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.

An artificial intelligence platform to optimize workflow during ovarian stimulation and IVF: process improvement and outcome-based predictions.

RESEARCH QUESTION: Can workflow during IVF be facilitated by artificial intelligence to limit monitoring during ovarian stimulation to a single day and enable level-loading of retrievals? DESIGN: The dataset consisted of 1591 autologous cycles in unique patients with complete data including age, FSH, oestradiol and anti-Müllerian concentrations, follicle counts and body mass index. Observations during ovarian stimulation included oestradiol concentrations and follicle diameters. An algorithm was designed to identify the single best day for monitoring and predict trigger day options and total number of oocytes retrieved. RESULTS: The mean error to predict the single best day for monitoring was 1.355 days. After identifying the single best day for evaluation, the algorithm identified the trigger date and range of three oocyte retrieval days specified by the earliest and the latest day on which the number of oocytes retrieved was minimally changed with a variance of 0-3 oocytes. Accuracy for prediction of total number of oocytes with baseline testing alone or in combination with data on the day of observation was 0.76 and 0.80, respectively. The sensitivities for estimating the total number and number of mature oocytes based solely on pre-IVF profiles in group I (0-10) were 0.76 and 0.78, and in group II (>10) 0.76 and 0.81, respectively. CONCLUSIONS: A first-iteration algorithm is described designed to improve workflow, minimize visits and level-load embryology work. This algorithm enables decisions at three interrelated nodal points for IVF workflow management to include monitoring on the single best day, assign trigger days to enable a range of 3 days for level-loading and estimate oocyte number.

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

Decision-making in fertility care is on the cusp of a significant frameshift. Online tools to integrate artificial intelligence into the decision-making process across all aspects of ART are rapidly emerging. These tools have the potential to improve outcomes and transition decision-making from one based on traditional provider centric assessments toward a hybrid triad of expertise, evidence, and algorithmic data analytics using AI. We can look forward to a time when AI will be the third part of a provider's tool box to complement expertise and medical literature to enable ever more accurate predictions and outcomes in ART. In their fully integrated format, these tools will be part of a digital fertility ecosystem of analytics embedded within an EMR. To date, the impact of AI on ART outcomes is inconclusive. No prospective studies have shown clear cut benefit or cost reductions over current practices, but we are very early in the process of developing and evaluating these tools. We owe it to ourselves to begin to examine these AI-driven analytics and develop a very clear idea about where we can and should go before we roll these tools into clinical care. Thoughtful scrutiny is essential lest we find ourselves in a position of trying to modulate and modify after entry of these tools into our clinics and patient care. The purpose of this commentary is to highlight the evolution and impact AI has had in other fields relevant to the fertility sector and describe a vision for applications within ART that could improve outcomes, reduce costs, and positively impact clinical care.

Outcomes of medical malpractice claims in assisted reproductive technology over a 10-year period from a single carrier.

OBJECTIVE: Medical malpractice claims vary by specialty. Contributory factors to malpractice in reproductive endocrinology and infertility (REI) are not well defined. We sought to determine claims' frequency, basis of claims, and outcomes of settled claims in REI. DESIGN: This is a retrospective, descriptive review of 10 years of claims. SETTING: The setting is private practices. MATERIALS AND METHODS: Claims were monitored within one malpractice carrier between 2006 and 2015 covering 10 practices and 184,015 IVF cycles. Total claims, basis of claims, and indemnity paid were evaluated. RESULTS: There were 176 incidents resulting in 30 settled claims with indemnity payments in 21. Categories of claims settled included misdiagnosis (N = 4), lack of informed consent (N = 5), embryology errors (N = 8), and surgical complications (N = 4). Total and average awards were $15,062,000 and $717,238, respectively. Misdiagnosis and lack of informed consent had highest total award amount at $11,583,000 accounting for 76% of award dollars. The two highest awards were $4.5 million and $3.0 million for cancer and genetic misdiagnosis, respectively. Excluding these two awards, payments totaled $7,562,000, ranged from $6000 to $900,000 and averaged $170,363. Errors in handling of embryos were highest in frequency accounting for 38% of claims paid for a total of $1,593,000 with average payment of $199,188. Settlements for surgical complications totaled $1,855,000 and averaged $463,750 per claim. CONCLUSIONS: Misdiagnosis and lack of informed consent are the highest award categories. Embryology lab errors are the most frequent causes of claims with the lowest award per settlement. The average cost for claims settled is relatively high compared to settlements in other specialties.

