Learning Curve For Procedure Research Articles

The Learning Curve in Urogynecology and Functional Urology: A Systematic Review.

When adopting new methods, surgeons may experience a period of complexity and longer operation times because of their inexperience. This period is known as the "learning curve." This study was aimed at systematically reviewing the current literature on functional urology learning curves. A comprehensive search was conducted across multiple databases from inception to July 2023 with no language restrictions. All original studies on urogynecological and functional urological procedures, including cross-sectional, cohort, and clinical trials, were eligible for inclusion. Relevant data were extracted, and methodological quality was appraised using standardized Joanna Briggs Institute critical appraisal tools. To quantitatively investigate learning curves, a mixed-effects generalized linear regression analysis was conducted on studies employing cumulative summation methods. From the 7,104 records, 68 studies met the inclusion criteria. The majority of studies were observational and the most common outcome measures were surgical duration, blood loss, and hospital stay. The learning curves varied by procedure type-for incontinence surgeries, 15-80 cases were required; for pelvic organ prolapse surgeries, 18-47 cases; for laparoscopic procedures, 10-105 cases; and for robotic procedures, 5-84 cases. The analysis showed that the number of cases required to surpass the learning curve decreased over time, likely reflecting technological advancements and increased surgical experience. The learning curve for surgical procedures varies significantly. It varies between 5 cases for robotic supratrigonal cystectomy to 75 cases for robot-assisted ventral mesh rectopexy or robotic sacrocolpopexy surgery in 84 cases. These variable learning curves highlight the need for structured training programs and ongoing assessment.

Assessment of Safety and Procedural Learning Curve for Pulmonary Embolism Patients Undergoing Percutaneous Mechanical Thrombectomy under Local Anesthesia: A Retrospective Chart Review

Assessment of Safety and Procedural Learning Curve for Pulmonary Embolism Patients Undergoing Percutaneous Mechanical Thrombectomy under Local Anesthesia: A Retrospective Chart Review

Learning Curve for Dynamic Navigation Procedure during Endodontic Management of Permanent Maxillary Anterior Teeth with Pulp Canal Calcification: A Risk-Adjusted Cumulative Summation Analysis of a Single Operator's Experience.

The dynamic navigation system (DNS) in endodontics presents a significant learning curve. This cross-sectional study aimed to assess the number of cases required to achieve consistent performance in DNS-assisted treatment of maxillary anterior teeth with pulp canal calcification. A series of DNS procedures were performed on 45 calcified maxillary anterior teeth with pulp necrosis by a single endodontist who had no prior clinical DNS experience. Preoperative cone-beam computed tomography was obtained. After trace registration and calibration, drilling was executed using a low-speed bur. Once the canal was located and scouted to the working length, a postoperative cone-beam computed tomography was taken immediately. Angular deviation (AD), linear deviation (LD), and operating time (OT) were measured. The learning curve was evaluated using the risk-adjusted cumulative sum analysis method. The overall success rate in locating canals was 93.33% (95% CI 80.7, 98.3). The mean (±SD) for AD, LD and OT was 3.21±2.23°, 0.52±0.33mm and 34.14±13.18minutes, respectively. For AD, 2 distinct peaks were observed at the 5th and 18th cases, identifying 3 learning phases: Phase I (cases 1-5), Phase II (cases 6-18), and Phase III (cases 19-45). Similarly, LD exhibited peaks at the 13th and 28th cases. Two peaks for OT were identified at the 7th and 26th cases. Achieving technical proficiency in locating calcified canals using DNS required approximately 18 to 28 cases, indicating a significant learning curve that must be overcome for optimal accuracy.

