OBJECTIVE: Neoadjuvant chemoradiotherapy has been the standard practice for patients with locally advanced rectal cancer. However, the treatment response varies greatly among individuals, how to select the optimal candidates for neoadjuvant chemoradiotherapy is crucial. This study aimed to develop an endoscopic image-based deep learning model for predicting the response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer.
METHODS: In this multicenter observational study, pre-treatment endoscopic images of patients from two Chinese medical centers were retrospectively obtained and a deep learning-based tumor regression model was constructed. Treatment response was evaluated based on the tumor regression grade and was defined as good response and non-good response. The prediction performance of the deep learning model was evaluated in the internal and external test sets. The main outcome was the accuracy of the treatment prediction model, measured by the AUC and accuracy.
RESULTS: This deep learning model achieved favorable prediction performance. In the internal test set, the AUC and accuracy were 0.867 (95% CI: 0.847-0.941) and 0.836 (95% CI: 0.818-0.896), respectively. The prediction performance was fully validated in the external test set, and the model had an AUC of 0.758 (95% CI: 0.724-0.834) and an accuracy of 0.807 (95% CI: 0.774-0.843).
CONCLUSIONS: The deep learning model based on endoscopic images demonstrated exceptional predictive power for neoadjuvant treatment response, highlighting its potential for guiding personalized therapy.

The aim of the present study was to investigate the impact of CCR5 Δ32 and CTLA-4 polymorphisms on the response to IFN-β treatment in our cohort of MS patients from Croatia and Slovenia. Genomic DNA was obtained from 295 MS patients (230 female; 65 male) classified as responders (n = 173) and non-responders (n = 122) based on clinical criteria for treatment efficacy. Genotyping was performed via PCR/PCR-RFLP. No significant differences in the genotype/allele frequencies of CCR5Δ32 and CTLA-4 +49 A/G were detected between male responders and non-responders. A significantly higher prevalence (p = 0.039) of the CTLA-4 +49 AA genotype was found in female responders (42.1%) compared to non-responders (28.9%). Using multiple forward regression analysis, the CTLA-4 +49 AA genotype significantly predicted a positive response to IFN-β therapy in females (p = 0.011) and contributed to 4.5% of response variability. Furthermore, the combined presence of the CCR5Δ32 wtwt/CTLA-4 +49 AA genotype significantly predicted a positive response to treatment in females (p = 0.025). The age at disease onset, pretreatment relapse rate, and baseline EDSS score were not reliable predictors of treatment response in MS patients. Our results indicate that the presence of the CCR5Δ32 polymorphism was not associated with the response to IFN-β treatment, whereas the CTLA-4 +49 polymorphism showed a positive correlation with an optimal response in female patients.

Background: Disease-modifying antirheumatic drugs (bDMARDs) have shown efficacy in treating Rheumatoid Arthritis (RA). Predicting treatment outcomes for RA is crucial as approximately 30% of patients do not respond to bDMARDs and only half achieve a sustained response. This study aims to leverage machine learning to predict both initial response at 6 months and sustained response at 12 months using baseline clinical data. Methods: Baseline clinical data were collected from 154 RA patients treated at the University Hospital in Erlangen, Germany. Five machine learning models were compared: Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), K-nearest neighbors (KNN), Support Vector Machines (SVM), and Random Forest. Nested cross-validation was employed to ensure robustness and avoid overfitting, integrating hyperparameter tuning within its process. Results: XGBoost achieved the highest accuracy for predicting initial response (AUC-ROC of 0.91), while AdaBoost was the most effective for sustained response (AUC-ROC of 0.84). Key predictors included the Disease Activity Score-28 using erythrocyte sedimentation rate (DAS28-ESR), with higher scores at baseline associated with lower response chances at 6 and 12 months. Shapley additive explanations (SHAP) identified the most important baseline features and visualized their directional effects on treatment response and sustained response. Conclusions: These findings can enhance RA treatment plans and support clinical decision-making, ultimately improving patient outcomes by predicting response before starting medication.

