Bootstrap Enhanced Penalized Regression for Variable Selection with Neuroimaging Data

Baseline circulating biomarkers, their changes, and subsequent suicidal ideation and depression severity at 6 months: A prospective analysis in patients with mood disorders

BACKGROUND

Identifying circulating biomarkers associated with prospective suicidal ideation (SI) and depression could help better understand the dynamics of these phenomena and identify people in need of intense care. In this study, we investigated the associations between baseline peripheral biomarkers implicated in neuroplasticity, vascular homeostasis and inflammation, and prospective SI and depression severity during 6 months of follow-up in patients with mood disorders.

METHODS

149 patients underwent a psychiatric evaluation and gave blood to measure 32 plasma soluble proteins. At follow-up, SI incidence over six months was measured with the Columbia Suicide Severity Rating Scale, and depressive symptoms were assessed with the Inventory for Depressive Symptomatology. Ninety-six patients provided repeated blood samples. Statistical analyses included Spearman partial correlation and Elastic Net regression, followed by the covariate-adjusted regression models.

RESULTS

51.4 % (N = 71) of patients reported SI during follow-up. After adjustment for covariates, higher baseline levels of interferon-γ were associated with SI occurrence during follow-up. Higher baseline interferon-γ and lower orexin-A were associated with increased depression severity, and atypical and anxious, but not melancholic, symptoms. There was also a tendency for associations of elevated baseline levels of interferon-γ, interleukin-1β, and lower plasma serotonin levels with SI at the six-month follow-up time point. Meanwhile, reduction in transforming growth factor- β1 (TGF-β1) plasma concentration correlated with atypical symptoms reduction.

CONCLUSION

We identified interferon-γ and orexin-A as potential predictive biomarkers of SI and depression, whereas TGF-β1 was identified as a possible target of atypical symptoms.

Prediction of image interpretation cognitive ability under different mental workloads: a task-state fMRI study

Visual imaging experts play an important role in multiple fields, and studies have shown that the combination of functional magnetic resonance imaging and machine learning techniques can predict cognitive abilities, which provides a possible method for selecting individuals with excellent image interpretation skills. We recorded behavioral data and neural activity of 64 participants during image interpretation tasks under different workloads. Based on the comprehensive image interpretation ability, participants were divided into two groups. general linear model analysis showed that during image interpretation tasks, the high-ability group exhibited higher activation in middle frontal gyrus (MFG), fusiform gyrus, inferior occipital gyrus, superior parietal gyrus, inferior parietal gyrus, and insula compared to the low-ability group. The radial basis function Support Vector Machine (SVM) algorithm shows the most excellent performance in predicting participants' image interpretation abilities (Pearson correlation coefficient = 0.54, R2 = 0.31, MSE = 0.039, RMSE = 0.002). Variable importance analysis indicated that the activation features of the fusiform gyrus and MFG played an important role in predicting this ability. Our study revealed the neural basis related to image interpretation ability when exposed to different mental workloads. Additionally, our results demonstrated the efficacy of machine learning algorithms in extracting neural activation features to predict such ability.

A Multigene Signature Associated with Progression-Free Survival after Treatment for IDH Mutant and 1p/19q Codeleted Oligodendrogliomas

BACKGROUND

IDH mutant and 1p/19q codeleted oligodendrogliomas are the gliomas associated with the best prognosis. However, despite their sensitivity to treatment, patient survival remains heterogeneous. We aimed to identify gene expressions associated with response to treatment from a national cohort of patients with oligodendrogliomas, all treated with radiotherapy +/- chemotherapy.

METHODS

We extracted total RNA from frozen tumor samples and investigated enriched pathways using KEGG and Reactome databases. We applied a stability selection approach based on subsampling combined with the lasso-pcvl algorithm to identify genes associated with progression-free survival and calculate a risk score.

RESULTS

We included 68 patients with oligodendrogliomas treated with radiotherapy +/- chemotherapy. After filtering, 1697 genes were obtained, including 134 associated with progression-free survival: 35 with a better prognosis and 99 with a poorer one. Eight genes (ST3GAL6, QPCT, NQO1, EPHX1, CST3, S100A8, CHI3L1, and OSBPL3) whose risk score remained statistically significant after adjustment for prognostic factors in multivariate analysis were selected in more than 60% of cases were associated with shorter progression-free survival.

CONCLUSIONS

We found an eight-gene signature associated with a higher risk of rapid relapse after treatment in patients with oligodendrogliomas. This finding could help clinicians identify patients who need more intensive treatment.

Development and validation of a metabolite score for red meat intake: an observational cohort study and randomized controlled dietary intervention

BACKGROUND

Self-reported meat consumption is associated with disease risk but objective assessment of different dimensions of this heterogeneous dietary exposure in observational and interventional studies remains challenging.

OBJECTIVES

We aimed to derive and validate scores based on plasma metabolites for types of meat consumption. For the most predictive score, we aimed to test whether the included metabolites varied with change in meat consumption, and whether the score was associated with incidence of type 2 diabetes (T2D) and other noncommunicable diseases.

METHODS

We derived scores based on 781 plasma metabolites for red meat, processed meat, and poultry consumption assessed with 7-d food records among 11,432 participants in the EPIC-Norfolk (European Prospective Investigation into Cancer and Nutrition-Norfolk) cohort. The scores were then tested for internal validity in an independent subset (n = 853) of the same cohort. In focused analysis on the red meat metabolite score, we examined whether the metabolites constituting the score were also associated with meat intake in a randomized crossover dietary intervention trial of meat (n = 12, Lyon, France). In the EPIC-Norfolk study, we assessed the association of the red meat metabolite score with T2D incidence (n = 1478) and other health endpoints.

