Neurocognitive function as outcome and predictor for prefrontal transcranial direct current stimulation in major depressive disorder: an analysis from the DepressionDC trial.

Transcranial direct current stimulation (tDCS) of the prefrontal cortex might beneficially influence neurocognitive dysfunctions associated with major depressive disorder (MDD). However, previous studies of neurocognitive effects of tDCS have been inconclusive. In the current study, we analyzed longitudinal, neurocognitive data from 101 participants of a randomized controlled multicenter trial (DepressionDC), investigating the efficacy of bifrontal tDCS (2 mA, 30 min/d, for 6 weeks) in patients with MDD and insufficient response to selective serotonin reuptake inhibitors (SSRI). We assessed whether active tDCS compared to sham tDCS elicited beneficial effects across the domains of memory span, working memory, selective attention, sustained attention, executive process, and processing speed, assessed with a validated, digital test battery. Additionally, we explored whether baseline cognitive performance, as a proxy of fronto-parietal-network functioning, predicts the antidepressant effects of active tDCS versus sham tDCS. We found no statistically significant group differences in the change of neurocognitive performance between active and sham tDCS. Furthermore, baseline cognitive performance did not predict the clinical response to tDCS. Our findings indicate no advantage in neurocognition due to active tDCS in MDD. Additional research is required to systematically investigate the effects of tDCS protocols on neurocognitive performance in patients with MDD.

Digitalising mental health care: Practical recommendations from the European Psychiatric Association.

The digitalisation of mental health care is expected to improve the accessibility and quality of specialised treatment services and introduce innovative methods to study, assess, and monitor mental health disorders. In this narrative review and practical recommendation of the European Psychiatric Association (EPA), we aim to help healthcare providers and policymakers to navigate this rapidly evolving field. We provide an overview of the current scientific and implementation status across two major domains of digitalisation: i) digital mental health interventions and ii) digital phenotyping, discuss the potential of each domain to improve the accessibility and outcomes of mental health services, and highlight current challenges faced by researchers, clinicians, and service users. Furthermore, we make several recommendations meant to foster the widespread adoption of evidence-based digital solutions for mental health care in the member states of the EPA. To realise the vision of a digitalised, patient-centred, and data-driven mental health ecosystem, a number of implementation challenges must be considered and addressed, spanning from human, technical, ethical-legal, and economic barriers. The list of priority areas and action points our expert panel has identified could serve as a playbook for this process.

Driving-related cognitive skills during antidepressant transcranial direct current stimulation: results in a subsample from the DepressionDC trial.

Therapeutic transcranial direct current stimulation (tDCS) is a well-tolerated neuromodulatory intervention. However, there are currently no data on its impact on driving skills. Therefore, we conducted a validated assessment of driving-related cognitive skills in participants of the DepressionDC trial, a multicenter, randomized-controlled trial investigating the antidepressant effects of 6-week prefrontal tDCS in patients with major depressive disorder (MDD). Twenty-one patients (12 women, active tDCS, n = 11, sham, n = 10) underwent an assessment of driving-related cognitive skills before and after the intervention. Using a Bayesian analysis approach, we found no group differences between active tDCS and sham tDCS in the pre-post treatment changes for visual perception (estimated median difference: 3.41 [-3.17, 10.55 89%-CI], BF01: 2.1), stress tolerance (estimated median difference: 0.77 [-2.40, 4.15 89%-CI], BF01: 1.6), and reaction time (estimated median difference: 2.06 [-12.33, 16.83 89%-CI], BF01: 6.5). Our results indicate that repeated sessions of a conventional bifrontal tDCS protocol do not negatively impact driving-related cognitive skills in patients with MDD.

Transcranial direct current stimulation as treatment for major depression in a home treatment setting (HomeDC trial): study protocol and methodology of a double-blind, placebo-controlled pilot study.

