The Integration of Artificial Intelligence in In Vitro Fertilization: A Comprehensive Narrative Review

ABSTRACT

Artificial Intelligence (AI) in Assisted Reproductive Technology (ART) is transforming key areas of fertility treatments such as sperm collection, analysis of ovum quality, selection of embryos, genetic tests, customized treatment plans, stimulation protocols, as well as monitoring of equipment. This review article aims to review how every one of these fields is advanced by AI and the contribution to the precision, speed, and outcomes of the patients. Sperm selection in ART is enhanced by AI capacity in identifying and characterizing sperm quality through morphology, motility, and deoxyribonucleic acid (DNA) integrity, eliminating chances of human errors. A range of AI systems involves the procedure of selection and sorting of sperm in order to maximize fertilization and minimize contamination. Likewise, AI optimizes the assessment of ova quality by bringing in morphological evaluations and time-lapse video imaging for continuous observation of ova maturation. Predictive analytics in AI deal with large patient data to tailor treatment options, modify stimulation schedules, and increase the likelihood of pregnancy. In embryo selection, AI assesses morphological characteristics and developmental trends obtained from time-lapse imaging to select embryos with the best implantation chances. Combining it with genetic screening technologies, AI can identify genetic disorders on time to guarantee that only healthy genetic material is transferred. Moreover, artificial intelligence equipment tracking systems track equipment status and prognosis thus improving laboratory productivity and compliance with the relevant laws. On the ethical front, AI enhances matters of ownership, data protection, and patient safety through all these processes. With the help of AI, ART clinics can increase effectiveness, enhance patients’ satisfaction, and develop the field of fertility treatments to make them more available and affordable.

INTRODUCTION AND BACKGROUND

The first in-vitro fertilization (IVF) baby was born in 1978, assisted reproductive technology has been advanced significantly.[1] In the last 40 years, Assisted Reproductive Technology (ART) has provided an opportunity to infertile couples a chance to conceive across the world, resulting in the birth of millions of children. IVF procedures are complex and demand constant supervision. During the process, clinicians and embryologists have to make numerous vital choices.[2] Some decisions are informed by research evidence, while others are more or less based on experience, and therefore, decisions made vary from one level to the other. The saying that ART is an art. By acknowledging these difficulties, an attempt is made to find more objective, more consistent, and more effective solutions, that can improve the results, which is the reason for the increased use of data-based methods. Due to the mass of data collected during IVF cycles, artificial intelligence (AI) approaches have been developed to tailor-made treatment. These methodologies include algorithm clinical dosing tools and artificial intelligence clinical decision support system (CDSS) for embryo selection where the AI provides support, but humans make the decision.[3]

The number of reproduction clinics and reported treatments in Europe has risen significantly. The European Society of Human Reproduction and Embryology (ESHRE) includes numerous institutions offering ART services such as IVF, intracytoplasmic sperm injection (ICSI), frozen embryo transfer (FET), preimplantation genetic testing (PGT), egg donation (ED), in vitro maturation (IVM), and frozen oocyte replacement (FOR).[4] Intrauterine insemination (IUI) using both husband/partner’s and donor semen is also common. Spain, Russia, France, and Germany report the highest treatment numbers.

In summary, integrating AI into ART holds the potential to revolutionize fertility treatments by enhancing efficiency, accuracy, and personalized care, ultimately leading to better outcomes for infertile couples worldwide.

REVIEW

What can be improved?

The use of AI and ML in IVF and ART has the capability to improve different aspects of these processes to a great extent. AI systems can review embryo images and rate them based on their quality compared with human embryologists concerning embryos’ morphological and developmental characteristics, which would help predict the possibility of implantation and subsequent pregnancy.[5] Time-lapse imaging processed by AI allows for the constant observation of embryo development and the detection of patterns and anomalies leading to successful development. ML can work on the patient’s history, genetic data, and previous experiences with the treatment; it can also recommend optimized stimulation protocols and medication dosages.[6]

Additionally, AI applies the probability of success rates of the treatments depending on the characteristics of each patient, which assists in setting realistic expectations and planning treatment.[7] It may also help choose the best sperm based on motility, morphology, and DNA integrity, leading to higher fertilization rates and better embryos.[8]

Sperm selection in ART using AI

Sperm selection in ART using AI significantly enhances the accuracy and efficiency of choosing the best sperm for fertilization. AI algorithms can precisely analyze sperm morphology, assessing size, shape, and structure to identify optimal candidates, eliminating the variability and errors associated with manual methods.[9] Besides, in selecting sperm to be used for fertilization, AI also assesses sperm motility through video analysis of various aspects such as speed and the frequency of sperm movement. Besides morphology and motility, AI is useful in evaluating the DNA fragmentation of sperm, selecting those samples with the least DNA fragmentation to minimize the likelihood of genetic disorders and enhance the possibility of embryonic development.[10]

Ovum quality assessment

AI in ovum quality assessment in ART has a remarkable impact on its accuracy, consistency, and efficiency. It is possible to point to the capability of AI algorithms to analyze the images of oocytes (eggs) to assess qualitative characteristics: size, shape, and cytoplasm hue, which are the signs of oocyte quality. The use of conventional evaluation methods is generally based on the opinion of professionals, which can be highly variable.[11,12]

