Multilevel approach to male fertility by machine learning highlights a hidden link between haematological and spermatogenetic cells.

BACKGROUND: Male infertility represents a complex clinical condition requiring an accurate multilevel assessment, in which machine learning technology, combining large data series in non-linear and highly interactive ways, could be innovatively applied. METHODS: A longitudinal, observational, retrospective, big data study was carried out, applying for the first time the ML in the context of male infertility. A large database including all semen samples collected between 2010 and 2016 was generated, together with blood biochemical examinations, environmental temperature and air pollutants exposure. First, the database was analysed with principal component analysis and multivariable linear regression analyses. Second, classification analyses were performed, in which patients were a priori classified according to semen parameters. Third, machine learning algorithms were applied in a training phase (80% of the entire database) and in a tuning phase (20% of the data set). Finally, conventional statistical analyses were applied considering semen parameters and those other variables extracted during machine learning. RESULTS: The final database included 4239 patients, aggregating semen analyses, blood and environmental parameters. Classification analyses were able to recognize oligozoospermic, teratozoospermic, asthenozoospermic and patients with altered semen parameters (0.58 accuracy, 0.58 sensitivity and 0.57 specificity). Machine learning algorithms detected three haematological variables, that is lymphocytes number, erythrocyte distribution and mean globular volume, significantly related to semen parameters (0.69 accuracy, 0.78 sensitivity and 0.41 specificity). CONCLUSION: This is the first machine learning application to male fertility, detecting potential mathematical algorithms able to describe patients' semen characteristics changes. In this setting, a possible hidden link between testicular and haematopoietic tissues was suggested, according to their similar proliferative properties.

Reduction of multiple pregnancies in the advanced maternal age population after implementation of an elective single embryo transfer policy coupled with enhanced embryo selection: pre- and post-intervention study.

STUDY QUESTION: Is an elective single-embryo transfer (eSET) policy an efficient approach for women aged >35 years when embryo selection is enhanced via blastocyst culture and preimplantation genetic screening (PGS)? SUMMARY ANSWER: Elective SET coupled with enhanced embryo selection using PGS in women older than 35 years reduced the multiple pregnancy rates while maintaining the cumulative success rate of the IVF programme. WHAT IS KNOWN ALREADY: Multiple pregnancies mean an increased risk of premature birth and perinatal death and occur mainly in older patients when multiple embryos are transferred to increase the chance of pregnancy. A SET policy is usually recommended in cases of good prognosis patients, but no general consensus has been reached for SET application in the advanced maternal age (AMA) population, defined as women older than 35 years. Our objective was to evaluate the results in terms of efficacy, efficiency and safety of an eSET policy coupled with increased application of blastocyst culture and PGS for this population of patients in our IVF programme. STUDY DESIGN, SIZE, DURATION: In January 2013, a multidisciplinary intervention involving optimization of embryo selection procedure and introduction of an eSET policy in an AMA population of women was implemented. This is a retrospective 4-year (January 2010-December 2013) pre- and post-intervention analysis, including 1161 and 499 patients in the pre- and post-intervention period, respectively. The primary outcome measures were the cumulative delivery rate (DR) per oocyte retrieval cycle and multiple DR. PARTICIPANTS/MATERIALS, SETTING, METHODS: Surplus oocytes and/or embryos were vitrified during the entire study period. In the post-intervention period, all couples with good quality embryos and less than two previous implantation failures were offered eSET. Embryo selection was enhanced by blastocyst culture and PGS (blastocyst stage biopsy and 24-chromosomal screening). Elective SET was also applied in cryopreservation cycles. MAIN RESULTS AND THE ROLE OF CHANCE: Patient and cycle characteristics were similar in the pre- and post-intervention groups [mean (SD) female age: 39.6 ± 2.1 and 39.4 ± 2.2 years; range 36-44] as assessed by logistic regression. A total of 1609 versus 574 oocyte retrievals, 937 versus 350 embryo warming and 138 versus 27 oocyte warming cycles were performed in the pre- and post-intervention periods, respectively, resulting in 1854 and 508 embryo transfers, respectively. In the post-intervention period, 289 cycles were blastocyst stage with (n = 182) or without PGS (n = 107). A mean (SD) number of 2.9 ± 1.1 (range 1-4) and 1.4 ± 0.8 (range 1-3) embryos were transferred pre- and post-intervention, respectively (P < 0.01) and similar cumulative clinical pregnancy rates per transfer and per cycle were obtained: 26.8, 30.9% and 29.7, 26.3%, respectively. The total DR per oocyte retrieval cycle (21.0 and 20.4% pre- and post-intervention, respectively) defined as efficacy was not affected by the intervention [odds ratio (OR) = 0.8, 95% confidence interval (CI) = 0.7-1.1; P = 0.23]. However, a significantly increased live birth rate per transferred embryo (defined as efficiency) was observed in the post-intervention group 17.0 versus 10.6% (P < 0.01). Multiple DRs decreased from 21.0 in the preintervention to 6.8% in the post-intervention group (OR = 0.3. 95% CI = 0.1-0.7; P < 0.01). LIMITATIONS, REASONS FOR CAUTION: In this study, the suitability of SET was assessed in individual women on the basis of both clinical and embryological prognostic factors and was not standardized. For the described eSET strategy coupled with an enhanced embryo selection policy, an optimized culture system, cryopreservation and aneuploidy screening programme is necessary. WIDER IMPLICATIONS OF THE FINDINGS: Owing to the increased maternal morbidity and perinatal complications related to multiple pregnancies, it is recommended to extend the eSET policy to the AMA population. As shown in this study, enhanced embryo selection procedures might allow a reduction in the number of embryos transferred and the number of transfers to be performed without affecting the total efficacy of the treatment but increasing efficiency and safety. STUDY FUNDING/COMPETING INTERESTS: None. TRIAL REGISTRATION NUMBER: None.

Role of type I collagen C telopeptide, bone-specific alkaline phosphatase and osteocalcin in the assessment of bone status in postmenopausal women.

AIM: To investigate the clinical role of the bone turnover markers type I collagen C telopeptide (CTX), osteocalcin (OC) and bone-specific alkaline phosphatase (BAP) in the assessment of bone status in women with postmenopausal osteoporosis. METHODS: Serum CTX (s-CTX), OC and BAP were measured in 200 healthy menopausal women at their initial visit and were correlated with spine and femur bone mineral density (BMD), determined on dual-energy X-ray absorptiometry. The relationship between biochemical markers of bone turnover and age, age at menopause, body mass index (BMI) and BMD was analyzed using linear correlation. A receiver operating characteristic (ROC) curve was constructed for each serum marker versus both femur and vertebral BMD. RESULTS: No correlation was found between serum levels of OC and BAP and vertebral or femur BMD. A statistically significant inverse correlation was found between s-CTX and BMD at spine and femur. S-CTX levels were higher in women with osteoporosis than in women with normal or moderately low (osteopenic) values of BMD. The sensitivity and specificity versus spine BMD were 73.9% and 41.6% for s-CTX, 40.4% and 80.6% for BAP, and 68.3% and 39% for OC, respectively. The sensitivity and specificity versus femur BMD were 76.9% and 40.4% for s-CTX, 23.8% and 88.3% for BAP, and 80.4% and 53.3% for OC, respectively. CONCLUSIONS: Determination of s-CTX, BAP and OC is of limited clinical value in the initial evaluation of bone status in menopausal women.