Three ways of knowing: the integration of clinical expertise, evidence-based medicine, and artificial intelligence in assisted reproductive technologies

Application of a methodological framework for the development and multicenter validation of reliable artificial intelligence in embryo evaluation

BACKGROUND

Artificial intelligence (AI) models analyzing embryo time-lapse images have been developed to predict the likelihood of pregnancy following in vitro fertilization (IVF). However, limited research exists on methods ensuring AI consistency and reliability in clinical settings during its development and validation process. We present a methodology for developing and validating an AI model across multiple datasets to demonstrate reliable performance in evaluating blastocyst-stage embryos.

METHODS

This multicenter analysis utilizes time-lapse images, pregnancy outcomes, and morphologic annotations from embryos collected at 10 IVF clinics across 9 countries between 2018 and 2022. The four-step methodology for developing and evaluating the AI model include: (I) curating annotated datasets that represent the intended clinical use case; (II) developing and optimizing the AI model; (III) evaluating the AI's performance by assessing its discriminative power and associations with pregnancy probability across variable data; and (IV) ensuring interpretability and explainability by correlating AI scores with relevant morphologic features of embryo quality. Three datasets were used: the training and validation dataset (n = 16,935 embryos), the blind test dataset (n = 1,708 embryos; 3 clinics), and the independent dataset (n = 7,445 embryos; 7 clinics) derived from previously unseen clinic cohorts.

RESULTS

The AI was designed as a deep learning classifier ranking embryos by score according to their likelihood of clinical pregnancy. Higher AI score brackets were associated with increased fetal heartbeat (FH) likelihood across all evaluated datasets, showing a trend of increasing odds ratios (OR). The highest OR was observed in the top G4 bracket (test dataset G4 score ≥ 7.5: OR 3.84; independent dataset G4 score ≥ 7.5: OR 4.01), while the lowest was in the G1 bracket (test dataset G1 score < 4.0: OR 0.40; independent dataset G1 score < 4.0: OR 0.45). AI score brackets G2, G3, and G4 displayed OR values above 1.0 (P < 0.05), indicating linear associations with FH likelihood. Average AI scores were consistently higher for FH-positive than for FH-negative embryos within each age subgroup. Positive correlations were also observed between AI scores and key morphologic parameters used to predict embryo quality.

CONCLUSIONS

Strong AI performance across multiple datasets demonstrates the value of our four-step methodology in developing and validating the AI as a reliable adjunct to embryo evaluation.

Artificial Intelligence in Human Reproduction

The use of artificial intelligence (AI) in human reproduction is a rapidly evolving field with both exciting possibilities and ethical considerations. This technology has the potential to improve success rates and reduce the emotional and financial burden of infertility. However, it also raises ethical and privacy concerns. This paper presents an overview of the current and potential applications of AI in human reproduction. It explores the use of AI in various aspects of reproductive medicine, including fertility tracking, assisted reproductive technologies, management of pregnancy complications, and laboratory automation. In addition, we discuss the need for robust ethical frameworks and regulations to ensure the responsible and equitable use of AI in reproductive medicine.

GYNs at the REI gates: unsolvable conundrum or unambiguous opportunity?

Contemporary fertility care has matured from a restricted, special interest in women's health care where success sometimes made magazine covers to a well-honed start-to-finish process with ever-improving success rates and an ever-expanding panoply of treatment options. Innovations in both lab and clinic have been exponential and game changing. The specialty now finds itself in the enviable position of an extensive menu of highly successful treatment options but a complicated set of circumstances of access to these options. Emerging technology such as artificial intelligence could facilitate this transition and improve access. But a key corollary to access and leveraging new technology relates to having a credentialed team to deliver care on scale and maintain best practices and outcomes. The current debate focuses on this Rubik's cube of personnel needs in reproductive endocrinology (REI) and weighs how best to expand access and maintain the culture and spirit of REI. A model to include providers other than REI viz, GYNs or APPs is now front and center. The objective of this Opinion is to define the current context for fertility care and within that context evaluate options and consider what a collaborative model that incorporates a spectrum of non-REI providers including GYNs might look like. Such a model may be feasible (or not) to expand access to care on scale while maintaining high standards and best outcomes.

