Nakhil N, Najem S, Driss R
… +2 more, Chaabouni T, Dufour N
Crit Care Med
· 2026 May · PMID 41823506
·
Full text
OBJECTIVES: Blood electrolyte panels, especially sodium ion (Na + ) and potassium ion (K + ), are fundamental and routine tests. In critical care settings, these measurements are typically performed by central laboratori...OBJECTIVES: Blood electrolyte panels, especially sodium ion (Na + ) and potassium ion (K + ), are fundamental and routine tests. In critical care settings, these measurements are typically performed by central laboratories using indirect potentiometry (IP) or via point-of-care blood gas analyzers using direct potentiometry (DP). Discrepancies between the two methods exist, and clinicians often have limited knowledge regarding the strengths and weaknesses of each technique. We wanted to quantify these observations. DESIGN: We compared prospectively Na + and K + measurements obtained from the same blood draw using both IP and DP (including analyses of correlation, agreement, and discrepancies). We also conducted a brief survey among physicians to assess their knowledge regarding IP and DP. SETTINGS: A tertiary hospital. PATIENTS: A total of 501 paired measurements were prospectively collected from an ICU population. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We assessed the degree of agreement between the two methods. We also examined the impact of proteinemia and hemolysis on Na + and K + values, respectively. Only 31.1% of the 103 responding physicians were aware of the analytical bias in Na + measurements obtained by IP, and 45.6% considered K + measurements from DP to be as reliable or more reliable than those obtained by IP. The agreement between the two methods was moderate (Lin's concordance correlation coefficient: 0.90 for Na + and 0.93 for K + ). The 95% limit of agreement for Na + was particularly large (10.48 mmol/L). The divergence between the two methods, defined as a discrepancy in classification (within, below, or above the normal range), occurred in approximately 10% of cases, for both Na + and K + . CONCLUSIONS: IP and DP were not interchangeable, each exhibiting distinct strengths and limitations. Enhancing physician awareness of the differences between these methods could improve the quality of care.
Urbano V, Alvarez V, Schindler K
… +6 more, Rüegg S, Hahn CD, Beuchat I, Benghanem S, Novy J, Rossetti AO
Crit Care Med
· 2026 Jun · PMID 41823503
·
Publisher ↗
BACKGROUND: Sex-related discrepancies concerning the treatment of patients in intensive care are increasingly described. However, information about management and outcome of critically ill patients undergoing electroence...BACKGROUND: Sex-related discrepancies concerning the treatment of patients in intensive care are increasingly described. However, information about management and outcome of critically ill patients undergoing electroencephalography is scarce. OBJECTIVES: This study explores sex-related disparities in management and clinical outcomes in critically ill patients needing electroencephalography for clinical purposes. DESIGN, SETTING, PATIENTS, AND INTERVENTIONS: In this post hoc analysis of the multicenter Continuous Electroencephalography Randomized Trial in Adults (CERTA), which included patients with impaired consciousness requiring electroencephalography, we explored correlations between sex and the timing of electroencephalography, detection of electroencephalography abnormalities, mechanical ventilation, sedation, antiseizure therapy, mortality, and favorable functional outcome (Cerebral Performance Category [CPC] 1-2) at 6 months, using univariable and multivariable analyses. MEASUREMENTS AND MAIN RESULTS: Among 364 patients (33.8% women), women showed a higher prevalence of intracranial hemorrhage (women 30.9%, men 19.5%; p = 0.015) and epileptiform electroencephalography discharges (women 27.6%, men 21.2%; p = 0.008), but use of sedation, antiseizure medication and mechanical ventilation was similar between sexes. Although mortality was similar (adjusted odds ratio [OR], 0.70; 95% CI, 0.39-1.28), women were less likely to reach CPC 1-2 (adjusted OR, 0.50; 95% CI, 0.28-0.90). CONCLUSIONS: Critically ill women and men requiring electroencephalography appear to receive similar clinical management and have comparable mortality, although long-term functional outcome in surviving women is worse. These findings warrant further investigation to identify modifiable factors contributing to sex-related outcome differences.
