Advances in Predictive Modeling: The Role of Artificial Intelligence in Monitoring Blood Lactate Levels Post-Cardiac Surgery
DOI:
10.47709/ijmdsa.v3i4.4957Keywords:
AI, lactate tracking, cardiac procedures, intensive care, prognostic analysis, effectiveness, patients’ experiences, Intensive Care Unit, live data, big data, alerting, critical care, advanced technologies, ethical issues, possible overtones, overstimulation, medicines for individualsDimension Badge Record
Abstract
Total blood lactate levels monitoring through the use of Artificial Intelligence in individuals that have undergone cardio surgeries is a milestone in critical care because it indicates metabolic problems earlier than traditional approaches. Lactate levels have to be significantly raised in order they may indicate complications like tissue hypoxia, sepsis or organ dysfunction. The previous method of monitoring lactate entails conducting tests after a few hours or days and can be very unresponsive; in the application of AI models, the algorithm scans through data acquired from patient monitoring systems to predict and advance notice the clinicians on the trends in lactate levels. This review outlines the basic mechanisms, algorithms, and features required to build an AI-based lactate predictor and the multiple physiologic signals such as heart rate, oxygen saturation, and blood pressure into the support vector regression model. Illustrative cases show that AI can facilitate more effective clinical decision-making to increase ICU patient safety and decrease such hospital stays. While AI based lactate tracking is something that has been bandied about in the research literature for some time, there are real questions as to how this is implemented in existing hospitals, how one minimizes the negative impacts of alarm fatigue, and how the results are persistent across population groups. Ethical and legal necessities concerning patient’s data confidentiality, security, and further reporting also play the vital role of its clinical endorsement. Other directions for future work are more flexible and multiple modality models that include additional data and require learning from new patient data.
Abstract viewed = 36 times
References
Hoste EAJ, Kellum JA, Selby NM et al (2018) Global epidemiology and outcomes of acute kidney injury. Nat Rev Nephrol 14(10):607–625. https://doi.org/10.1038/s41581-018-0052-02.
Van den Eynde J, Delpire B, Jacquemyn X et al (2022) Risk factors for acute kidney injury after pediatric cardiac surgery: a meta-analysis. Pediatr Nephrol 37(3):509–519. https://doi.org/10.1007/s00467-021-05297-0
Webb TN, Goldstein SL (2017) congenital heart surgery and acute kidney injury. Curr Opin Anaesthesiol 30(1):105–112. https://doi.org/10.1097/ACO.0000000000000406
Ricci Z, Raggi V, Marinari E et al (2022) acute kidney injury in pediatric cardiac intensive care children: not all admissions are equal: a retrospective study. J Cardiothorac Vasc Anesth 36(3):699–706. https://doi.org/10. 1053/j.jvca.2021.04.015
Romagnoli S, Ricci Z (2015) Postoperative acute kidney injury. Minerva Anestesiol 81(6):684–696
Meersch M, Schmidt C, Hofmeier A et al (2017) (2017) Prevention of cardiac surgery-associated AKI by implementing the KDIGO guidelines in high risk patient’s identifed by biomarkers: the PrevAKI randomized controlled trial [published correction appears in Intensive Care Med. Intensive Care Med 43(11):1551–1561. https://doi.org/10.1007/s00134-016-4670-3
Bellos I, Iliopoulos DC, Perrea DN (2019) Pharmacological interventions for the prevention of acute kidney injury after pediatric cardiac surgery: a network meta-analysis. Clin Exp Nephrol 23(6):782–791. https://doi.org/10.1007/s10157-019-01706-9
Kelly BJ, Chevarria J, O’Sullivan B, Shorten G (2021) the potential for artifcial intelligence to predict clinical outcomes in patients who have acquired acute kidney injury during the perioperative period. Perioper Med (Lond) 10(1):49. https://doi.org/10.1186/s13741-021-00219-y
von Elm E, Altman DG, Egger M, Pocock SJ, Gøtzsche PC, Vandenbroucke JP, STROBE Initiative (2008) The strengthening the reporting of observational studies in epidemiology (STROBE) statement: guidelines for reporting observational studies. J Clin Epidemiol 61(4):344–9. https://doi. org/10.1016/j.jclinepi.2007.11.008
Neugarten J, Sandilya S, Singh B, Golestaneh L. Sex and the risk of AKI following cardio-thoracic surgery: a meta-analysis. Clin J Am Soc Nephrol. 2016; 11:2113–22.
James MT, Bhatt M, Pannu N, Tonelli M. Long-term outcomes of acute kidney injury and strategies for improved care. Nat Rev Nephrol. 2020; 16:193–205.
Pickkers P, Darmon M, Hoste E, Joannidis M, Legrand M, Ostermann M, et al. Acute kidney injury in the critically ill: an updated review on pathophysiology and management. Intensive Care Med. 2021; 47:835–50.