BACKGROUND: The aim of this prospective observational cohort study was to unveil the predictors of treatment response to tocilizumab (TCZ) therapy in rheumatoid arthritis (RA) patients, in terms of clinical characteristics and serum proinflammatory cytokines, especially to explore the predictive value of granulocyte macrophage-colony stimulating factor (GM-CSF).
METHODS: Active adult RA patients with inadequate response to MTX intending to receive TCZ therapy were recruited prospectively in the study. A total of 174 severe RA patients were included for the identification of the associations between treatment response and the following characteristic features: demographics, medications, disease activity, serum proinflammatory cytokines and so on.
RESULTS: Disease duration (OR = 0.996), tender joint count (TJC)/68 (OR = 0.943), neutrophil ratio (W4/baseline) (OR = 0.224), the high level of GM-CSF > 5 ng/ml (OR = 0.414) at baseline were the independent adverse predictors of good response assessed by clinical disease activity index (CDAI) at week 24 (W24) for TCZ therapy in RA patients. Moreover, DAS28-ESR (OR = 2.951, P = 0.002) and the high level of GM-CSF > 10 ng/ml at baseline (OR = 5.419, P = 0.002) were independent predictors of poor response, but not the high level of GM-CSF > 5 ng/ml (OR = 2.713, P = 0.054). The patients in the high GM-CSF group had significantly higher DAS28-ESR and serum levels of cytokines (IL-17A, IL-1β, IL-6, TNF-α) at baseline, as well as significantly higher rate of non-good response (62.8% vs. 39.4%, P = 0.010) and poor response (27.9% vs. 9.1%, P = 0.004) than the low GM-CSF group at W24. In addition, poor responders had significantly higher levels of GM-CSF with concomitant increase in the serum levels of IL-17A and IL-1β at baseline than those in moderate and good response groups, while serum levels of IL-6 and TNF-α at baseline were not significantly different in three response groups.
CONCLUSIONS: The high levels of GM-CSF (> 5 ng/ml and > 10 ng/ml) at baseline were the independent predictors of non-good response and poor response to TCZ at W24 respectively. The high level of GM-CSF at baseline is a marker of high disease activity and a predictor of poor response to TCZ in severe RA patients, which may facilitate the development of individualized treatment strategies for refractory RA.

Triple-negative breast cancer (TNBC) is often treated with neoadjuvant systemic therapy (NAST). We investigated if radiomic models based on multiparametric Magnetic Resonance Imaging (MRI) obtained early during NAST predict pathologic complete response (pCR). We included 163 patients with stage I-III TNBC with multiparametric MRI at baseline and after 2 (C2) and 4 cycles of NAST. Seventy-eight patients (48%) had pCR, and 85 (52%) had non-pCR. Thirty-six multivariate models combining radiomic features from dynamic contrast-enhanced MRI and diffusion-weighted imaging had an area under the receiver operating characteristics curve (AUC) > 0.7. The top-performing model combined 35 radiomic features of relative difference between C2 and baseline; had an AUC = 0.905 in the training and AUC = 0.802 in the testing set. There was high inter-reader agreement and very similar AUC values of the pCR prediction models for the 2 readers. Our data supports multiparametric MRI-based radiomic models for early prediction of NAST response in TNBC.

UNASSIGNED: Abnormal accumulation of copper could induce cell death and tumor growth, and affect tumor immune escape by regulating programmed cell death ligand 1 (PD-L1) expression. This study aims to establish and verify a risk signature based on cuproptosis- and immune-related genes (CIRGs) for hepatocellular carcinoma (HCC) management.
UNASSIGNED: HCC RNA-seq and clinical data were obtained from open databases. Least absolute shrinkage and selection operator (LASSO) and Cox regression analyses were utilized to screen CIRGs and develop a risk signature. The signature\'s value for clinical applications, functional enrichment, tumor mutation burden (TMB), and immune profile analyses were investigated systematically.
UNASSIGNED: A risk signature was developed utilizing seven CIRGs, and it performed well in predicting the prognosis of HCC patients in both the training and external validation cohorts. The model\'s risk score was discovered to be related to important clinical features. Top 15 mutated genes in HCC were significantly different among different risk groups. High-risk patients showed higher TMB, and high TMB was closely identified with a poorer prognosis. Immune profile analyses showed that immune infiltration level was higher in low-risk patients than high-risk patients, and the level of immune checkpoint genes expression varied significantly between patients in two different risk groups. Low-risk patients responded well to immunotherapy treatment, whereas high-risk patients were more sensitive to sorafenib, doxorubicin, gemcitabine and AKT (also known as protein kinase B) inhibitors.
UNASSIGNED: The established risk signature based on CIRGs can not only well predict the prognosis of HCC patients but is also promising in evaluating TMB and treatment response to immunotherapy, targeted therapy and chemotherapy, which has the potential to assist in the clinical management of HCC.

