Search

Introduction: Abdominal aortic aneurysm (AAA), often characterized by an abdominal aortic diameter over 3.0 cm, is managed through screening, surveillance, and surgical intervention. AAA growth can be heterogeneous and rupture carries a high mortality rate, with size and certain risk factors influencing rupture risk. Research is ongoing to accurately predict individual AAA growth rates for personalized management. Machine learning, a subset of artificial intelligence, has shown promise in various medical fields, including endoleak detection post-EVAR. However, its application for predicting AAA growth remains insufficiently explored, thus necessitating further investigation. Subsequently, this paper aims to summarize the current status of machine learning in predicting AAA growth. Evidence acquisition: A systematic database search of Embase, MEDLINE, Cochrane, PubMed and Google Scholar from inception till December 2022 was conducted of original articles that discussed the use of machine learning in predicting AAA growth using the aforementioned databases. Evidence synthesis: Overall, 2742 articles were extracted, of which seven retrospective studies involving 410 patients were included using a predetermined criteria. Six out of seven studies applied a supervised learning approach for their machine learning (ML) models, with considerable diversity observed within specific ML models. The majority of the studies concluded that machine learning models perform better in predicting AAA growth in comparison to reference models. All studies focused on predicting AAA growth over specified durations. Maximal luminal diameter was the most frequently used indicator, with alternative predictors being AAA volume, ILT (intraluminal thrombus) and flow-medicated diameter (FMD). Conclusions: The nascent field of applying machine learning (ML) for Abdominal Aortic Aneurysm (AAA) expansion prediction exhibits potential to enhance predictive accuracy across diverse parameters. Future st

Introduction: Abdominal aortic aneurysm (AAA), often characterized by an abdominal aortic diameter over 3.0 cm, is managed through screening, surveillance, and surgical intervention. AAA growth can be heterogeneous and rupture carries a high mortality rate, with size and certain risk factors influencing rupture risk. Research is ongoing to accurately predict individual AAA growth rates for personalized management. Machine learning, a subset of artificial intelligence, has shown promise in various medical fields, including endoleak detection post-EVAR. However, its application for predicting AAA growth remains insufficiently explored, thus necessitating further investigation. Subsequently, this paper aims to summarize the current status of machine learning in predicting AAA growth. Evidence acquisition: A systematic database search of Embase, MEDLINE, Cochrane, PubMed and Google Scholar from inception till December 2022 was conducted of original articles that discussed the use of machine learning in predicting AAA growth using the aforementioned databases. Evidence synthesis: Overall, 2742 articles were extracted, of which seven retrospective studies involving 410 patients were included using a predetermined criteria. Six out of seven studies applied a supervised learning approach for their machine learning (ML) models, with considerable diversity observed within specific ML models. The majority of the studies concluded that machine learning models perform better in predicting AAA growth in comparison to reference models. All studies focused on predicting AAA growth over specified durations. Maximal luminal diameter was the most frequently used indicator, with alternative predictors being AAA volume, ILT (intraluminal thrombus) and flow-medicated diameter (FMD). Conclusions: The nascent field of applying machine learning (ML) for Abdominal Aortic Aneurysm (AAA) expansion prediction exhibits potential to enhance predictive accuracy across diverse parameters. Future st

Background: The ideal timing of a durable assist device implantation in patients with end-stage heart failure presenting with INTERMACS profile I is still controversial. The data on extracorporeal life support (ECLS) bridge to durable left ventricular assist device (LVAD) in these patients is limited. Materials and methods: We retrospectively analyzed the outcomes of 35 patients in acute cardiogenic shock (CS) who, between December 2013 and September 2020, were bridged with ECLS to durable LVAD. The mean age was 52.3 +/- 12.0 years. The primary endpoints of this study were in-hospital, 30-day, 6-month, and 1-year mortality. The secondary endpoint was the development of any postoperative adverse events and other characteristics during the follow-up period. We also assessed the impact of the rescue ECLS on the recovery of the end-organ function. Results: In-hospital, 30-day, 6-month, and 1-year survival was 65.6%, 75.9%, 69.2%, and 62.7% respectively. The median time on ECLS was 7 days (IQR 5.0-13.0). We observed a high incidence of a severe right heart failure (22.9%), acute kidney injury on dialysis (68.6%), and respiratory failure (77.1%). Bridge with ECLS provided a significant recovery of liver and kidney function prior to durable LVAD implantation. Conclusion: The concept of bridging patients presenting in end-stage heart failure and cardiogenic shock with ECLS prior to durable LVAD implantation is a feasible method to ensure acceptable survival rates and significant recovery of the end-organ function.

