Prashanth Panduranga
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Prashanth Panduranga has a total of 362 co-authors. Here are the top co-authors by number of shared publications:
Kadhim Sulaiman
Department of Cardiology, Royal Hospital, and Director General of Specialized Medical Care, Ministry of Health, Muscat, Oman
24 shared publicationsMohammed Al-Mukhaini
Department of Cardiology, National Heart Center, Royal Hospital, Muscat, Sultanate of Oman
23 shared publications- Ibrahim Al-Zakwani
Department of Pharmacology and Clinical Pharmacy, College of Medicine and Health Sciences, Sultan Qaboos University, Muscat, Oman
18 shared publications Haitham Amin
Mohammed Bin Khalifa Bin Salman Al Khalifa Specialist Cardiac Centre, Awali, Bahrain
17 shared publications- Jassim Al Suwaidi
Hamad Medical Corporation, Doha, Qatar
17 shared publications - Khalid F. AlHabib
Affiliation Department of Cardiac Sciences, King Fahad Cardiac Center, College of Medicine, King Saud University, Riyadh, Saudi Arabia
12 shared publications
Latest Publications
- Open Access
- 10 October 2026
- Published by SAGE Publications in Indian Journal of Clinical Cardiology
Ticagrelor-induced Central Sleep Apnea Syndrome in a Ventilated Patient
Ticagrelor is an orally administered P2Y12-receptor antagonist with more potent inhibition of platelet aggregation than clopidogrel. There is an association between ticagrelor use and dyspnea. We present a complex patient with stent thrombosis on clopidogrel and multiple comorbidities who was initiated on ticagrelor, with subsequent development of central sleep apnea, though reported in the literature but was not considered the cause of central sleep apnea initially. This adverse effect was suspected late, as he was unable to be weaned off the ventilator and had documented apnea events. On discontinuing ticagrelor, apnea episodes ceased. This case cautions cardiologists and other physicians about this rare complication of ticagrelor, which needs to be considered as a possible cause of central sleep apnea in patients on a ventilator with difficult weaning.
- 10 October 2026
- Published by SAGE Publications in Indian Journal of Clinical Cardiology
Open AccessTicagrelor-induced Central Sleep Apnea Syndrome in a Ventilated Patient
Ticagrelor is an orally administered P2Y12-receptor antagonist with more potent inhibition of platelet aggregation than clopidogrel. There is an association between ticagrelor use and dyspnea. We present a complex patient with stent thrombosis on clopidogrel and multiple comorbidities who was initiated on ticagrelor, with subsequent development of central sleep apnea, though reported in the literature but was not considered the cause of central sleep apnea initially. This adverse effect was suspected late, as he was unable to be weaned off the ventilator and had documented apnea events. On discontinuing ticagrelor, apnea episodes ceased. This case cautions cardiologists and other physicians about this rare complication of ticagrelor, which needs to be considered as a possible cause of central sleep apnea in patients on a ventilator with difficult weaning.
- Open Access
- 20 May 2026
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 10, e79678
Postangiography Prediction of Renal Replacement Therapy in Acute Myocardial Infarction–Related Cardiogenic Shock: Least Absolute Shrinkage and Selection Operator Nomogram Development and Validation
Background: Acute kidney injury critically impacts outcomes in cardiogenic shock secondary to acute myocardial infarction (CS-AMI). Acute kidney injury is one of the strongest independent predictors of in-hospital mortality in CS-AMI. Despite evidence that early renal replacement therapy (RRT) initiation improves survival, comprehensive prediction models for RRT in this population remain lacking. Objective: This study aimed to develop and internally validate a Least Absolute Shrinkage and Selection Operator (LASSO) regression–based prediction model and clinical nomogram for in-hospital RRT in patients with CS-AMI. Methods: This multicenter retrospective cohort study included 1431 patients with CS-AMI from the Gulf Cardiogenic Shock (Gulf-CS) registry across 13 centers in 6 Gulf countries (2020‐2022). LASSO logistic regression was applied to a training set (1071/1431, 80%) to select baseline predictors of RRT; performance was evaluated on a held-out testing set (268/1431, 20%). Internal validation included 10-fold cross-validation and bootstrapping (1000 iterations). Cluster-robust SEs accounted for center effects. The model