Pub Date : 2024-11-01DOI: 10.1016/j.medin.2024.07.005
María Jesús Broch Porcar, Álvaro Castellanos-Ortega
{"title":"Respuesta a «Seguridad del paciente, ¿qué aportan la simulación clínica y la innovación docente?»","authors":"María Jesús Broch Porcar, Álvaro Castellanos-Ortega","doi":"10.1016/j.medin.2024.07.005","DOIUrl":"10.1016/j.medin.2024.07.005","url":null,"abstract":"","PeriodicalId":49268,"journal":{"name":"Medicina Intensiva","volume":"48 11","pages":"Pages 670-671"},"PeriodicalIF":2.7,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142592698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-01DOI: 10.1016/j.medin.2024.06.004
Alejandro González-Castro , Elena Cuenca Fito , Carmen Huertas Martín , Yhivian Peñasco , Aurio Fajardo Campoverdi
{"title":"Análisis de los valores de carga de energía en ventilación mecánica en pacientes obesos con insuficiencia respiratoria hipoxémica secundaria a SARS-CoV-2","authors":"Alejandro González-Castro , Elena Cuenca Fito , Carmen Huertas Martín , Yhivian Peñasco , Aurio Fajardo Campoverdi","doi":"10.1016/j.medin.2024.06.004","DOIUrl":"10.1016/j.medin.2024.06.004","url":null,"abstract":"","PeriodicalId":49268,"journal":{"name":"Medicina Intensiva","volume":"48 11","pages":"Pages 663-666"},"PeriodicalIF":2.7,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141847730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1016/j.medin.2024.07.009
Luis Martin-Villen , Alejandro Adsuar Gomez , José Manuel Garrido Jimenez , Jose Luis Perez Vela , María Paz Fuset Cabanes
Cardiogenic shock (CS) is a highly complex clinical condition that requires a management strategy focused on early resolution of the underlying cause and the provision of circulatory support. In cases of refractory CS, mechanical circulatory support (MCS) is employed to replace the failed cardiocirculatory system, thereby preventing the development of multiorgan failure. There are various types of MCS, and patients with CS typically require devices that are either short-term (< 15 days) or intermediate-term (15-30 days). When choosing the device the underlying cause of CS, as well as the presence or absence of concomitant conditions such as failed ventricle, respiratory failure, and the intended purpose of the support should be taken into consideration. Patients with MCS require the comprehensive care indicated in complex critically ill patients with multiorgan dysfunction, with an emphasis on device monitoring and control. Different complications may arise during support management, and its withdrawal must be protocolized.
{"title":"Soporte circulatorio mecánico en el paciente en shock cardiogénico","authors":"Luis Martin-Villen , Alejandro Adsuar Gomez , José Manuel Garrido Jimenez , Jose Luis Perez Vela , María Paz Fuset Cabanes","doi":"10.1016/j.medin.2024.07.009","DOIUrl":"10.1016/j.medin.2024.07.009","url":null,"abstract":"<div><div>Cardiogenic shock (CS) is a highly complex clinical condition that requires a management strategy focused on early resolution of the underlying cause and the provision of circulatory support. In cases of refractory CS, mechanical circulatory support (MCS) is employed to replace the failed cardiocirculatory system, thereby preventing the development of multiorgan failure. There are various types of MCS, and patients with CS typically require devices that are either short-term (< 15 days) or intermediate-term (15-30 days). When choosing the device the underlying cause of CS, as well as the presence or absence of concomitant conditions such as failed ventricle, respiratory failure, and the intended purpose of the support should be taken into consideration. Patients with MCS require the comprehensive care indicated in complex critically ill patients with multiorgan dysfunction, with an emphasis on device monitoring and control. Different complications may arise during support management, and its withdrawal must be protocolized.</div></div>","PeriodicalId":49268,"journal":{"name":"Medicina Intensiva","volume":"48 12","pages":"Pages 714-727"},"PeriodicalIF":2.7,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142721578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-26DOI: 10.1016/j.medin.2024.04.011
Jesús Abelardo Barea-Mendoza, Zaira Molina-Collado, María Ángeles Ballesteros-Sanz, Luisa Corral-Ansa, Maite Misis del Campo, Cándido Pardo-Rey, Juan Angel Tihista-Jiménez, Carmen Corcobado-Márquez, Juan Pedro Martín del Rincón, Juan Antonio Llompart-Pou, Luis Alfonso Marcos-Prieto, Ander Olazabal-Martínez, Rubén Herrán-Monge, Ana María Díaz-Lamas, Mario Chico-Fernández
Objective
To analyze the impact of positive end-expiratory pressure (PEEP) changes on intracranial pressure (ICP) dynamics in patients with acute brain injury (ABI).