Background Machine learning is a set of models and methods that can automatically detect patterns in vast amounts of data, extract information, and use it to perform decision-making under uncertain conditions. The potential of machine learning is significant, and breast surgeons must strive to be informed with up-to-date knowledge and its applications. Methods A systematic database search of Embase, MEDLINE, the Cochrane database, and Google Scholar, from inception to December 2021, was conducted of original articles that explored the use of machine learning and/or artificial intelligence in breast surgery in EMBASE, MEDLINE, Cochrane database and Google Scholar. Results The search yielded 477 articles, of which 14 studies were included in this review, featuring 73 847 patients. Four main areas of machine learning application were identified: predictive modelling of surgical outcomes; breast imaging-based context; screening and triaging of patients with breast cancer; and as network utility for detection. There is evident value of machine learning in preoperative planning and in providing information for surgery both in a cancer and an aesthetic context. Machine learning outperformed traditional statistical modelling in all studies for predicting mortality, morbidity, and quality of life outcomes. Machine learning patterns and associations could support planning, anatomical visualization, and surgical navigation. Conclusion Machine learning demonstrated promising applications for improving breast surgery outcomes and patient-centred care. Neveretheless, there remain important limitations and ethical concerns relating to implementing artificial intelligence into everyday surgical practices.

A systematic review evaluating the applications of machine learning in the field of breast surgery. We evaluate the current evidence and areas of application in order to improve patient outcomes. We further examine the limitations of the field and provide recommendations for future research in the field of machine learning and breast surgery. Background Machine learning is a set of models and methods that can automatically detect patterns in vast amounts of data, extract information, and use it to perform decision-making under uncertain conditions. The potential of machine learning is significant, and breast surgeons must strive to be informed with up-to-date knowledge and its applications. Methods A systematic database search of Embase, MEDLINE, the Cochrane database, and Google Scholar, from inception to December 2021, was conducted of original articles that explored the use of machine learning and/or artificial intelligence in breast surgery in EMBASE, MEDLINE, Cochrane database and Google Scholar. Results The search yielded 477 articles, of which 14 studies were included in this review, featuring 73 847 patients. Four main areas of machine learning application were identified: predictive modelling of surgical outcomes; breast imaging-based context; screening and triaging of patients with breast cancer; and as network utility for detection. There is evident value of machine learning in preoperative planning and in providing information for surgery both in a cancer and an aesthetic context. Machine learning outperformed traditional statistical modelling in all studies for predicting mortality, morbidity, and quality of life outcomes. Machine learning patterns and associations could support planning, anatomical visualization, and surgical navigation. Conclusion Machine learning demonstrated promising applications for improving breast surgery outcomes and patient-centred care. Neveretheless, there remain important limitations and ethical concerns relating to impleme

Background: The rapid development of transcatheter treatment methods has made transcatheter aortic valve replacement (TAVR) a feasible alternative to conventional surgical aortic valve replacement (SAVR). Recently, indications for TAVR have been expanded to intermediate- and low-risk patients, although there still remains a portion of ineligible patients. We sought to evaluate and compare our experience with sutureless SAVR and transapical TAVR in the grey-area of patients unsuitable for transfemoral access. Methods: Between April 2018 and June 2021, 248 consecutive patients underwent a sutureless SAVR (SU-SAVR) or TA-TAVR at our institution. We performed a pair-matched analysis and identified 56 patient pairs based on the EuroSCORE II. All transcatheter procedures were performed using SAPIEN XT/3 (TM) prostheses, while all surgical procedures deployed the Perceval (LivaNova) aortic valve. Results: All patients presented with multiple comorbidities as reflected by the median EuroSCORE-II of 3.1% (IQR 1.9-5.3). Thirty-four patients from the surgical group (60.7%) underwent a concomitant myocardial revascularization. There was no significant difference in major adverse events, pacemaker implantation or postoperative mortality during follow-up. Both interventions demonstrated technical success with similar mean postoperative pressure gradients at follow-up and no cases of paravalvular leakage. Conclusions: Sutureless aortic valve replacement constitutes a feasible treatment alternative for patients with aortic valve disease who are ineligible for transfemoral access route and/or require concomitant coronary revascularization. With its excellent hemodynamic performance, similar survival compared to TA-TAVR, and high cost-efficiency without compromising the postoperative outcomes and in-hospital length of stay SU-AVR might be considered for patients in the grey-area between TAVR and SAVR.

