Scoring Algorithms Research Articles

Accuracy of alternative PHQ-9 scoring algorithms to screen for depression in people living with HIV in Sub-Saharan Africa.

Screening for depression remains a priority for people living with HIV (PLWH) accessing care. The nine-item Patient Health Questionnaire (PHQ-9) is a widely used depression screening tool, but has limited accuracy when applied across various cultural contexts. We aimed to evaluate the performance of alternative PHQ-9 scoring algorithms in sub-Saharan African PLWH. five HIV programs in Cameroon, Côte d'Ivoire, Kenya, Senegal and the Republic of Congo. Adult PLWH were screened for depression during the 2018-2022 period. Diagnosis confirmation was done by psychiatrist blinded clinical evaluation (gold standard). Diagnostic performances, including sensitivity, and area under the curve (AUC)) of the traditional PHQ-9 scoring (positive screening - score≥10) was compared to alternative scoring algorithms including: i) the presence of ≥1 mood symptom (PHQ-9 items 1&2) combined with ≥2 other symptoms listed in the PHQ-9, and ii) a simplified recoding of each 4-response item into two categories (absence/presence). A total of 735 participants were included (54% female, median age 42 years [IQR 34-50]). Depression was diagnosed by a psychiatrist in 95(13%) participants. Alternative scoring sensitivities (0.59 to 0.74) were higher than that of the traditional score's (0.39). Compared to traditional scoring, AUC were significantly higher for PHQ-9 alternative scoring. Across settings, alternative scoring algorithms increased sensitivity and reduced variability. As a primary screening test, new scoring algorithms appeared to improve the PHQ-9 sensitivity in identifying depression and reduce heterogeneity across settings. This alternative might be considered to identify PLWH in need of referral for further diagnostic evaluations.

Time–frequency ridge characterisation of sleep stage transitions: Towards improving electroencephalogram annotations using an advanced visualisation technique

Manual sleep stage scoring of polysomnography recordings is an expensive and time-consuming process, further complicated by inconsistent sleep stage agreement among sleep experts (clinicians and sleep technologists). Hence, development of automated sleep scoring algorithms are an emerging topic of interest. Automation typically mimics the clinical decision path by implementing a series of predefined rules, such as the American Academy of Sleep Medicine’s (AASM) scoring manual. Recently, data driven methods have emerged using machine or deep learning. Both manual and automated methods of scoring have known limitations; primarily, unacceptable variation in agreement between different scorers and algorithms. Within the literature, electroencephalogram (EEG) frequency is an important feature considered by both sleep experts and automated approaches for classifying sleep stages.This study presents a novel approach to sleep stage analysis, by developing a methodology to precisely determine the temporal location of sleep stage transitions. The current gold standard fails to identify such transitional changes, which leads to poor inter-scorer reliability. Therefore, development and implementation of such methodologies is a crucial, but overlooked, step in improving the consistency of scoring within sleep studies. In this work, EEG time–frequency ridge analysis was used to characterise the dominant frequency component of EEG signals in time, at the point of sleep stage transition. An in-depth analysis of N3 → N2 and N2 → N3 transitions in the 2018 PhysioNet challenge “You Snooze, You Win” and the Wisconsin Sleep Cohort (WSC) datasets (n = 994, n = 742; approximately 13,888 h of sleep data) showed consistent time–frequency patterns at the point of transition, from one sleep stage to another. This methodology allows simple and ‘interpretable’ features to be generated in future work, to precisely identify the temporal location of sleep stage transitions with the aim of improving inter-scorer reliability.

Assessment of trabecular bone score using updated TBSTT in anorexia nervosa-The AN-BO study.

