% of the cost of a medical stretcher. Comparative analysis was performed using the Student t test analysis and one-way analysis of variance. The frequency of completed seated ABI, seated-adjusted ABI, and supine ABI examinations performed at independent MMCs was quantified to determine feasibility. ResultsIn 166 individuals experiencing homelessness or housing instability who were screened over the course of five MMCs, 89 underwent PAD screening with ABI. Of the patients screened, 38 patients had seated, seated-adjusted, and supine ABIs measured (43% of total number of patients undergoing any ABI measurement). PAD (ABI < 0.9) was identified in one patient using all three ABI methods. Noncompressible ABI (ABI ≥ 1.3) were identified in 32 patients (32/38 [84%]) screened with seated ABI. Of these 32 patients, 24 (75%) continued to have noncompressible ABIs using seated-adjusted ABI. Of these 24 patients, 4 (17%) continued to have noncompressible ABI using supine ABI. The average seated ABI significantly differed from supine ABI (1.34 vs 1.14; P < .0001). The average seated ABI also significantly differed from seated-adjusted ABI (1.34 vs 1.29; P = .026). The average seated-adjusted ABI significantly differed from supine ABI (1.29 vs 1.14; P = .0204). ConclusionsWe found that seated and seated-adjusted ABI are grossly inaccurate and more often lead to falsely elevated noncompressible ABI (32/38 [84%] and 24/38 [75%], respectively) compared with supine ABI (6/38 [16%]). We recommend using supine ABI on patients for PAD screening. Supine measurement is technically feasible in outreach mobile clinics using a transportable folding massage table and is a more accurate tool for PAD screening.

Dumbbell Dual-Hairpin Triggered DNA Nanonet Assembly for Cascade-Amplified Sensing of Exosomal MicroRNA.

Exosomal microRNAs (miRNAs) are valuable biomarkers closely associated with cancer progression. Therefore, sensitive and specific exosomal miRNA biosensing has been employed for cancer diagnosis, prognosis, and prediction. In this study, a miRNA-based DNA nanonet assembly strategy is proposed, enabling the biosensing of exosomal miRNAs through dumbbell dual-hairpin under isothermal enzyme-free conditions. This strategy dexterously designs a specific dumbbell dual-hairpin that can selectively recognize exosomal miRNA, inducing conformational changes to cascade-generated X-shaped DNA structures, facilitating the extension of the X-shaped DNA in three-dimensional space, ultimately forming a DNA nanonet assembly. On the basis of the target miRNA, our design enriches the fluorescence signal through the cascade assembly of DNA nanonet and realizes the secondary signal amplification. Using exosomal miR-141 as the target, the resultant fluorescence sensing demonstrates an impressive detection limit of 57.6 pM and could identify miRNA sequences with single-base variants with high specificity. Through the analysis of plasma and urine samples, this method effectively distinguishes between benign prostatic hyperplasia, prostate cancer, and metastatic prostate cancer. Serving as a novel noninvasive and accurate screening and diagnostic tool for prostate cancer, this dumbbell dual-hairpin triggered DNA nanonet assembly strategy is promising for clinical applications.

Modification of the Revised National Institute for Occupational Safety and Health (NIOSH) Lifting Equation to Determine the Individual Manual Lifting Risk in Malaysia's Manufacturing Industry.

The National Institute for Occupational Safety and Health (NIOSH) established the Revised NIOSH Lifting Equation (RNLE) for manual lifting risk assessment. The objectives of this study were to determine the characteristics of physical factors using the RNLE and to explore additional factors to RNLE by modifying it to an Individual Lifting Equation (ILE). This cross-sectional study was conducted in the manufacturing industry of three states in Malaysia among manual lifting workers. A questionnaire was administered, which comprised the sociodemographic characteristics and Nordic Musculoskeletal Questionnaire (NMQ) assessing low back pain (LBP). The RNLE dataset includes a load constant and six manual lifting variables collected from observational ergonomic risk assessment. The RNLE was modified to ILE by incorporating age, gender, and BMI. The equations' Lifting Index (LI) computed provides an overall manual lifting risk estimate. There were 165 participants, with a mean age of 28 years, and 108 (65.5%) were male. Most participants had a BMI within the normal range (60 (36.4%)) or were classified as overweight (54 (32.7%)). The lifting horizontal location showed the highest risk estimates, with the lowest meanmultiplier value of 0.55. In contrast, age and BMI had the lowest risk estimates, with mean multiplier values of 0.99 and 0.98, respectively. Among the participants, LI values of one or less, indicating very low risk, were observed in 58 (35.1%) for RNLE and 39 (23.6%) for ILE. Additionally, RNLE and ILE showed figures of 11 (6.7%) and 20 (12.1%), respectively, signifying a very high risk of LI exceeding three. Studying the lifting factors and equation multipliers from RNLE is critical for evaluating the risk estimates of manual lifting. Exploring the ILE based on individual characteristics is appropriate to support the ergonomic program. Further study is needed to validate the ILE as an accurate screening tool for determining LBP risk estimates.