Transbronchial lung cryobiopsy for interstitial lung disease: early experience, learning curve, and the impact of sedation on complication rates at a single centre in Japan

BackgroundTransbronchial lung cryobiopsy (TBLC) has emerged as a promising diagnostic tool for interstitial lung disease (ILD). This study aimed to assess the initial experience, procedural learning curve, and influence of sedative medications on complication rates, particularly bleeding and pneumothorax, in the implementation of a TBLC program for ILD diagnosis.MethodsIn this retrospective cohort study, we analysed 119 patients who underwent TBLC at Nippon Medical School Hospital from April 2021 to March 2024. Procedural times, complication rates, and histopathological outcomes were evaluated. The learning curve was assessed using cumulative sum (CUSUM) analysis, focusing on procedure time and biopsy yield. The association between sedative medication dosages and bleeding risk was also examined.ResultsThe overall diagnostic yield was high, with alveolar tissue obtained in 97.5% of cases and a definitive pathological diagnosis achieved in 81.5% of patients. CUSUM analysis revealed a proficiency threshold at approximately 56 cases, with improved efficiency and biopsy yield in the consolidation phase. Fentanyl dosage was significantly associated with reduced bleeding complications (odds ratio 0.51, 95% confidence interval 0.27–0.97, p = 0.041).ConclusionsTBLC is a safe and effective diagnostic tool for ILDs, with a manageable learning curve for procedural efficiency. Sedation, particularly fentanyl dosage, may plays a crucial role in minimizing complications, but further research is needed to clarify this relationship. These findings support the adoption of TBLC as a standard diagnostic approach for ILD and highlight the importance of adequate training and optimized sedation protocols to ensure safety and efficacy in clinical practice.

A 3D-Printed, High-Fidelity Pelvis Training Model: Cookbook Instructions and First Experience.

Background: Since laparoscopic surgery became the gold standard for colorectal procedures, specific skills are required to achieve good outcomes. The best way to acquire basic and advanced skills and reach the learning curve plateau is by using dedicated simulators: box-trainers, video-trainers and virtual reality simulators. Laparoscopic skills training outside the operating room is cost-beneficial, faster and safer, and does not harm the patient. When compared to box-trainers, virtual reality simulators and cadaver models have no additional benefits. Several laparoscopic trainers available on the market as well as homemade box and video-trainers, most of them using plastic boxes and standard webcams, were described in the literature. The majority of them involve training on a flat surface without any anatomical environment. In addition to their demonstrated benefits, box-trainers which add anatomic details can improve the training quality and skills development of surgeons. Methods: We created a 3D-printed anatomic pelvi-trainer which offers a real-size narrow pelvic space environment for training. The model was created starting with a CT-scan performed on a female pelvis from the Anatomy Museum (Cluj-Napoca University of Medicine and Pharmacy, Romania), using Invesalius 3 software (Centro de Tecnologia da informação Renato Archer CTI, InVesalius open-source software, Campinas, Brazil) for segmentation, Fusion 360 with Netfabb software (Autodesk software company, Fusion 360 with Netfabb, San Francisco, CA, USA) for 3D modeling and a FDM technology 3D printer (Stratasys 3D printing company, Fortus 380mc 3D printer, Minneapolis, MN, USA). In addition, a metal mold for casting silicone valves was made for camera and endoscopic instruments ports. The trainer was tested and compared using a laparoscopic camera, a standard full HD webcam and "V-Box" (INTECH-Innovative Training Technologies, Milano, Italia), a dedicated hard paper box. The pelvi-trainer was tested by 33 surgeons with different qualifications and expertise. Results: We made a complete box-trainer with a versatile 3D-printed pelvi-trainer inside, designed for a wide range of basic and advanced laparoscopic skills training in the narrow pelvic space. We assessed the feedback of 33 surgeons regarding their experience using the anatomic 3D-printed pelvi-trainer for laparoscopic surgery training in the narrow pelvic space. Each surgeon tested the pelvi-trainer in three different setups: using a laparoscopic camera, using a webcam connected to a laptop and a "V-BOX" hard paper box. In the experiments that were performed, each participant completed a questionnaire regarding his/her experience using the pelvi-trainer. The results were positive, validating the device as a valid tool for training. Conclusions: We validated the anatomic pelvi-trainer designed by our team as a valuable alternative for basic and advanced laparoscopic surgery training outside the operating room for pelvic organs procedures, proving that it supports a much faster learning curve for colorectal procedures without harming the patients.

Metabolic and Bariatric Surgeon Criteria-An International Experts' Consensus.

