Plasmon-Enhanced Digital Fluoroimmunoassay for Subfemtomolar Detection of Protein Biomarkers.

Rapid and accurate quantification of low-abundance protein biomarkers in biofluids can transform the diagnosis of a range of pathologies, including infectious diseases. Here, we harness ultrabright plasmonic fluors as "digital nanolabels" and demonstrate the detection and quantification of subfemtomolar concentrations of human IL-6 and SARS-CoV-2 alpha and variant proteins in clinical nasopharyngeal swab and saliva samples from COVID-19 patients. The resulting digital plasmonic fluor-linked immunosorbent assay (digital p-FLISA) enables detection of SARS-CoV-2 nucleocapsid protein, both in solution and in live virions. Digital p-FLISA outperforms the "gold standard" enzyme-linked immunosorbent assay (ELISA), having a nearly 7000-fold lower limit-of-detection, and outperforms a commercial antigen test, having over 5000-fold improvement in analytical sensitivity. Detection and quantification of very low concentrations of target proteins holds potential for early detection of pathological conditions, treatment monitoring, and personalized medicine.

Impact of Clinician Training Background and Stroke Location on Bedside Diagnostic Test Accuracy in the Acute Vestibular Syndrome - A Meta-Analysis.

OBJECTIVE: Acute dizziness/vertigo is usually due to benign inner-ear causes but is occasionally due to dangerous neurologic ones, particularly stroke. Because symptoms and signs overlap, misdiagnosis is frequent and overuse of neuroimaging is common. We assessed the accuracy of bedside findings to differentiate peripheral vestibular from central neurologic causes. METHODS: We performed a systematic search (MEDLINE and Embase) to identify studies reporting on diagnostic accuracy of physical examination in adults with acute, prolonged dizziness/vertigo ("acute vestibular syndrome" [AVS]). Diagnostic test properties were calculated for findings. Results were stratified by examiner type and stroke location. RESULTS: We identified 6,089 citations and included 14 articles representing 10 study cohorts (n = 800). The Head Impulse, Nystagmus, Test of Skew (HINTS) eye movement battery had high sensitivity 95.3% (95% confidence interval [CI] = 92.5-98.1) and specificity 92.6% (95% CI = 88.6-96.5). Sensitivity was similar by examiner type (subspecialists 94.3% [95% CI = 88.2-100.0] vs non-subspecialists 95.0% [95% CI = 91.2-98.9], p = 0.55), but specificity was higher among subspecialists (97.6% [95% CI = 94.9-100.0] vs 89.1% [95% CI = 83.0-95.2], p = 0.007). HINTS sensitivity was lower in anterior cerebellar artery (AICA) than posterior inferior cerebellar artery (PICA) strokes (84.0% [95% CI = 65.3-93.6] vs 97.7% [95% CI = 93.3-99.2], p = 0.014) but was "rescued" by the addition of bedside hearing tests (HINTS+). Severe (grade 3) gait/truncal instability had high specificity 99.2% (95% CI = 97.8-100.0) but low sensitivity 35.8% (95% CI = 5.2-66.5). Early magnetic resonance imaging (MRI)-diffusion-weighted imaging (DWI; within 24-48 hours) was falsely negative in 15% of strokes (sensitivity 85.1% [95% CI = 79.2-91.0]). INTERPRETATION: In AVS, HINTS examination by appropriately trained clinicians can differentiate peripheral from central causes and has higher diagnostic accuracy for stroke than MRI-DWI in the first 24-48 hours. These techniques should be disseminated to all clinicians evaluating dizziness/vertigo. ANN NEUROL 2023;94:295-308.

Systematic Review and Meta-Analysis of the Diagnostic Accuracy of a Graded Gait and Truncal Instability Rating in Acutely Dizzy and Ataxic Patients.

