Braune Stefan, Stuehler Elisabeth, Heer Yanic, van Hoevell Philip, Bergmann Arnfin
NeuroTransData, Neuburg an der Donau, Germany.
PwC Data and Analytics, Zurich, Switzerland.
Front Digit Health. 2022 Mar 11;4:856829. doi: 10.3389/fdgth.2022.856829. eCollection 2022.
With increasing availability of disease-modifying therapies (DMTs), treatment decisions in relapsing-remitting multiple sclerosis (RRMS) have become complex. Data-driven algorithms based on real-world outcomes may help clinicians optimize control of disease activity in routine praxis.
We previously introduced the PHREND (Predictive-Healthcare-with-Real-World-Evidence-for-Neurological-Disorders) algorithm based on data from 2018 and now follow up on its robustness and utility to predict freedom of relapse and 3-months confirmed disability progression (3mCDP) during 1.5 years of clinical practice.
The impact of quarterly data updates on model robustness was investigated based on the model's C-index and credible intervals for coefficients. Model predictions were compared with results from randomized clinical trials (RCTs). Clinical relevance was evaluated by comparing outcomes of patients for whom model recommendations were followed with those choosing other treatments.
Model robustness improved with the addition of 1.5 years of data. Comparison with RCTs revealed differences <10% of the model-based predictions in almost all trials. Treatment with the highest-ranked (by PHREND) or the first-or-second-highest ranked DMT led to significantly fewer relapses ( < 0.001 and < 0.001, respectively) and 3mCDP events ( = 0.007 and = 0.035, respectively) compared to non-recommended DMTs.
These results further support usefulness of PHREND® in a shared treatment-decision process between physicians and patients.
随着疾病修饰疗法（DMTs）的可及性不断提高，复发缓解型多发性硬化症（RRMS）的治疗决策变得复杂。基于真实世界结果的数据驱动算法可能有助于临床医生在常规实践中优化疾病活动的控制。
我们之前基于2018年的数据引入了PHREND（基于神经疾病真实世界证据的预测性医疗保健）算法，现在对其在1.5年临床实践中预测复发自由度和3个月确诊残疾进展（3mCDP）的稳健性和实用性进行随访。
基于模型的C指数和系数的可信区间，研究季度数据更新对模型稳健性的影响。将模型预测结果与随机临床试验（RCTs）的结果进行比较。通过比较遵循模型建议治疗的患者与选择其他治疗方法的患者的结果，评估临床相关性。
增加1.5年的数据后，模型稳健性得到提高。与RCTs比较发现，在几乎所有试验中，差异均小于基于模型预测的10%。与未推荐的DMTs相比，使用排名最高（由PHREND评定）或排名第一或第二高的DMT进行治疗导致的复发（分别为<0.001和<0.001）和3mCDP事件（分别为=（此处可能有误，推测为P）0.007和=（此处可能有误，推测为P）0.035）显著减少。
这些结果进一步支持了PHREND®在医生与患者共同治疗决策过程中的有用性。
