Prediction Of Treatment Effect Research Articles

Optimal Statistical Inference for Individualized Treatment Effects in High-Dimensional Models

AbstractThe ability to predict individualized treatment effects (ITEs) based on a given patient's profile is essential for personalized medicine. We propose a hypothesis testing approach to choosing between two potential treatments for a given individual in the framework of high-dimensional linear models. The methodological novelty lies in the construction of a debiased estimator of the ITE and establishment of its asymptotic normality uniformly for an arbitrary future high-dimensional observation, while the existing methods can only handle certain specific forms of observations. We introduce a testing procedure with the type I error controlled and establish its asymptotic power. The proposed method can be extended to making inference for general linear contrasts, including both the average treatment effect and outcome prediction. We introduce the optimality framework for hypothesis testing from both the minimaxity and adaptivity perspectives and establish the optimality of the proposed procedure. An extension to high-dimensional approximate linear models is also considered. The finite sample performance of the procedure is demonstrated in simulation studies and further illustrated through an analysis of electronic health records data from patients with rheumatoid arthritis.

A unified approach for evaluating the prediction of treatment effect across different types of endpoints.

Phase 2 and 3 development failure is one of the key factors for high drug development cost. Robust prediction of a candidate drug's efficacy and safety profile could potentially improve the success rate of the drug development. Therefore, systematic evaluation of the prediction is important for learning and continuous improvement of the prediction. In this article, we proposed a set of unified criteria that allow to evaluate the predictions across different endpoints, indications and development stages: standardized bias (SB), standardized mean squared errors (SMSE), and credibility of prediction. We applied the SB and SMSE to the predicted treatment effects for 54 comparisons in 5 compounds in immunology and diabetes.

MO825PERSONALIZING TREATMENT IN END-STAGE KIDNEY DISEASE: DECIDING BETWEEN HAEMODIAFILTRATION AND HEMODIALYSIS BASED ON INDIVIDUALIZED TREATMENT EFFECT PREDICTION

Abstract Background and Aims An individual participant data (IPD) meta-analysis of four randomized controlled trials (RCTs) demonstrated that hemodiafiltration (HDF) reduced overall mortality compared to hemodialysis (HD) in patients with end-stage kidney disease (ESKD). It remains, however, difficult to translate these average results into clinical practice as absolute treatment effects may substantially differ between individuals. The aim of this study was to develop and validate a treatment effect prediction model to determine which patients would benefit the most from HDF or HD in terms of all-cause mortality. Method We used an IPD meta-analysis based on four RCTs comparing HDF with HD on mortality endpoints to derive a Royston-Parmar model for prediction of absolute treatment effect of HDF based on pre-specified patient and disease characteristics. Validation of the model with regard to model discrimination, calibration and net benefit was performed using internal-external cross validation. Results The median predicted gain in median survival was 44 (Q1-Q3: 44-46) days for every year of treatment with HDF compared to HD. The overall gain in median survival with HDF ranged from 2 to 48 months (Figure). Patients who benefited most from HDF were younger, less likely to have diabetes or a cardiovascular history and had higher serum creatinine and albumin levels. Internal-external cross validation showed adequate calibration and discrimination. Decision curve analysis indicated that prediction-based treatment allocation improved the net clinical benefit compared to treating all with patients HDF or treating all with HD. Conclusion Although overall mortality is reduced by HDF compared to HD in ESKD patients, the absolute survival gain can vary greatly between individuals. Our results indicate that the effects of HDF on survival can be predicted using a combination of readily available patient and disease characteristics, which could guide shared decision-making.

