Integrating Social Determinants of Health with SOFA Scoring to Enhance Mortality Prediction in Septic Patients: A Multidimensional Prognostic Model

Background The Sequential Organ Failure Assessment (SOFA) score is an established tool for monitoring organ failure and defining sepsis. However, its predictive power for sepsis mortality may not account for the full spectrum of influential factors. Recent literature highlights the potential impact of socioeconomic and demographic factors on sepsis outcomes. Objective This study assessed the prognostic value of SOFA scores relative to demographic and social health determinants in predicting sepsis mortality, and evaluated whether a combined model enhances predictive accuracy. Methods We utilized the Medical Information Mart for Intensive Care (MIMIC)-IV database for retrospective data and the Penn State Health (PSH) cohort for prospective external validation. SOFA scores, social/demographic data, and the Charlson Comorbidity Index were used to train a Random Forest model using the MIMIC-IV dataset, and then to externally validate it using the PSH dataset. Findings Of 32,970 sepsis patients in the MIMIC-IV dataset, 6,824 (20.7%) died within 30 days. The model incorporating demographic, socioeconomic, and comorbidity data with SOFA scores showed improved predictive accuracy over SOFA parameters alone. Day 2 SOFA components were highly predictive, with additional factors like age, weight, and comorbidity enhancing prognostic precision. External validation demonstrated consistency in the model’s performance, with delta SOFA between days 1 and 3 emerging as a strong mortality predictor. Conclusion Integrating patient-specific information with clinical measures significantly enhances the predictive accuracy for sepsis mortality. Our findings suggest the need for a multidimensional prognostic framework, considering both clinical and non-clinical patient information for a more accurate sepsis outcome prediction. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This study was funded by the National Institute of General Medical Sciences ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Ethics committee/IRB of Penn State University gave ethical approval for this work I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors * AUROC : area under the receiver operating characteristic curve CCI : Charlson comorbidity index ICU : intensive care unit MIMIC : Medical Information Mart for Intensive Care NPV : negative predictive value PPV : positive predictive value PSH : Penn State Health SOFA : sequential (or sepsis-associated) organ failure assessment