Exploring the Potentials of Artificial Intelligence in Sepsis Management in the Intensive Care Unit

Early identification of sepsis is critical to improving patient outcomes. Impact of the new sepsis definition (Sepsis-3) on timing of recognition in the emergency department has not been evaluated. Our study objective was to compare time to meeting systemic inflammatory response syndrome (Sepsis-2) criteria, Sequential Organ Failure Assessment (Sepsis-3) criteria, and quick Sequential Organ Failure Assessment criteria using electronic health record data. Retrospective, observational study. The emergency department at the University of California, San Francisco. Emergency department encounters between June 2012 and December 2016 for patients greater than or equal to 18 years old with blood cultures ordered, IV antibiotic receipt, and identification with sepsis via systemic inflammatory response syndrome or Sequential Organ Failure Assessment within 72 hours of emergency department presentation. None. We analyzed timestamped electronic health record data from 16,612 encounters identified as sepsis by greater than or equal to 2 systemic inflammatory response syndrome criteria or a Sequential Organ Failure Assessment score greater than or equal to 2. The primary outcome was time from emergency department presentation to meeting greater than or equal to 2 systemic inflammatory response syndrome criteria, Sequential Organ Failure Assessment greater than or equal to 2, and/or greater than or equal to 2 quick Sequential Organ Failure Assessment criteria. There were 9,087 patients (54.7%) that met systemic inflammatory response syndrome-first a median of 26 minutes post-emergency department presentation (interquartile range, 0-109 min), with 83.1% meeting Sequential Organ Failure Assessment criteria a median of 118 minutes later (interquartile range, 44-401 min). There were 7,037 patients (42.3%) that met Sequential Organ Failure Assessment-first, a median of 113 minutes post-emergency department presentation (interquartile range, 60-251 min). Quick Sequential Organ Failure Assessment was met in 46.4% of patients a median of 351 minutes post-emergency department presentation (interquartile range, 67-1,165 min). Adjusted odds of in-hospital mortality were 39% greater in patients who met systemic inflammatory response syndrome-first compared with those who met Sequential Organ Failure Assessment-first (odds ratio, 1.39; 95% CI, 1.20-1.61). Systemic inflammatory response syndrome and Sequential Organ Failure Assessment initially identified distinct populations. Using systemic inflammatory response syndrome resulted in earlier electronic health record sepsis identification in greater than 50% of patients. Using Sequential Organ Failure Assessment alone may delay identification. Using systemic inflammatory response syndrome alone may lead to missed sepsis presenting as acute organ dysfunction. Thus, a combination of inflammatory (systemic inflammatory response syndrome) and organ dysfunction (Sequential Organ Failure Assessment) criteria may enhance timely electronic health record-based sepsis identification.

BackgroundWith Sepsis-3, the increase in sequential organ failure assessment (SOFA) as a clinical score for the identification of patients with sepsis and quickSOFA (qSOFA) for the identification of patients at risk of sepsis outside the intensive care unit (ICU) were introduced in 2016. However, their validity has been questioned, and their applicability in different settings and subgroups, such as hematological cancer patients, remains unclear. We therefore assessed the validity of SOFA, qSOFA, and the systemic inflammatory response syndrome (SIRS) criteria regarding the diagnosis of sepsis and the prediction of in-hospital mortality in a multicenter cohort of hematological cancer patients treated on ICU and non-ICU settings.MethodsWe retrospectively calculated SIRS, SOFA, and qSOFA scores in our cohort and applied the definition of sepsis as “life-threatening organ dysfunction caused by dysregulated host response to infection” as reference. Discriminatory capacity was assessed using the area under the receiver operating characteristic curve (AUROC).ResultsAmong 450 patients with hematological cancer (median age 58 years, 274 males [61%]), 180 (40%) had sepsis of which 101 (56%) were treated on ICU. For the diagnosis of sepsis, sensitivity was 86%, 64%, and 42% for SIRS, SOFA, and qSOFA, respectively. However, the AUROCs of SOFA and qSOFA indicated better discrimination for sepsis than SIRS (SOFA, 0.69 [95% CI, 0.64–0.73] p < 0.001; qSOFA, 0.67 [95% CI, 0.62–0.71] p < 0.001; SIRS, 0.57 [95% CI, 0.53–0.61] p < 0.001).In-hospital mortality was 40% and 14% in patients with and without sepsis, respectively (p < 0.001). Regarding patients with sepsis, mortality was similar in patients with positive and negative SIRS scores (39% vs. 40% (p = 0.899), respectively). For patients with qSOFA ≥ 2, mortality was 49% compared to 33% for those with qSOFA < 2 (p = 0.056), and for SOFA 56% vs. 11% (p < 0.001), respectively. SOFA allowed significantly better discrimination for in-hospital mortality (AUROC 0.74 [95% CI, 0.69–0.79] p < 0.001) than qSOFA (AUROC 0.65 [95% CI, 0.60–0.71] p < 0.001) or SIRS (AUROC 0.49 [95% CI, 0.44–0.54] p < 0.001).ConclusionsAn increase in SOFA score of ≥ 2 had better prognostic accuracy for both diagnosis of sepsis and in-hospital mortality in this setting, and especially on ICU, we observed limited validity of SIRS criteria and qSOFA in identifying hematological patients with sepsis and at high risk of death.