was compared to a parsimonious model (age+creatinine clearance), and a clinical nomogram was developed. Results: Of 1431 patients, 190 (13.3%) required RRT. Patients requiring RRT were significantly older (mean 64.17, SD 12.14 y vs mean 59.75, SD 11.77 y; P <.001), with higher prevalences of diabetes mellitus (72.1% vs 61.9%; P =.008), peripheral arterial disease (11.6% vs 3.7%; P <.001), and prior cerebrovascular accident (11.1% vs 5.7%; P =.005). The RRT group had lower creatinine clearance (46 vs 72 mL/min; P <.001), higher baseline lactate (2.7 vs 2.1 mmol/L; P <.001), and more advanced Society for Cardiovascular Angiography and Interventions (SCAI) shock stages (stages D and E: 90.5% vs 64.9%; P <.001). LASSO selected 15 baseline predictors. The model achieved an area under the receiver operating characteristic curve (AUC) of 0.714 on the testing set, significantly outperforming the parsimonious model (AUC: 0.624; P <.001). Bootstrap-corrected AUC was 0.745 (95% CI 0.730‐0.756). In-hospital mortality was markedly higher in the RRT group (75.8% vs 38.8%; P <.001), with longer hospital stay (10 vs 6 d; P <.001), more major bleeding (16.8% vs 7.3%; P <.001), and cerebrovascular accidents (11.1% vs 4.9%; P =.001). Conclusions: We have developed and internally validated a robust 15-variable nomogram (Gulf-CS-Nomogram) that accurately predicts the need for RRT in patients with CS-AMI using baseline data intended for use after coronary angiography. This tool may facilitate early nephrology consultation and timely RRT initiation to improve outcomes.
- 20 May 2026
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 10, e79678
Open AccessPostangiography Prediction of Renal Replacement Therapy in Acute Myocardial Infarction–Related Cardiogenic Shock: Least Absolute Shrinkage and Selection Operator Nomogram Development and Validation
Background: Acute kidney injury critically impacts outcomes in cardiogenic shock secondary to acute myocardial infarction (CS-AMI). Acute kidney injury is one of the strongest independent predictors of in-hospital mortality in CS-AMI. Despite evidence that early renal replacement therapy (RRT) initiation improves survival, comprehensive prediction models for RRT in this population remain lacking. Objective: This study aimed to develop and internally validate a Least Absolute Shrinkage and Selection Operator (LASSO) regression–based prediction model and clinical nomogram for in-hospital RRT in patients with CS-AMI. Methods: This multicenter retrospective cohort study included 1431 patients with CS-AMI from the Gulf Cardiogenic Shock (Gulf-CS) registry across 13 centers in 6 Gulf countries (2020‐2022). LASSO logistic regression was applied to a training set (1071/1431, 80%) to select baseline predictors of RRT; performance was evaluated on a held-out testing set (268/1431, 20%). Internal validation included 10-fold cross-validation and bootstrapping (1000 iterations). Cluster-robust SEs accounted for center effects. The model was compared to a parsimonious model (age+creatinine clearance), and a clinical nomogram was developed. Results: Of 1431 patients, 190 (13.3%) required RRT. Patients requiring RRT were significantly older (mean 64.17, SD 12.14 y vs mean 59.75, SD 11.77 y; P <.001), with higher prevalences of diabetes mellitus (72.1% vs 61.9%; P =.008), peripheral arterial disease (11.6% vs 3.7%; P <.001), and prior cerebrovascular accident (11.1% vs 5.7%; P =.005). The RRT group had lower creatinine clearance (46 vs 72 mL/min; P <.001), higher baseline lactate (2.7 vs 2.1 mmol/L; P <.001), and more advanced Society for Cardiovascular Angiography and Interventions (SCAI) shock stages (stages D and E: 90.5% vs 64.9%; P <.001). LASSO selected 15 baseline predictors. The model achieved an area under the receiver operating characteristic curve (AUC) of 0.714 on the testing set, significantly outperforming the parsimonious model (AUC: 0.624; P <.001). Bootstrap-corrected AUC was 0.745 (95% CI 0.730‐0.756). In-hospital mortality was markedly higher in the RRT group (75.8% vs 38.8%; P <.001), with longer hospital stay (10 vs 6 d; P <.001), more major bleeding (16.8% vs 7.3%; P <.001), and cerebrovascular accidents (11.1% vs 4.9%; P =.001). Conclusions: We have developed and internally validated a robust 15-variable nomogram (Gulf-CS-Nomogram) that accurately predicts the need for RRT in patients with CS-AMI using baseline data intended for use after coronary angiography. This tool may facilitate early nephrology consultation and timely RRT initiation to improve outcomes.
