Search

This article provides an introduction to randomized response polling, a technique which was designed to allow for questioning on sensitive issues while protecting the respondent's privacy and avoiding social desirability bias. It is described in terms that are suitable for presentation and use in any classroom environment. Instructions for plain users are included, along with the results of a small in-class implementation. The underpinnings of the method, which are laid out for the statistically savvy, illustrate the tradeoff between data acquisition and privacy protection. A few suitable references are also included for those who wish to dig further into the subject. for this article are available online. [ABSTRACT FROM AUTHOR]

An individualised treatment rule (ITR) is a decision rule that aims to improve individuals' health outcomes by recommending treatments according to subject-specific information. In observational studies, collected data may contain many variables that are irrelevant to treatment decisions. Including all variables in an ITR could yield low efficiency and a complicated treatment rule that is difficult to implement. Thus, selecting variables to improve the treatment rule is crucial. We propose a doubly robust variable selection method for ITRs, and show that it compares favourably with competing approaches. We illustrate the proposed method on data from an adaptive, web-based stress management tool. [ABSTRACT FROM AUTHOR]

The reporting of research participant demographics provides insights into study generalizability. Our study aimed to determine the frequency at which participant age, sex/gender, race/ethnicity, and socioeconomic status (SES) are reported and used for subgroup analyses in radiology randomized controlled trials (RCTs) and their secondary analyses; as well as the study characteristics associated with, and the classification systems used for demographics reporting. RCTs and their secondary analyses published in 8 leading radiology journals between 2013 and 2021 were included. Associations between study characteristics and demographic reporting were tested with the chi-square goodness of fit test for categorical variables, Wilcoxon-Mann-Whitney test for impact factor, and logistic regression for publication year. Among 432 included articles, 89.4% (386) reported age, 90.3% (390) sex/gender, 5.6% (24) race/ethnicity, and 3.0% (13) SES. Among articles that reported these demographics and were not specific to a subgroup, results were analyzed by age in 14.2% (55/386), sex/gender in 19.4% (66/340), race/ethnicity in 13.6% (3/22), and SES in 46.2% (6/13). Journal, impact factor, and last author continent were predictors of race/ethnicity and SES reporting. Funding was associated with race/ethnicity reporting. No study reported sex and gender separately, or documented transgender, nonbinary gender spectrum or intersex participants. A single category for race/ethnicity was used in 37.5% (9/24) of studies, consisting of either "White" or "Caucasian." The reporting of participant demographics in radiology trials is variable and not always representative of the population diversity. Editorial guidelines on the reporting and analysis of participant demographics could help standardize practices. [ABSTRACT FROM AUTHOR]

Supplemental Digital Content is Available in the Text. Background: Low-risk perception is an important barrier to the utilization of HIV services. In this context, offering an online platform for people to assess their risk of HIV and inform their decision to test can be impactful in increasing testing uptake. Using secondary data from the HIVSmart! quasirandomized trial, we aimed to identify predictors of HIV, develop a risk staging model for South African township populations, and validate it in combination with the HIVSmart! digital self-testing program. Setting: Townships in Cape Town, South Africa. Methods: Using Bayesian predictive projection, we identified predictors of HIV and constructed a risk assessment model that we validated in external data. Results: Our analyses included 3095 participants from the HIVSmart! trial. We identified a model of 5 predictors (being unmarried, HIV testing history, having had sex with a partner living with HIV, dwelling situation, and education) that performed best during external validation (area under the receiver operating characteristic curve, 89% credible intervals: 0.71, 0.68 to 0.72). The sensitivity of our HIV risk staging model was 91.0% (89.1% to 92.7%) and the specificity was 13.2% (8.5% to 19.8%) but increased when combined with a digital HIV self-testing program, the specificity was 91.6% (95.9% to 96.4%) and sensitivity remained similar at 90.9% (89.1% to 92.6%). Conclusions: This is the first validated digital HIV risk assessment tool developed for South African township populations and the first study to evaluate the added value of a risk assessment tool with an app-based HIV self-testing program. Study findings are relevant for application of digital programs to improve utilization of HIV testing services. [ABSTRACT FROM AUTHOR]