BACKGROUND: In patients presenting with acute prolonged vertigo and/or gait imbalance, the HINTS [Head-Impulse, Nystagmus, Test-of-Skew] are very valuable. However, their application may be limited by lack of training and absence of vertigo/nystagmus. Alternatively, a graded gait/truncal-instability (GTI, grade 0-3) rating may be applied. METHODS: We performed a systematic search (MEDLINE/Embase) to identify studies reporting on the diagnostic accuracy of bedside examinations in adults with acute vestibular syndrome. Diagnostic test properties were calculated for findings using a random-effects model. Results were stratified by GTI-rating used. RESULTS: We identified 6515 articles and included 18 studies (n = 1025 patients). Ischemic strokes (n = 665) and acute unilateral vestibulopathy (n = 306) were most frequent. Grade 2/3 GTI had moderate sensitivity (70.8% [95% confidence-interval (CI) = 59.3-82.3%]) and specificity (82.7 [71.6-93.8%]) for predicting a central cause, whereas grade 3 GTI had a lower sensitivity (44.0% [34.3-53.7%] and higher specificity (99.1% [98.0-100.0%]). In comparison, diagnostic accuracy of HINTS (sensitivity = 96.8% [94.8-98.8%]; specificity = 97.6% [95.3-99.9%]) was higher. When combining central nystagmus-patterns and grade 2/3 GTI, sensitivity was increased to 76.4% [71.3-81.6%] and specificity to 90.3% [84.3-96.3%], however, no random effects model could be used. Sensitivity was higher in studies using the GTI rating (grade 2/3) by Lee (2006) compared to the approach by Moon (2009) (73.8% [69.0-78.0%] vs. 57.4% [49.5-64.9%], p = 0.001). CONCLUSIONS: In comparison to HINTS, the diagnostic accuracy of GTI is inferior. When combined with central nystagmus-patterns, diagnostic accuracy could be improved based on preliminary findings. GTI can be readily applied in the ED-setting and also in patients with acute imbalance syndrome.

Microneedle patch-based enzyme-linked immunosorbent assay to quantify protein biomarkers of tuberculosis.

There is a clinical need for differential diagnosis of the latent versus active stages of tuberculosis (TB) disease by a simple-to-administer test. Alpha-crystallin (Acr) and early secretory antigenic target-6 (ESAT-6) are protein biomarkers associated with the latent and active stages of TB, respectively, and could be used for differential diagnosis. We therefore developed a microneedle patch (MNP) designed for application to the skin to quantify Acr and ESAT-6 in dermal interstitial fluid by enzyme-linked immunosorbent assay (ELISA). We fabricated mechanically strong microneedles made of polystyrene and coated them with capture antibodies against Acr and ESAT-6. We then optimized assay sensitivity to achieve a limit of detection of 750 pg/ml and 3,020 pg/ml for Acr and ESAT-6, respectively. This study demonstrates the feasibility of an MNP-based ELISA for differential diagnosis of latent TB disease.

Aptamer-based fluorescent sensor for highly sensitive detection of methamphetamine.

The construction of a fluorescence aptamer sensor was achieved by employing the fundamental principle of fluorescence resonance energy transfer. By employing molecular modeling technologies to identify the binding site, the high-affinity aptamer APT-40nt was derived from the whole sequence and utilized on the graphene oxide (GO) fluorescent platform for the purpose of achieving a highly sensitive detection of methamphetamine (METH). The aptamer tagged with fluorescein (FAM) dye undergoes quenching in the presence of GO due to π-stacking interaction. With the addition of the target, the aptamer that has been tagged was detached from the GO surface, forming a stable complex with METH. This process resulted in fluorescence restoration of the system, and the degree of fluorescence restoration was proportional to METH concentration in the linear range of 1-50 and 50-200 nM. Notably, under optimized conditions, the detection limit of this aptasensor was as low as 0.78 nM, which meets the detection limit requirements of METH detection in saliva and urine in some countries and regions. Moreover, other common illicit drugs and metabolites had minimizing interference with the determination. The established aptasensor, therefore, has been successfully applied to detect METH in saliva and urine samples and exhibited satisfactory recoveries (87%-111%). This aptasensor has the advantages of low detection limit, excellent selectivity, ease of operation, and low cost, providing a promising strategy for on-site detection of METH in saliva and urine.

Nodeless Superconductivity in Kagome Metal CsV3Sb5 with and without Time Reversal Symmetry Breaking.