The aim of the present study was to validate the prognostic effectiveness of Sepsis-3 criteria, including sequential organ failure assessment (SOFA) and quick SOFA (qSOFA), with systemic inflammatory response syndrome (SIRS) criteria among patients with urolithiasis associated sepsis that were transferred to intensive care unit (ICU) facilities following surgical interventions. To achieve this, the records of all patients transferred to ICU following surgical interventions with urolithiasis-associated sepsis between January 2010 to July 2017 at Xin Hua Hospital Affiliated to Shanghai Jiao Tong University were retrospectively reviewed. A total of 107 patients were enrolled. The prognostic performances of SOFA, qSOFA and SIRS for predicting in-hospital mortality (sepsis-related mortality during patients' hospitalizations) or prolonged length of ICU stay (>3 days) were compared using the area under the receiver operating characteristic curve (AUROC) and Z statistic values. The results revealed that the overall in-hospital mortality rate was 8.4% and the percentage of in-hospital mortality or prolonged length of ICU stay (>3 days) was 72.0% among the 107 patients. The favorable outcome group exhibited significantly decreased white blood cell counts, and levels of C-reactive protein and procalcitonin and increased systolic blood pressure and mean arterial pressure. The AUROC of qSOFA, SIRS and SOFA were 0.615, 0.625 and 0.860, respectively. SOFA was significantly more effective at predicting adverse outcomes when compared with SIRS and qSOFA criteria. Following adjustments for patient age and comorbidities, the AUROC values of qSOFA, SIRS and SOFA were 0.713, 0.722 and 0.940. In conclusion, the results of the present study indicate that the prognostic performance of SOFA for predicting in-hospital mortality or prolonged ICU stay among patients with urolithiasis-associated sepsis following surgical interventions was significantly improved when compared with qSOFA or SIRS criteria. Based on these results it is recommended that urologists use the SOFA score for patients with urolithiasis-associated sepsis.

Clinical Evaluation of Sepsis-1 and Sepsis-3 in the ICU

The sepsis-3 criteria have emphasized the value of a change of two or more points on the SOFA, introduced the qSOFA, and removed the systemic inflammatory response syndrome (SIRS) criteria from the sepsis definition. To externally validate and assess the discriminatory capacities of an increase in the SOFA score by two or more points, the presence of two or more SIRS criteria, or a qSOFA score of 2 or more points for outcomes in 5109 patients, the vast majority of whom were postcardiac surgery patients who were admitted to a Cardiothoracic Surgical ICU in Singapore. A retrospective cohort analysis of 5109 patients with an infection-related primary admission diagnosis in the cardiothoracic intensive care unit (CTICU) at the National University Hospital (NUH) in Singapore from 2010 to 2016. The SOFA, qSOFA, and SIRS criteria were applied to the data representing the worst condition within 24 hours of ICU admission. The primary outcome was in-hospital mortality. Discrimination was assessed using the area under the receiver operating characteristic curve (AUROC). In 5109 patients, the average mortality of patients with an increase in the SOFA scores of less than 2 points was 3.5% (n = 64), and it was 6% (n = 199) for those with an increase in the SOFA scores of 2 or more points. The mortality of patients with an increase in the qSOFA scores of less than 2 points was 2.6% (n = 7), and it was 5.3% (n = 256) for those with an increase in the qSOFA scores of 2 or more points. The mortality of patients with an increase in the SIRS criteria of less than 2 points was 3.6% (n = 30), and it was 5.4% (n = 233) for those with an increase in the SIRS criteria of 2 or more points. The AUROC of in-hospital mortality of patients with an increase in the SOFA, qSOFA, and SIRS criteria of 2 or more points was 0.96, 0.95, and 0.95, respectively. In adults with suspected infection admitted to the CTICU in NUH, the change in in-hospital mortality between patients with an increase in SOFA scores of less than 2 and those with an increase of 2 or more was 2.5 percentage points. In contrast to other studies, the absolute change in mortality was nearly the same compared to the qSOFA and SIRS criteria, and the qSOFA score had the greatest percentage increase of 104%, compared to 71% for the SOFA score and 50% for the SIRS criteria. Besides, from the perspective of discriminatory capacities, an increase in SOFA scores of 2 or more did not demonstrate significantly greater prognostic accuracy for in-hospital mortality than equivalent increases in qSOFA scores or SIRS criteria. These findings suggest distinctive characteristics of the study population in the CTICU that are different from the general population.