RESULTS

The best-performing score was for red meat, comprising 139 metabolites which accounted for 17% of the explained variance of red meat consumption in the validation set. In the intervention, 11 top-ranked metabolites in the red meat metabolite score increased significantly after red meat consumption. In the EPIC-Norfolk study, the red meat metabolite score was associated with T2D incidence (adjusted HR per SD: 1.17; 95% CI: 1.10, 1.24).

CONCLUSIONS

The red meat metabolite score derived and validated in this study contains metabolites directly derived from meat consumption and is associated with T2D risk. These findings suggest the potential for objective assessment of dietary components and their application for understanding diet-disease associations.The trial in Lyon, France, was registered at clinicaltrials.gov as NCT03354130.

Systemic inflammation and metabolic disturbances underlie inpatient mortality among ill children with severe malnutrition

Children admitted to hospital with an acute illness and concurrent severe malnutrition [complicated severe malnutrition (CSM)] have a high risk of dying. The biological processes underlying their mortality are poorly understood. In this case-control study nested within a multicenter randomized controlled trial among children with CSM in Kenya and Malawi, we found that blood metabolomic and proteomic profiles robustly differentiated children who died (n = 92) from those who survived (n = 92). Fatalities were characterized by increased energetic substrates (tricarboxylic acid cycle metabolites), microbial metabolites (e.g., propionate and isobutyrate), acute phase proteins (e.g., calprotectin and C-reactive protein), and inflammatory markers (e.g., interleukin-8 and tumor necrosis factor-α). These perturbations indicated disruptions in mitochondria-related bioenergetic pathways and sepsis-like responses. This study identified specific biomolecular disturbances associated with CSM mortality, revealing that systemic inflammation and bioenergetic deficits are targetable pathophysiological processes for improving survival of this vulnerable population.

Predicting child anaemia in the North-Eastern states of India: a machine learning approach

Child anaemia is a serious global health issue and India is one of the highest contributors among the developing nations. Researchers identify many harmful effects of anaemia, which include psychomotor retardation, which in turn decreases the learning ability and causes low intelligence among pre-school children. The effects also include behavioural delays, low immunity, and susceptibility to frequent infections, increased mortality, and disability. The present study aims to predict anaemia among children in North-East India by applying Machine Learning (ML) algorithms to latest available National Family Health Survey (NFHS)-4 data. Out of the total 29,312 eligible children (6–59 months) in North-East India, a total of 21,000 children with demographic variables without any missing observations, wherein 10,460 are anaemic, is considered for this study. Machine learning (ML) algorithms have been applied through 3 different types of penalized regression methods—ridge, least absolute shrinkage and selection operator, and elastic net for predicting anaemia. A systematic assessment of algorithms is performed in terms of accuracy, sensitivity, specificity, F1-Score, and Cohen’s \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$k$$\end{document} k -Statistics. Having achieved the receiver operating characteristic value of over 70% in training and accuracy of above 64% while testing, it can be safely asserted that factors like mother’s anaemic status, age of the child, social status, mother’s age, mother’s education, religion are important in identifying the child as anaemic.

Monitoring inflammation in psychiatry: Caveats and advice

Most researchers working in the field of immunopsychiatry would agree with the statement that "severe psychiatric disorders are associated with inflammation and more broadly with changes in immune variables". However, as many other fields in biology and medicine, immunopsychiatry suffers from a replication crisis characterized by lack of reproducibility. In this paper, we will comment on four types of immune variables which have been studied in psychiatric disorders: Acute Phase Proteins (AAPs), cytokines, lipid mediators of inflammation and immune cell parameters, and discuss the rationale for looking at them in blood. We will briefly describe the analytical methods that are currently used to measure the levels of these biomarkers and comment on overlooked analytical and statistical methodological issues that may explain some of the conflicting data reported in the literature. Lastly, we will briefly summarize what cross-sectional, longitudinal and mendelian randomization studies have brought to our understanding of schizophrenia (SZ).

Factors correlated with therapeutic effects of globus pallidus deep brain stimulation on freezing of gait in advanced Parkinson's disease: A pilot study

INTRODUCTION

Deep brain stimulation (DBS) has showed variable therapeutic effect on freezing of gait (FOG) in Parkinson's disease (PD). It is unclear which factors associated with the effect of DBS on FOG in patients with advanced PD. In this study, we investigated the correlation of pre and postoperative factors with the therapeutic effect of globus pallidus interna (GPi) DBS on FOG in PD patients.

METHODS

We retrospectively analyzed PD patients with FOG (N = 20) who underwent GPi DBS surgery. Postoperatively, video-based analysis for FOG severity was performed at the first DBS programming and patients were categorized into two groups according to DBS effect on FOG (11 FOG responders and 9 FOG non-responders) at medication-off state. We analyzed preoperative clinical characteristics, cognitive function, striatal dopamine transporter availability, postoperative DBS programming parameters, lead locations, and volume of tissue activated in functional subregions of GPi. Bootstrap enhanced Elastic-Net logistic regression was used to select pre and postoperative factors associated with the effect of GPi DBS.

RESULTS

Therapeutic effect of GPi DBS on FOG were correlated with the disease duration of PD before DBS surgery, preoperative improvement in FOG severity by levodopa medication, and the distance from active contact of DBS electrode to the prefrontal region of GPi anatomical site.

CONCLUSIONS

Our study results suggest that the effect of GPi DBS on FOG is correlated with disease duration, levodopa responsiveness on FOG before DBS surgery and DBS electrode location, providing useful information to predict FOG outcome after GPi DBS in PD patients.