Selection of best quality embryo for transfer

AI makes the process very accurate and faster when selecting the best quality embryo for transfer in ART. AI in embryo selection is a complex procedure that uses a number of sophisticated methodologies that help to enhance the efficiency of selecting the best embryos with the ability to implant and result in pregnancy.[3]

Embryo morphology analysis

In this work, the morphological characteristics of embryos can be assessed using the AI algorithms proposed based on images of embryos of high resolution. Since cell morphology is one of the parameters determining embryo quality, AI allows for an accurate evaluation of all the morphological aspects, including cell uniformity, fragmentation and symmetry.[12] This lessens the subjectivity and variability that are often involved when the evaluation is done manually by the embryologists, making the outcomes more consistent and accurate.[13]

Predictive analytics

It can use big data such as demographics of ART patients, hormonal data obtained from the previous cycles, and genetic markers to determine the probability of success in terms of embryos.[14]

Genetic screening integration

PGT can be improved through the incorporation of AI in that the previous will utilize genetics and chromosomal analysis to obtain embryos with no genetic disorders. This reduces the chances of miscarriages and genetically affected children from being developed from the chosen embryos. AI can smoothen the screening process, making it faster and more effective.[15]

Non-invasive assessment

It can enhance a non-invasive approach to embryo grading, like scoring based on the analysis of the culture media for metabolites that depict the health of the embryo. Due to imaging and biochemical analysis, AI can give important information about embryo physiology without physically touching the embryos and, therefore, not damaging them, and it can provide better selection results.[16]

Real-time decision support

Decision support for embryologists can be made using AI immediately during selection. The AI systems can provide timely recommendations and alerts based on embryonic development and patient data on the best time to select the best quality embryos for transfer.[17] Artificial intelligence application in embryo selection for transfer in ART brings some improvements, mainly in precision, speed, and individualized approach.

Personalized treatment plan

This allows clinicians to adjust the intensity and frequency of stimulation sessions, the dosage of medication, and even the time spent administering medicines in response to the patient’s needs. An important step here is the use of predictive analytics because it is possible to determine the probability of a successful treatment based on the patient’s characteristics.[18] It also assists in controlling patient expectations and deciding fairly on the most suitable management steps. Also, AI can continuously monitor patients’ responses to treatment in real time, leading to program modifications.

Optimization of stimulation protocols

The application of artificial intelligence in selecting protocols for ovarian stimulation in IVF improves ART outcomes. IVF employs computer intelligence in order to take into account a wide variety of patient information, such as hormonal levels, ovarian reserve, age, medication history, and response to earlier treatments. By integrating this data, AI can determine how the specific patients under treatment will respond to the different stimulation patterns, making it possible to adjust other aspects, such as medication dosage and time.[19] Real-time monitoring and the ability to modify the protocol depending on the ovarian response allow for excessive stimulation and, thus, the occurrence of ovarian hyperstimulation syndrome (OHSS) to be avoided. In this manner, AI systems can deliver important information back to clinicians for assessment to modify the best course of action as predicted in the analysis of hormonal feedback and follicular growth.[20]

Equipment monitoring

Equipment monitoring in ART using AI introduces significant advancements in ensuring the reliability, efficiency, and safety of laboratory processes critical to successful fertility treatments. Computer-augmented monitoring systems transform how incubators, microscopes, cryopreservation equipment, and other equipment are managed and maintained.[21] Original real-time data acquisition and constant equipment condition monitoring are achieved with data on temperature, humidity, gases, and vibration parameters. If implemented, such suboptimal circumstances for the embryos or the lab can be detected and relayed to the staff before it becomes a problem in the lab.[22]

Integration with other ART technologies

Suppose in PGT, AI uses data from the patient’s genome to determine embryos with aberrations, not to transfer affected embryos to the uterus for implantation. Continuous evaluation of morphological changes of embryos, such as at the time of assessment of the developmental stages, has thus made time-lapse imaging with the help of artificial intelligence vital in selecting only the highest likely to bring viability.[23]

CONCLUSIONS

The innovations in the IVF and ART procedures whereby AI and ML offer improvement on multiple aspects of these solutions hold a lot of promise for creating change in the industry. Morphological and developmental assessments of AI algorithms for selecting embryos are much more accurate than conventional arbitrary assessments. Non-invasive imaging is done using time-lapse technology with the help of AI technology to acquire images of embryos and analyze their progression in order to identify key developmental problems that are beneficial when choosing the embryos to transfer. It also brings efficiency in the usage of the data collected from the patients as it enhances the stimulation programs for patients with different needs and adjusts the dosage level of the administered medication. AI’s predictive analysis helps in determining the likelihood of success of the treatment plan, making informed decisions, and setting expectable patient outcomes. In sperm selection, individual identification is done, and automation of morphology, motility, and DNA integrity increases fertilization rates and embryo quality. Automating the lab processes reduces errors and helps manage resources through the use of predictive maintenance and supply chains. AI also improves the accuracy of the genetic test in PGT, including detecting chromosomal abnormalities and improving the selection of embryos for positive outcomes.

Ethical clearance

Approval received from Datta Meghe Institute of Higher Education and Research.

Conflicts of interest

There are no conflicts of interest.

Funding Statement

Nil.