Durr KM, Ehlebracht A, Rochwerg B
… +10 more, Fernando SM, Gillen JR, Buccholz C, McIntyre L, Carrier M, Siegal DM, Patel R, Kanji S, Williamson D, Tran A
Crit Care Med
· 2026 May · PMID 41811030
·
Publisher ↗
OBJECTIVES: To determine the relationships between subprophylactic anti-Xa levels and low-molecular-weight heparin (LMWH) thromboprophylaxis regimens with venous thromboembolism (VTE) risk, and to identify predictors of...OBJECTIVES: To determine the relationships between subprophylactic anti-Xa levels and low-molecular-weight heparin (LMWH) thromboprophylaxis regimens with venous thromboembolism (VTE) risk, and to identify predictors of subprophylactic anti-Xa levels in critically ill adults. DATA SOURCES: Medline and Embase were searched from inception to May 7, 2025. STUDY SELECTION: We included studies enrolling critically ill adults receiving LMWH thromboprophylaxis and assessing the relationship between anti-Xa levels and risk of subprophylactic measurements associated with: 1) standard dosing strategies; 2) VTE risk; or 3) predisposing factors. DATA EXTRACTION: We extracted or calculated mean, sd , median, interquartile range, mean difference (MD), unadjusted odds ratios (uORs), and adjusted odds ratios (aORs), when available. Risk of bias was evaluated using Cochrane tools. We assessed certainty of evidence using the Grading of Recommendations, Assessment, Development, and Evaluation approach. DATA SYNTHESIS: We included 39 studies (7124 patients). The proportion of patients receiving LMWH prophylaxis achieving target anti-Xa levels was 47% (95% CI, 36-57%). Subprophylactic anti-Xa levels were associated with an increased risk of VTE (uOR, 2.87; 95% CI, 1.42-5.81; low certainty). Variables with a moderate certainty association with subprophylactic anti-Xa levels include male sex (aOR, 2.65; 95% CI, 1.07-6.56), increased weight (MD, 4.90 kg higher weight compared with those with target levels; 95% CI, 2.78-7.02), and elevated body mass index (MD, 1.36 per kg/m 2 higher compared with those with target levels; 95% CI, 0.64-2.09). CONCLUSIONS: Less than half of critically ill patients achieved their prophylactic anti-Xa targets despite LMWH thromboprophylaxis. Subprophylactic anti-Xa levels may be associated with an increased risk of VTE. Male sex, increased weight, and elevated body mass index have a moderate certainty association with developing subprophylactic anti-Xa levels. This study highlights the clinical importance of anti-Xa level monitoring in critically ill adults and the need for a future randomized controlled trial to further evaluate this topic.
Mina GN, McGonigle T, Liu J
… +7 more, Brummel NE, Patel MB, Smith JR, Pandharipande PP, Dittus RS, Ely EW, Wilson JE
Crit Care Med
· 2026 May · PMID 41805231
·
Publisher ↗
OBJECTIVES: Catatonia occurs in critical illness, however, underlying causal mechanisms are unknown. We aim to determine if exposure to antipsychotic medication is associated with less days alive and free from catatonia...OBJECTIVES: Catatonia occurs in critical illness, however, underlying causal mechanisms are unknown. We aim to determine if exposure to antipsychotic medication is associated with less days alive and free from catatonia in critically ill adults. DESIGN: The Delirium and Catatonia Prospective Cohort Investigation is a prospective cohort. SETTING: Single academic medical center's medical, surgical, and trauma ICUs. PATIENTS: Critically ill adult patients on mechanical ventilation or vasopressors without a major neurocognitive disorder, severe psychiatric disorder, or catatonia at baseline. INTERVENTIONS: The primary exposure was antipsychotic administration and cumulative dosage during the first 5 and 14 days from enrollment. MEASUREMENTS AND MAIN RESULTS: Catatonia was evaluated with the Bush-Francis Catatonia Rating Scale mapped to Diagnostic and Statistical Manual of Mental Disorders , Fifth Edition criteria. The primary outcome was catatonia-free days (CFDs), defined as the number of days the patient was alive and free from catatonia. Adjusted proportional odds logistic regression was used to estimate the odds ratio (OR) of outcome events. Patients ( n = 270) were enrolled with a median (interquartile range) age of 54.5 years (36.7-67.2 yr). Of patients who were exposed to antipsychotic medication ( n = 102), 27 (26%) experienced catatonia. Compared with patients who were never exposed to antipsychotics, those exposed in both the 5- and 14-day models had a 74% and 51% reduction in the odds of more CFD (OR, 0.2568; 95% CI, 0.1580-0.4173) and (OR, 0.4939; 95% CI, 0.3857-0.6325), respectively. Furthermore, those exposed to higher dosages had a 97% reduction in the odds of more CFD (OR, 0.0281; 95% CI, 0.0142-0.0556) and (OR, 0.0335; 95% CI, 0.0166-0.0673) compared with those exposed to lower dosages in both the 5- and 14-day models, respectively. CONCLUSIONS: This study may influence how intensivists approach the use of antipsychotic medications and may build upon existing evidence that dopamine blockade is an underlying biologic mechanism underlying catatonia.