On the role of artificial intelligence in analysing oocytes during in vitro fertilisation procedures

Nowadays, the most adopted technique to address infertility problems is in vitro fertilisation (IVF). However, its success rate is limited, and the associated procedures, known as assisted reproduction technology (ART), suffer from a lack of objectivity at the laboratory level and in clinical practice. This paper deals with applications of Artificial Intelligence (AI) techniques to IVF procedures. Artificial intelligence is considered a promising tool for ascertaining the quality of embryos, a critical step in IVF. Since the oocyte quality influences the final embryo quality, we present a systematic review of the literature on AI-based techniques used to assess oocyte quality; we analyse its results and discuss several promising research directions. In particular, we highlight how AI-based techniques can support the IVF process and examine their current applications as presented in the literature. Then, we discuss the challenges research must face in fully deploying AI-based solutions in current medical practice. Among them, the availability of high-quality data sets as well as standardised imaging protocols and data formats, the use of physics-informed simulation and machine learning techniques, the study of informative, descriptive yet observable features, and, above all, studies of the quality of oocytes and embryos, specifically about their live birth potential. An improved understanding of determinants for oocyte quality can improve success rates while reducing costs, risks for long-term embryo cultures, and bioethical concerns.

Moonshot. Long shot. Or sure shot. What needs to happen to realize the full potential of AI in the fertility sector?

Quality healthcare requires two critical components: patients' best interests and best decisions to achieve that goal. The first goal is the lodestar, unchanged and unchanging over time. The second component is a more dynamic and rapidly changing paradigm in healthcare. Clinical decision-making has transitioned from an opinion-based paradigm to an evidence-based and data-driven process. A realization that technology and artificial intelligence can bring value adds a third component to the decision process. And the fertility sector is not exempt. The debate about AI is front and centre in reproductive technologies. Launching the transition from a conventional provider-driven decision paradigm to a software-enhanced system requires a roadmap to enable effective and safe implementation. A key nodal point in the ascending arc of AI in the fertility sector is how and when to bring these innovations into the ART routine to improve workflow, outcomes, and bottom-line performance. The evolution of AI in other segments of clinical care would suggest that caution is needed as widespread adoption is urged from several fronts. But the lure and magnitude for the change that these tech tools hold for fertility care remain deeply engaging. Exploring factors that could enhance thoughtful implementation and progress towards a tipping point (or perhaps not) should be at the forefront of any 'next steps' strategy. The objective of this Opinion is to discuss four critical areas (among many) considered essential to successful uptake of any new technology. These four areas include value proposition, innovative disruption, clinical agency, and responsible computing.

Harnessing Artificial Intelligence to Predict Ovarian Stimulation Outcomes in In Vitro Fertilization: Scoping Review

BACKGROUND

In the realm of in vitro fertilization (IVF), artificial intelligence (AI) models serve as invaluable tools for clinicians, offering predictive insights into ovarian stimulation outcomes. Predicting and understanding a patient's response to ovarian stimulation can help in personalizing doses of drugs, preventing adverse outcomes (eg, hyperstimulation), and improving the likelihood of successful fertilization and pregnancy. Given the pivotal role of accurate predictions in IVF procedures, it becomes important to investigate the landscape of AI models that are being used to predict the outcomes of ovarian stimulation.

OBJECTIVE

The objective of this review is to comprehensively examine the literature to explore the characteristics of AI models used for predicting ovarian stimulation outcomes in the context of IVF.

METHODS

A total of 6 electronic databases were searched for peer-reviewed literature published before August 2023, using the concepts of IVF and AI, along with their related terms. Records were independently screened by 2 reviewers against the eligibility criteria. The extracted data were then consolidated and presented through narrative synthesis.

RESULTS

Upon reviewing 1348 articles, 30 met the predetermined inclusion criteria. The literature primarily focused on the number of oocytes retrieved as the main predicted outcome. Microscopy images stood out as the primary ground truth reference. The reviewed studies also highlighted that the most frequently adopted stimulation protocol was the gonadotropin-releasing hormone (GnRH) antagonist. In terms of using trigger medication, human chorionic gonadotropin (hCG) was the most commonly selected option. Among the machine learning techniques, the favored choice was the support vector machine. As for the validation of AI algorithms, the hold-out cross-validation method was the most prevalent. The area under the curve was highlighted as the primary evaluation metric. The literature exhibited a wide variation in the number of features used for AI algorithm development, ranging from 2 to 28,054 features. Data were mostly sourced from patient demographics, followed by laboratory data, specifically hormonal levels. Notably, the vast majority of studies were restricted to a single infertility clinic and exclusively relied on nonpublic data sets.

