Machine Learning Predictive Models for Evaluating Risk Factors Affecting Sperm Count: Predictions Based on Health Screening Indicators

Abstract

In many countries, especially developed nations, the fertility rate and birth rate have continually declined. Taiwan’s fertility rate has paralleled this trend and reached its nadir in 2022. Therefore, the government uses many strategies to encourage more married couples to have children. However, couples marrying at an older age may have declining physical status, as well as hypertension and other metabolic syndrome symptoms, in addition to possibly being overweight, which have been the focus of the studies for their influences on male and female gamete quality. Many previous studies based on infertile people are not truly representative of the general population. This study proposed a framework using five machine learning (ML) predictive algorithms—random forest, stochastic gradient boosting, least absolute shrinkage and selection operator regression, ridge regression, and extreme gradient boosting—to identify the major risk factors affecting male sperm count based on a major health screening database in Taiwan. Unlike traditional multiple linear regression, ML algorithms do not need statistical assumptions and can capture non-linear relationships or complex interactions between dependent and independent variables to generate promising performance. We analyzed annual health screening data of 1375 males from 2010 to 2017, including data on health screening indicators, sourced from the MJ Group, a major health screening center in Taiwan. The symmetric mean absolute percentage error, relative absolute error, root relative squared error, and root mean squared error were used as performance evaluation metrics. Our results show that sleep time (ST), alpha-fetoprotein (AFP), body fat (BF), systolic blood pressure (SBP), and blood urea nitrogen (BUN) are the top five risk factors associated with sperm count. ST is a known risk factor influencing reproductive hormone balance, which can affect spermatogenesis and final sperm count. BF and SBP are risk factors associated with metabolic syndrome, another known risk factor of altered male reproductive hormone systems. However, AFP has not been the focus of previous studies on male fertility or semen quality. BUN, the index for kidney function, is also identified as a risk factor by our established ML model. Our results support previous findings that metabolic syndrome has negative impacts on sperm count and semen quality. Sleep duration also has an impact on sperm generation in the testes. AFP and BUN are two novel risk factors linked to sperm counts. These findings could help healthcare personnel and law makers create strategies for creating environments to increase the country’s fertility rate. This study should also be of value to follow-up research.

Predicting Male Infertility Using Artificial Neural Networks: A Review of the Literature

“…Therefore, to answer the PICO questions formulated in the previous section, we organized and schematically summarized them in the upcoming tables. Indeed, the studies were divided based on the general topic they dealt with; therefore, the specific variables considered in each model included sperm retrieval (Table 2, four studies [37][38][39][40]); sperm quality, further divided into the investigation of sperm quality and morphology (Table 3a, seventeen studies [41][42][43][44][45][46][47][48][49][50][51][52][53][54][55][56][57]) and quality of sperm and environmental factors (Table 3b, four studies [58][59][60][61]); non-obstructive azoospermia (Table 4, three studies [62][63][64]); IVF outcome (Table 5, three studies [65][66][67]); environmental and medical factors (Table 6, twelve studies [68][69][70][71][72][73][74][75]…”

“…In these studies, about forty different AI and ML methods were used, most of the time in combination with other methods (mean = 3.1, IQR = 1-9). Two studies [37,43] reported the generic term ML, while in eight studies [42,43,[45][46][47]51,59,61], algorithms available on the industrial market were used. Of the 40 models analyzed, most are models with 73% supervised learning, 20% are unsupervised, 3% are semi-supervised, and the remaining 5% are models that can be programmed in both modes, as in the case of ANNs.…”

“…The remaining 31 models were used in percentages ranging from 3 to 1%. Despite the variety of these studies, from the different data sources processed, and the methods used, it seems very clear that ML algorithms can process a huge amount of data, as in the studies [39,43,68,79] in which the sample size exceeded one thousand units, and multiple variables were combined for the prediction. However, this does not imply that a lower number of inputs corresponds to lower model efficiency [52,55,56].…”

“…Finally, since the aim of this review was to understand not only which models were used but also what their actual level of prediction accuracy was, we analyzed the results of the reported accuracy, considering as a primary outcome measure the tested accuracy of the model in the prediction of male infertility. In six studies [43,47,[55][56][57]76], the performance of each model was not evaluated as accuracy, but an error estimation of the model prediction was made; in two studies [74,75], there was no information on the matter. In the remaining 35 studies, there was an average accuracy of 88% (IQR = 80-94%), with 26 studies declaring an accuracy greater than 80%.…”

Revolutionizing Chronic Kidney Disease Management with Machine Learning and Artificial Intelligence

“…AI is the ability of a human-made machine to display complex decision-making or data analysis compared to human intelligence [6,[10][11][12][13][14]. Machine learning is a subset of AI that involves teaching machines to recognize patterns and make predictions from data without explicit programming [15][16][17][18][19].…”