1
|
Liu L, Liu D, He T, Liang B, Zhao J. Coagulation Risk Predicting in Anticoagulant-Free Continuous Renal Replacement Therapy. Blood Purif 2024:1-12. [PMID: 39134011 DOI: 10.1159/000540695] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Accepted: 07/31/2024] [Indexed: 09/05/2024]
Abstract
INTRODUCTION Continuous renal replacement therapy (CRRT) is a prolonged continuous extracorporeal blood purification therapy to replace impaired renal function. Typically, CRRT therapy requires routine anticoagulation, but for patients at risk of bleeding and with contraindications to sodium citrate, anticoagulant-free dialysis therapy is necessary. However, this approach increases the risk of CRRT circuit coagulation, leading to treatment interruption and increased resource consumption. In this study, we utilized artificial intelligence machine learning methods to predict the risk of CRRT circuit coagulation based on pre-CRRT treatment metrics. METHODS We retrospectively analyzed 212 patients who underwent anticoagulant-free CRRT from October 2022 to October 2023. Patients were categorized into high-risk and low-risk groups based on CRRT circuit coagulation within 24 h. We employed eight machine learning methods to predict the risk of circuit coagulation. The performance of the model was evaluated using the area under the curve (AUC) of the receiver operating characteristic. 5-fold cross-validation was used to validate the machine learning models. Feature importance and SHAP plots were used to interpret the model's performance and key drivers. RESULTS We identified 88 patients (41.51%) at high risk of circuit coagulation within 24 h of CRRT. Our machine learning models showed excellent predictive performance, with ensemble learning achieving an AUC of 0.863 (95% CI: 0.860-0.868), outperforming individual algorithms. Random forest was the best single-algorithm model, with an AUC of 0.819 (95% CI: 0.814-0.823). The top three features identified as most important by the SHAP summary plot and feature importance graph are platelet, filtration fraction (FF), and triglycerides. CONCLUSION We created a model using machine learning to predict the risk of circuit coagulation during anticoagulant-free CRRT therapy. Our model performs well (AUC 0.863) and identifies key factors like platelets, FF, and triglycerides. This facilitates the development of personalized treatment strategies by clinicians aimed at reducing circuit coagulation risk, thereby enhancing patient outcomes and reducing healthcare expenses.
Collapse
Affiliation(s)
- Liang Liu
- Department of Nephrology, The Key Laboratory for the Prevention and Treatment of Chronic Kidney Disease of Chongqing, Chongqing Clinical Research Center of Kidney and Urology Diseases, Xinqiao Hospital, Army Medical University (Third Military Medical University), Chongqing, China,
| | - Dashuang Liu
- Department of Nephrology, The Key Laboratory for the Prevention and Treatment of Chronic Kidney Disease of Chongqing, Chongqing Clinical Research Center of Kidney and Urology Diseases, Xinqiao Hospital, Army Medical University (Third Military Medical University), Chongqing, China
| | - Ting He
- Department of Nephrology, The Key Laboratory for the Prevention and Treatment of Chronic Kidney Disease of Chongqing, Chongqing Clinical Research Center of Kidney and Urology Diseases, Xinqiao Hospital, Army Medical University (Third Military Medical University), Chongqing, China
| | - Bo Liang
- Department of Nephrology, The Key Laboratory for the Prevention and Treatment of Chronic Kidney Disease of Chongqing, Chongqing Clinical Research Center of Kidney and Urology Diseases, Xinqiao Hospital, Army Medical University (Third Military Medical University), Chongqing, China
| | - Jinghong Zhao
- Department of Nephrology, The Key Laboratory for the Prevention and Treatment of Chronic Kidney Disease of Chongqing, Chongqing Clinical Research Center of Kidney and Urology Diseases, Xinqiao Hospital, Army Medical University (Third Military Medical University), Chongqing, China
| |
Collapse
|
2
|