Kim S, Murphy TE, O'Leary JR
… +6 more, Leo-Summers L, Falvey JR, Gill TM, Krumholz HM, Ferrante LE, Jain S
Crit Care Med
· 2026 May · PMID 41805229
·
Full text
OBJECTIVES: Older adults hospitalized to the ICU are at risk for functional decline. In-hospital rehabilitation can mitigate functional decline; however, its association with long-term outcomes is unknown. Our objective...OBJECTIVES: Older adults hospitalized to the ICU are at risk for functional decline. In-hospital rehabilitation can mitigate functional decline; however, its association with long-term outcomes is unknown. Our objective was to describe days alive and at home (DAAH) in the 100 days (DAAH 100 ) after ICU hospitalization among older adults and evaluate whether in-hospital rehabilitation is associated with improved DAAH 100 . DESIGN: Retrospective cohort study. SETTING: National Health and Aging Trends Study linked with Medicare claims (2011-2019). PATIENTS: Community-dwelling Medicare beneficiaries 65 years old or older who survived ICU hospitalization. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The outcome DAAH 100 was calculated by subtracting all post-discharge days in any of emergency department, observation unit, inpatient medical, psychiatric, rehabilitation unit, skilled nursing or hospice facility, and post-death from 100. The exposure was units of in-hospital rehabilitation, that is, physical and/or occupational therapy. We constructed a proportional odds logistic regression model of DAAH 100 (ordinal) adjusted for demographics, pre-hospitalization frailty and functional status, and hospitalization characteristics. We identified 884 ICU hospitalizations (weighted n = 5,330,486) of older adults discharged alive (age, median [interquartile range (IQR)]: 81 yr [75-86]; 50.5% female). Median DAAH 100 was 95 (IQR: 58.4-100) with median of 4 units (~1 hr) of in-hospital rehabilitation delivered over 6 days. After adjustment, each hour of in-hospital rehabilitation was associated with 8% higher odds of experiencing any of the three highest levels of DAAH 100 after discharge (adjusted odds ratio [95% CI], 1.08 [1.04-1.08]). CONCLUSIONS: In this nationally representative study of older ICU survivors, the average patient spent 95 of the first 100 post-discharge DAAH; delivery of greater amounts of in-hospital rehabilitation was associated with increased DAAH 100 after discharge. These findings highlight the substantial heterogeneity in time spent at home by older ICU survivors and the potential for in-hospital rehabilitation to improve this important patient-centered outcome.
Kang Z, Hou C, Qi S
… +3 more, Li Z, Bai X, Dong X
Crit Care Med
· 2026 Jun · PMID 41784457
·
Full text
OBJECTIVES: Sepsis triggers both excessive inflammation and immunosuppression, the latter partly characterized by CD4 + T-cell depletion. The mechanisms underlying this depletion, especially its interplay with cytokine s...OBJECTIVES: Sepsis triggers both excessive inflammation and immunosuppression, the latter partly characterized by CD4 + T-cell depletion. The mechanisms underlying this depletion, especially its interplay with cytokine storms driven by inflammatory factors such as interleukin (IL)-6, remain unclear. This study aimed to elucidate the molecular mechanisms contributing to CD4 + T-cell depletion in sepsis, focusing specifically on the IL-6/Janus kinases (JAKs)/signal transducer and activator of transcription 3 (STAT3) signaling axis and programmed cell death. DESIGN: Prospective cohort study. SETTING: Adult ICUs at a university hospital. PATIENTS: Adult sepsis and septic shock patients without any documented immune comorbidity. