ABSTRACT
The last three years have been a game changer in the way medicine is practiced. The COVID-19 pandemic changed the obstetrics and gynecology scenery. Pregnancy complications, and even death, are preventable due to maternal-fetal monitoring. A fast and accurate diagnosis can be established by a doctor + Artificial Intelligence combo. The aim of this paper is to propose a framework designed as a merger between Deep learning algorithms and Gaussian Mixture Modelling clustering applied in differentiating between the view planes of a second trimester fetal morphology scan. The deep learning methods chosen for this approach were ResNet50, DenseNet121, InceptionV3, EfficientNetV2S, MobileNetV3Large, and Xception. The framework establishes a hierarchy of the component networks using a statistical fitness function and the Gaussian Mixture Modelling clustering method, followed by a synergetic weighted vote of the algorithms that gives the final decision. We have tested the framework on two second trimester morphology scan datasets. A thorough statistical benchmarking process has been provided to validate our results. The experimental results showed that the synergetic vote of the framework outperforms the vote of each stand-alone deep learning network, hard voting, soft voting, and bagging strategy.
ABSTRACT
Introduction: the COVID-19 pandemic has had a considerable impact on healthcare systems worldwide. Since the actual influence of the pandemic on gynecological care is still unclear, we aim to evaluate the effect of the SARS-CoV-2 pandemic on gynecological procedures compared to the pre-pandemic period in Romania. Materials and Methods: this is a single-center retrospective observational study, involving patients hospitalized in the year before the SARS-CoV-2 pandemic (PP), in the first year of the pandemic (P1), and in the second year of the pandemic until February 2022 (P2). The percentages of interventions were analyzed globally but also according to the type of surgery applied on the female genital organs. Results: during pandemic, the number of gynecological surgeries dropped considerably, by more than 50% in some cases, or even decreased by up to 100%, having a major impact on women's health, especially in the first year of the pandemic (P1), before slightly increasing in the post-vaccination period (PV). Surgically treated cancer cases dropped by over 80% during the pandemic, and the consequences of this will be seen in the future. Conclusions: the COVID-19 pandemic played an important part in gynecological care management in the Romanian public health care system, and the effect will have to be investigated in the future.
Subject(s)
COVID-19 , Genital Neoplasms, Female , Female , Humans , SARS-CoV-2 , COVID-19/epidemiology , Pandemics , Gynecologic Surgical ProceduresABSTRACT
The last two years have taught us that we need to change the way we practice medicine. Due to the COVID-19 pandemic, obstetrics and gynecology setting has changed enormously. Monitoring pregnant women prevents deaths and complications. Doctors and computer data scientists must learn to communicate and work together to improve patients' health. In this paper we present a good practice example of a competitive/collaborative communication model for doctors, computer scientists and artificial intelligence systems, for signaling fetal congenital anomalies in the second trimester morphology scan.
ABSTRACT
Background and objectives. The risk of developing invasive cancer increased during the COVID-19 pandemic, especially in Romania, where the incidence of this disease is high due to limited medical education and broad screening. This study's objective is to analyze the number of patients admitted with different types of cervical dysplasia and the treatment applied for the lesions during the SARS-CoV-2 pandemic compared to the same period for the year before the pandemic. Materials and methods: This is a retrospective study that took place in the Obstetrics and Gynecology Clinics I/II (OG I/II) of the Emergency County Hospital of Craiova during the SARS-CoV-2 pandemic (SP) (15.03.2020-14.03.2021) and in the 12 months before (non-pandemic period) (NPP) (15.03.2019-14.03.2020). The study includes 396 patients with pathological PAP smear results. All the patients included in this study were clinically examined and with colposcopy. The patients with Low-Grade Dysplasia were managed in a conservatory manner and reevaluated after six months. The patients with High-Grade Dysplasia were admitted for an excisional biopsy of the lesion. The excised fragments were sent to the Pathological Anatomy Laboratory for a histopathological examination. Results: This study reveals a decrease of more than half in the number of patients admitted with cervical intraepithelial neoplasia (CIN) lesions during the pandemic compared to the same period of the year before. The number of biopsies and excisional procedures has been decreasing by more than a factor of three during the pandemic period compared to the year before. Conclusion: During the SARS-CoV-2 pandemic, we found that the patients' admission rate, diagnosis, and treatment was almost four times lower. As hospital restrictions were not dictated for cancer/precancer management during SP, we may assume that the differences were due to the fear of becoming infected with SARS-CoV-2 due to hospitalization. In the context of poor screening performance and high cervical cancer incidence, the influence of the SP may result in a further increase of severe cases related to this condition.