Artificial intelligence and assisted reproductive technologies: 2023. Ready for prime time? Or not.

Artificial intelligence has transformed many aspects of health care from image analysis to clinical decision making. Its evolution in medicine has been gradual and deliberate with several unanswered questions regarding efficiency, privacy, and bias. These artificial intelligence-based tools have relevance to assisted reproductive technologies with opportunities to impact informed consent, day-to-day management of ovarian stimulation, oocyte and embryo selection, and workflow. However, implementation must be an informed, cautious, and circumspect process to maximize outcomes and improve the clinical experience for patients and providers alike.

Legal personhood and frozen embryos: implications for fertility patients and providers in post-Roe America.

The demise of Roe v. Wade has prompted some state lawmakers to try to redefine legal personhood to begin before birth and even before pregnancy. The sweeping abortion bans passed and pending in the wake of Dobbs pose a threat to reproductive rights that extends beyond abortion. That threat spills over into in vitro fertilization (IVF) and other assisted reproductive technologies (ART). If legislatures designate embryos as legal persons, fertility clinics will be forced to change how they manage embryos, including current standard practices such as pre-implantation genetic testing, storage of unused embryos, and the disposal of those unlikely to have reproductive potential. This essay examines the many ways in which conferring the status of persons under private and public law is likely to impact patients pursuing IVF and clinics practicing ART.

In re: the disposition of frozen embryos: 2022.

Debates regarding reproductive rights have waxed and waned since the early twentieth century. The current front-and-center debate draws this discussion into tighter focus. Challenges to reproductive rights, changes in definitions of personhood and a pending decision regarding Roe v Wade could change the management and options regarding the disposition of frozen embryos. This commentary outlines how changes in abortion law and reproductive rights could potentially impact the options available to both patients and clinics.

Management of congenital uterine abnormalities.

Congenital uterine abnormalities are a heterogeneous group of uterine configurations that may adversely affect reproductive potential. Although subtle variations can occur, the more common abnormalities fall into two broad categories of unilateral development or failure of midline fusion. These abnormalities have been well described for over a century although the mechanisms of their unfavourable impact on fertility and clinical management have not been systematically studied until recently. The quality of the literature on this topic has traditionally fallen below the level on which solid evidence-based decisions can be made. Nonetheless, considerable progress has been made in recent times. The understanding of the aetiology of these abnormalities and how they impact reproduction has matured and evolved and this evolution and the growing body of recent studies better define clinical scenarios in which intervention will clearly and positively impact outcome. This article will review four common congenital abnormalities, their impact on reproduction, options for management and the role of assisted reproduction treatment in maximizing reproductive potential. Recommendations are made with consideration of the quality of the literature in an outcome-driven environment.

Artificial intelligence in in vitro fertilization: a computer decision support system for day-to-day management of ovarian stimulation during in vitro fertilization.

OBJECTIVE: To describe a computer algorithm designed for in vitro fertilization (IVF) management and to assess the algorithm's accuracy in the day-to-day decision making during ovarian stimulation for IVF when compared to evidence-based decisions by the clinical team. DESIGN: Descriptive and comparative study of new technology. SETTING: Private fertility practice. INTERVENTION(S): None. PATIENT(S): Data were derived from monitoring during ovarian stimulation from IVF cycles. The database consisted of 2,603 cycles (1,853 autologous and 750 donor cycles) incorporating 7,376 visits for training. An additional 556 unique cycles were used for challenge and to calculate accuracy. There were 59,706 data points. Input variables included estradiol concentrations in picograms per milliliter; ultrasound measurements of follicle diameters in two dimensions in millimeters; cycle day during stimulation and dose of recombinant follicle-stimulating hormone during ovarian stimulation for IVF. MAIN OUTCOME MEASURE(S): Accuracy of the algorithm to predict four critical clinical decisions during ovarian stimulation for IVF: [1] stop stimulation or continue stimulation. If the decision was to stop, then the next automated decision was to [2] trigger or cancel. If the decision was to return, then the next key decisions were [3] number of days to follow-up and [4] whether any dosage adjustment was needed. RESULT(S): Algorithm accuracies for these four decisions are as follows: continue or stop treatment: 0.92; trigger and schedule oocyte retrieval or cancel cycle: 0.96; dose of medication adjustment: 0.82; and number of days to follow-up: 0.87. These accuracies are for first iteration of the algorithm. CONCLUSION(S): We describe a first iteration of a predictive analytic algorithm that is highly accurate and in agreement with evidence-based decisions by expert teams during ovarian stimulation during IVF. These tools offer a potential platform to optimize clinical decision making during IVF.