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: A prospective analysis enrolled 151 patients (93 sepsis, 58 septic shock) and 20 controls. Flow cytometry and enzyme-linked immunosorbent assay were used to assess immune cell populations and cytokine profiles, with multivariate analyses exploring their interrelationships. An additional 30 sepsis patients and ten controls were recruited to investigate mechanisms. Peripheral blood mononuclear cells (PBMCs) underwent RNA sequencing (RNA-seq). Isolated CD4 + T cells were stimulated with IL-6 in vitro, followed by treatment with specific inhibitors targeting pyroptosis, apoptosis, necroptosis, the JAKs/STAT3 pathway, or receptor-interacting protein kinase 1 (RIPK1). Western blotting, flow cytometry, immunofluorescence, Cell Counting Kit-8 assays, and interferon-gamma staining evaluated cell death pathways, PANoptosome (a complex mediating apoptosis, pyroptosis and necroptosis)-assembly, and function. Significant CD4 + T-cell loss occurred in both sepsis and septic shock groups, strongly correlating with elevated IL-6 levels. Sepsis PBMC RNA-seq revealed activated IL-6/JAKs/STAT3 signaling and upregulated apoptosis/pyroptosis/necroptosis genes. In vitro, IL-6 induced pyroptosis, apoptosis, and necroptosis (PANoptosis) in CD4 + T cells via IL-6/JAKs/STAT3-dependent RIPK1-PANoptosome assembly. Inhibiting JAKs/STAT3 or RIPK1 significantly reduced PANoptosis, partially restored CD4 + T-cell viability and functional capacity. CONCLUSIONS: PANoptosis has been observed to be a form of CD4 + T-cell death in sepsis patients. Evidence suggests that IL-6 may be associated with the exhaustion process, mechanistically involving the activation of the JAKs/STAT3 pathway. It is also hypothesized that this process might be linked to RIPK1-PANoptosome-mediated PANoptosis.
Tiruvoipati R, Zheng J, Gupta S
… +4 more, Pilcher D, Haji K, Bailey M, Paul E
Crit Care Med
· 2026 May · PMID 41784455
·
Publisher ↗
OBJECTIVES: The mortality among patients admitted with sepsis remains high and varies depending on the site of infection. The impact of hypercapnia and acidemia on clinical outcomes in mechanically ventilated patients wi...OBJECTIVES: The mortality among patients admitted with sepsis remains high and varies depending on the site of infection. The impact of hypercapnia and acidemia on clinical outcomes in mechanically ventilated patients with sepsis is not well understood. DESIGN: Multicenter, binational, retrospective study assessed the association of compensated hypercapnia, hypercapnic acidemia, and nonrespiratory acidemia, in mechanically ventilated patients with mortality in sepsis. SETTING: Data were extracted from the "Australian and New Zealand Intensive Care Society Centre for Outcome and Resource Evaluation adult patient" database over a 17-year period (from January 2006 to December 2022) from 201 ICUs. PATIENTS: Patients were classified into four mutually exclusive groups based on a combination of arterial pH and arterial C o2 recorded during the first 24 hours of ICU stay: normocapnia with normal pH, fully compensated hypercapnia, hypercapnic acidemia, and nonrespiratory acidemia. Logistic regression and Cox proportional hazards regression were used to examine the association of compensated hypercapnia, hypercapnic, and nonrespiratory academia to hospital mortality. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Fifty-two thousand four hundred five patients were included. Overall compensated hypercapnia (odds ratio [OR], 1.39; 95% CI, 1.24-1.55; p < 0.001), hypercapnic acidemia (OR, 1.68; 95% CI, 1.57-1.80; p < 0.001), and nonrespiratory acidemia (OR, 1.75; 95% CI, 1.61-1.90; p < 0.001) was associated with increased risk of hospital mortality as compared with patients with normocapnia and normal pH. The risk of increased hospital mortality associated with hypercapnic and nonrespiratory acidemia persisted in all prespecified diagnostic subgroups when compared with patients who had normal pH and normocapnia. Compensated hypercapnia was associated with increased mortality risk in neurologic and unspecified subgroups of sepsis. CONCLUSIONS: Hypercapnic acidemia and nonrespiratory acidemia within the first 24 hours of ICU admission are associated with increased risk of hospital mortality in mechanically ventilated patients with sepsis. This association remains consistent in all diagnostic subgroups of sepsis.