BACKGROUND: Head and neck cancers (HNC) are associated with high rates of anxiety. Anxiety has been linked to biological pathways implicated in cancer progression, though little is known about its effects on overall survival. We hypothesized that higher pretreatment anxiety levels in patients with HNC would predict poorer 2-year overall survival and expected this relationship to be mediated by both systemic inflammation and tumor response to treatment.
METHODS: Patients (N = 394) reported anxiety symptomatology via the GAD-7 at treatment planning. Pre-treatment hematology workup provided an index of systemic inflammation (SII; N = 292). Clinical data review yielded tumor response and overall survival. Logistic and multiple regressions and Cox proportional hazard models tested hypothesized relationships.
RESULTS: Higher pretreatment anxiety levels were significantly associated with poorer 2-year survival (hazard ratio [HR], 1.039; 95% confidence interval [CI], 1.014-1.066, p = 0.002). The association between anxiety and SII was not significant, though anxiety was associated with poorer tumor response (odds ratio [OR], 1.033; 95% CI, 1.001-1.066, p = 0.043). Tumor response fully mediated the relationship between anxiety symptoms and 2-year survival (HR, 9.290, 95% CI, 6.152-14.031, p < 0.001).
CONCLUSIONS: Anxiety was associated with overall survival. Tumor response, but not systemic inflammation, emerged as a potential biological pathway mediating this effect. Screening for anxiety may be beneficial to help prospectively address these concerns and ameliorate potentially detrimental impact on clinically meaningful cancer outcomes.

OBJECTIVE: Vital rules learned from FDG-PET radiomics of tumor subregional response can provide clinical decision support for precise treatment adaptation. We combined a rule-based machine learning (ML) model (RuleFit) with a heuristic algorithm (Gray Wolf Optimizer, GWO) for mid-chemoradiation FDG-PET response prediction in patients with locally advanced non-small cell lung cancer. Approach: Tumors subregions were identified using K-means clustering. GWO+RuleFit consists of three main parts: (i) a random forest is constructed based on conventional features or radiomic features extracted from tumor regions or subregions in FDG-PET images, from which the initial rules are generated; (ii) GWO is used for iterative rule selection; (iii) the selected rules are fit to a linear model to make predictions about the target variable. Two target variables were considered: a binary response measure (∆SUVmean⩾20% decline) for classification and a continuous response measure (∆SUVmean) for regression. GWO+RuleFit was benchmarked against common ML algorithms and RuleFit, with leave-one-out cross-validated performance evaluated by the area under the receiver operating characteristic curve (AUC) in classification and root-mean-square error (RMSE) in regression. Main results: GWO+RuleFit selected 15 rules from the radiomic feature dataset of 23 patients. For treatment response classification, GWO+RuleFit attained numerically better cross-validated performance than RuleFit across tumor regions and sets of features (AUC:0.58-0.86 vs. 0.52-0.78, p=0.170-0.925). GWO+Rulefit also had the best or second-best performance numerically compared to all other algorithms for all conditions. For treatment response regression prediction, GWO+RuleFit (RMSE:0.162-0.192) performed better numerically for low-dimensional models (p=0.097-0.614) and significantly better for high-dimensional models across all tumor regions except one (RMSE:0.189-0.219, p<0.004). Significance: The GWO+RuleFit selected rules were interpretable, highlighting distinct radiomic phenotypes that modulated treatment response. GWO+Rulefit achieved parsimonious models while maintaining utility for treatment response prediction, which can aid clinical decisions for patient risk stratification, treatment selection, and biologically driven adaptation. Clinical trial: NCT02773238.

