Arterial Blood Gas (ABG) analysis is an important diagnostic tool in intensive care unit (ICU) settings that provides valuable information about the patient's respiratory and metabolic status. However, in the absence of predictive information, when testing is over-utilized or not planned, it can cause discomfort to the patient, costs to the healthcare system, and overtax already burdened resources. This work develops a predictive model that employs machine learning to classify acid-base imbalances and guides testing, which will advance diagnosis and efficiency in practice. The primary data source for model development was a dataset that included ABG profiles of ICU patients along with parameters of pH, PaCO₂, HCO₃⁻, PaO₂, lactate, and clinical indications of hemodynamic stability, respiratory support, and therapeutic interventions. Data pre-processing included: normalization, missing value imputation, and feature scaling, and the Synthetic Minority Over-sampling Technique (SMOTE) was used to create better class balance to improve generalization. The predictive utility used a family of Support Vector Machine (SVM) classifiers with linear, polynomial, and radial basis function (RBF) kernels, which were tuned using a grid search and 10-fold cross-validation. The implementation framework was created in Python 3.11 using Scikit-learn, NumPy, and Panda’s libraries. The optimized SVM classifier achieved a maximum accuracy of 93.02%, F-measure of 92.8%, precision of 93%, and an area under the ROC curve (AUC) of 0.97, for test data. The incorporation of SMOTE resulted in better class balance. This is the first application of its kind, exploring machine learning algorithms to achieve such high-performance metrics in the analysis of clinical ABG data obtained in the ICU, supporting and enhancing healthcare diagnostics.
Nadkarni A, Besic N, Yap J, Micik S, Chapple L anne S, Gnanamanickam E, et al. Rationalising arterial blood gas sampling analysis in the intensive care unit: A before-and-after study. Australian Critical Care. 2025;38(4):101237.
2.
Rosnelly R, Riza BS, S. S. Comparative Analysis of Support Vector Machine and Convolutional Neural Network for Malaria Parasite Classification and Feature Extraction. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications. 2023;14(3):194–217.
3.
Marik P. Evidence-Based Critical Care. 2014;329–47.
4.
Salman R. DeepQ Residue Analysis of Computer Vision Dataset using Support Vector Machine. Journal of Internet Services and Information Security. 2023;13(1):78–84.
5.
Langley R, Wong H. Predictive and prognostic tools for the management of sepsis in the intensive care unit: a work in progress. Clin Chest Med. 2013;(3):587–601.
6.
Verma S, Kapoor H. Machine learning for predictive maintenance: a cloud computing architecture and lessons for a healthcare context. International Academic Journal of Science and Engineering. 2021;(2):1–5.
7.
AARC clinical practice guideline. Sampling for arterial blood gas analysis. Respir Care. 1992;(8):913–7.
8.
Jalali Z, Shaemi A. The impact of nurses’ empowerment and decisionmaking on the care quality of patients in healthcare reform plan. Human Resource Management. 2015;(9):33–9.
9.
Blum FE, Lund ET, Hall HA, Tachauer AD, Chedrawy EG, Zilberstein J. Reevaluation of the utilization of arterial blood gas analysis in the Intensive Care Unit: Effects on patient safety and patient outcome. Journal of Critical Care. 2015;30(2):438.e1-438.e5.
10.
Abd IS, Farazdaq H, Khudair AN. Integrative Evaluation of adeA and adeS Efflux Gene Expression, Biofilm Production, and Antimicrobial Resistance in Clinical Isolates of Acinetobacter Baumannii. Natural and Engineering Sciences. 2025;10(2):342–51.
11.
Capovilla J, Vancouwenberghe C, Miller W. Noninvasive blood gas monitoring. Critical Care Nursing Quarterly. 2000;(2):79–86.
12.
Chinnasamy. A blockchain and machine learning integrated hybrid system for drug supply chain management for the smart pharmaceutical industry. Clinical Journal for Medicine, Health and Pharmacy. 2024;(2):29–40.
13.
Cunanan B, Muppa H, Orellana L, Bates S, McGain F. Blood gas sampling in the intensive care unit: A prospective before-and-after interventional study on the effect of an educational program on blood gas testing frequency. Australian Critical Care. 2024;37(5):755–60.
14.
Delvaux N, Piessens V, Burghgraeve T, Mamouris P, Vaes B, Stichele R, et al. Clinical decision support improves the appropriateness of laboratory test ordering in primary care without increasing diagnostic error: the ELMO cluster randomized trial. Implementation Science. 2020;(1):100.
15.
Stanski N, Wong H. Prognostic and predictive enrichment in sepsis. Nature Reviews Nephrology. 2020;(1):20–31.