Associations between cardiac irradiation and survival in patients with non-small cell lung cancer: Validation and new discoveries in an independent dataset

INTRODUCTION

In 'IDEAL-6' patients (N = 78) treated for locally-advanced non-small-cell lung cancer using isotoxically dose-escalated radiotherapy, overall survival (OS) was associated more strongly with VLAwall-64-73-EQD2, the left atrial (LA) wall volume receiving 64-73 Gy equivalent dose in 2 Gy fractions (EQD2), than with whole-heart irradiation measures. Here we test this in an independent cohort 'OX-RT' (N = 64) treated routinely.

METHODS

Using Cox regression analysis we assessed how strongly OS was associated with VLAwall-64-73-EQD2, with whole-heart volumes receiving 64-73 Gy EQD2 or doses above 10-to-70 Gy thresholds, and with principal components of whole-heart dose-distributions. Additionally, we tested associations between OS and volumes of cardiac substructures receiving dose-ranges described by whole-heart principal components significantly associated with OS.

RESULTS

In univariable analyses of OX-RT, OS was associated more strongly with VLAwall-64-73-EQD2 than with whole-heart irradiation measures, but more strongly still with VAortV-29-38-EQD2, the volume of the aortic valve region receiving 29-38 Gy EQD2. The best multivariable OS model included LA wall and aortic valve region mean doses, and the aortic valve volume receiving ≥38 Gy EQD2, VAortV-38-EQD2. In a subsidiary analysis of IDEAL-6, the best multivariable model included VLAwall-64-73-EQD2, VAortV-29-38-EQD2, VAortV-38-EQD2 and mean aortic valve dose.

CONCLUSION

We propose reducing heart mean doses to the lowest levels possible while meeting protocol dose-limits for lung, oesophagus, proximal bronchial tree, cord and brachial plexus. This in turn achieves large reductions in VAortV-29-38-EQD2 and VLAwall-64-73-EQD2, and we plan to closely monitor patients with values of these measures still >0% (their median value in OX-RT) following reduction.

Blood cytokines differentiate bipolar disorder and major depressive disorder during a major depressive episode: Initial discovery and independent sample replication

Bipolar disorder (BD) diagnosis currently relies on assessment of clinical symptoms, mainly retrospective and subject to memory bias. BD is often misdiagnosed as Major Depressive Disorder (MDD) resulting in ineffective treatment and worsened clinical outcome. The primary purpose of this study was to identify blood biomarkers that discriminate MDD from BD patients when in a depressed state. We have used clinical data and serum samples from two independent naturalistic cohorts of patients with a Major Depressive Episode (MDE) who fulfilled the criteria of either BD or MDD at inclusion. The discovery and replication cohorts consisted of 462 and 133 patients respectively. Patients were clinically assessed using standard diagnostic interviews, and clinical variables including current treatments were recorded. Blood was collected and serum assessed for levels of 31 cytokines using a sensitive multiplex assay. A penalized logistic regression model combined with nonparametric bootstrap was subsequently used to identify cytokines associated with BD. Interleukin (IL)-6, IL-10, IL-15, IL-27 and C-X-C ligand chemokine (CXCL)-10 were positively associated with BD in the discovery cohort. Of the five cytokines identified as discriminant features in the discovery cohort, IL-10, IL-15 and IL-27 were also positively associated with BD in the replication cohort therefore providing an external validation to our finding. Should our results be validated in a prospective cohort, they could provide new insights into the pathophysiological mechanisms of mood disorders.

Extrahippocampal Radiomics Analysis Can Potentially Identify Laterality in Patients With MRI-Negative Temporal Lobe Epilepsy

Objective: The objective of the study was to investigate whether radiomics features of extrahippocampal regions differ between patients with epilepsy and healthy controls, and whether any differences can identify patients with magnetic resonance imaging (MRI)-negative temporal lobe epilepsy (TLE).

Methods: Data from 36 patients with hippocampal sclerosis (HS) and 50 healthy controls were used to construct a radiomics model. A total of 1,618 radiomics features from the affected hippocampal and extrahippocampal regions were compared with features from healthy controls and the unaffected side of patients. Using a stepwise selection method with a univariate t-test and elastic net penalization, significant predictors for identifying TLE were separately selected for the hippocampus (H+) and extrahippocampal region (H–). Each model was independently validated with an internal set of MRI-negative adult TLE patients (n = 22) and pediatric validation cohort with MRI-negative TLE (n = 20) from another tertiary center; diagnostic performance was calculated using area under the curve (AUC) of the receiver-operating-characteristic curve analysis.

Results: Forty-eight significant H+ radiomic features and 99 significant H– radiomic features were selected from the affected side of patients and used to create a hippocampus model and an extrahippocampal model, respectively. Texture features were the most frequently selected feature. Training set showed slightly higher accuracy between hippocampal (AUC = 0.99) and extrahippocampal model (AUC = 0.97). In the internal validation and external validation sets, the extrahippocampal model (AUC = 0.80 and 0.92, respectively) showed higher diagnostic performance for identifying the affected side of patients than the hippocampus model (AUC = 0.67 and 0.69).

Significance: Radiomics revealed extrahippocampal abnormality in the affected side of patients with TLE and could potentially help to identify MRI-negative TLE.

Classification of Evidence: Class IV Criteria for Rating Diagnostic Accuracy Studies.

Circulating inflammatory markers impact cognitive functions in bipolar depression

BACKGROUND

Cognitive impairment is a core feature of bipolar disorder, with a prevalence of about 64.4% during episodes and 57.1% in euthymia. Recent evidences suggest that cognitive deficits in BD may follow immune dysfunction and elevated levels of inflammatory cytokines have been reported during periods of depression, mania and euthymia, suggesting the presence of a chronic, low-grade inflammatory state. The aim of the study is to investigate if immune/inflammatory markers and especially chemokines associate to cognitive performances.

METHODS

Seventy-six consecutively admitted inpatients with a depressive episode in course of bipolar disorder performed a neuropsychological evaluation with the Brief Assessment of Cognition in Schizophrenia and plasma blood levels of cytokines, chemokines and growth factors were analyzed with Luminex technology.

