Dynamic Model for Assisted Reproductive Technology Outcome Prediction

Abstract Infertility is becoming a growing issue in almost all countries. Assisted Reproductive Technologies (ART) are recent development in treating infertility that give hope to the infertile couples. However, the pregnancy rates achieved with the aid of ART is considerably low, as success in ART is not only based on the treatment but also on many other controllable and uncontrollable biological, social, and environmental features. High expenditures and painful process of ART cycles are the two major barriers for opting for ART. Moreover, ART treatments are not covered by any health insurance schemes. Computational prediction models could be used to improve the success rate by predicting the treatment outcome, before the start of an ART cycle. This may suggest the couples and the doctors to decide on the next course of action i.e. either to opt for ART or opt for correcting determinants or quit the ART. With the intension to improve the success rate of ART by providing decision support system to the physicians as well to the patients before entering into the treatment this research work proposes a dynamic model for ART outcome prediction using Machine Learning (ML) techniques. The proposed dynamic model is partially implemented with the help of an ensemble of heterogeneous incremental classifier and its performance is compared with state-of-art classifiers such as Naïve Bayes (NB), Random Forest (RF), K-star etc.,using ART dataset. Performance of the model is evaluated with various metrics such as accuracy, Precision Recall Curve (PRC), Receiver Operating Characteristic (ROC), F-Measure etc., However, ROC cure area is taken as the chief metric. Evaluation results shows that the model achieves the performance with the ROC area value of 94.1 %.

Early life history of the Caribbean coral Orbicella faveolata (Scleractinia: Merulinidae) / Historia de vida temprana del coral caribeño Orbicella faveolata (Scleractinia: Merulinidae)

Introduction: Rehabilitation of hermatypic coral species that have declined in the Caribbean in recent decades is a priority. Production of sexual recruits is considered the best restoration method to aid affected populations. Objective: To gain knowledge of early life stages of Orbicella faveolata and to enhance production of new sexual recruits. Methods: Gamete bundles from the coral species O. faveolata were collected over two years (2018 and 2019) from Los Corales del Rosario y de San Bernardo Natural National Park, Cartagena, Colombia. Assisted fertilization, larval rearing, settlement (onto crustose coralline algae, CCA) and post settlement survival in laboratory conditions were monitored. Results: Embryonic and larval development were documented over 55 hours after the first cleavage, when larvae were fully developed and started pre-settlement behavior. Settlement began 7 days after first cleavage and after 37 days polyps had acquired zooxanthellae. Larval settlement was higher on Lythophyllum congestum and Titanoderma prototypum than in response to Porolithon pachydermum, Neogoniolithon sp., Hydrolithon sp., and Lythophyllum sp. Larvae did not settle on dead coral or on the negative control (sterilized seawater). After the first week post settlement survival was 59 % amongst O. faveolata recruits. During the second week, survival dropped to 42 %, and was further reduced to 0 % at the end of the third week. Conclusions: O. faveolata larvae require cues from certain CCA species to settle, they do not settle in absence of CCA. Increased larvae availability is possible through assisted fertilization in the laboratory, however, due to the high mortality in early post-settlement phases, additional research needs to be conducted in order to scale up larvae production and improve understanding of the cues that enhance settlement and the factors which cause post-settlement mortality.

Introducción: La rehabilitación de las especies de corales hermatípicos del Caribe que han disminuido en las últimas décadas es una prioridad. La producción de reclutas sexuales se considera el mejor método de restauración para ayudar a las poblaciones afectadas. Objetivo: Obtener conocimiento de las primeras etapas de la vida de O. faveolata y mejorar la producción de nuevos reclutas sexuales. Métodos: Por dos años (2018 y 2019), seis días después de luna llena en septiembre, se recolectaron paquetes gaméticos en arrecifes del Parque Nacional Natural Los Corales del Rosario y de San Bernardo, Cartagena, Colombia. Se siguió la fertilización asistida, la cría de larvas, el asentamiento y la supervivencia posterior al asentamiento en algas coralinas costrosas (ACC) en condiciones de laboratorio. Resultados: El desarrollo de embriones y larvas se documenta a lo largo de 55 h después del primer clivaje, cuando la larva está desarrollada completamente y comenzó el comportamiento previo al asentamiento. El asentamiento comienza 7 días después del primer clivaje y 37 días después, la mayoría de los pólipos presentan zooxantelas. El asentamiento larval fue más alto en Lythophyllum congestum y Titanoderma prototypum que en respuesta a Porolithon pachydermum, Neogoniolithon sp., Hydrolithon sp., y Lythophyllum sp. No hubo asentamiento sobre coral muerto ni en el control negativo (agua de mar esterilizada). La supervivencia bajó de un 59 % en la primera semana después del asentamiento, a 42 % durante la segunda semana y 0 % para el final de la tercera semana. Conclusiones: Las larvas de O. faveolata requieren señales de ciertas especies de ACC para asentarse, ellas no se asientan en ausencia de ACC. La disponibilidad de larvas es posible mediante la fertilización asistida en laboratorio. Sin embargo, debido a la alta mortalidad en las primeras fases posteriores al asentamiento, queda mucho por hacer para aumentar la producción de larvas y mejorar nuestro conocimiento y comprensión de las señales que mejoran el asentamiento y las que previenen o inhiben la supervivencia del recluta.