Prediction Of Therapy Outcome Research Articles

Effect of methimazole treatment on Th1, Th17, and Th22 lymphocytes in pediatric Graves' disease patients.

Graves' disease is the leading cause of autoimmune hyperthyroidism. Thyroid hormones are an essential element of the endocrine system, playing a pivotal role in the body's development, especially important in children with intensified growth. Disturbance within thyroid tissue certainly affected the whole body. Nowadays, numerous research studies indicate different factors contributing to the onset of the disease; however, the exact pathomechanism of Graves' disease is still not fully understood, especially in the context of immune-related processes. Th1, Th17, and Th22 effector lymphocytes were found to be crucial participants in the disease outcome, as well as in autoimmune diseases. Here, our study aimed at assessing selected effector T lymphocytes, Th1, Th17, and Th22, in newly diagnosed pediatric Graves' disease patients, together with their association with thyroid-related parameters and the potential outcome of disease management. We indicated significant increases in the frequencies and absolute numbers of selected effector lymphocytes in Graves' disease patients. In addition, their mutual ratios, as well as Th1/Th17, Th/Th22, and Th17/Th22, seem to be significant in those diseases. Notably, low Th17/Th22 ratio values were distinguished as potential prognostic factors for normalizing TSH levels in response to methimazole treatment. To sum up, our research determines the crucial contribution of Th1, Th17, and Th22 cells in the pathogenesis of Graves' disease. Moreover, the mentioned subset of T cells is highly likely to play a substantial role in the potential prediction of therapy outcomes.

Predicting the outcome of psychotherapy for chronic depression by person-specific symptom networks.

Psychotherapies are efficacious in the treatment of depression, albeit only with a moderate effect size. It is hoped that personalization of treatment can lead to better outcomes. The network theory of psychopathology offers a novel approach suggesting that symptom interactions as displayed in person-specific symptom networks could guide treatment planning for an individual patient. In a sample of 254 patients with chronic depression treated with either disorder-specific or non-specific psychotherapy for 48 weeks, we investigated if person-specific symptom networks predicted observer-rated depression severity at the end of treatment and one and two years after treatment termination. Person-specific symptom networks were constructed based on a time-varying multilevel vector autoregressive model of patient-rated symptom data. We used statistical parameters that describe the structure of these person-specific networks to predict therapy outcome. First, we used symptom centrality measures as predictors. Second, we used a machine learning approach to select parameters that describe the strength of pairwise symptom associations. We found that information on person-specific symptom networks strongly improved the accuracy of the prediction of observer-rated depression severity at treatment termination compared to common covariates recorded at baseline. This was also shown for predicting observer-rated depression severity at one- and two-year follow-up. Pairwise symptom associations were better predictors than symptom centrality parameters for depression severity at the end of therapy and one year later. Replication and external validation of our findings, methodological developments, and work on possible ways of implementation are needed before person-specific networks can be reliably used in clinical practice. Nevertheless, our results indicate that the structure of person-specific symptom networks can provide valuable information for the personalization of treatment for chronic depression.

Comparison of Modified ROX Index Score and ROX Index Score for Early Prediction of High Flow Nasal Oxygen Therapy Outcome in Patients with Acute Respiratory Failure: A Prospective Observational Cohort Study.

We compared the modified ROX index and ROX index scores in earlier predictions of high-flow nasal oxygen (HFNO) therapy outcomes in patients with acute respiratory failure. We conducted a prospective observational study on 151 acute respiratory failure patients initiated on HFNO therapy. The primary objective of this research was to compare the modified ROX index and ROX index to investigate which score predicted HFNO treatment outcome earlier. The modified ROX index score had better predictive power than the ROX score at different time points, especially one hour following the start of HFNO therapy (AUC 0.790; 95% CI: 0.717-0.863; p < 0.001). For the ROX Index at 1 hour, the ideal cut-off value for HFNO outcome was 4.36 (sensitivity: 72.6%, specificity: 53.9%), and for the modified ROX index at 1 hour, it was 4.63 (sensitivity: 74.2%, specificity: 69.7%). The presence of various comorbidities didn't show any change in ROX-HR cut-off values. The modified ROX index is a better predictor of the success of HFNO therapy than the ROX index. Furthermore, the presence of any comorbidities did not affect modified ROX index cut-off values or the outcome of HFNO therapy. Sarkar AG, Sharma A, Kothari N, Goyal S, Meshram T, Kumari K, et al. Comparison of Modified ROX Index Score and ROX Index Score for Early Prediction of High Flow Nasal Oxygen Therapy Outcome in Patients with Acute Respiratory Failure: A Prospective Observational Cohort Study. Indian J Crit Care Med 2024;28(9):842-846.