P596 Trough concentration of ustekinumab was a useful biomarker for the prediction of treatment-effects in patients with Crohn’s Diseases

Abstract Background Ustekinumab, anti-IL12/23 antibody have contributed to the good prognosis in patients with Crohn’s disease (CD). However, good biomarkers for the prediction of treatment- effects of ustekinumab (UST) are not clear. We elucidated whether trough concentration of UST could predict the clinical remission and seronegative inflammation in CD patients in clinical practice. Methods This was a single-centre prospective observational study approved by the institutional review board of our hospital. Forty CD patients treated by administration of intravenous UST 6 mg/kg and subcutaneous UST 90mg every 8 weeks were enrolled in this study. CDAI, serum CRP and plasma UST trough concentration were evaluated at every visit. All data were examined in total patients, patients with UST induction at remission state after pretreatment (Induction at remission group) and patients with UST induction at active state after pretreatment (Induction at non-remission group). Endpoints were time course changes of clinical remission rate, CDAI, CRP and UST trough concentration until week 40. Results In total, 40 participants were included in the final analysis. The mean age and disease duration of the participants were 41.3 and 11.7 years. Of the participants, 65% (26/40) were male, 25% (10/40) used thiopurine, and 30% (12/40) used steroids. TNF-failure of the patients were 65.0% (26/40). Remission rate of total patients significantly increased at week 8 (30, 60, 68, 78, 78, and 73% at every 8 weeks from baseline). Both CDAI and CRP significantly decreased from baseline at week 8. Remission rate of Induction at remission group (n=12) did not significantly decrease from baseline (100, 92, 92, 92, 92, and 83% at every 8 weeks from baseline). Remission rate of Induction at non-remission group (n=28) significantly increased until week 24 from baseline (0, 46, 57, 71, 71, and 68% at every 8 weeks from baseline). Trough concentrations of total patients at week 8, 16, 24 were 3.54, 1.57 and 1.43 μg/mL, respectively. Trough at each week was not significantly different between Induction at remission and at non-remission groups. Immunomodulator use did not affect trough concentration. Cut-off values of prediction for remission at week 8, 16, and 24 were 2.80, 1.28* and 1.12* μg/mL, respectively. Cut-off values of prediction for normal CRP at week 8, 16, and 24 were 3.27, 1.24* and 1.24* mg/mL, respectively (*: Each factor significantly could be detected). Conclusion UST trough concentration at subcutaneous injection could predict clinical remission and normal CRP. Pretreatment did not affect UST trough concentration.

Independent action models and prediction of combination treatment effects for response rate, duration of response and tumor size change in oncology drug development

An unprecedented number of new cancer targets are in development, and most are being developed in combination therapies. Early oncology development is strategically challenged in choosing the best combinations to move forward to late stage development. The most common early endpoints to be assessed in such decision-making include objective response rate, duration of response and tumor size change. In this paper, using independent-drug-action and Bliss-drug-independence concepts as a foundation, we introduce simple models to predict combination therapy efficacy for duration of response and tumor size change. These models complement previous publications using the independent action models (Palmer 2017, Schmidt 2020) to predict progression-free survival and objective response rate and serve as new predictive models to understand drug combinations for early endpoints. The models can be applied to predict the combination treatment effect for early endpoints given monotherapy data, or to estimate the possible effect of one monotherapy in the combination if data are available from the combination therapy and the other monotherapy. Such quantitative work facilitates strategic planning and decision making in early stage oncology drug development.

Glioblastoma Metabolomics-In Vitro Studies.

In 2016, the WHO introduced new guidelines for the diagnosis of brain gliomas based on new genomic markers. The addition of these new markers to the pre-existing diagnostic methods provided a new level of precision for the diagnosis of glioma and the prediction of treatment effectiveness. Yet, despite this new classification tool, glioblastoma (GBM), a grade IV glioma, continues to have one of the highest mortality rates among central nervous system tumors. Metabolomics is a particularly promising tool for the analysis of GBM tumors and potential methods of treating them, as it is the only “omics” approach that is capable of providing a metabolic signature of a tumor’s phenotype. With careful experimental design, cell cultures can be a useful matrix in GBM metabolomics, as they ensure stable conditions and, under proper conditions, are capable of capturing different tumor phenotypes. This paper reviews in vitro metabolomic profiling studies of high-grade gliomas, with a particular focus on sample-preparation techniques, crucial metabolites identified, cell culture conditions, in vitro-in vivo extrapolation, and pharmacometabolomics. Ultimately, this review aims to elucidate potential future directions for in vitro GBM metabolomics.