INTRODUCTION: Transcranial direct current stimulation (tDCS) of prefrontal cortex regions has been reported to exert therapeutic effects in patients with major depressive disorder (MDD). Due to its beneficial safety profile, its easy mode of application, and its cost-effectiveness, tDCS has recently been proposed for treatment at home. This would offer new chances for regionally widespread and long-term application. However, tDCS at home must meet the new methodological challenges of handling and adherence. At the same time, data from randomized controlled trials (RCT) investigating this mode of application are still lacking. In this pilot RCT, we therefore investigate the feasibility, safety, and effectiveness of a new antidepressant tDCS application set-up. METHODS AND ANALYSIS: The HomeDC trial will be conducted as a double-blind, placebo-controlled, parallel-group design trial. Thirty-two study participants with MDD will be randomly assigned to active or sham tDCS groups. Participants will self-administer prefrontal tDCS for 6 weeks. Active tDCS will be conducted with anode over F3, cathode over F4, for 5 sessions/week, with a duration of 30 min/day, and 2 mA stimulation intensity. Sham tDCS, conversely, follows an identical protocol in regard to electrode montage and timing, but with no electric stimulation between the ramp-in and ramp-out periods. Both conditions will be administered either as a monotherapy or an adjunctive treatment to a stable dose of antidepressant medication. Adjunctive magnetic resonance imaging (MRI) and electric field (E-field) modelling will be conducted at baseline. Primary outcome is feasibility based on successfully completed stimulations and drop-out rates. The intervention is considered feasible when 20 out of 30 sessions have been fully conducted by at least 75% of the participants. Effectiveness and safety will be assessed as secondary outcomes. DISCUSSION: In the HomeDC trial, the technical requirements for a placebo-controlled tDCS study in a home-based treatment setting have been established. The trial addresses the crucial points of the home-based tDCS treatment approach: uniform electrode positioning, frequent monitoring of stimulation parameters, adherence, and ensuring an appropriate home treatment environment. This study will further identify constraints and drawbacks of this novel mode of treatment. TRIAL REGISTRATION: www. CLINICALTRIALS: gov . TRIAL REGISTRATION NUMBER: NCT05172505. Registration date: 12/13/2021.

Suicidal behaviors and adverse childhood experiences: A cross-diagnostic study in persistent depressive disorder and borderline personality disorder.

Adverse childhood experiences (ACE) constitute a known risk factor for suicidality. There is a research gap regarding differential patterns of associations between variants of suicidal ideations and behaviors (SIB) and characteristics of ACE in severe mental disorders. This cross-diagnostic study investigates whether SIB are related to ACE subtypes in two high-risk conditions, i.e., persistent depressive disorder (PDD) and borderline personality disorder (BPD). Inpatients with PDD (n = 117; age 40.2 years ± 12.3) and BPD (n = 74; age 26.2 ± 7.9) were assessed with the Columbia-Suicide Severity Rating Scale for suicidal ideations (SI), suicidal behaviors (SB) and actual suicide attempts (SA); ACE were recorded with the Childhood Trauma Questionnaire. In PDD, SI and SA were associated with childhood physical abuse (ORs 7.2 and 2.3, respectively). In BPD, SA were associated with severe experiences of physical abuse (OR 6.5). Weaker yet significant associations were found for childhood emotional abuse in PDD with SB (including SA), and in BPD with SA. Recall of childhood physical abuse may be clinically relevant information for identifying particular risks of SIB. Future studies should investigate these differential patterns in more depth and in terms of causality.

Transdiagnostic analysis of adverse childhood experiences and their association with psychopathology-A TRANS-D conform study.

Transdiagnostic approaches challenge traditional psychiatric classification systems. Adverse childhood experiences (ACE) represent a transdiagnostic risk factor for psychopathology with dose dependency. As different qualities of ACE typically co-occur, we identified ACE patterns to assess their power for predicting psychopathology compared to traditional diagnoses. Following TRANS-D guidelines, we categorized participants (N=360) with persistent depressive disorder (PDD), borderline personality disorder (BPD), or healthy control status (HC) into subcategories defined by ACE pattern, using the Childhood Trauma Questionnaire (CTQ). Improvement of the transdiagnostic vs. diagnostic approach in predicting psychopathology was evaluated in a cross-validated predictive modeling framework focusing on the clinical sample of PDD and BPD patients. Results were externally validated in another transdiagnostic sample (N=138). Seven pattern-based subcategories with distinct ACE profiles were identified in the primary sample and replicated in the validation sample. Patterns cut across diagnostic groups. Predictive modeling showed that diagnoses could not predict depressive symptoms and loneliness. Transdiagnostic constructs systematically predicted all measures. This study showcases ACE as a promising construct for transdiagnostic research. Our data-driven framework identified robust ACE subcategories mapping onto general and interpersonal psychopathology. Patterns of CTQ-based information may provide an approach to integrating information on co-occurring ACE to inform diagnostics and treatment.

