Mustafa Kemal Arslantas
Research Subjects
Research Interests
Mustafa Kemal Arslantas has a total of 265 co-authors. Here are the top co-authors by number of shared publications:
- Reyhan Arslantas
Anesthesiology and Reanimation Clinic, Dr. Lütfi Kirdar Training and Research Hospital, Istanbul, Turkey
8 shared publications Ismail Cinel
Department of Anesthesiology and Reanimation, School of Medicine, Marmara University, Istanbul, Turkey
6 shared publicationsAlper Kararmaz
Marmara University
5 shared publicationsGulbin Tore Altun
Kadıköy Florence Nightingale Hospital
5 shared publicationsPelin Corman Dincer
Marmara University
5 shared publications- Pelin Corman Dincer
Marmara University
5 shared publications
Latest Publications
- 22 June 2026
- Published by Academician Publishing
Günübirlik Anestezi ve Ameliyathane Dışı Anestezi Uygulamaları
- 22 June 2026
- Published by Academician Publishing
Günübirlik Anestezi ve Ameliyathane Dışı Anestezi Uygulamaları
- 22 June 2026
- Published by Academician Publishing
- p. 291-306
Günübirlik Anestezi Uygulamalarında Yapay Zeka
- 22 June 2026
- Published by Academician Publishing
- p. 291-306
Günübirlik Anestezi Uygulamalarında Yapay Zeka
- Open Access
- 5 May 2024
- Published by Springer Nature
- p. 3-16
Using Machine Learning Methods to Predict the Lactate Trend of Sepsis Patients in the ICU
Serum lactate levels are considered a biomarker of tissue hypoxia. In sepsis or septic shock patients, as suggested by The Surviving Sepsis Campaign, early lactate clearance-directed therapy is associated with decreased mortality; thus, serum lactate levels should be assessed. Monitoring a patient’s vital parameters and repetitive blood analysis may have deleterious effects on the patient and also bring an economic burden. Machine learning and trend analysis are gaining importance to overcome these issues. In this context, we aimed to investigate if a machine learning approach can predict lactate trends from non-invasive parameters of patients with sepsis. This retrospective study analyzed adult sepsis patients in the Medical Information Mart for Intensive Care IV (MIMIC-IV) dataset. Inclusion criteria were two or more lactate tests within 6 h of diagnosis, an ICU stay of at least 24 h, and a change of ≥1 mmol/liter in lactate level. Naïve Bayes, J48 Decision Tree, Logistic Regression, Random Forest, and Logistic Model Tree (LMT) classifiers were evaluated for lactate trend prediction. LMT algorithm outperformed other classifiers (AUC = 0.803; AUPRC = 0.921). J48 decision tree performed worse than the other methods when predicting constant trend. LMT algorithm with four features (heart rate, oxygen saturation, initial lactate, and time interval variables) achieved 0.80 in terms of AUC (AUPRC = 0.921). We can say that machine learning models that employ logistic regression architectures, i.e., LMT algorithm achieved good results in lactate trend prediction tasks, and it can be effectively used to assess the state of the patient, whether it is stable or improving.
- 5 May 2024
- Published by Springer Nature
- p. 3-16
Open AccessUsing Machine Learning Methods to Predict the Lactate Trend of Sepsis Patients in the ICU
Serum lactate levels are considered a biomarker of tissue hypoxia. In sepsis or septic shock patients, as suggested by The Surviving Sepsis Campaign, early lactate clearance-directed therapy is associated with decreased mortality; thus, serum lactate levels should be assessed. Monitoring a patient’s vital parameters and repetitive blood analysis may have deleterious effects on the patient and also bring an economic burden. Machine learning and trend analysis are gaining importance to overcome these issues. In this context, we aimed to investigate if a machine learning approach can predict lactate trends from non-invasive parameters of patients with sepsis. This retrospective study analyzed adult sepsis patients in the Medical Information Mart for Intensive Care IV (MIMIC-IV) dataset. Inclusion criteria were two or more lactate tests within 6 h of diagnosis, an ICU stay of at least 24 h, and a change of ≥1 mmol/liter in lactate level. Naïve Bayes, J48 Decision Tree, Logistic Regression, Random Forest, and Logistic Model Tree (LMT) classifiers were evaluated for lactate trend prediction. LMT algorithm outperformed other classifiers (AUC = 0.803; AUPRC = 0.921). J48 decision tree performed worse than the other methods when predicting constant trend. LMT algorithm with four features (heart rate, oxygen saturation, initial lactate, and time interval variables) achieved 0.80 in terms of AUC (AUPRC = 0.921). We can say that machine learning models that employ logistic regression architectures, i.e., LMT algorithm achieved good results in lactate trend prediction tasks, and it can be effectively used to assess the state of the patient, whether it is stable or improving.