RESULTS

Higher levels of IL-1β, IL-6, CCL2, CCL4, CCL5, CXCL10, and bFGF are associated with the likelihood of having a poor cognitive performance.

LIMITATIONS

Limitation include the lack of a group of healthy controls and the lack of information regarding previous psychopharmacological treatments, alcohol and tobacco use.

CONCLUSIONS

Our results confirm the importance of chemokines in bipolar disorder and suggest that inflammatory markers suggestive of a low-grade inflammatory state could contribute to the neurocognitive deficits observed in depressed patients.

Clinical Outcome Evaluations and CBT Response Prediction in Myotonic Dystrophy

BACKGROUND

The European OPTIMISTIC clinical trial has demonstrated a significant, yet heterogenous effect of Cognitive Behavioural Therapy (CBT) for Myotonic Dystrophy type 1 (DM1) patients. One of its remaining aims was the assessment of efficacy and adequacy of clinical outcome measures, including the relatively novel primary trial outcome, the DM1-Activ-c questionnaire.

OBJECTIVES

Assessment of the relationship between the Rasch-built DM1-Activ-c questionnaire and 26 commonly used clinical outcome measurements. Identification of variables associated with CBT response in DM1 patients.

METHODS

Retrospective analysis of the to date largest clinical trial in DM1 (OPTIMISTIC), comprising of 255 genetically confirmed DM1 patients randomized to either standard care or CBT with optionally graded exercise therapy. Correlations of 27 different outcome measures were calculated at baseline (cross-sectional) and of their respective intervention induced changes (longitudinal). Bootstrap enhanced Elastic-Net (BeEN) regression was validated and implemented to select variables associated with CBT response.

RESULTS

In cross-sectional data, DM1-Activ-c correlated significantly with the majority of other outcome measures, including Six Minute Walk Test and Myotonic Dystrophy Health Index. Fewer and weaker significant longitudinal correlations were observed. Nine variables potentially associated with CBT response were identified, including measures of disease severity, executive cognitive functioning and perceived social support.

CONCLUSIONS

The DM1-Activ-c questionnaire appears to be a well suited cross-sectional instrument to assess a variety of clinically relevant dimensions in DM1. Yet, apathy and experienced social support measures were less well captured. CBT response was heterogenous, requiring careful selection of outcome measures for different disease aspects.

Investigating predictive factors of dialectical behavior therapy skills training efficacy for alcohol and concurrent substance use disorders: A machine learning study

BACKGROUND

Dialectical Behavior Therapy Skills Training (DBT-ST) as stand-alone treatment has demonstrated promising outcomes for the treatment of alcohol use disorder (AUD) and concurrent substance use disorders (SUDs). However, no studies have so far empirically investigated factors that might predict efficacy of this therapeutic model.

METHODS

275 treatment-seeking individuals with AUD and other SUDs were consecutively admitted to a 3-month DBT-ST program (in- + outpatient; outpatient settings). The machine learning routine applied (i.e. penalized regression combined with a nested cross-validation procedure) was conducted in order to estimate predictive values of a wide panel of clinical variables in a single statistical framework on drop-out and substance-use behaviors, dealing with related multicollinearity, and eliminating redundant variables.

RESULTS

The cross-validated elastic net model significantly predicted the drop-out. The bootstrap analysis revealed that subjects who showed substance-use behaviors during the intervention and who were treated with the mixed setting (i.e., in- and outpatient) program, together with higher ASI alcohol scores were associated with an higher probability of drop-out. On the contrary, older subjects, higher levels of education, together with higher scores of DERS awareness subscale were negatively associated to drop-out. Similarly, lifetime co-diagnoses of anxiety, bipolar, and gambling disorders, together with bulimia nervosa negatively predicted the drop-out. The machine learning model did not identify predictive variables of substance-use behaviors during the treatment.

CONCLUSIONS

The DBT-ST program could be considered a valid therapeutic approach especially when AUD and other SUDs co-occur with other psychiatric conditions and, it is carried out as a full outpatient intervention.

Prediction of type 2 diabetes mellitus based on nutrition data

Numerous predictive models for the risk of type 2 diabetes mellitus (T2DM) exist, but a minority of them has implemented nutrition data so far, even though the significant effect of nutrition on the pathogenesis, prevention and management of T2DM has been established. Thus, in the present study, we aimed to build a predictive model for the risk of T2DM that incorporates nutrition data and calculates its predictive performance. We analysed cross-sectional data from 1591 individuals from the population-based Cooperative Health Research in the Region of Augsburg (KORA) FF4 study (2013–14) and used a bootstrap enhanced elastic net penalised multivariate regression method in order to build our predictive model and select among 193 food intake variables. After selecting the significant predictor variables, we built a logistic regression model with these variables as predictors and T2DM status as the outcome. The values of area under the receiver operating characteristic (ROC) curve, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy of our predictive model were calculated. Eleven out of the 193 food intake variables were selected for inclusion in our model, which yielded a value of area under the ROC curve of 0⋅79 and a maximum PPV, NPV and accuracy of 0⋅37, 0⋅98 and 0⋅91, respectively. The present results suggest that nutrition data should be implemented in predictive models to predict the risk of T2DM, since they improve their performance and they are easy to assess.

