Automatic real-time analysis and interpretation of arterial blood gas sample for Point-of-care testing: Clinical validation

Interpretation of acid-base metabolism on arterial blood gas samples via machine learning algorithms

BACKGROUND

Arterial blood gas evaluation is crucial for critically ill patients, as it provides essential information about acid-base metabolism and respiratory balance, but evaluation can be complex and time-consuming. Artificial intelligence can perform tasks that require human intelligence, and it is revolutionizing healthcare through technological advancements.

AIM

This study aims to assess arterial blood gas evaluation using artificial intelligence algorithms.

METHODS

The study included 21.541 retrospective arterial blood gas samples, categorized into 15 different classes by experts for evaluating acid-base metabolism status. Six machine learning algorithms were utilized; accuracy, balanced accuracy, sensitivity, specificity, precision, and F1 values of the models were determined; and ROC curves were drawn to assess areas under the curve for each class. Evaluation of which sample was estimated in which class was conducted using the confusion matrices of the models.

RESULTS

The bagging classifier (BC) model achieved the highest balanced accuracy with 99.24%, whereas the XGBoost model reached the highest accuracy with 99.66%. The BC model shows 100% sensitivity for nine classes and 100% specificity for 10 classes, and the model correctly predicted 6438 of 6463 test samples and achieved an accuracy of 99.61%, with an area under the curve > 0.9 in all classes on a class basis.

CONCLUSION

The machine learning models developed exhibited remarkable accuracy, sensitivity, and specificity in predicting the status of acid-base metabolism. However, implementing these models can aid clinicians, freeing up their time for more intricate tasks.

Analysis of arterial blood gas values when discarding different volumes of blood samples in an arterial heparin blood collector during thoracoscopic surgery

BACKGROUND

Arterial blood gas analysis (ABGA) plays a vital role in emergency and intensive care, which is affected by many factors, such as different instrumentation, temperature, and testing time. However, there are still no relevant reports on the difference in discarding different blood volumes on ABGA values.

METHODS

We enrolled 54 patients who underwent thoracoscopic surgery and analysed differences in blood gas analysis results when different blood volumes were discarded from the front line of the arterial heparin blood collector. A paired t test was used to compare the results of the same patient with different volumes of blood discarded from the samples. The difference was corrected by Bonferroni correction.

RESULTS

Our results demonstrated that the PaO2, PaCO2, and THbc were more stable in the 4th ml (PaO2 = 231.3600 ± 68.4878 mmHg, PaCO2 = 41.9232 ± 7.4490 mmHg) and 5th ml (PaO2 = 223.7600 ± 12.9895 mmHg, PaCO2 = 42.5679 ± 7.6410 mmHg) blood sample than in the 3rd ml (PaO2 = 234.1000 ± 99.7570 mmHg, PaCO2 = 40.6179 ± 7.2040 mmHg).

CONCLUSION

It may be more appropriate to discard the first 3 ml of blood sample in the analysis of blood gas results without wasting blood samples.

Electrolyte Disturbances Related to Sodium and Potassium and Electroconvulsive Therapy: A Systematic Review

INTRODUCTION

Electrolyte disturbances related to sodium and potassium affect patients with mental disorders undergoing electroconvulsive therapy (ECT). The objective of this study was to systematically summarize the data regarding ECT and electrolyte disturbances related to sodium and potassium.

MATERIALS AND METHODS

A systematic literature review in accordance with PRISMA guidelines was conducted. Clinical studies of patients receiving ECT with electrolyte disturbances reported before or after treatment were included.

RESULTS

We identified nine case reports and two retrospective studies describing electrolyte abnormalities occurring before or after ECT. ECT was effective and safe in patients with hyponatremia and hypernatremia, including the elderly patient population. This treatment was also effective in treating psychiatric symptoms that may persist after ionic equalization. Electrolyte disturbances after ECT were rare. Reports have suggested that succinylcholine used as a muscle relaxant was the main cause of hyperkalemia after ECT.

CONCLUSIONS

Electrolyte control is a crucial aspect of guiding ECT therapy. In the context of sodium-related disorders, it is critical to control patient hydration as part of therapy. In addition, succinylcholine should not be used in patients with immobilization, such as catatonia or neuroleptic malignant syndrome. It is necessary to conduct further studies to clarify whether electrolyte concentration affects ECT parameters and clinical efficacy. In addition, it is necessary to assess the influence of various anesthetics on these conditions during ECT. The result of this review should be interpreted bearing in mind the small number of studies conducted to date and the low quality of the evidence they provide.

Lab at home: a promising prospect for on-site chemical and biological analysis

The continuing pursuit for a healthy life has led to the urgent need for on-site analysis. In response to the urgent needs of on-site analysis, we propose a novel concept, called lab at home (LAH), for building automated and integrated total analysis systems to perform chemical and biological testing at home. It represents an emerging research area with broad prospects that has not yet attracted sufficient attention. In this paper, we discuss the urgent need, challenges, and future prospects of this area, and the possible roadmap for achieving the goal of LAH has also been proposed.