Topic Evolution Analysis for Omics Data Integration in Cancers.

One of the vital challenges for cancer diseases is efficient biomarkers monitoring formation and development are limited. Omics data integration plays a crucial role in the mining of biomarkers in the human condition. As the link between omics study on biomarkers discovery and cancer diseases is deepened, defining the principal technologies applied in the field is a must not only for the current period but also for the future. We utilize topic modeling to extract topics (or themes) as a probabilistic distribution of latent topics from the dataset. To predict the future trend of related cases, we utilize the Prophet neural network to perform a prediction correction model for existing topics. A total of 2,318 pieces of literature (from 2006 to 2020) were retrieved from MEDLINE with the query on “omics” and “cancer.” Our study found 20 topics covering current research types. The topic extraction results indicate that, with the rapid development of omics data integration research, multi-omics analysis (Topic 11) and genomics of colorectal cancer (Topic 10) have more studies reported last 15 years. From the topic prediction view, research findings in multi-omics data processing and novel biomarker discovery for cancer prediction (Topic 2, 3, 10, 11) will be heavily focused in the future. From the topic visuallization and evolution trends, metabolomics of breast cancer (Topic 9), pharmacogenomics (Topic 15), genome-guided therapy regimens (Topic 16), and microRNAs target genes (Topic 17) could have more rapidly developed in the study of cancer treatment effect and recurrence prediction.

A preliminary study of hepatocellular carcinoma post proton beam therapy using MRI as an early prediction of treatment effectiveness.

PurposeTo demonstrate the feasibility of magnetic resonance imaging (MRI) for early prediction of proton beam therapy (PBT) effectiveness in hepatocellular carcinoma (HCC).MethodsClinical data of the HCC patients without regional lymph node involvement or distant metastasis who received PBT at this institution between 2014 and 2017 were reviewed. A total of 43 patients were included. Tumor regression pattern after PBT were examined on the basis of follow-up duration. The variables were compared between patients with and without early tumor regression (ETR).ResultsThe median follow-up duration was 40 months (range, 9–62 months). The cumulative overall survival rate at 6 months, 1 years and 5 years was 100%, 88.4%, 63.4%, respectively. Child-Pugh class A, local tumor control (LTC), complete response (CR), and ETR were significantly associated with overall survival (p < 0.05 each). Of 43 patients, 25 patients (58.1%) reached CR in the PBT-irradiated region. Twelve patients (27.9%) had a partial response and 3 patients (7.0%) had a stationary disease. Three patients (7.0%) developed in-field progression. The LTC rate at 5 years was 93.0%. Of the 25 patients who achieved a CR in the PBT-irradiated region, the median time to CR was 5 months (range, 1–19 months). Twenty-two patients (51.2%) showed ETR of the HCC, while 21 patients (48.8%) showed non-ETR. A significant association was observed between ETR and CR of the HCC after PBT (p < 0.001).ConclusionThe post-PBT MRI follow-up at 3 months is helpful for monitoring therapeutic response. ETR of the HCC predicted a higher rate of CR and was associated with overall survival, which provides more accurate clinical management.

Treatment effect prediction using CT after balloon pulmonary angioplasty in chronic thromboembolic pulmonary hypertension.

