Breast cancer, the most common cancer in women, is receiving increasing attention. The lack of high-quality medical resources, especially highly skilled doctors, in remote areas makes the diagnosis of breast cancer inefficient and causes great harm to women. The emergence of remote e-health has improved the situation to a certain extent, but its capabilities are still hampered by technical limitations, which manifest in two main aspects. First, due to network bandwidth limitations, it is difficult to guarantee the real-time transmission of breast cancer pathology images between remote areas and cities. Second, the highly skilled breast cancer doctors at large city hospitals are not guaranteed to be available for online diagnosis at all times. To overcome these limitations, this article proposes a deep-learning-empowered breast cancer auxiliary diagnosis scheme for remote e-health supported by 5G technology and beyond (5GB remote e-health). In this scheme, breast pathology images are first received from major hospitals via 5G, and a deep learning model based on the Inception-v3 network is subjected to transfer learning to obtain a diagnostic model. This diagnostic model is then employed on edge servers for auxiliary diagnosis at remote area hospitals. A theoretical analysis and experimental results show that this solution not only overcomes the two problems mentioned above but also improves the diagnostic accuracy for breast cancer in remote areas to 98.19 percent.

Deep-Learning-Empowered Breast Cancer Auxiliary Diagnosis for 5GB Remote E-Health

Introduction The Global Safe Motherhood Initiative, launched in 1987, is designed to improve antenatal care and counselling throughout the world Nutrient intake and weight gain during pregnancy are the two main modifiable factors influencing maternal and infant outcomes (1) Indeed, a low body mass index (BMI) and suboptimal weight gain during pregnancy are long-recognized risk factors for the delivery of infants too small for gestational age (2) Being born small for gestational age is a major predictor of neonatal mortality and morbidity, (2) failure to grow, slow cognitive development and chronic diseases in adulthood (3) Infants too large for gestational age also experience higher perinatal and long-term health risks (4-7) In addition, both groups of infants are more likely to be delivered by Caesarean section Thus, reducing the delivery of excessively small or large infants translates into fewer surgical risks for women (8) Appropriate antenatal management of maternal nutrition, as dictated by scientific evidence, is critical in reducing the delivery of these babies for whom both the intrauterine environment and the birth process can be life-threatening (8,9) Maternal anthropometry differs across populations (10) Women belonging to ethnic groups characterized by a small body size have been reported to gain less weight on average during pregnancy than larger women In less-developed Asian countries, including Viet Nam, women generally have a lower BMI and/or a smaller gestational weight gain than in developed countries (11,12) In the United States of America, for example, 2% of pregnant women have a BMI 25 (13) There is a need to assess whether the current anthropometric recommendations for pregnant women of the United States National Academy of Sciences Institute of Medicine (IOM), which are based on data from western countries, are appropriate for preventing adverse pregnancy outcomes across populations everywhere, including south-east Asia The objectives of this study were: (i) to determine the prevalence of small and large size for gestational age among infants of Vietnamese women, and (ii) to estimate the risk of giving birth to an infant too small or too large for gestational age as a function of maternal gestational weight gain and BMI in Viet Nam Methods Study setting and population Viet Nam is a low-income country with an estimated total population of 87 million According to data from the United Nations Children's Fund, from 2003 to 2008 the average annual number of births in the country was 1494 000 and the average annual prevalence of low birth weight was 7% In 2008, the maternal mortality ratio was 150 per 100 000 live births, and the infant mortality rate was 12 per 1000 live births (14,15) We conducted a prospective health-facility-based study in Nha Trang city, in the province of Khanh Hoa The study included women from eight community health centres and one provincial hospital in the catchment area of Nha Trang, whose total population is approximately 400 000 (16) Trained midwives conducted semi-Structured interviews with women residents of the study catchment area with singleton pregnancies who were admitted to the aforementioned health institutions for delivery from 3 July 2007 to 15 June 2008 Women who delivered a stillborn or who gave birth before the 22nd week of gestation were excluded from the study A stillborn was defined as a fetus with a gestational age of at least 22 full weeks that did not breathe, cry or show minimal movement of the chest or limbs at birth Ethical approval The institutional review boards of the University of Tokyo (Tokyo, Japan) and the National Institute of Hygiene and Epidemiology (Hanoi, Viet Nam) approved the study All participants received detailed information about the study and were asked to give written informed consent …

Maternal Body Mass Index and Gestational Weight Gain and Their Association with Perinatal Outcomes in Viet Nam/ Indice Maternel De Masse Corporelle et Augmentation Du Poids En Gestation et Leur Association Avec Les Observations Perinatales Au Viet Nam/Relacion Entre Los Resultados Perinatales En Viet Nam Y El Indice De Masa Corporal De la Madre Y El Aumento De Peso Durante El Embarazo

