Machine learning for rhabdomyosarcoma histopathology.

Correctly diagnosing a rare childhood cancer such as sarcoma can be critical to assigning the correct treatment regimen. With a finite number of pathologists worldwide specializing in pediatric/young adult sarcoma histopathology, access to expert differential diagnosis early in case assessment is limited for many global regions. The lack of highly-trained sarcoma pathologists is especially pronounced in low to middle-income countries, where pathology expertise may be limited despite a similar rate of sarcoma incidence. To address this issue in part, we developed a deep learning convolutional neural network (CNN)-based differential diagnosis system to act as a pre-pathologist screening tool that quantifies diagnosis likelihood amongst trained soft-tissue sarcoma subtypes based on whole histopathology tissue slides. The CNN model is trained on a cohort of 424 centrally-reviewed histopathology tissue slides of alveolar rhabdomyosarcoma, embryonal rhabdomyosarcoma and clear-cell sarcoma tumors, all initially diagnosed at the originating institution and subsequently validated by central review. This CNN model was able to accurately classify the withheld testing cohort with resulting receiver operating characteristic (ROC) area under curve (AUC) values above 0.889 for all tested sarcoma subtypes. We subsequently used the CNN model to classify an externally-sourced cohort of human alveolar and embryonal rhabdomyosarcoma samples and a cohort of 318 histopathology tissue sections from genetically engineered mouse models of rhabdomyosarcoma. Finally, we investigated the overall robustness of the trained CNN model with respect to histopathological variations such as anaplasia, and classification outcomes on histopathology slides from untrained disease models. Overall positive results from our validation studies coupled with the limited worldwide availability of sarcoma pathology expertise suggests the potential of machine learning to assist local pathologists in quickly narrowing the differential diagnosis of sarcoma subtype in children, adolescents, and young adults.

Prediction of clinical outcomes in women with placenta accreta spectrum using machine learning models: an international multicenter study.

INTRODUCTION: Placenta accreta spectrum is a major obstetric disorder that is associated with significant morbidity and mortality. The objective of this study is to establish a prediction model of clinical outcomes in these women. MATERIALS AND METHODS: PAS-ID is an international multicenter study that comprises 11 centers from 9 countries. Women who were diagnosed with PAS and were managed in the recruiting centers between 1 January 2010 and 31 December 2019 were included. Data were reanalyzed using machine learning (ML) models, and 2 models were created to predict outcomes using antepartum and perioperative features. ML model was conducted using python® programing language. The primary outcome was massive PAS-associated perioperative blood loss (intraoperative blood loss ≥2500 ml, triggering massive transfusion protocol, or complicated by disseminated intravascular coagulopathy). Other outcomes include prolonged hospitalization >7 days and admission to the intensive care unit (ICU). RESULTS: 727 women with PAS were included. The area under curve (AUC) for ML antepartum prediction model was 0.84, 0.81, and 0.82 for massive blood loss, prolonged hospitalization, and admission to ICU, respectively. Significant contributors to this model were parity, placental site, method of diagnosis, and antepartum hemoglobin. Combining baseline and perioperative variables, the ML model performed at 0.86, 0.90, and 0.86 for study outcomes, respectively. Ethnicity, pelvic invasion, and uterine incision were the most predictive factors in this model. DISCUSSION: ML models can be used to calculate the individualized risk of morbidity in women with PAS. Model-based risk assessment facilitates a priori delineation of management.

Prediction of success of uterus-preserving management in women with placenta accreta spectrum (CON-PAS score): A multicenter international study.

OBJECTIVE: To create a model for prediction of success of uterine-preserving procedures in women with placenta accreta spectrum (PAS). METHODS: PAS-ID is a multicenter study that included 11 centers from 9 countries. Women with PAS, who were managed between January 1, 2010 and December 31, 2019, were retrospectively included. Data were split into model development and validation cohorts, and a prediction model was created using logistic regression. Main outcome was success of uterine preservation. RESULTS: Out of 797 women with PAS, 587 were eligible. Uterus-preserving procedures were successful in 469 patients (79.9%). Number of previous cesarean sections (CS) was inversely associated with management success (adjusted odds ratio [aOR] 0.02, 95% confidence interval [CI] 0.001-3.63 with five previous CS). Other variables were complete placental invasion (aOR 0.14, 95% CI 0.05-0.43), type of CS incision (aOR 0.04, 95% CI 0.01-0.25 for classical incision), compression sutures (aOR 2.48, 95% CI 1.00-6.16), accreta type (aOR 3.76, 95% CI 1.13-12.53), incising away from placenta (aOR 5.09, 95% CI 1.52-16.97), and uterine resection (aOR 102.57, 95% CI 3.97-2652.74). CONCLUSION: The present study provides a prediction model for success of uterine preservation, which may assist preoperative and intraoperative decisions, and promote incorporation of uterine preservation procedures in comprehensive PAS protocols.

Non-technical skills training to enhance performance of obstetrics and gynaecology residents in the operating room.

The importance of incorporating non-technical skills in surgical training cannot be understated, however, these remain non-core components of training. The aim of our study was to evaluate the effectiveness of a training course in improving residents' non-technical skills performance in the operating room. Twenty-eight eligible Obstetrics and Gynaecology residents were divided into conventional and experimental groups by using blocked randomisation. The experimental group received a training course comprising of 20 h over 5 weeks as an educational intervention. A blinded assessor assessed non-technical skill performance by using non-technical skill for surgeons rating system while performing two procedures evacuation and curettage and elective caesarean section in pretest and post-test phase. The post-test results of experimental training group improved significantly in all four categories: situational awareness, decision-making, communication and leadership than the conventional training group demonstrating the effectiveness of a training course. Participants found the course useful and relevant to their practices and strongly recommended the incorporation of similar courses in early years of training. Impact Statement What is already known on this subject? Operating room is the mainstay of surgeons and the majority of the studies done in the operating room relate to structured courses to teach residents about non-technical skills, with training and evaluation done on the same day. These either explores the perception of trainees, expansion of the cognitive component and/or feasibility of training for non-technical skills. To date, there is a lack of evidence in the literature to address questions regarding the appropriate time to incorporate non-technical skills in the curriculum, due to study designs. This highlights the need for more randomised control trials with different curricular designs to evaluate effectiveness. What do the results of this study add? The results of our study enable a comparative analysis between learning curves of conventional training, with the experimental group demonstrating the effectiveness of a training course. This strongly supports implementation of non-technical training in postgraduate competency-based curricula. What are the implications of these findings for clinical practice and/or further research? This study shall be used as an evidence-based source to design curricula for teaching non-technical skills to residents.

Torsion of a Term Uterus.

Torsion of the pregnant uterus, at term, is a very rare event in obstetric practice. It is associated with high perinatal mortality. We are reporting a case of uterine torsion, where a booked second gravida with previous lower segment cesarean section underwent an emergency cesarean section due to severe lower abdominal pain, persistent fetal tachycardia and poor Bishop Score. Following delivery of baby and placenta, uterus untwisted on itself through 180 degrees and it was realized that the incision had been made on the posterior wall of the uterus. Bilateral tubal ligation (BTL) was done after proper informed consent. This decision was based on unavailability of data on safety of future pregnancies in patients with both anterior and posterior uterine scars. Efforts need to be made to develop consensus for management of these cases, in future.