Anorexia Nervosa (AN) is characterized by a distortion of body image, very low body weight, malnutrition and hormonal dysregulations, resulting in reduced bone mineral density (BMD) and impaired bone microarchitecture. The updated Trabecular Bone Score (TBS) algorithm accounts for soft tissue thickness (TBSTT) instead of BMI (TBSBMI). The aim of the study was to assess both TBS algorithms in adult AN patients compared to normal-weight controls(CTRL). This retrospective cross-sectional study investigated 34 adult female anorexia nervosa (AN) patients and 26 healthy normal-weighted age- and sex-matched controls (CTRL). Bone texture analysis was assessed by TBSTT and TBSBMI (TBS iNsight® V4.0 and V3.1), bone mineral density (BMD; lumbar spine LS, femoral neck, total hip) and body composition by DXA (GE Lunar iDXATM). Laboratory analyses included bone turnover markers (CTX; P1NP; sclerostin). Data analysis was performed using parametric (t-test) or non-parametric test (Mann-Whitney-U-Test) depending on normality, one-way ANCOVA and correlation analysis (Perason's or Spearman's). AN patients (BMI 14.7(1.6)) and CTRL (BMI 22.4(4.0)) were of comparable age (22.8(7.1) vs.25.0(4.0)years, p = 0.145). TBSTT(1.319±0.09 vs.1.502±0.07, p<0.001) and TBSBMI(1.317±0.10 vs.1.548±0.09, p<0.001) were significantly lower in AN patients compared to CTRL. Soft tissue thickness was lower in AN (p<0.001). Within the CTRL group, but not in AN, TBSTT and TBSBMI were significantly different (p<0.001). BMD was lower at all sites in AN patients (p<0.001 for all), being lowest at LS. Bone Mineral Content, Lean Body mass and Fat Mass were lower in AN (p<0.001). AN patients had lower P1NP (p = 0.05), but higher CTX (p = 0.001) and sclerostin (p = 0.003) levels. Adult AN patients have lower TBSTT and TBSBMI, reduced BMD and an uncoupling of bone turnover. In AN both TBS algorithms show similar reduced trabecular bone microarchitecture. The observed difference of TBSTT and TBSBMI in CTRL with normal body composition highlight the importance of the new algorithm.

Concordance Between Platelet Expression Assay (PEA) and Serotonin Release Assay (SRA) in Heparin-Induced Thrombocytopenia: Implications for Diagnostic Accuracy and Laboratory Test Utilization

Abstract Introduction The Serotonin Release Assay (SRA) serves as the gold standard functional assay for heparin-induced thrombocytopenia (HIT) diagnosis at our institution. The present turnaround time (TAT) for SRA results ranges from 4-5 days, occasionally extending beyond 8 days, given outsourcing to a reference laboratory. Recently, an alternative functional assay, the Platelet Expression Assay (PEA), has been introduced. The PEA detects platelet activation through p-selectin expression by flow cytometry, with a reported sensitivity of 100% and specificity of 95% for HIT. The PEA is also a send-out test, and thus has similar TAT and cost profiles as the SRA, but with potential to transition into an in-house assay in the future. Herein, we sought to determine the concordance of the PEA and SRA for the detection and diagnosis of HIT within our patient population. Methods A retrospective review was conducted on all cases in which a HIT ELISA (screening immunoassay) was performed by the Special Coagulation Laboratory during a one-year period. A 4Ts score was calculated if not already documented by chart review. In a subset analysis, specimens with a positive screening ELISA were concurrently tested by both SRA and PEA to compare performance. Results Of the 1341 cases, a 4Ts score was calculated and found to be less than 4 for 30-50% of cases. A total of 490 cases were sent out for SRA, of which 49 (10%) returned positive results. In a subset analysis of 20 samples from 14 patients, all with positive ELISAs, results revealed concordance between the SRA and PEA for all but one sample (19/20, 95%). Specifically, three successive samples from one patient had [negative, negative, positive] results for SRA, and [negative, positive, positive] results for PEA, respectively. This discordant result suggests a potential difference in sensitivity between the two assays. Further subset analysis focused on an additional 13 samples from 10 patients, all with SRA-positive results. Only 8 samples were concordant (8/13, 62%). One case showed a negative PEA and presumed false positive SRA, given the clinical history, while 4 samples showed likely true positive SRA results, given strength of ELISA results and 4Ts score, but were negative by PEA. Conclusions The lack of adherence to the 4Ts score algorithm to drive laboratory test utilization resulted in unnecessary ELISA and functional assay testing, potentially resulting in increased costs and false positive results. This result underscores the need for vigilance in assessing and refining diagnostic strategies. Additionally, our discordant findings in the subset analysis underscore the importance of evaluating the concordance and discordance between SRA and PEA results, providing insights into the diagnostic accuracy and potential limitations of each assay in identifying HIT.