Classification of Childhood Obstructive Sleep Apnea based on X-ray images analysis by Quasi-conformal Geometry

Craniofacial profile is one of the anatomical causes of obstructive sleep apnea (OSA). By medical research, cephalometry provides information on patients’ skeletal structures and soft tissues. In this work, a novel approach to cephalometric analysis using quasi-conformal geometry based local deformation information was proposed for OSA classification. Our study was a retrospective analysis based on 60 case-control pairs with accessible lateral cephalometry and polysomnography (PSG) data (mean age: 8.9 ± 2.3 years). By using the quasi-conformal geometry to study the local deformation around 15 landmark points, and combining the results with three linear distances between landmark points, a total of 1218 information features were obtained per subject. A L2 norm based classification model was built. Under experiments, our proposed model achieves high testing accuracy. The accurate classification tool provides us with a reliable and accurate screening tool for childhood OSA.

Daratumumab Treatment for "Truly Frail" Elderly Myeloma Patients.

Remarkable advancements have been made in the treatment outcomes of multiple myeloma (MM) patients; however, for frail elderly patients, these treatment outcomes are still insufficient. Elderly MM patients are increasing, as are their treatment regimens. There is a heightened demand to assess these patients in order to provide optimized treatments. While continuous treatment is more common for MM patients when compared to fixed-duration treatment, due to the risk of treatment interruption causing reduced survival rates, effectiveness and safety are essential. Treatment goals vary for each patient, but must preserve their quality of life (QOL). When planning treatments for these patients, frailty evaluation is increasingly emphasized as a stratification factor which helps develop accurate screening tools. Daratumumab (DARA) therapy, used globally, is not only effective in frail elderly MM patients, but also has QOL benefits. Proficiency in utilizing DARA regimens is potentially advantageous for patients not included in clinical trials, and innovative usage can further broaden its scope. The development of tools to accurately assess frailty and the establishment of optimal treatments for frail elderly MM patients are imperative. This review is an overview, challenging the frailty assessments for MM patients, re-examining the evidence for DARA regimens in frail elderly MM patients, and discussing potential areas for improvement.

EsophaCap Sponge Cytology Screening for Esophageal Squamous Cell Dysplasia and Carcinoma is Feasible in a High-Risk Area in Western India

Objective: Conventional endoscopy remains the gold standard for detecting esophageal squamous cell carcinoma (ESCC) despite its high cost and need for expertise. In resource-poor regions, a less labor-intensive yet accurate screening tool is needed. The purpose of this study is to assess feasibility of establishing a non-endoscopic screening program in rural India and to test the diagnostic accuracy of the EsophaCap swallowable sponge in detecting ESCC in a high-risk patient population. Methods: A prospective cohort study was conducted between 2017 and 2019, in which subjects with risk factors for ESCC (tobacco smoking or chewing, betel nut/leaf, alcohol and hot beverage consumption) were approached during upper endoscopy visits at a clinic in Western India. After obtaining EsophaCap sponge cytology samples, random endoscopic biopsies were obtained at 20 and 30 cm from the incisors. Histologic diagnoses were confirmed and select biopsy samples were sequenced for genomic aberrations. Visual Analog Scale (VAS) scores were used to assess patient experience of sponge swallowing (range 1-5, “very comfortable” to “very uncomfortable”). Results: In our cohort of 178 patients, 157 (88%) were males. Mean age was 52 ± 12 years. Sixty-eight (38%) patients were current cigarette or bidi smokers; 132 (74%) patients were daily tobacco chewers, and 83 (47%) patients chewed betel nuts/leaves on a daily basis. Forty-six (26%) patients were daily alcohol users and 151 (85%) patients drank ≥3 hot beverages per day. The median number of risk factors per patient was 3. The first-time swallow rate of the encapsulated sponge was successful in 190/200 (95%) patients. Median VAS score was 2 (“comfortable”). EsophaCap cytology revealed 6 (3%) patients with atypical squamous cells of unknown significance (ASCUS) and 3 (1%) patients with dysplasia. Based on the endoscopic biopsies, 6 (3%) patients had ESCC, 4 (2%) patients had lesions with squamous dysplasia, and 63 (35%) patients had esophageal leukoplakia. Four patients classified as ASCUS pathology via EsophaCap were normal, benign, or leukoplakia via endoscopy. EsophaCap’s sensitivity and specificity for detecting dysplasia or ESCC by histology was 30% and 97%, respectively. Conclusions: Establishing a non-endoscopic screening program in a high-risk area with language barriers and low medical literacy is very safe and feasible. EsophaCap may help identify ASCUS patients in need of serial endoscopic monitoring. Further studies of combined sponge cytology with immunohistochemistry studies are necessary to improve accuracy of ESCC screening.

