Influence of ambient air pollution on successful pregnancy with frozen embryo transfer: A machine learning prediction model

Wan, Shouhong; Xin, Zhao; Niu, Zhihong; Li, Dong; Wu, Yang‐Chang; Gu, Shengyi; Feng, Yong; Hua, Xiaolin

doi:10.1016/j.ecoenv.2022.113444

Cited by 7 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…47 Thus, negatively correlation of nearsurface O3 concentration with concentrations of those precursors. As for NO2, two studies reported adverse correlation between NO2 exposure and intrauterine pregnancy in ART treatment, 43,48 while another publication observed null association. 31 Interestingly, we observed positive association of NO2 with ART outcomes.…”

Section: Discussionmentioning

confidence: 99%

Individual-level air pollutants exposure and pregnancy outcomes in patients who underwent assisted reproductive technology: A retrospective longitudinal cohort study

Fang,

Guo,

Jiang

et al. 2023

Preprint

View full text Add to dashboard Cite

Background The effects of air pollution on the results of assisted reproductive technology (ART) treatment in terms of pregnancy outcomes were inconclusive. Methods We performed an individual-level retrospective longitudinal cohort study among 11,968 participants undergoing ART treatment from a general hospital in Hefei, China in 2013-20. Monthly mean concentrations of air pollutants [fine particulate matter (PM2.5), suspended particulate matter (PM10), ozone (O3), sulfur dioxide (SO2), Nitrogen dioxide (NO2) and carbon oxide (CO)] during 3 Periods were obtained from ChinaHighAirPollutants (CHAP) dataset: respective Periods 1, 2 and 3 refer to 90 days, one or two years prior to oocyte retrieval. Multiple logistic regression model was applied to explore the impact of air pollution on four ART results (biochemical pregnancy, clinical pregnancy, pregnancy loss, and live birth). Results We observed negative relationships of PM10, PM2.5, CO and SO2 exposures with pregnancy outcomes were more evident during one year exposure (Period 2). An interquartile range increment of ambient PM10, PM2.5, CO, and SO2 exposures during Period 2 was associated with respective decrements of 5.85% (aOR: 0.94, 95% CI: 0.90–0.99), 7.82% (aOR: 0.92, 95% CI: 0.88–0.97), 10.60% (aOR: 0.89, 95% CI: 0.82–0.93) and 12.38% (aOR: 0.88, 95% CI: 0.82–0.93) on clinical pregnancy, while O3 and NO2 showed positive associations. Associations were stronger in patients undergoing frozen embryo transfer, aged < 32 years, with normal BMI, employed status, one embryo transferred, and in warm season. Conclusions Our data show that long-term individual-level exposure to the air pollutants of PM10, PM2.5, CO, SO2 but not O3 or NO2, especially in one year exposure before oocyte retrieval, could have a negative impact on ART outcomes.

show abstract

Section: Discussionmentioning

confidence: 99%

Individual-level air pollutants exposure and pregnancy outcomes in patients who underwent assisted reproductive technology: A retrospective longitudinal cohort study

Fang,

Guo,

Jiang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, for the regression problem, the evaluation indexes of the model include: coefficient of determination (R 2 ) (Uddin et al 2022;Suvarna et al 2022), mean absolute error (MAE) (Zhang et al 2021a;Lamoureux et al 2021;Chang and Medford 2021), mean square error (MSE), root mean square error (RMSE) (Wei et al 2022;Kim et al 2021) and mean absolute percentage error (MAPE) (Mir et al 2022;Ke et al 2021b;Bhagat et al 2021). For classification problems, the evaluation indicators of the model are accuracy (Liu et al 2022d), error rate, recall rate (Somarowthu et al 2011), balanced F score (F1 score) (Avakyan et al 2022;Findlay et al 2018), receiver operating characteristic (ROC) curve (Xu et al 2022;Razavi-Termeh et al 2021) and the area under ROC curve (AUROC or AUC) (Wan et al 2022;Ding et al 2022;Cashman et al 2017).…”

Section: Evaluation Metrics For Machine Learningmentioning

confidence: 99%

Synthesis optimization and adsorption modeling of biochar for pollutant removal via machine learning