Design
Observational, prospective and multicenter study (PEEP-PIC study).
Setting
Seventeen intensive care units in Spain.
Patients
Neurocritically ill patients who underwent invasive neuromonitorization from November 2017 to June 2018.
Interventions
Baseline ventilatory, hemodynamic and neuromonitoring variables were collected immediately before PEEP changes and during the following 30 min.
Main variables of interest
PEEP and ICP changes.
Results
One-hundred and nine patients were included. Mean age was 52.68 (15.34) years, male 71 (65.13%). Traumatic brain injury was the cause of ABI in 54 (49.54%) patients. Length of mechanical ventilation was 16.52 (9.23) days. In-hospital mortality was 21.1%. PEEP increases (mean 6.24–9.10 cmH2O) resulted in ICP increase from 10.4 to 11.39 mmHg, P < .001, without changes in cerebral perfusion pressure (CPP) (P = .548). PEEP decreases (mean 8.96 to 6.53 cmH2O) resulted in ICP decrease from 10.5 to 9.62 mmHg (P = .052), without changes in CPP (P = .762). Significant correlations were established between the increase of ICP and the delta PEEP (R = 0.28, P < .001), delta driving pressure (R = 0.15, P = .038) and delta compliance (R = −0.14, P = .052). ICP increment was higher in patients with lower baseline ICP.
Conclusions
PEEP changes were not associated with clinically relevant modifications in ICP values in ABI patients. The magnitude of the change in ICP after PEEP increase was correlated with the delta of PEEP, the delta driving pressure and the delta compliance.
{"title":"Effects of PEEP on intracranial pressure in patients with acute brain injury: An observational, prospective and multicenter study","authors":"Jesús Abelardo Barea-Mendoza, Zaira Molina-Collado, María Ángeles Ballesteros-Sanz, Luisa Corral-Ansa, Maite Misis del Campo, Cándido Pardo-Rey, Juan Angel Tihista-Jiménez, Carmen Corcobado-Márquez, Juan Pedro Martín del Rincón, Juan Antonio Llompart-Pou, Luis Alfonso Marcos-Prieto, Ander Olazabal-Martínez, Rubén Herrán-Monge, Ana María Díaz-Lamas, Mario Chico-Fernández","doi":"10.1016/j.medin.2024.04.011","DOIUrl":"10.1016/j.medin.2024.04.011","url":null,"abstract":"<div><h3>Objective</h3><div>To analyze the impact of positive end-expiratory pressure (PEEP) changes on intracranial pressure (ICP) dynamics in patients with acute brain injury (ABI).</div></div><div><h3>Design</h3><div>Observational, prospective and multicenter study (PEEP-PIC study).</div></div><div><h3>Setting</h3><div>Seventeen intensive care units in Spain.</div></div><div><h3>Patients</h3><div>Neurocritically ill patients who underwent invasive neuromonitorization from November 2017 to June 2018.</div></div><div><h3>Interventions</h3><div>Baseline ventilatory, hemodynamic and neuromonitoring variables were collected immediately before PEEP changes and during the following 30 min.</div></div><div><h3>Main variables of interest</h3><div>PEEP and ICP changes.</div></div><div><h3>Results</h3><div>One-hundred and nine patients were included. Mean age was 52.68 (15.34) years, male 71 (65.13%). Traumatic brain injury was the cause of ABI in 54 (49.54%) patients. Length of mechanical ventilation was 16.52 (9.23) days. In-hospital mortality was 21.1%. PEEP increases (mean 6.24–9.10 cmH2O) resulted in ICP increase from 10.4 to 11.39 mmHg, <em>P</em> < .001, without changes in cerebral perfusion pressure (CPP) (<em>P</em> = .548). PEEP decreases (mean 8.96 to 6.53 cmH2O) resulted in ICP decrease from 10.5 to 9.62 mmHg (<em>P</em> = .052), without changes in CPP (<em>P</em> = .762). Significant correlations were established between the increase of ICP and the delta PEEP (R = 0.28, <em>P</em> < .001), delta driving pressure (R = 0.15, <em>P</em> = .038) and delta compliance (R = −0.14, <em>P</em> = .052). ICP increment was higher in patients with lower baseline ICP.</div></div><div><h3>Conclusions</h3><div>PEEP changes were not associated with clinically relevant modifications in ICP values in ABI patients. The magnitude of the change in ICP after PEEP increase was correlated with the delta of PEEP, the delta driving pressure and the delta compliance.</div></div>","PeriodicalId":49268,"journal":{"name":"Medicina Intensiva","volume":"48 10","pages":"Pages 594-601"},"PeriodicalIF":2.7,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142322286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-26DOI: 10.1016/j.medin.2024.05.023