The effect of heparin concentration on results of venous blood gas of patients admitted to cardiac intensive care unit: A double-blind clinical trial

Background

The aim of the present study was to investigate the effect of heparin (1000 IU/mL) in the blood sample on the results of venous blood gases of patients admitted to the cardiac intensive care unit.

Materials and methods

The present double-blind randomized clinical trial study was performed on 282 samples from 141 patients admitted to the cardiac intensive care unit. Insulin syringes with heparin (1000 IU/mL) and heparin (5000 IU/mL) and 1 cc of blood sample were taken from the peripheral vein, then distributed in two syringes and given to the analyzer.

Results

In the present study, the mean age of the samples was 49.96 ± 9.58. There was a statistically significant difference between the two groups in terms of values of partial pressure of carbon dioxide (PCO2) (P < 0.001), partial pressure of oxygen (PaO2) (P < 0.001), blood oxygen saturation (P < 0.001), bicarbonate ion (P < 0.001), excess base (P < 0.001), hemoglobin (P < 0.001), calcium (P < 0.001), potassium (P < 0.001), and sodium (P < 0.001) in the two groups.

Conclusion

Overall, heparin (1000 IU/mL) led to a less disruption in the results of venous blood gases, and since it has not significantly increased the risk of clots, it is recommended to be used for venous blood gas sampling.

Diagnostic Modalities in Critical Care: Point-of-Care Approach

The concept of intensive care units (ICU) has existed for almost 70 years, with outstanding development progress in the last decades. Multidisciplinary care of critically ill patients has become an integral part of every modern health care system, ensuing improved care and reduced mortality. Early recognition of severe medical and surgical illnesses, advanced prehospital care and organized immediate care in trauma centres led to a rise of ICU patients. Due to the underlying disease and its need for complex mechanical support for monitoring and treatment, it is often necessary to facilitate bed-side diagnostics. Immediate diagnostics are essential for a successful treatment of life threatening conditions, early recognition of complications and good quality of care. Management of ICU patients is incomprehensible without continuous and sophisticated monitoring, bedside ultrasonography, diverse radiologic diagnostics, blood gas analysis, coagulation and blood management, laboratory and other point-of-care (POC) diagnostic modalities. Moreover, in the time of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic, particular attention is given to the POC diagnostic techniques due to additional concerns related to the risk of infection transmission, patient and healthcare workers safety and potential adverse events due to patient relocation. This review summarizes the most actual information on possible diagnostic modalities in critical care, with a special focus on the importance of point-of-care approach in the laboratory monitoring and imaging procedures.

Systemic acidemia impairs cardiac function in critically Ill patients

BACKGROUND

Acidemia, is associated with reduced cardiac function in animals, but no studies showing an effect of acidemia on cardiac function in humans are reported. In the present study, we examined the effect of acidemia on cardiac function assessed with transpulmonary thermodilution technique with integrated pulse contour analysis (Pulse Contour Cardiac Output, PiCCO™) in a large cohort of critically ill patients.

METHODS

This was a prospective multicenter observational cross-sectional study of 297 patients from 6 intensive care units in London, England selected from all patients admitted consecutively between May 2018 and March 2019. Measurements of lowest plasma pH and concurrent assessment of cardiac function were obtained.

FINDINGS

There was a significant difference between two pH categories (pH ≤ 7.28 vs. pH > 7.28) for the following variables of cardiac function: SVI (difference in means 32.7; 95% CI: 21 to 45 mL/m2; p < 0.001); GEF (18; 95% CI: 11 to 26%; p < 0.001), dPmax (-331; 95% CI: -510 to -153 mmHg/s; p = 0.001), CFI (0.7; 95% CI: 0.2 to 1.3 1/min; p = 0.01) and CPI (0.09; 95% CI: 0.03 to 0.15 W/m2; p < 0.001). However, there was no significant difference in CI (0.13; 95% CI: -0.20 to 0.47 L/min/m2; p = 0.12) between the pH categories. Also, a significant relationship was found between the quantitative pH and the following variables: SVI (132; 95% CI: 77 to 188 mL/m2; p < 0.001), GEF (74.7; 95% CI: 37.1 to 112.4%; p < 0.001), dPmax (-1587; 95% CI: -2361 to -815 mmHg/s; p < 0.001), CFI (3.5; 95% CI: 0.9 to 6.1 /min; p = 0.009), CPI (0.62; 95% CI: 0.36 to 0.88 W/m2; p < 0.001) and CI (regression coefficient 1.96; 95% CI:0.45 to 3.47 L/min/m2; p = 0.01).

INTERPRETATION

Acidemia is associated with impaired cardiac function in seriously ill patients hospitalized in the intensive care unit supporting the potential value of early diagnosis and improvement of arterial pH in these patients.

FUNDING

The study was partially supported by unrestricted funds from the UCLA School of Medicine.