Dynamic treatment regimes (DTRs) consist of a sequence of decision rules, one per stage of intervention, that aim to recommend effective treatments for individual patients according to patient information history. DTRs can be estimated from models which include interactions between treatment and a (typically small) number of covariates which are often chosen a priori. However, with increasingly large and complex data being collected, it can be difficult to know which prognostic factors might be relevant in the treatment rule. Therefore, a more data‐driven approach to select these covariates might improve the estimated decision rules and simplify models to make them easier to interpret. We propose a variable selection method for DTR estimation using penalized dynamic weighted least squares. Our method has the strong heredity property, that is, an interaction term can be included in the model only if the corresponding main terms have also been selected. We show our method has both the double robustness property and the oracle property theoretically; and the newly proposed method compares favorably with other variable selection approaches in numerical studies. We further illustrate the proposed method on data from the Sequenced Treatment Alternatives to Relieve Depression study. [ABSTRACT FROM AUTHOR]

Motivation Sparse regularized regression methods are now widely used in genome-wide association studies (GWAS) to address the multiple testing burden that limits discovery of potentially important predictors. Linear mixed models (LMMs) have become an attractive alternative to principal components (PCs) adjustment to account for population structure and relatedness in high-dimensional penalized models. However, their use in binary trait GWAS rely on the invalid assumption that the residual variance does not depend on the estimated regression coefficients. Moreover, LMMs use a single spectral decomposition of the covariance matrix of the responses, which is no longer possible in generalized linear mixed models (GLMMs). Results We introduce a new method called pglmm , a penalized GLMM that allows to simultaneously select genetic markers and estimate their effects, accounting for between-individual correlations and binary nature of the trait. We develop a computationally efficient algorithm based on penalized quasi-likelihood estimation that allows to scale regularized mixed models on high-dimensional binary trait GWAS. We show through simulations that when the dimensionality of the relatedness matrix is high, penalized LMM and logistic regression with PC adjustment fail to select important predictors, and have inferior prediction accuracy compared to pglmm. Further, we demonstrate through the analysis of two polygenic binary traits in a subset of 6731 related individuals from the UK Biobank data with 320K SNPs that our method can achieve higher predictive performance, while also selecting fewer predictors than a sparse regularized logistic lasso with PC adjustment. Availability and implementation Our Julia package PenalizedGLMM.jl is publicly available on github: https://github.com/julstpierre/PenalizedGLMM. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Although it is a widely used—and misused—discrete distribution, textbooks tend to give the history of the Poisson distribution short shrift, typically deriving it in the abstract as a limiting case of a binomial. The biological and physical scientists who independently derived it using space and time considerations and used it in their work are seldom mentioned. Nor are the difficulties of applying it to counts involving human activities/behavior. We (a) sketch the early history of the Poisson distribution (b) illustrate principles of the Poisson distribution involving space and time using the original biological and physical applications, as well as modern multimedia reenactments of them, and (c) motivate count distributions accounting for extra-Poisson variation. The replayed historical applications can help today's students, teachers and practitioners to see or hear what randomness looks or sounds like, to get practice in the practicalities of "counting statistics," to distinguish situations where the pure Poisson distribution does and doesn't hold—and to think about what one might do when it doesn't. [ABSTRACT FROM AUTHOR]

Genetic risk scores (GRS) and polygenic risk scores (PRS) are weighted sums of, respectively, several or many genetic variant indicator variables. Although they are being increasingly proposed for clinical use, the best ways to construct them are still actively debated. In this commentary, we present several case studies illustrating practical challenges associated with building or attempting to improve score performance when there is expected to be heterogeneity of disease risk between cohorts or between subgroups of individuals. Specifically, we contrast performance associated with several ways of selecting single nucleotide polymorphisms (SNPs) for inclusion in these scores. By considering GRS and PRS as predictors that are measured with error, insights into their strengths and weaknesses may be obtained, and SNP selection approaches play an important role in defining such errors. [ABSTRACT FROM AUTHOR]

In clinical studies of time-to-event data, a quantity of interest to the clinician is their patient's risk of an event. However, methods relying on time matching or risk-set sampling (including Cox regression) eliminate the baseline hazard from the estimating function. As a consequence, the focus has been on reporting hazard ratios instead of survival or cumulative incidence curves. Indeed, reporting patient risk or cumulative incidence requires a separate estimation of the baseline hazard. Using case-base sampling, Hanley & Miettinen (2009) explained how parametric hazard functions can be estimated in continuous-time using logistic regression. Their approach naturally leads to estimates of the survival or risk function that are smooth-in-time. In this paper, we present the casebase R package, a comprehensive and flexible toolkit for parametric survival analysis. We describe how the case-base framework can also be used in more complex settings: non-linear functions of time and non-proportional hazards, competing risks, and variable selection. Our package also includes an extensive array of visualization tools to complement the analysis. We illustrate all these features through three different case studies. * SRB and MT contributed equally to this work. [ABSTRACT FROM AUTHOR]

