Background: Data on the benefits of rapid microbiological testing on antimicrobial consumption (AC) and antimicrobial resistance patterns (ARPs) are scarce. We evaluated the impact of a protocol based on rapid techniques on AC and ARP in intensive care (ICU) patients. Methods: A retrospective pre- (2018) and post-intervention (2019–2021) study was conducted in ICU patients. A rapid diagnostic algorithm was applied starting in 2019 in patients with a lower respiratory tract infection. The incidence of nosocomial infections, ARPs, and AC as DDDs (defined daily doses) were monitored. Results: A total of 3635 patients were included: 987 in the pre-intervention group and 2648 in the post-intervention group. The median age was 60 years, the sample was 64% male, and the average APACHE II and SOFA scores were 19 points and 3 points. The overall ICU mortality was 17.2% without any differences between the groups. An increase in the number of infections was observed in the post-intervention group (44.5% vs. 17.9%, p < 0.01), especially due to an increase in the incidence of ventilator-associated pneumonia (44.6% vs. 25%, p < 0.001). AC decreased from 128.7 DDD in 2018 to 66.0 DDD in 2021 (rate ratio = 0.51). An increase in Pseudomonas aeruginosa susceptibility of 23% for Piperacillin/tazobactam and 31% for Meropenem was observed. Conclusion: The implementation of an algorithm based on rapid microbiological diagnostic techniques allowed for a significant reduction in AC and ARPs without affecting the prognosis of critically ill patients.

Background: Liposomal amphotericin B (L-AmB) has become the mainstay of treatment for severe invasive fungal infections. However, the potential for renal toxicity must be considered. Aims: To evaluate the incidence of acute kidney injury (AKI) in critically ill patients receiving L-AmB for more than 48 h. Methods: Retrospective, observational, single-center study. Clinical, demographic and laboratory variables were obtained automatically from the electronic medical record. AKI incidence was analyzed in the entire population and in patients with a “low” or “high” risk of AKI based on their creatinine levels at the outset of the study. Factors associated with the development of AKI were studied using random forest models. Results: Finally, 67 patients with a median age of 61 (53–71) years, 67% male, a median SOFA of 4 (3–6.5) and a crude mortality of 34.3% were included. No variations in serum creatinine were observed during the observation period, except for a decrease in the high-risk subgroup. A total of 26.8% (total population), 25% (low risk) and 13% (high risk) of patients developed AKI. Norepinephrine, the SOFA score, furosemide (general model), potassium, C-reactive protein and procalcitonin (low-risk subgroup) were the variables identified by the random forest models as important contributing factors to the development of AKI other than L-AmB administration. Conclusions: The development of AKI is multifactorial and the administration of L-AmB appears to be safe in this group of patients.

Background/Objectives: Ventilator-associated pneumonia (VAP) is the main nosocomial infection in intensive care units (ICUs) that causes the highest morbidity and mortality. The aim of our study is to investigate variations in crude ICU mortality among patients with VAP over the past decade. We also wish to identify associated risk factors, evaluate changes in the etiology, and assess the incidence and impact of inappropriate empirical antibiotic treatment (IEAT). Methods: We conducted a retrospective, observational, single-center study over a 10-year period (2014–2024), including critically ill patients who developed VAP. The population was divided into three periods: (P1) from 2014 to 2018 (pre-COVID-19); (P2) from 2019 to 2021 (COVID-19); and (P3) from 2022 to 2024 (post-COVID-19). Binary logistic regression was used to identify which variables were independently associated with ICU mortality. Results: A total of 220 patients were included in the study (P1 = 47, P2 = 96, and P3 = 77 patients). The most prevalent microorganisms identified were P. aeruginosa, Klebsiella spp., and S. aureus. Significant variations in etiology were not observed over the years. The incidence of IEAT was 4.5%, with no observed differences between the study periods. Crude ICU mortality was 33.6%, with higher rates observed in IEAT (40% vs. 33.3%, p = 0.73). In patients with appropriate empiric antibiotic treatment (AEAT), there was a significant decrease in crude mortality over the years from 42.2% in P1 to 22.2% in P3 (p < 0.001). Age (OR = 1.04; 95% CI = 1.01–1.08) and P2 (OR = 2.8; 95% CI = 1.1–7.4) were found to be independently associated with an increased risk of mortality. Conversely, a lower risk of death was associated with mean arterial pressure (OR = 0.94; 95% CI = 0.69–0.99) and the use of syndromic respiratory panel (OR = 0.23; 95% CI = 0.07–0.68). Conclusions: A reduction in crude VAP mortality over the years was observed, with no change in the etiology or rate of IEAT. The implementation of protocols using respiratory syndromic panels could be a measure to implement to reduce VAP mortality.