Lawsuit frequency and claims basis over lost, damaged, and destroyed frozen embryos over a 10-year period.

OBJECTIVE: To review the claims, claims basis, and frequency of lawsuits over lost or damaged frozen embryos and to estimate their frequency over a 10-year interval. DESIGN: Retrospective analysis of case law. SETTING: Private in vitro fertilization clinic and school of law. PATIENTS: None. INTERVENTIONS: Case law identified using Bloomberg Law, Westlaw, and Lexis Nexis databases for coverage of court dockets regarding allegations and claims. MAIN OUTCOME MEASURES: Lawsuits brought and settled in state and federal court, with data extracted included claims basis and location in federal or state courts. RESULTS: We reviewed case law from January 1, 2009, to April 22, 2019, using the terms frozen, discarded, lost, and damaged embryo/s, and calculated clinical cases using frozen embryos from Centers for Disease Control and Prevention data. We identified 133 cases: 122 and 11 lawsuits in the state and federal court dockets, respectively. Of these, 87 cases involved alleged freezer tank failure in California and Ohio in 2018-2019. In the remaining 44 cases, the majority (37 cases) were brought for personal injury, breach of contract or warranty, product liability, professional negligence, unfair business practices, and miscellaneous tort. A minority (7 cases) were brought for medical malpractice. During this interval, a total of 398,256 embryo-thaw procedures were reported nationally. CONCLUSIONS: Allegations range from business practices to product liability and are seldom for medical malpractice. Our results suggest that best practices in storage of frozen embryos should include not only improvements in hardware and monitoring of storage conditions of specimens but also setting standards for communications among patients, providers, and embryology laboratories regarding disposition of embryos.

Association of In Vitro Fertilization With Childhood Cancer in the United States.

Importance: In vitro fertilization (IVF) is associated with birth defects and imprinting disorders. Because these conditions are associated with an increased risk of childhood cancer, many of which originate in utero, descriptions of cancers among children conceived via IVF are imperative. Objective: To compare the incidence of childhood cancers among children conceived in vitro with those conceived naturally. Design, Setting, and Participants: A retrospective, population-based cohort study linking cycles reported to the Society for Assisted Reproductive Technology Clinical Outcomes Reporting System from January 1, 2004, to December 31, 2012, that resulted in live births from September 1, 2004, to December 31, 2013, to the birth and cancer registries of 14 states, comprising 66% of United States births and 75% of IVF-conceived births, with follow-up from September 1, 2004, to December 31, 2014. The study included 275 686 children conceived via IVF and a cohort of 2 266 847 children, in which 10 births were randomly selected for each IVF birth. Statistical analysis was performed from April 1, 2017, to October 1, 2018. Exposure: In vitro fertilization. Main Outcomes and Measures: Cancer diagnosed in the first decade of life. Results: A total of 321 cancers were detected among the children conceived via IVF (49.1% girls and 50.9% boys; mean [SD] age, 4.6 [2.5] years for singleton births and 5.9 [2.4] years for multiple births), and a total of 2042 cancers were detected among the children not conceived via IVF (49.2% girls and 50.8% boys; mean [SD] age, 6.1 [2.6] years for singleton births and 4.7 [2.6] years for multiple births). The overall cancer rate (per 1 000 000 person-years) was 251.9 for the IVF group and 192.7 for the non-IVF group (hazard ratio, 1.17; 95% CI, 1.00-1.36). The rate of hepatic tumors was higher among the IVF group than the non-IVF group (hepatic tumor rate: 18.1 vs 5.7; hazard ratio, 2.46; 95% CI, 1.29-4.70); the rates of other cancers did not differ between the 2 groups. There were no associations with specific IVF treatment modalities or indication for IVF. Conclusions and Relevance: This study found a small association of IVF with overall cancers of early childhood, but it did observe an increased rate of embryonal cancers, particularly hepatic tumors, that could not be attributed to IVF rather than to underlying infertility. Continued follow-up for cancer occurrence among children conceived via IVF is warranted.