16.
Sampling for arterial blood gas analysis. Respir Care. 1992;891–7.
17.
Wilinska M, Hovorka R. Glucose control in the ICU using continuous glucose monitoring: What level of the measurement error is acceptable? 2015;(3).
18.
Castro D, Patil S, Zubair M, Keenaghan M. Arterial blood gas. StatPearls. 2024;
19.
Kumaravel A, Vijayan T. Comparing cost sensitive classifiers by the false-positive to false- negative ratio in diagnostic studies. Expert Systems with Applications. 2023;227:120303.
20.
Kajanan S, Kumara BTGS, Banujan K, Prasanth S, Manitheepan K. Classify the Outcome of Arterial Blood Gas Test to Detect the Respiratory Failure Using Machine Learning. 2022 International Conference on Decision Aid Sciences and Applications (DASA). IEEE; 2022. p. 1139–43.
21.
Ramadoss S, Kumaravel A. Medical dataset for arterial blood gas analysis.
22.
Kaggle. 2025;
23.
Ayala-De la Cruz S, Arenas-Hernández PE, Fernández-Herrera MF, Quiñones-Díaz RA, Llaca-Díaz JM, Díaz-Chuc EA, et al. Human-in-the-Loop Performance of LLM-Assisted Arterial Blood Gas Interpretation: A Single-Center Retrospective Study. Journal of Clinical Medicine. 2025;14(18):6676.
24.
Ozdemir H, Sasmaz M, Guven R, Avci A. Interpretation of acid-base metabolism on arterial blood gas samples via machine learning algorithms. Irish Journal of Medical Science. 1971;(1):277–87.
25.
Guo J, Wu H, Chen X, Lin W. Adaptive SV-Borderline SMOTE-SVM algorithm for imbalanced data classification. Applied Soft Computing. 2024;150:110986.
26.
Guido R, Ferrisi S, Lofaro D, Conforti D. An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review. Information. 2024;15(4):235.
27.
Yu H, Saffaran S, Tonelli R, Laffey J, Esquinas A, De Lima L, et al. Machine learning models compared with current clinical indices to predict the outcome of high flow nasal cannula therapy in acute hypoxemic respiratory failure. Critical Care. 2025;(1):101.
28.
Mousavinejad SN, Lachouri R, Bahadorzadeh M, Khatami SH. Artificial intelligence for arterial blood gas interpretation. Clinica Chimica Acta. 2026;579:120691.
29.
Manoochehri S. Evaluating SMOTE-based machine learning algorithms for clinical imbalanced datasets. Comput Biol Med. 2025;108265.
30.
Helleberg J, Sundelin A, Mårtensson J, Rooyackers O, Thobaben R. Beyond labels: determining the true type of blood gas samples in ICU patients through supervised machine learning. BMC Medical Informatics and Decision Making. 2025;(1):275.
31.
Wibowo A, Masruriyah AFN, Rahmawati S. Refining Diabetes Diagnosis Models: The Impact of SMOTE on SVM, Logistic Regression, and Naïve Bayes. Journal of Electronics, Electromedical Engineering, and Medical Informatics. 2025;7(1):197–207.
32.
G K, K P I, Hasin A J, M LFJ, Siluvai S, G K. Support Vector Machines: A Literature Review on Their Application in Analyzing Mass Data for Public Health. Cureus. 2025;
33.
Zhou X, Li X, Zhang Z, Han Q, Deng H, Jiang Y, et al. Support vector machine deep mining of electronic medical records to predict the prognosis of severe acute myocardial infarction. Frontiers in Physiology. 2022;13.
34.
Hu J, Lv S, Zhou T, Chen H, Xiao L, Huang X, et al. Identification of pulmonary hypertension animal models using a new evolutionary machine learning framework based on blood routine indicators. Journal of Bionic Engineering. 2023;(2):762–81.
35.
Raoufy M, Eftekhari P, Gharibzadeh S, Masjedi M. Predicting arterial blood gas values from venous samples in patients with acute exacerbation chronic obstructive pulmonary disease using artificial neural network. Journal of medical systems. 2011;(4):483–8.
36.
Li Y, Yang Y, Song P, Duan L, Ren R. An improved SMOTE algorithm for enhanced imbalanced data classification by expanding sample generation space. Scientific Reports. 2025;(1):23521.
37.
Qaiser A, Manzoor S, Hashmi AH, Javed H, Zafar A, Ashraf J. Support Vector Machine Outperforms Other Machine Learning Models in Early Diagnosis of Dengue Using Routine Clinical Data. Advances in Virology. 2024;2024(1).
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.
,