Aim: Low anterior resection syndrome (LARS) refers to a constellation of bowel symptoms that affect the majority of patients following restorative proctectomy. LARS is associated with poorer quality of life (QoL), and can lead to distress, anxiety and isolation. Peer support could be an important resource for people living with LARS, helping them normalize and validate their experience. The aim of this work is to describe the development of an interactive online informational and peer support app for LARS and the protocol for a randomized controlled trial. Method: A multicentre, randomized, assessor‐blind, parallel‐groups pragmatic trial will involve patients from five large colorectal surgery practices across Canada. The trial will evaluate the impact of an interactive online informational and peer support app for LARS, consisting of LARS informational modules and a closed forum for peers and trained peer support mentors, on patient‐reported outcomes of people living with LARS. The primary outcome will be global QoL at 6 months following app exposure. The treatment effect on global QoL will be modelled using generalized estimating equations. Secondary outcomes will include patient activation and bowel function as measured by LARS scores. Results: In order to better understand patients' interest and preferences for an online peer support intervention for LARS, we conducted a single institution cross‐sectional survey study of rectal cancer survivors. In total, 35/69 (51%) participants reported interest in online peer support for LARS. Age <65 years (OR 9.1; 95% CI 2.3‐50) and minor/major LARS (OR 20; 95% CI 4.2‐100) were significant predictors of interest in LARS online peer support. Conclusion: There is significant interest in the use of online peer support for LARS among younger patients and those with significant bowel dysfunction. Based on results of the needs assessment study, the app content and features were modified reflect patients' needs and preferences. We are now in an optimal position to rigorously test the potential effects of this initiative on patient‐centered outcomes using a randomized controlled trial. [ABSTRACT FROM AUTHOR]

Background: Since screening programs identify only a small proportion of the population as eligible for an intervention, genomic prediction of heritable risk factors could decrease the number needing to be screened by removing individuals at low genetic risk. We therefore tested whether a polygenic risk score for heel quantitative ultrasound speed of sound (SOS)-a heritable risk factor for osteoporotic fracture-can identify low-risk individuals who can safely be excluded from a fracture risk screening program.Methods and Findings: A polygenic risk score for SOS was trained and selected in 2 separate subsets of UK Biobank (comprising 341,449 and 5,335 individuals). The top-performing prediction model was termed "gSOS", and its utility in fracture risk screening was tested in 5 validation cohorts using the National Osteoporosis Guideline Group clinical guidelines (N = 10,522 eligible participants). All individuals were genome-wide genotyped and had measured fracture risk factors. Across the 5 cohorts, the average age ranged from 57 to 75 years, and 54% of studied individuals were women. The main outcomes were the sensitivity and specificity to correctly identify individuals requiring treatment with and without genetic prescreening. The reference standard was a bone mineral density (BMD)-based Fracture Risk Assessment Tool (FRAX) score. The secondary outcomes were the proportions of the screened population requiring clinical-risk-factor-based FRAX (CRF-FRAX) screening and BMD-based FRAX (BMD-FRAX) screening. gSOS was strongly correlated with measured SOS (r2 = 23.2%, 95% CI 22.7% to 23.7%). Without genetic prescreening, guideline recommendations achieved a sensitivity and specificity for correct treatment assignment of 99.6% and 97.1%, respectively, in the validation cohorts. However, 81% of the population required CRF-FRAX tests, and 37% required BMD-FRAX tests to achieve this accuracy. Using gSOS in prescreening and limiting further assessment to those with a low gSOS resulted in small changes to the sensitivity and specificity (93.4% and 98.5%, respectively), but the proportions of individuals requiring CRF-FRAX tests and BMD-FRAX tests were reduced by 37% and 41%, respectively. Study limitations include a reliance on cohorts of predominantly European ethnicity and use of a proxy of fracture risk.Conclusions: Our results suggest that the use of a polygenic risk score in fracture risk screening could decrease the number of individuals requiring screening tests, including BMD measurement, while maintaining a high sensitivity and specificity to identify individuals who should be recommended an intervention. [ABSTRACT FROM AUTHOR]