- Open Access
- 1 January 2026
- Published by Wolters Kluwer Health in Annals of Clinical Cardiology
- Vol. 8 (1) , 18-29
Aortic Regurgitation Quantification, Management, and Guidelines: A 2026 Update
We sought to compare recommendations from the European Society of Cardiology and the American College of Cardiology/American Heart Association guidelines, for the diagnosis and management of aortic regurgitation (AR), a major cause of valvular heart disease. Both guidelines agreed on a multidisciplinary approach to grade the mechanism and severity of AR. In both guidelines, surgical aortic valve (AV) replacement remains the predominant treatment modality after the surgical risk profile has been determined. Trans-catheter AV implantation is an alternative, but further data are needed to determine its efficacy. This review article focuses on AR and describes the prevalence, mechanisms, diagnosis, and treatment of AR.
- 1 January 2026
- Published by Wolters Kluwer Health in Annals of Clinical Cardiology
- Vol. 8 (1) , 18-29
Open AccessAortic Regurgitation Quantification, Management, and Guidelines: A 2026 Update
We sought to compare recommendations from the European Society of Cardiology and the American College of Cardiology/American Heart Association guidelines, for the diagnosis and management of aortic regurgitation (AR), a major cause of valvular heart disease. Both guidelines agreed on a multidisciplinary approach to grade the mechanism and severity of AR. In both guidelines, surgical aortic valve (AV) replacement remains the predominant treatment modality after the surgical risk profile has been determined. Trans-catheter AV implantation is an alternative, but further data are needed to determine its efficacy. This review article focuses on AR and describes the prevalence, mechanisms, diagnosis, and treatment of AR.
- Open Access
- 1 January 2026
- Published by Wolters Kluwer Health in QAI Journal for Healthcare Quality and Patient Safety
- Vol. 7 (1) , 14-17
Use of Messaging App in Reducing Outpatient Visits and Waiting Time for Re-prescription in a Tertiary Hospital Cardiology Clinic in Oman: An Audit
Introduction: Stable cardiac patients after their visit at cardiology outpatient department (OPD) clinic are given a referral letter to follow-up in local health centers for their monthly medications. However, majority come as walk-in for medications which causes overcrowding. Objective: The aim of this quality-improvement project was to evaluate use of a messaging App in reducing outpatient visits for patient’s re-prescription. Methods: We used a messaging App to communicate between patients and pharmacy. We employed Lean and Six Sigma quality improvement methodologies such as value-stream mapping (VSM), a lean manufacturing technique to compare project efficiency before and after implementation of a messaging App to dispense monthly refill medications. Results: Patients spent about 109 min (total lead time), when they come to the clinic without an appointment. The ratio of value added time (VAD) to lead time was 17% (VAD %). After initiation of the project, patients spent about 9 min (total lead time). The ratio of VAD to lead time was 80% (VAD %). Two hundred and four patients attended the OPD for prescriptions in the 1 st month which reduced every month and finally to 0 in the following month’s, i.e., 100% reduction. Simultaneously, the messaging App pharmacy request messages/dispensation increased from 32 to 150 numbers by the end of the 8 th month, i.e. from 18% to 87%. Conclusions: The use of a messaging App for monthly medication refill eliminated walk-in OPD visits and significantly reduced total waiting time by 90%.