Association between Mood and Sensation Seeking Following rTMS.

Previous studies investigating mood changes in healthy subjects after prefrontal repetitive transcranial magnetic stimulation (rTMS) have shown largely inconsistent results. This may be due to methodological issues, considerable inter-individual variation in prefrontal connectivity or other factors, e.g., personality traits. This pilot study investigates whether mood changes after rTMS are affected by personality parameters. In a randomized cross-over design, 17 healthy volunteers received three sessions of 1 Hz rTMS to Fz, F3 and T3 (10/20 system). The T3 electrode site served as the control condition with the coil angled 45° to the scalp. Subjective mood was rated at baseline and after each condition. Personality traits were assessed using the NEO Five-Factor Inventory (NEO-FFI) and the Sensation Seeking Scale (SSS). For all conditions, a significant association between mood changes towards a deterioration in mood and SSS scores was observed. There were no differences between conditions and no correlations between mood changes and NEO-FFI. The data show that sensation-seeking personality has an impact on subjective mood changes following prefrontal rTMS in all conditions. Future studies investigating the effects of rTMS on emotional paradigms should include individual measures of sensation-seeking personality. The pre-selection of subjects according to personality criteria may reduce the variability in results.

Transcranial direct current stimulation as an additional treatment to selective serotonin reuptake inhibitors in adults with major depressive disorder in Germany (DepressionDC): a triple-blind, randomised, sham-controlled, multicentre trial.

BACKGROUND: Transcranial direct current stimulation (tDCS) has been proposed as a feasible treatment for major depressive disorder (MDD). However, meta-analytic evidence is heterogenous and data from multicentre trials are scarce. We aimed to assess the efficacy of tDCS versus sham stimulation as an additional treatment to a stable dose of selective serotonin reuptake inhibitors (SSRIs) in adults with MDD. METHODS: The DepressionDC trial was triple-blind, randomised, and sham-controlled and conducted at eight hospitals in Germany. Patients being treated at a participating hospital aged 18-65 years were eligible if they had a diagnosis of MDD, a score of at least 15 on the Hamilton Depression Rating Scale (21-item version), no response to at least one antidepressant trial in their current depressive episode, and treatment with an SSRI at a stable dose for at least 4 weeks before inclusion; the SSRI was continued at the same dose during stimulation. Patients were allocated (1:1) by fixed-blocked randomisation to receive either 30 min of 2 mA bifrontal tDCS every weekday for 4 weeks, then two tDCS sessions per week for 2 weeks, or sham stimulation at the same intervals. Randomisation was stratified by site and baseline Montgomery-Åsberg Depression Rating Scale (MADRS) score (ie, <31 or ≥31). Participants, raters, and operators were masked to treatment assignment. The primary outcome was change on the MADRS at week 6, analysed in the intention-to-treat population. Safety was assessed in all patients who received at least one treatment session. The trial was registered with ClinicalTrials.gov (NCT02530164). FINDINGS: Between Jan 19, 2016, and June 15, 2020, 3601 individuals were assessed for eligibility. 160 patients were included and randomly assigned to receive either active tDCS (n=83) or sham tDCS (n=77). Six patients withdrew consent and four patients were found to have been wrongly included, so data from 150 patients were analysed (89 [59%] were female and 61 [41%] were male). No intergroup difference was found in mean improvement on the MADRS at week 6 between the active tDCS group (n=77; -8·2, SD 7·2) and the sham tDCS group (n=73; -8·0, 9·3; difference 0·3 [95% CI -2·4 to 2·9]). Significantly more participants had one or more mild adverse events in the active tDCS group (50 [60%] of 83) than in the sham tDCS group (33 [43%] of 77; p=0·028). INTERPRETATION: Active tDCS was not superior to sham stimulation during a 6-week period. Our trial does not support the efficacy of tDCS as an additional treatment to SSRIs in adults with MDD. FUNDING: German Federal Ministry of Education and Research.

TDCS at home for depressive disorders: an updated systematic review and lessons learned from a prematurely terminated randomized controlled pilot study.