With the global epidemic of obesity, the importance of metabolic and bariatric surgery (MBS) is greater than ever before. Performing these surgeries requires academic training and the completion of a dedicated fellowship training program. This study aimed to develop guidelines based on expert consensus using a modified Delphi method to create the criteria for metabolic and bariatric surgeons that must be mastered before obtaining privileges to perform MBS. Eighty-nine recognized MBS surgeons from 42 countries participated in the Modified Delphi consensus to vote on 30 statements in two rounds. An agreement/disagreement among ≥ 70.0% of the experts was regarded to indicate a consensus. Consensus was reached on 29 out of 30 statements. Most experts agreed that before getting privileges to perform MBS, surgeons must hold a general surgery degree and complete or have completed a dedicated fellowship training program. The experts agreed that the learning curves for the various operative procedures are approximately 25-50 operations for the LSG, 50-75 for the OAGB, and 75-100 for the RYGB. 93.1% of experts agreed that MBS surgeons should diligently record patients' data in their National or Global database. MBS surgeons should have a degree in general surgery and have been enrolled in a dedicated fellowship training program with a structured curriculum. The learning curve of MBS procedures is procedure dependent. MBS surgeons must demonstrate proficiency in managing postoperative complications, collaborate within a multidisciplinary team, commit to a minimum 2-year patient follow-up, and actively engage in national and international MBS societies.

Investigation of a chronic single-stage sheep Fontan model

ObjectivesOur goal was to conduct a hemodynamic analysis of a novel animal model of Fontan physiology. Poor late-term outcomes in Fontan patients are believed to arise from Fontan-induced hemodynamics, but the mechanisms remain poorly understood. Recent advances in surgical experimentation have resulted in the development of a chronic sheep model of Fontan physiology; however, detailed analysis of this model is lacking. MethodsWe created a single-stage Fontan model in juvenile sheep with normal biventricular circulation. The superior vena cava was anastomosed to the main pulmonary artery, and the inferior vena cava was connected to the main pulmonary artery using an expanded polytetrafluoroethylene conduit. Longitudinal hemodynamics, including catheterization and magnetic resonance imaging were evaluated. ResultsFour out of 12 animals survived, with the longest surviving animal living 3 years after single-stage Fontan. We showed a significant era effect regarding survival (1 out of 8 and subsequently 3 out of 4 animals surviving beyond 2 months) attributed in large part to the procedural learning curve. Key characteristics of Fontan hemodynamics, namely systemic venous hypertension and low normal cardiac output, were observed. However, recapitulation of passive human Fontan hemodynamics is affected by volume loading of the right ventricle given an anatomic difference in sheep azygous venous anatomy draining to the coronary sinus. ConclusionsA significant learning curve exists to ensure long-term survival and future surgical modifications, including banding of the main pulmonary artery and ligation of the azygous to coronary sinus connection are promising strategies to improve the fidelity of model hemodynamics.

Trained to cut? A literature review of veterinary surgical resident training.

A surgical residency trains veterinary graduates to a higher level of expertise in surgical procedures than is possible during veterinary school and prepares a resident to pursue board certification in surgery. The education of veterinary surgical residents has changed minimally since its inception in the twentieth century, and there are insufficient studies to determine if residency programs are producing surgeons with competence in each of the necessary procedural categories. The aims of this review were to report the current theory and methods used to provide surgical education to residents, to discuss the training most likely to create a competent, board-certified surgeon and to review assessment methods used during training. Several literature searches using broad terms such as "veterinary surgery residency," "veterinary surgery resident," and "veterinary surgical training" were performed using PubMed, CAB abstracts, and Google Scholar. Literature pertinent to theory, methods, training, and assessment of veterinary surgical residents was included. The reviewed literature demonstrated the need for research-based learning curves for specific procedures. Simulation training is known to facilitate deliberate practice and should be leveraged where possible to reach competency. The creation of validated assessment methods should be pursued as it enables assessment of competency instead of inferring its development from case logs. Understanding and supporting learner cognition and providing sufficient feedback remain important issues in the field. Surgical educators are urged to continue to search for innovative and evidence-based ways to train competent surgical residents.

Ergonomic wellness for the trainee in gastrointestinal endoscopy.