Preeclampsia, a multisystem disorder in pregnancy, is still one of the main causes of maternal morbidity and mortality. Due to a lack of a causative therapy, an accurate prediction of women at risk for the disease and its associated adverse outcomes is of utmost importance to tailor care. In the past two decades, there have been successful improvements in screening as well as in the prediction of the disease in high-risk women. This is due to, among other things, the introduction of biomarkers such as the sFlt-1/PlGF ratio. Recently, the traditional definition of preeclampsia has been expanded based on new insights into the pathophysiology and conclusive evidence on the ability of angiogenic biomarkers to improve detection of preeclampsia-associated maternal and fetal adverse events.However, with the widespread availability of digital solutions, such as decision support algorithms and remote monitoring devices, a chance for a further improvement of care arises. Two lines of research and application are promising: First, on the patient side, home monitoring has the potential to transform the traditional care pathway. The importance of the ability to input and access data remotely is a key learning from the COVID-19 pandemic. Second, on the physician side, machine-learning-based decision support algorithms have been shown to improve precision in clinical decision-making. The integration of signals from patient-side remote monitoring devices into predictive algorithms that power physician-side decision support tools offers a chance to further improve care.The purpose of this review is to summarize the recent advances in prediction, diagnosis and monitoring of preeclampsia and its associated adverse outcomes. We will review the potential impact of the ability to access to clinical data via remote monitoring. In the combination of advanced, machine learning-based risk calculation and remote monitoring lies an unused potential that allows for a truly patient-centered care. 

https://link.springer.com/content/pdf/10.1007/s00404-022-06864-y.pdf

New advances in prediction and surveillance of preeclampsia: role of machine learning approaches and remote monitoring

Preeclampsia is one of the leading causes of maternal deaths and pregnancy-related complications in many low-income countries. Factors related to preeclampsia include lack of prenatal care and access to medical services, lack of facilities, and inadequate diagnosis and treatment of preeclampsia patients. Early detection and prompt treatment of preeclampsia are essential for the prevention of eclampsia and other life-threatening complications. Several studies have developed the risk prediction models for preeclampsia using mobile applications and machine learning techniques. The use of a soft voting-based ensemble method and recommendation system for women at high risk of preeclampsia remains unexplored. We developed a mobile application with two functionalities of preeclampsia prediction and recommendation system for women at high risk of preeclampsia. We employed the soft voting ensemble learning for the preeclampsia prediction. We obtained a high accuracy value of 98.51% ± 0.0186% compared to the six individual classifiers (k-Nearest Neighbors, Linear SVM, RBF SVM, Gaussian Process, Multi-Layer Perceptron, and Ada Boost). Our proposed recommender system also yielded in a high accuracy value of 96.66% ± 0.0229%. Both our proposed ensemble based on soft-voting and recommendation system had small variance values, which indicated high stability.

Predicting the Risk of Preeclampsia using Soft Voting-based Ensemble and Its Recommendation

Preeclampsia is one of the illnesses associated with placental dysfunction and pregnancy-induced hypertension, which appears after the first 20 weeks of pregnancy and is marked by proteinuria and hypertension. It can affect pregnant women and limit fetal growth, resulting in low birth weights, a risk factor for neonatal mortality. Approximately 10% of pregnancies worldwide are affected by hypertensive disorders during pregnancy. In this review, we discuss the machine learning and deep learning methods for preeclampsia prediction that were published between 2018 and 2022. Many models have been created using a variety of data types, including demographic and clinical data. We determined the techniques that successfully predicted preeclampsia. The methods that were used the most are random forest, support vector machine, and artificial neural network (ANN). In addition, the prospects and challenges in preeclampsia prediction are discussed to boost the research on artificial intelligence systems, allowing academics and practitioners to improve their methods and advance automated prediction.

/pdf/prediction-of-preeclampsia-using-machine-learning-and-deep-2ds9z1jo.pdf

Prediction of Preeclampsia Using Machine Learning and Deep Learning Models: A Review

Preeclampsia is one of the death causes of pregnant women and their unborn children. Preventive measures should be taken for detecting the illness as early as possible. The current paper determines the presence of preeclampsia using a non-invasive approach. The blood pressure measurements are generated using a smart bracelet which is part of the i-bracelet Eurostars project, "Intelligent bracelet for blood pressure monitoring and detection of preeclampsia". The considered input data are the age, weight and blood pressure measurements of every pregnant woman. The prediction model comprised a series of hidden states. The Viterbi algorithm was used to determine the presence of a certain hidden state, namely preeclampsia. The accuracy, sensitivity and specificity values of the tested solution prove that it is useful in remote and hospital settings.

Constantin-Viorel Marian

Papers

Early Detection of Preeclampsia based on a Machine Learning Approach