Improving diagnostic precision in amyloid brain PET imaging through data-driven motion correction.

BACKGROUND: Head motion during brain positron emission tomography (PET)/computed tomography (CT) imaging degrades image quality, resulting in reduced reading accuracy. We evaluated the performance of a head motion correction algorithm using 18F-flutemetamol (FMM) brain PET/CT images. METHODS: FMM brain PET/CT images were retrospectively included, and PET images were reconstructed using a motion correction algorithm: (1) motion estimation through 3D time-domain signal analysis, signal smoothing, and calculation of motion-free intervals using a Merging Adjacent Clustering method; (2) estimation of 3D motion transformations using the Summing Tree Structural algorithm; and (3) calculation of the final motion-corrected images using the 3D motion transformations during the iterative reconstruction process. All conventional and motion-corrected PET images were visually reviewed by two readers. Image quality was evaluated using a 3-point scale, and the presence of amyloid deposition was interpreted as negative, positive, or equivocal. For quantitative analysis, we calculated the uptake ratio (UR) of 5 specific brain regions, with the cerebellar cortex as a reference region. The results of the conventional and motion-corrected PET images were statistically compared. RESULTS: In total, 108 sets of FMM brain PET images from 108 patients (34 men and 74 women; median age, 78 years) were included. After motion correction, image quality significantly improved (p < 0.001), and there were no images of poor quality. In the visual analysis of amyloid deposition, higher interobserver agreements were observed in motion-corrected PET images for all specific regions. In the quantitative analysis, the UR difference between the conventional and motion-corrected PET images was significantly higher in the group with head motion than in the group without head motion (p = 0.016). CONCLUSIONS: The motion correction algorithm provided better image quality and higher interobserver agreement. Therefore, we suggest that this algorithm be adopted as a routine post-processing protocol in amyloid brain PET/CT imaging and applied to brain PET scans with other radiotracers.

Milk Consumption and Its Association with Dental Caries: Gender-Specific Insights from the Korea National Health and Nutrition Examination Survey (2013-2015).

Background and Objectives: This study aims to bridge these gaps by utilizing data from the Korea National Health and Nutrition Examination Survey (2013-2015), examining the nuanced associations between milk consumption's quantity, frequency, and type and the prevalence of dental caries. Materials and Methods: Utilizing data from the Korea National Health and Nutrition Examination Survey (2013-2015), this study explores the association between milk consumption and the prevalence of dental caries in a sample of 4843 subjects (weighted n = 15,581), including 2856 males and 1987 females; weighted sample sizes were 6656 and 8925 for men and women, respectively. The prevalence of dental caries was assessed by evaluating the number of decayed, filled, and missing teeth. Results: The analysis demonstrated a significant positive association between increased milk consumption and the risk of developing dental caries, with an overall odds ratio of 1.653 (95% CI: 1.153-2.370, p < 0.05). The association was more pronounced in females, exhibiting an odds ratio of 1.865 (95% CI: 1.157-3.006, p < 0.05), and age was identified as a significant variable, particularly among participants aged 50 and above. In contrast, the relationship among the male group, though positive (odds ratio: 1.613, 95% CI: 0.991-2.625), was not statistically significant (p = 0.054). Conclusion: These findings suggest that milk consumption may be a potential risk indicator for dental caries, particularly among women, emphasizing the need for targeted dietary recommendations in dental health practices.

Change in Maxillary Sinus Mucosal Thickness in Patients with Preoperative Maxillary Sinus Mucosal Thickening as Assessed by Otolaryngologists: A Retrospective Study.

Background and Objectives: Maxillary sinus pathologic conditions may increase the risk of complications during posterior maxillary sinus augmentation surgery. The purpose of this study was to evaluate the changes in participants with preoperative maxillary sinus mucosal thickening and to assess this factor as a preoperative risk indicator for sinusitis after maxillary dental implantation. Materials and Methods: We compared the preoperative and postoperative maxillary sinus mucosal thickness (MSMT), the distance between the maxillary sinus ostium and sinus floor (MOD), and the MSMT/MOD ratio. The participants were divided into three groups (sinus augmentation, bone grafting, and no grafting). Results: The mean preoperative MSMT was 4.3 ± 2.0 mm, and the mean MSMT/MOD ratio was 0.13 ± 0.05. No postoperative sinusitis was observed in these patients, including cases caused by anatomical variations. The mean postoperative MSMT was 4.5 ± 2.3 mm, and the mean postoperative MSMT/MOD ratio was 0.15 ± 0.06. There was no statistically significant difference between the groups at each time point (p > 0.05). Conclusions: The study found no significant change in MSMT at post-treatment evaluation, even when considering different subgroups. It underscores the importance of preoperative maxillary sinus radiographic assessments and collaboration between dentists and otolaryngologists for better outcomes in patients with preoperative maxillary sinus mucosal thickening.