- Open Access
- 21 September 2022
- Published by Springer Nature in Research Square
Using machine learning methods to predict the lactate trend of sepsis patients in the ICU
Purpose Serum lactate levels are considered a biomarker of tissue hypoxia. In sepsis or septic shock patients as suggested by The Surviving Sepsis Campaign serum lactate levels should be assessed and early lactate clearance-directed therapy is associated with decreased mortality. Monitoring a patient's vital parameters and repeatedly done blood analysis may have deleterious effects on the patient and brings an economical burden. Machine learning algorithms and trend analysis are gaining importance to overcome these unwanted facts. In this context, we aimed to investigate if an artificial intelligence approach can predict lactate trends from non-invasive clinical variables of patients with sepsis. Methods In this retrospective study, adult patients with sepsis from the MIMIC-IV dataset who had at least two serum lactate measurements recorded within the first 6 hours of sepsis diagnosis and who also has an ICU length of stay ≥ 24 hours are evaluated and ≥1mmol/l change is considered as a trend indicator. For prediction of lactate trend Naïve Bayes, J48 Decision Tree, Logistic Regression, Random Forest, and Logistic Model Tree (LMT) classifiers are evaluated. Results LMT algorithm outperformed other classifiers (AUC= 0.832). J48 decision tree performed worse when predicting constant lactate trend. LMT algorithm with 4 features (heart rate, oxygen saturation, lactate value before sepsis diagnosis, and time interval variables) achieved 0.821 in terms of AUC. Conclusion We can say that machine learning models that employ logistic regression architectures, i.e. LMT algorithm achieved good results in lactate trend prediction tasks can be effectively used to assess the state of the patient whether it is stable or improving.
- 21 September 2022
- Published by Springer Nature in Research Square
Open AccessUsing machine learning methods to predict the lactate trend of sepsis patients in the ICU
Purpose Serum lactate levels are considered a biomarker of tissue hypoxia. In sepsis or septic shock patients as suggested by The Surviving Sepsis Campaign serum lactate levels should be assessed and early lactate clearance-directed therapy is associated with decreased mortality. Monitoring a patient's vital parameters and repeatedly done blood analysis may have deleterious effects on the patient and brings an economical burden. Machine learning algorithms and trend analysis are gaining importance to overcome these unwanted facts. In this context, we aimed to investigate if an artificial intelligence approach can predict lactate trends from non-invasive clinical variables of patients with sepsis. Methods In this retrospective study, adult patients with sepsis from the MIMIC-IV dataset who had at least two serum lactate measurements recorded within the first 6 hours of sepsis diagnosis and who also has an ICU length of stay ≥ 24 hours are evaluated and ≥1mmol/l change is considered as a trend indicator. For prediction of lactate trend Naïve Bayes, J48 Decision Tree, Logistic Regression, Random Forest, and Logistic Model Tree (LMT) classifiers are evaluated. Results LMT algorithm outperformed other classifiers (AUC= 0.832). J48 decision tree performed worse when predicting constant lactate trend. LMT algorithm with 4 features (heart rate, oxygen saturation, lactate value before sepsis diagnosis, and time interval variables) achieved 0.821 in terms of AUC. Conclusion We can say that machine learning models that employ logistic regression architectures, i.e. LMT algorithm achieved good results in lactate trend prediction tasks can be effectively used to assess the state of the patient whether it is stable or improving.
- 31 January 2022
- Published by Marmara University in Marmara Medical Journal
- Vol. 35 (1) , 61-66
Prognostic value of the lactate–albumin difference for predicting in-hospital mortality in critically ill patients with sepsis
Objective: To evaluate the prognostic performance of the lactate–albumin difference (LAD), maximum lactate levels, and the Sequential Organ Failure Assessment (SOFA) score taken on the first day in critically ill patients with sepsis, on in-hospital mortality and 90-day survival.Patients and Methods: Data from the Medical Information Mart for Intensive Care III (MIMIC III) version 1.4 were evaluated retrospectively. The first day data of adult patients with sepsis diagnosed according to the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) criteria were recorded. The effectiveness of all diagnostic modalities on admission was analyzed to predict in-hospital mortality and 90-day survival. Results: In-hospital mortality was 20.3% among the 2270 patients included in this study. The area below the receiver operating characteristic curve (AUC) value of the LAD was higher than lactate for predicting mortality (AUC, 0.691; 95% confidence interval [CI], 0.663–0.718; p< 0.01, and AUC, 0.675; 95% CI, 0.646–0.703; p< 0.01, respectively), and the AUC of SOFA score was the highest (AUC, 0.716; 95% CI, 0.663–0.718). The optimal cutoff of LAD was 0.7. Conclusion: In addition to its easy and simple calculability relative to the SOFA, the prognostic performance of LAD was superior to maximum lactate levels for predicting in-hospital mortality and 90-day survival in adult patients with sepsis.