Background In the era of transcatheter methods, patients presenting with a pure aortic regurgitation (AR) are not considered eligible for transcatheter treatment and therefore require another less invasive surgical option. We sought to review our experience with sutureless aortic valve replacement (SU-AVR) in patients presenting with symptomatic pure AR, which until now is a contraindication for implementation of sutureless valve prostheses in Europe. Methods Between April 2018 and June 2021, 80 consecutive patients underwent a SU-AVR for various indications at our institution. We analyzed the outcomes and postoperative complications of 12 patients presenting with a pure severe AR undergoing SU-AVR using Perceval (Corcym). Results The mean age of the patients was 67 +/- 9.1 years old. All patients presented with symptomatic pure AR. Patients presented with multiple comorbidities as reflected by the mean EuroSCORE-II of 3.6 +/- 2.6%. Six patients (50%) underwent a concomitant CABG procedure. The mean operating- and cross clamp time was 127.25 +/- 45.9 and 40.33 +/- 17.3 min respectively. All isolated SU-AVR were performed via J-sternotomy or right anterolateral thoracotomy. There were no cases of device dislocation. No patients presented with a paravalvular leakage. We observed excellent mean postoperative pressure gradient at follow-up 5.7 +/- 1.5 mmHg. Conclusions Our experience with SU-AVR shows the feasibility of sutureless technologies in the aortic valve surgery due to pure AR. Besides the great technical success and excellent hemodynamics, SU-AVR in severe AR offers a great opportunity of reducing the invasivity of the surgical procedure and potentially reducing hospital cost without compromising the postoperative outcomes and in-hospital length of stay.

Background Machine learning is a set of models and methods that can automatically detect patterns in vast amounts of data, extract information, and use it to perform decision-making under uncertain conditions. The potential of machine learning is significant, and breast surgeons must strive to be informed with up-to-date knowledge and its applications. Methods A systematic database search of Embase, MEDLINE, the Cochrane database, and Google Scholar, from inception to December 2021, was conducted of original articles that explored the use of machine learning and/or artificial intelligence in breast surgery in EMBASE, MEDLINE, Cochrane database and Google Scholar. Results The search yielded 477 articles, of which 14 studies were included in this review, featuring 73 847 patients. Four main areas of machine learning application were identified: predictive modelling of surgical outcomes; breast imaging-based context; screening and triaging of patients with breast cancer; and as network utility for detection. There is evident value of machine learning in preoperative planning and in providing information for surgery both in a cancer and an aesthetic context. Machine learning outperformed traditional statistical modelling in all studies for predicting mortality, morbidity, and quality of life outcomes. Machine learning patterns and associations could support planning, anatomical visualization, and surgical navigation. Conclusion Machine learning demonstrated promising applications for improving breast surgery outcomes and patient-centred care. Neveretheless, there remain important limitations and ethical concerns relating to implementing artificial intelligence into everyday surgical practices.

Background: The ideal timing of a durable assist device implantation in patients with end-stage heart failure presenting with INTERMACS profile I is still controversial. The data on extracorporeal life support (ECLS) bridge to durable left ventricular assist device (LVAD) in these patients is limited. Materials and methods: We retrospectively analyzed the outcomes of 35 patients in acute cardiogenic shock (CS) who, between December 2013 and September 2020, were bridged with ECLS to durable LVAD. The mean age was 52.3 +/- 12.0 years. The primary endpoints of this study were in-hospital, 30-day, 6-month, and 1-year mortality. The secondary endpoint was the development of any postoperative adverse events and other characteristics during the follow-up period. We also assessed the impact of the rescue ECLS on the recovery of the end-organ function. Results: In-hospital, 30-day, 6-month, and 1-year survival was 65.6%, 75.9%, 69.2%, and 62.7% respectively. The median time on ECLS was 7 days (IQR 5.0-13.0). We observed a high incidence of a severe right heart failure (22.9%), acute kidney injury on dialysis (68.6%), and respiratory failure (77.1%). Bridge with ECLS provided a significant recovery of liver and kidney function prior to durable LVAD implantation. Conclusion: The concept of bridging patients presenting in end-stage heart failure and cardiogenic shock with ECLS prior to durable LVAD implantation is a feasible method to ensure acceptable survival rates and significant recovery of the end-organ function.