Endoscopy-related injuries (ERIs) are prevalent in gastrointestinal endoscopy. The aim of this review is to address the growing concern of ERIs by evaluating the ergonomic risk factors and the efficacy of interventions and educational strategies aimed at mitigating these risks, including novel approaches. ERIs are highly prevalent, exacerbated by factors such as repetitive strain, nonneutral postures, suboptimal equipment design, and the procedural learning curve. Female sex and smaller hand sizes have been identified as specific risk factors. Recent guidelines underscore the importance of ergonomic education and the integration of ergonomic principles into the foundational training of gastroenterology fellows. Advances in equipment design focus on adaptability to different hand sizes and ergonomic positions. Furthermore, the incorporation of microbreaks and macrobreaks, along with neutral monitor and bed positioning, has shown promise in reducing the incidence of ERIs. Wearable sensors may be helpful in monitoring and promoting ergonomic practices among trainees. Ergonomic wellness is paramount for gastroenterology trainees to prevent ERIs and ensure a sustainable career. Effective strategies include ergonomic education integrated into curricula, equipment design improvements, and procedural adaptations such as scheduled breaks and optimal positioning. Sensor-based and camera-based systems may allow for education and feedback to be provided regarding ergonomics to trainees in the future.

Education in Interventional Pulmonology: How We Got Here and Where to Go from Here

Interventional pulmonology is a rapidly growing field with increasing demand. To meet this demand, training in interventional pulmonology is expanding. What started as a single training program without a standardized curriculum has grown to 40 accredited training programs with a well-defined curriculum that is now overseen by the Accreditation Council for Graduate Medical Education. As the field develops, research is being actively performed to develop validated competency assessment tools and describe the learning curves for pulmonary procedures. As research evolves, this information can be used to better standardize training in interventional pulmonology and move the field towards a competency-based training model.

Narrative review in learning curve and pediatric robotic training program.

Studying learning curve (LC) for robotic procedures and developing an adequate training program are two fundamental steps to standardize robotic procedures. With this aim, we analyzed the literature to study the LCs of different robotic procedures and the availability of standardized training problems. The PubMed database was searched in the period from January 1995 to September 2022. Articles presenting LC and potential training programs in the pediatric population were chosen. Twenty papers were screened describing LC of robotic-assisted laparoscopic pyeloplasty (n=12), fundoplication (n=4), cholecystectomy (n=2), choledochal cyst resection (n=1), nephrectomy/partial nephrectomy (n=1) and lingual tonsillectomy (n=1), with a total of 1,251 procedures. In 10 studies there was only one single surgeon; nine had more than one; one did not specify how many surgeons participated. Twelve papers were retrospective single-center, three multicentric retrospective, four prospective and one was compared a retrospective case series to a prospective cohort. Most of these studies focused on operative time as the primary outcome. It was analyzed as the only outcome in three articles, along with complications in 14, time to discharge in eight, blood loss in three and pain killer use in three. The selected studies analyzed LC impacting operative planning (n=20), training (n=10) and costs (n=2). There is still a long way to go to complete a standardized functional training for robotic surgery procedures in pediatric surgery. Moreover, the progressive reduction in costs expected in the years to come will play a key role in progressing the diffusion of this technology enabling the collection of data necessary to create a standardized pediatric surgery robotic training program.

Can my surgeon scope? Trends in endoscopy training volume and experience among general surgery residents in the United States: a nationwide analysis.