- 31 January 2022
- Published by Marmara University in Marmara Medical Journal
- Vol. 35 (1) , 61-66
Prognostic value of the lactate–albumin difference for predicting in-hospital mortality in critically ill patients with sepsis
Objective: To evaluate the prognostic performance of the lactate–albumin difference (LAD), maximum lactate levels, and the Sequential Organ Failure Assessment (SOFA) score taken on the first day in critically ill patients with sepsis, on in-hospital mortality and 90-day survival.Patients and Methods: Data from the Medical Information Mart for Intensive Care III (MIMIC III) version 1.4 were evaluated retrospectively. The first day data of adult patients with sepsis diagnosed according to the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) criteria were recorded. The effectiveness of all diagnostic modalities on admission was analyzed to predict in-hospital mortality and 90-day survival. Results: In-hospital mortality was 20.3% among the 2270 patients included in this study. The area below the receiver operating characteristic curve (AUC) value of the LAD was higher than lactate for predicting mortality (AUC, 0.691; 95% confidence interval [CI], 0.663–0.718; p< 0.01, and AUC, 0.675; 95% CI, 0.646–0.703; p< 0.01, respectively), and the AUC of SOFA score was the highest (AUC, 0.716; 95% CI, 0.663–0.718). The optimal cutoff of LAD was 0.7. Conclusion: In addition to its easy and simple calculability relative to the SOFA, the prognostic performance of LAD was superior to maximum lactate levels for predicting in-hospital mortality and 90-day survival in adult patients with sepsis.
- 12 November 2021
- Published by Elsevier
- p. 273-280
Problems with epidural catheter
- 20 August 2020
- Published by Wolters Kluwer Health in Shock
- Vol. 56 (1) , 150-151
Prognostic Value of the Lactate–Albumin Difference in Predicting 30-Day Mortality in Critically Ill Patients
An abstract is unavailable. This article is available as a PDF only.
- 20 August 2020
- Published by Wolters Kluwer Health in Shock
- Vol. 56 (1) , 150-151
Prognostic Value of the Lactate–Albumin Difference in Predicting 30-Day Mortality in Critically Ill Patients
An abstract is unavailable. This article is available as a PDF only.
- 31 May 2020
- Published by Marmara University in Marmara Medical Journal
- Vol. 33 (2) , 54-60
The effects of pneumoperitoneum and patient position on the perfusion index and pleth variability index during laparoscopic bariatric surgery
Objective: Limited data are available on the use of the perfusion index (PI) and the pleth variability index (PVI) during laparoscopic bariatric surgery. We investigated the effects of pneumoperitoneum and the reverse Trendelenburg position on these indices. Materials and Methods: PI, PVI, heart rate (HR), blood pressure, SpO2 and ventilation parameters were recorded before anaesthesia induction (T0), 5 min after endotracheal intubation (T1), immediately before surgery, after the patient had been in the reverse Trendelenburg position for 5 min (T2), after inflating the abdomen with CO2 in reverse Trendelenburg (T3), after the abdomen had been deflated (T4) and 5 min after extubation (T5). Results: General anaesthesia induced an increase in the PI (P<.001), and a decrease in the PVI (P=.002). The PI and PVI values were not affected during T2 or T3. Pneumoperitoneum caused an increase in mean arterial pressure (MAP) and a decrease in HR. PVI and MAP decreased during T4, but the PI and HR remained unchanged. PVI, HR and MAP increased during T5. Conclusion: Our data suggest that the reverse Trendelenburg position and pneumoperitoneum did not affect the PI or PVI values, whereas deflation decreased the PVI in morbidly obese patients under general anaesthesia.