The application of transcranial direct current stimulation (tDCS) at home for the treatment of major depressive disorder (MDD) is the subject of current clinical trials. This is due to its positive safety profile, cost-effectiveness, and potential scalability for a wide outreach in clinical practice. Here, we provide a systematic review of the available studies and also a report on the results of a randomized controlled trial (RCT) on tDCS at home for the treatment of MDD. This trial had to be prematurely terminated due to safety concerns. The HomeDC trial is a double-blinded, placebo-controlled, parallel-group study. Patients with MDD (DSM-5) were randomized to active or sham tDCS. Patients conducted tDCS at home for 6 weeks with 5 sessions/week (30 min at 2 mA) anode over F3, cathode over F4. Sham tDCS resembled active tDCS, with ramp-in and ramp-out periods, but without intermittent stimulation. The study was prematurely terminated due to an accumulation of adverse events (AEs, skin lesions), so that only 11 patients were included. Feasibility was good. Safety monitoring was not sufficient enough to detect or prevent AEs within an appropriate timeframe. Regarding antidepressant effects, the reduction in depression scales over time was significant. However, active tDCS was not superior to sham tDCS in this regard. Both the conclusions from this review and the HomeDC trial show that there are several critical issues with the use of tDCS at home that need to be addressed. Nevertheless the array of transcranial electric simulation (TES) methods that this mode of application offers, including tDCS, is highly interesting and warrants further investigation in high quality RCTs. TRIAL REGISTRATION: www. CLINICALTRIALS: gov . TRIAL REGISTRATION NUMBER: NCT05172505. Registration date: 12/13/2021, https://clinicaltrials.gov/ct2/show/NCT05172505 . *Consider, if feasible to do so, reporting the number of records identified from each database or register searched (rather than the total number across all databases/registers) **If automation tools were used, indicate how many records were excluded by a human and how many were excluded by automation tools From: Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 2021;372:n71. https://doi.org/10.1136/bmj.n71 . For more information, visit: http://www.prisma-statement.org/.

Examining the synergistic effects of a cognitive control video game and a home-based, self-administered non-invasive brain stimulation on alleviating depression: the DiSCoVeR trial protocol.

Enhanced behavioral interventions are gaining increasing interest as innovative treatment strategies for major depressive disorder (MDD). In this study protocol, we propose to examine the synergistic effects of a self-administered home-treatment, encompassing transcranial direct current stimulation (tDCS) along with a video game based training of attentional control. The study is designed as a two-arm, double-blind, randomized and placebo-controlled multi-center trial (ClinicalTrials.gov: NCT04953208). At three study sites (Israel, Latvia, and Germany), 114 patients with a primary diagnosis of MDD undergo 6 weeks of intervention (30 × 30 min sessions). Patients assigned to the intervention group receive active tDCS (anode F3 and cathode F4; 2 mA intensity) and an action-like video game, while those assigned to the control group receive sham tDCS along with a control video game. An electrode-positioning algorithm is used to standardize tDCS electrode positioning. Participants perform their designated treatment at the clinical center (sessions 1-5) and continue treatment at home under remote supervision (sessions 6-30). The endpoints are feasibility (primary) and safety, treatment efficacy (secondary, i.e., change of Montgomery-Åsberg Depression Rating Scale (MADRS) scores at week six from baseline, clinical response and remission, measures of social, occupational, and psychological functioning, quality of life, and cognitive control (tertiary). Demonstrating the feasibility, safety, and efficacy of this novel combined intervention could expand the range of available treatments for MDD to neuromodulation enhanced interventions providing cost-effective, easily accessible, and low-risk treatment options.ClinicalTrials.gov: NCT04953208.

Biobanking in everyday clinical practice in psychiatry-The Munich Mental Health Biobank.