The kagome metal CsV3Sb5 features an unusual competition between the charge-density-wave (CDW) order and superconductivity. Evidence for time reversal symmetry breaking (TRSB) inside the CDW phase has been accumulating. Hence, the superconductivity in CsV3Sb5 emerges from a TRSB normal state, potentially resulting in an exotic superconducting state. To reveal the pairing symmetry, we first investigate the effect of nonmagnetic impurity. Our results show that the superconducting critical temperature is insensitive to disorder, pointing to conventional s-wave superconductivity. Moreover, our measurements of the self-field critical current (Ic,sf), which is related to the London penetration depth, also confirm conventional s-wave superconductivity with strong coupling. Finally, we measure Ic,sf where the CDW order is removed by pressure and superconductivity emerges from the pristine normal state. Our results show that s-wave gap symmetry is retained, providing strong evidence for the presence of conventional s-wave superconductivity in CsV3Sb5 irrespective of the presence of the TRSB.

Investigating the association between serum ADAM/ADAMTS levels and bone mineral density by mendelian randomization study.

PURPOSE: A Disintegrin and Metalloproteinase (ADAM) and A Disintegrin and Metalloproteinase with Thrombospondin Motif (ADAMTS) have been reported potentially involved in bone metabolism and related to bone mineral density. This Mendelian Randomization (MR) analysis was performed to determine whether there are causal associations of serum ADAM/ADAMTS with BMD in rid of confounders. METHODS: The genome-wide summary statistics of four site-specific BMD measurements were obtained from studies in individuals of European ancestry, including forearm (n = 8,143), femoral neck (n = 32,735), lumbar spine (n = 28,498) and heel (n = 426,824). The genetic instrumental variables for circulating levels of ADAM12, ADAM19, ADAM23, ADAMTS5 and ADAMTS6 were retrieved from the latest genome-wide association study of European ancestry (n = 5336 ~ 5367). The estimated causal effect was given by the Wald ratio for each variant, the inverse-variance weighted model was used as the primary approach to combine estimates from multiple instruments, and sensitivity analyses were conducted to assess the robustness of MR results. The Bonferroni-corrected significance was set at P < 0.0025 to account for multiple testing, and a lenient threshold P < 0.05 was considered to suggest a causal relationship. RESULTS: The causal effects of genetically predicted serum ADAM/ADAMTS levels on BMD measurements at forearm, femoral neck and lumbar spine were not statistically supported by MR analyses. Although causal effect of ADAMTS5 on heel BMD given by the primary MR analysis (ß = -0.006, -0.010 to 0.002, P = 0.004) failed to reach Bonferroni-corrected significance, additional MR approaches and sensitivity analyses indicated a robust causal relationship. CONCLUSION: Our study provided suggestive evidence for the causal effect of higher serum levels of ADAMTS5 on decreased heel BMD, while there was no supportive evidence for the associations of ADAM12, ADAM19, ADAM23, and ADAMTS6 with BMD at forearm, femoral neck and lumbar spine in Europeans.

Misdiagnosis-related harm quantification through mixture models and harm measures.

Investigating and monitoring misdiagnosis-related harm is crucial for improving health care. However, this effort has traditionally focused on the chart review process, which is labor intensive, potentially unstable, and does not scale well. To monitor medical institutes' diagnostic performance and identify areas for improvement in a timely fashion, researchers proposed to leverage the relationship between symptoms and diseases based on electronic health records or claim data. Specifically, the elevated disease risk following a false-negative diagnosis can be used to signal potential harm. However, off-the-shelf statistical methods do not fully accommodate the data structure of a well-hypothesized risk pattern and thus fail to address the unique challenges adequately. To fill these gaps, we proposed a mixture regression model and its associated goodness-of-fit testing. We further proposed harm measures and profiling analysis procedures to quantify, evaluate, and compare misdiagnosis-related harm across institutes with potentially different patient population compositions. We studied the performance of the proposed methods through simulation studies. We then illustrated the methods through data analyses on stroke occurrence data from the Taiwan Longitudinal Health Insurance Database. From the analyses, we quantitatively evaluated risk factors for being harmed due to misdiagnosis, which unveiled some insights for health care quality research. We also compared general and special care hospitals in Taiwan and observed better diagnostic performance in special care hospitals using various new evaluation measures.