Sepsis-3 consensus suggests "the need to develop similar updated definitions for pediatric populations." Sequential organ failure assessment (SOFA) and systemic inflammatory response syndrome (SIRS) criteria are two systems widely used to define the status of infection. However, it is still unclear whether SOFA is more accurate than SIRS in predicting children mortality in low- and middle-income countries. Thus, we validated the accuracy of age-adapted SOFA and SIRS in predicating the poor prognosis of infected children in China's pediatric intensive care unit (PICU). We performed a retrospective and observational cohort study of children admitted for infection to PICU in the hospital between January 1, 2009 and December 31, 2017. The indexes within 24 h after intensive care unit (ICU) admission were analyzed according to age-adapted SOFA and SIRS, and all data were sourced from the hospital's electronic health record database. The prognosis was illustrated with primary outcome and secondary outcome. Primary outcome referred to in-hospital mortality, and secondary outcome to in-hospital mortality or ICU length of stay ≥ 7 days. The predictive power of age-adapted SOFA and SIRS was compared using crude and adjusted area under the receiver operating characteristic curve (AUROC). Of 1,831 PICU-admitted children due to infection, 164 (9.0%) experienced primary outcome, and 948 (51.8%) secondary outcome. Of 164 deaths, 65.9% were males (median age of 7.53 months, range of 2.67-41.00 months). Children who scored ≥ 2 in age-adapted SOFA or met two SIRS criteria accounted for 92.5% and 73.3%, respectively. In addition, age-adapted SOFA score of ≥2 predicted adverse outcome more accurately than pediatric SIRS (adjusted AUROC, 0.753; 0.713-0.796 vs. 0.674; 0.631-0.702; P < 0.001). Compared with SIRS criteria, age-adapted SOFA score of ≥ 2 enjoys a more accuracy in predicting in-hospital mortality of PICU-admitted children, and a higher sensitivity in identifying children with severe infection.

BackgroundFew prospective studies have evaluated the quick Sequential (Sepsis-Related) Organ Failure Assessment (qSOFA) criteria in emergency department (ED)settings. The aim of this study was to determine the prognostic accuracy of...

ObjectiveThis study aims to assess the performance of various scoring systems in predicting the 28-day mortality of patients with aortic aneurysms (AA) admitted to the intensive care unit (ICU).MethodsWe utilized data from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) to perform a comparative analysis of various predictive systems, including the Glasgow Aneurysm Score (GAS), Simplified Acute Physiology Score (SAPS) III, SAPS II, Logical Organ Dysfunction System (LODS), Sequential Organ Failure Assessment (SOFA), Systemic Inflammatory Response Syndrome (SIRS), and The Oxford Acute Illness Severity Score (OASIS). The discrimination abilities of these systems were compared using the area under the receiver operating characteristic curve (AUROC). Additionally, a 4-knotted restricted cubic spline regression was employed to evaluate the association between the different scoring systems and the risk of 28-day mortality. Finally, we conducted a subgroup analysis focusing on patients with abdominal aortic aneurysms (AAA).ResultsThis study enrolled 586 patients with AA (68.39% male). Among them, 26 patients (4.4%) died within 28 days. Comparative analysis revealed higher SAPS II, SAPS III, SOFA, LODS, OASIS, and SIRS scores in the deceased group, while no statistically significant difference was observed in GAS scores between the survivor and deceased groups (P = 0.148). The SAPS III system exhibited superior predictive value for the 28-day mortality rate (AUROC 0.805) compared to the LODS system (AUROC 0.771), SOFA (AUROC 0.757), SAPS II (AUROC 0.759), OASIS (AUROC 0.742), SIRS (AUROC 0.638), and GAS (AUROC 0.586) systems. The results of the univariate and multivariate logistic analyses showed that SAPS III was statistically significant for both 28-day and 1-year mortality. Subgroup analyses yielded results consistent with the overall findings. No nonlinear relationship was identified between these scoring systems and 28-day all-cause mortality (P for nonlinear > 0.05).ConclusionThe SAPS III system demonstrated superior discriminatory ability for both 28-day and 1-year mortality compared to the GAS, SAPS II SIRS, SOFA, and OASIS systems among patients with AA.