Novel Diagnostic Approach for Acute Pharyngitis: Combining Machine Learning With Thermal Imaging.

We evaluated the effect of infrared thermography (IRT) on the clinical assessment of bacterial and viral pharyngitis and its impact on the predictive value of the McIsaac score algorithm for streptococcal pharyngitis in children. We also investigated if IRT could distinguish between bacterial and viral pharyngitis. The study included children aged 2-17 years presenting with sore throat and fever over 38°C from November 1, 2021, to April 30, 2022. Of the 76 assessed children, 16 were excluded due to missing data or technical issues, leaving 60 children (32 males, 28 females) divided into three groups: Group A with streptococcal pharyngitis (N = 30), viral pharyngitis (N = 16), and healthy controls (N = 14). McIsaac score and IRT imaging showed a 90% positive predictive value for streptococcal pharyngitis. While IRT alone could not distinguish between bacterial and viral infections, it significantly increased the predictive value when combined with the McIsaac score.

B-051 Clinical Validation of Vectra® DA: A Multi-Biomarker Based Test for the Objective Measurement of Disease Activity in Patients with Rheumatoid Arthritis

Abstract Background The Vectra® DA test measures serum levels of 12 protein biomarkers associated with rheumatoid arthritis (RA) and uses these levels in an algorithmic calculation to generate a numeric score that represents RA disease activity where established categories are low for scores 1 to 29, moderate for 30 to 44, and high for 45 to 100. LabCorp Specialty Lab in Calabasas, CA completed the quantitative analytical validations of 12 Vectra biomarkers (SAA, CRP, VCAM-1, IL-6, TNF-RI, EGF, VEGF-A, Leptin, Resistin, MMP-1, MMP-3, and YKL-40) and the clinical verification of the Vectra score algorithm. Methods The Vectra test consists of the quantitative measurements of EGF, Leptin, MMP-1, TNF-R1, VEGF, MMP-3, Resistin, VCAM, YKL-40, CRP, SAA and IL-6 using multiplex immunoassay platforms. The data acquired from each biomarker assay is processed through an algorithm where a composite Vectra score adjusted based on age, gender, and adiposity of the patient is computed. Analytical parameters validated for each biomarkers include sensitivity, precision, accuracy, specificity and stability. Precision was validated using pooled human serum controls at low, moderate, and high Vectra score levels. Method comparison was performed using 584 clinically defined serum samples. Quantitatively measured analyte values and computed Vectra scores by the Labcorp Vectra assay were compared with Vectra data produced by Myriad laboratory. Results Intra- and inter-assay sample precision of the final Vectra score was &amp;lt;13% and &amp;lt;18%, respectively. Sample stability using freshly collected serum subject to ambient and refrigerated temperature up to 14 days and frozen up to 364 days and up to 6 freeze-thaw cycles were acceptable. Of 584 clinical Vectra data compared, Labcorp vs Myriad, 96% of data were comparable within the acceptable criteria. Correlation of Vectra score from Labcorp and Myriad was excellent. A linear least square model resulted in a correlation coefficient (R) of 0.981 and a Deming slope of 1.009. Qualitative method comparison of Vectra scores resulted in excellent agreement of risk of radiographic progression and rheumatoid arthritis disease activity. A 91% agreement of risk category match between Labcorp and Myriad and 100% agreement of Vectra scores within 1 risk category was achieved. Conclusions We validated the Vectra® DA multiplex assay for measuring serum levels of 12 protein biomarkers associated with RA. Vectra combines biomarker levels into a personalized disease score that represents a patient’s RA inflammation and predict their risk of radiographic progression. High Vectra® DA scores (&amp;gt; 44) have been associated with a 20% 1-year risk of radiographic progression while low scores (&amp;lt; 30) carry only a 1% risk. Thus, the Vectra score provides an objective measurement of RA disease activity that can be used in combination with existing assessment tools to aid physicians to manage patients with RA.