Hair glucocorticoid levels decrease after multimodal inpatient treatment and predict therapy outcome in burnout-related depressive disorders

Objectives Hair cortisol concentration (HCC) indicates chronic stress exposure, which is a risk factor in the pathogenesis of burnout and depression. However, findings on HCC are inconsistent. Similarly, intervention studies show mixed effects on HCC. The present study aimed to shed light on these inconsistencies, by additionally considering also hair cortisone. Methods Twenty-five patients with a burnout-related depressive disorder receiving a multimodal inpatient treatment for clinical burnout and 17 matched healthy controls participated in this study. All participants provided 1 cm long hair samples at the beginning and end of the treatment. HCC and hair cortisone levels (HCNC) were determined. Meteorological data and duration of sick leave were considered as potential covariates. Burnout and depression were assessed with self-ratings, the latter also with examiner ratings. Results There were no significant group differences in glucocorticoid levels. Treatment led to a decrease in both depression severity and hair glucocorticoid concentration in inpatients, while lower HCNC in particular predicted a greater reduction in depression severity. Moreover, meteorological data and the duration of sick leave were also found to have an effect on hair glucocorticoid concentrations. Conclusions These results suggest that multimodal inpatient treatment of clinical burnout considerably reduced stress on both a psychological and biological level. In parallel, hair glucocorticoids appear to be sensitive biomarkers for the evaluation of treatment success and prediction. Examining both HCC and HCNC in intervention studies may provide clearer results than the usual examination of HCC alone.

Plasma mutational burden in PIK3CA and TP53 independently predicts early progression in patients with HR+/HER2- metastatic breast cancer (MBC) enrolled in the GEICAM/2014-12 FLIPPER trial.

1029 Background: There is an unmet need for molecular diagnostics to predict therapy outcomes using blood-based biomarker monitoring to guide treatments in HR+/HER2- MBC patients. Here, we report initial results of serial ctDNA analyses in a trial of Fulvestrant (F) + CDK4/6 inhibitor (CDK4/6i) Palbociclib (Pa) vs. F + Placebo (Pl). Endocrine therapy + CDK4/6i are currently the cornerstones of treatment for HR+/HER2- MBC. However, between 10–30% of patients suffer primary resistance. Thus, early identification of HR+/HER2- MBC patients that progress during CDK4/6i treatment is required. Methods: The GEICAM FLIPPER trial (NCT02690480) is a multicenter, double-blind, randomized, phase II study comparing F+Pa vs F+Pl in postmenopausal women with HR+/HER2- MBC. Sequential plasma was collected from 187 patients at baseline, 12, 24, 36, and 48 weeks on treatment and at progression. In total, 903 samples were analyzed using the Plasma-SeqSensei BC IVD kit (Sysmex Inostics) that identifies and quantifies ctDNA mutations in six BC-related genes. The mutant allele frequency (MAF) of PIK3CA and TP53 variants was assessed in baseline samples (median value as cutoff). These variants, identified as the most prevalent, were used as surrogate markers for mutational burden. The Kaplan-Meier method was used to estimate median (m) PFS and overall survival (OS). Hazard ratio (HR) and odds ratio (OR) were calculated with 95% confidence interval (CI) using Cox proportional hazards regression model and logistic regression respectively, unadjusted or adjusted by age, site of disease, disease presentation at study entry and clinical subtype. Results: Previously we showed that F+Pa improved 1-year PFS (83.5% vs. 71.9%, p=0.064) and mPFS (31.8 vs. 22.0 months, p=0.001) vs F+Pl. Here, ctDNA analyses revealed that having ≥1 mutation in PIK3CA + TP53 was prognostic of early (≤12 months) progression (OR 2.37; 95% CI 1.1-5.12, p=0.0274) independent of treatment arm. Furthermore, having ≥2 mutations was associated with treatment resistance (not achieving objective response; OR 3.55; 95% CI 1.28-9.87, p=0.0151). Additionally, worse mPFS and mOS were seen in patients with ≥2 mutations in PIK3CA + TP53 (PFS: HR 3.6; 95% CI 2.25-5.76, p&lt;0.0001; OS: HR 2.92; 95% CI 1.66-5.12, p=0.002) and in patients with high MAF (PFS: HR 2.43; 95% CI 1.6-3.68, p&lt;0.0001; OS: HR 2.83; 95% CI 1.75-4.58, p&lt;0.0001). Finally, having ≥2 mutations in PIK3CA + TP53 was predictive of early progression (OR 22.32; 95% CI 4.12-120.9, p&lt;0.0001) and worse mOS (61.8 vs. 34.79 months) in the F+Pl arm (HR 5.91; 95% CI 2.65-13.16, p&lt;0.0001) but not in the F+Pa arm. Conclusions: Baseline plasma mutational burden in both PIK3CA and TP53 genes was significantly associated with Fulvestrant +/- Palbociclib treatment outcome in HR+/HER2- MBC and appeared to be predictive of Palbociclib benefit. Clinical trial information: NCT02690480 .