Systemic inflammation is negatively associated with early post discharge growth following acute illness among severely malnourished children - a pilot study

Background: Rapid growth should occur among children with severe malnutrition (SM) with medical and nutritional management. Systemic inflammation (SI) is associated with death among children with SM and is negatively associated with linear growth. However, the relationship between SI and weight gain during therapeutic feeding following acute illness is unknown. We hypothesised that growth post-hospital discharge is associated with SI among children with SM. Methods: We conducted secondary analysis of data from HIV-uninfected children with SM (n=98) who survived and were not readmitted to hospital during one year of follow-up. We examined the relationship between changes in absolute deficits in weight and mid-upper-arm circumference (MUAC) from enrolment at stabilisation to 60 days and one year later, and untargeted plasma proteome, targeted cytokines/chemokines, leptin, and soluble CD14 using multivariate regularized linear regression. Results: The mean change in absolute deficit in weight and MUAC was -0.50kg (standard deviation; SD±0.69) and -1.20cm (SD±0.89), respectively, from enrolment to 60 days later. During the same period, mean weight and MUAC gain was 3.3g/kg/day (SD±2.4) and 0.22mm/day (SD±0.2), respectively. Enrolment interleukins; IL17-alpha and IL-2, and serum amyloid P were negatively associated with weight and MUAC gain during 60 days. Lipopolysaccharide binding protein and complement component 2 were negatively associated with weight gain only. Leptin was positively associated with weight gain. Soluble CD14, beta-2 microglobulin, and macrophage inflammatory protein 1 beta were negatively associated with MUAC gain only. Glutathione peroxidase 3 was positively associated with weight and MUAC gain during one year. Conclusions: Early post-hospital discharge weight and MUAC gain were rapid and comparable to children with uncomplicated SM treated in the community. Higher concentrations of SI markers were associated with less weight and MUAC gain, suggesting inflammation negatively impacts recovery from wasting. This finding warrants further research on reducing inflammation on growth among children with SM.

A peripheral inflammatory signature discriminates bipolar from unipolar depression: A machine learning approach

BACKGROUND

Mood disorders (major depressive disorder, MDD, and bipolar disorder, BD) are considered leading causes of life-long disability worldwide, where high rates of no response to treatment or relapse and delays in receiving a proper diagnosis (~60% of depressed BD patients are initially misdiagnosed as MDD) contribute to a growing personal and socio-economic burden. The immune system may represent a new target to develop novel diagnostic and therapeutic procedures but reliable biomarkers still need to be found.

METHODS

In our study we predicted the differential diagnosis of mood disorders by considering the plasma levels of 54 cytokines, chemokines and growth factors of 81 BD and 127 MDD depressed patients. Clinical diagnoses were predicted also against 32 healthy controls. Elastic net models, including 5000 non-parametric bootstrapping procedure and inner and outer 10-fold nested cross-validation were performed in order to identify the signatures for the disorders.

RESULTS

Results showed that the immune-inflammatory signature classifies the two disorders with a high accuracy (AUC = 97%), specifically 92% and 86% respectively for MDD and BD. MDD diagnosis was predicted by high levels of markers related to both pro-inflammatory (i.e. IL-1β, IL-6, IL-7, IL-16) and regulatory responses (IL-2, IL-4, and IL-10), whereas BD by high levels of inflammatory markers (CCL3, CCL4, CCL5, CCL11, CCL25, CCL27, CXCL11, IL-9 and TNF-α).

CONCLUSIONS

Our findings provide novel tools for early diagnosis of BD, strengthening the impact of biomarkers research into clinical practice, and new insights for the development of innovative therapeutic strategies for depressive disorders.

Higher baseline interleukin-1β and TNF-α hamper antidepressant response in major depressive disorder

Raised pro-inflammatory immune/inflammatory setpoints, leading to an increased production of peripheral cytokines, have been associated with Major Depressive Disorder (MDD) and with failure to respond to first-line antidepressant drugs. However, the usefulness of these biomarkers in clinical psychopharmacology has been questioned because single findings did not translate into the clinical practice, where patients are prescribed treatments upon clinical need. We studied a panel of 27 inflammatory biomarkers in a sample of 108 inpatients with MDD, treated with antidepressant monotherapy for 4 weeks upon clinical need in a specialized hospital setting, and assessed the predictive effect of baseline peripheral measures of inflammation on antidepressing efficacy (response rates and time-lagged pattern of decrease of depression severity) using a machine-learning approach with elastic net penalized regression, and multivariate analyses in the context of the general linear model. When considering both categorical and continuous measures of response, baseline levels of IL-1β predicted non-response to antidepressants, with the predicted probability to respond being highly dispersed at low levels of IL-1β, and stratifying toward non-response when IL-1β is high. Significant negative effects were also detected for TNF-α, while IL-12 weakly predicted response. These findings support the usefulness of inflammatory biomarkers in the clinical psychopharmacology of depression, and add to ongoing research efforts aiming at defining reliable cutoff values to identify depressed patients in clinical settings with high inflammation, and low probability to respond.

Intrinsic network interactions explain individual differences in mentalizing ability in adolescents

Mentalizing is an important aspect of social cognition and people vary in their ability to mentalize. Despite initial evidence that mentalizing continues to develop throughout adolescence, it is unclear which neural mechanisms underlie individual variability in mentalizing ability in adolescents. Interactions within and between the default-mode network (DMN), frontoparietal network (FPN) and cingulo-opercular/salience network (CO/SN) have been related to inter-individual differences in cognitive processes in both adults and adolescents. Here, we investigated whether intrinsic connectivity within and between these brain networks explained inter-individual differences in affective mentalizing ability in adolescents. Resting-state brain activity was measured using functional MRI and affective mentalizing ability was defined as correct performance on the Reading the Mind in the Eyes test performed outside the scanner. We identified the DMN, FPN and CO/SN, and within and between network connectivity values were submitted to a bootstrapping enhanced penalized multiple regression analysis to predict mentalizing in 66 young adolescents (11-14 years). We showed that stronger connectivity between the DMN and the FPN, together with lower within-network connectivity of the FPN and the CO/SN predicted better mentalizing performance. These novel findings provide insight into the normative developmental trajectory of the neural mechanisms underlying affective mentalizing in early adolescence.