CONCLUSIONS

These insights highlight an urgent need to diversify data sources and explore varied AI techniques for improved prediction accuracy and generalizability of AI models for the prediction of ovarian stimulation outcomes. Future research should prioritize multiclinic collaborations and consider leveraging public data sets, aiming for more precise AI-driven predictions that ultimately boost patient care and IVF success rates.

Deep learning for embryo evaluation using time-lapse: a systematic review of diagnostic test accuracy

OBJECTIVE

This study aimed to investigate the accuracy of convolutional neural network models in the assessment of embryos using time-lapse monitoring.

DATA SOURCES

A systematic search was conducted in PubMed and Web of Science databases from January 2016 to December 2022. The search strategy was carried out by using key words and MeSH (Medical Subject Headings) terms.

STUDY ELIGIBILITY CRITERIA

Studies were included if they reported the accuracy of convolutional neural network models for embryo evaluation using time-lapse monitoring. The review was registered with PROSPERO (International Prospective Register of Systematic Reviews; identification number CRD42021275916).

METHODS

Two reviewer authors independently screened results using the Covidence systematic review software. The full-text articles were reviewed when studies met the inclusion criteria or in any uncertainty. Nonconsensus was resolved by a third reviewer. Risk of bias and applicability were evaluated using the QUADAS-2 tool and the modified Joanna Briggs Institute or JBI checklist.

RESULTS

Following a systematic search of the literature, 22 studies were identified as eligible for inclusion. All studies were retrospective. A total of 522,516 images of 222,998 embryos were analyzed. Three main outcomes were evaluated: successful in vitro fertilization, blastocyst stage classification, and blastocyst quality. Most studies reported >80% accuracy, and embryologists were outperformed in some. Ten studies had a high risk of bias, mostly because of patient bias.

CONCLUSION

The application of artificial intelligence in time-lapse monitoring has the potential to provide more efficient, accurate, and objective embryo evaluation. Models that examined blastocyst stage classification showed the best predictions. Models that predicted live birth had a low risk of bias, used the largest databases, and had external validation, which heightens their relevance to clinical application. Our systematic review is limited by the high heterogeneity among the included studies. Researchers should share databases and standardize reporting.

The 10 "Cardinal Sins" in the Clinical Diagnosis and Treatment of Endometriosis: A Bayesian Approach

Evidence-based data for endometriosis management are limited. Experiments are excluded without adequate animal models. Data are limited to symptomatic women and occasional observations. Hormonal medical therapy cannot be blinded if recognised by the patient. Randomised controlled trials are not realistic for surgery, since endometriosis is a variable disease with low numbers. Each diagnosis and treatment is an experiment with an outcome, and experience is the means by which Bayesian updating, according to the past, takes place. If the experiences of many are similar, this holds more value than an opinion. The combined experience of a group of endometriosis surgeons was used to discuss problems in managing endometriosis. Considering endometriosis as several genetically/epigenetically different diseases is important for medical therapy. Imaging cannot exclude endometriosis, and diagnostic accuracy is limited for superficial lesions, deep lesions, and cystic corpora lutea. Surgery should not be avoided for emotional reasons. Shifting infertility treatment to IVF without considering fertility surgery is questionable. The concept of complete excision should be reconsidered. Surgeons should introduce quality control, and teaching should move to explain why this occurs. The perception of information has a personal bias. These are the major problems involved in managing endometriosis, as identified by the combined experience of the authors, who are endometriosis surgeons.

At-home urine estrone-3-glucuronide quantification predicts oocyte retrieval outcomes comparably with serum estradiol

Objective

To investigate the feasibility of monitoring urine estrone-3-glucuronide (E3G) with an at-home device during gonadotropin stimulation for in vitro fertilization and oocyte cryopreservation.

Design

Prospective, observational cohort study.

Setting

Private fertility clinic.

Patients

Thirty patients undergoing stimulation with a gonadotropin-releasing hormone antagonist protocol for in vitro fertilization or oocyte cryopreservation.

Interventions

Daily collection of the first urine in the morning during stimulation and analysis performed at home by each patient with the Mira Fertility Tracker.

Main Outcome Measures

Primary outcomes were correlation of urine E3G and serum estradiol (E2) concentrations on the day of trigger to the number of total and metaphase 2 oocytes (MII). Secondary outcomes of interest were the correlation of matched E3G and E2 measurements and the daily trends of E3G and E2 during stimulation.

Results

Both urine E3G and serum E2 concentrations on the day of trigger significantly correlated with retrieval outcomes to a similar extent, with E3G demonstrating slightly higher correlation to the number of MII oocytes than that demonstrated by E2 (r = 0.485 vs. 0.391, respectively). The Pearson correlation coefficient for matched E3G and E2 levels was 0.761. The correlation coefficients of determination for daily trends of E3G and E2 during stimulation were 0.7066 and 0.6102, respectively.

Conclusions

Measured on the day of trigger, urine E3G monitoring during gonadotropin stimulation was comparable with serum E2 for predicting oocyte retrieval outcomes. Matched daily samples confirmed good correlation of urine E3G and serum E2. The option of at-home estrogen monitoring with devices such as Mira offers an alternative to traditional serum monitoring that may improve patient experience.

Clinical Trial Registration Number

NCT05493202.

Reconsidering evidence-based management of endometriosis

Background: Without an adequate animal model permitting experiments the pathophysiology of endometriosis remains unclear and without a non-invasive diagnosis, information is limited to symptomatic women. Lesions are macroscopically and biochemically variable. Hormonal medical therapy cannot be blinded since recognised by the patient and the evidence of extensive surgery is limited because of the combination of low numbers of interventions of variable difficulty with variable surgical skills. Experience is spread among specialists in imaging, medical therapy, infertility, pain and surgery. In addition, the limitations of traditional statistics and p-values to interpret results and the complementarity of Bayesian inference should be realised. Objectives: To review and discuss evidence in endometriosis management Materials and Methods: A PubMed search for blinded randomised controlled trials in endometriosis. Results: Good-quality evidence is limited in endometriosis. Conclusions: Clinical experience remains undervalued especially for surgery. What is new? Evidence-based medicine should integrate traditional statistical analysis and the limitations of P-values, with the complementary Bayesian inference which is predictive and sequential and more like clinical medicine. Since clinical experience is important for grading evidence, specific experience in the different disciplines of endometriosis should be used to judge trial designs and results. Finally, clinical medicine can be considered as a series of experiments controlled by the outcome. Therefore, the clinical opinion of many has more value than an opinion.

Current trends in artificial intelligence in reproductive endocrinology

PURPOSE OF REVIEW

Artificial Intelligence, a tool that integrates computer science and machine learning to mimic human decision-making processes, is transforming the world and changing the way we live. Recently, the healthcare industry has gradually adopted artificial intelligence in many applications and obtained some degree of success. In this review, we summarize the current applications of artificial intelligence in Reproductive Endocrinology, in both laboratory and clinical settings.

RECENT FINDINGS

Artificial Intelligence has been used to select the embryos with high implantation potential, proper ploidy status, to predict later embryo development, and to increase pregnancy and live birth rates. Some studies also suggested that artificial intelligence can help improve infertility diagnosis and patient management. Recently, it has been demonstrated that artificial intelligence also plays a role in effective laboratory quality control and performance.

SUMMARY

In this review, we discuss various applications of artificial intelligence in different areas of reproductive medicine. We summarize the current findings with their potentials and limitations, and also discuss the future direction for research and clinical applications.

An Image Processing Protocol to Extract Variables Predictive of Human Embryo Fitness for Assisted Reproduction

Despite the use of new techniques on embryo selection and the presence of equipment on the market, such as EmbryoScope® and Geri®, which help in the evaluation of embryo quality, there is still a subjectivity between the embryologist’s classifications, which are subjected to inter- and intra-observer variability, therefore compromising the successful implantation of the embryo. Nonetheless, with the acquisition of images through the time-lapse system, it is possible to perform digital processing of these images, providing a better analysis of the embryo, in addition to enabling the automatic analysis of a large volume of information. An image processing protocol was developed using well-established techniques to segment the image of blastocysts and extract variables of interest. A total of 33 variables were automatically generated by digital image processing, each one representing a different aspect of the embryo and describing a different characteristic of the blastocyst. These variables can be categorized into texture, gray-level average, gray-level standard deviation, modal value, relations, and light level. The automated and directed steps of the proposed processing protocol exclude spurious results, except when image quality (e.g., focus) prevents correct segmentation. The image processing protocol can segment human blastocyst images and automatically extract 33 variables that describe quantitative aspects of the blastocyst’s regions, with potential utility in embryo selection for assisted reproductive technology (ART).

Artificial intelligence-the future is now

The pros and cons of artificial intelligence in assisted reproductive technology are presented.