RESUMEN
OBJECTIVES: To assess the value of machine learning approaches in the development of a multivariable model for early prediction of ICU death in patients with acute respiratory distress syndrome (ARDS). DESIGN: A development, testing, and external validation study using clinical data from four prospective, multicenter, observational cohorts. SETTING: A network of multidisciplinary ICUs. PATIENTS: A total of 1,303 patients with moderate-to-severe ARDS managed with lung-protective ventilation. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We developed and tested prediction models in 1,000 ARDS patients. We performed logistic regression analysis following variable selection by a genetic algorithm, random forest and extreme gradient boosting machine learning techniques. Potential predictors included demographics, comorbidities, ventilatory and oxygenation descriptors, and extrapulmonary organ failures. Risk modeling identified some major prognostic factors for ICU mortality, including age, cancer, immunosuppression, Pa o2 /F io2 , inspiratory plateau pressure, and number of extrapulmonary organ failures. Together, these characteristics contained most of the prognostic information in the first 24 hours to predict ICU mortality. Performance with machine learning methods was similar to logistic regression (area under the receiver operating characteristic curve [AUC], 0.87; 95% CI, 0.82-0.91). External validation in an independent cohort of 303 ARDS patients confirmed that the performance of the model was similar to a logistic regression model (AUC, 0.91; 95% CI, 0.87-0.94). CONCLUSIONS: Both machine learning and traditional methods lead to promising models to predict ICU death in moderate/severe ARDS patients. More research is needed to identify markers for severity beyond clinical determinants, such as demographics, comorbidities, lung mechanics, oxygenation, and extrapulmonary organ failure to guide patient management.
Asunto(s)
Síndrome de Dificultad Respiratoria , Humanos , Unidades de Cuidados Intensivos , Pulmón , Estudios Prospectivos , Respiración Artificial/métodos , Síndrome de Dificultad Respiratoria/terapiaRESUMEN
OBJECTIVE: To evaluate the effect of selective decontamination of the digestive tract (SDD) on hospital-acquired infections (HAIs) in patients with acute burn injury requiring admission to a Burns Unit (BU). DESIGN: Retrospective before-and-after cohort study, between January 2017 and June 2023. SDD was implemented in March 2019, dividing patients into two groups. SETTING: Four-bed BU, in a referral University Hospital in Spain. PATIENTS: All the patients admitted during the study period were eligible for analysis. Patients who died or were discharged within 48hours of admission, and patients with an estimated survival less than 10% not considered for full escalation of therapy were excluded. INTERVENTION: SDD comprised the administration of a 4-day course of an intravenous antibiotic, and an oral suspension and oral topical paste of non-absorbable antibiotics during the stay in the BU. MAIN VARIABLE OF INTEREST: Incidence of HAIs during the stay in the BU. SECONDARY OUTCOMES: incidence of specific types of infections by site (bacteremia, pneumonia, skin and soft tissue infection) and microorganism (Gram-positive, Gram-negative, fungi), and safety endpoints. RESULTS: We analyzed 72 patients: 27 did not receive SDD, and 45 received SDD. The number of patients who developed HAIs were 21 (77.8%) and 21 (46.7%) in the non-SDD and the SDD groups, respectively (p=0.009). The number of hospital-acquired infectious episodes were 2.52 (1.21-3.82) and 1.13 (0.54-1.73), respectively (p=0.029). CONCLUSIONS: SDD was associated with a reduced incidence of bacterial HAIs and a decrease in the number of infectious episodes per patient.
