Kashani, Kianoush

ABSTRACT Adsorption-based extracorporeal therapies have been subject to technical developments and clinical application for close to five decades. More recently, new technological developments in membrane and sorbent manipulation have made it possible to deliver more biocompatible extracorporeal adsorption therapies to patients with a variety of conditions. There are several key rationales based on physicochemical principles and clinical considerations that justify the application and investigation of such therapies as evidenced by multiple ex vivo, experimental and clinical observations. Accordingly, unspecific adsorptive extracorporeal therapies have now been applied to the treatment of a wide array of conditions from poisoning to drug overdoses, to inflammatory states and sepsis, and acute or chronic liver and kidney failure. In response to the rapidly expanding knowledge base and increased clinical evidence, we convened an Acute Disease Quality Initiative consensus conference dedicated to such treatment. The data show that hemoadsorption has clinically acceptable short-term biocompatibility and safety, technical feasibility and experimental demonstration of specified target molecule removal. Pilot studies demonstrate potentially beneficial effects on physiology and larger studies of endotoxin-based hemoadsorption have identified possible target phenotypes for larger randomized controlled trials. Moreover, in a variety of endogenous and exogenous intoxications, removal of target molecules has been confirmed in vivo. However, some studies have raised concerns about harm, or failed to deliver benefits. Thus, despite many achievements, modern hemoadsorption remains a novel and experimental intervention with limited data, and a large research agenda.

*Nature Reviews Nephrology* welcomes you to this webinar, in which our two speakers — Leo Celi and Kianoush Kashani — will present on the theme of Digital Determinants of Health, with a focus on artificial intelligence (AI) and the need for equity-focused innovation. The webinar will be held on 14th of March 2024 — World Kidney Day — which this year focuses on “Advancing equitable access to care and optimal medication practice”. In their [Comment](https://www.nature.com/articles/s41581-023-00763-4.epdf?sharing_token=ihZn7Tzp1ixBfK7a3X_6x9RgN0jAjWel9jnR3ZoTv0NaWQBzIFRPdPKT7AS3IVVHez49nwrLVjZJyLsCUt5034qu70IjW6yS7U3gUuTEQjm0O_u1j1PiMZLzRs7qKAyY_28RvtE3kXcXmwKeyufyUyKP715Wx73c6p6Bfp6w6Sg%3D) “Digital determinants of health: opportunities and risks amidst health inequities”, Leo Celi and colleagues argue that given the current digital revolution, digital tools and AI applications in health care must be developed with equity at the forefront to avoid perpetuating historical biases and inequities. With their [Consensus Statement](https://www.nature.com/articles/s41581-023-00744-7) on “Digital health and acute kidney injury”, Kianoush Kashani and colleagues highlight some of the potential applications of digital health tools in nephrology, as well as the need for equitable digitization. Artificial Intelligence: The digital determinant of health to rule them all Artificial intelligence (AI) is poised to be the biggest digital determinant of health. From healthcare, to education, to law enforcement, AI can theoretically augment every human task that involves thinking. We will see every decision-making infiltrated by AI. This is why AI is different. Most technologies are much narrower in scope, and therefore, easier to regulate. In addition, the data that we use to build AI reflects everything about the systems we would like to disrupt, both good and bad. Behind the façade of AI lies our legacy systems with all their flaws. The biggest threat to AI delivering its promise stems from the risk of cementing the structural inequities that permeate every aspect of society. AI provides an opportunity to inch us closer to a better care delivery system, but it will require us to design an equity-focused sociotechnical ecosystem. Engineering AI in a vacuum that does not build capacity nor include cultural transformation of how we learn and how we work together will be a waste of time and money, and a huge opportunity cost. To avert the disaster from AI, we need to diversify those sitting at the table. We need to diversify those who are developing and deploying AI. Digital health in acute kidney injury management Acute kidney injury (AKI) is a highly prevalent clinical syndrome that substantially impacts patient outcomes. It is accepted by the clinical communities that the management of AKI is time sensitive. Unfortunately, despite growing proof of its preventability, AKI management remains suboptimal in community, acute care, and post-acute care settings. Digital health solutions comprise various tools and models to improve care processes and patient outcomes in multiple medical fields. AKI development, progression, recovery, or lack thereof, offers tremendous opportunities for developing, validating, and implementing digital health solutions in multiple settings.