Translational research on complex, multifactorial mental health disorders, such as bipolar disorder, major depressive disorder, schizophrenia, and substance use disorders requires databases with large-scale, harmonized, and integrated real-world and research data. The Munich Mental Health Biobank (MMHB) is a mental health-specific biobank that was established in 2019 to collect, store, connect, and supply such high-quality phenotypic data and biosamples from patients and study participants, including healthy controls, recruited at the Department of Psychiatry and Psychotherapy (DPP) and the Institute of Psychiatric Phenomics and Genomics (IPPG), University Hospital of the Ludwig-Maximilians-University (LMU), Munich, Germany. Participants are asked to complete a questionnaire that assesses sociodemographic and cross-diagnostic clinical information, provide blood samples, and grant access to their existing medical records. The generated data and biosamples are available to both academic and industry researchers. In this manuscript, we outline the workflow and infrastructure of the MMHB, describe the clinical characteristics and representativeness of the sample collected so far, and reveal future plans for expansion and application. As of 31 October 2021, the MMHB contains a continuously growing set of data from 578 patients and 104 healthy controls (46.37% women; median age, 38.31 years). The five most common mental health diagnoses in the MMHB are recurrent depressive disorder (38.78%; ICD-10: F33), alcohol-related disorders (19.88%; ICD-10: F10), schizophrenia (19.69%; ICD-10: F20), depressive episode (15.94%; ICD-10: F32), and personality disorders (13.78%; ICD-10: F60). Compared with the average patient treated at the recruiting hospitals, MMHB participants have significantly more mental health-related contacts, less severe symptoms, and a higher level of functioning. The distribution of diagnoses is also markedly different in MMHB participants compared with individuals who did not participate in the biobank. After establishing the necessary infrastructure and initiating recruitment, the major tasks for the next phase of the MMHB project are to improve the pace of participant enrollment, diversify the sociodemographic and diagnostic characteristics of the sample, and improve the utilization of real-world data generated in routine clinical practice.

Efficacy of Augmentation of Cognitive Behavioral Therapy With Transcranial Direct Current Stimulation for Depression: A Randomized Clinical Trial.

Importance: Major depressive disorder (MDD) affects approximately 10% of the population globally. Approximately 20% to 30% of patients with MDD do not sufficiently respond to standard treatment. Therefore, there is a need to develop more effective treatment strategies. Objective: To investigate whether the efficacy of cognitive behavioral therapy (CBT) for the treatment of MDD can be enhanced by concurrent transcranial direct current stimulation (tDCS). Design, Setting, and Participants: The double-blind, placebo-controlled randomized clinical trial PsychotherapyPlus was conducted at 6 university hospitals across Germany. Enrollment took place between June 2, 2016, and March 10, 2020; follow-up was completed August 27, 2020. Adults aged 20 to 65 years with a single or recurrent depressive episode were eligible. They were either not receiving medication or were receiving a stable regimen of antidepressant medication (selective serotonin reuptake inhibitor and/or mirtazapine). A total of 148 women and men underwent randomization: 53 individuals were assigned to CBT alone (group 0), 48 to CBT plus tDCS (group 1), and 47 to CBT plus sham-tDCS (group 2). Interventions: Participants attended a 6-week group intervention comprising 12 sessions of CBT. If assigned, tDCS was applied simultaneously. Active tDCS included stimulation with an intensity of 2 mA for 30 minutes (anode over F3, cathode over F4). Main Outcomes and Measures: The primary outcome was the change in Montgomery-Åsberg Depression Rating Scale (MADRS) score from baseline to posttreatment in the intention-to-treat sample. Scores of 0 to 6 indicate no depression; 7 to 19, mild depression; 20 to 34, moderate depression; and 34 and higher, severe depression. Results: A total of 148 patients (89 women, 59 men; mean [SD] age, 41.1 [13.7] years; MADRS score at baseline, 23.0 [6.4]) were randomized. Of these, 126 patients (mean [SD] age, 41.5 [14.0] years; MADRS score at baseline, 23.0 [6.3]) completed the study. In each of the intervention groups, intervention was able to reduce MADRS scores by a mean of 6.5 points (95% CI, 3.82-9.14 points). The Cohen d value was -0.90 (95% CI, -1.43 to -0.50), indicating a significant effect over time. However, there was no significant effect of group and no significant interaction of group × time, indicating the estimated additive effects were not statistically significant. There were no severe adverse events throughout the whole trial, and there were no significant differences of self-reported adverse effects during and after stimulation between groups 1 and 2. Conclusions and Relevance: Based on MADRS score changes, this trial did not indicate superior efficacy of tDCS-enhanced CBT compared with 2 CBT control conditions. The study confirmed that concurrent group CBT and tDCS is safe and feasible. However, additional research on mechanisms of neuromodulation to complement CBT and other behavioral interventions is needed. Trial Registration: ClinicalTrials.gov Identifier: NCT02633449.

The intervention, the patient and the illness - Personalizing non-invasive brain stimulation in psychiatry.