The intelligent Impella: Future perspectives of artificial intelligence in the setting of Impella support.

Artificial intelligence (AI) has emerged as a potential useful tool to support clinical treatment of heart failure, including the setting of mechanical circulatory support (MCS). Modern Impella pumps are equipped with advanced technology (SmartAssist), enabling real-time acquisition and display of data related to both pump performance and the patient's haemodynamic status. These data emerge as an 'ideal' source for data-driven AI applications to predict the clinical course of an ongoing therapeutic protocol. Yet, no evidence of effective application of AI tools in the setting of Impella support is available. On this background, we aimed at identifying possible future applications of AI-based tools in the setting of temporary MCS with an Impella device. We explored the state of research and development at the intersection of AI and Impella support and derived future potential applications of AI in routine Impella clinical management. We identified different areas where the future implementation of AI tools may contribute to addressing important clinical challenges in the setting of Impella support, including (i) early identification of the best suited pathway of care according to patients' conditions at presentation and intention to treat, (ii) prediction of therapy outcomes according to different possible therapeutic actions, (iii) optimization of device implantation procedures and evaluation of proper pump position over the whole course of support and (iv) prevention and/or rationale management of haemocompatibility-related adverse events. For each of those areas, we discuss the potential advantages, challenges and implications of harnessing AI-driven insights in the setting of MCS with an Impella device. Temporary MCS with an Impella device has great potential to benefit from the integration of AI-based tools. Such tools may indeed translate into groundbreaking innovation supporting clinical decision-making and therapy regulation, in particular in complex scenarios such as the multidevice MCS strategy.

#2388 Relevance of anti-PLA2R levels in therapy decision and prediction of therapy outcome in patients with membranous nephropathy

Abstract Background and Aims Detection of anti-phospholipase A2 receptor (PLA2R) antibodies in patients with primary membranous nephropathy (MN) supports diagnosis as well as disease monitoring. An individualised therapy approach was introduced for anti-PLA2R positive MN patients at the Radboud University Medical Center. Immunosuppressive treatment (cyclophosphamide combined with steroids) was stopped when anti-PLA2R results by indirect immunofluorescence testing (IIFT) became negative. Here, we evaluated the relevance of anti-PLA2R levels for therapeutic decisions and the outcome of MN, comparing qualitative and quantitative detection methods. Method Stored serum samples were retrieved for beginning of treatment (baseline), decision point, and follow-up. Anti-PLA2R levels were determined qualitatively by IIFT as well as quantitatively by enzyme-linked immunosorbent assay (ELISA) and chemiluminescence immunoassay (ChLIA) at baseline as well as after treatment and correlated to immunological remission and persistence. Results For an evaluation of the relevance of anti-PLA2R levels at the start of therapy, serum samples of 60 patients were available. Patients sampled at the beginning of the therapy were grouped according to tertiles of anti-PLA2R levels determined by ChLIA (n[lowest tertile] = 20, n[middle tertile] = 20, n[highest tertile] = 20). Lower anti-PLA2R levels were seen in patients with relapsing disease. Higher anti-PLA2R levels were associated with more severe proteinuria. Patients in the lowest tertile of anti-PLA2R were more likely to develop immunological remission after 8 weeks of therapy. In total, 90% vs 75% vs 45% of patients in the tertiles turned anti-PLA2R negative after being treated for 8 weeks. Moreover, in this subgroup of patients who showed immunological remission after 8 weeks of therapy, only 11% of the patients in the lowest tertile needed renewed immunosuppressive therapy, while this percentage increased in the middle and highest tertiles (11% vs 53% vs 33%, p=0.033). For the assessment of anti-PLA2R levels before and after therapy, samples at baseline and week 8 of treatment were examined. At baseline, 50/50 (100%) tested positive in IIFT and ChLIA as well as 48/50 (94%) in ELISA. After 8 weeks on treatment, immunological remission based on IIFT was found in 37/51 (73%) patients. At this point, the overall agreement compared to IIFT was 92% for ChLIA and 82% for ELISA. Yet the availability of quantitative levels provided further insight into this group of patients in whom treatment was discontinued. With ChLIA, anti-PLA2R titers &amp;gt;5 RU/mL after 8 weeks of therapy were found in 4% of IIFT negative patients with persistent remission, vs 55% of IIFT negative patients with early relapse (p=0.006). Conclusion Individualised treatment of MN patients with cyclophosphamide and steroids has been recently introduced. In this respect, the quantitative determination of anti-PLA2R levels adds further value. Of the examined quantitative methods, ChLIA demonstrated the highest agreement with IIFT. Additional studies are needed to evaluate the impact on clinical decision making and outcome.