María Romero Carratala , Luis Pérez de Amezaga Tomás , María Sala Carazo , Gemma Rialp Cervera
{"title":"Meropenem for the management of valproic acid intoxication: a case report and a review of the literature","authors":"María Romero Carratala , Luis Pérez de Amezaga Tomás , María Sala Carazo , Gemma Rialp Cervera","doi":"10.1016/j.medin.2024.05.023","DOIUrl":"10.1016/j.medin.2024.05.023","url":null,"abstract":"","PeriodicalId":49268,"journal":{"name":"Medicina Intensiva","volume":"48 10","pages":"Pages 620-622"},"PeriodicalIF":2.7,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142322347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-26DOI: 10.1016/j.medin.2024.06.007
María Martínez-Martínez , María Vidal-Burdeus , Jordi Riera , Aitor Uribarri , Elisabet Gallart , Laia Milà , Pau Torrella , Irene Buera , Luis Chiscano-Camon , Bruno García del Blanco , Carlota Vigil-Escalera , José A. Barrabés , Jordi Llaneras , Juan Carlos Ruiz-Rodríguez , Cristopher Mazo , Jorge Morales , Ricard Ferrer , Ignacio Ferreira-Gonzalez , Eduard Argudo
Objective
To analyze if the implementation of a multidisciplinary extracorporeal cardiopulmonary resuscitation (ECPR) program in a tertiary hospital in Spain is feasible and could yield survival outcomes similar to international published experiences.
Design
Retrospective observational cohort study.
Setting
One tertiary referral university hospital in Spain.
Patients
All adult patients receiving ECPR between January 2019 and April 2023.
Interventions
Prospective collection of variables and follow-up for up to 180 days.
Main variables of interest
To assess outcomes, survival with good neurological outcome defined as a Cerebral Performance Categories scale 1–2 at 180 days was used. Secondary variables were collected including demographics and comorbidities, cardiac arrest and cannulation characteristics, ROSC, ECMO-related complications, survival to ECMO decannulation, survival at Intensive Care Unit (ICU) discharge, survival at 180 days, neurological outcome, cause of death and eligibility for organ donation.
Results
Fifty-four patients received ECPR, 29 for OHCA and 25 for IHCA. Initial shockable rhythm was identified in 27 (50%) patients. The most common cause for cardiac arrest was acute coronary syndrome [29 (53.7%)] followed by pulmonary embolism [7 (13%)] and accidental hypothermia [5 (9.3%)]. Sixteen (29.6%) patients were alive at 180 days, 15 with good neurological outcome. Ten deceased patients (30.3%) became organ donors after neuroprognostication.
Conclusions
The implementation of a multidisciplinary ECPR program in an experienced Extracorporeal Membrane Oxygenation center in Spain is feasible and can lead to good survival outcomes and valid organ donors.
{"title":"Outcomes of an extracorporeal cardiopulmonary resuscitation (ECPR) program for in- and out-of-hospital cardiac arrest in a tertiary hospital in Spain","authors":"María Martínez-Martínez , María Vidal-Burdeus , Jordi Riera , Aitor Uribarri , Elisabet Gallart , Laia Milà , Pau Torrella , Irene Buera , Luis Chiscano-Camon , Bruno García del Blanco , Carlota Vigil-Escalera , José A. Barrabés , Jordi Llaneras , Juan Carlos Ruiz-Rodríguez , Cristopher Mazo , Jorge Morales , Ricard Ferrer , Ignacio Ferreira-Gonzalez , Eduard Argudo","doi":"10.1016/j.medin.2024.06.007","DOIUrl":"10.1016/j.medin.2024.06.007","url":null,"abstract":"<div><h3>Objective</h3><div>To analyze if the implementation of a multidisciplinary extracorporeal cardiopulmonary resuscitation (ECPR) program in a tertiary hospital in Spain is feasible and could yield survival outcomes similar to international published experiences.</div></div><div><h3>Design</h3><div>Retrospective observational cohort study.</div></div><div><h3>Setting</h3><div>One tertiary referral university hospital in Spain.</div></div><div><h3>Patients</h3><div>All adult patients receiving ECPR between January 2019 and April 2023.</div></div><div><h3>Interventions</h3><div>Prospective collection of variables and follow-up for up to 180 days.</div></div><div><h3>Main variables of interest</h3><div>To assess outcomes, survival with good neurological outcome defined as a Cerebral Performance Categories scale 1–2 at 180 days was used. Secondary variables were collected including demographics and comorbidities, cardiac arrest and cannulation characteristics, ROSC, ECMO-related complications, survival to ECMO decannulation, survival at Intensive Care Unit (ICU) discharge, survival at 180 days, neurological outcome, cause of death and eligibility for organ donation.