Translational Psychiatry ( IF 6.8 ) Pub Date : 2021-01-11 , DOI: 10.1038/s41398-020-01172-y Stephen Puntis 1 , Daniel Whiting 1 , Sofia Pappa 2, 3 , Belinda Lennox 1
Early Intervention in psychosis (EIP) teams are the gold standard treatment for first-episode psychosis (FEP). EIP is time-limited and clinicians are required to make difficult aftercare decisions that require weighing up individuals’ wishes for treatment, risk of relapse, and health service capacity. Reliable decision-making tools could assist with appropriate resource allocation and better care. We aimed to develop and externally validate a readmission risk tool for application at the point of EIP discharge. All persons from EIP caseloads in two NHS Trusts were eligible for the study. We excluded those who moved out of the area or were only seen for assessment. We developed a model to predict the risk of hospital admission within a year of ending EIP treatment in one Trust and externally validated it in another. There were n = 831 participants in the development dataset and n = 1393 in the external validation dataset, with 79 (9.5%) and 162 (11.6%) admissions to inpatient hospital, respectively. Discrimination was AUC = 0.76 (95% CI 0.75; 0.77) in the development dataset and AUC = 0.70 (95% CI 0.66; 0.75) in the external dataset. Calibration plots in external validation suggested an underestimation of risk in the lower predicted probabilities and slight overestimation at predicted probabilities in the 0.1–0.2 range (calibration slope = 0.86, 95% CI 0.68; 1.05). Recalibration improved performance at lower predicted probabilities but underestimated risk at the highest range of predicted probabilities (calibration slope = 1.00, 95% CI 0.79; 1.21). We showed that a tool for predicting admission risk using routine data has good performance and could assist clinical decision-making. Refinement of the model, testing its implementation and further external validation are needed.
中文翻译:
精神病服务早期干预后的入院风险预测模型的开发和外部验证
精神病早期干预(EIP)小组是首发精神病(FEP)的金标准治疗方法。EIP是有时间限制的,因此临床医生必须做出艰难的护理决定,这需要权衡个人的治疗意愿,复发风险和医疗服务能力。可靠的决策工具可以协助适当的资源分配和更好的照顾。我们旨在开发和外部验证再入院风险工具,以在EIP排放点应用。两个NHS信托中所有来自EIP案例的人员都有资格参加研究。我们排除了那些搬出该地区或仅被接受评估的人。我们开发了一种模型,以预测在一个Trust中终止EIP治疗后一年内住院的风险,并在另一个Trust中进行外部验证。曾经有n = 831名开发数据集中的参与者,n =外部验证数据集中的1393,住院医院的入院率分别为79(9.5%)和162(11.6%)。开发数据集中的AUC = 0.76(95%CI 0.75; 0.77),外部数据集中的AUC = 0.70(95%CI 0.66; 0.75)。外部验证中的校准图表明,较低的预测概率中的风险被低估了,而在0.1-0.2范围内的预测概率中有一些高估了(校正斜率= 0.86,95%CI 0.68; 1.05)。重新校准在较低的预测概率下提高了性能,但在最高的预测概率范围内却低估了风险(校准斜率= 1.00,95%CI 0.79; 1.21)。我们表明,使用常规数据预测入院风险的工具具有良好的性能,可协助临床决策。完善模型