Search

Background: Electroconvulsive therapy (ECT) is the most effective intervention for patients with treatment resistant depression. A clinical decision support tool could guide patient selection to improve the overall response rate and avoid ineffective treatments with adverse effects. Initial small-scale, monocenter studies indicate that both structural magnetic resonance imaging (sMRI) and functional MRI (fMRI) biomarkers may predict ECT outcome, but it is not known whether those results can generalize to data from other centers. The objective of this study was to develop and validate neuroimaging biomarkers for ECT outcome in a multicenter setting., Methods: Multimodal data (i.e. clinical, sMRI and resting-state fMRI) were collected from seven centers of the Global ECT-MRI Research Collaboration (GEMRIC). We used data from 189 depressed patients to evaluate which data modalities or combinations thereof could provide the best predictions for treatment remission (HAM-D score ⩽7) using a support vector machine classifier., Results: Remission classification using a combination of gray matter volume and functional connectivity led to good performing models with average 0.82-0.83 area under the curve (AUC) when trained and tested on samples coming from the three largest centers ( N = 109), and remained acceptable when validated using leave-one-site-out cross-validation (0.70-0.73 AUC)., Conclusions: These results show that multimodal neuroimaging data can be used to predict remission with ECT for individual patients across different treatment centers, despite significant variability in clinical characteristics across centers. Future development of a clinical decision support tool applying these biomarkers may be feasible.

Introduction: Electroconvulsive therapy (ECT) and ketamine are two effective treatments for depression with similar efficacy; however, individual patient outcomes may be improved by models that predict optimal treatment assignment. Here, we adapt the Personalized Advantage Index (PAI) algorithm using machine learning to predict optimal treatment assignment between ECT and ketamine using medical record data from a large, naturalistic patient cohort. We hypothesized that patients who received a treatment predicted to be optimal would have significantly better outcomes following treatment compared to those who received a non-optimal treatment., Methods: Data on 2526 ECT and 235 mixed IV ketamine and esketamine patients from McLean Hospital was aggregated. Depressive symptoms were measured using the Quick Inventory of Depressive Symptomatology (QIDS) before and during acute treatment. Patients were matched between treatments on pretreatment QIDS, age, inpatient status, and psychotic symptoms using a 1:1 ratio yielding a sample of 470 patients (n=235 per treatment). Random forest models were trained and predicted differential patientwise minimum QIDS scores achieved during acute treatment (min-QIDS) scores for ECT and ketamine using pretreatment patient measures. Analysis of Shapley Additive exPlanations (SHAP) values identified predictors of differential outcomes between treatments., Results: Twenty-seven percent of patients with the largest PAI scores who received a treatment predicted optimal had significantly lower min-QIDS scores compared to those who received a non-optimal treatment (mean difference=1.6, t=2.38, q<0.05, Cohen's D=0.36). Analysis of SHAP values identified prescriptive pretreatment measures., Conclusions: Patients assigned to a treatment predicted to be optimal had significantly better treatment outcomes. Our model identified pretreatment patient factors captured in medical records that can provide interpretable and actionable guidelines treatment selection., Competing Interests: Conflict of Interest JL has received funding from Harvard Medical School and the National Institute of Mental Health. He has received equity from Revival Therapeutics. The remaining authors report no conflict of interest.

Repetitive transcranial magnetic stimulation (rTMS) is an effective treatment for depression and has been shown to modulate resting-state functional connectivity (RSFC) of depression-relevant neural circuits. To date, however, few studies have investigated whether individual treatment-related symptom changes are predictable from pretreatment RSFC. We use machine learning to predict dimensional changes in depressive symptoms using pretreatment patterns of RSFC. We hypothesized that changes in dimensional depressive symptoms would be predicted more accurately than scale total scores. Patients with depression (n=26) underwent pretreatment RSFC MRI. Depressive symptoms were assessed with the 17-item Hamilton Depression Rating Scale (HDRS-17). Random forest regression (RFR) models were trained and tested to predict treatment-related symptom changes captured by the HDRS-17, HDRS-6 and three previously identified HDRS subscales: core mood/anhedonia (CMA), somatic disturbances, and insomnia. Changes along the CMA, HDRS-17, and HDRS-6 were predicted significantly above chance, with 9%, 2%, and 2% of out-of-sample outcome variance explained, respectively (all p<0.01). CMA changes were predicted more accurately than the HDRS-17 (p<0.05). Higher baseline global connectivity (GC) of default mode network (DMN) subregions and the somatomotor network (SMN) predicted poorer symptom reduction, while higher GC of the right dorsal attention (DAN) frontoparietal control (FPCN), and visual networks (VN) predicted reduced CMA symptoms. HDRS-17 and HDRS-6 changes were predicted with similar GC patterns. These results suggest that RSFC spanning the DMN, SMN, DAN, FPCN, and VN subregions predict dimensional changes with greater accuracy than syndromal changes following rTMS. These findings highlight the need to assess more granular clinical dimensions in therapeutic studies, particularly device neuromodulation studies, and echo earlier studies supporting that dimensional outcomes improve model accuracy., Competing Interests: Conflict of Interest The authors report no conflict of interest.