Use of the Quick Sequential Organ Failure Assessment Score for Prediction of Intensive Care Unit Admission Due to Septic Shock after Percutaneous Nephrolithotomy: A Multicenter Study.

Sepsis is a leading cause of death, particularly in immunocompromised people. The revised definition of sepsis (Sepsis-3) uses the Sequential Organ Failure Assessment (SOFA) and quick SOFA (qSOFA) to identify patients with sepsis. The aim of this study was to evaluate the performance of SOFA, qSOFA, and systemic inflammatory response syndrome (SIRS) in immunocompromised patients. Adult immunocompromised patients admitted to Michigan Medicine between 2012 and 2018 with suspected infection were included based on criteria adopted from the Sepsis-3 study. Each clinical score (SOFA ≥2, qSOFA ≥2, SIRS ≥2) was added to the baseline risk model as an ordinal variable as well as a dichotomous variable, and area under the receiver operating characteristic curve (AUROC) values were calculated. In addition, breakpoints of SOFA between 2 and 10 were assessed to identify the breakpoints with the highest sensitivity and specificity for hospital mortality. The analysis was stratified for intensive care unit (ICU) status. Of 2822 immunocompromised patients with a mean age of 56.8±15.6 years, 213 (7.5%) died during hospitalization. When added to the baseline risk model, SOFA score had the greatest predictive validity for hospital mortality (AUROC,0.802; 95% CI, 0.771-0.832), followed by qSOFA (AUROC,0.783; 95% CI, 0.754-0.812) and SIRS (AUROC,0.741; 95% CI, 0.708-0.774). Among the SOFA breakpoints that were evaluated, SOFA ≥6 had the greatest predictive validity and a moderate positive likelihood ratio (2.75) for hospital mortality. The predictive validity for hospital mortality of qSOFA was similar among immunocompromised patients as that reported in the Sepsis-3 study. The sensitivity of qSOFA ≥2 for hospital mortality was low. SOFA ≥6 might be an effective tool to identify immunocompromised patients with suspected infection at high risk for clinical deterioration.

BackgroundSepsis is one of the leading causes of mortality in hospitalized patients. Despite this fact, a reliable means of predicting sepsis onset remains elusive. Early and accurate sepsis onset predictions could allow more aggressive and targeted therapy while maintaining antimicrobial stewardship. Existing detection methods suffer from low performance and often require time-consuming laboratory test results.ObjectiveTo study and validate a sepsis prediction method, InSight, for the new Sepsis-3 definitions in retrospective data, make predictions using a minimal set of variables from within the electronic health record data, compare the performance of this approach with existing scoring systems, and investigate the effects of data sparsity on InSight performance.MethodsWe apply InSight, a machine learning classification system that uses multivariable combinations of easily obtained patient data (vitals, peripheral capillary oxygen saturation, Glasgow Coma Score, and age), to predict sepsis using the retrospective Multiparameter Intelligent Monitoring in Intensive Care (MIMIC)-III dataset, restricted to intensive care unit (ICU) patients aged 15 years or more. Following the Sepsis-3 definitions of the sepsis syndrome, we compare the classification performance of InSight versus quick sequential organ failure assessment (qSOFA), modified early warning score (MEWS), systemic inflammatory response syndrome (SIRS), simplified acute physiology score (SAPS) II, and sequential organ failure assessment (SOFA) to determine whether or not patients will become septic at a fixed period of time before onset. We also test the robustness of the InSight system to random deletion of individual input observations.ResultsIn a test dataset with 11.3% sepsis prevalence, InSight produced superior classification performance compared with the alternative scores as measured by area under the receiver operating characteristic curves (AUROC) and area under precision-recall curves (APR). In detection of sepsis onset, InSight attains AUROC = 0.880 (SD 0.006) at onset time and APR = 0.595 (SD 0.016), both of which are superior to the performance attained by SIRS (AUROC: 0.609; APR: 0.160), qSOFA (AUROC: 0.772; APR: 0.277), and MEWS (AUROC: 0.803; APR: 0.327) computed concurrently, as well as SAPS II (AUROC: 0.700; APR: 0.225) and SOFA (AUROC: 0.725; APR: 0.284) computed at admission (P<.001 for all comparisons). Similar results are observed for 1-4 hours preceding sepsis onset. In experiments where approximately 60% of input data are deleted at random, InSight attains an AUROC of 0.781 (SD 0.013) and APR of 0.401 (SD 0.015) at sepsis onset time. Even with 60% of data missing, InSight remains superior to the corresponding SIRS scores (AUROC and APR, P<.001), qSOFA scores (P=.0095; P<.001) and superior to SOFA and SAPS II computed at admission (AUROC and APR, P<.001), where all of these comparison scores (except InSight) are computed without data deletion.ConclusionsDespite using little more than vitals, InSight is an effective tool for predicting sepsis onset and performs well even with randomly missing data.