Machine learning models for predicting depression in Korean young employees.

Background: The incidence of depression among employees has gradually risen. Previous studies have focused on predicting the risk of depression, but most studies were conducted using basic statistical methods. This study used machine learning algorithms to build models that detect and identify the important factors associated with depression in the workplace. Methods: A total of 503 employees completed an online survey that included questionnaires on general characteristics, physical health, job-related factors, psychosocial protective, and risk factors in the workplace. The dataset contained 27 predictor variables and one dependent variable which referred to the status of employees (normal or at the risk of depression). The prediction accuracy of three machine learning models using sparse logistic regression, support vector machine, and random forest was compared with the accuracy, precision, sensitivity, specificity, and AUC. Additionally, the important factors identified via sparse logistic regression and random forest. Results: All machine learning models demonstrated similar results, with the lowest accuracy obtained from sparse logistic regression and support vector machine (86.8%) and the highest accuracy from random forest (88.7%). The important factors identified in this study were gender, physical health, job, psychosocial protective factors, and psychosocial risk and protective factors in the workplace. Discussion: The results of this study indicated the potential of machine learning models to accurately predict the risk of depression among employees. The identified factors that influence the risk of depression can contribute to the development of intelligent mental healthcare systems that can detect early signs of depressive symptoms in the workplace.

CT Scan Differences of Pulmonary TB According to Presence of Pleural Effusion.

BACKGROUND: Subpleural micronodules and interlobular septal thickening are common CT scan findings in TB pleural effusion. These CT scan features could help us differentiate between TB pleural effusion and nonTB empyema. RESEARCH QUESTION: Does the frequency of subpleural micronodules and interlobular septal thickening correlate with the presence of pleural effusion in patients with pulmonary TB? STUDY DESIGN AND METHODS: CT scan findings of pulmonary TB, micronodules and their distribution (peribronchovascular, septal, subpleural, centrilobular, and random), large opacity (consolidation/macronodule), cavitation, tree-in-buds, bronchovascular bundle thickening, interlobular septal thickening, lymphadenopathy, and pleural effusion were retrospectively analyzed. Patients were divided into two groups according to the presence of pleural effusion. Clinicoradiologic findings of the two groups were then analyzed. We presented Benjamini-Hochberg critical value for multiple testing correction of CT scan findings, with a false discovery rate of 0.05. RESULTS: Of a total of 338 consecutive patients diagnosed with pulmonary TB who underwent CT scans, 60 were excluded because of coexisting pulmonary diseases. The frequency of subpleural nodules (47/68, 69% in pulmonary TB with pleural effusion vs 30/210, 14% in pulmonary TB without effusion, P < .001, Benjamini-Hochberg [B-H] critical value = 0.0036) and interlobular septal thickening (55/68, 81% vs 134/210, 64%, P = .009, B-H critical value = 0.0107) was significantly higher in the group of patients with pulmonary TB with pleural effusion than in the group without pleural effusion. In contrast, tree-in-buds (20/68, 29% vs 101/210, 48%, P = .007, B-H critical value = 0.0071) were less frequently seen in patients with pulmonary TB with pleural effusion. INTERPRETATION: Subpleural nodules and septal thickening were more common in pulmonary TB patients with pleural effusion than in those without pleural effusion. TB involvement of the lymphatics in the peripheral interstitium could be associated with the development of pleural effusion.

Evaluation of the Association between Amount and Type of Milk Consumption and Periodontitis: Data from the Korea National Health and Nutrition Examination Survey (2016-2018).

