'Intracytoplasmic sperm injection (ICSI) paradox' and 'andrological ignorance': AI in the era of fourth industrial revolution to navigate the blind spots

The quandary known as the Intracytoplasmic Sperm Injection (ICSI) paradox is found at the juncture of Assisted Reproductive Technology (ART) and 'andrological ignorance' - a term coined to denote the undervalued treatment and comprehension of male infertility. The prevalent use of ICSI as a solution for severe male infertility, despite its potential to propagate genetically defective sperm, consequently posing a threat to progeny health, illuminates this paradox. We posit that the meteoric rise in Industrial Revolution 4.0 (IR 4.0) and Artificial Intelligence (AI) technologies holds the potential for a transformative shift in addressing male infertility, specifically by mitigating the limitations engendered by 'andrological ignorance.' We advocate for the urgent need to transcend andrological ignorance, envisaging AI as a cornerstone in the precise diagnosis and treatment of the root causes of male infertility. This approach also incorporates the identification of potential genetic defects in descendants, the establishment of knowledge platforms dedicated to male reproductive health, and the optimization of therapeutic outcomes. Our hypothesis suggests that the assimilation of AI could streamline ICSI implementation, leading to an overall enhancement in the realm of male fertility treatments. However, it is essential to conduct further investigations to substantiate the efficacy of AI applications in a clinical setting. This article emphasizes the significance of harnessing AI technologies to optimize patient outcomes in the fast-paced domain of reproductive medicine, thereby fostering the well-being of upcoming generations.

Using feature optimization and LightGBM algorithm to predict the clinical pregnancy outcomes after in vitro fertilization

Background

According to a recent report by the WHO, approximately 17.5\% (about one-sixth) of the global adult population is affected by infertility. Consequently, researchers worldwide have proposed various machine learning models to improve the prediction of clinical pregnancy outcomes during IVF cycles. The objective of this study is to develop a machine learning(ML) model that predicts the outcomes of pregnancies following in vitro fertilization (IVF) and assists in clinical treatment.

Methods

This study conducted a retrospective analysis on provincial reproductive centers in China from March 2020 to March 2021, utilizing 13 selected features. The algorithms used included XGBoost, LightGBM, KNN, Naïve Bayes, Random Forest, and Decision Tree. The results were evaluated using performance metrics such as precision, recall, F1-score, accuracy and AUC, employing five-fold cross-validation repeated five times.

Results

Among the models, LightGBM achieved the best performance, with an accuracy of 92.31%, recall of 87.80%, F1-score of 90.00\%, and an AUC of 90.41%. The model identified the estrogen concentration at the HCG injection(etwo), endometrium thickness (mm) on HCG day(EM TNK), years of infertility(Years), and body mass index(BMI) as the most important features.

Conclusion

This study successfully demonstrates the LightGBM model has the best predictive effect on pregnancy outcomes during IVF cycles. Additionally, etwo was found to be the most significant predictor for successful IVF compared to other variables. This machine learning approach has the potential to assist fertility specialists in providing counseling and adjusting treatment strategies for patients.

Deep Inception-ResNet: A Novel Approach for Personalized Prediction of Cumulative Pregnancy Outcomes in Vitro Fertilization Treatment (IVF)

Background

Infertility is one of the major causes of socioeconomic stress worldwide due to social stigma and stressful lifestyles. Despite technological advances, couples still undergo several IVF cycles for conceiving without knowing their true prognosis which is causing a huge social and medical impact, and the live birth rate continues to be relatively low (~ 25%). A prediction model that predicts IVF prognosis accurately considering the pre-treatment parameters before starting the IVF cycle will help clinicians and patients to make better-informed choices.

Methods

In this study, clinical details of 2268 patients with 79 features who underwent IVF/ICSI procedure from January 2018 to December 2020, at the Center of IVF and Human Reproduction, Sir Ganga Ram Hospital were retrospectively collected. The machine learning model was developed considering features such as maternal age, number of IVF cycle, type of infertility, duration of infertility, AMH, indication for IVF, sperm type, BMI, embryo transfer, and β-hCG value at the end of a fresh cycle and/or one subsequent frozen embryo transfer cycle was selected as the measure of outcome.

Results

Compared to other classifiers, for an 80:20 train-test split with feature selection, the proposed Deep Inception-Residual Network architecture-based neural network gave the best accuracy (76%) and ROC-AUC score of 0.80. For tabular datasets, the applied approach has remained unexplored in previously made studies for reproductive health.

Conclusion

This model is the starting point for providing a personalized prediction of a successful outcome for an infertile couple before they enter the IVF procedure.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13224-023-01773-9.

Modification of Case-Based Reasoning Similarity Formula to Enhance the Performance of Smart System in Handling the Complaints of in vitro Fertilization Program Patients

Objectives

Eighty percent of in vitro fertilization (IVF) patients have high anxiety levels, which influence the success of IVF and drive IVF patients to quickly report any abnormal symptoms. Rapid responses from fertility subspecialist doctors may reduce patients’ anxiety levels, but fertility subspecialist doctors’ high workload and their patients’ worsening health conditions make them unable to handle IVF patients’ complaints quickly. Research suggests that smart systems using case-based reasoning (CBR) can help doctors handle patients quickly. However, a prior study reported enhanced accuracy by modifying the CBR similarity formula based on Lin’s similarity theory to generate the Chris case-based reasoning (CCBR) similarity formula.

Methods

The data were validated through interviews with two fertility subspecialist doctors, interviews with two IVF patients, a questionnaire administered to 17 community members, the relevant literature, and 256 records with data on IVF patients’ complaints and how they were handled. An experiment compared the performance of the CBR similarity formula algorithm with the CCBR similarity formula algorithm.

Results

A confusion matrix showed that the CCBR similarity formula had an accuracy value of 52.58% and a precision value of 100%. Fertility subspecialist doctors stated that 89.69% of the CCBR similarity formula recommendations were accurate.

Conclusions

We recommend applying a combination of the CCBR similarity formula and a minimum reference value of 80% with a CBR smart system for handling IVF patients’ complaints. This recommendation for an accurate system produced by the CBR similarity formula may help fertility subspecialist doctors handle IVF patients’ complaints.