MAE-Based Self-Supervised Pretraining Algorithm for Heart Rate Estimation of Radar Signals.

Noncontact heart rate monitoring techniques based on millimeter-wave radar have advantages in unique medical scenarios. However, the accuracy of the existing noncontact heart rate estimation methods is still limited by interference, such as DC offsets, respiratory harmonics, and environmental noise. Additionally, these methods still require longer observation times. Most deep learning methods related to heart rate estimation still need to collect more heart rate marker data for training. To address the above problems, this paper introduces a radar signal-based heart rate estimation network named the "masked phase autoencoders with a vision transformer network" (MVN). This network is grounded on masked autoencoders (MAEs) for self-supervised pretraining and a vision transformer (ViT) for transfer learning. During the phase preprocessing stage, phase differencing and interpolation smoothing are performed on the input phase signal. In the self-supervised pretraining step, masked self-supervised training is performed on the phase signal using the MAE network. In the transfer learning stage, the encoder segment of the MAE network is integrated with the ViT network to enable transfer learning using labeled heart rate data. The innovative MVN offers a dual advantage-it not only reduces the cost associated with heart rate data acquisition but also adeptly addresses the issue of respiratory harmonic interference, which is an improvement over conventional signal processing methods. The experimental results show that the process in this paper improves the accuracy of heart rate estimation while reducing the requisite observation time.

Plasmonically Enhanced Ultrasensitive Epitope-Specific Serologic Assay for COVID-19.

Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has rapidly spread and resulted in the global pandemic of COVID-19. Although IgM/IgG serology assay has been widely used, with the entire spike or nucleocapsid antigens, they only indicate the presence or absence of antibodies against these proteins but are not specific to the neutralization antibodies, therefore providing only generic information about infection stage and possible future immune protection. Novel technologies enabling easy-to-use and sensitive detection of multiple specific antibodies simultaneously will facilitate precise diagnosis of infection stage, prediction of clinical outcomes, and evaluation of future immune protection upon viral exposure or vaccination. Here, we demonstrate a rapid and ultrasensitive quantification method for epitope-specific antibodies, including different isotypes and subclasses, in a multiplexed manner. Using an ultrabright fluorescent nanolabel, plasmonic-fluor, this novel assay can be completed in 20 min and more importantly, the limit of detection of the plasmon-enhanced immunoassay for SARS-CoV-2 antibodies is as much as 100-fold lower compared to the assays relying on enzymatic amplification of colorimetric signals. Using convalescent patient plasma, we demonstrate that this biodetection method reveals the patient-to-patient variability in immune response as evidenced by the variations in whole protein and epitope-specific antibodies. This cost-effective, rapid, and ultrasensitive plasmonically enhanced multiplexed epitope-specific serological assay has the potential to be broadly employed in the detection of specific antibodies, which may benefit the advanced epidemiology studies and enable improvement of the clinical outcomes and prediction of the future protection against the SARS-CoV-2.

Kinetic modeling: A tool for temperature shift and feeding optimization in cell culture process development.

Mammalian cells have dominated the biopharmaceutical industry for biotherapeutic protein production and tremendous efforts have been devoted to enhancing productivity during the cell culture process development. However, determining the optimal process conditions is still a huge challenge. Constrained by the limited resources and timeline, usually it is impossible to fully explore the optimal range of all process parameters (temperature, pH, dissolved oxygen, basal and feeding medium, additives, etc.). Kinetic modeling, which finds out the global optimum by systematically screening all potential conditions for cell culture process, provides a solution to this dilemma. However, studies on optimizing temperature shift and feeding strategies simultaneously using this approach have not been reported. In this study, we built up a kinetic model of fed-batch culture process for simultaneous optimization of temperature shift and feeding strategies. The fitting results showed high accuracy and demonstrated that the kinetic model can be used to describe the mammalian cell culture performance. In addition, five more fed-batch experiments were conducted to test this model's predicting power on different temperature shift and feeding strategies. It turned out that the predicted data matched well with experimental ones on viable cell density (VCD), metabolites, and titer for the entire culture duration and allowed selecting the same best condition with the experimental results. Therefore, adopting this approach can potentially reduce the number of experiments required for culture process optimization.