Tumor response prediction in 90Y radioembolization with PET-based radiomics features and absorbed dose metrics

Purpose

To evaluate whether lesion radiomics features and absorbed dose metrics extracted from post-therapy ⁹⁰Y PET can be integrated to better predict outcomes in microsphere radioembolization of liver malignancies

Methods

Given the noisy nature of ⁹⁰Y PET, first, a liver phantom study with repeated acquisitions and varying reconstruction parameters was used to identify a subset of robust radiomics features for the patient analysis. In 36 radioembolization procedures, ⁹⁰Y PET/CT was performed within a couple of hours to extract 46 radiomics features and estimate absorbed dose in 105 primary and metastatic liver lesions. Robust radiomics modeling was based on bootstrapped multivariate logistic regression with shrinkage regularization (LASSO) and Cox regression with LASSO. Nested cross-validation and bootstrap resampling were used for optimal parameter/feature selection and for guarding against overfitting risks. Spearman rank correlation was used to analyze feature associations. Area under the receiver-operating characteristics curve (AUC) was used for lesion response (at first follow-up) analysis while Kaplan-Meier plots and c-index were used to assess progression model performance. Models with absorbed dose only, radiomics only, and combined models were developed to predict lesion outcome.

Results

The phantom study identified 15/46 reproducible and robust radiomics features that were subsequently used in the patient models. A lesion response model with zone percentage (ZP) and mean absorbed dose achieved an AUC of 0.729 (95% CI 0.702–0.758), and a progression model with zone size nonuniformity (ZSN) and absorbed dose achieved a c-index of 0.803 (95% CI 0.790–0.815) on nested cross-validation (CV). Although the combined models outperformed the radiomics only and absorbed dose only models, statistical significance was not achieved with the current limited data set to establish expected superiority.

Conclusion

We have developed new lesion-level response and progression models using textural radiomics features, derived from ⁹⁰Y PET combined with mean absorbed dose for predicting outcome in radioembolization. These encouraging, but limited results, will need further validation in independent and larger datasets prior to any clinical adoption.

Supplementary Information

Supplementary information accompanies this paper at 10.1186/s40658-020-00340-9.

Systemic inflammation is negatively associated with early post discharge growth following acute illness among severely malnourished children - a pilot study

Background: Rapid growth should occur among children with severe malnutrition (SM) when medically and nutritionally treated. Systemic inflammation (SI) is associated with death among children with SM and is negatively associated with linear growth. However, the relationship between SI and weight gain during therapeutic feeding following acute illness is unknown. We hypothesised that growth in the first 60 days post-hospital discharge is associated with SI among children with SM. Methods: We conducted secondary analysis of data from HIV-uninfected children with SM (n=98) who survived and were not readmitted to hospital during one year of follow up. We examined the relationship between changes in absolute deficits in weight and mid-upper-arm circumference (MUAC) from enrolment at stabilisation to 60 days later and untargeted plasma proteome, targeted cytokines/chemokines, leptin, and soluble CD14 (sCD14) using multivariate regularized linear regression. Results: The mean change in absolute deficit in weight and MUAC was -0.50kg (standard deviation; SD±0.69) and -1.20cm (SD±0.89), respectively, from enrolment to 60 days later. During the same period, mean weight and MUAC gain was 3.3g/kg/day (SD±2.4) and 0.22mm/day (SD±0.2), respectively. Enrolment inflammatory cytokines interleukin 17 alpha (IL17α), interleukin 2 (IL2), and serum amyloid P (SAP) were negatively associated with weight and MUAC gain. Lipopolysaccharide binding protein (LBP) and complement component 2 were negatively associated with weight gain only. Leptin was positively associated with weight gain. sCD14, beta-2 microglobulin (β2M), and macrophage inflammatory protein 1 beta (MIP1β) were negatively associated with MUAC gain only. Conclusions: Early post-hospital discharge weight and MUAC gain were rapid and comparable to children with uncomplicated SM treated with similar diet in the community. Higher concentrations of SI markers were associated with less weight and MUAC gain, suggesting inflammation negatively impacts recovery from wasting. This finding warrants further research on the role of inflammation on growth among children with SM.

Immune activity at birth and later psychopathology in childhood

Disruption of neurodevelopmental trajectories can alter brain circuitry and increase the risk of psychopathology later in life. While preclinical studies have demonstrated that the immune system and cytokines influence neurodevelopment, whether immune activity and in particular which cytokines at birth are associated with psychopathology remains poorly explored in children. We used data and biological samples from 869 mother-child pairs participating in the French mother-child cohort EDEN. As proxies for immune activity at birth, we measured the levels of 27 cytokines in umbilical cord blood sera (CBS). We then explored the association between CBS cytokine levels and five psychopathological dimensions assessed in 5-year-old children using the Strengths and Difficulties Questionnaire (SDQ). Five cytokines were positively associated with psychopathology: C-X-C motif chemokine Ligand (CXCL)10, interleukin (IL)-10 and IL-12p40 with emotional symptoms, C–C motif chemokine Ligand (CCL)11 with conduct problems, and CCL11, and IL-17A with peer relationships problems. In contrast, seven cytokines were negatively associated with psychopathology: IL-7, IL-15 and Tumor Necrosis Factor (TNF)-β with emotional symptoms, CCL4 and IL-6 with conduct problems, CCL26 and IL-15 with peer relationships problems, and CCL26, IL-7, IL-15, and TNF-α with abnormal prosocial behavior. Without implying causation, these associations support the notion that cytokines influence neurodevelopment in humans and the risk of psychopathology later in life.

•

Twelve cytokines at birth are associated with psychopathology in 5-year-old children.

•

IL-7, IL-10, IL-12p40, IL-15, TNF-β and CXCL10 are associated with emotional symptoms.