Performance of a HER2 testing algorithm tailored for urothelial bladder cancer: A Bi-centre study

AimsThis study aimed to develop an AI algorithm for automated HER2 scoring in urothelial bladder cancer (UBCa) and assess the interobserver agreement using both manual and AI-assisted methods based on breast cancer criteria. Methods and ResultsWe utilized 330 slides from two institutions for initial AI development and selected 200 slides for the ring study, involving six pathologists (3 senior, 3 junior). Our AI algorithm achieved high accuracy in two independent tests, with accuracies of 0.94 and 0.92. In the ring study, the AI-assisted method improved both accuracy (0.66 vs 0.94) and consistency (kappa=0.48; 95 % CI, 0.443–0.526 vs kappa=0.87; 95 % CI, 0.852–0.885) compared to manual scoring, especially in HER2-low cases (F1-scores: 0.63 vs 0.92). Additionally, in 62.3 % of heterogeneous HER2-positive cases, the interpretation accuracy significantly improved (0.49 vs 0.93). Pathologists, particularly junior ones, experienced enhanced accuracy and consistency with AI assistance. ConclusionsThis is the first study to provide a quantification algorithm for HER2 scoring in UBCa to assist pathologists in diagnosis. The ring study demonstrated that HER2 scoring based on breast cancer criteria can be effectively applied to UBCa. Furthermore, AI assistance significantly improves the accuracy and consistency of interpretations among pathologists with varying levels of experience, even in heterogeneous cases.

What do women want to see in a personalized breast cancer risk report? A qualitative study of Asian women of two countries.

A breast cancer risk assessment tool for Asian populations, incorporating Polygenic Risk Score and Gail Model algorithm, has been established and validated. However, effective methods for delivering personalized risk information remain underexplored. This study aims to identify and develop effective methods for conveying breast cancer risk information to Asian women. Through ten focus group discussions with 32 women in Indonesia and Singapore, we explored preferences for the presentation of risk information. Participants favored comprehensive reports featuring actionable steps, simplified language, non-intimidating visuals, and personalized risk reduction recommendations. Singaporean participants, more aware of breast cancer prevention, showed a lower likelihood of seeking follow-ups upon receiving low-risk results compared to Indonesians. Overall, participants found the reports useful and advocated for similar approaches in other disease assessments. Balancing content and complexity in reports is crucial, highlighting the need for improved patient understanding and engagement with healthcare providers. Future studies could explore physicians' roles in delivering personalized risk assessments for breast cancer prevention.

Probabilistic Record Linkage for Families (PRLF): A Discussion of the Development and Validation of this Open-Source Linkage Tool

Linking administrative records across programs can yield person-centered information, including client characteristics, public service trajectories, and outcomes and help to answer policy-related questions. Several solutions are available for undertaking record linkage, producing linkage keys for merging data sources for positively matched pairs of records. In this session, we will demonstrate a new application of the Python RecordLinkage package to family-based record linkages with machine learning algorithms for probability scoring, which we call probabilistic record linkage for families (PRLF). First, we will demonstrate the utility of PRLF with a simulation of administrative records and assess linkage accuracy with variations in match rates and data degradation. Second, we will compare generalized linear model estimates across three record linkage solutions (PRLF, ChoiceMaker, and Link Plus). Findings from the simulation study indicate linkage accuracy is largely influenced by degradation (e.g., missing data fields, erroneous or incomplete values) compared to the proportion of simulated matches between datasets. Results from the methods comparison using real world data indicate that all three solutions, when optimized, provide similar results for researchers. We discuss the strengths of our process, such as the use of ensemble methods, to improve match accuracy. We then will identify caveats of record linkage in the context of administrative data. The tool was developed in Python to allow for researchers to work with open-source software and adjust the basic workflow to fit their linkage needs. We will identify several partnerships where this collaboration has worked successfully and empower attendees with access to this useful tool.

Updated Risk Score Algorithms for Acute HIV Infection Detection at a Sexually Transmitted Infections Clinic in Lilongwe, Malawi

