Search

Background: One challenge in the field of in-vitro fertilisation is the selection of the most viable embryos for transfer. Morphological quality assessment and morphokinetic analysis both have the disadvantage of intra-observer and inter-observer variability. A third method, preimplantation genetic testing for aneuploidy (PGT-A), has limitations too, including its invasiveness and cost. We hypothesised that differences in aneuploid and euploid embryos that allow for model-based classification are reflected in morphology, morphokinetics, and associated clinical information., Methods: In this retrospective study, we used machine-learning and deep-learning approaches to develop STORK-A, a non-invasive and automated method of embryo evaluation that uses artificial intelligence to predict embryo ploidy status. Our method used a dataset of 10 378 embryos that consisted of static images captured at 110 h after intracytoplasmic sperm injection, morphokinetic parameters, blastocyst morphological assessments, maternal age, and ploidy status. Independent and external datasets, Weill Cornell Medicine EmbryoScope+ (WCM-ES+; Weill Cornell Medicine Center of Reproductive Medicine, NY, USA) and IVI Valencia (IVI Valencia, Health Research Institute la Fe, Valencia, Spain) were used to test the generalisability of STORK-A and were compared measuring accuracy and area under the receiver operating characteristic curve (AUC)., Findings: Analysis and model development included the use of 10 378 embryos, all with PGT-A results, from 1385 patients (maternal age range 21-48 years; mean age 36·98 years [SD 4·62]). STORK-A predicted aneuploid versus euploid embryos with an accuracy of 69·3% (95% CI 66·9-71·5; AUC 0·761; positive predictive value [PPV] 76·1%; negative predictive value [NPV] 62·1%) when using images, maternal age, morphokinetics, and blastocyst score. A second classification task trained to predict complex aneuploidy versus euploidy and single aneuploidy produced an accuracy of 74·0% (95% CI 71·7-76·1; AUC 0·760; PPV 54·9%; NPV 87·6%) using an image, maternal age, morphokinetic parameters, and blastocyst grade. A third classification task trained to predict complex aneuploidy versus euploidy had an accuracy of 77·6% (95% CI 75·0-80·0; AUC 0·847; PPV 76·7%; NPV 78·0%). STORK-A reported accuracies of 63·4% (AUC 0·702) on the WCM-ES+ dataset and 65·7% (AUC 0·715) on the IVI Valencia dataset, when using an image, maternal age, and morphokinetic parameters, similar to the STORK-A test dataset accuracy of 67·8% (AUC 0·737), showing generalisability., Interpretation: As a proof of concept, STORK-A shows an ability to predict embryo ploidy in a non-invasive manner and shows future potential as a standardised supplementation to traditional methods of embryo selection and prioritisation for implantation or recommendation for PGT-A., Funding: US National Institutes of Health., Competing Interests: Declaration of interests OE is scientific adviser for, and an equity holder in, Freenome, Owkin, Volastra Therapeutics, OneThree Biotech, Genetic Intelligence, Acuamark DX, Harmonic Discovery, and Champions Oncology, and has received funding from Eli Lilly, Johnson & Johnson–Janssen, Sanofi, AstraZeneca, and Volastra. NZ is a paid consultant for AIVF and Fairtility, and is on the advisory board of, and has equity in, Alife Health. IH gave an academic lecture for Fairtility on a related topic (precision medicine and artificial intelligence: what we have learned and how it can impact assisted reproductive technology). JB, JEM, ZR, OE, NZ, and IH are listed as inventors on a provisional patent filed by Cornell University (application number 63/308,710) about the technology described in this study. MM received speaker fees from Merck, Vitrolife, Ferring, Theramex, and Gideon Richter. PZ holds stocks in Pfizer and Bristol Myers Squibb. JB received funding support for attending meetings for the 2022 Association for Clinical and Translational Science Conference. All other authors declare no competing interests., (Copyright © 2023 Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.)

The 2017 American College of Cardiology (ACC)/American Heart Association (AHA) lowered the diagnostic criteria for hypertension. We aimed to explore whether clustering of multiple risk factors are associated with the risk of new-onset hypertension defined by the 2017 ACC/AHA Hypertension Guideline. Subjects who attended ≥2 annual health examinations without baseline hypertension and cardiovascular disease were included. Hypertension was defined according to the 2017 ACC/AHA Hypertension Guideline. Seven predefined risk factors, including age, resting heart rate, overweight or obesity, dyslipidemia, hyperuricemia, impaired glucose regulation, and a poor estimated glomerular filtration rate, were analyzed. A composite, individual-level, cumulative score incorporating these seven risk factors (no = 0 point; yes = 1 point; total range of 0-7 points) was calculated. The association between the cumulative score and the risk of hypertension was analyzed using a Cox regression model. A total of 4424 (21.6%) of 20,190 subjects included had new-onset hypertension during a follow-up duration of 3.6 years. Compared with subjects with 0 points, the adjusted hazard ratios (95% confidence intervals) for the development of hypertension for those with 1, 2, 3, and ≥4 points were 1.21 (1.07-1.38), 1.34 (1.19-1.52), 1.44 (1.26-1.63), and 1.64 (1.44-1.87), respectively (P < 0.001), after adjustment for sex and baseline blood pressure. Age, resting heart rate, overweight/obesity, dyslipidemia, hyperuricemia, impaired glucose regulation, and a poor estimated glomerular filtration rate are associated with an increased risk of future hypertension. When these factors are combined, there is an accumulated increase in risk.