The accurate interpretation of CRRT machine alarms is crucial in the intensive care setting. ChatGPT, with its advanced natural language processing capabilities, has emerged as a tool that is evolving and advancing in its ability to assist with healthcare information. This study is designed to evaluate the accuracy of the ChatGPT-3.5 and ChatGPT-4 models in addressing queries related to CRRT alarm troubleshooting. This study consisted of two rounds of ChatGPT-3.5 and ChatGPT-4 responses to address 50 CRRT machine alarm questions that were carefully selected by two nephrologists in intensive care. Accuracy was determined by comparing the model responses to predetermined answer keys provided by critical care nephrologists, and consistency was determined by comparing outcomes across the two rounds. The accuracy rate of ChatGPT-3.5 was 86% and 84%, while the accuracy rate of ChatGPT-4 was 90% and 94% in the first and second rounds, respectively. The agreement between the first and second rounds of ChatGPT-3.5 was 84% with a Kappa statistic of 0.78, while the agreement of ChatGPT-4 was 92% with a Kappa statistic of 0.88. Although ChatGPT-4 tended to provide more accurate and consistent responses than ChatGPT-3.5, there was no statistically significant difference between the accuracy and agreement rate between ChatGPT-3.5 and -4. ChatGPT-4 had higher accuracy and consistency but did not achieve statistical significance. While these findings are encouraging, there is still potential for further development to achieve even greater reliability. This advancement is essential for ensuring the highest-quality patient care and safety standards in managing CRRT machine-related issues.

OBJECTIVES: Among patients with severe acute kidney injury (AKI) admitted to the ICU in high-income countries, regional practice variations for fluid balance (FB) management, timing, and choice of renal replacement therapy (RRT) modality may be significant. DESIGN: Secondary post hoc analysis of the STandard vs. Accelerated initiation of Renal Replacement Therapy in Acute Kidney Injury (STARRT-AKI) trial (ClinicalTrials.gov number NCT02568722). SETTING: One hundred-fifty-three ICUs in 13 countries. PATIENTS: Altogether 2693 critically ill patients with AKI, of whom 994 were North American, 1143 European, and 556 from Australia and New Zealand (ANZ). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Total mean FB to a maximum of 14 days was +7199 mL in North America, +5641 mL in Europe, and +2211 mL in ANZ (p < 0.001). The median time to RRT initiation among patients allocated to the standard strategy was longest in Europe compared with North America and ANZ (p < 0.001; p < 0.001). Continuous RRT was the initial RRT modality in 60.8% of patients in North America and 56.8% of patients in Europe, compared with 96.4% of patients in ANZ (p < 0.001). After adjustment for predefined baseline characteristics, compared with North American and European patients, those in ANZ were more likely to survive to ICU (p < 0.001) and hospital discharge (p < 0.001) and to 90 days (for ANZ vs. Europe: risk difference [RD], –11.3%; 95% CI, –17.7% to –4.8%; p < 0.001 and for ANZ vs. North America: RD, –10.3%; 95% CI, –17.5% to –3.1%; p = 0.007). CONCLUSIONS: Among STARRT-AKI trial centers, significant regional practice variation exists regarding FB, timing of initiation of RRT, and initial use of continuous RRT. After adjustment, such practice variation was associated with lower ICU and hospital stay and 90-day mortality among ANZ patients compared with other regions.