The Sepsis-3 Criteria emphasized the value of a change of 2 or more points in the Sequential [Sepsis-related] Organ Failure Assessment (SOFA) score, introduced quick SOFA (qSOFA), and removed the systemic inflammatory response syndrome (SIRS) criteria from the sepsis definition. Externally validate and assess the discriminatory capacities of an increase in SOFA score by 2 or more points, 2 or more SIRS criteria, or a qSOFA score of 2 or more points for outcomes among patients who are critically ill with suspected infection. Retrospective cohort analysis of 184 875 patients with an infection-related primary admission diagnosis in 182 Australian and New Zealand intensive care units (ICUs) from 2000 through 2015. SOFA, qSOFA, and SIRS criteria applied to data collected within 24 hours of ICU admission. The primary outcome was in-hospital mortality. In-hospital mortality or ICU length of stay (LOS) of 3 days or more was a composite secondary outcome. Discrimination was assessed using the area under the receiver operating characteristic curve (AUROC). Adjusted analyses were performed using a model of baseline risk determined using variables independent of the scoring systems. Among 184 875 patients (mean age, 62.9 years [SD, 17.4]; women, 82 540 [44.6%]; most common diagnosis bacterial pneumonia, 32 634 [17.7%]), a total of 34 578 patients (18.7%) died in the hospital, and 102 976 patients (55.7%) died or experienced an ICU LOS of 3 days or more. SOFA score increased by 2 or more points in 90.1%; 86.7% manifested 2 or more SIRS criteria, and 54.4% had a qSOFA score of 2 or more points. SOFA demonstrated significantly greater discrimination for in-hospital mortality (crude AUROC, 0.753 [99% CI, 0.750-0.757]) than SIRS criteria (crude AUROC, 0.589 [99% CI, 0.585-0.593]) or qSOFA (crude AUROC, 0.607 [99% CI, 0.603-0.611]). Incremental improvements were 0.164 (99% CI, 0.159-0.169) for SOFA vs SIRS criteria and 0.146 (99% CI, 0.142-0.151) for SOFA vs qSOFA (P <.001). SOFA (AUROC, 0.736 [99% CI, 0.733-0.739]) outperformed the other scores for the secondary end point (SIRS criteria: AUROC, 0.609 [99% CI, 0.606-0.612]; qSOFA: AUROC, 0.606 [99% CI, 0.602-0.609]). Incremental improvements were 0.127 (99% CI, 0.123-0.131) for SOFA vs SIRS criteria and 0.131 (99% CI, 0.127-0.134) for SOFA vs qSOFA (P <.001). Findings were consistent for both outcomes in multiple sensitivity analyses. Among adults with suspected infection admitted to an ICU, an increase in SOFA score of 2 or more had greater prognostic accuracy for in-hospital mortality than SIRS criteria or the qSOFA score. These findings suggest that SIRS criteria and qSOFA may have limited utility for predicting mortality in an ICU setting.