Background: Detection of acute (pre-seroconversion) HIV infection (AHI), the phase of highest transmission risk, requires resource-intensive RNA- or antigen-based detection methods that can be infeasible for routine use. Risk score algorithms can improve the efficiency of AHI detection by identifying persons at highest risk of AHI for prioritized RNA/antigen testing, but prior algorithms have not considered geospatial information, potential differences by sex, or current antibody testing paradigms. Methods: We used elastic net models to develop sex-stratified risk score algorithms in a case-control study of persons (136 with AHI, 250 without HIV) attending a sexually transmitted infections (STI) clinic in Lilongwe, Malawi from 2015 to 2019. We designed algorithms for varying clinical contexts according to three levels of data availability: 1) routine demographic and clinical information, 2) behavioral and occupational data obtainable through patient interview, and 3) geospatial variables requiring external datasets or field data collection. We calculated sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) to assess model performance and developed a web application to support implementation. Results: The highest-performing AHI risk score algorithm for men (AUC=0.74) contained five variables (condom use, body aches, fever, rash, genital sores/ulcers) from the first two levels of data availability. The highest-performing algorithm for women (AUC=0.81) contained fifteen variables from all three levels of data availability. A risk score cut-point of 0.26 had an AHI detection sensitivity of 93% and specificity of 27% for males, and a cut-point of 0.15 had 97% sensitivity and 44% specificity for females. Additional models are available in the web application. Conclusion: Risk score algorithms can facilitate efficient AHI detection in STI clinic settings, creating opportunities for HIV transmission prevention interventions during this critical period of elevated transmission risk.

177P HER2 testing in multiple solid tumors: Concordance between 3 scoring algorithms

177P HER2 testing in multiple solid tumors: Concordance between 3 scoring algorithms

An Improved Scoring Algorithm for Indirect Evaluation Measurement With the Evaluative Priming Task

People tend to categorize the valence of a target stimulus more quickly and accurately if the target appears after a prime stimulus of the same (than of the opposite) valence. The evaluative priming task (EPT) utilizes this priming effect for indirect evaluation measurement but suffers from low reliability. The present research compared the reliability and validity of 2,160 EPT scoring algorithms across 12 datasets. In contrast to current norms to delete trials with error responses and to rely solely on differences in response latency between different task conditions, superior performance was found when incorporating latency and accuracy data, and when basing the score on differences in mean ranking of each condition’s trials by performance (a scale-invariant non-parametric dominance score named G score). We recommend seven new scoring algorithms that, in comparison to current scoring norms, increase internal consistency by a mean of 41% and correlations with other measures by 17%.

Cross-ValidatedFunctional Generalized Partially Linear Single-Functional Index Model

In this paper, we have introduced a functional approach for approximating nonparametric functions and coefficients in the presence of multivariate and functional predictors. By utilizing the Fisher scoring algorithm and the cross-validation technique, we derived the necessary components that allow us to explain scalar responses, including the functional index, the nonlinear regression operator, the single-index component, and the systematic component. This approach effectively addresses the curse of dimensionality and can be applied to the analysis of multivariate and functional random variables in a separable Hilbert space. We employed an iterative Fisher scoring procedure with normalized B-splines to estimate the parameters, and both the theoretical and practical evaluations demonstrated its favorable performance. The results indicate that the nonparametric functions, the coefficients, and the regression operators can be estimated accurately, and our method exhibits strong predictive capabilities when applied to real or simulated data.

Predicting radiotherapy efficacy and prognosis in tongue squamous cell carcinoma through an in-depth analysis of a radiosensitivity gene signature.

Tongue squamous cell carcinoma (TSCC) is a prevalent tumor that affects many people worldwide. Radiotherapy is a common treatment option, but its efficacy varies greatly. This study seeks to validate the identified gene signature associated with radiosensitivity in TSCC, and its potential in predicting radiotherapy response and prognosis. We analyzed 122 TSCC patients from TCGA database using the radiosensitivity signature and classified them into radiosensitive (RS) and radioresistant (RR) groups. Immune infiltration analysis methods were applied to investigate the immune status between different subgroups. Immunophenotype Score (IPS) and pRRophetic algorithm were employed to estimate the efficiency of treatment. A radioresistant TSCC cell line was established by gradually increasing radiation doses. Cell radiosensitivity was evaluated using the CCK-8 and colony formation assays. The expression of radiosensitivity-related genes was validated by qRT-PCR. Our study validated the predictive capacity of a previously identified "31-gene signature" in the TCGA-TSCC cohort, which effectively stratified patients into RS and RR groups. We observed that the RS group exhibited superior overall survival and progression-free survival rates relative to the RR group when treated with radiotherapy. The RS group was significantly enriched in most immune-related hallmark pathways, and may therefore benefit from immune checkpoint inhibitors. However, the RS group displayed lower sensitivity to first-line chemotherapy. A radioresistant TSCC cell line (CAL-27R) exhibited increased clonogenic potential and cell viability following irradiation, accompanied by downregulation of three radiosensitivity-related genes compared to its parental non-resistant cell (CAL-27). In addition, we constructed and validated a radiosensitivity-related prognostic index (PI) using 4 radiosensitivity-related genes associated with TSCC prognosis. We assessed the ability of the radiosensitivity gene signature to predict outcomes in TSCC patients. our research provided valuable insights into the molecular pathways associated with radiosensitivity in TSCC and offered clinicians a practical tool to predict patient radiotherapy effectiveness and prognosis.