Schunk SJ, Zarbock A, Meersch M, Küllmar M, Kellum JA, Schmit D, et al. Association between urinary dickkopf-3, acute kidney injury, and subsequent loss of kidney function in patients undergoing cardiac surgery: an observational cohort study. Lancet. 2019; 394:488–96
Ugwuowo U, Yamamoto Y, Arora T, Saran I, Partridge C, Biswas A, et al. Real-time prediction of acute kidney injury in hospitalized adults: implementation and proof of concept. Am J Kidney Dis. 2020; 76:806–14?
Wijeysundera DN, Karkouti K, Dupuis JY, Rao V, Chan CT, Granton JT, et al. Derivation and validation of a simplifed predictive index for renal replacement therapy after cardiac surgery. JAMA. 2007; 297:1801–9.
Mehta RH, Grab JD, O’Brien SM, Bridges CR, Gammie JS, Haan CK, et al. Bedside tool for predicting the risk of postoperative dialysis in patients undergoing cardiac surgery. Circulation. 2006; 114:2208–16.
Jiang W, Xu J, Shen B, Wang C, Teng J, Ding X. Validation of four prediction scores for cardiac surgery-associated acute kidney injury in chinese patients. Braz J Cardiovasc Surg. 2017; 32:481–6.
Tomašev N, Glorot X, Rae JW, Zielinski M, Askham H, Saraiva A, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019; 572:116–9.
Lundberg SM, Erion GG, Lee S-I. Consistent individualized feature attribution for tree ensembles. arXiv [Preprint]. 2018. https://arxiv.org/abs/1802. 03888. Accessed 12 Feb 2018.
Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. 2015; 350:g7594.
Stevens PE, Levin A. Evaluation and management of chronic kidney disease: synopsis of the kidney disease: improving global outcomes 2012 clinical practice guideline. Ann Intern Med. 2013; 158:825–30.
Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. arXiv [Preprint]. 2016. https://arxiv.org/abs/1603.02754. Accessed 9 Mar 2016
Zhou ZH, Feng J. Deep Forest: towards an alternative to deep neural networks. arXiv [Preprint]. 2017. https://arxiv.org/abs/1702.08835v1. Accessed 28 Feb 2017
Niculescu-Mizil A, Caruana R. Predicting good probabilities with supervised learning. In: Machine learning: Proceedings of the 22nd international conference. 2005. See section 4 (Qualitative Analysis of Predictions).
Shapley LS. A value for n-person games. Princeton: Princeton University Press; 1953. 19. Nagin DS, Jones BL, Passos VL, Tremblay RE. Group-based multi-trajectory modeling. Stat Methods Med Res. 2018; 27:2015–23.
. Cook NR. Statistical evaluation of prognostic versus diagnostic models: beyond the ROC curve. Clin Chem. 2008; 54:17–23.
Vickers AJ, Elkin EB. Decision curve analysis: a novel method for evaluating prediction models. Med Decis Making. 2006; 26:565–74.
Kanji HD, Schulze CJ, Hervas-Malo M, Wang P, Ross DB, Zibdawi M, et al. Diference between pre-operative and cardiopulmonary bypass mean arterial pressure is independently associated with early cardiac surgeryassociated acute kidney injury. J Cardiothorac Surg. 2010; 5:71.
O’Neal JB, Shaw AD, Billings FT. Acute kidney injury following cardiac surgery: current understanding and future directions. Crit Care. 2016; 20:187.
Gambardella I, Gaudino M, Ronco C, Lau C, Ivascu N, Girardi LN. Congestive kidney failure in cardiac surgery: the relationship between central venous pressure and acute kidney injury. Interact Cardiovasc Thorac Surg. 2016; 23:800–5.
Lopez MG, Shotwell MS, Morse J, Liang Y, Wanderer JP, Absi TS, et al. Intraoperative venous congestion and acute kidney injury in cardiac surgery: an observational cohort study. Br J Anaesth. 2021; 126:599–607.
Manning MW, Li YJ, Linder D, Haney JC, Wu YH, Podgoreanu MV, et al. Conventional ultrafltration during elective cardiac surgery and postoperative acute kidney injury. J Cardiothorac Vasc Anesth. 2021; 35:1310–8.
Tseng PY, Chen YT, Wang CH, Chiu KM, Peng YS, Hsu SP, et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Crit Care. 2020; 24:478.
Esteve F, Lopez-Delgado JC, Javierre C, Skaltsa K, Carrio ML, RodríguezCastro D, et al. Evaluation of the PaO2/FiO2 ratio after cardiac surgery as a predictor of outcome during hospital stay. BMC Anesthesiol. 2014; 14:83.