PurposeThis study aimed to construct a mortality model for the risk stratification of intensive care unit (ICU) patients with sepsis by applying a machine learning algorithm.MethodsAdult patients who were diagnosed with sepsis during admission to ICU were extracted from MIMIC-III, MIMIC-IV, eICU, and Zigong databases. MIMIC-III was used for model development and internal validation. The other three databases were used for external validation. Our proposed model was developed based on the Extreme Gradient Boosting (XGBoost) algorithm. The generalizability, discrimination, and validation of our model were evaluated. The Shapley Additive Explanation values were used to interpret our model and analyze the contribution of individual features.ResultsA total of 16,741, 15,532, 22,617, and 1,198 sepsis patients were extracted from the MIMIC-III, MIMIC-IV, eICU, and Zigong databases, respectively. The proposed model had an area under the receiver operating characteristic curve (AUROC) of 0.84 in the internal validation, which outperformed all the traditional scoring systems. In the external validations, the AUROC was 0.87 in the MIMIC-IV database, better than all the traditional scoring systems; the AUROC was 0.83 in the eICU database, higher than the Simplified Acute Physiology Score III and Sequential Organ Failure Assessment (SOFA),equal to 0.83 of the Acute Physiology and Chronic Health Evaluation IV (APACHE-IV), and the AUROC was 0.68 in the Zigong database, higher than those from the systemic inflammatory response syndrome and SOFA. Furthermore, the proposed model showed the best discriminatory and calibrated capabilities and had the best net benefit in each validation.ConclusionsThe proposed algorithm based on XGBoost and SHAP-value feature selection had high performance in predicting the mortality of sepsis patients within 24 h of ICU admission.

Controversy exists regarding the best diagnostic and screening tool for sepsis outside the intensive care unit (ICU). Sequential organ failure assessment (SOFA) score has been shown to be superior to systemic inflammatory response syndrome (SIRS) criteria, however, the performance of "Red Flag sepsis criteria" has not been tested formally.The aim of the study was to investigate the ability of Red Flag sepsis criteria to identify the patients at high risk of sepsis-related death in comparison to SOFA based sepsis criteria. We also investigated the comparison of Red Flag sepsis to quick SOFA (qSOFA), SIRS, and national early warning score (NEWS) scores and factors influencing patient mortality.Patients were recruited into a 24-hour point-prevalence study on the general wards and emergency departments across all Welsh acute hospitals. Inclusion criteria were: clinical suspicion of infection and NEWS 3 or above in-line with established escalation criteria in Wales. Data on Red Flag sepsis and SOFA criteria was collected together with qSOFA and SIRS scores and 90-day mortality.459 patients were recruited over a 24-hour period. 246 were positive for Red Flag sepsis, mortality 33.7% (83/246); 241 for SOFA based sepsis criteria, mortality 39.4% (95/241); 54 for qSOFA, mortality 57.4% (31/54), and 268 for SIRS, mortality 33.6% (90/268). 55 patients were not picked up by any criteria. We found that older age was associated with death with OR (95% CI) of 1.03 (1.02-1.04); higher frailty score 1.24 (1.11-1.40); DNA-CPR order 1.74 (1.14-2.65); ceiling of care 1.55 (1.02-2.33); and SOFA score of 2 and above 1.69 (1.16-2.47).The different clinical tools captured different subsets of the at-risk population, with similar sensitivity. SOFA score 2 or above was independently associated with increased risk of death at 90 days. The sequalae of infection-related organ dysfunction cannot be reliably captured based on routine clinical and physiological parameters alone.

BackgroundThere is a need to update the cardiovascular (CV) Sequential Organ Failure Assessment (SOFA) score to reflect the current practice in sepsis. We previously proposed the modified CV SOFA score from data on blood pressure, norepinephrine equivalent dose, and lactate as gathered from emergency departments. In this study, we externally validated the modified CV SOFA score in multicenter intensive care unit (ICU) patients.MethodsA multicenter retrospective observational study was conducted on ICU patients at six hospitals in Korea. We included adult patients with sepsis who were admitted to ICUs. We compared the prognostic performance of the modified CV/total SOFA score and the original CV/total SOFA score in predicting 28-day mortality. Discrimination and calibration were evaluated using the area under the receiver operating characteristic curve (AUROC) and the calibration curve, respectively.ResultsWe analyzed 1,015 ICU patients with sepsis. In overall patients, the 28-day mortality rate was 31.2%. The predictive validity of the modified CV SOFA (AUROC, 0.712; 95% confidence interval [CI], 0.677–0.746; P < 0.001) was significantly higher than that of the original CV SOFA (AUROC, 0.644; 95% CI, 0.611–0.677). The predictive validity of modified total SOFA score for 28-day mortality was significantly higher than that of the original total SOFA (AUROC, 0.747 vs. 0.730; 95% CI, 0.715–0.779; P = 0.002). The calibration curve of the original CV SOFA for 28-day mortality showed poor calibration. In contrast, the calibration curve of the modified CV SOFA for 28-day mortality showed good calibration.ConclusionIn patients with sepsis in the ICU, the modified SOFA score performed better than the original SOFA score in predicting 28-day mortality.