Zhang

Chen

et al. 2023

Biochar

View full text Add to dashboard Cite

Due to large specific surface area, abundant functional groups and low cost, biochar is widely used for pollutant removal. The adsorption performance of biochar is related to biochar synthesis and adsorption parameters. But the influence factor is numerous, the traditional experimental enumeration is powerless. In recent years, machine learning has been gradually employed for biochar, but there is no comprehensive review on the whole process regulation of biochar adsorbents, covering synthesis optimization and adsorption modeling. This review article systematically summarized the application of machine learning in biochar adsorbents from the perspective of all-round regulation for the first time, including the synthesis optimization and adsorption modeling of biochar adsorbents. Firstly, the overview of machine learning was introduced. Then, the latest advances of machine learning in biochar synthesis for pollutant removal were summarized, including prediction of biochar yield and physicochemical properties, optimal synthetic conditions and economic cost. And the application of machine learning in pollutant adsorption by biochar was reviewed, covering prediction of adsorption efficiency, optimization of experimental conditions and revelation of adsorption mechanism. General guidelines for the application of machine learning in whole-process optimization of biochar from synthesis to adsorption were presented. Finally, the existing problems and future perspectives of machine learning for biochar adsorbents were put forward. We hope that this review can promote the integration of machine learning and biochar, and thus light up the industrialization of biochar. Graphical Abstract

show abstract

“…Most of these models take images as input, for instance, to evaluate sperm motility, concentration, and morphology for selecting high-quality sperm for fertilization [9][10][11] or for diagnosing male infertility [12][13][14], to help identify and distinguish sperm and debris in testicular sperm samples [15,16], or to examine the quality of oocytes [17]. Models have also been developed to use embryo images or time-lapse videos to grade embryos [18,19] and to predict treatment outcomes such as implantation [20], pregnancy [21], and live birth [22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Testing the reproducibility and effectiveness of deep learning models among clinics: sperm detection as a pilot study

Wang,

Jin,

Jiang

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Deep learning has been increasingly investigated for assisting clinical in vitro fertilization (IVF). The first technical step in many tasks is to visually detect and locate sperm, oocytes, and embryos in images. For clinical deployment of such deep learning models, different clinics use different image acquisition hardware and different sample preprocessing protocols, raising the concern over whether the reported accuracy of a deep learning model by one clinic could be reproduced in another clinic. Here we aim to investigate the effect of each imaging factor on the reproducibility of object detection models, using sperm analysis as a pilot example. Methods: Ablation studies were performed using state-of-the-art models for detecting human sperm to quantitatively assess how model precision (false-positive detection) and recall (missed detection) were affected by imaging magnification, imaging mode, and sample preprocessing protocols. The results led to the hypothesis that the richness of image acquisition conditions in a training dataset deterministically affects model reproducibility. The hypothesis was tested by first enriching the training dataset with a wide range of imaging conditions, then validated through internal blind tests on new samples and external multi-center clinical validations. Results: Ablation experiments revealed that removing subsets of data from the training dataset significantly reduced model precision. Removing raw sample images from the training dataset caused the largest drop in model precision, whereas removing 20x images caused the largest drop in model recall. by incorporating different imaging and sample preprocessing conditions into a rich training dataset, the model achieved an intraclass correlation coefficient (ICC) of 0.97 (95% CI: 0.94-0.99) for precision, and an ICC of 0.97 (95% CI: 0.93-0.99) for recall. Multi-center clinical validation showed no significant differences in model precision or recall across different clinics and applications. Conclusions: The results validated the hypothesis that the richness of data in the training dataset is a key factor impacting model reproducibility. These findings highlight the importance of diversity in a training dataset for model evaluation and suggest that future deep learning models in andrology and reproductive medicine should incorporate comprehensive feature sets for enhanced reproducibility across clinics.

show abstract

Influence of ambient air pollution on successful pregnancy with frozen embryo transfer: A machine learning prediction model

Cited by 7 publications

References 46 publications

Individual-level air pollutants exposure and pregnancy outcomes in patients who underwent assisted reproductive technology: A retrospective longitudinal cohort study

Individual-level air pollutants exposure and pregnancy outcomes in patients who underwent assisted reproductive technology: A retrospective longitudinal cohort study

Synthesis optimization and adsorption modeling of biochar for pollutant removal via machine learning

Testing the reproducibility and effectiveness of deep learning models among clinics: sperm detection as a pilot study

Contact Info

Product

Resources

About