基于结构化临床数据的IVF/ICSI术后活产预测机器学习模型：系统评价、荟萃分析与批判性评估
Machine Learning for Live-Birth Prediction After IVF/ICSI From Structured Clinical Data: A Systematic Review, Meta-Analysis, and Critical Appraisal
AI总结：
本研究系统评价IVF/ICSI术后活产预测的机器学习模型，荟萃分析其性能，发现未明确决策点的模型AUC最高，模型提升源于分期预测与局部校准，而非深层架构，且多数研究偏倚风险高。
摘要：
从常规临床数据预测体外受精（IVF）或卵胞浆内单精子注射（ICSI）术后活产的机器学习模型，其性能从接近随机水平到接近完美不等。我们依据PRISMA 2020进行系统评价，检索OpenAlex、Scopus和Web of Science至2026年10月22日，采用PROBAST+AI和TRIPOD+AI对模型进行评估，并采用随机效应荟萃分析在logit尺度上合并其判别性能。我们明确了决定模型输出含义的要素（决策点、终点、分析单位、数据源），并按模型家族、决策点和验证设计对纳入的48项研究进行分类。仅在内部评估的模型合并的受试者工作特征曲线下面积（AUC）为0.814；在后续时期或其他中心评估的模型合并AUC为0.756（95%预测区间0.546-0.889）；无高偏倚风险的研究合并AUC为0.764；两种差异均无统计学意义，且异质性极高。未明确决策点的模型合并AUC为0.910，是荟萃回归中唯一显著的调节因素。与拟合相同数据的逻辑回归相比，最优机器学习模型的合并AUC提升了0.056（95%CI 0.017-0.090）。在48项研究中，47项存在高或不明确的偏倚风险，仅4项评估了校准斜率，且无模型有临床影响的证据。合并证据的确定性为低至极低；经验证保留的提升来自于将预测与决策点分期及局部校准，而非更深的架构。我们提供了TRIPOD+AI映射的清单、基准规范及研究议程。
英文摘要：
Machine-learning models predicting live birth after in vitro fertilisation (IVF) or intracytoplasmic sperm injection (ICSI) from routine clinical data report performance from near chance to near perfect. We systematically reviewed these models under PRISMA 2020, searching OpenAlex, Scopus and Web of Science to 22 October 2026, appraised them with PROBAST+AI and TRIPOD+AI, and pooled their discrimination with random-effects meta-analysis on the logit scale. We define what fixes the meaning of a model's output (decision point, endpoint, unit of analysis, data source) and map the 48 included studies by model family, decision point and validation design. Models evaluated only internally pooled to an area under the receiver operating characteristic curve (AUC) of 0.814, against 0.756 (95% prediction interval 0.546-0.889) for models evaluated on a later period or another centre, and 0.764 for studies not at high risk of bias; neither difference was significant, and heterogeneity was extreme. Models whose decision point was not stated pooled to 0.910, the only significant moderator in meta-regression. Against logistic regression fitted to the same data, the best machine-learning model gained a pooled 0.056 AUC (95% CI 0.017-0.090). Of 48 studies, 47 were at high or unclear risk of bias, only four assessed the calibration slope, and no model has evidence of clinical impact. The certainty of the pooled evidence is low to very low; the gains that survive validation came from staging predictions to decision points and local calibration, not deeper architectures. We provide a TRIPOD+AI-mapped checklist, a benchmark specification and a research agenda.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