Assessment of ovarian reserve by using the follicle-stimulating hormone isoform distribution pattern to predict the outcome of in vitro fertilization.

Changes in FSH isoforms occur at temporally specific times during the menstrual cycle and reproductive lifespan. Changes in ratio in FSH isoforms may provide a sensitive test of ovarian reserve before IVF.

Three-dimensional ultrasound-guided embryo transfer: a preliminary study.

OBJECTIVE: Embryo transfer techniques have emerged as 1 of the most important variables during in vitro fertilization. Two-dimensional ultrasound guidance is an integral part of this procedure and a method to monitor catheter passage through the cervix into the endometrial cavity. Catheter placement may better be achieved with 3-dimensional monitoring to assess the relationship of the catheter tip to the uterine cavity. The purpose of this study was to compare the precision of catheter placement and position by 2- and 3-dimensional ultrasound. STUDY DESIGN: Twenty-four patients were studied. The cervix, uterus, and endometrial cavity were prescreened in 2 dimensions at the midline in the longitudinal plane of the uterus. Embryo transfers were then performed under 2-dimensional guidance. After satisfactory catheter placement and transfer of the embryos, the catheter was held in place for 60 to 120 seconds. During this interval, an automated, single sweep of the uterus and endometrial cavity was performed for net volume acquisition. All images were stored and retrospectively reviewed. Embryo transfer catheter placement with 2-dimensional ultrasound guidance was then compared with the images obtained in 3 simultaneous planes. RESULTS: Visualization of the embryo catheter tip with 2-dimensional ultrasound was achieved in all patients. These images suggested that the catheter was 2 cm from the uterine fundus and in the midline. Satisfactory 3-dimensional images for review and comparison were obtained in 21 of 24 patients. Three-dimensional ultrasound images confirmed placement and agreed with findings of 2-dimensional ultrasound images in 17 of 21 patients. In 4 patients, the catheter tip on 3-dimensional ultrasound was observed to be displaced either anteriorly or laterally from the ideal region as suggested by 2-dimensional ultrasound. In 1 case, the catheter tip on 3-dimensional ultrasound was observed to be far laterally in the region of the uterine cornua. CONCLUSION: Two-dimensional ultrasound-guided embryo transfer continues to be the standard for image-guided transfers. Data of the present study suggest that the precision of catheter tip placement and consequently embryo transfer may be improved with 3-dimensional imaging. Four of 21 patients studied had catheter tip placement in a different and less-than-ideal area when studied with 3-dimensional ultrasound. Three-dimensional imaging may provide an improvement in embryo transfer technique and have a positive impact on overall pregnancy rates.

The relationship of clinical response, oocyte number, and success in oocyte donor cycles.

PURPOSE: The purpose of the study was to determine if there is a threshold of clinical response to ovarian stimulation below which pregnancy rates diminish in oocyte donation cycles. METHODS: Two hundred and seventy-six oocyte donor cycles were reviewed. Data were stratified by number of oocytes retrieved and divided into pregnant versus non-pregnant outcomes. RESULTS: There were no differences in fertilization rates or clinical pregnancy rates regardless of the number of oocytes retrieved ranging from 3 to > 25. There was no difference in the mean age of the donors in pregnant versus non-pregnant cycles. CONCLUSIONS: These data suggest that a lower threshold below which cycle cancellation should be considered donation cycles is different than standard IVF.

Medical education as a science: the quality of evidence for computer-assisted instruction.