OBJECTIVES: Conduct a systematic review and meta-analysis to assess prevalence and timing of acute kidney injury (AKI) development after acute respiratory distress syndrome (ARDS) and its association with mortality. DATA SOURCES: Ovid MEDLINE(R), Ovid Embase, Ovid Cochrane Central Register of Controlled Trials, Ovid Cochrane Database of Systematic Reviews, Ovid PsycINFO database, Scopus, and Web of Science thought April 2023. STUDY SELECTION: Titles and abstracts were screened independently and in duplicate to identify eligible studies. Randomized controlled trials and prospective or retrospective cohort studies reporting the development of AKI following ARDS were included. DATA EXTRACTION: Two reviewers independently extracted data using a pre piloted abstraction form. We used Review Manager 5.4 software (Cochrane Library, Oxford, United Kingdom) and Open Meta software (Brown University, Providence, RI) for statistical analyses. DATA SYNTHESIS: Among the 3646 studies identified and screened, 17 studies comprising 9359 ARDS patients met the eligibility criteria and were included in the meta-analysis. AKI developed in 3287 patients (40%) after the diagnosis of ARDS. The incidence of AKI at least 48 hours after ARDS diagnosis was 20% (95% CI, 0.18–0.21%). The pooled risk ratio (RR) for the hospital (or 30-d) mortality among ARDS patients who developed AKI was 1.93 (95% CI, 1.71–2.18). AKI development after ARDS was identified as an independent risk factor for mortality in ARDS patients, with a pooled odds ratio from multivariable analysis of 3.69 (95% CI, 2.24–6.09). Furthermore, two studies comparing mortality between patients with late vs. early AKI initiation after ARDS revealed higher mortality in late AKI patients with RR of 1.46 (95% CI, 1.19–1.8). However, the certainty of evidence for most outcomes was low to very low. CONCLUSIONS: While our findings highlight a significant association between ARDS and subsequent development of AKI, the low to very low certainty of evidence underscores the need for cautious interpretation. This systematic review identified a significant knowledge gap, necessitating further research to establish a more definitive understanding of this relationship and its clinical implications.

ABSTRACT Purpose: The aim of the study is to evaluate whether serial assessment of shock severity can improve prognostication in intensive care unit (ICU) patients. Materials and Methods: This is a retrospective cohort of 21,461 ICU patient admissions from 2014 to 2018. We assigned the Society for Cardiovascular Angiography and Interventions (SCAI) Shock Stage in each 4-h block during the first 24 h of ICU admission; shock was defined as SCAI Shock stage C, D, or E. In-hospital mortality was evaluated using logistic regression. Results: The admission SCAI Shock stages were as follows: A, 39.0%; B, 27.0%; C, 28.9%; D, 2.6%; and E, 2.5%. The SCAI Shock stage subsequently increased in 30.6%, and late-onset shock developed in 30.4%. In-hospital mortality was higher in patients who had shock on admission (11.9%) or late-onset shock (7.3%) versus no shock (4.3%). Persistence of shock predicted higher mortality (adjusted OR = 1.09; 95% CI = 1.06–1.13, for each ICU block with shock). The mean SCAI Shock stage had higher discrimination for in-hospital mortality than the admission or maximum SCAI Shock stage. Dynamic modeling of the SCAI Shock classification improved discrimination for in-hospital mortality (C-statistic = 0.64–0.71). Conclusions: Serial application of the SCAI Shock classification provides improved mortality risk stratification compared with a single assessment on admission, facilitating dynamic prognostication.

Introduction: Hyperkalemia has been associated with increased mortality in cardiac intensive care unit (CICU) patients. An artificial intelligence (AI) augmented electrocardiogram (ECG) can predict hyperkalemia, and other AI-ECG algorithms have predicted mortality in CICU patients. Hypothesis: We hypothesized that the AI-ECG hyperkalemia algorithm could stratify mortality risk beyond the serum potassium measurement. Methods: We included 11 234 unique Mayo Clinic CICU patients admitted from 2007 to 2018 who had both a 12 lead ECG and blood potassium (K) level obtained at admission with K>=5 mEq/L defining hyperkalemia. ECGs underwent AI evaluation for probability of hyperkalemia (probability >=0.5 defined as positive). Hospital mortality was analyzed using logistic regression and survival to one year was estimated using Kaplan-Meier and Cox analysis. Results: The mean age was 70 years, 37.8% were females, and 92.4% were white. Chronic kidney disease was present in 20%. The mean K value was 4.2 mEq/L, and 13% (n=1460) had hyperkalemia. AI-ECG predicted hyperkalemia in 34% (n=3820). In-hospital mortality was higher in patients with laboratory and/or AI-ECG hyperkalemia, and these patients had lower survival out to 1 year. Mortality was lowest in patients with normal K and negative AI-ECG and highest in patients with both laboratory-confirmed hyperkalemia and AI-ECG predicted hyperkalemia. Patients with isolated laboratory hyperkalemia (false-negative AI-ECG) had higher mortality than those with isolated AI-ECG hyperkalemia (false-positive AI-ECG). Conclusions: AI-ECG probability of hyperkalemia, even with a normal laboratory K, was associated with higher short-term and long-term mortality in CICU patients. The laboratory K value and AI-ECG probability of hyperkalemia are complementary risk factors. The AI algorithm can detect prognostically important ECG abnormalities which may reflect the effects of K levels on the myocardium.