Endoscopy is a major part of surgical training. Accreditation Council for Graduate Medical Education (ACGME) has set standards regarding the minimum volume of endoscopy cases required for graduation. However, there is paucity of high-quality data on the number of cases that most surgical graduates perform. We conducted a retrospective analysis of operative case logs of all general surgery residents graduating from ACGME-accredited programs from 2010 to 2023. Data on mean number of endoscopy cases, including mean in each subcategory, were retrieved. Mann-Kendall trend test was used to investigate trends in endoscopy experience. Between 2010 and 2023, the mean overall endoscopy procedures per resident remained stable, with 129.5 in 2010 and 132.1 in 2023 (t = 0.429; p-value = 0.037). The majority of these cases were performed as surgeon junior (76.6% in 2010; 80.9% in 2023), while the remaining cases were logged as surgeon chief. The most substantial contribution to the overall volume was from flexible colonoscopy (mean: 64.1 in 2010 and 67.2 in 2023). The volume for colonoscopy remained fairly stable (t = 0.429; p-value = 0.036). This was followed by esophagogastroduodenoscopy (mean: 35.3 in 2010 and 35.5 in 2023), which saw a significant increase in volume (t = 0.890; p-value ≤ 0.001). There was a significant increase in the number of overall upper endoscopic procedures (t = 0.791; p-value ≤ 0.001), while lower endoscopic procedures did not change significantly (t = 0.319; p-value = 0.125). The procedural volume for endoscopic retrograde cholangiography, sigmoidoscopy, cystoscopy/ureteroscopy, laryngoscopy, and bronchoscopy decreased significantly (p-value < 0.05 for all). The overall endoscopy volume for general surgery residents has largely remained stable, with a minor increase in esophagogastroduodenoscopy and no change in colonoscopy. Future research should investigate whether simulation-based exercises can bridge the gap between procedural volume and learning curve requirements for endoscopy.

Hospital learning curves for robot-assisted surgeries: a population-based analysis.

Robot-assisted surgery has been rapidly adopted. It is important to define the learning curve to inform credentialling requirements, training programs, identify fast and slow learners, and protect patients. This study aimed to characterize the hospital learning curve for common robot-assisted procedures. This cohort study, using administrative health data for Ontario, Canada, included adult patients who underwent a robot-assisted radical prostatectomy (RARP), total robotic hysterectomy (TRH), robot-assisted partial nephrectomy (RAPN), or robotic portal lobectomy using four arms (RPL-4) between 2010 and 2021. The association between cumulative hospital volume of a robot-assisted procedure and major complications was evaluated using multivariable logistic models adjusted for patient characteristics and clustering at the hospital level. A total of 6814 patients were included, with 5230, 543, 465, and 576 patients in the RARP, TRH, RAPN, and RPL-4 cohorts, respectively. There was no association between cumulative hospital volume and major complications. Visual inspection of learning curves demonstrated a transient worsening of outcomes followed by subsequent improvements with experience. Operative time decreased for all procedures with increasing volume and reached plateaus after approximately 300 RARPs, 75 TRHs, and 150 RPL-4s. The odds of a prolonged length of stay decreased with increasing volume for patients undergoing a RARP (OR 0.87; 95% CI 0.82-0.92) or RPL-4 (OR 0.77; 95% CI 0.68-0.87). Hospitals may adopt robot-assisted surgery without significantly increasing the risk of major complications for patients early in the learning curve and with an expectation of increasing efficiency.

Abstract 13371: Left Bundle Branch Area Pacing: Experiences From the First Two Years Implanting in an Academic Training Program

Background: Left bundle branch area pacing (LBBAP) has emerged as a more durable physiologic pacing strategy to His bundle pacing and a promising alternative to cardiac resynchronization therapy. Integration of this procedural technique within an academic training program has not yet been described. Objective: Highlight the procedural learning curve of implanting LBBAP leads within a fellowship program. Methods: Retrospective analysis of consecutive patients who underwent placement of a Medtronic 3830 lead for LBBAP at our institution from 1/2021-12/2022. Results: A total of 180 patients underwent LBBAP lead placement over the study time period. Overall, total procedure time was 133.7±58.2min, lead placement time 30.7±20.0min, fluoroscopy time 22.5±21.2 min, left bundle branch (LBB) capture rate 70% and paced QRS duration 128.6±19.3 ms. When dividing the study period by 6-month intervals, there was a rise in procedural volume (21, 28, 62 and 59 cases, respectively), a trend towards less fluoroscopy use (20.2±12.2, 16.7±9.1, 16.2±12.6 and 16.6±14.4 min), less total radiation (345.2±323.3, 317.2±630.9, 214.9±271.2 and 171.7±253.9 mGy), decreased LBBAP lead placement time (37.8±24.3, 30.7±16.3, 28.2±21.5, 30.6±18.7 min), decreased delivery system exchanges (19%, 11%, 8% and 2%*, *p≤0.01 from first six months) and improved LBB capture rates (50%, 69%, 83%*, 64%, *p≤0.01 from first six months). Both fellowship classes showed significant improvements in LBB capture rates (40% to 94% and 38% to 84%, p≤0.01 for both) and paced-QRS duration (140.0±27.2ms to 120.2±16.5ms and 136.2±21.8ms to 121.7±17.2ms, p≤0.05 for both) after 12 months of experience. Conclusion: Over the first two years of performing LBBAP in an academic training program, there was a rise in procedural volume with trends towards less fluoroscopy use, decreased LBBAP lead placement time with significantly decreased delivery system exchanges and improved LBB capture rates. Significant improvements in LBB capture rates and paced-QRS duration were seen by fellows after 12 months of experience. LBBAP is an increasingly popular pacing technique that can be effectively integrated within a training program, with early introduction important to accommodate the initial learning curve.