- 1 January 2026
- Published by Wolters Kluwer Health in QAI Journal for Healthcare Quality and Patient Safety
- Vol. 7 (1) , 14-17
Open AccessUse of Messaging App in Reducing Outpatient Visits and Waiting Time for Re-prescription in a Tertiary Hospital Cardiology Clinic in Oman: An Audit
Introduction: Stable cardiac patients after their visit at cardiology outpatient department (OPD) clinic are given a referral letter to follow-up in local health centers for their monthly medications. However, majority come as walk-in for medications which causes overcrowding. Objective: The aim of this quality-improvement project was to evaluate use of a messaging App in reducing outpatient visits for patient’s re-prescription. Methods: We used a messaging App to communicate between patients and pharmacy. We employed Lean and Six Sigma quality improvement methodologies such as value-stream mapping (VSM), a lean manufacturing technique to compare project efficiency before and after implementation of a messaging App to dispense monthly refill medications. Results: Patients spent about 109 min (total lead time), when they come to the clinic without an appointment. The ratio of value added time (VAD) to lead time was 17% (VAD %). After initiation of the project, patients spent about 9 min (total lead time). The ratio of VAD to lead time was 80% (VAD %). Two hundred and four patients attended the OPD for prescriptions in the 1 st month which reduced every month and finally to 0 in the following month’s, i.e., 100% reduction. Simultaneously, the messaging App pharmacy request messages/dispensation increased from 32 to 150 numbers by the end of the 8 th month, i.e. from 18% to 87%. Conclusions: The use of a messaging App for monthly medication refill eliminated walk-in OPD visits and significantly reduced total waiting time by 90%.
- Open Access
Comparative outcomes of culprit-only versus complete revascularisation in cardiogenic shock complicating acute myocardial infarction: insights from the Gulf-Cardiogenic Shock registry
Objectives To compare in-hospital and long-term outcomes between culprit-only percutaneous coronary intervention (PCI) and multivessel PCI in patients with acute myocardial infarction complicated by cardiogenic shock and multivessel coronary artery disease. Design Retrospective subgroup analysis of the multicentre Gulf-Cardiogenic Shock registry. Setting 13 tertiary care centres across six Gulf countries (Saudi Arabia, Qatar, Oman, UAE, Kuwait and Bahrain) between January 2020 and December 2022. Participants 961 patients with angiographically confirmed multivessel coronary artery disease who underwent PCI were included from the Gulf-Cardiogenic Shock registry. Patients were divided into culprit-only PCI group (n=792, 82.4%) and multivessel PCI group (n=169, 17.6%). Patients with single-vessel disease were excluded. Interventions Patients underwent either culprit-only PCI (intervention limited to the culprit artery) or multivessel PCI (immediate intervention to both culprit and non-culprit arteries during the same procedure). Primary and secondary outcome measures The primary outcome was in-hospital all-cause mortality. Secondary outcomes included reinfarction, cerebrovascular accident, major and minor bleeding events, target lesion revascularisation, target vessel revascularisation, hospital stay duration and freedom from major adverse cardiac and cerebrovascular events (MACCEs) at 6 and 12 months. Results Hospital mortality was comparable between multivessel PCI and culprit-only PCI groups (43.2% vs 46.1%; p=0.493). Freedom from MACCE rates at 6 and 12 months were 62% and 46% for multivessel PCI versus 70% and 49% for culprit-only PCI, respectively (log-rank p=0.711). Subgroup analysis revealed that culprit-only PCI was associated with increased hospital mortality in patients older than 70 years (OR 1.55, 95% CI: 1.01 to 2.39). Multivariable analysis of the interaction between revascularisation strategy and the subgroups revealed that culprit vessel revascularisation was associated with increased mortality in patients with left main disease (OR: 1.99 (95% CI: 1.22 to 3.27), p=0.006) and left anterior descending lesions (OR: 1.54 (95% CI: 1.06 to 2.25), p=0.025). Conclusions No statistically significant differences in hospital mortality or long-term MACCE-free survival were observed between culprit-only PCI and multivessel PCI strategies in patients with cardiogenic shock complicating acute myocardial infarction. However, patients older than 70 years may benefit from a multivessel PCI approach. These findings support current guideline recommendations favouring culprit-only PCI due to reduced procedural complexity while highlighting the need for individualised treatment strategies based on patient age and clinical factors. Further prospective randomised studies are needed to validate these age-specific findings and identify optimal patient selection criteria for each revascularisation strategy.