To evaluate whether the change in computed tomography pulmonary angiography (CTPA) metrics after balloon pulmonary angioplasty (BPA) can predict treatment effect in chronic thromboembolic pulmonary hypertension (CTEPH) patients. This study included 82 CTEPH patients who underwent both CTPA and right heart catheterization (RHC) before and at the scheduled time of 6 months after BPA. The diameters of the main pulmonary artery (dPA), ascending aorta (dAA), right atrium (dRA), right ventricular free wall thickness (dRVW), and right and left ventricles (dRV, dLV) were measured on CTPA. The correlation of the New York Heart Association functional class (NYHA FC), 6-minute walking distance (6MWD), brain natriuretic peptide (BNP) level, and calculated CT metrics with a decrease in mean pulmonary artery pressure (ΔmPAP) using RHC (used as the reference for BPA effect) was investigated. Using multiple regression analysis, independent variables were also identified. In univariate analysis, clinical indicators (NYHA FC, 6MWD, and BNP level) improved significantly after BPA and were significantly correlated with ΔmPAP (p < 0.01). In the univariate analysis of CTPA parameters, dPA, dRA, dPA/dAA ratio, dRVW, and dRV/dLV ratio decreased significantly and were significantly correlated with ΔmPAP (p < 0.01). Multivariate analysis demonstrated that decreased dPA (p = 0.001) and decreased dRA (p = 0.039) on CTPA were independent predictive factors of ΔmPAP. Decreased dPA and dRA on CTPA could predict a decrease in mPAP after BPA, thus potentially eliminating unnecessary invasive catheterization. • The reduction in mean pulmonary artery pressure after balloon pulmonary angioplasty in CTEPH patients was significantly correlated with the clinical indices improvement and CTPA parameter decrease. • The decreased diameter of the main pulmonary artery and the decreased diameter of the right atrium on CTPA were independent predictors of mean pulmonary artery pressure reduction.

A MATHEMATICAL MODEL FOR PREDICTING THE OUTCOME OF TREATMENT OF MULTIDRUD-RESISTANT TUBERCULOSIS

The aim: Predicting the effectiveness of treatment for MRI of the lungs by developing a mathematical model to predict treatment outcomes. Materials and methods: 84 patients with MRI of the lungs: group 1 (n = 56) – with signs of effective TB treatment at the end of the intensive phase; group 2 (n = 28) – patients with signs of ineffective treatment. We used the multivariate discriminant analysis method using the statistical environment STATISTICA 13. Results: During the discriminant analysis, the parameters of the clinical blood analysis (monocytes, stab leukocytes, erythrocytes) were selected, which were associated with high (r&gt; 0.5) statistically significant correlations with the levels of MMP-9, TIMP-1, oxyproline and its fractions and aldosterone in the formation of the prognosis. The mathematical model allows, in the form of comparing the results of solving two linear equations and comparing their results, to predict the outcome of treatment: “1” effective treatment, “2” – ineffective treatment. Early prediction of treatment effectiveness is promising, as it allows the use of the developed mathematical model as an additional criterion for the selection of patients for whom surgical treatment is recommended, in order to increase the effectiveness of treatment. Conclusions: An additional criterion for predicting ineffective MRI treatment, along with the criteria provided for by WHO recommendations, is a mathematical model that takes into account probably strong correlation (r = 0.5, p &lt;0.05) between the factors of connective tissue destruction, collagen destruction, aldosterone , and indicators of a clinical blood test (between levels of OBZ and monocytes (r = 0.82, p = 0.00001), OB and monocytes (r = 0.92, p = 0.000001) OB and stab leukocytes (r = – 0.87, p = 0.0003) OBZ and stab leukocytes (r = – 0.53, p = 0.017), aldosterone and ESR.

Extrapolating Parametric Survival Models in Health Technology Assessment: A Simulation Study.

Extrapolations of parametric survival models fitted to censored data are routinely used in the assessment of health technologies to estimate mean survival, particularly in diseases that potentially reduce the life expectancy of patients. Akaike’s information criterion (AIC) and Bayesian information criterion (BIC) are commonly used in health technology assessment alongside an assessment of plausibility to determine which statistical model best fits the data and should be used for prediction of long-term treatment effects. We compare fit and estimates of restricted mean survival time (RMST) from 8 parametric models and contrast models preferred in terms of AIC, BIC, and log-likelihood, without considering model plausibility. We assess the methods’ suitability for selecting a parametric model through simulation of data replicating the follow-up of intervention arms for various time-to-event outcomes from 4 clinical trials. Follow-up was replicated through the consideration of recruitment duration and minimum and maximum follow-up times. Ten thousand simulations of each scenario were performed. We demonstrate that the different methods can result in disagreement over the best model and that it is inappropriate to base model selection solely on goodness-of-fit statistics without consideration of hazard behavior and plausibility of extrapolations. We show that typical trial follow-up can be unsuitable for extrapolation, resulting in unreliable estimation of multiple parameter models, and infer that selecting survival models based only on goodness-of-fit statistics is unsuitable due to the high level of uncertainty in a cost-effectiveness analysis. This article demonstrates the potential problems of overreliance on goodness-of-fit statistics when selecting a model for extrapolation. When follow-up is more mature, BIC appears superior to the other selection methods, selecting models with the most accurate and least biased estimates of RMST.