Are Mental Health and Substance Use Disorders Risk Factors for Missed Acute Myocardial Infarction Diagnoses Among Chest Pain or Dyspnea Encounters in the Emergency Department?

STUDY OBJECTIVE: To assess if having a mental health and/or substance use disorder is associated with a missed acute myocardial infarction diagnosis in the emergency department (ED). METHODS: This was a retrospective cohort analysis (2009 to 2017) of adult ED encounters at Kaiser Permanente Southern California. We used the validated symptom-disease pair analysis of diagnostic error methodological approach to "look back" and "look forward" and identify missed acute myocardial infarctions within 30 days of a treat-and-release ED visit. We use adjusted logistic regression to report the odds of missed acute myocardial infarction among patients with a history of mental health and/or substance use disorders. RESULTS: The look-back analysis identified 44,473 acute myocardial infarction hospital encounters; 574 (1.3%) diagnoses were missed. The odds of missed diagnoses were higher in patients with mental health disorders (odds ratio [OR] 1.48, 95% confidence interval [CI] 1.23 to 1.77) but not in those with substance abuse disorders (OR 1.22, 95% CI 0.91 to 1.62). The highest risk was observed in those with co-occurring disorders (OR 1.90, 95% CI 1.30 to 2.76). The look-forward analysis identified 325,088 chest pain/dyspnea ED encounters; 508 (0.2%) were missed acute myocardial infarctions. No significant associations of missed acute myocardial infarction were revealed in either group (mental health disorder: OR 0.92, 95% CI 0.71 to 1.18; substance use disorder: OR 1.22, 95% CI 0.80 to 1.85). CONCLUSION: The look-back analysis identified patients with mental illness at increased risk of missed acute myocardial infarction diagnosis, with the highest risk observed in those with a history of comorbid substance abuse. Having substance use disorders alone did not increase this risk in either cohort. The look-forward analysis revealed challenges in prospectively identifying high-risk patients to target for improvement.

Ultrabright plasmonic fluor nanolabel-enabled detection of a urinary ER stress biomarker in autosomal dominant tubulointerstitial kidney disease.

Autosomal dominant tubulointerstitial kidney disease (ADTKD)-uromodulin (UMOD) is the most common nonpolycystic genetic kidney disease, but it remains unrecognized due to its clinical heterogeneity and lack of screening test. Moreover, the fact that the clinical feature is a poor predictor of disease outcome further highlights the need for the development of mechanistic biomarkers in ADTKD. However, low abundant urinary proteins secreted by thick ascending limb cells, where UMOD is synthesized, have posed a challenge for the detection of biomarkers in ADTKD-UMOD. In the CRISPR/Cas9-generated murine model and patients with ADTKD-UMOD, we found that immunoglobulin heavy chain-binding protein (BiP), an endoplasmic reticulum chaperone, was exclusively upregulated by mutant UMOD in the thick ascending limb and easily detected by Western blot analysis in the urine at an early stage of disease. However, even the most sensitive ELISA failed to detect urinary BiP in affected individuals. We therefore developed an ultrasensitive, plasmon-enhanced fluorescence-linked immunosorbent assay (p-FLISA) to quantify urinary BiP concentration by harnessing the newly invented ultrabright fluorescent nanoconstruct, termed "plasmonic Fluor." p-FLISA demonstrated that urinary BiP excretion was significantly elevated in patients with ADTKD-UMOD compared with unaffected controls, which may have potential utility in risk stratification, disease activity monitoring, disease progression prediction, and guidance of endoplasmic reticulum-targeted therapies in ADTKD.NEW & NOTEWORTHY Autosomal dominant tubulointerstitial kidney disease (ADTKD)-uromodulin (UMOD) is an underdiagnosed cause of chronic kidney disease (CKD). Lack of ultrasensitive bioanalytical tools has hindered the discovery of low abundant urinary biomarkers in ADTKD. Here, we developed an ultrasensitive plasmon-enhanced fluorescence-linked immunosorbent assay (p-FLISA). p-FLISA demonstrated that secreted immunoglobulin heavy chain-binding protein is an early urinary endoplasmic reticulum stress biomarker in ADTKD-UMOD, which will be valuable in monitoring disease progression and the treatment response in ADTKD.