High-Dimensional Propensity Score and Its Machine Learning Extensions in Residual Confounding Control

“The use of health care claims datasets often encounters criticism due to the pervasive issues of omitted variables and inaccuracies or mis-measurements in available confounders. Ultimately, the treatment effects estimated using such data sources may be subject to residual confounding. Digital electronic administrative records routinely collect a large volume of health-related information; and many of which are usually not considered in conventional pharmacoepidemiological studies. A high-dimensional propensity score (hdPS) algorithm was proposed that uses such information as surrogates or proxies for mismeasured and unobserved confounders in an effort to reduce residual confounding bias. Since then, many machine learning and semi-parametric extensions of this algorithm have been proposed to better exploit the wealth of high-dimensional proxy information. In this tutorial, we will (i) demonstrate logic, steps and implementation guidelines of hdPS using an open data source as an example (using reproducible R codes), (ii) familiarize readers with the key difference between propensity score versus hdPS, as well as the requisite sensitivity analyses, (iii) explain the rationale for using the machine learning and double robust extensions of hdPS, and (iv) discuss advantages, controversies, and hdPS reporting guidelines while writing amanuscript.

Converting PROMIS®-29 v2.0 profile data to SF-36 physical and mental component summary scores in patients with cardiovascular disorders

BackgroundHealth-related quality of life (HRQL) has become an important outcome parameter in cardiology. The MOS 36-ltem Short-Form Health Survey (SF-36) and the PROMIS-29 are two widely used generic measures providing composite HRQL scores. The domains of the SF-36, a well-established instrument utilized for several decades, can be aggregated to physical (PCS) and mental (MCS) component summary scores. Alternative scoring algorithms for correlated component scores (PCSc and MCSc) have also been suggested. The PROMIS-29 is a newer but increasingly used HRQL measure. Analogous to the SF-36, physical and mental health summary scores can be derived from PROMIS-29 domain scores, based on a correlated factor solution. So far, scores from the PROMIS-29 are not directly comparable to SF-36 results, complicating the aggregation of research findings. Thus, our aim was to provide algorithms to convert PROMIS-29 data to well-established SF-36 component summary scores.MethodsData from n = 662 participants of the Berlin Long-term Observation of Vascular Events (BeLOVE) study were used to estimate linear regression models with either PROMIS-29 domain scores or aggregated PROMIS-29 physical/mental health summary scores as predictors and SF-36 physical/mental component summary scores as outcomes. Data from a subsequent assessment point (n = 259) were used to evaluate the agreement between empirical and predicted SF-36 scores.ResultsPROMIS-29 domain scores as well as PROMIS-29 health summary scores showed high predictive value for PCS, PCSc, and MCSc (R2 ≥ 70%), and moderate predictive value for MCS (R2 = 57% and R2 = 40%, respectively). After applying the regression coefficients to new data, empirical and predicted SF-36 component summary scores were highly correlated (r > 0.8) for most models. Mean differences between empirical and predicted scores were negligible (|SMD|<0.1).ConclusionsThis study provides easy-to-apply algorithms to convert PROMIS-29 data to well-established SF-36 physical and mental component summary scores in a cardiovascular population. Applied to new data, the agreement between empirical and predicted SF-36 scores was high. However, for SF-36 mental component summary scores, considerably better predictions were found under the correlated (MCSc) than under the original factor model (MCS). Additionally, as a pertinent byproduct, our study confirmed construct validity of the relatively new PROMIS-29 health summary scores in cardiology patients.