Treatment effect prediction with adversarial deep learning using electronic health records

BackgroundTreatment effect prediction (TEP) plays an important role in disease management by ensuring that the expected clinical outcomes are obtained after performing specialized and sophisticated treatments on patients given their personalized clinical status. In recent years, the wide adoption of electronic health records (EHRs) has provided a comprehensive data source for intelligent clinical applications including the TEP investigated in this study.MethodWe examined the problem of using a large volume of heterogeneous EHR data to predict treatment effects and developed an adversarial deep treatment effect prediction model to address the problem. Our model employed two auto-encoders for learning the representative and discriminative features of both patient characteristics and treatments from EHR data. The discriminative power of the learned features was further enhanced by decoding the correlational information between the patient characteristics and subsequent treatments by means of a generated adversarial learning strategy. Thereafter, a logistic regression layer was appended on the top of the resulting feature representation layer for TEP.ResultThe proposed model was evaluated on two real clinical datasets collected from the cardiology department of a Chinese hospital. In particular, on acute coronary syndrome (ACS) dataset, the proposed adversarial deep treatment effect prediction (ADTEP) (0.662) exhibited 1.4, 2.2, and 6.3% performance gains in terms of the area under the ROC curve (AUC) over deep treatment effect prediction (DTEP) (0.653), logistic regression (LR) (0.648), and support vector machine (SVM) (0.621), respectively. As for heart failure (HF) case study, the proposed ADTEP also outperformed all benchmarks. The experimental results demonstrated that our proposed model achieved competitive performance compared to state-of-the-art models in tackling the TEP problem.ConclusionIn this work, we propose a novel model to address the TEP problem by utilizing a large volume of observational data from EHR. With adversarial learning strategy, our proposed model can further explore the correlational information between patient statuses and treatments to extract more robust and discriminative representation of patient samples from their EHR data. Such representation finally benefits the model on TEP. The experimental results of two case studies demonstrate the superiority of our proposed method compared to state-of-the-art methods.

Prognostic value of the creatinine-albumin ratio in acute pancreatitis debridement

BackgroundIncreases in the levels of serum C-reactive protein (CRP) and creatinine (Cr) and decreases in those of albumin (Alb) are commonly observed in acute pancreatitis (AP). We aimed to evaluate the efficacy of the Cr/Alb and CRP/Alb ratios in the prediction of surgical treatment effect in AP patients.MethodsThis study retrospectively analyzed clinical data obtained from 140 AP patients who underwent debridement from January 2008 to November 2018 in Shanghai Ruijin Hospital. The Cr/Alb and CRP/Alb ratios at admission and before surgery were assessed in the analysis of clinical statistics, prediction of prognoses, and logistic regression analysis.ResultsThe admission Cr/Alb had the best predictive value of the four ratios. This value was significantly higher in patients with re-operation and those who died (P < 0.05) and was correlated with the Acute Physiology and Chronic Health Evaluation (APACHE II) score, admission CRP/Alb, preoperative Cr/Alb, and post-operative complications. The admission Cr/Alb could predict the risk of AP-related re-operation and mortality with sensitivities, specificities and areas under the curve of 86.3%, 61.7% and 0.824, and 73.4%, 81.3% and 0.794, respectively. At a cut-off value of 3.43, admission Cr/Alb values were indicative of a worse clinical state, including impaired laboratory test values, APACHE II scores, rates of post-operative complications and re-operation, and mortality (P < 0.05). In the logistic regression analysis, admission Cr/Alb values were independently related to the APACHE II score, post-operative renal failure, and mortality.ConclusionCr/Alb is a novel but promising, easy-to-measure, reproducible, non-invasive prognostic score for the prediction of the effect of debridement in AP patients.

