Background: Interest in critical care–related artificial intelligence (AI) research is growing rapidly. However, the literature is still lacking in comprehensive bibliometric studies that measure and analyze scientific publications globally. Objective: The objective of this study was to assess the global research trends in AI in intensive care medicine based on publication outputs, citations, coauthorships between nations, and co-occurrences of author keywords. Methods: A total of 3619 documents published until March 2022 were retrieved from the Scopus database. After selecting the document type as articles, the titles and abstracts were checked for eligibility. In the final bibliometric study using VOSviewer, 1198 papers were included. The growth rate of publications, preferred journals, leading research countries, international collaborations, and top institutions were computed. Results: The number of publications increased steeply between 2018 and 2022, accounting for 72.53% (869/1198) of all the included papers. The United States and China contributed to approximately 55.17% (661/1198) of the total publications. Of the 15 most productive institutions, 9 were among the top 100 universities worldwide. Detecting clinical deterioration, monitoring, predicting disease progression, mortality, prognosis, and classifying disease phenotypes or subtypes were some of the research hot spots for AI in patients who are critically ill. Neural networks, decision support systems, machine learning, and deep learning were all commonly used AI technologies. Conclusions: This study highlights popular areas in AI research aimed at improving health care in intensive care units, offers a comprehensive look at the research trend in AI application in the intensive care unit, and provides an insight into potential collaboration and prospects for future research. The 30 articles that received the most citations were listed in detail. For AI-based clinical research to be sufficiently convincing for routine critical care practice, collaborative research efforts are needed to increase the maturity and robustness of AI-driven models.

Background: Early identification and timely management of septic AKI continue to represent clinical challenges for intensive care. The aim was to evaluate the effect of renal replacement with oXiris filter on clinical outcomes in septic AKI. Methods: This was a single-center randomized controlled trial that enrolled surgical septic shock with AKI patients admitted in the ICU, Renji Hospital, Shanghai Jiao Tong University, School of Medicine from Jan 1, 2021 to Sep 30, 2021, were screened. Results: Sixteen subjects that met the inclusion and exclusion criteria were randomized into CRRT with AN69-oXiris group ( n = 8) and AN69-ST group ( n = 8). The PCT and IL-6 concentration decreased significantly after the first treatment compared to pre-CRRT levels in the oXiris group (PCT: 23.46 [4.18, 84.90] vs 52.79 [9.03, 100.00] µg/L, p = 0.046; IL-6: 3080.15 [527.62, 9806.61] vs 10,457.17 [8150.00, 15,528.87] pg/mL, p = 0.043). The levels of lactate decreased by 1.70 [1.03, 2.83] mmol/L after the first CRRT in the oXiris group ( p = 0.028). The norepinephrine infusion rate was decreased by 0.06 [0, 0.09], 0.05 [0, 0.23] and 0.11 [0, 0.23] μg/kg/min at 4, 6, and 8 h in the oXiris group compared to the ST group ( p = 0.005, 0.038, and 0.017). Conclusion: Using the oXiris filter may improve hemodynamic status during initial CRRT in severe surgical septic shock with AKI. Further large multicenter RCTs are needed to determine the effect of the oXiris filter on patient outcomes. ( http://www.chictr.org.cn/index.aspx (ChiCTR2200055732)).

Extracorporeal blood purification is a technique for reducing elevated levels of inflammatory mediators and/or endotoxins in critically ill patients with sepsis or other hyperinflammatory conditions. The oXiris filter combines endotoxin adsorption, cytokine adsorption, hemofiltration, and anti-thrombosis, and an emerging body of evidence demonstrates its use in critical care patients with hyperinflammatory conditions and acute kidney injury (AKI). A group of Asia-Pacific experts convened to formulate consensus statements for the use of the oXiris filter based on a comprehensive review of publications. After evaluation using a Delphi methodology, 17 statements achieved consensus (three recommendations and 14 practice points). These offer guidance on the initiation, monitoring, and evaluation of treatment with the oXiris filter in patients with sepsis, septic shock, severe COVID-19, or other hyperinflammatory states. We also recommend using the oXiris filter in patients undergoing cardiopulmonary bypass for cardiac surgery who are at risk for developing AKI. Other statements discuss modality, dosage, filter lifespan, anticoagulation, and combining the oXiris filter set with other extracorporeal therapies. Taken together, our statements offer targeted guidance for clinicians on the use of the oXiris filter across different patient populations. Additionally, we highlight the limitations of the current evidence base and identify key areas requiring further research.