Complex traits are known to be influenced by a combination of environmental factors and rare and common genetic variants. However, detection of such multivariate associations can be compromised by low statistical power and confounding by population structure. Linear mixed effects models (LMM) can account for correlations due to relatedness but have not been applicable in high-dimensional (HD) settings where the number of fixed effect predictors greatly exceeds the number of samples. False positives or false negatives can result from two-stage approaches, where the residuals estimated from a null model adjusted for the subjects' relationship structure are subsequently used as the response in a standard penalized regression model. To overcome these challenges, we develop a general penalized LMM with a single random effect called ggmix for simultaneous SNP selection and adjustment for population structure in high dimensional prediction models. We develop a blockwise coordinate descent algorithm with automatic tuning parameter selection which is highly scalable, computationally efficient and has theoretical guarantees of convergence. Through simulations and three real data examples, we show that ggmix leads to more parsimonious models compared to the two-stage approach or principal component adjustment with better prediction accuracy. Our method performs well even in the presence of highly correlated markers, and when the causal SNPs are included in the kinship matrix. ggmix can be used to construct polygenic risk scores and select instrumental variables in Mendelian randomization studies. Our algorithms are available in an R package available on CRAN (https://cran.r-project.org/package=ggmix). Author summary: This work addresses a recurring challenge in the analysis and interpretation of genetic association studies: which genetic variants can best predict and are independently associated with a given phenotype in the presence of population structure? Not controlling confounding due to geographic population structure, family and/or cryptic relatedness can lead to spurious associations. Much of the existing research has therefore focused on modeling the association between a phenotype and a single genetic variant in a linear mixed model with a random effect. However, this univariate approach may miss true associations due to the stringent significance thresholds required to reduce the number of false positives and also ignores the correlations between markers. We propose an alternative method for fitting high-dimensional multivariable models, which selects SNPs that are independently associated with the phenotype while also accounting for population structure. We provide an efficient implementation of our algorithm and show through simulation studies and real data examples that our method outperforms existing methods in terms of prediction accuracy and controlling the false discovery rate. [ABSTRACT FROM AUTHOR]

Introduction Low anterior resection syndrome (LARS) is described as disordered bowel function after rectal resection that leads to a detriment in quality of life, and affects the majority of individuals following restorative proctectomy for rectal cancer. The management of LARS includes personalised troubleshooting and effective selfmanagement behaviours. Thus, affected individuals need to be well informed and appropriately engaged in their own LARS management. This manuscript describes the development of a LARS patient-centred programme (LPCP) and the study protocol for its evaluation in a randomised controlled trial. Methods and analysis This will be a multicentre, randomised, assessor-blind, parallel-groups, pragmatic trial evaluating the impact of an LPCP, consisting of an informational booklet, patient diaries and nurse support, on patient-reported outcomes after restorative proctectomy for rectal cancer. The informational booklet was developed by a multidisciplinary LARS team, and was vetted in a focus group and semistructured interviews involving patients, caregivers, and healthcare professionals. The primary outcome will be global quality of life (QoL), as measured by the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire—Core 30 (QLQ-C30), at 6 months after surgery. The treatment effect on global QoL will be modelled using generalised estimating equations. Secondary outcomes include symptom change, patient activation, bowel function measures, emotional distress, knowledge about LARS and satisfaction with the LPCP. Ethics and dissemination The Research Ethics Committee (REC) at the Integrated Health and Social Services Network for West-Central Montreal (health network responsible for the Jewish General Hospital) is the overseeing REC for all Quebec sites. They have granted ethical approval (MP-05-2019-1628) for all Quebec hospitals (Jewish General Hospital, McGill University Health Center, CHU de Quebec) and have granted full authorisation to begin research at the Jewish General Hospital. Patient recruitment will not begin at the other Quebec sites until inter-institutional contracts are finalised and feasibility/authorisation for research is granted by their respective REC. The results of this study will be presented at national and international conferences, and a manuscript with results will be submitted for publication in a high-impact peer-reviewed journal. [ABSTRACT FROM AUTHOR]