This study evaluated the association between the consumption of milk and having severe periodontitis. It is based on the information from the 2016-2018 Korea National Health and Nutrition Examination Survey. Severe periodontitis was characterized as a community periodontal index of code 4. A total of 18,034 individual respondents (7835 men and 10,199 women) without missing values were included in this study. Adjusted odds ratios and a 95% confidence interval of periodontitis in a multivariate logistic regression model for the amount of milk consumption were 0.774 [0.633-0.945] after the adjustment of confounding factors. This trend was maintained in a subgroup analysis of males with adjusted odds ratios, with a 95% confidence interval of 0.705 [0.538-0.924]. Overall, the findings showed a negative association between Korean adults' milk consumption and the prevalence of severe periodontitis. Men with higher milk consumption were more likely to have a lower prevalence of severe periodontitis regardless of age, body mass index, smoking or drinking habits, education, income, region, and physical exercise, diabetes mellitus, hypertension, metabolic syndrome, white blood cell count and toothbrushing frequency. By contrast, in women, the amount of milk consumption was not significantly associated with severe periodontitis. The amount of milk consumed was discovered to be a potential risk indicator for severe periodontitis in men in this study.

Machine learning models for predicting risk of depression in Korean college students: Identifying family and individual factors.

Background: Depression is one of the most prevalent mental illnesses among college students worldwide. Using the family triad dataset, this study investigated machine learning (ML) models to predict the risk of depression in college students and identify important family and individual factors. Methods: This study predicted college students at risk of depression and identified significant family and individual factors in 171 family data (171 fathers, mothers, and college students). The prediction accuracy of three ML models, sparse logistic regression (SLR), support vector machine (SVM), and random forest (RF), was compared. Results: The three ML models showed excellent prediction capabilities. The RF model showed the best performance. It revealed five significant factors responsible for depression: self-perceived mental health of college students, neuroticism, fearful-avoidant attachment, family cohesion, and mother's depression. Additionally, the logistic regression model identified five factors responsible for depression: the severity of cancer in the father, the severity of respiratory diseases in the mother, the self-perceived mental health of college students, conscientiousness, and neuroticism. Discussion: These findings demonstrated the ability of ML models to accurately predict the risk of depression and identify family and individual factors related to depression among Korean college students. With recent developments and ML applications, our study can improve intelligent mental healthcare systems to detect early depressive symptoms and increase access to mental health services.

Multi-task learning based structured sparse canonical correlation analysis for brain imaging genetics.

The advances in technologies for acquiring brain imaging and high-throughput genetic data allow the researcher to access a large amount of multi-modal data. Although the sparse canonical correlation analysis is a powerful bi-multivariate association analysis technique for feature selection, we are still facing major challenges in integrating multi-modal imaging genetic data and yielding biologically meaningful interpretation of imaging genetic findings. In this study, we propose a novel multi-task learning based structured sparse canonical correlation analysis (MTS2CCA) to deliver interpretable results and improve integration in imaging genetics studies. We perform comparative studies with state-of-the-art competing methods on both simulation and real imaging genetic data. On the simulation data, our proposed model has achieved the best performance in terms of canonical correlation coefficients, estimation accuracy, and feature selection accuracy. On the real imaging genetic data, our proposed model has revealed promising features of single-nucleotide polymorphisms and brain regions related to sleep. The identified features can be used to improve clinical score prediction using promising imaging genetic biomarkers. An interesting future direction is to apply our model to additional neurological or psychiatric cohorts such as patients with Alzheimer's or Parkinson's disease to demonstrate the generalizability of our method.

Sparse linear discriminant analysis for multiview structured data.

Classification methods that leverage the strengths of data from multiple sources (multiview data) simultaneously have enormous potential to yield more powerful findings than two-step methods: association followed by classification. We propose two methods, sparse integrative discriminant analysis (SIDA), and SIDA with incorporation of network information (SIDANet), for joint association and classification studies. The methods consider the overall association between multiview data, and the separation within each view in choosing discriminant vectors that are associated and optimally separate subjects into different classes. SIDANet is among the first methods to incorporate prior structural information in joint association and classification studies. It uses the normalized Laplacian of a graph to smooth coefficients of predictor variables, thus encouraging selection of predictors that are connected. We demonstrate the effectiveness of our methods on a set of synthetic datasets and explore their use in identifying potential nontraditional risk factors that discriminate healthy patients at low versus high risk for developing atherosclerosis cardiovascular disease in 10 years. Our findings underscore the benefit of joint association and classification methods if the goal is to correlate multiview data and to perform classification.

