Dataset Information

Machine-learning algorithm incorporating capacitated sperm intracellular pH predicts conventional in vitro fertilization success in normospermic patients.

ABSTRACT:

Objective

To measure human sperm intracellular pH (pH_i) and develop a machine-learning algorithm to predict successful conventional in vitro fertilization (IVF) in normospermic patients.

Design

Spermatozoa from 76 IVF patients were capacitated in vitro. Flow cytometry was used to measure sperm pH_i, and computer-assisted semen analysis was used to measure hyperactivated motility. A gradient-boosted machine-learning algorithm was trained on clinical data and sperm pH_i and membrane potential from 58 patients to predict successful conventional IVF, defined as a fertilization ratio (number of fertilized oocytes [2 pronuclei]/number of mature oocytes) greater than 0.66. The algorithm was validated on an independent set of data from 18 patients.

Setting

Academic medical center.

Patient(s)

Normospermic men undergoing IVF. Patients were excluded if they used frozen sperm, had known male factor infertility, or used intracytoplasmic sperm injection only.

Intervention(s)

None.

Main outcome measure(s)

Successful conventional IVF.

Result(s)

Sperm pH_i positively correlated with hyperactivated motility and with conventional IVF ratio (n = 76) but not with intracytoplasmic sperm injection fertilization ratio (n = 38). In receiver operating curve analysis of data from the test set (n = 58), the machine-learning algorithm predicted successful conventional IVF with a mean accuracy of 0.72 (n = 18), a mean area under the curve of 0.81, a mean sensitivity of 0.65, and a mean specificity of 0.80.

Conclusion(s)

Sperm pH_i correlates with conventional fertilization outcomes in normospermic patients undergoing IVF. A machine-learning algorithm can use clinical parameters and markers of capacitation to accurately predict successful fertilization in normospermic men undergoing conventional IVF.

SUBMITTER: Gunderson SJ

PROVIDER: S-EPMC9110269 | biostudies-literature | 2021 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine-learning algorithm incorporating capacitated sperm intracellular pH predicts conventional in vitro fertilization success in normospermic patients.

Gunderson Stephanie Jean SJ Puga Molina Lis Carmen LC Spies Nicholas N Balestrini Paula Ania PA Buffone Mariano Gabriel MG Jungheim Emily Susan ES Riley Joan J Santi Celia Maria CM

Fertility and sterility 20210115 4

<h4>Objective</h4>To measure human sperm intracellular pH (pH<sub>i</sub>) and develop a machine-learning algorithm to predict successful conventional in vitro fertilization (IVF) in normospermic patients.<h4>Design</h4>Spermatozoa from 76 IVF patients were capacitated in vitro. Flow cytometry was used to measure sperm pH<sub>i</sub>, and computer-assisted semen analysis was used to measure hyperactivated motility. A gradient-boosted machine-learning algorithm was trained on clinical data and sp ...[more]

PMID: 33461755

Similar Datasets

Project description:ObjectiveTo compare cumulative live birth rate (CLBR) and cost-effectiveness of intracytoplasmic sperm injection (ICSI) vs. conventional in vitro fertilization (cIVF).DesignRetrospective cohort study of cycles reported to the Society for Assisted Reproductive Technology Clinic Outcomes Reporting System.SettingSociety for Assisted Reproductive Technology (SART) member IVF clinics in the United States.PatientsPatients with unexplained infertility who underwent first autologous retrieval cycles between January 2017 and December 2019 with linked fresh and frozen embryo transfers through December 2021.InterventionsICSI vs. cIVF.Main outcome measuresThe primary outcome was CLBR, defined as ≤1 live birth from a retrieval cycle and all linked embryo transfers. Secondary outcomes included two pronuclear (2PN) per oocyte retrieved, miscarriage rate, and total number of transferred or frozen embryos per 2PN. Subsamples with and without preimplantation genetic testing for aneuploidy (PGT-A) were analyzed. Outcomes were adjusted for age, body mass index, number of oocytes retrieved, length of follow-up, and clinic ICSI use rate.ResultsA total of 18,805 patients with unexplained infertility were included. No difference in CLBR was found among cycles without genetic testing (54.4% ICSI vs. 57.5% cIVF) and with PGT-A (47.6% ICSI vs. 51.8% cIVF). Intracytoplasmic sperm injection cycles without genetic testing had a higher miscarriage rate (16.4% vs. 14.4%) but no difference was seen in cycles with PGT-A (13.9% ICSI vs. 13.2% cIVF). Intracytoplasmic sperm injection cycles had a significantly lower ratio of 2PN per oocyte retrieved without genetic testing (59.7% vs. 60.9%) and with PGT-A (63.3% vs. 65.8%). The ratio of embryos transferred or frozen per 2PN was not significantly different in cycles without genetic testing (49.4% vs. 49.6%) or with PGT-A (54.2% vs. 55.2%). Total fertilization failure occurred in 216 patients (4%) who underwent cIVF and in 153 patients (1.1%) who used ICSI.Compared with cIVF alone, an estimated additional $11,011,500 was charged to patients for ICSI without genetic testing and $9,010,500 was charged to patients for ICSI with PGT-A over 2 years by Society for Assisted Reproductive Technology clinics. On the basis of total fertilization failure rates, 35 patients would require treatment with routine ICSI to avoid a single cycle of total fertilization failure with cIVF.ConclusionsRoutine use of ICSI in unexplained infertility is not warranted due to the additional cost and lack of CLBR benefit.

Dataset Information

Machine-learning algorithm incorporating capacitated sperm intracellular pH predicts conventional in vitro fertilization success in normospermic patients.

Objective

Design

Setting

Patient(s)

Intervention(s)

Main outcome measure(s)

Result(s)

Conclusion(s)

Publications

Machine-learning algorithm incorporating capacitated sperm intracellular pH predicts conventional in vitro fertilization success in normospermic patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets