Clinical prediction models for in vitro fertilization outcomes: a systematic review, meta-analysis, and external validation

Human Reproduction, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 21, 2025

Abstract STUDY QUESTION What is the best-performing model currently predicting live birth outcomes for IVF or ICSI? SUMMARY ANSWER Among identified prognostic models, McLernon’s post-treatment outperforms other models in both meta-analysis and external validation of a Chinese cohort. WHAT IS KNOWN ALREADY With numerous similar available across different time periods using various predictors there need to summarize evaluate them, due lack validated evidence distinguishing high-quality from low-quality prediction tools. However, notable dearth research form assessing performance births this field. DESIGN, SIZE, DURATION The researchers conducted comprehensive literature review PubMed, EMBASE, Web Science, keywords related IVF/ICSI outcomes. search included studies published up 3 April 2024, was limited English language studies. PARTICIPANTS/MATERIALS, SETTING, METHODS that developed while providing clear reports on characteristics. Researchers extracted analysed data accordance with guidelines outlined Preferred Reporting Items Systematic Reviews Meta-Analyses model-related guidelines. For effects meta-analysis, choice would be based heterogeneity assessed I2 statistic Cochrane Q test. Model evaluated by their area under receiver operating characteristic curves (AUCs) calibration plots MAIN RESULTS AND THE ROLE OF CHANCE This provides summary derived 72 an overall ROB high unclear. These contained total 132 86 then meta-analyses were performed each five selected models. random Templeton’s, Nelson’s, pre-treatment demonstrated AUCs 0.65 (95% CI: 0.61–0.69), 0.63 0.63–0.64), 0.67 0.62–0.71), 0.73 0.71–0.75), respectively. fixed intelligent analysis score (iDAScore) estimated AUC 0.66 0.63–0.68). initial four our cohort produced ranging 0.53 0.58, confirmed through plots. LIMITATIONS, REASONS FOR CAUTION While focus English-language may constrain generalizability findings diverse populations, approach equips clinicians, who view as ultimate objective, more precise actionable reference WIDER IMPLICATIONS FINDINGS study represents first field definitively confirming superior model. conclusion reinforced independent another perspective. Nevertheless, further investigation warranted develop new externally validate existing high-performing accuracy FUNDING/COMPETING INTEREST(S) supported National Natural Science Foundation China (Grant No. 82174517). authors report no conflict interest. REGISTRATION NUMBER 2022 CRD42022312018.

Language: Английский

---

Opportunities and limitations of introducing artificial intelligence technologies into reproductive medicine

Obstetrics Gynecology and Reproduction, Journal Year: 2025, Volume and Issue: unknown

Published: March 14, 2025

Given the increasing problem of infertility in Russian Federation, assisted reproductive technologies (ART) have proven to be one most effective treatments for this condition. Notably, introduction ART methods, particularly vitro fertilization (IVF), has led markedly increased birth rates over past two decades. Studies show that machine learning algorithms can process images embryos assess their quality, thus facilitating selection viable among them transfer. There are ethical and technical barriers hindering widespread adoption artificial intelligence (AI) clinical practice, including concerns data privacy as well a need train specialists deal with new technologies. AI analyze vast amounts data, medical histories research results, more accurately predict pregnancy outcomes. This enables doctors make justified decisions. In future, will able patient efficiently, helping identify causes at earlier stages.

Language: Английский

---

A review of artificial intelligence applications in in vitro fertilization

Journal of Assisted Reproduction and Genetics, Journal Year: 2024, Volume and Issue: 42(1), P. 3 - 14

Published: Oct. 14, 2024

Language: Английский

---

Artificial Intelligence in IVF Laboratories: Elevating Outcomes Through Precision and Efficiency

