Artificial Intelligence-Based Models for Prediction of Mortality in ICU Patients: A Scoping Review.

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.

Are individual analyses of multiple short urine collections throughout the 24 hours superior to a standard 24-hour urine collection in precipitation risk assessment of healthy subjects?

PURPOSE: The commonly used 24-hour collection technique has been the mainstay of diagnosis for supersaturation but has some certain limitations. Hence, superiority of multiple short urine collections as a new alternative in precipitation risk assessment was assessed compared to the standard 24-hour urine collection among healthy subjects. MATERIALS AND METHODS: Individual urine samples of 26 healthy subjects were acquired every 2 to 3 hours throughout the 24 hours. Urine samples were obtained and the time and volume of each sample were recorded. Urinary constituents involved in precipitation including, sodium-potassium, chloride, calcium, phosphate, citrate, magnesium, urea, creatinine and pH were measured. A simulated 24-hour collection was recalculated by the totalling of all shorter urine collections volume and urinary constituents excretions throughout the day. RESULTS: Urine pH, urine creatinine and precipitation rate had a significantly lower values in 24-hours urine collection compared to one individual value of multiple urine collections by -0.769 (P < .0001), -7.305 (P < .0001), and - 12.838 (P < .0001), respectively. However, calcium (2.697, P < .0001), citrate (3.54, P < .0001), total phosphate (19.961, P < .0001) and total creatinine (9.579, P < .0001) had statistically significantly higher values in the 24-hours urine collection compared to individual value of multiple urine collections. CONCLUSION: Based on the results, individual analysis of multiple shorter urine collections throughout the day improves the ability of identifying supersaturation points, precipitation risk zones and may potentially improve risk assessment compared to the 24-hour urine collection method.

Anticoagulation therapy in COVID-19 patients with chronic kidney disease.

Coagulopathy and derangements in the coagulation parameters are significant features of COVID-19 infection, which increases the risk of disseminated intravascular coagulation, thrombosis, and hemorrhage in these patients, resulting in increased morbidity and mortality. In times of COVID-19, special consideration should be given to patients with concurrent chronic kidney disease (CKD) and COVID-19 (CKD/COVID-19 patients) as renal dysfunction increases their risk of thrombosis and hemorrhage, and falsely affects some of the coagulation factors, which are currently utilized to assess thrombosis risk in patients with COVID-19. Hence, we believe extra attention should be given to determining the risk of thrombosis and bleeding and optimizing the timing and dosage of anticoagulant therapy in this unique population of patients. CKD/COVID-19 patients are considered a high-risk population for thrombotic events and hemorrhage. Furthermore, effects of renal function on paraclinical and clinical data should be considered during the evaluation and interpretation of thrombosis risk stratification. Individualized evaluation of clinical status and kidney function is necessary to determine the best approach and management for anticoagulant therapy, whereas there is a lack of studies about the population of CKD/COVID-19 patients who need anticoagulant therapy now.

Impact of Prolonged Fasting on the Risk of Calcium Phosphate Precipitation in the Urine: Calcium Phosphate Lithogenesis during Prolonged Fasting in a Healthy Cohort.

PURPOSE: Intermittent fasting and curtailing water intake for extended periods were likely common in Paleolithic times. Today it occurs for religious and dietary reasons. This restriction in intake should cause a decrease in the urine flow rate while raising the concentration of certain substances in urine to the point of precipitation. In this study we measured the risk of CaHPO4 precipitation following 18 hours of food and water deprivation. MATERIALS AND METHODS: Urine samples were periodically collected from 15 healthy subjects who fasted and abstained from drinking any liquid for 18 hours. The urine constituents Ca2+, HPO42- and pH involved in CaHPO4 formation were measured at various times throughout the fasting day. A comparison was made with control data, which consisted of diurnal urine collections taken throughout a separate nonfasting day prior to the fasting day. RESULTS: The mean ± SEM urine flow rate decreased significantly from 0.93 ± 0.1 ml per minute in the control group to 0.37 ± 0.05 ml per minute in the fasting group (p <0.05). Mean Na+ and Ca2+ excretion rates decreased significantly from 127 ± 12 to 54 ± 13 µmol per minute and from 3.2 ± 0.4 to 0.80 ± 0.21, respectively. Mean urinary Na+ and Ca2+ concentrations also decreased from 161 ± 11.6 to 122 ± 16.0 mmol/l and from 3.7 ± 0.5 to 2.0 ± 0.55, respectively. Urinary pH and the concentration of phosphate, citrate and magnesium were not significantly affected. CONCLUSIONS: Although the steady decrease in the urine flow rate was statistically significant during 18 hours of food and water deprivation, there was no evidence that the calculated risk of CaHPO4 precipitation in the healthy subjects had increased.

Conceptual Approach to Body Fluids and Edema, Education Determines Clinical Outcomes in Heart Failure.

In this brief communication, we reemphasize the importance of critical thinking in clinical practice using the example of edema. The common practice of thinking and inquiry by practicing clinicians has beneficial implications for healthcare by improving outcomes and patient care while alleviating the burden of misconceptions in practice. We provide an in-depth and interactive investigation of physiological concepts as a foundation for understanding body fluid dynamics. Finally, we offer a new classification of symptoms of heart failure. DOI: 10.52547/ijkd.8171.

Perioperative Hypertension Etiologies in Patients Undergoing Noncardiac Surgery in University Health Network Hospitals-Canada from 2015-2020.

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.

Conceptual Approach to Body Fluids and Edema, Education Determines Clinical Outcomes in Nephrotic Syndrome Management.

The objective of our paper is to reemphasize the importance of critical thinking in clinical practice and education in the field of internal medicine using the example of edema. We provide an in-depth and interactive investigation of physiological concepts as a foundation for the understanding of body fluid dynamics. Four fundamental concepts described are the hydrostatic and oncotic pressure gradients, capillary permeability, and lymphatic drainage. Furthermore, we visit the causes of edema in nephrotic syndrome. Traditional teaching considers hypoalbuminemia as a primary cause of edema formation in nephrotic syndrome. It has been proven that other etiologies causing edema include salt and water retention by the kidneys and a possible increase in capillary permeability are more important causes in the development of edema in nephrotic syndrome.

The Impact of Hemodialysis Frequency and Duration on Blood Pressure Management and Quality of Life in End-Stage Renal Disease Patients.

Cardiovascular complications are the most prominent causes of morbidity and mortality among chronic kidney disease (CKD) and end-stage renal disease (ESRD) patients undergoing standard hemodialysis (HD) therapy. Cardiovascular disease risk is increased significantly through persistent hypertension and blood pressure (BP) fluctuation, which are the most common complications of CKD. It was hypothesized that an extended approach with lengthier and more frequent dialysis sessions, referred to in this paper as "extended hemodialysis" (EHD), can potentially lower and stabilize blood pressure, and consequently reduce the rate of morbidity and mortality. A greater reduction of volume (salt and water) with higher frequency can improve patient quality of life (QOL). Eleven papers, including clinical trials and systematic reviews were chosen and analyzed. The extracted data was used to evaluate the change in blood pressure levels between standard HD and EHD. Overall, the studies showed that EHD resulted in improved blood pressure management; therefore, we concluded that there will be a decrease in cardiovascular disease risk, stroke, and morbidity and mortality rate. There will be also an improvement in patient QOL due to beneficial effects of the EHD.