Editorial: eDiagnostics and monitoring for precision endocrinology

COPYRIGHT © 2023 Kharb and Joshi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. TYPE Editorial PUBLISHED 04 July 2023 DOI 10.3389/fendo.2023.1229475

Females are more likely to suffer from autoimmune diseases such as Systemic lupus erythematosus (SLE). In patients with SLE, adverse pregnancy outcome occurs in about 20% of pregnancies, namely, preeclampsia (PE), abortion, preterm birth, stillbirth, renal failure and fetal growth restriction. The machine learning (ML) methodology (1) has been applied to a large cohort to identify additional predictors of adverse pregnancy outcome with mild to moderate SLE both with and without antiphospholipid antibody positivity. In this series, the first article by Deng et al. addresses the potential genetic biomarkers to predict adverse pregnancy outcomes during early and mid-pregnancy in women with systemic lupus erythematosus. They identified three predictive gene biomarkers (SEZ6, NRAD1, and LPAR4) of adverse pregnancy outcome with SLE. These findings would improve the understanding of the pathogenesis of adverse pregnancy outcome in women with SLE and contribute toward the development of personalized clinical management of pregnant women with SLE. Other machine learning strategies have also shown a promise such as EUREKA algorithm predicted obstetric risk in patients with different subsets of antiphospholipid antibodies (2). The utility of ML in aiding clinical risk stratification requires further validation and similar methodological approaches could be trialed across the autoimmune connective tissue disease spectrum to provide better prognostic information to patients at diagnosis, irrespective of their diagnostic label. Furthermore, infertility or subfertility is common in patients with autoimmune diseases (3) In their study, they documented that the bilateral axillo-breast approach (RT-BABA) is as safe and feasible as ET-BAA and even performed better in some surgical outcomes. Further prospective studies to confirm the safety of RT-BABA are needed.
The final review article gives an overview of female reproductive biology and the role of large-scale data analysis and -omics techniques in the diagnosis, prognosis, and management of female reproductive disorders. Also, the role of machine learning approaches for predictive models in prevention and management has been discussed. Personalizing maternity care by use of mobile apps and wearable devices in continuous monitoring of female (fertility-related) health and prediction of any early complications to provide personalized intervention solutions. These technologies should be implemented in the national healthcare planning systems by utilizing effective clinical decision-support tools and new educational models and machinelearning approaches along with appropriate resource allocation.
This series has focused on the role of eDiagnostics and precision medicine in endocrinology. Recent technological advances in -omics and wearable devices have transformed the rate of clinically relevant data production. Generation of data is no longer a bottleneck, but the analysis and interpretation of data into actionable information, allowing earlier diagnosis and treatment options. Sensor technologies allows tracking of heart rate, blood glucose, sleep, breath, voice etc. opening avenues for new digital biomarkers discovery. Clinical decision support systems will need highperformance algorithms to make use of big data, including the diversity it presents. Additionally, new protocols for sharing information as well as integrating patient data must be integrated in the clinical decision support systems for improved diagnosis, therapy assessment and prevention. Healthcare professionals will require training to implement and incorporate these applications into their everyday practice. Personalized preventive medicine thus can be facilitated by estimating an individual's disease risk and clinical response of a disease to a particular therapeutic option and applying personalized management accordingly.

Author contributions
SK conceived the special issue. SK and AJ wrote a review article and wrote the editorial. All authors approved the final version.

Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.