- 31 May 2020
- Published by Marmara University in Marmara Medical Journal
- Vol. 33 (2) , 54-60
The effects of pneumoperitoneum and patient position on the perfusion index and pleth variability index during laparoscopic bariatric surgery
Objective: Limited data are available on the use of the perfusion index (PI) and the pleth variability index (PVI) during laparoscopic bariatric surgery. We investigated the effects of pneumoperitoneum and the reverse Trendelenburg position on these indices. Materials and Methods: PI, PVI, heart rate (HR), blood pressure, SpO2 and ventilation parameters were recorded before anaesthesia induction (T0), 5 min after endotracheal intubation (T1), immediately before surgery, after the patient had been in the reverse Trendelenburg position for 5 min (T2), after inflating the abdomen with CO2 in reverse Trendelenburg (T3), after the abdomen had been deflated (T4) and 5 min after extubation (T5). Results: General anaesthesia induced an increase in the PI (P<.001), and a decrease in the PVI (P=.002). The PI and PVI values were not affected during T2 or T3. Pneumoperitoneum caused an increase in mean arterial pressure (MAP) and a decrease in HR. PVI and MAP decreased during T4, but the PI and HR remained unchanged. PVI, HR and MAP increased during T5. Conclusion: Our data suggest that the reverse Trendelenburg position and pneumoperitoneum did not affect the PI or PVI values, whereas deflation decreased the PVI in morbidly obese patients under general anaesthesia.
- Open Access
- 20 February 2020
- Published by Turkish Society of Intensive Care in Turkish Journal of Intensive Care
- Vol. 18 (1) , 35-42
Renal Resistive Index is Unsusceptible to Systemic Hemodynamics in Fluid Responsive Critically Ill Patients
Amaç: Kritik hastalarda sıvı resüsitasyonunun temel hedefi oksijen sunumunu artırarak organ perfüzyonunun sürdürülmesidir. Yoğun bakımda sıvı tedavisi renal monitorizasyon ilişkisi önemli olup, erken fazda sıvı tedavisine böbreğin yanıtı ile ilişkili literatür bilgisi kısıtlıdır. Bu çalışmada sıvı yanıtlı kritik yoğun bakım hastalarında sıvı replasmanından sonra renal rezistif indeks (RRI) değişimi ve bu değişimin hemodinamik parametrelerle olan ilişkinin değerlendirilmesi amaçlandı. Gereç ve Yöntem: Mekanik ventilasyon desteği altında 18 yaşından büyük, sedatize ve sıvı yanıtlı 20 hasta prospektif olarak çalışmaya dahil edildi. Pasif bacak kaldırma testi sonrası non-invaziv kardiyak monitörizasyon cihazında kardiyak outputta (CO) %10 ve daha fazla artış gösterenler sıvı yanıtlı olarak kabul edildi. Bu hastalara 30 dakika içersinde 500 mL izotonik solüsyonu intravenöz verildi. CO ölçümleri 0., 1. ve 30. dakikalarda yapıldı. RRI ve ortalama arteryal basınç (OAB) değerlerinin ölçümleri 0. ve 30. dakikalarda alındı. İstatiksel analiz için tekrarlayan ANOVA yöntemi uygulandı ve p
- 20 February 2020
- Published by Turkish Society of Intensive Care in Turkish Journal of Intensive Care
- Vol. 18 (1) , 35-42
Open AccessRenal Resistive Index is Unsusceptible to Systemic Hemodynamics in Fluid Responsive Critically Ill Patients
Amaç: Kritik hastalarda sıvı resüsitasyonunun temel hedefi oksijen sunumunu artırarak organ perfüzyonunun sürdürülmesidir. Yoğun bakımda sıvı tedavisi renal monitorizasyon ilişkisi önemli olup, erken fazda sıvı tedavisine böbreğin yanıtı ile ilişkili literatür bilgisi kısıtlıdır. Bu çalışmada sıvı yanıtlı kritik yoğun bakım hastalarında sıvı replasmanından sonra renal rezistif indeks (RRI) değişimi ve bu değişimin hemodinamik parametrelerle olan ilişkinin değerlendirilmesi amaçlandı. Gereç ve Yöntem: Mekanik ventilasyon desteği altında 18 yaşından büyük, sedatize ve sıvı yanıtlı 20 hasta prospektif olarak çalışmaya dahil edildi. Pasif bacak kaldırma testi sonrası non-invaziv kardiyak monitörizasyon cihazında kardiyak outputta (CO) %10 ve daha fazla artış gösterenler sıvı yanıtlı olarak kabul edildi. Bu hastalara 30 dakika içersinde 500 mL izotonik solüsyonu intravenöz verildi. CO ölçümleri 0., 1. ve 30. dakikalarda yapıldı. RRI ve ortalama arteryal basınç (OAB) değerlerinin ölçümleri 0. ve 30. dakikalarda alındı. İstatiksel analiz için tekrarlayan ANOVA yöntemi uygulandı ve p
- Open Access
- 1 February 2020
- Published by Wolters Kluwer Health in Anesthesia & Analgesia
- Vol. 130 (2) , e37
Sepsis Management in Resource-Limited Settings
- 1 February 2020
- Published by Wolters Kluwer Health in Anesthesia & Analgesia
- Vol. 130 (2) , e37
Open AccessSepsis Management in Resource-Limited Settings