•

IL-6, CCL4 and CCL11 are associated with conduct problems.

•

IL-15, IL-17A, CCL11 and CCL26 are associated with peer relationship problems.

•

IL-7, IL-15, TNF-α and CCL26 are associated with prosocial behavior.

Limnological Differences in a Two-Basin Lake Help to Explain the Occurrence of Anatoxin-a, Paralytic Shellfish Poisoning Toxins, and Microcystins

Chautauqua Lake, New York, is a two-basin lake with a deeper, cooler, and less nutrient-rich Northern Basin, and a warmer, shallower, nutrient-replete Southern Basin. The lake is populated by a complex mixture of cyanobacteria, with toxigenic strains that produce microcystins, anatoxins, and paralytic shellfish poisoning toxins (PSTs). Samples collected from 24 sites were analyzed for these three toxin classes over four years spanning 2014-2017. Concentrations of the three toxin groups varied widely both within and between years. During the study, the mean and median concentrations of microcystins, anatoxin-a, and PSTs were 91 and 4.0 μg/L, 0.62 and 0.33 μg/L, and 32 and 16 μg/L, respectively. Dihydro-anatoxin was only detected once in Chautauqua Lake, while homo-anatoxin was never detected. The Northern Basin had larger basin-wide higher biomass blooms with higher concentrations of toxins relative to the more eutrophied Southern Basin, however blooms in the North Basin were infrequent. Chlorophyll concentrations and toxins in the two basins were correlated with different sets of environmental and physical parameters, suggesting that implementing controls to reduce toxin loads may require applications focused on more than reductions in cyanobacterial bloom density (e.g., reduction of phosphorus inputs), and that lake limnological factors and morphology are important determinants in the selection of an appropriate management strategy. Chautauqua Lake is a drinking water source and is also heavily used for recreation. Drinking water from Chautauqua Lake is unlikely to be a significant source of exposure to cyanotoxins due to the location of the intakes in the deeper North Basin, where there were generally low concentrations of toxins in open water; however, toxin levels in many blooms exceeded the US Environmental Protection Agency's recreational guidelines for exposure to cyanotoxins. Current cyanotoxin monitoring in Chautauqua Lake is focused on microcystins. However, the occurrence of blooms containing neurotoxic cyanotoxins in the absence of the microcystins indicates this restricted monitoring may not be sufficient when aiming to protect against exposure to cyanotoxins. The lake has a large number of tourist visitors; thus, special care should be taken to prevent recreational exposure within this group.

Drawing the borderline: Predicting treatment outcomes in patients with borderline personality disorder

BACKGROUND

A routinely collected big data set was analyzed to determine the effectiveness of naturalistic inpatient treatment and to identify predictors of treatment outcome and discontinuation.

METHODS

The sample included 878 patients with borderline personality disorder who received non-manualized dialectic behavioral therapy in a psychosomatic clinic. Effect sizes (Hedge's g) were calculated to determine effectiveness. A bootstrap-enhanced regularized regression with 91 potential predictors was used to identify stable predictors of residualized symptom- and functional change and treatment discontinuation. Results were validated in a holdout sample and repeated cross validation.

RESULTS

Effect sizes were small to medium (g = 0.28-0.51). Positive symptom-related outcome was predicted by low affect regulation skills and no previous outpatient psychotherapy. Lower age, absence of work disability, high emotional and physical role limitations and low bodily pain were associated with greater improvement in functional outcome. Higher education and comorbid recurrent depressive disorder were the main predictors of treatment completion. The predictive quality of the models varied, with the best being found for symptom-related outcome (R2 = 18%).

CONCLUSION

While the exploratory process of variable selection replicates previous findings, the validation results suggest that tailoring treatment to the individual patient might not be based solely on sociodemographic, clinical and psychological baseline data.

Serum cytokines associated with behavior: A cross-sectional study in 5-year-old children

Nearly 10% of 5-year-old children experience social, emotional or behavioral problems and are at increased risk of developing mental disorders later in life. While animal and human studies have demonstrated that cytokines can regulate brain functions, it is unclear whether individual cytokines are associated with specific behavioral dimensions in population-based pediatric samples. Here, we used data and biological samples from 786 mother-child pairs participating to the French national mother-child cohort EDEN. At the age of 5, children were assessed for behavioral difficulties using the Strengths and Difficulties Questionnaire (SDQ) and had their serum collected. Serum samples were analyzed for levels of well-characterized effector or regulatory cytokines. We then used a penalized logistic regression method (Elastic Net), to investigate associations between serum levels of cytokines and each of the five SDQ-assessed behavioral dimensions after adjustment for relevant covariates and confounders, including psychosocial variables. We found that interleukin (IL)-6, IL-7, and IL-15 were associated with increased odds of problems in prosocial behavior, emotions, and peer relationships, respectively. In contrast, eight cytokines were associated with decreased odds of problems in one dimension: IL-8, IL-10, and IL-17A with emotional problems, Tumor Necrosis Factor (TNF)-α with conduct problems, C-C motif chemokine Ligand (CCL)2 with hyperactivity/inattention, C-X-C motif chemokine Ligand (CXCL)10 with peer problems, and CCL3 and IL-16 with abnormal prosocial behavior. Without implying causation, these associations support the notion that cytokines regulate brain functions and behavior and provide a rationale for launching longitudinal studies.

Novel Methodology to Investigate the Effect of Radiation Dose to Heart Substructures on Overall Survival

PURPOSE

For patients with lung cancer treated with radiation therapy, a dose to the heart is associated with excess mortality; however, it is often not feasible to spare the whole heart. Our aim is to define cardiac substructures and dose thresholds that optimally reduce early mortality.

