Algorithms for Predicting the Probability of Azoospermia from Follicle Stimulating Hormone: Design and Multi-Institutional External Validation

Purpose: To predict the probability of azoospermia without a semen analysis in men presenting with infertility by developing an azoospermia prediction model. Materials and Methods: Two predictive algorithms were generated, one with follicle stimulating hormone (FSH) as the only input and another logistic regression (LR) model with additional clinical inputs of age, luteinizing hormone, total testosterone, and bilateral testis volume. Men presenting between 01/2016 and 03/2020 with semen analyses, testicular ochiodemetry, and serum gonadotropin measurements collected within 120 days were included. An azoospermia prediction model was developed with multi-institutional two-fold external validation from tertiary urologic infertility clinics in Chicago, Miami, and Milan. Results: Total 3,497 participants were included (n=Miami 946, Milan 1,955, Chicago 596). Incidence of azoospermia in Miami, Milan, and Chicago was 13.8%, 23.8%, and 32.0%, respectively. Predictive algorithms were generated with Miami data. On Milan external validation, the LR and quadratic FSH models both demonstrated good discrimination with areas under the receiver-operating-characteristic (ROC) curve (AUC) of 0.79 and 0.78, respectively. Data from Chicago performed with AUCs of 0.71 for the FSH only model and 0.72 for LR. Correlation between the quadratic FSH model and LR model was 0.95 with Milan and 0.92 with Chicago data. Conclusions: We present and validate algorithms to predict the probability of azoospermia. The ability to predict the probability of azoospermia without a semen analysis is useful when there are logistical hurdles in obtaining a semen analysis or for reevaluation prior to surgical sperm extraction. Keywords: Azoospermia; Follicle stimulating hormone; Inftertility; Models, statistical; Semen analysis

研究目的：通过构建无精子症预测模型，实现对不育就诊男性无需精液分析即可预测其无精子症发生概率。
材料与方法：共构建两种预测算法，其一仅以促卵泡生成素（follicle stimulating hormone, FSH）作为输入变量；其二为逻辑回归（logistic regression, LR）模型，额外纳入年龄、黄体生成素、总睾酮以及双侧睾丸体积作为临床输入特征。本研究纳入2016年1月至2020年3月期间就诊，且在120天内完成精液分析、睾丸体积测量以及血清促性腺激素检测的男性患者。本研究所构建的无精子症预测模型，经芝加哥、迈阿密及米兰三地三级泌尿男科不育门诊的多中心双折外部验证。
结果：最终纳入3497名受试者（迈阿密队列946例，米兰队列1955例，芝加哥队列596例）。迈阿密、米兰及芝加哥队列的无精子症发生率分别为13.8%、23.8%及32.0%。预测算法基于迈阿密队列数据构建。经米兰队列外部验证时，逻辑回归模型与二次FSH模型均展现出良好的区分能力，受试者工作特征曲线（receiver-operating-characteristic, ROC）下面积（area under the curve, AUC）分别为0.79与0.78。芝加哥队列验证结果显示，仅FSH输入模型的AUC为0.71，逻辑回归模型的AUC为0.72。二次FSH模型与逻辑回归模型的相关性在米兰队列中为0.95，在芝加哥队列中为0.92。
结论：本研究提出并验证了可预测无精子症发生概率的算法。在存在精液分析获取流程障碍，或需在手术取精前进行术前评估时，无需精液分析即可预测无精子症发生概率的方法具有重要临床应用价值。
关键词：无精子症；促卵泡生成素；不育；统计模型；精液分析