Mathematical model for predicting treatment outcome in patients with destructive pulmonary multiresistant tuberculosis

The cessation of bacterial excretion is the main condition for the effective treatment of multiresistant tuberculosis (MRTB). Surgical procedures for treating tuberculosis patients significantly increase the effectiveness of treatment for such patients. The selection of new selection criteria for surgical treatment of MRI is relevant, as it will increase the effectiveness of MRI treatment, which remains insufficient.Objective — to predicting the effectiveness of treatment for MRI of the lungs by developing a mathematical model to predict treatment outcomes.Materials and methods. 84 patients with MRI of the lungs: group 1 (n = 56) — with signs of effective TB treatment at the end of the intensive phase; group 2 (n = 28) — patients with signs of ineffective treatment. We used the multivariate discriminant analysis method using the statistical environment Statistica 13.Results and discussion. During the discriminant analysis, the parameters of the clinical blood analysis (monocytes, stab leukocytes, erythrocytes) were selected, which were associated with high (r &gt; 0.5) statistically significant correlations with the levels of MMP-9, TIMP-1, oxyproline and its fractions and aldosterone in the formation of the prognosis. The mathematical model allows, in the form of comparing the results of solving two linear equations and comparing their results, to predict the outcome of treatment: 1 — effective treatment, 2 — ineffective treatment. Conсlusions. Early prediction of treatment effectiveness is promising, as it allows the use of the developed mathematical model as an additional criterion for the selection of patients for whom surgical treatment is recommended, in order to increase the effectiveness of treatment.

NIMG-49. VALIDATION OF SIMULTANEOUS PH- AND O2-WEIGHTED MOLECULAR MRI USING 18F-FDG PET, IMMUNOHISTOCHEMISTRY, AND BIOENERGETICS

Abstract This study aimed to investigate the potential of a novel MRI metric related to aerobic glycolysis in patients with diffuse gliomas. All subjects (Study I–III; 7, 26, and 11 subjects, respectively) were scanned on 3-T systems and underwent pH-weighted amine chemical exchange saturation transfer spin-and-gradient-echo echoplanar imaging (CEST-SAGE-EPI) or CEST-EPI, and perfusion imaging. Relative oxygen extraction fraction (rOEF) was calculated by dividing hypoxia-sensitive R2’ by normalized relative cerebral blood volume (nrCBV); a novel metric that characterizes glycolytic status (aerobic glycolytic index, AGI) was calculated by dividing amine CEST contrast by rOEF. Patients in Study I were additionally scanned by 18F-fluorodeoxyglucose (FDG)-PET. Stereotactic image-guided biopsies were performed on patients in Study II and III, and samples were analyzed by immunohistochemistry (IHC) and extracellular flux bioenergetic analysis, respectively. Pairwise correlation between MR metrics and standardized uptake value of 18F-FDG, IHC metrics, or indices of cellular metabolism was calculated using Spearman’s correlation analysis. In Study I, AGI showed very strong significant correlation with 18F-FDG uptake in glioma (correlation coefficient ρ = 0.86, P =0.014). In Study II, AGI was significantly correlated with glucose transporter 3 (ρ = 0.71; P = 0.0041) and hexokinase 2 (ρ = 0.73; P = 0.0029) in IDH wild-type glioma, while it was significantly correlated with monocarboxylate transporter 1 (ρ = 0.59; P = 0.0094) in IDH mutant glioma. This result may reflect the different glycolytic statuses of these gliomas; specifically, the rate-limiting steps in glycolysis. In Study III, a strong significant correlation with cellular AGI derived from the bioenergetic analysis was found for AGI derived from MRI (ρ = 0.79, P = .036). In conclusion, AGI derived from MRI was correlated with FDG, IHC measurements, and cellular AGI. Future studies investigating the clinical utility of AGI in prediction and evaluation of treatment effects are warranted.