Open AccessComparative outcomes of culprit-only versus complete revascularisation in cardiogenic shock complicating acute myocardial infarction: insights from the Gulf-Cardiogenic Shock registry
Objectives To compare in-hospital and long-term outcomes between culprit-only percutaneous coronary intervention (PCI) and multivessel PCI in patients with acute myocardial infarction complicated by cardiogenic shock and multivessel coronary artery disease. Design Retrospective subgroup analysis of the multicentre Gulf-Cardiogenic Shock registry. Setting 13 tertiary care centres across six Gulf countries (Saudi Arabia, Qatar, Oman, UAE, Kuwait and Bahrain) between January 2020 and December 2022. Participants 961 patients with angiographically confirmed multivessel coronary artery disease who underwent PCI were included from the Gulf-Cardiogenic Shock registry. Patients were divided into culprit-only PCI group (n=792, 82.4%) and multivessel PCI group (n=169, 17.6%). Patients with single-vessel disease were excluded. Interventions Patients underwent either culprit-only PCI (intervention limited to the culprit artery) or multivessel PCI (immediate intervention to both culprit and non-culprit arteries during the same procedure). Primary and secondary outcome measures The primary outcome was in-hospital all-cause mortality. Secondary outcomes included reinfarction, cerebrovascular accident, major and minor bleeding events, target lesion revascularisation, target vessel revascularisation, hospital stay duration and freedom from major adverse cardiac and cerebrovascular events (MACCEs) at 6 and 12 months. Results Hospital mortality was comparable between multivessel PCI and culprit-only PCI groups (43.2% vs 46.1%; p=0.493). Freedom from MACCE rates at 6 and 12 months were 62% and 46% for multivessel PCI versus 70% and 49% for culprit-only PCI, respectively (log-rank p=0.711). Subgroup analysis revealed that culprit-only PCI was associated with increased hospital mortality in patients older than 70 years (OR 1.55, 95% CI: 1.01 to 2.39). Multivariable analysis of the interaction between revascularisation strategy and the subgroups revealed that culprit vessel revascularisation was associated with increased mortality in patients with left main disease (OR: 1.99 (95% CI: 1.22 to 3.27), p=0.006) and left anterior descending lesions (OR: 1.54 (95% CI: 1.06 to 2.25), p=0.025). Conclusions No statistically significant differences in hospital mortality or long-term MACCE-free survival were observed between culprit-only PCI and multivessel PCI strategies in patients with cardiogenic shock complicating acute myocardial infarction. However, patients older than 70 years may benefit from a multivessel PCI approach. These findings support current guideline recommendations favouring culprit-only PCI due to reduced procedural complexity while highlighting the need for individualised treatment strategies based on patient age and clinical factors. Further prospective randomised studies are needed to validate these age-specific findings and identify optimal patient selection criteria for each revascularisation strategy.
- Open Access
Timing of mechanical ventilation and its association with in-hospital outcomes in patients with cardiogenic shock following ST-elevation myocardial infarction: a multicentre observational study
Objective To evaluate the association between the timing of invasive mechanical ventilation (MV) initiation and clinical outcomes in patients with cardiogenic shock (CS) secondary to ST-elevation myocardial infarction (STEMI). Design Retrospective analysis of a multicentre registry. Setting Data were obtained from the Gulf-Cardiogenic Shock registry, which includes hospitals across six countries in the Middle East. Participants 1117 patients diagnosed with STEMI and CS. Of these, 672 (60%) required MV and were included in this analysis. Primary and secondary outcome measures The primary outcome was in-hospital mortality. Secondary outcomes included comparisons of baseline characteristics, Society of Coronary Angiogram and Intervention (SCAI) shock stage, and clinical parameters among groups based on time to MV. Results Participants were categorised by time from shock diagnosis to MV: early (≤15 min), intermediate (30 min) and late (≥60 min). Median times were 15 min (IQR 10–20), 30 min (IQR 25–35) and 60 min (IQR 45–70), respectively. Baseline characteristics were comparable across groups. Increased delay in MV was associated with a higher mortality risk during the first 60 min post-diagnosis, beyond which the risk plateaued. Delayed MV was an independent predictor of in-hospital mortality (OR 2.14, 95% CI 1.36 to 3.38, pConclusions Early initiation of MV in patients with STEMI complicated by CS was associated with lower in-hospital mortality. These findings highlight the importance of timely respiratory support, warranting further investigation in prospective or randomised controlled studies.