Shorr AF, Kollef MH, Wunderink RG
… +6 more, Jauregui-Peredo LE, Bernard AC, Kim HK, Balk RA, Cristofaro P, Levy MM
Crit Care Med
· 2026 May · PMID 41778855
·
Publisher ↗
OBJECTIVES: To evaluate the diagnostic performance of a rapid point-of-care immunoassay measuring pancreatic stone protein (PSP) for early sepsis identification within the first three days of ICU admission. Subgroup anal...OBJECTIVES: To evaluate the diagnostic performance of a rapid point-of-care immunoassay measuring pancreatic stone protein (PSP) for early sepsis identification within the first three days of ICU admission. Subgroup analyses (sex, age, febrile status) were conducted, and the combined diagnostic value of PSP and C-reactive protein (CRP) was assessed. DESIGN: Multicenter, prospective, observational study. PATIENT: Four hundred sixty-six adults the ICU. SETTING: Six ICUs in the United States who were expected to required at least 24 hours of ICU care. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We calculated the Youden Index to evaluate the clinical performance of the PSP assay, and the resulting threshold was used to identify patients with sepsis. Diagnostic performance metrics included sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (LR+), and negative likelihood ratio (LR-). Receiver operating characteristic analysis were performed for PSP and CRP. At the optimal PSP cutoff point of 117 ng/mL, PSP demonstrated a sensitivity of 74.2%, specificity of 67.8%, accuracy of 71.0%, PPV of 70.3%, NPV of 71.9%, and LR+ and LR- ratios of 2.30 and 0.38, respectively. Combining PSP and CRP improved diagnostic specificity to 95.2%. Subgroup analyses demonstrated consistent performance across sex, and higher specificity was observed in patients 18-60 years old. In febrile patients, PSP achieved high specificity (77.8%) but lower sensitivity (63.6%). In non-febrile patients, specificity and sensitivity sensitivity and specificity were 67.0% and 76.6%, respectively. CONCLUSIONS: PSP can serve as a biomarker for the early identification of sepsis. Diagnostic performance across diverse ages, sex, and clinical presentation supports the assay's broad applicability. The combination of PSP and CRP enhances diagnostic specificity for sepsis detection, offering a complementary approach to improve sepsis detection and lead to earlier appropriate management.
Erstad BL, Cobas MA, Qadir N
… +20 more, Alshamsi F, Sharif S, Devine EM, Devine ST, Einav S, Elmer J, Fort AC, Harrod CG, Heavner MS, Lamb KD, Mehta S, Mitchell DA, Paruk F, Piraino T, Sacha G, Schell-Chaple HM, Sinha S, Smith SE, Topeli A, Sarwal A
Crit Care Med
· 2026 Mar · PMID 41773929
·
Publisher ↗
RATIONALE: Neuromuscular blocking agents (NMBAs) show potential benefits on mortality and other complications of acute respiratory distress syndrome (ARDS) in adult patients. Evidence-based decisions and processes ensure...RATIONALE: Neuromuscular blocking agents (NMBAs) show potential benefits on mortality and other complications of acute respiratory distress syndrome (ARDS) in adult patients. Evidence-based decisions and processes ensure appropriate use of neuromuscular blockade in adult patients with ARDS. OBJECTIVES: The objective of these guidelines was to develop evidence-based recommendations for the administration of NMBAs in critically ill adult patients with ARDS. DESIGN: The American College of Critical Care Medicine Board convened a 21-member multidisciplinary panel of experts in critical care medicine, nursing, respiratory therapy, pharmacology, surgery, neurology, and anesthesiology. The panel included two expert methodologists specialized in developing evidence-based recommendations in alignment with the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) methodology. Conflict-of-interest policies were strictly followed during all phases of guidelines development including task force selection and voting. METHODS: The panel members identified and formulated five Population, Intervention, Comparison, and Outcome questions. We conducted a systematic review for each question to identify the best available evidence, statistically analyzed the evidence, and assessed the certainty of the evidence using the GRADE methodology. We used the GRADE evidence-to-decision framework to formulate the recommendations. RESULTS: The panel generated two conditional recommendations. One recommendation is to use NMBAs in adults with ARDS with Pao2/Fio2 less than 150. For the other recommendations, there was equipoise in the recommendation for and against using titratable vs. fixed-dose NMBA dosing, a monitoring-based strategy for assessing depth of sedation and analgesia in adults with ARDS before initiating or while receiving neuromuscular blockade, and administration of NMBAs for patients who are proned, due to overall lack of evidence in critically ill patients and due to considerations of patient safety and experience concerns. CONCLUSIONS: These guidelines provide additional perspectives on the use of NMBA in patients with ARDS, recognizing that institutional and patient-specific considerations must help to guide the decision-making process.