Client preferences, therapy activities and preference-activity match as predictors of therapy outcome

ABSTRACT Objective: This study investigated whether distinct types of psychotherapy activities, the client’s preference towards these activities prior to therapy, and the degree of match between client preferences and therapy activities, served as predictors of treatment outcomes. Methods: A total of 621 clients (M age = 42 years, 71.7% female) received individual psychotherapy by 54 psychologists. Associations between activity preferences, therapy activities, and preference-activity match as predictors, and symptom change and treatment dropout as outcomes were analyzed using multilevel longitudinal and logistic modelling and polynomial regression models with response surface analysis. Results: No type of therapy activity or activity preference significantly predicted symptom change in therapy, while higher levels of inward orientation therapy activities predicted an increased risk of dropout. Moreover, matching and higher levels of inward orientation and affect expression activities predicted an increased risk of dropout, and matching and higher levels of outward orientation activities predicted a decreased risk of dropout. Finally, a preference-activity mismatch in affect suppression predicted an increased risk of dropout from therapy, both at higher and lower levels of affect suppression. Conclusion: Distinct types of therapy activity preferences may, especially when (mis)matched with similar levels of the same therapy activities, differentially predict particular dropout from therapy. Trial registration: ClinicalTrials.gov identifier: NCT05630560.

Identification of SMC2 and SMC4 as prognostic markers in breast cancer through bioinformatics analysis.

Breast cancer (BRCA) is one of the most common malignant tumors. The structural maintenance of chromosome (SMC) gene family has been shown to play an important role in human cancers. However, the role of SMC families in BRCA is unclear. This study aimed to explore the role and potential clinical value of whole SMCs in BRCA. TIMER and UALCAN database were used to analysis the expression level. Genetic variations were analyzed by cBioPortal. Promoter methylation and protein level were analyzed by UCLCAN. GO and KEGG were analyzed by Metascape database. Prognostic value of SMCs was analyzed by Kaplan-Meier and multivariate cox regression analyses. Immune infiltration analysis was conducted by CIBERSORT. Immunotherapy outcome prediction was conducted by Cancer Immunome Atlas. Targeted drug therapy outcome prediction was taken by GDSC and R language. The cell viability was tested by CCK8 and migration was tested by wound healing assay. Xenograft model was used to investigate the in vivo role of SMC2. Expression levels of SMC1A, SMC2, SMC4, SMC5 and SMC6 mRNA were increased in BRCA tissues, and negatively correlated with promoter methylation. Overexpression of SMC2 and SMC4 was negatively correlated with survival. Function of SMCs family regulatory genes was mainly related to ATPase activity. Expression of most SMCs was negatively correlated with immunotherapy and drug therapy outcomes. Interfere SMC2 and SMC4 decreased IC50 values of 5-fluorouracil and oxaliplatin and inhibited the migration of MCF7 cells. Tumor growth and weights were significantly decreased in si-SMC2 groups. Combined bioinformatics and clinical specimen analysis verified SMC2 and SMC4 as independent prognostic factors in BRCA, suggesting their significance for the diagnosis and treatment of BRCA.

Using host-mimicking conditions and a murine cutaneous abscess model to identify synergistic antibiotic combinations effective against Pseudomonas aeruginosa.