RESUMEN
OBJECTIVES: To establish the epidemiological characteristics, ventilator management, and outcomes in patients with acute hypoxemic respiratory failure (AHRF), with or without acute respiratory distress syndrome (ARDS), in the era of lung-protective mechanical ventilation (MV). DESIGN: A 6-month prospective, epidemiological, observational study. SETTING: A network of 22 multidisciplinary ICUs in Spain. PATIENTS: Consecutive mechanically ventilated patients with AHRF (defined as Pao2/Fio2 ≤ 300 mm Hg on positive end-expiratory pressure [PEEP] ≥ 5 cm H2O and Fio2 ≥ 0.3) and followed-up until hospital discharge. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Primary outcomes were prevalence of AHRF and ICU mortality. Secondary outcomes included prevalence of ARDS, ventilatory management, and use of adjunctive therapies. During the study period, 9,803 patients were admitted: 4,456 (45.5%) received MV, 1,271 (13%) met AHRF criteria (1,241 were included into the study: 333 [26.8%] met Berlin ARDS criteria and 908 [73.2%] did not). At baseline, tidal volume was 6.9 ± 1.1 mL/kg predicted body weight, PEEP 8.4 ± 3.1 cm H2O, Fio2 0.63 ± 0.22, and plateau pressure 21.5 ± 5.4 cm H2O. ARDS patients received higher Fio2 and PEEP than non-ARDS (0.75 ± 0.22 vs 0.59 ± 0.20 cm H2O and 10.3 ± 3.4 vs 7.7 ± 2.6 cm H2O, respectively [p < 0.0001]). Adjunctive therapies were rarely used in non-ARDS patients. Patients without ARDS had higher ventilator-free days than ARDS (12.2 ± 11.6 vs 9.3 ± 9.7 d; p < 0.001). All-cause ICU mortality was similar in AHRF with or without ARDS (34.8% [95% CI, 29.7-40.2] vs 35.5% [95% CI, 32.3-38.7]; p = 0.837). CONCLUSIONS: AHRF without ARDS is a very common syndrome in the ICU with a high mortality that requires specific studies into its epidemiology and ventilatory management. We found that the prevalence of ARDS was much lower than reported in recent observational studies.
RESUMEN
BET (Biological Engineering Technology) formula uses fluids with high albumin concentration to resuscitate burn patients. It estimates fluid resuscitation as a function of Body Burned Surface Area (BBSA) (ml/h = BBSA (m2) × 220) and administers it through a combination of lactated ringer and 20% Albumin starting at a 1:1 relationship. The proportion of albumin is decreased every 8 h, and infusion rate is modified according to urinary output. The study's purpose was to review resuscitation related variables of all burned patients treated in our unit using BET formula. We retrospectively analyzed all patients admitted to our critical care burn unit during a five year period. Only those admitted within the first 12 h post-burn injury were considered. 40 patients met all inclusion criteria. Resuscitation volume during the first 24 h was 2.58 ml/kg/%BBSA, significantly less than Parkland's estimation (4 ml/kg/%BBSA; P < 0.05). Patients were successfully resuscitated showing a significant base excess increase and lactate clearance during the resuscitation period (base excess 120%; lactate 29%; P < 0.05). Burn related complications where: ARDS 27%, renal dysfunction 53%, wound deepening 20%, abdominal compartment syndrome 4.5%. In conclusion, BET formula is capable of resuscitating burn patients successfully, limiting fluid administration.
Asunto(s)
Albúminas/administración & dosificación , Quemaduras/terapia , Coloides/administración & dosificación , Fluidoterapia/métodos , Lactato de Ringer/administración & dosificación , Lesión Renal Aguda/etiología , Adulto , Anciano , Albúminas/uso terapéutico , Superficie Corporal , Quemaduras/complicaciones , Quemaduras/metabolismo , Quemaduras/patología , Progresión de la Enfermedad , Femenino , Humanos , Ácido Láctico/metabolismo , Masculino , Persona de Mediana Edad , Síndrome de Dificultad Respiratoria/etiología , Resucitación/métodos , Estudios Retrospectivos , Lactato de Ringer/uso terapéutico , Resultado del TratamientoRESUMEN
Frostbite is a particularly severe form of cold-induced injury that most frequently causes tissular damage in acral parts (hands and feet) and usually involves a small extension of the TBSA. Here, we present a rare case of frostbite affecting a large area (27%), which was successfully treated in a similar way to a thermal burn injury.