为了在更接近真实临床的场景中对模型进行验证,研究人员选择一个包括了4种不同精神疾病患者和健康对照的数据集作为验证队列。
经过数据处理和过滤,最终用于验证模型的数据包括自闭症(n=24),双相情感障碍(n=21),重度抑郁症(n=23),未接受过药物治疗的精神分裂症患者(n=22),以及健康对照组(n=84)。
当模型用于区分健康对照和精神分裂症患者时,AUC值为0.84(95%CI:0.77-0.92)。用于区分精神分裂症和其他三种精神疾病的患者时,AUC值为0.83(95%CI:0.75 0.92)。
当模型分别用于区分精神分裂症患者与自闭症、双相情感障碍、重度抑郁症患者时,也都显示出较好的预测效果,AUC值分别为0.75(95%CI:0.61 0.89),0.85(95CI:0.74 0.97),0.90(95%CI:0.81 0.99)。
不过,研究人员也指出由于所使用队列的样本量和覆盖面有限,对模型的评估结果与真实世界的使用之间仍存在差距。而且这个模型是基于外周血多种活细胞的检测,在现阶段还较难成为快速而经济的临床诊断测试。
期待随着临床检测技术的发展和模型算法的进步,此类生物标志物的检测和相关诊断模型能早日进入临床应用。
参考文献:
1.Ayano G, Demelash S, Yohannes Z, et al. Misdiagnosis, detection rate, and associated factors of severe psychiatric disorders in specialized psychiatry centers in Ethiopia[J]. Ann Gen Psychiatry. 2021,20(1):10.
2.Gonzalez-Pinto A, Gutierrez M, Mosquera F, et al. First episode in bipolar disorder: misdiagnosis and psychotic symptoms[J]. J Affect Disord. 1998,50(1):41 44.
3.Zaki JK, Lago SG, Rustogi N, et al. Diagnostic model development for schizophrenia based on peripheral blood mononuclear cell subtype-specific expression of metabolic markers[J]. Transl Psychiatry. 2022,12(1):457.
4.Charlson FJ, Ferrari AJ, Santomauro DF, et al. Global epidemiology and burden of schizophrenia: findings from the global burden of disease study 2016[J]. Schizophr Bull. 2018,44(6):1195 203.
5.Penttil M, J skel inen E, Hirvonen N, et al. Duration of untreated psychosis as predictor of long-term outcome in schizophrenia: systematic review and meta-analysis[J]. Br J Psychiatry. 2014,205(2):88 94.
6.Schwarz E, Guest PC, Steiner J, Bogerts B, Bahn S. Identification of blood-based molecular signatures for prediction of response and relapse in schizophrenia patients. Transl Psychiatry. 2012,2(2):e82.
7.Lago SG, Tomasik J, van Rees GF, et al. Exploring cellular markers of metabolic syndrome in peripheral blood mononuclear cells across the neuropsychiatric spectrum[J]. Brain Behav Immun. 2021,91:673 82