Biology, Journal Year: 2024, Volume and Issue: 13(12), P. 988 - 988

Published: Nov. 28, 2024

Incorporating artificial intelligence (AI) into in vitro fertilization (IVF) laboratories signifies a significant advancement reproductive medicine. AI technologies, such as neural networks, deep learning, and machine promise to enhance quality control (QC) assurance (QA) through increased accuracy, consistency, operational efficiency. This comprehensive review examines the effects of on IVF laboratories, focusing its role automating processes embryo sperm selection, optimizing clinical outcomes, reducing human error. AI’s data analysis pattern recognition capabilities offer valuable predictive insights, enhancing personalized treatment plans increasing success rates fertility treatments. However, integrating also brings ethical, regulatory, societal challenges, including concerns about security, algorithmic bias, human–machine interface decision-making. Through an in-depth examination current case studies, advancements, future directions, this manuscript highlights how can revolutionize by standardizing processes, improving patient advancing precision It underscores necessity ongoing research ethical oversight ensure fair transparent applications sensitive field, assuring responsible use

Language: Английский

---

Detection of Interleukin-1 β (IL-1β) in Single Human Blastocyst-Conditioned Medium Using Ultrasensitive Bead-Based Digital Microfluidic Chip and Its Relationship with Embryonic Implantation Potential

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(7), P. 4006 - 4006

Published: April 3, 2024

The implantation of human embryos is a complex process involving various cytokines and receptors expressed by both endometrium embryos. However, the role produced single embryo in successful largely unknown. This study aimed to investigate IL-1β single-embryo-conditioned medium (ECM) implantation. Seventy samples ECM were analyzed specially designed magnetic-beads-based microfluidic chip from 15 women. We discovered that level increased as developed, difference was significant. In addition, receiver operator characteristic (ROC) curves analysis showed higher chance pregnancy when on day 5 below 79.37 pg/mL between 3 24.90 pg/mL. Our possible association embryonic proteomic expression implantation, which might facilitate single-embryo transfer future helping clinicians identify with greatest potential.

Language: Английский

---

The current clinical applications of preimplantation genetic testing (PGT): acknowledging the limitations of biology and technology

Expert Review of Molecular Diagnostics, Journal Year: 2024, Volume and Issue: 24(9), P. 767 - 775

Published: Aug. 7, 2024

Preimplantation Genetic Testing (PGT) is a cutting-edge test used to detect genetic abnormalities in embryos fertilized through Medically Assisted Reproduction (MAR). PGT aims ensure that selected for transfer are free of specific conditions or chromosome abnormalities, thereby reducing chances unsuccessful MAR cycles, complicated pregnancies, and diseases future children.

Language: Английский

---

Advanced KPI Framework for IVF Pregnancy Prediction Models in IVF protocols

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: June 4, 2024

The utilization of neural networks in assisted reproductive technology is essential due to their capability process complex and multidimensional data inherent IVF procedures, offering opportunities for clinical outcome prediction, personalized treatment implementation, overall advancement fertility treatment. aim this study was develop a novel approach laboratory analysis, employing deep predict the likelihood pregnancy occurrence within an individual protocol, integrating both key performance indicators data. We conducted retrospective analysis spanning 11 years, encompassing 8732 protocols, extract most relevant features our goal train model. Internal validation performed on 1600 preimplantation genetic testing aneuploidy embryo transfers, while external across two independent clinics (over 10,000 cases). Leveraging recurrent networks, model demonstrates high accuracy predicting specific protocols (AUC: 0.68–0.86; Test accuracy: 0.78, F1 Score: 0.71, Sensitivity: 0.62; Specificity: 0.86) comparable time-lapse system but with simpler approach. Our facilitates outcomes prospective evaluation chances, thus presenting promising avenue quality management programs promotes realization medical centers.

Language: Английский

---

Investigating developmental characteristics of biopsied blastocysts stratified by mitochondrial copy numbers using time-lapse monitoring

Reproductive Biology and Endocrinology, Journal Year: 2024, Volume and Issue: 22(1)

