Machine learning-based clustering to identify the combined effect of the DNA fragmentation index and conventional semen parameters on in vitro fertilization outcomes

Peng, Tianwen; Liao, Chen; Ye, Xin; Chen, Zhicong; Li, Xiaomin; Yu, Lan; Fu, Xin; An, Geng

doi:10.1186/s12958-023-01080-y

Cited by 5 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 15 Notably, applying these sophisticated algorithms has facilitated the clustering of diverse cases of male subfertility. 16 , 17 , 18 However, a clear methodology for detecting TE patterns that are associated with male subfertility has not been established.…”

Section: Introductionmentioning

confidence: 99%

A new clustering model based on the seminal plasma/serum ratios of multiple trace element concentrations in male patients with subfertility

Tanaka,

Kojo,

Nagumo

et al. 2024

Reprod Medicine & Biology

View full text Add to dashboard Cite

PurposeTo investigate whether seminal plasma (SP)/serum ratios of multiple trace elements (TEs) can classify patients with male subfertility.MethodsSP/serum ratios of 20 TEs (lithium, sodium, magnesium, phosphorus, sulfur, potassium, calcium, manganese, iron, cobalt, copper, zinc, arsenic, selenium, rubidium, strontium, molybdenum, cesium, barium, and thallium) were calculated for healthy volunteers (n = 4) and those consulting for male subfertility (n = 245). Volunteer semen samples were collected by split ejaculation into early and subsequent fractions, and SP/serum ratio data were compared between fractions. The patients' SP/serum ratio data were used in an unsupervised clustering analysis and qualitatively compared with the data from the fractions of ejaculation from the volunteers. Semen quality parameters and pregnancy outcomes were compared between patient clusters.ResultsThe early fraction of volunteers was characterized by lower phosphorus and arsenic and 18 other higher TEs than the subsequent fraction. Cluster analysis classified patients into four distinct clusters, one sharing characteristics with the early fraction and another with the subsequent fraction. One cluster with the early fraction characteristics had significantly lower semen volume and higher pregnancy rates from spontaneous pregnancies or intrauterine insemination.ConclusionsClassification of patients based on SP/serum ratios of multiple TEs represents the dominance of fractions of ejaculation samples.

show abstract

Section: Introductionmentioning

confidence: 99%

A new clustering model based on the seminal plasma/serum ratios of multiple trace element concentrations in male patients with subfertility

Tanaka,

Kojo,

Nagumo

et al. 2024

Reprod Medicine & Biology

View full text Add to dashboard Cite

show abstract

“…Thus, the level of evidence for SDF should be interpreted with caution. Many studies have reported a negative correlation between increased SDF and natural and assisted reproductive technology outcomes 29,32–34 . SDF is used to evaluate the integrity of sperm chromatin, and an increase in DNA‐damaged sperm can lead to embryo genomic damage after fertilization, potentially causing errors in DNA transcription and translation during the different stages of embryo development, ultimately resulting in developmental arrest 35,36 .…”

Section: Discussionmentioning

confidence: 99%

“…Many studies have reported a negative correlation between increased SDF and natural and assisted reproductive technology outcomes. 29,[32][33][34] SDF is used to evaluate the integrity of sperm chromatin, and an increase in DNA-damaged sperm can lead to embryo genomic damage after fertilization, potentially causing errors in DNA transcription and translation during the different stages of embryo development, ultimately resulting in developmental arrest. 35,36 The 2018 ESHRE guidelines for RPL suggested that SDF may be a cause of unexplained RPL, with moderate-level evidence to support its use as a diagnostic test.…”

Section: Possible Explanations Based On the Available Evidencementioning

confidence: 99%

Association between semen parameters and recurrent pregnancy loss: An umbrella review of meta‐analyses

Zhang,

Li,

Han

et al. 2024

J of Obstet and Gynaecol

View full text Add to dashboard Cite

AimRecurrent pregnancy loss (RPL) is a common clinical reproductive problem. With research advancements, an increasing number of studies have suggested that male factors play an important role in RPL. However, the evaluation results of male sperm quality in published meta‐analyses are inconsistent. We aimed to summarize the evidence of the association between semen factors and RPL and evaluate the level and validity of the evidence.MethodsWe searched PubMed, Cochrane Library, EMBASE, Web of Science, and Scopus databases for systematic reviews or meta‐analyses to evaluate the association between male semen parameters and RPL. The methodological quality of the included meta‐analyses was assessed, and data and evidence were re‐synthesized and stratified using a random‐effects model.ResultsSeven meta‐analyses and nine semen parameters were included in the final analysis. The methodological quality of all publications was considered low or very low. There was highly suggestive evidence for the association between sperm DNA fragmentation (SDF), sperm progressive motility rate, and RPL (class II). The evidence level for the association between sperm concentration, normal sperm morphology, sperm deformity rate, total motility, and RPL was suggestive evidence (class III). The evidence level for the association between sperm volume and sperm count and RPL was weak (class IV). There was no significant association between sperm pH and RPL (class NS).ConclusionsOur results suggest level II evidence for the association between male SDF and RPL, while the evidence level for the association between conventional semen routine parameters and RPL was low (classes III and IV).

show abstract

“…Emerging evidence increasingly suggests that sperm DNA fragmentation is associated with reduced male reproductive capability and can be assessed in combination with conventional sperm analysis 64 . However, routine testing remains contentious and may not necessarily provide predictive value 65 .…”

Section: Dna Fragmentationmentioning

confidence: 99%

The prospect of artificial intelligence to personalize assisted reproductive technology

Hanassab,

Abbara,

Yeung

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

Infertility affects 1-in-6 couples, with repeated intensive cycles of assisted reproductive technology (ART) required by many to achieve a desired live birth. In ART, typically, clinicians and laboratory staff consider patient characteristics, previous treatment responses, and ongoing monitoring to determine treatment decisions. However, the reproducibility, weighting, and interpretation of these characteristics are contentious, and highly operator-dependent, resulting in considerable reliance on clinical experience. Artificial intelligence (AI) is ideally suited to handle, process, and analyze large, dynamic, temporal datasets with multiple intermediary outcomes that are generated during an ART cycle. Here, we review how AI has demonstrated potential for optimization and personalization of key steps in a reproducible manner, including: drug selection and dosing, cycle monitoring, induction of oocyte maturation, and selection of the most competent gametes and embryos, to improve the overall efficacy and safety of ART.

show abstract

Machine learning-based clustering to identify the combined effect of the DNA fragmentation index and conventional semen parameters on in vitro fertilization outcomes

Cited by 5 publications

References 41 publications

A new clustering model based on the seminal plasma/serum ratios of multiple trace element concentrations in male patients with subfertility

A new clustering model based on the seminal plasma/serum ratios of multiple trace element concentrations in male patients with subfertility

Association between semen parameters and recurrent pregnancy loss: An umbrella review of meta‐analyses

The prospect of artificial intelligence to personalize assisted reproductive technology

Contact Info

Product

Resources

About