Alexander EC, Saxena R, Singla R, Douiri A, Deep A. Prevalence, Associated Factors, and Outcomes of Severe Acute Kidney Injury in Pediatric Acute Liver Failure: Single-Center Retrospective Study, 2003-2017. Pediatr Crit Care Med 2024; 25:e358-e366. [PMID: 38847576 DOI: 10.1097/pcc.0000000000003547] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 08/06/2024]
Abstract
OBJECTIVES Our aim was to determine the prevalence and explanatory factors associated with outcomes in children with acute liver failure (ALF) admitted to the PICU, who also develop severe acute kidney injury (AKI). DESIGN Retrospective cohort, 2003 to 2017. SETTING Sixteen-bed PICU in a university-affiliated tertiary care hospital. PATIENTS Admissions to the PICU with ALF underwent data review of the first week and at least 90-day follow-up. Patients with stages 2-3 AKI using the British Association of pediatric Nephrology definitions, or receiving continuous renal replacement therapy (CRRT) for renal indications, were defined as severe AKI. We excluded ALF cases on CRRT for hepatic-only indications. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS Baseline characteristics, proportion with severe AKI, illness severity and interventions, and outcomes (i.e., transplant, survival with native liver, overall survival, duration of PICU stay, and mechanical ventilation). Ninety-four children with ALF admitted to the PICU were included. Over the first week, 29 had severe AKI, and another eight received CRRT for renal/mixed reno-hepatic indications; hence, the total severe AKI cohort was 37 of 94 (39.4%). In a multivariable logistic regression model, peak aspartate aminotransferase (AST) and requirement for inotropes on arrival were associated with severe AKI. Severe AKI was associated with longer PICU stay and duration of ventilation, and lower spontaneous survival with native liver. In another model, severe AKI was associated with greater odds of mortality (odds ratio 7.34 [95% CI, 1.90-28.28], p = 0.004). After 90 days, 3 of 17 survivors of severe AKI had serum creatinine greater than the upper limit of normal for age. CONCLUSIONS Many children with ALF in the PICU develop severe AKI. Severe AKI is associated with the timecourse of PICU admission and outcome, including survival with native liver. Future work should look at ALF goal directed renoprotective strategies at the time of presentation.
Collapse
Affiliation(s)
- Emma C Alexander
- Paediatric ICU, King's College Hospital NHS Foundation Trust, Denmark Hill, London, United Kingdom
| | - Romit Saxena
- Paediatric ICU, King's College Hospital NHS Foundation Trust, Denmark Hill, London, United Kingdom
| | - Raman Singla
- Paediatric ICU, King's College Hospital NHS Foundation Trust, Denmark Hill, London, United Kingdom
| | - Abdel Douiri
- School of Life Course and Population Sciences, King's College London, London, United Kingdom
| | - Akash Deep
- Paediatric ICU, King's College Hospital NHS Foundation Trust, Denmark Hill, London, United Kingdom
- Department of Women and Children's Health, School of Life Course Sciences, King's College London, London, United Kingdom
| |
Collapse
|
3
|
Sondhi E, Stewart M, Harper J, Konyk L, McSteen C, Crowley KL, Kim-Campbell N, Fabio A, Fuhrman DY. A Comparison of the Anticoagulation Efficacy and Safety of Epoprostenol to Heparin and Citrate in Children Receiving Continuous Renal Replacement Therapy. Blood Purif 2024; 53:838-846. [PMID: 38991509 PMCID: PMC11444869 DOI: 10.1159/000540302] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2024] [Accepted: 07/07/2024] [Indexed: 07/13/2024]
Abstract
INTRODUCTION Anticoagulants are used in continuous renal replacement therapy (CRRT) to prolong filter life. There are no prior investigations directly comparing epoprostenol to more commonly used forms of anticoagulation in children. Therefore, the primary aim of this study was to assess the efficacy and safety of epoprostenol as compared to heparin and citrate anticoagulation in a pediatric cohort. METHODS We performed a retrospective analysis of all patients <18 years of age admitted to an academic quaternary care children's hospital from 2017-2022 who received epoprostenol, heparin, or citrate exclusively for CRRT anticoagulation. Efficacy was evaluated by comparing the hours to the first unintended filter change and the ratio of filters