EP07.02-16 Localization of Lung Nodules by Electromagnetic Navigation Bronchoscopy-Guided Dye Marking: Procedural Outcomes and Learning Curve

EP07.02-16 Localization of Lung Nodules by Electromagnetic Navigation Bronchoscopy-Guided Dye Marking: Procedural Outcomes and Learning Curve

324 The Learning Curves of Major Laparoscopic and Robotic Procedures in Urology: A Systematic Review

Abstract Aim Urology has been at the forefront of adopting laparoscopic and robot-assisted techniques to improve patient outcomes. Defining the learning curves for these procedures enables assessment of trainee performances relative to expected progress and has important implications in research. This systematic review aimed to examine the literature relating to the learning curves of major urological robotic and laparoscopic procedures. Method In accordance with PRISMA guidelines, a systematic literature search strategy was employed across PubMed, EMBASE, and the Cochrane Library from inception to December 2021 for eligible studies alongside a search of the grey literature. Two independent reviewers completed the article screening and data extraction stages, using the Newcastle-Ottawa Scale (NOS) to then undertake quality assessment of the included articles. The review was reported in accordance with AMSTAR guidelines. Results Of 3702 records identified, 97 eligible studies were included for narrative synthesis. 39 studies evaluated robot-assisted laparoscopic prostatectomy (RALP) with the learning curve identified as 10-250 cases for operative time and 250-300 for potency. The shortest learning curve was reported for hand-assisted laparoscopic nephrectomy, involving 4-10 cases. There was considerable variation in the study designs, outcome measures and prior experience of surgeons, with all studies scoring either 5 or 6 on the NOS. Conclusions Standardised reporting of outcomes and performance measures is required to reduce heterogeneity and enable the undertaking of a meta-analysis. Future studies should use multiple surgeons and large sample sizes of cases to identify the currently undefined learning curves for laparoscopic radical cystectomy and for robotic and laparoscopic retroperitoneal lymph node dissection.

Learning Curve Analysis of Robotic-Assisted Mitral Valve Repair with COVID-19 Exogenous Factor: A Single Center Experience.

Background and objective Renewed interest in robot-assisted cardiac procedures has been demonstrated by several studies. However, concerns have been raised about the need for a long and complex learning curve. In addition, the COVID-19 pandemic in 2020 might have affected the learning curve of these procedures. In this study, we investigated the impact of COVID-19 on the learning curve of robotic-assisted mitral valve surgery (RAMVS). The aim was to understand whether or not the benefits of RAMVS are compromised by its learning curve. Materials and Methods Between May 2019 and March 2023, 149 patients underwent RAMVS using the Da Vinci® X Surgical System at the Humanitas Gavazzeni Hospital, Bergamo, Italy. The selection of patients enrolled in the study was not influenced by case complexity. Regression models were used to formalize the learning curves, where preoperative data along with date of surgery and presence of COVID-19 were treated as the input covariates, while intraoperative and postoperative data were analyzed as output variables. Results The age of patients was 59.1 ± 13.3 years, and 70.5% were male. In total, 38.2% of the patients were operated on during the COVID-19 pandemic. The statistical analysis showed the positive impact of the learning curve on the trend of postoperative parameters, progressively reducing times and other key indicators. Focusing on the COVID-19 pandemic, statistical analysis did not recognize an impact on postoperative outcomes, although it became clear that variables not directly related to the intervention, especially ICU hours, were strongly influenced by hospital logistics during COVID-19. Conclusions Understanding the learning curve of robotic surgical procedures is essential to ensure their effectiveness and benefits. The learning curve involves not only surgeons but also other health care providers, and establishing a stable team in the early stage, as in our case, is important to shorten the duration. In fact, an exogenous factor such as the COVID-19 pandemic did not affect the robotic program despite the fact that the pandemic occurred early in the program.