Uptake and Survival Outcomes Following Immune Checkpoint Inhibitor Therapy Among Trial-Ineligible Patients With Advanced Solid Cancers.

IMPORTANCE: Immune checkpoint inhibitors (ICIs) are part of standard of care for patients with many advanced solid tumors. Patients with poor performance status or organ dysfunction are traditionally ineligible to partake in pivotal randomized clinical trials of ICIs. OBJECTIVE: To assess ICI use and survival outcomes among patients with advanced cancers who are traditionally trial ineligible based on poor performance status or organ dysfunction. DESIGN, SETTING, AND PARTICIPANTS: This retrospective cohort study was conducted in 280 predominantly community oncology practices in the US and included 34 131 patients (9318 [27.3%] trial ineligible) who initiated first-line systemic therapy from January 2014 through December 2019 for newly diagnosed metastatic or recurrent nontargetable non-small cell lung, urothelial cell, renal cell, or hepatocellular carcinoma. Data analysis was performed from December 1, 2019, to June 1, 2021. EXPOSURES: Trial ineligibility (Eastern Cooperative Oncology Group performance status ≥2 or the presence of kidney or liver dysfunction); first-line systemic therapy. MAIN OUTCOMES AND MEASURES: The association between trial ineligibility and ICI monotherapy uptake was assessed using inverse probability-weighted (IPW) logistic regressions. The comparative survival outcomes following ICI and non-ICI therapy among trial-ineligible patients were assessed using treatment IPW survival analyses. Because we observed nonproportional hazards, we reported 12-month and 36-month restricted mean survival times (RMSTs) and time-varying hazard ratios (HRs) of less than 6 months and 6 months or greater. RESULTS: Among the overall cohort (n = 34 131), the median (IQR) age was 70 (62-77) years; 23 586 (69%) were White individuals, and 14 478 (42%) were women. Over the study period, the proportion of patients receiving ICI monotherapy increased from 0% to 30.2% among trial-ineligible patients and 0.1% to 19.4% among trial-eligible patients. Trial ineligibility was associated with increased ICI monotherapy use (IPW-adjusted odds ratio compared with non-ICI therapy, 1.8; 95% CI, 1.7-1.9). Among trial-ineligible patients, there were no overall survival differences between ICI monotherapy, ICI combination therapy, and non-ICI therapy at 12 months (RMST, 7.8 vs 7.7 vs 8.1 months) or 36 months (RMST, 15.0 vs 13.9 vs 14.4 months). Compared with non-ICI therapy, ICI monotherapy showed evidence of early harm (IPW-adjusted HR within 6 months, 1.2; 95% CI, 1.1-1.2) but late benefit (adjusted HR among patients who survived 6 months, 0.8; 95% CI, 0.7-0.8). CONCLUSIONS AND RELEVANCE: In this cohort study, compared with trial-eligible patients, trial-ineligible patients with advanced cancers preferentially received first-line ICI therapy. A survival difference was not detected between ICI and non-ICI therapies among trial-ineligible patients. Positive results for ICI in phase 3 trials may not translate to this vulnerable population.

Blood-based gene expression signature associated with metastatic castrate-resistant prostate cancer patient response to abiraterone plus prednisone or enzalutamide.

BACKGROUND: Precision medicine approaches for managing patients with metastatic castrate-resistant prostate cancer (mCRPC) are lacking. Non-invasive approaches for molecular monitoring of disease are urgently needed, especially for patients suffering from bone metastases for whom tissue biopsy is challenging. Here we utilized baseline blood samples to identify mCRPC patients most likely to benefit from abiraterone plus prednisone (AAP) or enzalutamide. METHODS: Baseline blood samples were collected for circulating tumor cell (CTC) enumeration and qPCR-based gene expression analysis from 51 men with mCRPC beginning treatment with abiraterone or enzalutamide. RESULTS: Of 51 patients (median age 68 years [51-82]), 22 received AAP (abiraterone 1000 mg/day plus prednisone 10 mg/day) and 29 received enzalutamide (160 mg/day). The cohort was randomly divided into training (n = 37) and test (n = 14) sets. Baseline clinical variables (Gleason score, PSA, testosterone, and hemoglobin), CTC count, and qPCR-based gene expression data for 141 genes/isoforms in CTC-enriched blood were analyzed with respect to overall survival (OS). Genes with expression most associated with OS included MSLN, ARG2, FGF8, KLK3, ESRP2, NPR3, CCND1, and WNT5A. Using a Cox-elastic net model for our test set, the 8-gene expression signature had a c-index of 0.87 (95% CI [0.80, 0.94]) and was more strongly associated with OS than clinical variables or CTC count alone, or a combination of the three variables. For patients with a low-risk vs. high-risk gene expression signature, median OS was not reached vs. 18 months, respectively (HR 5.32 [1.91-14.80], p = 0.001). For the subset of 41 patients for whom progression-free survival (PFS) data was available, the median PFS for patients with a low-risk vs high-risk gene expression signature was 20 vs. 5 months, respectively (HR 2.95 [1.46-5.98], p = 0.003). CONCLUSIONS: If validated in a larger prospective study, this test may predict patients most likely to benefit from second-generation antiandrogen therapy.

