注意缺陷多动障碍的个体化预测模型:系统综述与元回归
该系统综述纳入100个注意缺陷多动障碍(ADHD)预测模型,其中88%为诊断模型、5%为预后模型、7%为治疗反应模型;96%仅内部验证、7%有外部验证,无模型进入临床实践。元回归显示含临床预测因子的模型AUC更高(β=6.54,p=0.007),验证类型、年龄范围、模型类型、预测因子数量、研究质量及其他类型预测因子未改变AUC。
要点
- 100个ADHD预测模型中88%为诊断模型,预后与治疗反应模型分别仅占5%和7%。
- 96%的模型仅内部验证、7%有外部验证,无一被实施于临床实践。
- 仅8%的模型偏倚风险低、67%为高偏倚风险;含临床预测因子的模型AUC更高(β=6.54,p=0.007)。
核心结论
- 已开发多个支持ADHD诊断的预测模型,但预测结局或治疗反应的努力有限,且现有模型均未准备好进入临床实践。
- 使用临床预测因子并可能与其他类型预测因子联合,似乎可提高模型性能。
- 作者认为新一代研究应通过开展高质量、可重复、经外部验证的模型及后续实施研究来弥补这些空白。
研究设计与样本
- 遵循PRISMA/CHARMS/TRIPOD的系统综述(PROSPERO注册号CRD42023387502),检索截至2023年12月20日,纳入报告内部和/或外部验证的ADHD诊断/预后/治疗反应预测模型研究。
- 从7764条记录中纳入100个预测模型;使用元回归探索影响模型曲线下面积(AUC)的因素,并用预测模型偏倚风险评估工具(PROBAST)评估偏倚风险。
主要发现
- 100个模型中88%为诊断模型、5%为预后模型、7%为治疗反应模型;96%经内部验证、7%经外部验证;无一被实施于临床实践。
- 仅8%的模型被判定为低偏倚风险,67%为高偏倚风险。
- 临床、神经影像和认知预测因子分别用于35%、31%和27%的研究。
- 含临床预测因子的模型较不含者AUC升高(β=6.54,p=0.007)。
- 验证类型、年龄范围、模型类型、预测因子数量、研究质量及其他类型预测因子均未改变AUC。
关键数值与推荐
- 含临床预测因子的模型与不含者相比AUC升高(β=6.54,p=0.007)。
- 96%的模型为内部验证、7%为外部验证;8%为低偏倚风险、67%为高偏倚风险。
- 临床、神经影像和认知预测因子使用比例分别为35%、31%和27%。
临床怎么用
- 原文未据此给出推荐。
局限性
- 96%的模型仅经内部验证、7%经外部验证,无一被实施于临床实践。
- 仅8%的模型为低偏倚风险,67%为高偏倚风险。
- 预测结局或治疗反应的研究有限。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
There have been increasing efforts to develop prediction models supporting personalised detection, prediction, or treatment of ADHD. We overviewed the current status of prediction science in ADHD by: (1) systematically reviewing and appraising available prediction models; (2) quantitatively assessing factors impacting the performance of published models. We did a PRISMA/CHARMS/TRIPOD-compliant systematic review (PROSPERO: CRD42023387502), searching, until 20/12/2023, studies reporting internally and/or externally validated diagnostic/prognostic/treatment-response prediction models in ADHD. Using meta-regressions, we explored the impact of factors affecting the area under the curve (AUC) of the models. We assessed the study risk of bias with the Prediction Model Risk of Bias Assessment Tool (PROBAST). From 7764 identified records, 100 prediction models were included (88% diagnostic, 5% prognostic, and 7% treatment-response). Of these, 96% and 7% were internally and externally validated, respectively. None was implemented in clinical practice. Only 8% of the models were deemed at low risk of bias; 67% were considered at high risk of bias. Clinical, neuroimaging, and cognitive predictors were used in 35%, 31%, and 27% of the studies, respectively. The performance of ADHD prediction models was increased in those models including, compared to those models not including, clinical predictors (β = 6.54, p = 0.007). Type of validation, age range, type of model, number of predictors, study quality, and other type of predictors did not alter the AUC. Several prediction models have been developed to support the diagnosis of ADHD. However, efforts to predict outcomes or treatment response have been limited, and none of the available models is ready for implementation into clinical practice. The use of clinical predictors, which may be combined with other type of predictors, seems to improve the performance of the models. A new generation of research should address these gaps by conducting high quality, replicable, and externally validated models, followed by implementation research.
引用
- Salazar de Pablo G, Iniesta R, Bellato A, et al. Individualized prediction models in ADHD: a systematic review and meta-regression. Mol Psychiatry. 2024. PMID: 38783054. doi:10.1038/s41380-024-02606-5
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。