Background Machine learning is a set of models and methods that can automatically detect patterns in vast amounts of data, extract information, and use it to perform decision-making under uncertain conditions. The potential of machine learning is significant, and breast surgeons must strive to be informed with up-to-date knowledge and its applications. Methods A systematic database search of Embase, MEDLINE, the Cochrane database, and Google Scholar, from inception to December 2021, was conducted of original articles that explored the use of machine learning and/or artificial intelligence in breast surgery in EMBASE, MEDLINE, Cochrane database and Google Scholar. Results The search yielded 477 articles, of which 14 studies were included in this review, featuring 73 847 patients. Four main areas of machine learning application were identified: predictive modelling of surgical outcomes; breast imaging-based context; screening and triaging of patients with breast cancer; and as network utility for detection. There is evident value of machine learning in preoperative planning and in providing information for surgery both in a cancer and an aesthetic context. Machine learning outperformed traditional statistical modelling in all studies for predicting mortality, morbidity, and quality of life outcomes. Machine learning patterns and associations could support planning, anatomical visualization, and surgical navigation. Conclusion Machine learning demonstrated promising applications for improving breast surgery outcomes and patient-centred care. Neveretheless, there remain important limitations and ethical concerns relating to implementing artificial intelligence into everyday surgical practices.

Introduction Primary cardiac sarcomas (PCSs) are an extremely rare and aggressive type of malignancies that have been described only by a limited number of observational studies. This study aimed to evaluate the currently existing evidence comparing surgical to multimodality treatment of PCS. Methods We systematically reviewed Embase, MEDLINE, Cochrane Database, and Google Scholar, from inception to December 2020, for original articles about surgical and multimodality treatment of PCS. The outcomes included were mortality at various time points, resection margin status, and mean estimated survival. The pooled treatment effects were calculated using a random-effects model. Results Ten studies including a total of 1570 patients met our inclusion criteria. Surgery was associated with significantly lower mortality when compared to conservative treatment at 1, 2, and 3 years, whereas no significant difference was found at 5 years. Furthermore, multimodality treatment showed significantly lower mortality at 1 year when compared to surgery alone, but not at 2 and 5 years. We found no difference in mortality between angiosarcomas and other PCS subtypes. Conclusion Overall, surgery was found to provide a significant mortality advantage to PCS patients up to 3 years following treatment. Multimodality treatment might be of additional benefit, although only within the first year. Prospective randomized studies are needed to further explore these differences in the treatment of PCS.

Introduction Primary cardiac sarcomas (PCSs) are an extremely rare and aggressive type of malignancies that have been described only by a limited number of observational studies. This study aimed to evaluate the currently existing evidence comparing surgical to multimodality treatment of PCS. Methods We systematically reviewed Embase, MEDLINE, Cochrane Database, and Google Scholar, from inception to December 2020, for original articles about surgical and multimodality treatment of PCS. The outcomes included were mortality at various time points, resection margin status, and mean estimated survival. The pooled treatment effects were calculated using a random-effects model. Results Ten studies including a total of 1570 patients met our inclusion criteria. Surgery was associated with significantly lower mortality when compared to conservative treatment at 1, 2, and 3 years, whereas no significant difference was found at 5 years. Furthermore, multimodality treatment showed significantly lower mortality at 1 year when compared to surgery alone, but not at 2 and 5 years. We found no difference in mortality between angiosarcomas and other PCS subtypes. Conclusion Overall, surgery was found to provide a significant mortality advantage to PCS patients up to 3 years following treatment. Multimodality treatment might be of additional benefit, although only within the first year. Prospective randomized studies are needed to further explore these differences in the treatment of PCS.