Tensor canonical correlation analysis.

Canonical correlation analysis (CCA) is a multivariate analysis technique for estimating a linear relationship between two sets of measurements. Modern acquisition technologies, for example, those arising in neuroimaging and remote sensing, produce data in the form of multidimensional arrays or tensors. Classic CCA is not appropriate for dealing with tensor data due to the multidimensional structure and ultrahigh dimensionality of such modern data. In this paper, we present tensor CCA (TCCA) to discover relationships between two tensors while simultaneously preserving multidimensional structure of the tensors and utilizing substantially fewer parameters. Furthermore, we show how to employ a parsimonious covariance structure to gain additional stability and efficiency. We delineate population and sample problems for each model and propose efficient estimation algorithms with global convergence guarantees. Also we describe a probabilistic model for TCCA that enables the generation of synthetic data with desired canonical variates and correlations. Simulation studies illustrate the performance of our methods.

Sparse multiple co-Inertia analysis with application to integrative analysis of multi -Omics data.

BACKGROUND: Multiple co-inertia analysis (mCIA) is a multivariate analysis method that can assess relationships and trends in multiple datasets. Recently it has been used for integrative analysis of multiple high-dimensional -omics datasets. However, its estimated loading vectors are non-sparse, which presents challenges for identifying important features and interpreting analysis results. We propose two new mCIA methods: 1) a sparse mCIA method that produces sparse loading estimates and 2) a structured sparse mCIA method that further enables incorporation of structural information among variables such as those from functional genomics. RESULTS: Our extensive simulation studies demonstrate the superior performance of the sparse mCIA and structured sparse mCIA methods compared to the existing mCIA in terms of feature selection and estimation accuracy. Application to the integrative analysis of transcriptomics data and proteomics data from a cancer study identified biomarkers that are suggested in the literature related with cancer disease. CONCLUSION: Proposed sparse mCIA achieves simultaneous model estimation and feature selection and yields analysis results that are more interpretable than the existing mCIA. Furthermore, proposed structured sparse mCIA can effectively incorporate prior network information among genes, resulting in improved feature selection and enhanced interpretability.

Is the age of diagnosis of esophageal adenocarcinoma getting younger? Analysis at a tertiary care center.

There are emerging data that patients <50 years are diagnosed with esophageal adenocarcinoma (EAC) more frequently, suggesting that the age threshold for screening should be revisited. This study aimed to determine the age distribution, outcomes, and clinical features of EAC over time. The pathology database at the Hospital of the University of Pennsylvania was reviewed from 1991 to 2018. The electronic health records and pathology were reviewed for age of diagnosis, pathology grade, race, and gender for a cohort of 630 patients with biopsy proven EAC. For the patients diagnosed from 2009 to 2018, the Penn Abramson Cancer Center Registry was reviewed for survival and TNM stage. Of the 630 patients, 10.3% (65 patients) were <50 years old [median 43 years, range 16-49]. There was no increase in the number of patients <50 years diagnosed with EAC (R = 0.133, P = 0.05). Characteristics of those <50 years versus >50 years showed no difference in tumor grade. Among the 179 eligible patients in the cancer registry, there was no significant difference in clinical or pathological stage for patients <50 years (P value = 0.18). There was no association between diagnosis age and survival (P = 0.24). A substantial subset of patients with EAC is diagnosed at <50 years. There was no increasing trend of EAC in younger cohorts from 1991 to 2018. We could not identify more advanced stage tumors in the younger cohort. There was no significant association between diagnosis age and survival.