Few evidence‐based services exist for people with Autism Spectrum Disorder (ASD) as they transition into adulthood, particularly those that foster appreciation of one's own goals and strengths. We developed a transition service for adults with ASD (without Intellectual Disability), and conducted a randomized controlled trial (RCT) focusing on self‐report of Quality of Life and Self‐Determination outcomes. Thirty participants aged 18–29 were randomized to immediate or delayed intervention, with 26 participants analyzed after 4 were lost to follow‐up. Curriculum was tailored to participants' self‐expressed needs in three areas: social communication, self‐determination, and working with others. Groups of four‐to‐six participants with ASD and two facilitators met weekly for 10 weeks. Positive intervention effects were observed on self‐report of Quality of Life; the intervention group scored on average 2 points higher than the control group, 95% CI [−0.2, 3.9]. Positive effects were also observed on the Self Determination Scale (Interpersonal Cognitive Problem‐Solving subdomain), where the intervention group scored 2 points higher than control group 95% CI [0.082, 3.4]. In addition, participants rated skills targeted by the curriculum 6 points higher after versus before intervention, 95% CI [3.7, 8.6]. This was echoed by a subset of parents rating their child's skills as seven points higher after versus before intervention, 95% CI [1, 14]. Autism Research2018, 11: 1712–1728. © 2018 International Society for Autism Research, Wiley Periodicals, Inc. Lay Summary: These findings indicate that it is possible to increase Self‐Determination and subjective Quality of Life in adults with ASD through a brief group‐format service, and provide a model for doing so. Self‐Determination abilities are linked to improved adult outcomes in individuals with other disabilities. These often overlooked factors should be incorporated in programming for adults with ASD as they transition to adulthood. [ABSTRACT FROM AUTHOR]

Background: We investigated whether visceral adiposity is associated with more aggressive disease at prostatectomy. Materials and methods: Four hundred and seventy-four patients referred for postoperative adjuvant or salvage radiotherapy were included in this study. Primary endpoints were positive surgical margins (pSM) or extracapsular extension (ECE). Visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) were manually contoured. Univariate and multivariate logistic regression was performed. Results: In univariate analysis, VAT volume (p = 0.006), adipose tissue ratio (VAT/SAT, p = 0.003), density of the SAT (p = 0.04), as well as age (p < 0.001) were associated with pSM. In the univariate analysis, SAT density was associated with a trend towards a higher rate of ECE (p = 0.051) but visceral fat volume (p = 0.01), as well as the adipose tissue ratio (p = 0.03) were both protective factors. None of the adipose tissue measurements or BMI had an influence on biochemical recurrence or overall survival (all p ≥ 0.5). Conclusions: SAT-volume and increased SAT-density were generally associated with more aggressive prostate cancers whereas VAT as a protective factor. These findings emphasize a possible mechanism for the association between obesity and prostate cancer aggressiveness. [ABSTRACT FROM AUTHOR]

Objectives To identify molecular differences between chondrocytes from osteophytic and articular cartilage tissue from OA patients. Methods We investigated genes and pathways by combining genome-wide DNA methylation, RNA sequencing and quantitative proteomics in isolated primary chondrocytes from the cartilaginous layer of osteophytes and matched areas of low- and high-grade articular cartilage across nine patients with OA undergoing hip replacement surgery. Results Chondrocytes from osteophytic cartilage showed widespread differences to low-grade articular cartilage chondrocytes. These differences were similar to, but more pronounced than, differences between chondrocytes from osteophytic and high-grade articular cartilage, and more pronounced than differences between high- and low-grade articular cartilage. We identified 56 genes with significant differences between osteophytic chondrocytes and low-grade articular cartilage chondrocytes on all three omics levels. Several of these genes have known roles in OA, including ALDH1A2 and cartilage oligomeric matrix protein, which have functional genetic variants associated with OA from genome-wide association studies. An integrative gene ontology enrichment analysis showed that differences between osteophytic and low-grade articular cartilage chondrocytes are associated with extracellular matrix organization, skeletal system development, platelet aggregation and regulation of ERK1 and ERK2 cascade. Conclusion We present a first comprehensive view of the molecular landscape of chondrocytes from osteophytic cartilage as compared with articular cartilage chondrocytes from the same joints in OA. We found robust changes at genes relevant to chondrocyte function, providing insight into biological processes involved in osteophyte development and thus OA progression. [ABSTRACT FROM AUTHOR]