OBJECTIVE: Identifying biomarkers that predict treatment response in early psychosis (EP) is a priority for psychiatry research. Previous work suggests that resting-state connectivity biomarkers may have promise as predictive measures, although prior results vary considerably in direction and magnitude. Here, we evaluated the relationship between intrinsic functional connectivity of the attention, default mode, and salience resting-state networks and 12-month clinical improvement in EP.
METHODS: Fifty-eight individuals with EP (less than 2 years from illness onset, 35 males, average age 20 years) had baseline and follow-up clinical data and were included in the final sample. Of these, 30 EPs showed greater than 20% improvement in Brief Psychiatric Rating Scale (BPRS) total score at follow-up and were classified as \"Improvers.\"
RESULTS: The overall logistic regression predicting Improver status was significant (χ2 = 23.66, Nagelkerke\'s R2 = 0.45, P < .001, with 85% concordance). Significant individual predictors of Improver status included higher default mode within-network connectivity, higher attention-default mode between-network connectivity, and higher attention-salience between-network connectivity. Including baseline BPRS as a predictor increased model significance and concordance to 92%, and the model was not significantly influenced by the dose of antipsychotic medication (chlorpromazine equivalents). Linear regression models predicting percent change in BPRS were also significant.
CONCLUSIONS: Overall, these results suggest that resting-state functional magnetic resonance imaging connectivity may serve as a useful biomarker of clinical outcomes in recent-onset psychosis.

BACKGROUND: Arthritis is a common clinical condition seen in Ayurveda clinics. Clinical trials have reported Ayurvedic interventions to be of benefits in many arthritic conditions including Rheumatoid Arthritis (RA). No mechanistic details however are available about how such interventions on their own or as a combination of whole system Ayurveda might be working.
OBJECTIVE: The study aims to evaluate simultaneously the clinical outcome of Ayurveda whole system (AWS) intervention in RA patients and identifying the serum metabolic signatures which could be useful for diagnosing the disease and monitoring treatment response.
METHODS: RA patients (n = 37) simultaneously diagnosed as Amavata fulfilling the specific inclusion and exclusion criteria were recruited in the study and were given Ayurveda whole system (AWS) intervention comprised of oral medicines, local therapy and dietary recommendation for 3 months. The clinical and serum metabolic changes were investigated for pre-treatment RA patients (baseline RA group, n = 37) and post-treatment RA patients (following treatment of 6-weeks (RA_F, n = 26) and three months (RA_T, n = 36). For comparative serum metabolomics analysis, 57 normal healthy control (HC) subjects were also involved and the serum metabolic profiles were measured at high-field 800 MHz NMR spectrometer. The serum metabolic profiles were compared using multivariate statistical analysis and discriminatory metabolic features were evaluated for diagnostic potential using receiver operating characteristic (ROC) curve analysis.
RESULTS: A significant reduction in DAS-28 ESR, AAM Score, total swollen joints, total tender joints were observed following AWS intervention. The clinical outcomes were concordant with changes in metabolic profiles of RA patients as these were also shifting towards the normal levels following the intervention. Compared to healthy control (HC) subjects, the sera of baseline RA patients were characterised by increased circulatory level of succinate, lysine, mannose, creatine, and 3-Hydroxybutyrate (3-HB) and decreased levels of alanine. The present study also evaluated the serum metabolic ratios for their discriminatory and diagnostic potential and notably, six metabolic ratios (KHR, KThR, KVR, GHR, PTR and SHR) were found significantly altered (elevated) in baseline RA patients. However, in RA patients receiving AWS treatment, these metabolic changes showed marked convergence towards the metabolic signatures of healthy controls.
CONCLUSIONS: This first of its kind study clearly shows the clinical efficacy of Ayurvedic Whole System (AWS) intervention in the management of Rheumatoid Arthritis (RA), as demonstrated by significant improvements in key clinical parameters. The intervention not only alleviated symptoms but also induced a profound metabolic shifting towards normalization; thus, underscoring the potential of AWS intervention to modulate cellular metabolism in a manner that facilitates a return to homeostasis in RA patients. However, future studies are imperative to confirm these preliminary observations and delineate the underlying mechanisms of action of intervention in cases of RA.