An Enhanced Expression Level of CXCR3 on Tfh-like Cells from Lupus Skin Lesions Rather Than Lupus Peripheral Blood.

Systemic lupus erythematosus (SLE) is a systemic autoimmune disease, and the etiopathogenesis is unclear. Follicular helper T (Tfh) cells have been reported as an important pathogenic cell type in SLE. CXCR3 was reported to be decreased on lupus peripheral CD4+T cells. However, the expression level of CCR4, CCR6 and CXCR3 on Tfh-like cells in SLE peripheral blood and skin lesions is unknown. In this study, we detected CCR4, CCR6 and CXCR3 expression level on Tfh-like cells in the peripheral blood and skin lesions from SLE patients and normal controls (NCs). A decreased expression level of CXCR3 on Tfh-like cells was found in lupus peripheral blood. However, an increased CXCR3 expression was observed on total CD4+T and Tfh-like cells from lupus skin lesions. Moreover, we observed a higher expression level of CXCR3 in Tfh cells from human tonsils. These findings indicate that CXCR3 might help Tfh-like cells to migrate into the inflammatory sites.

Statistical insights for crude-rate-based operational measures of misdiagnosis-related harms.

In longitudinal event data, a crude rate is a simple quantification of the event rate, defined as the number of events during an evaluation window, divided by the at-risk population size at the beginning or mid-time point of that window. The crude rate recently received revitalizing interest from medical researchers who aimed to improve measurement of misdiagnosis-related harms using administrative or billing data by tracking unexpected adverse events following a "benign" diagnosis. The simplicity of these measures makes them attractive for implementation and routine operational monitoring at hospital or health system level. However, relevant statistical inference procedures have not been systematically summarized. Moreover, it is unclear to what extent the temporal changes of the at-risk population size would bias analyses and affect important conclusions concerning misdiagnosis-related harms. In this article, we present statistical inference tools for using crude-rate based harm measures, as well as formulas and simulation results that quantify the deviation of such measures from those based on the more sophisticated Nelson-Aalen estimator. Moreover, we present results for a generalized multibin version of the crude rate, for which the usual crude rate is a single-bin special case. The generalized multibin crude rate is more straightforward to compute than the Nelson-Aalen estimator and can reduce potential biases of the single-bin crude rate. For studies that seek to use multibin measures, we provide simulations to guide the choice regarding number of bins. We further bolster these results using a worked example of stroke after "benign" dizziness from a large data set.

Clinico-pathologic features, treatment and outcomes of breast cancer during pregnancy or the post-partum period.

PURPOSE: Breast cancer during pregnancy (BC-P) or the first year post-partum (BC-PP) is rare and whether it differs from breast cancer (BC) in young women not associated with pregnancy is uncertain. METHODS: We queried our institutional database for BC-P and BC-PP cases and matched controls with BC not associated with pregnancy diagnosed between January 1, 1985 and December 31, 2013. We performed two parallel retrospective cohort studies evaluating clinico-pathologic features, treatment and outcomes for BC-P and BC-PP cases compared to their controls. RESULTS: In our population of 65 BC-P cases, 135 controls for BC-P cases, 75 BC-PP cases and 145 controls for BC-PP cases, high grade and estrogen receptor-negativity were more frequent in both case groups than their controls. Among those with stage I-III BC, patterns of local therapy were similar for both case groups and their controls, with the majority undergoing surgery and radiation. Over three-fourths of those with stage I-III BC received chemotherapy. BC-P cases tolerated chemotherapy well, with the majority receiving doxorubicin/cyclophosphamide every 3 weeks. On multivariate analyses of those with stage I-III BC, BC-P cases had non-significantly higher hazards of recurrence and death compared to their controls, while BC-PP cases had non-significantly lower hazards of recurrence and death compared to their controls. CONCLUSION: BC-P and BC-PP were associated with adverse clinic-pathologic features in our population. However, we did not observe inferior outcomes for BC-P or BC-PP compared to controls, likely due to receipt of aggressive multi-modality therapy.