Published: July 30, 2024

Abstract Background For in vitro fertilization (IVF), mitochondrial DNA (mtDNA) levels the trophectodermal (TE) cells of biopsied blastocysts have been suggested to be associated with cells’ developmental potential. However, scholars reached differing opinions regarding use mtDNA as a reliable biomarker for predicting IVF outcomes. Therefore, this study aims assess association copy number measured by mitoscore embryonic characteristics and ploidy. Methods This retrospective analyzed embryos cells. The analysis was carried out using time-lapse monitoring next-generation sequencing from September 2021 2022. Five hundred fifteen were 88 patients undergoing who met inclusion criteria. Embryonic morphokinetics morphology evaluated at 118 h after insemination all recorded images. Blastocysts appropriate on day 5 or 6 underwent TE biopsy preimplantation genetic testing aneuploidy (PGT-A). Statistical involved generalized estimating equations, Pearson’s chi-squared test, Fisher’s exact Kruskal–Wallis significance level set P < 0.05. Results To examine differences between low versus high mitoscores, divided into quartiles based their mitoscore. Regarding morphokinetic characteristics, no significant most kinetics observed cleavage dysmorphisms discovered. group 1 had longer time reaching 3-cell stage tPNf (t3; median: 14.4 h) than did those 2 (median: 13.8 second cell cycle (CC2; 11.7 groups 11.3 4 11.4 h; 0.05). Moreover, lower euploid rate (22.6%) higher aneuploid (59.1%) other (39.6–49.3% 30.3–43.2%; whole-chromosomal alterations (63.4%) that (47.3%) (40.1%; A multivariate logistic regression model used analyze associations euploidy elective blastocysts. After accounting factors could potentially affect outcome, still exhibited negative likelihood (adjusted OR = 0.581, 95% CI: 0.396–0.854; 0.006). Conclusions varying DNA, identified through biopsies, displayed similar early development imaging. determined can standalone predictor euploidy.

Language: Английский

---

Neural networks pipeline for quality management in IVF laboratory

Journal of IVF-Worldwide, Journal Year: 2024, Volume and Issue: 2(4)

Published: Oct. 23, 2024

This study introduces a novel neural network-based pipeline for predicting clinical pregnancy rates in IVF treatments, integrating both and laboratory data. We developed metamodel combining deep networks Kolmogorov-Arnold networks, leveraging their complementary strengths to enhance predictive accuracy interpretability. The achieved robust performance metrics after training fitting on 11500 cases: = 0.72, AUC 0.75, F1 score 0.60, Matthews Correlation Coefficient of 0.42. According morpho-kinetical embryo evaluation, our model’s PRC 0.66 significantly improves over existing time-lapse systems prediction, demonstrating better handling imbalanced metamodel’s calibration (Brier 0.20, expected error 0.06, maximum 0.12, Hosmer-Lemeshow test p-value 0.06) indicate reliability outcomes. validated the reproducibility using an independent dataset 665 treatment cycles, showing close alignment between predicted actual (58.9% vs. 59.1%). With Bayesian method, we proposed framework historical data with real-time predictions from enabling transition retrospective prospective analysis. Our approach extends beyond conventional selection, incorporating post-analytical phase evaluation laboratory. comprehensive enables detailed analysis across different patient subpopulations time periods, facilitating identification systemic issues protocol optimization. ability track probabilities staff members allows outcome prediction assessment efficacy, providing data-driven strategy continuous improvement assisted reproductive technology.

Language: Английский

---

Advanced KPI framework for IVF pregnancy prediction models in IVF protocols

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 27, 2024

The utilization of neural networks in assisted reproductive technology is essential due to their ability process complex and multidimensional data inherent IVF procedures, offering opportunities for clinical outcome prediction, personalized treatment implementation, overall advancement fertility treatment. aim this study was develop a novel approach laboratory analysis, employing deep predict the likelihood pregnancy occurrence within an individual cycle, integrating both key performance indicators data. We conducted retrospective analysis spanning 11 years, encompassing 8732 cycles, extract most relevant features our goal train model. Internal validation performed on 1600 preimplantation genetic testing aneuploidy embryo transfers, while external across two independent clinics (over 10,000 cases). Leveraging recurrent networks, model demonstrates high accuracy predicting specific cycles (AUC = 0.68–0.86; test 0.78, F1 score 0.71, sensitivity 0.62; specificity 0.86) comparable time-lapse system but with simpler approach. Our facilitates outcomes prospective evaluation chances, thus presenting promising avenue quality management programs promotes realization medical centers.

Language: Английский

---