Diagnostic Valuation of Serum miR-184 and miR-191 in Patients With Non-Small-Cell Lung Cancer.

Objective:This study aims to determine the diagnosis and prediction value of serum miR-184 and miR-191 levels in patients with non-small-cell lung cancer (NSCLC).Methods:One hundred patients with NSCLC were enrolled (NSCLC group) and treated with gefitinib. In addition, 59 pneumonia cases (pneumonia group) and 51 healthy cases in the corresponding period (normal group) were included. Serum miR-184 and miR-191 expressions were detected by real-time quantitative polymerase chain reaction. Furthermore, the relationships between serum miR-184 and miR-191 expressions and clinicopathological parameters were analyzed. The use of serum miR-184 and miR-191 levels in the diagnosis of NSCLC and the prediction of treatment effectiveness and 3-year overall survival (OS) were assessed by the receiver operating characteristic curve. Hazard factors affecting the efficacy of treatment in patients with NSCLC were determined by logistic regression.Results:The serum levels of miR-184 in the NSCLC group were significantly lower than those in the pneumonia group and normal group, whereas miR-191 expression was significantly higher in the NSCLC group. Serum miR-184 and miR-191 levels were closely correlated with smoking history, the tumor node metastasis (TNM) stage, and the degree of pathological differentiation. The area under curve (AUC) of serum miR-184 combined with miR-191 in the diagnosis of patients in the NSCLC group and normal group, NSCLC group and pneumonia group, and the efficacy of treatment in patients with NSCLC was 0.925, 0.929, and 0.916, respectively. The AUC of serum miR-184 and miR-191 for the 3-year OS in patients with NSCLC was 0.869 and 0.879, respectively. Smoking history, the degree of pathological differentiation, local treatment, miR-184, and miR-191 were independent risk factors that affected treatment efficacy.Conclusion:Serum miR-184 and miR-191 levels can potentially be used as molecular markers to diagnose and predict the curative effect of treatment in patients with NSCLC.

Treatment effect prediction for sarcoma patients treated with preoperative radiotherapy using radiomics features from longitudinal diffusion-weighted MRIs

The objective of this study was to explore radiomics features from longitudinal diffusion-weighted MRIs (DWIs) for pathologic treatment effect prediction in patients with localized soft tissue sarcoma (STS) undergoing hypofractionated preoperative radiotherapy (RT). Thirty patients with localized STS treated with preoperative hypofractionated RT were recruited to this longitudinal imaging study. DWIs were acquired at three time points using a 0.35 T MRI-guided radiotherapy system. Treatment effect score (TES) was obtained from the post-surgery pathology as a surrogate of treatment outcome. Patients were divided into two groups based on TES. Response prediction was first performed using a support vector machine (SVM) with only mean apparent diffusion coefficient (ADC) or delta ADC to serve as the benchmark. Radiomics features were then extracted from tumor ADC maps at each of the three time points. Logistic regression and SVM were constructed to predict the TES group using features selected by univariate analysis and sequential forward selection. Classification performance using SVM with features from different time points and with or without delta radiomics were evaluated. Prediction performance using only mean ADC or delta ADC was poor (area under the curve (AUC) < 0.7). For the radiomics study using features from all time points and corresponding delta radiomics, SVM significantly outperformed logistic regression (AUC of 0.91 ± 0.05 v.s. 0.85 ± 0.06). Prediction AUC values using single or multiple time points without delta radiomics were all below 0.74. Including delta radiomics of mid- or post-treatment relative to the baseline drastically boosted the prediction. In this work, an SVM model was built to predict the TES using radiomics features from longitudinal DWI. Based on this study, we found that use of mean ADC, delta ADC, or radiomics features alone was not sufficient for response prediction, and including delta radiomics features of mid- or post-treatment relative to the baseline can optimize the prediction of TES, a pathologic and clinical endpoint.