used to CRRT days. Safety was assessed by evaluating changes in platelet count and vasoactive-ionotropic score (VIS). RESULTS Of 101 patients, 44 received epoprostenol (43.6%), 38 received heparin (37.6%), and 19 received citrate (18.8%). The first filter change was more commonly planned in patients receiving anticoagulation with epoprostenol (43%) as compared to citrate (11%) or heparin (29%) (p = 0.034). Of those patients where the first filter change was unintended (n = 33), there were greater median hours until the filter was replaced in those receiving epoprostenol (29) when compared to citrate (21) (p = 0.002) or heparin (18) (p = 0.003). There was a smaller median ratio of filters used to days on therapy in the patients that received epoprostenol (0.53) when compared to citrate (1) (p = 0.003) or heparin (0.75) (p = 0.001). For those receiving epoprostenol, there was no significant decrease in platelet count when comparing values prior to CRRT initiation through 7 days of therapy. There was no significant difference in VIS when comparing values prior to CRRT initiation through the first 2 days of CRRT. CONCLUSIONS Epoprostenol-based anticoagulation is effective when compared to other anticoagulation strategies used in pediatric CRRT with a favorable side effect profile.
Collapse
Affiliation(s)
- Esha Sondhi
- Department of Critical Care Medicine, Division of Pediatric Critical Care, University of Pittsburgh School of Medicine, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
| | - Martha Stewart
- Department of Pediatrics, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
| | - Jenna Harper
- Department of Critical Care Medicine, Division of Pediatric Critical Care, University of Pittsburgh School of Medicine, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
- Pediatric CRRT Program, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
| | - Leslie Konyk
- Department of Critical Care Medicine, Division of Pediatric Critical Care, University of Pittsburgh School of Medicine, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
- Pediatric CRRT Program, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
| | - Coleen McSteen
- Department of Critical Care Medicine, Division of Pediatric Critical Care, University of Pittsburgh School of Medicine, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
- Pediatric CRRT Program, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
| | - Kelli L. Crowley
- Department of Pharmacy, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
| | - Nahmah Kim-Campbell
- Department of Critical Care Medicine, Division of Pediatric Critical Care, University of Pittsburgh School of Medicine, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
- Safar Center Safar Center for Resuscitation Research, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Anthony Fabio
- Department of Epidemiology, Epidemiology Data Center, University of Pittsburgh, Pittsburgh, PA, USA
| | - Dana Y. Fuhrman
- Department of Critical Care Medicine, Division of Pediatric Critical Care, University of Pittsburgh School of Medicine, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
- Department of Pediatrics, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
- Pediatric CRRT Program, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
- Department of Pediatrics, Division of Nephrology, UPMC Children’s Hospital of Pittsburgh, Pittsburgh, PA, USA
| |
Collapse
|
5
|
Tasker RC. Editor's Choice Articles for January. Pediatr Crit Care Med 2024; 25:1-3. [PMID: 38169335 DOI: 10.1097/pcc.0000000000003416] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/05/2024]
Affiliation(s)
- Robert C Tasker
- orcid.org/0000-0003-3647-8113
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, MA
- Selwyn College, Cambridge University, Cambridge, United Kingdom
| |
Collapse
|
6
|
Affiliation(s)
- Warwick Butt
- Department of Critical Care, Faculty of Medicine Dentistry and Health Sciences, University of Melbourne, Melbourne, VIC, Australia
- Intensive Care Research, Clinical Sciences Theme, Murdoch Childrens Research Institute, Melbourne, VIC, Australia
- Intensive Care Unit, Royal Childrens Hospital, Melbourne, VIC, Australia
| |
Collapse
|