Antibiotic drug combination therapy is critical for the successful treatment of infections caused by multidrug resistant pathogens. We investigated the efficacy of β-lactam and β-lactam/β-lactamase inhibitor combinations with other antibiotics, against the hypervirulent, ceftazidime/avibactam resistant Pseudomonas aeruginosa Liverpool epidemic strain (LES) B58. Although minimum inhibitory concentrations in vitro differed by up to eighty-fold between standard and host-mimicking media, combinatorial effects only marginally changed between conditions for some combinations. Effective combinations in vitro were further tested in a chronic, high-density murine infection model. Colistin and azithromycin demonstrated combinatorial effects with ceftazidime and ceftazidime/avibactam both in vitro and in vivo. Conversely, while tobramycin and tigecycline exhibited strong synergy in vitro, this effect was not observed in vivo. Our approach of using host-mimicking conditions and a sophisticated animal model to evaluate drug synergy against bacterial pathogens represents a promising approach. This methodology may offer insights into the prediction of combination therapy outcomes and the identification of potential treatment failures.

Correlation analysis between the quantitative parameters of iodine-131 single-photon emission computed tomography-computed tomography thyroid bed uptake and the efficacy of radioactive iodine adjuvant therapy for papillary thyroid cancer.

Single-photon emission computed tomography-computed tomography (SPECT/CT) quantification has emerged as a valuable tool for assessing disease prognosis by accurately identifying and characterizing abnormal lesions with accumulated radionuclides. Papillary thyroid carcinoma (PTC) is the most prevalent type of thyroid cancer, and radioactive iodine (RAI) therapy is a standard treatment following total thyroidectomy. This study aimed to explore the potential utility the quantitative parameters of the thyroid bed under iodine-131 (I-131) SPECT/CT in the efficacy of RAI adjuvant therapy for patients with PTC. The retrospective cohort study enrolled 107 patients with PTC who underwent RAI adjuvant therapy from June 2020 to January 2023. Three days after the RAI adjuvant therapy, all patients underwent I-131 whole-body scans and SPECT/CT imaging. The quantitative parameters, including maximum standardized uptake value (SUVmax), mean standardized uptake value (SUVmean), and percent injected dose (%ID), were measured using image analysis software based on I-131 SPECT/CT thyroid bed uptake. Successful therapy was defined as inhibitory thyroglobulin (Tg) <0.2 ng/mL with negative thyroglobulin antibody (TgAb) and negative imaging examination 6 months after RAI adjuvant therapy. The relationship between the quantitative parameters and the treatment efficacy, in addition to the potential influencing factors, were analyzed. The quantitative parameters from the successful group [SUVmax: median 6.15 g/mL, interquartile range (IQR) 2.34-13.80 g/mL; SUVmean: median 2.02 g/mL, IQR 0.89-4.93 g/mL; %ID: median 2.00%, IQR 1.00-4.00%] were significantly lower than those from the unsuccessful group (SUVmax: median 19.03 g/mL, IQR 5.31-45.10 g/mL, SUVmean 4.64 g/mL, IQR 2.07-19.05 g/mL; %ID: median 8.00%, IQR 3.00-18.00%) (SUVmax: Z=-3.755; SUVmean; Z=-3.671; %ID: Z=-4.070; all P values <0.001). SUVmax, SUVmean and %ID were positively correlated with the stimulated thyroglobulin (sTg) and inhibitory Tg at 6 months after RAI adjuvant therapy, respectively (all P values <0.001). SUVmax [odds ratio (OR) =1.045], SUVmean (OR =1.130), and %ID (OR =1.092) were predictive factors for the failure of RAI adjuvant therapy (all P values <0.001). Our study suggested that quantitative parameters (SUVmax, SUVmean, and %ID) derived from I-131 SPECT/CT imaging of the thyroid bed can serve as useful tools for predicting therapy outcomes following RAI adjuvant therapy.

Bone marrow infiltration in diffuse large B-cell lymphoma: impact of 18FDG-PET/CT in detection and prediction of therapy outcome

Bone marrow infiltration in diffuse large B-cell lymphoma: impact of 18FDG-PET/CT in detection and prediction of therapy outcome

Determining differences between therapists using an extended version of the facilitative interpersonal skills performance test.