Background: This study was designed to explore the early predictive value of the respiratory rate oxygenation (ROX) index modified by PaO₂ (mROX) in high-flow nasal cannula (HFNC) therapy in patients with acute hypoxemia respiratory failure (AHRF). Method: Seventy-five patients with AHRF treated with HFNC were retrospectively reviewed. Respiratory parameters at baseline and 2 h after HFNC initiation were analyzed. The predictive value of the ROX (ratio of pulse oximetry/FIO₂ to respiratory rate) and mROX (ratio of arterial oxygen /FIO₂ to respiratory rate) indices with two variations by adding heart rate to each index (ROX-HR and mROX-HR) was evaluated. Results: HFNC therapy failed in 24 patients, who had significantly higher intensive care unit (ICU) mortality and longer ICU stay. Both the ROX and mROX indices at 2 h after HFNC initiation can predict the risk of intubation after HFNC. Two hours after HFNC initiation, the mROX index had a higher area under the receiver operating characteristic curve (AUROC) for predicting HFNC success than the ROX index. Besides, baseline mROX index of greater than 7.1 showed a specificity of 100% for HFNC success. Conclusion: The mROX index may be a suitable predictor of HFNC therapy outcomes at the early phase in patients with AHRF.

Current paradigms of detecting acute kidney injury (AKI) are insensitive and non-specific. Klotho is a pleiotropic protein that is predominantly expressed in renal tubules. In this study, we evaluated the diagnostic and prognostic roles of urine Klotho for AKI following cardiac surgery. We conducted a prospective study involving 91 patients undergoing cardiac surgery. AKI was defined according to the AKIN definition. The renal outcomes within 7 days after operation were evaluated. Perioperative levels of urine Klotho and urine neutrophil gelatinase-associated lipocalin (NGAL) were measured by using ELISA. Of 91 participants, 33 patients (36.26%) developed AKI. Of these AKI patients, 21 (63.64%), 8 (24.24%), and 4 (12.12%) were staged 1, 2, and 3, respectively. Serum creatinine in AKI patients began to slightly increase at first postoperative time and reached the AKI diagnostic value 1 day after operation. Postoperative urine Klotho peaked at the first postoperative time (0 h after admission to the intensive care unit (ICU)) in patients with AKI, and was higher than that in non-AKI patients up to day 3. The AUC of detecting AKI for urine Klotho was higher than urine NGAL at the first postoperative time and 4 h after admission to the ICU. In a multivariate model, increased first postoperative urine Klotho may be an independent predictor for AKI occurrence following cardiac surgery. The concentrations of first postoperative urine Klotho were higher in AKI stage 2 and 3 than those in stage 1 (p < 0.05), and were higher in patients with incomplete recovery of renal function than those with complete recovery (p < 0.05). Urine Klotho may serve as an early biomarker for AKI and subsequent poor short-term renal outcome in patients undergoing cardiac surgery.

Purpose: It is not clear whether patient who is dialyzing with a well-functioning vascular access may appear venous stenosis. The aim is to see the prevalence of central or other vein stenoses/occlusions in patients with asymptomatic, normal functioning fistulas. Methods: A total of 54 patients met the inclusion criteria. We performed angiography examinations for these patients and reviewed venography of the superficial and deep venous systems. Results: Among these patients, 21 (39%) were detected positive cases by the angiography, the remainder was negative cases. Thirteen of 54 (24%) had mild central venous stenosis (stenosis 0.05). Conclusion: The frequency of venous lesion is not low in hemodialysis patients with a well-functioning AVF. To value the impact of these abnormalities on access, prognosis needs longer time follow-up.