A retrospective study of ovarian tissue cryopreservation in female patients with hematological diseases for fertility preservation.

PURPOSES: To investigate the effect and safety of ovarian tissue cryopreservation (OTC) for fertility preservation in female patients with hematological diseases. METHODS: We designed a retrospective study. The clinical data of patients with hematological diseases undergoing OTC admitted to Peking University People's Hospital from April 2017 to January 2023 were analyzed and summarized. RESULTS: A total of 24 patients were included in the study, including 19 patients with malignant hematological diseases and 5 patients with non-malignant hematological diseases. The former included 14 patients with acute leukemia, 1 patient with chronic leukemia, and 4 patients with myelodysplastic syndrome, while the latter 5 patients were aplastic anemia (AA). 16 patients had received chemotherapy before OTC. The average age of 24 patients was 22.80 ± 6.81 years. The average anti-Mullerian hormone (AMH) was 1.97 ± 2.12 ng/mL, and the average follicle-stimulating hormone (FSH) was 7.01 ± 4.24 IU/L in examination before OTC. FSH was greater than 10.0 IU/L in 4 cases. The pre-OTC laboratory tests showed that the average white blood cell (WBC) count was (3.33 ± 1.35) × 109/L, the average hemoglobin was 91.42 ± 22.84 g/L, and the average platelet was (147.38 ± 114.46) × 109/L. After injection of recombinant human granulocyte colony-stimulating factor (rhG-CSF), blood transfusion, and iron supplementation in pre-OTC treatment, the average WBC count was (4.91 ± 3.07) × 109/L, the average hemoglobin was 98.67 ± 15.43 g/L, and the average platelet was (156.38 ± 103.22) × 109/L. Of the 24 patients, 22 underwent laparoscopic bilateral partial oophorectomy and oophoroplasty, and 2 underwent laparoscopic unilateral oophorectomy. The average duration of OTC was 59.54 ± 17.58 min, and the average blood loss was 32.1 ± 41.6 mL. The maximum blood loss was 200 mL. There was no significant difference in WBC count and hemoglobin concentration after OTC compared to pre-OTC period. Only the platelet count after OTC surgery was significantly different from that before surgery ([134.54 ± 80.84 vs. 156.38 ± 103.22] × 109/L, p < 0.05). None of the 24 patients had serious complications after OTC. 2 patients had mild infection symptoms, but both recovered well. 23 patients underwent hematopoietic stem cell transplantation (HSCT) after OTC. The median and interquartile range from OTC to the pretreatment of HSCT was 33 (57) days, and the median and interquartile range from OTC to HSCT was 41 (57) days. Seven of them began pretreatment of HSCT within 20 days and began HSCT within 30 days after OTC. All patients were followed up. Of the 23 patients who underwent HSCT after surgery, 22 presented with amenorrhea and 1 with scanty menstrual episodes. Seven patients underwent hormone replacement therapy (HRT) after HSCT. A patient with AA underwent ovarian tissue transplantation (OTT) 3 years after HSCT and resumed regular menstruation 6 months after OTT. CONCLUSIONS: Ovarian tissue cryopreservation has a promising future in fertility protection in patients with hematological diseases. However, patients with hematological malignancies often have received gonadotoxic therapy before OTC, which may be accompanied by myelosuppression while patients with non-malignant hematological diseases often present with severe hemocytopenia. So perioperative complete blood count of patients should be paid attention to. There was no significant difference in the WBC count and hemoglobin concentration in patients with hematological diseases before and after OTC surgery, and the platelet count decreased slightly within the normal range. Infection is the most common post-OTC complication, and HSCT pretreatment can be accepted as early as the 10th day after OTC. OTC has no adverse effects on patients with hematological diseases and does not delay HSCT treatment. For young patients with hematological diseases, OTC is an effective method of fertility preservation.

Postmenopausal endometrial non-benign lesion risk classification through a clinical parameter-based machine learning model.

OBJECTIVE: This study aimed to develop and evaluate a machine learning model utilizing non-invasive clinical parameters for the classification of endometrial non-benign lesions, specifically atypical hyperplasia (AH) and endometrioid carcinoma (EC), in postmenopausal women. METHODS: Our study collected clinical parameters from a cohort of 999 patients with postmenopausal endometrial lesions and conducted preprocessing to identify 57 relevant characteristics from these irregular clinical data. To predict the presence of postmenopausal endometrial non-benign lesions, including atypical hyperplasia and endometrial cancer, we employed various models such as eXtreme Gradient Boosting (XGBoost), Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), Back Propagation Neural Network (BPNN), as well as two ensemble models. Additionally, a test set was performed on an independent dataset consisting of 152 patients. The performance evaluation of all models was based on metrics including the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, precision, and F1 score. RESULTS: The RF model demonstrated superior recognition capabilities for patients with non-benign lesions compared to other models. In the test set, it attained a sensitivity of 88.1% and an AUC of 0.93, surpassing all alternative models evaluated in this study. Furthermore, we have integrated this model into our hospital's Clinical Decision Support System (CDSS) and implemented it within the outpatient electronic medical record system to continuously validate and optimize its performance. CONCLUSIONS: We have trained a model and deployed a system with high discriminatory power that may provide a novel approach to identify patients at higher risk of postmenopausal endometrial non-benign lesions who may benefit from more tailored screening and clinical intervention.