The therapist-facilitative interpersonal skills (FIS) has shown to predict therapy outcomes, demonstrating that high FIS therapists are more effective than low FIS therapists. There is a need for more insight into the variability in strengths and weaknesses in therapist skills. This study investigates whether a revised and extended FIS-scoring leads to more differentiation in measuring therapists'interpersonal skills. Furthermore, we explorative examine whether subgroups of therapists can be distinguished in terms of differences in their interpersonal responses. Using secondary data analysis, 93 therapists were exposed to seven FIS-clips. Responses of therapists using the original and the extended FIS scoring were rated. Three factors were found on the extended FIS scoring distinguishing supportive, expressive, and persuasive interpersonal responses of therapists. A latent profile analysis enlightened the presence of six subgroups of therapists. Using the revised and extended FIS-scoring contributes to our understanding of the role of interpersonal skills in the therapeutic setting by unraveling the question what works for whom.

Preliminary results of anti-inflammatory cytokine concentrations predicting therapy outcome in panic disorder

BackgroundPatients with panic disorder (PD) show alterations of the immune reactivity to acute stress, which could serve as a marker for effective treatment. Nevertheless, the effect of immune reactivity under acute stress before treatment on therapy outcome remains unclear. MethodsA total of N = 16 PD patients performed the Trier Social Test. Blood sample collection of anti-inflammatory cytokine IL-10 accompanied the TSST. The Mobility Inventory was handed out for the assessment of avoidance behavior before and after treatment. Area under the curve with respect to the ground (AUCG) and increase (AUCI) were calculated for assessed cytokine levels and were used as predictors for therapy outcome in regression analyses. ResultsAUCG significantly predicts avoidance behavior in company after treatment (β = −0.007, p = .033) but not avoidance behavior alone (β = −0.003, p = .264). AUCI does not significantly predict therapy outcome. ConclusionHigher concentrations of anti-inflammatory cytokine IL-10 under acute stress before treatment predicts less avoidance behavior in company after therapy. Immune markers seem to play a crucial role in the maintenance of mental disorders such as PD. Underlying mechanisms and IL-10 as a marker for individualized treatments should be investigated in future studies.

Dual-purposing disulfiram for enhanced chemotherapy and afterglow imaging using chlorin e6 and semiconducting polymer combined strategy.

Rationale: One of the main challenges in chemotherapy is achieving high treatment efficacy while minimizing adverse events. Fully exploiting the therapeutic potential of an old drug and monitoring its effects in vivo is highly valuable, but often difficult to achieve. Methods: In this study, by encapsulating disulfiram (DSF) approved by US Food and Drug Administration, semiconducting polymer nanocomplex (MEHPPV), and Chlorin e6 into a polymeric matrix F127 via nanoprecipitation method, a nanosystem (FCMC) was developed for afterglow imaging guided cancer treatment. The characteristics, stability as well as the ability of singlet oxygen (1O2) production of FCMC were first carefully examined. Then, we studied the mechanism for enhanced anti-cancer efficiency and afterglow luminescence in vitro. For experiments in vivo, 4T1 subcutaneous xenograft tumor mice were injected with FCMC via the tail vein every three days and the antitumor effect of FCMC was evaluated by monitoring tumor volume and body weight every three day. Results: The nanosystem, which combines DSF with Ce6, can generates abundant 1O2 that enhances the antitumor activity of DSF. The in vivo results show that FCMC-treated group exhibits an obviously higher tumor-growth inhibition rate of 67.89% after 15 days of treatment, compared to the control group of F127@MEHPPV-CuET. Moreover, Ce6 also greatly enhances the afterglow luminescence intensity of MEHPPV and promotes the redshift of the afterglow emission towards the ideal near-infrared imaging window, thereby enabling efficient afterglow tumor imaging in vivo. Conclusions: This multifunctional nanoplatform not only improves the anticancer efficacy of DSF, but also enables monitoring tumor via robust afterglow imaging, thus exhibiting great potential for cancer therapy and early therapeutic outcome prediction.