In a variety of solid cancers, missense mutations in the well-established TP53 tumor suppressor gene may lead to the presence of a partially-functioning protein molecule, whereas mutations affecting the protein encoding reading frame, often referred to as null mutations, result in the absence of p53 protein. Both types of mutations have been observed in the same cancer type. As the resulting tumor biology may be quite different between these two groups, we used RNA-sequencing data from The Cancer Genome Atlas (TCGA) from four different cancers with poor prognosis, namely ovarian, breast, lung and skin cancers, to compare the patterns of coexpression of genes in tumors grouped according to their TP53 missense or null mutation status. We used Weighted Gene Coexpression Network analysis (WGCNA) and a new test statistic built on differences between groups in the measures of gene connectivity. For each cancer, our analysis identified a set of genes showing differential coexpression patterns between the TP53 missense- and null mutation-carrying groups that was robust to the choice of the tuning parameter in WGCNA. After comparing these sets of genes across the four cancers, one gene (KIR3DL2) consistently showed differential coexpression patterns between the null and missense groups. KIR3DL2 is known to play an important role in regulating the immune response, which is consistent with our observation that this gene's strongly-correlated partners implicated many immune-related pathways. Examining mutation-type-related changes in correlations between sets of genes may provide new insight into tumor biology. [ABSTRACT FROM AUTHOR]

Interactions between genes and environmental factors may play a key role in the etiology of many common disorders. Several regularized generalized linear models have been proposed for hierarchical selection of gene by environment interaction effects, where a gene-environment interaction effect is selected only if the corresponding genetic main effect is also selected in the model. However, none of these methods allow to include random effects to account for population structure, subject relatedness and shared environmental exposure. In this article, we develop a unified approach based on regularized penalized quasi-likelihood estimation to perform hierarchical selection of gene-environment interaction effects in sparse regularized mixed models. We compare the selection and prediction accuracy of our proposed model with existing methods through simulations under the presence of population structure and shared environmental exposure. We show that for all simulation scenarios, including and additional random effect to account for the shared environmental exposure reduces the false positive rate and false discovery rate of our proposed method for selection of both gene-environment interaction and main effects. Using the F 1 score as a balanced measure of the false discovery rate and true positive rate, we further show that in the hierarchical simulation scenarios, our method outperforms other methods for retrieving important gene-environment interaction effects. Finally, we apply our method to a real data application using the Orofacial Pain: Prospective Evaluation and Risk Assessment (OPPERA) study, and found that our method retrieves previously reported significant loci. [ABSTRACT FROM AUTHOR]

Simple Summary: Head and neck squamous cell carcinoma (HNSCC) is the most common mucosal malignancy of the head and neck and a leading cause of cancer death. HNSCC arises from different primary anatomical locations that are typically combined during radiomic analyses assuming that the radiomic features, i.e., quantitative image-based features, are similar based on histopathologic characteristics. However, whether these quantitative features are comparable across tumor sites remains unknown. The aim of our retrospective study was to assess if systematic differences exist between radiomic features based on different tumor sites in HNSCC and how they might affect machine learning model performance in endpoint prediction. Using a population of 605 HNSCC patients, we observed significant differences in radiomic features of tumors from different locations and showed that these differences can impact machine learning model performance. This suggests that tumor site should be considered when developing and evaluating radiomics-based models. Current radiomic studies of head and neck squamous cell carcinomas (HNSCC) are typically based on datasets combining tumors from different locations, assuming that the radiomic features are similar based on histopathologic characteristics. However, molecular pathogenesis and treatment in HNSCC substantially vary across different tumor sites. It is not known if a statistical difference exists between radiomic features from different tumor sites and how they affect machine learning model performance in endpoint prediction. To answer these questions, we extracted radiomic features from contrast-enhanced neck computed tomography scans (CTs) of 605 patients with HNSCC originating from the oral cavity, oropharynx, and hypopharynx/larynx. The difference in radiomic features of tumors from these sites was assessed using statistical analyses and Random Forest classifiers on the radiomic features with 10-fold cross-validation to predict tumor sites, nodal metastasis, and HPV status. We found statistically significant differences (p-value ≤ 0.05) between the radiomic features of HNSCC depending on tumor location. We also observed that differences in quantitative features among HNSCC from different locations impact the performance of machine learning models. This suggests that radiomic features may reveal biologic heterogeneity complementary to current gold standard histopathologic evaluation. We recommend considering tumor site in radiomic studies of HNSCC. [ABSTRACT FROM AUTHOR]

• GPT-4o & LLaMA 3-70b demonstrated comparable diagnostic accuracy in radiology. • No significant performance gap was observed between GPT-4o and LLaMA 70-b. • LLaMA 3-70b is competitive with GPT-4o, though generalizability is limited. • Open-source LLaMA 3-70b offers a cost-effective alternative to proprietary GPT-4o. [ABSTRACT FROM AUTHOR]