Introduction: A single assessment of the SCAI shock classification robustly predicts mortality, and a repeat assessment may improve prognostication. Hypothesis: We hypothesized that frequent serial assignment of the SCAI shock stage could further improve risk stratification. Methods: Unique AHA Level 1 cardiac intensive care unit (CICU) admissions at a single center from 2015 to 2018 were reviewed retrospectively. Time-stamped electronic health record data were used to assign the SCAI shock stage in each 4-hour block during the first 24 hours of CICU admission. Shock was defined as SCAI shock stage C, D, or E. In-hospital mortality was evaluated using logistic regression. Results: Among 2,918 CICU patients, 1,537 (52.7%) met criteria for shock during >=1 block and 266 (9.1%) died in hospital. The SCAI shock stage on admission was: A, 37.6%; B, 31.5%; C, 25.9%; D, 1.8%; E, 3.3%. Patients with worsening SCAI shock stage after admission (first 4 hours) were at higher risk of mortality ( Figure A ), as were patients who met SCAI criteria for shock (particularly those with shock on admission, Figure B ). The pattern was consistent in patients with acute coronary syndromes, heart failure, or cardiac arrest (who had very high mortality). Each higher admission (aOR 1.36, 95% CI 1.18-1.56, AUC 0.70), maximum (aOR 1.59, 95% CI 1.37-1.85, AUC 0.73) and 24 hour mean (aOR 2.42, 95% CI 1.99-2.95, AUC 0.78) SCAI shock stage were incrementally associated with increasing in-hospital mortality. Discrimination was highest for the mean SCAI shock stage (p <0.05). Each additional 4 hour block meeting SCAI criteria for shock was associated with higher mortality (aOR 1.15, 95% CI 1.07-1.24). Conclusions: Dynamic assessment of shock using serial SCAI shock classification assignment can improve mortality risk stratification in CICU patients. Cumulative time in shock was a strong mortality risk indicator, highlighting the area under the curve of shock severity as an important determinant of outcomes.

Introduction: An elevated shock index (SI) predicts worse outcomes in multiple clinical arenas. We aimed to determine whether the SI can aid in mortality risk stratification in unselected CICU patients. Methods: We included admissions to the Mayo Clinic from 2007 to 2015 and stratified them based on admission SI, defined as heart rate divided by systolic blood pressure. The primary outcome was in-hospital mortality, and predictors of in-hospital mortality were analyzed using multivariable logistic regression. Results: We included 9,939 unique CICU patients with available data for SI. The mean age was 69 years old (37% female). Median HR, SBP, and shock index for our cohort were 79 beats per minute (BPM), 121 mmHg, and 0.65 BPM/mmHg, respectively. Patients were grouped by SI as follows: < 0.6, 3,973 (40%); 0.6-0.99, 4,810 (48%); and ≥ 1.0, 1,156 (12%). After multivariable adjustment, both HR (adjusted OR 1.06 per 10 BPM higher; CI 1.02-1.10; p-value 0.005) and SBP (adjusted OR 0.94 per 10 mmHg higher; CI 0.90-0.97; p-value < 0.001) remained associated with higher in-hospital mortality. As SI increased there was an incremental increase in in-hospital mortality (adjusted OR 1.07 per 0.1 BPM/mmHg higher, CI 1.04-1.10, p-Value < 0.001). A higher SI was associated with increased mortality across all examined admission diagnoses, including acute coronary syndromes, heart failure, and cardiogenic shock. Conclusions: The SI is a simple and universally available bedside marker that can be used at the time of admission to predict in-hospital mortality in CICU patients across a variety of cardiac conditions.