</div></div><div><h3>Results</h3><div>Fifty-four patients received ECPR, 29 for OHCA and 25 for IHCA. Initial shockable rhythm was identified in 27 (50%) patients. The most common cause for cardiac arrest was acute coronary syndrome [29 (53.7%)] followed by pulmonary embolism [7 (13%)] and accidental hypothermia [5 (9.3%)]. Sixteen (29.6%) patients were alive at 180 days, 15 with good neurological outcome. Ten deceased patients (30.3%) became organ donors after neuroprognostication.</div></div><div><h3>Conclusions</h3><div>The implementation of a multidisciplinary ECPR program in an experienced Extracorporeal Membrane Oxygenation center in Spain is feasible and can lead to good survival outcomes and valid organ donors.</div></div>","PeriodicalId":49268,"journal":{"name":"Medicina Intensiva","volume":"48 10","pages":"Pages 565-574"},"PeriodicalIF":2.7,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142322059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-26DOI: 10.1016/j.medin.2024.04.002
Lubov Stroh , Dennis Nurjadi , Florian Uhle , Thomas Bruckner , Armin Kalenka , Markus Alexander Weigand , Mascha Onida Fiedler-Kalenka
Objective
Oxygen has been used liberally in ICUs for a long time to prevent hypoxia in ICU- patients. Current evidence suggests that paO2 >300 mmHg should be avoided, it remains uncertain whether an “optimal level” exists. We investigated how “mild” hyperoxia influences diseases and in-hospital mortality.
Design
This is a retrospective study.
Setting
112 mechanically ventilated ICU-patients were enrolled.
Patients or participants
112 ventilated patients were included and categorized into two groups based on the median paO2 values measured in initial 24 h of mechanical ventilation: normoxia group (paO2 ≤ 100 mmHg, n = 43) and hyperoxia group patients (paO2 > 100 mmHg, n = 69).
Interventions
No interventions were performed.
Main variables of interest
The primary outcome was the incidence of pulmonary events, the secondary outcomes included the incidence of other new organ dysfunctions and in-hospital mortality.
Results
The baseline characteristics, such as age, body mass index, lactate levels, and severity of disease scores, were similar in both groups. There were no statistically significant differences in the incidence of pulmonary events, infections, and new organ dysfunctions between the groups. 27 out of 69 patients (39.1%) in the “mild” hyperoxia group and 12 out of 43 patients (27.9%) in the normoxia group died during their ICU or hospital stay (p = 0.54). The mean APACHE Score was 29.4 (SD 7.9) in the normoxia group and 30.0 (SD 6.7) in the hyperoxia group (p = 0.62).
Conclusions
We found no differences in pulmonary events, other coded diseases, and in-hospital mortality between both groups. It remains still unclear what the "best oxygen regime" is for intensive care patients.
{"title":"Pulmonary Events in ICU patients with hyperoxia: is it possible to relate arterial partial pressure of oxygen to coded diseases? A retrospective analysis","authors":"Lubov Stroh , Dennis Nurjadi , Florian Uhle , Thomas Bruckner , Armin Kalenka , Markus Alexander Weigand , Mascha Onida Fiedler-Kalenka","doi":"10.1016/j.medin.2024.04.002","DOIUrl":"10.1016/j.medin.2024.04.002","url":null,"abstract":"<div><h3>Objective</h3><div>Oxygen has been used liberally in ICUs for a long time to prevent hypoxia in ICU- patients. Current evidence suggests that paO<sub>2</sub> >300 mmHg should be avoided, it remains uncertain whether an “optimal level” exists. We investigated how “mild” hyperoxia influences diseases and in-hospital mortality.</div></div><div><h3>Design</h3><div>This is a retrospective study.</div></div><div><h3>Setting</h3><div>112 mechanically ventilated ICU-patients were enrolled.</div></div><div><h3>Patients or participants</h3><div>112 ventilated patients were included and categorized into two groups based on the median paO<sub>2</sub> values measured in initial 24 h of mechanical ventilation: normoxia group (paO<sub>2</sub> ≤ 100 mmHg, n = 43) and hyperoxia group patients (paO<sub>2</sub> > 100 mmHg, n = 69).</div></div><div><h3>Interventions</h3><div>No interventions were performed.</div></div><div><h3>Main variables of interest</h3><div>The primary outcome was the incidence of pulmonary events, the secondary outcomes included the incidence of other new organ dysfunctions and in-hospital mortality.