OBJECTIVE: A marked increase in the number of computer programs for computer-assisted instruction in the medical sciences has occurred over the past 10 years. The quality of both the programs and the literature that describe these programs has varied considerably. The purposes of this study were to evaluate the published literature that described computer-assisted instruction in medical education and to assess the quality of evidence for its implementation, with particular emphasis on obstetrics and gynecology. STUDY DESIGN: Reports published between 1988 and 2000 on computer-assisted instruction in medical education were identified through a search of MEDLINE and Educational Resource Identification Center and a review of the bibliographies of the articles that were identified. Studies were selected if they included a description of computer-assisted instruction in medical education, regardless of the type of computer program. Data were extracted with a content analysis of 210 reports. The reports were categorized according to study design (comparative, prospective, descriptive, review, or editorial), type of computer-assisted instruction, medical specialty, and measures of effectiveness. RESULTS: Computer-assisted instruction programs included online technologies, CD-ROMs, video laser disks, multimedia work stations, virtual reality, and simulation testing. Studies were identified in all medical specialties, with a preponderance in internal medicine, general surgery, radiology, obstetrics and gynecology, pediatrics, and pathology. Ninety-six percent of the articles described a favorable impact of computer-assisted instruction in medical education, regardless of the quality of the evidence. Of the 210 reports that were identified, 60% were noncomparative, descriptive reports of new techniques in computer-assisted instruction, and 15% and 14% were reviews and editorials, respectively, of existing technology. Eleven percent of studies were comparative and included some form of assessment of the effectiveness of the computer program. These assessments included pre- and posttesting and questionnaires to score program quality, perceptions of the medical students and/or residents regarding the program, and impact on learning. In one half of these comparative studies, computer-assisted instruction was compared with traditional modes of teaching, such as text and lectures. Six studies compared performance before and after the computer-assisted instruction. Improvements were shown in 5 of the studies. In the remainder of the studies, computer-assisted instruction appeared to result in similar test performance. Despite study design or outcome, most articles described enthusiastic endorsement of the programs by the participants, including medical students, residents, and practicing physicians. Only 1 study included cost analysis. Thirteen of the articles were in obstetrics and gynecology. CONCLUSION: Computer-assisted instruction has assumed to have an increasing role in medical education. In spite of enthusiastic endorsement and continued improvements in software, few studies of good design clearly demonstrate improvement in medical education over traditional modalities. There are no comparative studies in obstetrics and gynecology that demonstrate a clear-cut advantage. Future studies of computer-assisted instruction that include comparisons and cost assessments to gauge their effectiveness over traditional methods may better define their precise role.

Anovulation in the prevention of cytotoxic-induced follicular attrition and ovarian failure.

BACKGROUND: Gonadal failure secondary to alkylating agents may be related to ovulatory status. The objective of this investigation was to evaluate whether anovulation protected ovarian follicles during treatment with cyclophosphamide. METHODS: Four groups (n = 20 mature female Sprague-Dawley rats per group) were studied: control (group I), 5 mg/kg/day cyclophosphamide only (group II), 5 mg/kg/day cyclophosphamide and the combination of 50 micro g ethinyl estradiol/2 mg norgestrel (group III) and 5 mg/kg/day cyclophosphamide and 2.5 micro g leuprolide acetate daily (group IV). Animals were sacrificed after 4 weeks of treatment. Follicles were classified as medium (300-450 micro m) and large (>450 micro m) per section of ovary. RESULTS: Group II developed a significantly greater number of medium and large follicles [15.1 +/- 6.1 and 4.9 +/- 1.9 (mean +/- SD), respectively] compared with group I [7.1 +/- 2.1 and 1.0 +/- 0.7 (mean +/- SD), respectively] (P

How virtual reality may enhance training in obstetrics and gynecology.

OBJECTIVE: Contemporary training in obstetrics and gynecology is aimed at the acquisition of a complex set of skills oriented to both the technical and personal aspects of patient care. The ability to create clinical simulations through virtual reality (VR) may facilitate the accomplishment of these goals. The purpose of this paper is 2-fold: (1) to review the circumstances and equipment in industry, science, and education in which VR has been successfully applied, and (2) to explore the possible role of VR for training in obstetrics and gynecology and to suggest innovative and unique approaches to enhancing this training. MATERIAL AND METHODS: Qualitative assessment of the literature describing successful applications of VR in industry, law enforcement, military, and medicine from 1995 to 2000. Articles were identified through a computer-based search using Medline, Current Contents, and cross referencing bibliographies of articles identified through the search. RESULTS: One hundred and fifty-four articles were reviewed. This review of contemporary literature suggests that VR has been successfully used to simulate person-to-person interactions for training in psychiatry and the social sciences in a variety of circumstances by using real-time simulations of personal interactions, and to launch 3-dimensional trainers for surgical simulation. These successful applications and simulations suggest that this technology may be helpful and should be evaluated as an educational modality in obstetrics and gynecology in two areas: (1) counseling in circumstances ranging from routine preoperative informed consent to intervention in more acute circumstances such as domestic violence or rape, and (2) training in basic and advanced surgical skills for both medical students and residents. CONCLUSION: Virtual reality is an untested, but potentially useful, modality for training in obstetrics and gynecology. On the basis of successful applications in other nonmedical and medical areas, VR may have a role in teaching essential elements of counseling and surgical skill acquisition.