Long-distance disorder-disorder relation extraction with bootstrapped noisy data.

OBJECTIVE: Artificial intelligence in healthcare increasingly relies on relations in knowledge graphs for algorithm development. However, many important relations are not well covered in existing knowledge graphs. We aim to develop a novel long-distance relation extraction algorithm that leverages the article section structure and is trained with bootstrapped noisy data to identify important relations for diagnosis, including may cause, may be caused by, and differential diagnosis. METHODS: Known relations were extracted from semistructured web pages and a relational database and were paired with sentences containing corresponding medical concepts to form training data. The sentence form was extended to allow one concept to be in the title. An attention mechanism was applied to reduce the effect of noisily labeled sentences. Section structure embedding was added to provide additional context for relation expressions. Graph information was further incorporated into the model to differentiate the target relations whose expressions were often similar and interwoven. RESULTS: The extended sentence form allowed 1.75 times as many relations and 2.17 times as many sentences to be found compared to the conventional form. The various components of the proposed model all added to the accuracy. Overall, the positive sample accuracy of the proposed model was 9 percentage points higher than baseline deep learning models and 13 percentage points higher than naïve Bayes and support vector machines. CONCLUSION: Our bootstrap data preparation method and the extended sentence form could form a large training dataset to enable algorithm development and data mining efforts. Section structure embedding and graph information significantly increased prediction accuracy.

AD risk score for the early phases of disease based on unsupervised machine learning.

INTRODUCTION: Identifying cognitively normal individuals at high risk for progression to symptomatic Alzheimer's disease (AD) is critical for early intervention. METHODS: An AD risk score was derived using unsupervised machine learning. The score was developed using data from 226 cognitively normal individuals and included cerebrospinal fluid, magnetic resonance imaging, and cognitive measures, and validated in an independent cohort. RESULTS: Higher baseline AD progression risk scores (hazard ratio = 2.70, P < 0.001) were associated with greater risks of progression to clinical symptoms of mild cognitive impairment (MCI). Baseline scores had an area under the curve of 0.83 (95% confidence interval: 0.75 to 0.91) for identifying subjects who progressed to MCI/dementia within 5 years. The validation procedure, using data from the Alzheimer's Disease Neuroimaging Initiative, demonstrated accuracy of prediction across the AD spectrum. DISCUSSION: The derived risk score provides high predictive accuracy for identifying which individuals with normal cognition are likely to show clinical decline due to AD within 5 years.

Bioplasmonic paper-based assay for perilipin-2 non-invasively detects renal cancer.

Renal cell carcinoma (RCC) has poor survival prognosis because it is asymptomatic at an early, more curative stage. Recently, urine perilipin-2 (PLIN-2) was demonstrated to be a sensitive and specific biomarker for the noninvasive, early detection of RCC and an indispensable indicator to distinguish cancer from a benign renal mass. However, current Western blot or ELISA PLIN-2 assays are complicated, expensive, time-consuming or insensitive, making them unsuitable for routine analysis in clinical settings. Here we developed a plasmonic biosensor based on the high refractive index sensitivity of gold nanorattles for the rapid detection of PLIN-2 in patient urine. The paper-based plasmonic assay is highly sensitive and has a dynamic range of 50 pg/ml to 5 µg/ml PLIN-2. The assay is not compromised by variations in urine pH or high concentrations of interfering proteins such as albumin and hemoglobin, making it an excellent candidate for routine clinical applications. The urine PLIN-2 assay readily distinguished patients with pathologically proven clear cell carcinomas of various size, stage and grade (55.9 [39.5, 75.8] ng/ml, median [1st and 3rd quartile]) from age-matched controls (0.3 [0.3, 0.5] ng/ml), patients with bladder cancer (0.5 [0.4, 0.6] ng/ml) and patients with diabetic nephropathy (0.6 [0.4, 0.7] ng/ml). Urine PLIN-2 concentrations were roughly proportional to tumor size (Pearson coefficient 0.59). Thus, this cost-effective and label-free method represents a novel approach to conduct a non-invasive population screen or rapid differential diagnosis of imaged renal masses, significantly facilitating the early detection and diagnosis of RCC.