Early Tumor and Nodal Response in Patients with Locally Advanced Non-Small Cell Lung Carcinoma Predict for Oncologic Outcomes in Patients Treated with Concurrent Proton Therapy and Chemotherapy.

PURPOSE: There are no established imaging biomarkers that predict response during chemoradiation for patients with locally advanced non-small cell lung carcinoma. At our institution, proton therapy (PT) patients undergo repeat computed tomography (CT) simulations twice during radiation. We hypothesized that tumor regression measured on these scans would separate early and late responders and that early response would translate into better outcomes. METHODS AND MATERIALS: Patients underwent CT simulations before starting PT (CT0) and between weeks 1 to 3 (CT1) and weeks 4 to 7 (CT2) of PT. Primary tumor volume (TVR) and nodal volume (NVR) reduction were calculated at CT1 and CT2. Based on recursive partitioning analysis, early response at CT1 and CT2 was defined as ≥20% and ≥40%, respectively. Locoregional and overall progression-free survival (PFS), distant metastasis-free survival, and overall survival by response status were measured using Kaplan-Meier analysis. RESULTS: Ninety-seven patients with locally advanced non-small cell lung carcinoma underwent definitive PT to a median dose of 66.6 Gy with concurrent chemotherapy. Median TVR and NVR at CT1 were 19% (0-79%) and 19% (0-75%), respectively. At CT2, they were 33% (2-98%) and 35% (0-89%), respectively. With a median follow-up of 25 months, the median overall survival and PFS for the entire cohort was 24.9 and 13.2 months, respectively. Compared with patients with TVR and NVR <20% at T1 and <40% at T2, patients with TVR and NVR ≥20% at CT1 and ≥40% at CT2 had improved median locoregional PFS (27.15 vs 12.97 months for TVR ≥40% vs <40%, P < .01, and 25.67 vs 12.09 months for NVR ≥40% vs <40%, P < .01) and median PFS (22.7 vs 9.2 months, P < .01, and 20.3 vs 7.9 months, P < .01), confirmed on multivariate Cox regression analysis. CONCLUSIONS: Significantly improved outcomes in patients with early responses to therapy, as measured by TVR and NVR, were seen. Further study is warranted to determine whether treatment intensification will improve outcomes in slow-responding patients.

Difference in Cognitive Function by First Onset Age of Alcohol Induced Blackout and Its Duration.

OBJECTIVE: Alcohol-induced blackout (blackout) is a typical early symptom of cognitive impairment caused by drinking. However, the first onset age of blackout or the duration after onset of blackout has not been directly compared in previous studies. The purpose of this study was to investigate the differences in cognitive function to the first start age of blackouts and their duration. METHODS: Thirty-one male subjects were included in this study. Their age at the first blackout and the duration after the onset of blackout were investigated. Neuropsychological tests were conducted to determine their attention, memory, and executive function. Subjects were divided into three groups according to their age of the first onset blackout (group O1, < 20 years; group O2, 21-39 years; and group O3, > 40 years). Subjects were also divided into three groups by duration after the onset of blackout (P1, < 10 years; P2, 10-29 years; and P3, > 30 years). We then examined differences in neurocognitive function among these groups. RESULTS: O1 tended to have a lower memory score than O2 (F = 3.28, p = 0.053). Significant differences were observed in attention and executive function between groups P1 and P3 (Digit Span_backward: F = 6.07, p < 0.05; visual span_forward: F = 4.19, p < 0.05; executive intelligence quotient: F = 3.55, p < 0.05). CONCLUSION: Greater memory impairment was detected in subjects having an earlier age of the first blackout. The longer the duration after the onset of blackout, the more impaired their attention and executive function skills.

Four-Year Outcomes From a Prospective Phase II Clinical Trial of Moderately Hypofractionated Proton Therapy for Localized Prostate Cancer.