Tension headache. State of the problem, new aspects of etiopathogenesis, neuroimaging possibilities, non-drug treatment methods (review)

The prospects for the use of functional magnetic resonance imaging methods in the diagnosis of cognitive and neuropsychiatric disorders in patients with tension headaches are quite wide, as they allow a more detailed study of the pathogenesis of the above disorders. To date, the effectiveness of osteopathy in the treatment of patients with tension headaches has been shown. It remains an open question to develop a generally accepted method of diagnosis and treatment, including the use of complementary therapies, neuroimaging objectification and determination of the state of functional connections of the brain for more accurate diagnosis and prediction of treatment effectiveness. The present review summarizes the current ideas about the etiopathogenesis of tension headache (including the study of the functional connections of the brain) and available data on the clinical efficacy of osteopathic correction.

Prognostic Value of Ki67 Percentage, WT-1 Expression and p16/CDKN2A Deletion in Diffuse Malignant Peritoneal Mesothelioma: A Single-Centre Cohort Study.

Diffuse malignant peritoneal mesothelioma (DMPM) is a rare malignant neoplasm with a poor survival. Although some advances in knowledge have been obtained for the pleural form, much less is known about DMPM. Advantages in terms of prognosis are still limited and strong efforts need to be made. The aim of our study was to correlate several histological and molecular factors with survival in a large cohort of 45 DMPMs. We evaluated histotype, nuclear grade, mitotic count, necrosis, inflammation, desmoplastic reaction, Ki67 percentage, WT-1 expression, p16 protein by immunohistochemistry and CDKN2A deletion by FISH. Our results showed that epithelioid histotype, nuclear grade 2, mitotic count ≤5 x mm2, absence of desmoplasia and p16/CDKN2A deletion, low Ki67 value, and high WT-1 expression were correlated with the most prolonged survival (p = 0.0001). Moreover, p16 loss in immunohistochemistry reflected CDKN2A deletion detected with FISH, and both were correlated with the worst survival (p = 0.0001). At multivariate analysis, Ki67 value, WT-1 expression and p16/CDKN2A deletion emerged as independent prognostic factors (p = 0.01, p = 0.0001 and p = 0.01, respectively). These parameters are easy to analyse at the time of DMPM diagnosis and may support better patient stratification, prediction of treatment effectiveness and therapeutic optimization.

Individual participant data meta-analysis to examine interactions between treatment effect and participant-level covariates: Statistical recommendations for conduct and planning.

Precision medicine research often searches for treatment‐covariate interactions, which refers to when a treatment effect (eg, measured as a mean difference, odds ratio, hazard ratio) changes across values of a participant‐level covariate (eg, age, gender, biomarker). Single trials do not usually have sufficient power to detect genuine treatment‐covariate interactions, which motivate the sharing of individual participant data (IPD) from multiple trials for meta‐analysis. Here, we provide statistical recommendations for conducting and planning an IPD meta‐analysis of randomized trials to examine treatment‐covariate interactions. For conduct, two‐stage and one‐stage statistical models are described, and we recommend: (i) interactions should be estimated directly, and not by calculating differences in meta‐analysis results for subgroups; (ii) interaction estimates should be based solely on within‐study information; (iii) continuous covariates and outcomes should be analyzed on their continuous scale; (iv) nonlinear relationships should be examined for continuous covariates, using a multivariate meta‐analysis of the trend (eg, using restricted cubic spline functions); and (v) translation of interactions into clinical practice is nontrivial, requiring individualized treatment effect prediction. For planning, we describe first why the decision to initiate an IPD meta‐analysis project should not be based on between‐study heterogeneity in the overall treatment effect; and second, how to calculate the power of a potential IPD meta‐analysis project in advance of IPD collection, conditional on characteristics (eg, number of participants, standard deviation of covariates) of the trials (potentially) promising their IPD. Real IPD meta‐analysis projects are used for illustration throughout.