Perinatal anxiety disorders screening study: a study protocol

BackgroundThe anxiety and their related disorders (AD) are the most common of all mental health conditions, and affect approximately 20% of pregnant and postpartum people. They are associated with significant distress and life interference for sufferers, as well as negative consequences for fetal and infant development. At present, little if any routine screening for prenatal AD is being conducted and data regarding the most effective tools to screen for these disorders is lacking. The majority of screening studies suffer from methodological difficulties which undermine the confidence needed to recommend measures for population distribution. The primary purpose of this research is to identify the most accurate self-report tool(s) to screen for perinatal AD.MethodsA large, prospective cohort of pregnant people (N = 1,000) is being recruited proportionally across health service delivery regions in British Columbia (BC). The screening accuracy of a broad range of perinatal AD self-report measures are being assessed using gold standard methodology. Consenting individuals are administered online questionnaires followed by a semi-structured diagnostic interview between 16- and 36-weeks’ gestation, and again between 6 and 20 weeks postpartum. Questionnaires include all screening measures, measures of sleep and unpaid family work, and questions pertaining to demographic and reproductive history, COVID-19, gender role burden, and mental health treatment utilization. Interviews assess all current anxiety disorders, as well as obsessive–compulsive disorder, and posttraumatic stress disorder.DiscussionThis research is in response to an urgent demand for accurate perinatal AD screening tools based on high quality evidence. AD among perinatal people often go unidentified and untreated, resulting in continued suffering and life impairment. Findings from this research will inform healthcare providers, policymakers, and scientists, about the most effective approach to screening for anxiety and related disorders in pregnancy in the postpartum period.

Translating color fundus photography to indocyanine green angiography using deep-learning for age-related macular degeneration screening

Age-related macular degeneration (AMD) is the leading cause of central vision impairment among the elderly. Effective and accurate AMD screening tools are urgently needed. Indocyanine green angiography (ICGA) is a well-established technique for detecting chorioretinal diseases, but its invasive nature and potential risks impede its routine clinical application. Here, we innovatively developed a deep-learning model capable of generating realistic ICGA images from color fundus photography (CF) using generative adversarial networks (GANs) and evaluated its performance in AMD classification. The model was developed with 99,002 CF-ICGA pairs from a tertiary center. The quality of the generated ICGA images underwent objective evaluation using mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity measures (SSIM), etc., and subjective evaluation by two experienced ophthalmologists. The model generated realistic early, mid and late-phase ICGA images, with SSIM spanned from 0.57 to 0.65. The subjective quality scores ranged from 1.46 to 2.74 on the five-point scale (1 refers to the real ICGA image quality, Kappa 0.79–0.84). Moreover, we assessed the application of translated ICGA images in AMD screening on an external dataset (n = 13887) by calculating area under the ROC curve (AUC) in classifying AMD. Combining generated ICGA with real CF images improved the accuracy of AMD classification with AUC increased from 0.93 to 0.97 (P < 0.001). These results suggested that CF-to-ICGA translation can serve as a cross-modal data augmentation method to address the data hunger often encountered in deep-learning research, and as a promising add-on for population-based AMD screening. Real-world validation is warranted before clinical usage.

A longitudinal study to determine if all critically ill patients should be considered at nutrition risk or is there a highly accurate screening tool to be adopted?

Nutrition risk is prevalent in intensive care unit (ICU) settings and related to poor prognoses. We aimed to evaluate the concurrent and predictive validity of different nutrition risk screening tools in the ICU. Data were collected between 2019 and 2022 in six ICUs (n = 450). Nutrition risk was evaluated by modified Nutrition Risk in Critically ill (mNUTRIC), Nutritional Risk Screening (NRS-2002), Malnutrition Screening Tool (MST), Malnutrition Universal Screening Tool (MUST), and Nutritional Risk in Emergency (NRE-2017). Accuracy and agreement of the tools were assessed; logistic regression was used to verify the association between nutrition risk and prolonged ICU stay; Cox regression was used for mortality in the ICU, both with adjustment for confounders. NRS-2002 ≥5 showed the best accuracy (0.63 [95% CI, 0.58-0.69]) with mNUTRIC, and MST with NRS-2002 ≥5 (0.76 [95% CI, 0.71-0.80]). All tools had a poor/fair agreement with mNUTRIC (k = 0.019-0.268) and moderate agreement with NRS-2002 ≥5 (k = 0.474-0.503). MUST (2.26 [95% CI 1.40-3.63]) and MST (1.69 [95% CI, 1.09-2.60]) predicted death in the ICU, and the NRS-2002 ≥5 (1.56 [95% CI 1.02-2.40]) and mNUTRIC (1.86 [95% CI, 1.26-2.76]) predicted prolonged ICU stay. No nutrition risk screening tool demonstrated a satisfactory concurrent validity; only the MUST and MST predicted ICU mortality and the NRS-2002 ≥5 and mNUTRIC predicted prolonged ICU stay, suggesting that it could be appropriate to adopt the ESPEN recommendation to assess nutrition status in patients with ≥48 h in the ICU.