Background/Objectives: The SARS-CoV-2 and influenza A (H1N1)pdm09 pandemics have resulted in high numbers of ICU admissions, with high mortality. Identifying risk factors for ICU mortality at the time of admission can help optimize clinical decision making. However, the risk factors identified may differ, depending on the type of analysis used. Our aim is to compare the risk factors and performance of a linear model (multivariable logistic regression, GLM) with a non-linear model (random forest, RF) in a large national cohort. Methods: A retrospective analysis was performed on a multicenter database including 8902 critically ill patients with influenza A (H1N1)pdm09 or COVID-19 admitted to 184 Spanish ICUs. Demographic, clinical, laboratory, and microbiological data from the first 24 h were used. Prediction models were built using GLM and RF. The performance of the GLM was evaluated by area under the ROC curve (AUC), precision, sensitivity, and specificity, while the RF by out-of-bag (OOB) error and accuracy. In addition, in the RF, the im-portance of the variables in terms of accuracy reduction (AR) and Gini index reduction (GI) was determined. Results: Overall mortality in the ICU was 25.8%. Model performance was similar, with AUC = 76% for GLM, and AUC = 75.6% for RF. GLM identified 17 independent risk factors, while RF identified 19 for AR and 23 for GI. Thirteen variables were found to be important in both models. Laboratory variables such as procalcitonin, white blood cells, lactate, or D-dimer levels were not significant in GLM but were significant in RF. On the contrary, acute kidney injury and the presence of Acinetobacter spp. were important variables in the GLM but not in the RF. Conclusions: Although the performance of linear and non-linear models was similar, different risk factors were determined, depending on the model used. This alerts clinicians to the limitations and usefulness of studies limited to a single type of model.

Background: Bacterial/fungal coinfections (COIs) are associated with antibiotic overuse, poor outcomes such as prolonged ICU stay, and increased mortality. Our aim was to develop machine learning-based predictive models to identify respiratory bacterial or fungal coinfections upon ICU admission. Methods: We conducted a secondary analysis of two prospective multicenter cohort studies with confirmed influenza A (H1N1)pdm09 and COVID-19. Multiple logistic regression (MLR) and random forest (RF) were used to identify factors associated with BFC in the overall population and in each subgroup (influenza and COVID-19). The performance of these models was assessed by the area under the ROC curve (AUC) and out-of-bag (OOB) methods for MLR and RF, respectively. Results: Of the 8902 patients, 41.6% had influenza and 58.4% had SARS-CoV-2 infection. The median age was 60 years, 66% were male, and the crude ICU mortality was 25%. BFC was observed in 14.2% of patients. Overall, the predictive models showed modest performances, with an AUC of 0.68 (MLR) and OOB 36.9% (RF). Specific models did not show improved performance. However, age, procalcitonin, CRP, APACHE II, SOFA, and shock were factors associated with BFC in most models. Conclusions: Machine learning models do not adequately predict the presence of co-infection in critically ill patients with pandemic virus infection. However, the presence of factors such as advanced age, elevated procalcitonin or CPR, and high severity of illness should alert clinicians to the need to rule out this complication on admission to the ICU.

Background: The Patient Outcome Assessment and Decision Support (PADS) model is a real-time framework designed to predict both mortality and the likelihood of discharge within 48 h in critically ill patients. By combining these predictions, PADS enables clinically meaningful stratification of patient trajectories, supporting bedside decision-making and the planning of critical care resources such as nursing allocation and surgical scheduling. Methods: PADS integrates routinely collected clinical data: SOFA variables, age, gender, admission type, and comorbidities. It consists of two Long Short-Term Memory (LSTM) neural networks—one predicting the probability of death and the other the probability of discharge within 48 h. The combination places each patient into one of four states: alive/discharged within 48 h, alive/not discharged, dead within 48 h, or dead later. The model was trained using MIMIC-IV data, emphasizing ease of implementation in units with electronic health records. Out of the 76,540 stays present in MIMIC-IV (53,150 patients), 32,875 (25,555 patients) were used after excluding those with short stays (<48 h) or life support treatment limitations. The code is open, well-documented, and designed for reproducibility and external validation. Results: The model achieved strong performance: AUCROC of 0.94 (±0.03) for mortality and 0.89 (±0.07) for discharge on training data, and 0.87 (±0.02) and 0.88 (±0.03), respectively, on the test set. As a comparison, benchmark models obtain worse accuracy (−13.4% for APS III, −19% for OASIS, and −7.4% for SAPS II). Predictions are visualized in an intuitive format to support clinical interpretation. Conclusions: PADS offers a transparent, reproducible, and practical tool that supports both individual patient care and the strategic organization of intensive care resources by anticipating short-term outcomes.