Open AccessTiming of mechanical ventilation and its association with in-hospital outcomes in patients with cardiogenic shock following ST-elevation myocardial infarction: a multicentre observational study
Objective To evaluate the association between the timing of invasive mechanical ventilation (MV) initiation and clinical outcomes in patients with cardiogenic shock (CS) secondary to ST-elevation myocardial infarction (STEMI). Design Retrospective analysis of a multicentre registry. Setting Data were obtained from the Gulf-Cardiogenic Shock registry, which includes hospitals across six countries in the Middle East. Participants 1117 patients diagnosed with STEMI and CS. Of these, 672 (60%) required MV and were included in this analysis. Primary and secondary outcome measures The primary outcome was in-hospital mortality. Secondary outcomes included comparisons of baseline characteristics, Society of Coronary Angiogram and Intervention (SCAI) shock stage, and clinical parameters among groups based on time to MV. Results Participants were categorised by time from shock diagnosis to MV: early (≤15 min), intermediate (30 min) and late (≥60 min). Median times were 15 min (IQR 10–20), 30 min (IQR 25–35) and 60 min (IQR 45–70), respectively. Baseline characteristics were comparable across groups. Increased delay in MV was associated with a higher mortality risk during the first 60 min post-diagnosis, beyond which the risk plateaued. Delayed MV was an independent predictor of in-hospital mortality (OR 2.14, 95% CI 1.36 to 3.38, pConclusions Early initiation of MV in patients with STEMI complicated by CS was associated with lower in-hospital mortality. These findings highlight the importance of timely respiratory support, warranting further investigation in prospective or randomised controlled studies.
- Top Cited PapersOpen Access
- 19 February 2025
- Published by Ubiquity Press, Ltd. in Global Heart
- Vol. 20 (1) , 15
Cardiovascular Effects of Smoking and Smoking Cessation: A 2024 Update
Smoking is a significant risk factor for both acute and chronic cardiovascular diseases. These diseases contribute to approximately twenty percent of all-cause mortality. Research indicates that quitting smoking can substantially reduce or even reverse the harmful effects associated with smoking on cardiovascular health. Notably, these benefits can be observed in a relatively short period compared to the duration of smoking history. This article aims to provide data to understand the effects of smoking on the cardiovascular system locally as well as its effects as a pandemic globally and hence provide comprehensive strategies in the management of cardiovascular patients for smoking cessation.
- 19 February 2025
- Published by Ubiquity Press, Ltd. in Global Heart
- Vol. 20 (1) , 15
Top Cited PapersOpen AccessCardiovascular Effects of Smoking and Smoking Cessation: A 2024 Update
Smoking is a significant risk factor for both acute and chronic cardiovascular diseases. These diseases contribute to approximately twenty percent of all-cause mortality. Research indicates that quitting smoking can substantially reduce or even reverse the harmful effects associated with smoking on cardiovascular health. Notably, these benefits can be observed in a relatively short period compared to the duration of smoking history. This article aims to provide data to understand the effects of smoking on the cardiovascular system locally as well as its effects as a pandemic globally and hence provide comprehensive strategies in the management of cardiovascular patients for smoking cessation.
- Open Access
- 1 January 2025
- Published by Wolters Kluwer Health in Annals of Clinical Cardiology
- Vol. 7 (1) , 59-60
Critical Review of “Mortality and Morbidity in Acute Heart Failure: A Critical Examination of Gulf CARE Registry Data”: Authors Response
An abstract is unavailable. This article is available as a PDF only.
- 1 January 2025
- Published by Wolters Kluwer Health in Annals of Clinical Cardiology
- Vol. 7 (1) , 59-60
Open AccessCritical Review of “Mortality and Morbidity in Acute Heart Failure: A Critical Examination of Gulf CARE Registry Data”: Authors Response
An abstract is unavailable. This article is available as a PDF only.