An online review-based method for dealing with exogenous shocks in the hospitality industry

To provide hospitality managers with an effective way to respond to exogenous shocks, this study proposes a quantitative opportunity score algorithm based on the primary effect of psychology and the affect-as-information theory. The proposed algorithm can assist managers in prioritizing service improvements by calculating the importance and performance of restaurant service attributes. Specifically, using the COVID-19 pandemic as an example, this study explores shifts in the importance and performance of restaurant service attributes under different degrees of restrictions based on online reviews. The results of this study show that whether or not restaurants take measures to respond to the pandemic and the different degrees of restrictions have an impact on the importance and performance of service attributes, which means that managers develop eventual service improvement strategies differently. This study not only provides insights and management recommendations for hospitality managers to deal with the post-epidemic but also provides methodological support for hospitality managers to further respond to other exogenous shocks.

Single-cell multiomics analysis reveals cell/tissue-specific associations in bipolar disorder

This study investigates the cellular origin and tissue heterogeneity in bipolar disorder (BD) by integrating multiomics data. Four distinct datasets were employed, including single-cell RNA sequencing (scRNA-seq) data (embryonic and fetal brain, n = 8, 1,266 cells), BD Assay for Transposase-Accessible Chromatin using sequencing (ATAC-seq) data (adult brain, n = 210), BD bulk RNA-seq data (adult brain, n = 314), and BD genome-wide association study (GWAS) summary data (n = 413,466). The integration of scRNA-seq data with multiomics data relevant to BD was accomplished using the single-cell disease relevance score (scDRS) algorithm. We have identified a novel brain cell cluster named ADCY1, which exhibits distinct genetic characteristics. From a high-resolution genetic perspective, glial cells emerge as the primary cytopathology associated with BD. Specifically, astrocytes were significantly related to BD at the RNA-seq level, while microglia showed a strong association with BD across multiple panels, including the transcriptome-wide association study (TWAS), ATAC-seq, and RNA-seq. Additionally, oligodendrocyte precursor cells displayed a significant association with BD in both ATAC-seq and RNA-seq panel. Notably, our investigation of brain regions affected by BD revealed significant associations between BD and all three types of glial cells in the dorsolateral prefrontal cortex (DLPFC). Through comprehensive analyses, we identified several BD-associated genes, including CRMP1, SYT4, UCHL1, and ZBTB18. In conclusion, our findings suggest that glial cells, particularly in specific brain regions such as the DLPFC, may play a significant role in the pathogenesis of BD. The integration of multiomics data has provided valuable insights into the etiology of BD, shedding light on potential mechanisms underlying this complex psychiatric disorder.

DNA-binding factor footprints and enhancer RNAs identify functional non-coding genetic variants

BackgroundGenome-wide association studies (GWAS) have revealed a multitude of candidate genetic variants affecting the risk of developing complex traits and diseases. However, the highlighted regions are typically in the non-coding genome, and uncovering the functional causative single nucleotide variants (SNVs) is challenging. Prioritization of variants is commonly based on genomic annotation with markers of active regulatory elements, but current approaches still poorly predict functional variants. To address this, we systematically analyze six markers of active regulatory elements for their ability to identify functional variants.ResultsWe benchmark against molecular quantitative trait loci (molQTL) from assays of regulatory element activity that identify allelic effects on DNA-binding factor occupancy, reporter assay expression, and chromatin accessibility. We identify the combination of DNase footprints and divergent enhancer RNA (eRNA) as markers for functional variants. This signature provides high precision, but with a trade-off of low recall, thus substantially reducing candidate variant sets to prioritize variants for functional validation. We present this as a framework called FINDER—Functional SNV IdeNtification using DNase footprints and eRNA.ConclusionsWe demonstrate the utility to prioritize variants using leukocyte count trait and analyze variants in linkage disequilibrium with a lead variant to predict a functional variant in asthma. Our findings have implications for prioritizing variants from GWAS, in development of predictive scoring algorithms, and for functionally informed fine mapping approaches.

Research on the Design of a System based on Machine Learning Algorithms for Automatic Scoring of English Writing Ability

Research on the Design of a System based on Machine Learning Algorithms for Automatic Scoring of English Writing Ability