Neurostimulation is a mainstream treatment option for major depression. Neuromodulation techniques apply repetitive magnetic or electrical stimulation to some neural target but significantly differ in their invasiveness, spatial selectivity, mechanism of action, and efficacy. Despite these differences, recent analyses of transcranial magnetic stimulation (TMS) and deep brain stimulation (DBS)-treated individuals converged on a common neural network that might have a causal role in treatment response. We set out to investigate if the neuronal underpinnings of electroconvulsive therapy (ECT) are similarly associated with this common causal network (CCN). Our aim here is to provide a comprehensive analysis in three cohorts of patients segregated by electrode placement (N = 246 with right unilateral, 79 with bitemporal, and 61 with mixed) who underwent ECT. We conducted a data-driven, unsupervised multivariate neuroimaging analysis (Principal Component Analysis, PCA) of the cortical and subcortical volume changes and electric field (EF) distribution to explore changes within the CCN associated with antidepressant outcomes. Despite the different treatment modalities (ECT vs TMS and DBS) and methodological approaches (structural vs functional networks), we found a highly similar pattern of change within the CCN in the three cohorts of patients (spatial similarity across 85 regions: r = 0.65, 0.58, 0.40, df = 83). Most importantly, the expression of this pattern correlated with clinical outcomes. This evidence further supports that treatment interventions converge on a CCN in depression. Optimizing modulation of this network could serve to improve the outcome of neurostimulation in depression., Competing Interests: Conflict of Interest Joan A. Campordon is a member of the scientific advisory board of Hyka and Flow Neuroscience and has been a consultant for Mifu Technologies. Rene Hurlemann received lecture fees from Lundbeck, Otsuka, Rovi and honoraria of Atheneum Consultation, Janssen und Rovi. Antoine Yrondi received speaker’s honoraria from AstraZeneca, Lundbeck, Janssen and Jazz. None of the above is related to this data, analysis or the writing of this manuscript. The other authors declared no conflict of interests.

Background: Anthropogenic disturbance has the potential to negatively affect wildlife health by altering food availability and diet composition, increasing the exposure to agrochemicals, and intensifying the contact with humans, domestic animals, and their pathogens. However, the impact of these factors on the fecal microbiome composition of wildlife hosts and its link to host health modulation remains barely explored. Here we investigated the composition of the fecal bacterial microbiome of the insectivorous bat Kuhl's pipistrelle (Pipistrellus kuhlii) dwelling in four environmental contexts with different levels of anthropogenic pressure. We analyzed their microbiome composition, structure and diversity through full-length 16S rRNA metabarcoding using the nanopore long-read sequencer MinION™. We hypothesized that the bacterial community structure of fecal samples would vary across the different scenarios, showing a decreased diversity and richness in samples from disturbed ecosystems., Results: The fecal microbiomes of 31 bats from 4 scenarios were sequenced. A total of 4,829,302 reads were obtained with a taxonomic assignment percentage of 99.9% at genus level. Most abundant genera across all scenarios were Enterococcus, Escherichia/Shigella, Bacillus and Enterobacter. Alpha diversity varied significantly between the four scenarios (p < 0.05), showing the lowest Shannon index in bats from urban and intensive agriculture landscapes, while the highest alpha diversity value was found in near pristine landscapes. Beta diversity obtained by Bray-Curtis distance showed weak statistical differentiation of bacterial taxonomic profiles among scenarios. Furthermore, core community analysis showed that 1,293 genera were shared among localities. Differential abundance analyses showed that the highest differentially abundant taxa were found in near pristine landscapes, with the exception of the family Alcaligenaceae, which was also overrepresented in urban and intensive agriculture landscapes., Conclusions: This study suggests that near pristine and undisturbed landscapes could promote a more resilient gut microbiome in wild populations of P. kuhlii. These results highlight the potential of the fecal microbiome as a non-invasive bioindicator to assess insectivorous bats' health and as a key element of landscape conservation strategies., (© 2023. The Author(s).)