Nates JL, Jayaprakash N, Carayannopoulos KL
… +18 more, Honarmand K, Anesi GL, Bartlett Davis L, Brunson ME, Chen LL, Christian MD, Fuentes M, Gallagher JJ, Harrod CG, Gutmann Koch V, Miles WS, Mitarai T, Narva AM, Sprung CL, Stempek S, Zimmerman JL, Boling B, Sicoutris C
Crit Care Med
· 2026 Mar · PMID 41773927
·
Publisher ↗
RATIONALE: Efficient distribution of scarce critical care resources is essential to save the most lives in times of crisis. Evidence-based practices and processes enhance clinical decision-making. OBJECTIVES: The objecti...RATIONALE: Efficient distribution of scarce critical care resources is essential to save the most lives in times of crisis. Evidence-based practices and processes enhance clinical decision-making. OBJECTIVES: The objective of these guidelines was to develop evidence-based, rather than expert-based, recommendations for triaging critically ill patients eligible for ICU admission during times of crisis-level shortages in ICU capacity. DESIGN: The American College of Critical Care Medicine Board convened a 21-member multidisciplinary panel, comprising doctors in medicine, nursing, and law; advanced practice providers; respiratory therapists; ethicists; and patient/family representatives. The panel included two expert methodologists specialized in developing evidence-based recommendations in alignment with the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) methodology. Conflict-of-interest policies were strictly followed during all phases of guidelines development including task force selection and voting. METHODS: The panel members identified and formulated five fundamental Patient, Intervention, Comparator, and Outcomes questions. The panel conducted a systematic review for each question to identify the best available evidence, analyzed the evidence, and assessed the certainty of the evidence using the GRADE methodology. The GRADE evidence-to-decision framework was used to formulate the recommendations. Good practice statements were included to provide additional guidance. RESULTS: The panel generated one conditional recommendation and five no recommendation statements. CONCLUSIONS: Crisis-level shortages significantly disrupt patient care. Despite the role of triage in minimizing adverse outcomes, there is a lack of evidence, as opposed to expert opinion, to guide practice recommendations in the critical clinical scenarios considered by the panel.
Sarton B, Mattia GM, Cervoni E
… +9 more, Decourt J, Peran P, Riu B, Bounes F, Naboulsi E, Barttfeld P, Olivot JM, Silva S, Cussat-Blanc S
Crit Care Med
· 2026 Jul · PMID 41757998
·
Full text
OBJECTIVES: Advanced MRI is recommended for the clinical evaluation of patients with coma. However, the implementation of these guidelines has been hindered by an inadequate identification of relevant markers among the v...OBJECTIVES: Advanced MRI is recommended for the clinical evaluation of patients with coma. However, the implementation of these guidelines has been hindered by an inadequate identification of relevant markers among the vast amount of reported MRI-derived metrics. We developed and validated an innovative and explainable machine learning (ML) analytical pipeline to fill this critical knowledge gap. DESIGN: Prospective cross-sectional study. SETTING: Three Intensive Critical Care Units affiliated to the University in Toulouse (France). PATIENTS: Patients with coma (Glasgow Coma Scale score at the hospital admission ≤ 9) from either traumatic or anoxic origin. Patient's neurologic outcome was assessed at 3 months by using the Coma Recovery Scale-Revised. Whole-brain advanced structural MRI data and functional connectivity analysis of resting-state networks known to contribute to conscious processing. A specifically designed ensemble of explainable ML methods was applied and cross-validated. INTERVENTIONS: None. MEASUREMENT AND MAIN RESULTS: Overall, 64 patients with coma due to either traumatic ( n = 26) or anoxic ( n = 38) brain injuries were studied and compared with 55 controls. The median delay between ICU admission and MRI scan was 9 days (interquartile range, 6-16 d). At 3 months, 50% patients (32/64) had an unfavorable outcome. All the models showed valuable generalization capacities: coma diagnosis (mean accuracy, 0.934%), primary brain injury discrimination (mean accuracy, 0.762 %), and neurologic outcome prediction (mean accuracy, 0.824 %). CONCLUSIONS: A new ensemble of brain MRI-derived metrics was specifically related to coma state, its etiology, and the patient's potential for recovery at 3 months. The structural and functional integrity of mesocircuit and frontoparietal networks appeared to carry the most relevant information.