RESUMO
BACKGROUND AND OBJECTIVE: Healthcare professionals may be able to anticipate more accurately a patient's timing of death and assess their possibility of recovery by implementing a real-time clinical decision support system. Using such a tool, the healthcare system can better understand a patient's condition and make more informed judgements about distributing limited resources. This scoping review aimed to analyze various death prediction AI (Artificial Intelligence) algorithms that have been used in ICU (Intensive Care Unit) patient populations. METHODS: The search strategy of this study involved keyword combinations of outcome and patient setting such as mortality, survival, ICU, terminal care. These terms were used to perform database searches in MEDLINE, Embase, and PubMed up to July 2022. The variables, characteristics, and performance of the identified predictive models were summarized. The accuracy of the models was compared using their Area Under the Curve (AUC) values. RESULTS: Databases search yielded an initial pool of 8271 articles. A two-step screening process was then applied: first, titles and abstracts were reviewed for relevance, reducing the pool to 429 articles. Next, a full-text review was conducted, further narrowing down the selection to 400 key studies. Out of 400 studies on different tools or models for prediction of mortality in ICUs, 16 papers focused on AI-based models which were ultimately included in this study that have deployed different AI-based and machine learning models to make a prediction about negative patient outcome. The accuracy and performance of the different models varied depending on the patient populations and medical conditions. It was found that AI models compared with traditional tools like SAP3 or APACHE IV score were more accurate in death prediction, with some models achieving an AUC of up to 92.9%. The overall mortality rate ranged from 5% to more than 60% in different studies. CONCLUSION: We found that AI-based models exhibit varying performance across different patient populations. To enhance the accuracy of mortality prediction, we recommend customizing models for specific patient groups and medical contexts. By doing so, healthcare professionals may more effectively assess mortality risk and tailor treatments accordingly. Additionally, incorporating additional variables-such as genetic information-into new models can further improve their accuracy.
RESUMO
Introduction: Perioperative hypertension, defined as increased blood pressure around the surgery, is a known risk factor for perioperative complications, including cardiovascular events. Identifying reasons associated with hypertension in each period is of great help in preventing and better managing perioperative hypertension. Objective: The aim of the study was to explore common etiologies of hypertension during the perioperative period (pre, intra, and post-operation) in patients who underwent noncardiac surgeries in University Health Network (UHN) hospitals, Canada, from 2015 to 2020. Patients and Methods: We retrospectively analyzed the medical records of 174 patients undergoing noncardiac surgeries who experienced perioperative hypertension. We assessed the prevalence of 10 reasons for perioperative hypertension as a whole and also each period separately according to the physicians' notes in patients' medical records. Two-way measurements ANOVA was used to determine the change of mean hypertension among patients for specific etiology. Results: The common etiologies of perioperative hypertension were poorly controlled hypertension (21.8%), excessive fluid therapy (19.5%), excessive vasopressor (18.4%), and medication withdrawal (13.7%). Regarding each period separately, the most common reasons were poorly controlled hypertension for pre (42.9%) and intraoperative period (22.7%) and fluid overload for the postoperative period (20.1%). Poor control of hypertension showed both within-subject statistical significance for systolic and between-subject statistical significance for diastolic blood pressure. Conclusion: Poorly controlled hypertension is the most significant etiology of perioperative hypertension in patients undergoing noncardiac surgeries. Apart from poorly controlled hypertension, as a patient-related factor, iatrogenic factors such as excessive vasopressor therapy, aggressive fluid replacement and poor management of antihypertensive medications can also cause perioperative hypertension.
RESUMO
BACKGROUND: The coronavirus disease 2019 (COVID-19) presents various phenotypes from asymptomatic involvement to death. Disseminated intravascular coagulopathy (DIC) is among the poor prognostic complications frequently observed in critical illness. To improve mortality, a timely diagnosis of DIC is essential. The International Society on Thrombosis and Hemostasis (ISTH) introduced a scoring system to detect overt DIC (score ≥5) and another category called sepsis-induced coagulopathy (SIC) to identify the initial stages of DIC (score ≥4). This study aimed to determine whether clinicians used these scoring systems while assessing COVID-19 patients and the role of relevant biomarkers in disease severity and outcome. MATERIALS AND METHODS: An exhaustive search was performed according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses, using Medline, Embase, Cochrane, CINAHL, and PubMed until August 2020. Studies considering disease severity or outcome with at least two relevant biomarkers were included. For all studies, the definite, maximum, and minimum ISTH/SIC scores were calculated. RESULTS: A total of 37 papers and 12,463 cases were reviewed. Studies considering ISTH/SIC criteria to detect DIC suggested a higher rate of ISTH ≥5 and SIC ≥4 in severe cases and nonsurvivors compared with nonsevere cases and survivors. The calculated ISTH scores were dominantly higher in severe infections and nonsurvivors. Elevated D-dimer was the most consistent abnormality on admission. CONCLUSION: Higher ISTH and SIC scores positively correlate with disease severity and death. In addition, more patients with severe disease and nonsurvivors met the ISTH and SIC scores for DIC. Given the high prevalence of coagulopathy in COVID-19 infection, dynamic monitoring of relevant biomarkers in the form of ISTH and SIC scoring systems is of great importance to timely detect DIC in suspicious patients.