PURPOSE: Moderately hypofractionated radiation therapy represents an effective treatment for localized prostate cancer (PC). Although large randomized trials have reported the efficacy of photon-based hypofractionated therapy, hypofractionated proton therapy (HFPT) has not been extensively studied. This study was performed to determine the clinical and patient-reported outcomes for patients with PC treated with HFPT. METHODS AND MATERIALS: Between 2010 and 2017, 184 men were enrolled on a trial of 70 Gy in 28 fractions of HFPT for low- to intermediate-risk PC. Acute and late toxicity was evaluated using National Cancer Institute Common Terminology Criteria for Adverse Events version 4.0. Patient-reported outcomes were measured by International Prostate Symptom Score, International Index of Erectile Function Questionnaire, and Expanded Prostate Cancer Index Composite scores. RESULTS: Median follow-up was 49.2 months. Enrolled patients had low-risk (n = 18), favorable intermediate-risk (n = 78), and unfavorable intermediate-risk (n = 88) PC. Four-year rates of biochemical-clinical failure-free survival were 93.5% (95% confidence interval, 89%-98%), 94.4% (89%-100%), 92.5% (86%-100%), and 93.8% (88%-100%) in the overall group and the low-risk, favorable intermediate-risk, and unfavorable intermediate-risk cohorts, respectively (log-rank P > .4). The incidence of acute grade 2 or higher gastrointestinal (GI) and urologic toxicities were 3.8% and 12.5%, respectively. The 4-year incidence of late grade 2 or higher urologic and GI toxicity was 7.6% (4%-13%) and 13.6% (9%-20%), respectively. One late grade 3 GI toxicity was reported. All late toxicities were transient. Patient-reported International Prostate Symptom, International Index of Erectile Function, and Expanded Prostate Cancer Index Composite scores had no significant long-term changes after completion of HFPT (Supplementary Table 1, available at https://doi.org/10.1016/j.ijrobp.2019.05.069). CONCLUSIONS: HFPT is associated with low rates of toxicity and does not appear to negatively affect 4-year patient reported urinary and bowel health. Further comparative analyses are warranted to better understand differences between proton and photon HFRT.

Knowledge-Guided Biclustering via Sparse Variational EM Algorithm.

A biclustering in the analysis of a gene expression data matrix, for example, is defined as a set of biclusters where each bicluster is a group of genes and a group of samples for which the genes are differentially expressed. Although many data mining approaches for biclustering exist in the literature, only few are able to incorporate prior knowledge to the analysis, which can lead to great improvements in terms of accuracy and interpretability, and all are limited in handling discrete data types. We propose a generalized biclustering approach that can be used for integrative analysis of multi-omics data with different data types. Our method is capable of utilizing biological information that can be represented by graph such as functional genomics and functional proteomics and accommodating a combination of continuous and discrete data types. The proposed method builds on a generalized Bayesian factor analysis framework and a variational EM approach is used to obtain parameter estimates, where the latent quantities in the loglikelihood are iteratively imputed by their conditional expectations. The biclusters are retrieved via the sparse estimates of the factor loadings and the conditional expectation of the latent factors. In order to obtain the sparse conditional expectation of the latent factors, a novel sparse variational EM algorithm is used. We demonstrate the superiority of our method over several existing biclustering methods in extensive simulation experiements and in integrative analysis of multi-omics data.

Penalized co-inertia analysis with applications to -omics data.

MOTIVATION: Co-inertia analysis (CIA) is a multivariate statistical analysis method that can assess relationships and trends in two sets of data. Recently CIA has been used for an integrative analysis of multiple high-dimensional omics data. However, for classical CIA, all elements in the loading vectors are nonzero, presenting a challenge for the interpretation when analyzing omics data. For other multivariate statistical methods such as canonical correlation analysis (CCA), penalized least squares (PLS), various approaches have been proposed to produce sparse loading vectors via l1-penalization/constraint. We propose a novel CIA method that uses l1-penalization to induce sparsity in estimators of loading vectors. Our method simultaneously conducts model fitting and variable selection. Also, we propose another CIA method that incorporates structure/network information such as those from functional genomics, besides using sparsity penalty so that one can get biologically meaningful and interpretable results. RESULTS: Extensive simulations demonstrate that our proposed penalized CIA methods achieve the best or close to the best performance compared to the existing CIA method in terms of feature selection and recovery of true loading vectors. Also, we apply our methods to the integrative analysis of gene expression data and protein abundance data from the NCI-60 cancer cell lines. Our analysis of the NCI-60 cancer cell line data reveals meaningful variables for cancer diseases and biologically meaningful results that are consistent with previous studies. AVAILABILITY AND IMPLEMENTATION: Our algorithms are implemented as an R package which is freely available at: https://www.med.upenn.edu/long-lab/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.