LASSO logistic regression reveals a mixed MiRNA and serum-marker classifier for prediction of immunotherapy response in liquid biopsies of melanoma patients

IntroductionCutaneous malignant melanoma suffers from the highest metastasis rate and mortality among different skin cancer entities. However, with emerging immune checkpoint inhibitor (ICI) therapy, prognosis has significantly improved over the last years. To better assess treatment response stable and reliable biomarkers are needed. MethodsWe gathered blood samples of 81 patients with predominantly AJCC Stage III/IV melanoma to evaluate serum markers and plasma-derived miRNAs. A machine learning model was developed to predict immunotherapy response. Serum markers were measured according to standard clinical routines. Expression levels of 61 miRNAs were quantified via flowcytometry. LASSO logistic regression was fit to the data to predict therapy outcome, employing AUROC as the performance metric. Nested cross-validation was used to mitigate overfitting. ResultsPlasma-derived miRNA expression exhibited significant association with therapy response for 5 miRNAs: miR-132–3p, miR-137, miR-197, miR-214, miR-514a-3p. Serum markers LDH, CRP, S100 and eosinophile concentration showed significant differences between Responders and Non-Responders. Age and previous anti-BRAF therapy (BRAFi/MEKi) were the only demographic parameters significantly related to therapy outcome. Among six machine learning models tested, a relaxed LASSO approach on the entire dataset performed best (AUC = 0.851). ConclusionValidation of the relaxed LASSO model in the outer loop of the nested cross validation yielded an AUC of 0.847. This model incorporated expression of a miRNA-quartet, LDH, patient age and prior BRAFi/MEKi. It effectively identifies Responders and Non-Responders with high sensitivity and specificity, presenting promising candidates for the validation of future biomarkers.

Select or adjust? How information from early treatment stages boosts the prediction of non-response in internet-based depression treatment.

Internet-based interventions produce comparable effectiveness rates as face-to-face therapy in treating depression. Still, more than half of patients do not respond to treatment. Machine learning (ML) methods could help to overcome these low response rates by predicting therapy outcomes on an individual level and tailoring treatment accordingly. Few studies implemented ML algorithms in internet-based depression treatment using baseline self-report data, but differing results hinder inferences on clinical practicability. This work compares algorithms using features gathered at baseline or early in treatment in their capability to predict non-response to a 6-week online program targeting depression. Our training and test sample encompassed 1270 and 318 individuals, respectively. We trained random forest algorithms on self-report and process features gathered at baseline and after 2 weeks of treatment. Non-responders were defined as participants not fulfilling the criteria for reliable and clinically significant change on PHQ-9 post-treatment. Our benchmark models were logistic regressions trained on baseline PHQ-9 sum or PHQ-9 early change, using 100 iterations of randomly sampled 80/20 train-test-splits. Best performances were reached by our models involving early treatment characteristics (recall: 0.75-0.76; AUC: 0.71-0.77). Therapeutic alliance and early symptom change constituted the most important predictors. Models trained on baseline data were not significantly better than our benchmark. Fair accuracies were only attainable by involving information from early treatment stages. In-treatment adaptation, instead of a priori selection, might constitute a more feasible approach for improving response when relying on easily accessible self-report features. Implementation trials are needed to determine clinical usefulness.

Dysbiosis and Associated Stool Features Improve Prediction of Response to Biological Therapy in Inflammatory Bowel Disease

Dysbiosis of the gut microbiota is considered a key contributor to inflammatory bowel disease (IBD) etiology. Here, we investigated potential associations between microbiota composition and the outcomes to biological therapies. The study prospectively recruited 296 patients with active IBD (203 with Crohn's disease, 93 with ulcerative colitis) initiating biological therapy. Quantitative microbiome profiles of pretreatment and posttreatment fecal samples were obtained combining flow cytometry with 16S amplicon sequencing. Therapeutic response was assessed by endoscopy, patient-reported outcomes, and changes in fecal calprotectin. The effect of therapy on microbiome variation was evaluated using constrained ordination methods. Prediction of therapy outcome was performed using logistic regression with 5-fold cross-validation. At baseline, 65.9% of patients carried the dysbiotic Bacteroides2 (Bact2) enterotype, with a significantly higher prevalence among patients with ileal involvement (76.8%). Microbiome variation was associated with the choice of biological therapy rather than with therapeutic outcome. Only anti-tumor necrosis factor-α treatment resulted in a microbiome shift away from Bact2, concomitant with an increase in microbial load and butyrogen abundances and a decrease in potentially opportunistic Veillonella. Remission rates for patients hosting Bact2 at baseline were significantly higher with anti-tumor necrosis factor-α than with vedolizumab (65.1% vs 35.2%). A prediction model, based on anthropometrics and clinical data, stool features (microbial load, moisture, and calprotectin), and Bact2 detection predicted treatment outcome with 73.9% accuracy for specific biological therapies. Fecal characterization based on microbial load, moisture content, calprotectin concentration, and enterotyping may aid in the therapeutic choice of biological therapy in IBD.