METHODS AND MATERIALS

Fourteen cardiac substructures were delineated on 5 template patients with representative anatomies. One thousand one hundred sixty-one patients with non-small cell lung cancer were registered nonrigidly to these 5 template anatomies, and their radiation therapy doses were mapped. Mean and maximum dose to each substructure were extracted, and the means were evaluated as input to prediction models. The cohort was bootstrapped into 2 variable reduction techniques: elastic net least absolute shrinkage and selection operator and the random survival forest model. Each method was optimized to extract variables contributing most to overall survival, and model coefficients were evaluated to select these substructures. The most important variables common to both models were selected and evaluated in multivariable Cox-proportional hazard models. A threshold dose was defined, and Kaplan-Meier survival curves plotted.

RESULTS

Nine hundred seventy-eight patients remained after visual quality assurance of the registration. Ranking the model coefficients across the bootstraps selected the maximum dose to the right atrium, right coronary artery, and ascending aorta as the most important factors associated with survival. The maximum dose to the combined cardiac region showed significance in the multivariable model, a hazard ratio of 1.01/Gy, and P = .03 after accounting for tumor volume (P < .001), N stage (P < .01), and performance status (P = .01). The optimal threshold for the maximum dose, equivalent dose in 2-Gy fractions, was 23 Gy. Kaplan-Meier survival curves showed a significant split (log-rank P = .008).

CONCLUSIONS

The maximum dose to the combined cardiac region encompassing the right atrium, right coronary artery, and ascending aorta was found to have the greatest effect on patient survival. A maximum equivalent dose in 2-Gy fractions of 23 Gy was identified for consideration as a dose limit in future studies.

Oxytocin Enhances an Amygdala Circuit Associated With Negative Symptoms in Schizophrenia: A Single-Dose, Placebo-Controlled, Crossover, Randomized Control Trial

Negative symptoms are core contributors to vocational and social deficits in schizophrenia (SZ). Available antipsychotic medications typically fail to reduce these symptoms. The neurohormone oxytocin (OT) is a promising treatment for negative symptoms, given its role in complex social behaviors mediated by the amygdala. In sample 1, we used a double-blind, placebo-controlled, crossover design to test the effects of a single dose of intranasal OT on amygdala resting-state functional connectivity (rsFC) in SZ (n = 22) and healthy controls (HC, n = 24) using a whole-brain corrected approach: we identified regions for which OT modulated SZ amygdala rsFC, assessed whether OT-modulated circuits were abnormal in SZ relative to HC on placebo, and evaluated whether connectivity on placebo and OT-induced connectivity changes correlated with baseline negative symptoms in SZ. Given our modest sample size, we used a second SZ (n = 183) and HC (n = 178) sample to replicate any symptom correlations. In sample 1, OT increased rsFC between the amygdala and left middle temporal gyrus, superior temporal sulcus, and angular gyrus (MTG/STS/AngG) in SZ compared to HC. Further, SZ had hypo-connectivity in this circuit compared to HC on placebo. More severe negative symptoms correlated with less amygdala-to-left-MTG/STS/AngG connectivity on placebo and with greater OT-induced connectivity increases. In sample 2, we replicated the correlation between amygdala-left-MTG/STS/AngG hypo-connectivity and negative symptoms, finding a specific association with expressive negative symptoms. These data suggest intranasal OT can normalize functional connectivity in an amygdala-to-left-MTG/STS/AngG circuit that contributes to negative symptoms in SZ.

Bootstrapping promotes the RSFC-behavior associations: An application of individual cognitive traits prediction

Resting‐state functional connectivity (RSFC) records enormous functional interaction information between any pair of brain nodes, which enriches the individual‐phenotypic prediction. To reduce high‐dimensional features, correlation analysis is a common way for feature selection. However, resting state fMRI signal exhibits typically low signal‐to‐noise ratio and the correlation analysis is sensitive to outliers and data distribution, which may bring unstable features to prediction. To alleviate this problem, a bootstrapping‐based feature selection framework was proposed and applied to connectome‐based predictive modeling, support vector regression, least absolute shrinkage and selection operator, and Ridge regression to predict a series of cognitive traits based on Human Connectome Project data. To systematically investigate the influences of different parameter settings on the bootstrapping‐based framework, 216 parameter combinations were evaluated and the best performance among them was identified as the final prediction result for each cognitive trait. By using the bootstrapping methods, the best prediction performances outperformed the baseline method in all four prediction models. Furthermore, the proposed framework could effectively reduce the feature dimension by retaining the more stable features. The results demonstrate that the proposed framework is an easy‐to‐use and effective method to improve RSFC prediction of cognitive traits and is highly recommended in future RSFC‐prediction studies.

Proinflammatory Cytokines Predict Brain Metabolite Concentrations in the Anterior Cingulate Cortex of Patients With Bipolar Disorder

Bipolar disorder (BD) is a severe psychiatric illness characterized by abnormalities in the immune/inflammatory function and in brain metabolism. Evidences suggest that inflammation may affect the levels of brain metabolites as measured by single-proton magnetic resonance spectroscopy (¹H-MRS). The aim of the study was to investigate whether a wide panel of inflammatory markers (i.e., cytokines, chemokines, and growth factors) can predict brain metabolite concentrations of glutamate, myo-inositol, N-acetylaspartate, and glutathione in a sample of 63 bipolar patients and 49 healthy controls. Three cytokines influenced brain metabolite concentrations: IL-9 positively predicts glutamate, IL-1β positively predicts Myo-inositol, and CCL5 positively predicts N-acetylaspartate concentrations. Furthermore, patients showed higher concentrations of glutamate, Myo-inositol, and glutathione and lower concentrations of N-acetylaspartate in respect to healthy controls. Our results confirm that inflammation in BD alters brain metabolism, through mechanisms possibly including the production of reactive oxygen species and glia activation.