- Open Access
- 19 November 2024
- Published by Elsevier in Journal of the Society for Cardiovascular Angiography & Interventions
- Vol. 4 (1) , 102461
The Utility and Validation of SCAI-CSWG Stages in Patients With Acute Myocardial Infarction-Related Cardiogenic Shock
- 19 November 2024
- Published by Elsevier in Journal of the Society for Cardiovascular Angiography & Interventions
- Vol. 4 (1) , 102461
Open AccessThe Utility and Validation of SCAI-CSWG Stages in Patients With Acute Myocardial Infarction-Related Cardiogenic Shock
- Open Access
- 8 August 2024
- Published by Wolters Kluwer Health in International Journal of Surgery
- Vol. 110 (11) , 7142-7149
Leveraging machine learning to enhance postoperative risk assessment in coronary artery bypass grafting patients with unprotected left main disease: a retrospective cohort study
Background: Risk stratification for patients undergoing coronary artery bypass surgery (CABG) for left main coronary artery (LMCA) disease is essential for informed decision-making. This study explored the potential of machine learning (ML) methods to identify key risk factors associated with mortality in this patient group. Methods: This retrospective cohort study was conducted on 866 patients from the Gulf Left Main Registry who presented between 2015 and 2019. The study outcome was hospital all-cause mortality. Various machine learning models [logistic regression, random forest (RF), k-nearest neighbor, support vector machine, naïve Bayes, multilayer perception, boosting] were used to predict mortality, and their performance was measured using accuracy, precision, recall, F1 score, and area under the receiver operator characteristic curve (AUC). Results: Nonsurvivors had significantly greater EuroSCORE II values (1.84 (10.08–3.67) vs. 4.75 (2.54–9.53) %, PP<0.001), with an AUC of 0.736. RF achieved the best ML performance (accuracy=98, precision=100, recall=97, and F1 score=98). Explainable artificial intelligence using SHAP demonstrated the most important features as follows: preoperative lactate level, emergency surgery, chronic kidney disease (CKD), NSTEMI, nonsmoking status, and sex. QLattice identified lactate and CKD as the most important factors for predicting hospital mortality this patient group. Conclusion: This study demonstrates the potential of ML, particularly the Random Forest, to accurately predict hospital mortality in patients undergoing CABG for LMCA disease and its superiority over traditional methods. The key risk factors identified, including preoperative lactate levels, emergency surgery, chronic kidney disease, NSTEMI, nonsmoking status, and sex, provide valuable insights for risk stratification and informed decision-making in this high-risk patient population. Additionally, incorporating newly identified risk factors into future risk-scoring systems can further improve mortality prediction accuracy.
- 8 August 2024
- Published by Wolters Kluwer Health in International Journal of Surgery
- Vol. 110 (11) , 7142-7149
Open AccessLeveraging machine learning to enhance postoperative risk assessment in coronary artery bypass grafting patients with unprotected left main disease: a retrospective cohort study
Background: Risk stratification for patients undergoing coronary artery bypass surgery (CABG) for left main coronary artery (LMCA) disease is essential for informed decision-making. This study explored the potential of machine learning (ML) methods to identify key risk factors associated with mortality in this patient group. Methods: This retrospective cohort study was conducted on 866 patients from the Gulf Left Main Registry who presented between 2015 and 2019. The study outcome was hospital all-cause mortality. Various machine learning models [logistic regression, random forest (RF), k-nearest neighbor, support vector machine, naïve Bayes, multilayer perception, boosting] were used to predict mortality, and their performance was measured using accuracy, precision, recall, F1 score, and area under the receiver operator characteristic curve (AUC). Results: Nonsurvivors had significantly greater EuroSCORE II values (1.84 (10.08–3.67) vs. 4.75 (2.54–9.53) %, PP<0.001), with an AUC of 0.736. RF achieved the best ML performance (accuracy=98, precision=100, recall=97, and F1 score=98). Explainable artificial intelligence using SHAP demonstrated the most important features as follows: preoperative lactate level, emergency surgery, chronic kidney disease (CKD), NSTEMI, nonsmoking status, and sex. QLattice identified lactate and CKD as the most important factors for predicting hospital mortality this patient group. Conclusion: This study demonstrates the potential of ML, particularly the Random Forest, to accurately predict hospital mortality in patients undergoing CABG for LMCA disease and its superiority over traditional methods. The key risk factors identified, including preoperative lactate levels, emergency surgery, chronic kidney disease, NSTEMI, nonsmoking status, and sex, provide valuable insights for risk stratification and informed decision-making in this high-risk patient population. Additionally, incorporating newly identified risk factors into future risk-scoring systems can further improve mortality prediction accuracy.