Dynamic and static predictive modelling of psychotherapy outcome-Comparison of two statistical approaches.

Improving prediction abilities in the therapy process can increase therapeutic success for a variety of reasons, such as more personalised treatment or resource optimisation. The increasingly applied methods of dynamic prediction seem to be very promising for this purpose. Prediction models are usually based on static approaches of frequentist statistics. However, the application of this statistical approach has been widely criticised in this research area. Bayesian statistics has been proposed in the literature as an alternative, especially for the task of dynamic modelling. In this study, we compare the performance of predicting therapy outcome over the course of therapy between both statistical approaches. Based on a sample of 341 patients, a logistic regression analysis was performed using both statistical approaches. Therapy success was conceptualised as reliable pre-post improvement in brief symptom inventory (BSI) scores. As predictors, we used the subscales of the Outcome Questionnaire (OQ-30) and the Helping Alliance Questionnaire (HAQ) measured every fifth session, as well as baseline BSI scores. The influence of the predictors during therapy differs between the frequentist and the Bayesian approach. In contrast, predictive validity is comparable with a mean area under the curve (AUC) of 0.76 in both model types. Bayesian statistic provides an innovative and useful alternative to the frequentist approach in predicting therapy outcome. The theoretical foundation is particularly well suited for dynamic prediction. Nevertheless, no differences in predictive validity were found in this study. More complex methodology as well as further research seems necessary to exploit the potential of Bayesian statistics in this area.

Hemodynamic forces from 4D flow magnetic resonance imaging for optimised prediction of cardiac resynchronisation therapy outcome

Abstract Background Patients with heart failure and left bundle branch block (LBBB) may receive cardiac resynchronisation therapy (CRT), but many patients have limited treatment response (1). The use of imaging to optimise patient selection has been repeatedly attempted with some success (2), and scar detected on late gadolinium enhancement (LGE) imaging has been associated with reduced response rates (3). Intraventricular hemodynamic force (HDF) analysis has been suggested as a novel marker for assessment of patients eligible for CRT (4). The aim of this study was therefore to investigate if septal scar from LGE or left ventricular HDF computed from cardiac magnetic resonance (CMR) imaging can improve prediction of CRT outcome. Methods Patients with heart failure, EF&amp;lt;35% and LBBB (n=22) underwent CMR with 4D flow at 1.5T or 3T (Achieva, Philips Healthcare) prior to CRT (Figure 1). Scar was assessed by LGE. Left ventricular HDF were computed based on the Navier-Stokes equations, using a validated module in the software Segment v3.3 R10057 (Medviso, Lund, Sweden) (5). Forces (N) were analysed in three orthogonal directions as root mean square (RMS) and peak values, reported in median [interquartile range]. Transversal/longitudinal HDF ratio was calculated for systole and diastole. Echocardiography was performed before and six months after CRT, and patients with end-systolic volume reduction ≥15% at follow-up were defined as responders. The Mann-Whitney U test was used for group comparisons, Fisher’s exact test for binary categorical data, Wilcoxon test for paired comparisons, and receiver operating characteristic analysis for prediction of CRT response. Results There was no difference between responders and non-responders in LGE (Table 1). Non-responders had smaller HDF than responders in the inferior-anterior direction in systole (RMS: 0.055 [0.027] vs 0.070 [0.032], p=0.04; peak: 0.11 [0.069] vs 0.15 [0.083], p=0.03), and in the apex-base direction in diastole (RMS: 0.087 [0.018] vs 0.11 [0.046], p=0.047). Non-responders had larger diastolic HDF ratio than responders (RMS: 0.89 [0.45] vs 0.67 [0.20], p=0.004; peak: 1.1 [0.51] vs 0.57 [0.40], p=0.01) (Figure 1). Receiver operating characteristic analysis of diastolic HDF ratio found an area under the curve of 0.88 (p=0.005). Identification of non-responders using diastolic HDF ratio with a specificity of 100%, resulted in a ratio of &amp;gt;0.87 for non-responders, with a sensitivity of 57%. Intragroup comparison found higher HDF ratio in systole than diastole for responders but not for non-responders (Figure 1). Conclusions Prediction of left ventricular remodelling following CRT may be optimized by hemodynamic force analysis from 4D flow CMR, while septal scar from LGE was not found indicative of CRT outcome in this pilot study. Larger-scale studies are required before clinical implementation of HDF analysis.Table 1Figure 1