Current hypotheses on the therapeutic action of non-invasive brain stimulation (NIBS) in psychiatric disorders build on the abundant data from neuroimaging studies. This makes NIBS a very promising tool for developing personalized interventions within a precision medicine framework. NIBS methods fundamentally vary in their neurophysiological properties. They comprise repetitive transcranial magnetic stimulation (rTMS) and its variants (e.g. theta burst stimulation - TBS) as well as different types of transcranial electrical stimulation (tES), with the largest body of evidence for transcranial direct current stimulation (tDCS). In the last two decades, significant conceptual progress has been made in terms of NIBS targets, i.e. from single brain regions to neural circuits and to functional connectivity as well as their states, recently leading to brain state modulating closed-loop approaches. Regarding structural and functional brain anatomy, NIBS meets an individually unique constellation, which varies across normal and pathophysiological states. Thus, individual constitutions and signatures of disorders may be indistinguishable at a given time point, but can theoretically be parsed along course- and treatment-related trajectories. We address precision interventions on three levels: 1) the NIBS intervention, 2) the constitutional factors of a single patient, and 3) the phenotypes and pathophysiology of illness. With examples from research on depressive disorders, we propose solutions and discuss future perspectives, e.g. individual MRI-based electrical field strength as a proxy for NIBS dosage, and also symptoms, their clusters, or biotypes instead of disorder focused NIBS. In conclusion, we propose interleaved research on these three levels along a general track of reverse and forward translation including both clinically directed research in preclinical model systems, and biomarker guided controlled clinical trials. Besides driving the development of safe and efficacious interventions, this framework could also deepen our understanding of psychiatric disorders at their neurophysiological underpinnings.

[Psychosocial support during the COVID-19 pandemic: interdisciplinary concept of care at a university hospital]. / Psychosoziale Unterstützung während der COVID-19-Pandemie: interdisziplinäres Versorgungskonzept an einem Universitätsklinikum.

BACKGROUND: Since the beginning of the outbreak, the COVID-19 pandemic has caused an increased demand for psychosocial support for patients, their family members, and healthcare workers. Concurrently, possibilities to provide this support have been hindered. Quarantine, social isolation, and SARS-CoV­2 infections represent new and severe stressors that have to be addressed with innovative psychosocial care. OBJECTIVE AND METHOD: This article describes the COVID-19 psychosocial first aid concept at the University Hospital Munich (LMU Klinikum) developed by an interdisciplinary team of psychiatric, psychological, spiritual care, psycho-oncological, and palliative care specialists. RESULTS: A new psychosocial first aid model has been implemented for COVID-19 inpatients, family members, and hospital staff consisting of five elements. CONCLUSION: The concept integrates innovative and sustainable ideas, e.g. telemedicine-based approaches and highlights the importance of multidisciplinary collaboration to cope with challenges in the healthcare system.

A machine learning approach to risk assessment for alcohol withdrawal syndrome.

At present, risk assessment for alcohol withdrawal syndrome relies on clinical judgment. Our aim was to develop accurate machine learning tools to predict alcohol withdrawal outcomes at the individual subject level using information easily attainable at patients' admission. An observational machine learning analysis using nested cross-validation and out-of-sample validation was applied to alcohol-dependent patients at two major detoxification wards (LMU, n = 389; TU, n = 805). 121 retrospectively derived clinical, blood-derived, and sociodemographic measures were used to predict 1) moderate to severe withdrawal defined by the alcohol withdrawal scale, 2) delirium tremens, and 3) withdrawal seizures. Mild and more severe withdrawal cases could be separated with significant, although highly variable accuracy in both samples (LMU, balanced accuracy [BAC] = 69.4%; TU, BAC = 55.9%). Poor outcome predictions were associated with higher cumulative clomethiazole doses during the withdrawal course. Delirium tremens was predicted in the TU cohort with BAC of 75%. No significant model predicting withdrawal seizures could be found. Our models were unique to each treatment site and thus did not generalize. For both treatment sites and withdrawal outcome different variable sets informed our models' decisions. Besides previously described variables (most notably, thrombocytopenia), we identified new predictors (history of blood pressure abnormalities, urine screening for benzodiazepines and educational attainment). In conclusion, machine learning approaches may facilitate generalizable, individualized predictions for alcohol withdrawal severity. Since predictive patterns highly vary for different outcomes of withdrawal severity and across treatment sites, prediction tools should not be recommended for clinical practice unless adequately validated in specific cohorts.