Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms

A Focus on the Pathophysiology of Adrenomedullin Expression: Endothelitis and Organ Damage in Severe Viral and Bacterial Infections

Adrenomedullin (ADM) is a peptide hormone produced primarily in the adrenal glands, playing a crucial role in various physiological processes. As well as improving vascular integrity and decreasing vascular permeability, ADM acts as a vasodilator, positive inotrope, diuretic, natriuretic and bronchodilator, antagonizing angiotensin II by inhibiting aldosterone secretion. ADM also has antihypertrophic, anti-apoptotic, antifibrotic, antioxidant, angiogenic and immunoregulatory effects and antimicrobial properties. ADM expression is upregulated by hypoxia, inflammation-inducing cytokines, viral or bacterial substances, strength of shear stress, and leakage of blood vessels. These pathological conditions are established during systemic inflammation that can result from infections, surgery, trauma/accidents or burns. The ability to rapidly identify infections and the prognostic, predictive power makes it a valuable tool in severe viral and bacterial infections burdened by high incidence and mortality. This review sheds light on the pathophysiological processes that in severe viral or bacterial infections cause endothelitis up to the development of organ damage, the resulting increase in ADM levels dosed through its more stable peptide mid-regional proadrenomedullin (MR-proADM), the most significant studies that attest to its diagnostic and prognostic accuracy in highlighting the severity of viral or bacterial infections and appropriate therapeutic insights.

Mid-Regional Pro-Adrenomedullin Can Predict Organ Failure and Prognosis in Sepsis?

Sepsis causes immune dysregulation and endotheliitis, with an increase in mid-regional pro-adrenomedullin (MR-proADM). The aim of the study is to determine an MR-proADM value that, in addition to clinical diagnosis, can identify patients with localized infection or those with sepsis/septic shock, with specific organ damage or with the need for intensive care unit (ICU) transfer and prognosis. The secondary aim is to correlate the MR-proADM value with the length of stay (LOS). In total, 301 subjects with sepsis (124/301 with septic shock) and 126 with localized infection were retrospectively included. In sepsis, MR-proADM ≥ 3.39 ng/mL identified acute kidney injury (AKI); ≥2.99 ng/mL acute respiratory distress syndrome (ARDS); ≥2.28 ng/mL acute heart failure (AHF); ≥2.55 ng/mL Glascow Coma Scale (GCS) < 15; ≥3.38 multi-organ involvement; ≥3.33 need for ICU transfer; ≥2.0 Sequential Organ Failure Assessment (SOFA) score ≥ 2; and ≥3.15 ng/mL non-survivors. The multivariate analysis showed that MR-proADM ≥ 2 ng/mL correlates with AKI, anemia and SOFA score ≥ 2, and MR-proADM ≥ 3 ng/mL correlates with AKI, GCS < 15 and SOFA score ≥ 2. A correlation between mortality and AKI, GCS < 15, ICU transfer and cathecolamine administration was found. In localized infection, MR-proADM at admission ≥ 1.44 ng/mL identified patients with AKI; ≥1.0 ng/mL with AHF; and ≥1.44 ng/mL with anemia and SOFA score ≥ 2. In the multivariate analysis, MR-proADM ≥ 1.44 ng/mL correlated with AKI, anemia, SOFA score ≥ 2 and AHF. MR-proADM is a marker of oxidative stress due to an infection, reflecting severity proportionally to organ damage.

Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma

Purpose

Earlier research has identified several potentially predictive features including biomarkers associated with trauma, which can be used to assess the risk for harmful outcomes of polytraumatized patients. These features encompass various aspects such as the nature and severity of the injury, accompanying health conditions, immune and inflammatory markers, and blood parameters linked to organ functioning, however their applicability is limited. Numerous indicators relevant to the patients` outcome are routinely gathered in the intensive care unit (ICU) and recorded in electronic medical records, rendering them suitable predictors for risk assessment of polytraumatized patients.

Methods

317 polytraumatized patients were included, and the influence of 29 clinical and biological features on the complication patterns for systemic inflammatory response syndrome (SIRS), pneumonia and sepsis were analyzed with a machine learning workflow including clustering, classification and explainability using SHapley Additive exPlanations (SHAP) values. The predictive ability of the analyzed features within three days after admission to the hospital were compared based on patient-specific outcomes using receiver-operating characteristics.

Results

A correlation and clustering analysis revealed that distinct patterns of injury and biomarker patterns were observed for the major complication classes. A k-means clustering suggested four different clusters based on the major complications SIRS, pneumonia and sepsis as well as a patient subgroup that developed no complications. For classification of the outcome groups with no complications, pneumonia and sepsis based on boosting ensemble classification, 90% were correctly classified as low-risk group (no complications). For the high-risk groups associated with development of pneumonia and sepsis, 80% of the patients were correctly identified. The explainability analysis with SHAP values identified the top-ranking features that had the largest impact on the development of adverse outcome patterns. For both investigated risk scenarios (infectious complications and long ICU stay) the most important features are SOFA score, Glasgow Coma Scale, lactate, GGT and hemoglobin blood concentration.

Conclusion

The machine learning-based identification of prognostic feature patterns in patients with traumatic injuries may improve tailoring personalized treatment modalities to mitigate the adverse outcomes in high-risk patient clusters.

Dissecting contributions of individual systemic inflammatory response syndrome criteria from a prospective algorithm to the prediction and diagnosis of sepsis in a polytrauma cohort

Background

Sepsis is the leading cause of death in intensive care units (ICUs), and its timely detection and treatment improve clinical outcome and survival. Systemic inflammatory response syndrome (SIRS) refers to the concurrent fulfillment of at least two out of the following four clinical criteria: tachycardia, tachypnea, abnormal body temperature, and abnormal leukocyte count. While SIRS was controversially abandoned from the current sepsis definition, a dynamic SIRS representation still has potential for sepsis prediction and diagnosis.

Objective

We retrospectively elucidate the individual contributions of the SIRS criteria in a polytrauma cohort from the post-surgical ICU of University Medical Center Mannheim (Germany).

Methods

We used a dynamic and prospective SIRS algorithm tailored to the ICU setting by accounting for catecholamine therapy and mechanical ventilation. Two clinically relevant tasks are considered: (i) sepsis prediction using the first 24 h after admission to our ICU, and (ii) sepsis diagnosis using the last 24 h before sepsis onset and a time point of comparable ICU treatment duration for controls, respectively. We determine the importance of individual SIRS criteria by systematically varying criteria weights when summarizing the SIRS algorithm output with SIRS descriptors and assessing the classification performance of the resulting logistic regression models using a specifically developed ranking score.

Results

Our models perform better for the diagnosis than the prediction task (maximum AUROC 0.816 vs. 0.693). Risk models containing only the SIRS level average mostly show reasonable performance across criteria weights, with prediction and diagnosis AUROCs ranging from 0.455 (weight on leukocyte criterion only) to 0.693 and 0.619 to 0.800, respectively. For sepsis prediction, temperature and tachypnea are the most important SIRS criteria, whereas the leukocytes criterion is least important and potentially even counterproductive. For sepsis diagnosis, all SIRS criteria are relevant, with the temperature criterion being most influential.

Conclusion

SIRS is relevant for sepsis prediction and diagnosis in polytrauma, and no criterion should a priori be omitted. Hence, the original expert-defined SIRS criteria are valid, capturing important sepsis risk determinants. Our prospective SIRS algorithm provides dynamic determination of SIRS criteria and descriptors, allowing their integration in sepsis risk models also in other settings.