Gao XP, Zheng CF, Liao MQ, He H, Liu YH, Jing CX, et al. Admission serum sodium and potassium levels predict survival among critically ill patients with acute kidney injury: a cohort study. BMC Nephrol. 2019; 20:311
Zhang D, Shi L. Serum lactate dehydrogenase level is associated with inhospital mortality in critically Ill patients with acute kidney injury. Int Urol Nephrol. 2021; 53:2341–8.
Kym D, Cho YS, Yoon J, Yim H, Yang HT. Evaluation of diagnostic biomarkers for acute kidney injury in major burn patients. Ann Surg Treat Res. 2015; 88:281–8.
Guan C, Li C, Xu L, Zhen L, Zhang Y, Zhao L, et al. Risk factors of cardiac surgery-associated acute kidney injury: development and validation of a perioperative predictive nomogram. J Nephrol. 2019; 32:937–45.
Vermeulen Windsant IC, Snoeijs MG, Hanssen SJ, Altintas S, Heijmans JH, Koeppel TA, et al. Hemolysis is associated with acute kidney injury during major aortic surgery. Kidney Int. 2010; 77:913–20
Weedle RC, Da Costa M, Veerasingam D, Soo AWS. The use of neutrophil lymphocyte ratio to predict complications post cardiac surgery. Ann Transl Med. 2019; 7:778.
Wang Q, Li J, Wang X. The neutrophil-lymphocyte ratio is associated with postoperative mortality of cardiac surgery. J Thorac Dis. 2021; 13:67–75
Haran C, Gimpel D, Clark H, McCormack DJ. Preoperative neutrophil and lymphocyte ratio as a predictor of mortality and morbidity after cardiac surgery. Heart Lung Circ. 2021; 30:414–8.
Smith LE, Smith DK, Blume JD, Linton MF, Billings FT 4th. High-density lipoprotein cholesterol concentration and acute kidney injury after cardiac surgery. J Am Heart Assoc. 2017; 6:e006975.
Rhodes JF, Blaufox AD, Seiden HS, Asnes JD, Gross RP, Rossi AF (1999) Cardiac arrest in infants after congenital heart surgery. Circulation 100(19 Suppl): II 194-9. https://doi.org/10.1161/01.cir.100.suppl_2.ii-194. (PMID: 10567303)
Ichord R, Silverstein FS, Slomine BS, Telford R, Christensen J, Holubkov R, Dean JM, Moler FW (2018) THAPCA Trial Group Neurologic outcomes in pediatric cardiac arrest survivors enrolled in the THAPCA trials. Neurology 91(2):e123–e131. https://doi.org/10.1212/WNL.0000000000005773
Alten JA, Klugman D, Raymond TT et al (2017) Epidemiology and outcomes of cardiac arrest in pediatric cardiac ICUs. Pediatr Crit Care Med 18(10):935–943
Husnain, A., Alomari, G., & Saeed, A. AI-Driven Integrated Hardware and Software Solution for EEG-Based Detection of Depression and Anxiety.
Alten J, Cooper DS, Klugman D et al (2022) Preventing cardiac arrest in the pediatric cardiac intensive care unit through multicenter collaboration. JAMA Pediatr 176(10):1027–1036. https://doi.org/10.1001/jamap ediatrics.2022.2238
Ferguson LP, Thiru Y, Stafa SJ et al (2020) Reducing cardiac arrests in the PICU: initiative to improve time to administration of prearrest bolus epinephrine in patients with cardiac disease. Crit Care Med 48(7):e542–e549. https://doi.org/10.1097/ccm.0000000000004349
Riley CM, Murphy LD, Mastropietro CW (2022) Cardiac arrest in children following cardiac surgery: a scoping review of contributing factors. World J Pediatr Congenit Heart Surg 13(4):475–481. https://doi.org/10.1177/21501351221100791
Khoubian JJ, Alten JA (2022) Cardiac arrest in pediatric cardiac ICUs: prevention comes frst. Curr Treat Options Peds 8:325–333. https://doi.org/10.1007/s40746-022-00255-w
Alten J, Cooper DS, Klugman D et al (2022) Preventing cardiac arrest in the pediatric cardiac intensive care unit through multicenter collaboration. JAMA Pediatr 176(10):1027–1036. https://doi.org/10.1001/jamap ediatrics.2022.2238
Shin Y, Cho KJ, and Lee Y et al (2022) Multicenter validation of a deep-learning-based pediatric early warning system for prediction of deterioration events. Acute Crit Care 37(4):654–666. https://doi.org/10.4266/acc.2022. 00976
Husnain, A., & Saeed, A. (2024). AI-enhanced depression detection and therapy: Analyzing the VPSYC system. IRE Journals, 8(2), 162-168.
Downloads
ARTICLE Published HISTORY
Issue
Section
License
Copyright (c) 2024 Roman Khan, Hira Zainab, Arbaz Haider Khan, Hafiz Khawar Hussain
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.