</div></div><div><h3>Results</h3><div>The baseline characteristics, such as age, body mass index, lactate levels, and severity of disease scores, were similar in both groups. There were no statistically significant differences in the incidence of pulmonary events, infections, and new organ dysfunctions between the groups. 27 out of 69 patients (39.1%) in the “mild” hyperoxia group and 12 out of 43 patients (27.9%) in the normoxia group died during their ICU or hospital stay (p = 0.54). The mean APACHE Score was 29.4 (SD 7.9) in the normoxia group and 30.0 (SD 6.7) in the hyperoxia group (p = 0.62).</div></div><div><h3>Conclusions</h3><div>We found no differences in pulmonary events, other coded diseases, and in-hospital mortality between both groups. It remains still unclear what the \"best oxygen regime\" is for intensive care patients.</div></div>","PeriodicalId":49268,"journal":{"name":"Medicina Intensiva","volume":"48 10","pages":"Pages 575-583"},"PeriodicalIF":2.7,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142322060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A random forest classification model was calculated using the local and MIMIC III databases. The sensitivity of the model of our database, considering all the variables classified as important by the random forest, was 95.45%, the specificity was 100%, the accuracy was 96.77%, and an AUC of 95%. . In the case of the model based on the MIMIC III database, the sensitivity was 97.55%, the specificity was 100%, and the precision was 98.28%, with an AUC of 97.3%.
Conclusions
According to random forest classification in both databases, lactate levels, urine output and variables related to acid.base equilibrium were the most important variable in mortality due to sepsis in the ICU. The potassium levels were more critical in the MIMIC III database than the local database.
西班牙穆尔西亚三家医院的重症监护病房（ICU）和 MIMIC III 开放式数据库中的患者。主要关注变量年龄、体重、心率、呼吸频率、体温、乳酸水平、氧饱和度、收缩压和舒张压、pH值、尿液和血钾水平。结果利用本地数据库和MIMIC III数据库计算出随机森林分类模型。考虑到所有被随机森林分类为重要的变量，我们数据库的模型灵敏度为 95.45%，特异度为 100%，准确度为 96.77%，AUC 为 95%。.结论根据两个数据库的随机森林分类，乳酸水平、尿量和酸碱平衡相关变量是影响重症监护室败血症死亡率的最重要变量。与本地数据库相比，MIMIC III 数据库中的钾水平更为重要。
{"title":"Sepsis mortality prediction with Machine Learning Tecniques","authors":"Javier Carrillo Pérez-Tome , Tesifón Parrón-Carreño , Ana Belen Castaño-Fernández , Bruno José Nievas-Soriano , Gracia Castro-Luna","doi":"10.1016/j.medin.2024.04.010","DOIUrl":"10.1016/j.medin.2024.04.010","url":null,"abstract":"<div><h3>Objective</h3><div>To develop a sepsis death classification model based on machine learning techniques for patients admitted to the Intensive Care Unit (ICU).</div></div><div><h3>Design</h3><div>Cross-sectional descriptive study.</div></div><div><h3>Setting</h3><div>The Intensive Care Units (ICUs) of three Hospitals from Murcia (Spain) and patients from the MIMIC III open-access database.</div></div><div><h3>Patients</h3><div>180 patients diagnosed with sepsis in the ICUs of three hospitals and a total of 4559 patients from the MIMIC III database.</div></div><div><h3>Main variables of interest</h3><div>Age, weight, heart rate, respiratory rate, temperature, lactate levels, partial oxygen saturation, systolic and diastolic blood pressure, pH, urine, and potassium levels.</div></div><div><h3>Results</h3><div>A random forest classification model was calculated using the local and MIMIC III databases. The sensitivity of the model of our database, considering all the variables classified as important by the random forest, was 95.45%, the specificity was 100%, the accuracy was 96.77%, and an AUC of 95%. . In the case of the model based on the MIMIC III database, the sensitivity was 97.55%, the specificity was 100%, and the precision was 98.28%, with an AUC of 97.3%.</div></div><div><h3>Conclusions</h3><div>According to random forest classification in both databases, lactate levels, urine output and variables related to acid.base equilibrium were the most important variable in mortality due to sepsis in the ICU. The potassium levels were more critical in the MIMIC III database than the local database.</div></div>","PeriodicalId":49268,"journal":{"name":"Medicina Intensiva","volume":"48 10","pages":"Pages 584-593"},"PeriodicalIF":2.7,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142322285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号