A Coordinate-Regression-Based Deep Learning Model for Catheter Detection during Structural Heart Interventions

With a growing geriatric population estimated to triple by 2050, minimally invasive procedures that are image-guided are becoming both more popular and necessary for treating a variety of diseases. To lower the learning curve for new procedures, it is necessary to develop better guidance systems and methods to analyze procedure performance. Since fluoroscopy remains the primary mode of visualizations, the ability to perform catheter tracking from fluoroscopic images is an important part of this endeavor. This paper explores the use of deep learning to perform the landmark detection of a catheter from fluoroscopic images in 3D-printed heart models. We show that a two-stage deep-convolutional-neural-network-based model architecture can provide improved performance by initially locating a region of interest before determining the coordinates of the catheter tip within the image. This model has an average error of less than 2% of the image resolution and can be performed within 4 milliseconds, allowing for its potential use for real-time intraprocedural tracking. Coordinate regression models have the advantage of directly outputting values that can be used for quantitative tracking in future applications and are easier to create ground truth values (~50× faster), as compared to semantic segmentation models that require entire masks to be made. Therefore, we believe this work has better long-term potential to be used for a broader class of cardiac devices, catheters, and guidewires.

Clinical outcomes and learning curve for ERCP during advanced endoscopy training: a comparison of supine versus prone positioning

No studies have evaluated trainees' outcomes when learning ERCP with patients in the supine and prone positions simultaneously. We aimed to assess whether patient position impacts procedural outcomes and learning curve. We prospectively evaluated patients undergoing ERCP by a supervised advanced endoscopy trainee (AET) at a tertiary care center. Adult patients with native papillae were included. The AET was universally given 5 attempts per cannulation. Outcomes were evaluated quarterly. Successful cannulation was achieved in 44 supine (69%) and 17 prone (68%) patients (P= .95). Although mean time to reach the papilla was shorter in the supine patient position, time to biliary cannulation (7.8 vs 9.4 minutes, P= .53) and number of attempts were similar. A stepwise increase was seen in cannulation rates throughout the academic year (P< .01) and increased more in supine patients (P= .01). Procedure and total room times were shorter in supine patients. Shorter procedure and room turnover times and a comparable cannulation rate were found for supine versus prone ERCP.

Recent advances in endoscopic management of gastric neoplasms

The development and clinical application of new diagnostic endoscopic technologies such as endoscopic ultrasonography with biopsy, magnification endoscopy, and narrow-band imaging, more recently supplemented by artificial intelligence, have enabled wider recognition and detection of various gastric neoplasms including early gastric cancer (EGC) and subepithelial tumors, such as gastrointestinal stromal tumors and neuroendocrine tumors. Over the last decade, the evolution of novel advanced therapeutic endoscopic techniques, such as endoscopic mucosal resection, endoscopic submucosal dissection, endoscopic full-thickness resection, and submucosal tunneling endoscopic resection, along with the advent of a broad array of endoscopic accessories, has provided a promising and yet less invasive strategy for treating gastric neoplasms with the advantage of a reduced need for gastric surgery. Thus, the management algorithms of various gastric tumors in a defined subset of the patient population at low risk of lymph node metastasis and amenable to endoscopic resection, may require revision considering upcoming data given the high success rate of en bloc resection by experienced endoscopists. Moreover, endoscopic surveillance protocols for precancerous gastric lesions will continue to be refined by systematic reviews and meta-analyses of further research. However, the lack of familiarity with subtle endoscopic changes associated with EGC, as well as longer procedural time, evolving resection techniques and tools, a steep learning curve of such high-risk procedures, and lack of coding are issues that do not appeal to many gastroenterologists in the field. This review summarizes recent advances in the endoscopic management of gastric neoplasms, with special emphasis on diagnostic and therapeutic methods and their future prospects.