AI-generated Treatment Recommendations in Precision Oncology (AI-PRIME)
Eine Nichtunterlegenheitsstudie zu KI-generierten, Personalisierten Therapieempfehlungen für Die Präzisionsmedizin (AI-PRIME)
Non-interventional study to assess the non-inferiority of AI-generated treatment recommendations for precision oncology. Molecular tumor profiles will be assessed by local AI models to identify treatment options. Resulting treatment options will then be compared with actual personalized therapy recommendations.
研究概览
研究类型
注册 (估计的)
联系人和位置
学习联系方式
- 姓名：Damian T Rieke, MD
- 电话号码：+4930450 564 222
- 邮箱：cccc@charite.de
学习地点
-
-
-
Berlin、德国、10117
- 招聘中
- Charité - Universitätsmedizin Berlin
-
接触：
- Damian T Rieke, MD
- 电话号码：+49 30 450 564 222
- 邮箱：damian.rieke@charite.de
-
-
参与标准
资格标准
适合学习的年龄
接受健康志愿者
有资格学习的性别
取样方法
研究人群
Patients with advanced solid tumors planning to undergo comprehensive molecular tumor testing
描述
Inclusion Criteria:
- advanced solid tumor
- >=18years
- ECOG 0-1
- comprehensive molecular tumor analysis planned
Exclusion Criteria:
- lack of capacity to consent
- hematological neoplasm
学习计划
研究是如何设计的？
设计细节
- 观测模型：COHORT
- 时间观点：PROSPECTIVE
研究衡量的是什么？
主要结果指标
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
Fraction of all actual positively identified treatment options that the model has correctly identified (Recall)
大体时间：immediately after the intervention (which is the molecular tumor board MTB; standard-of-care intervention)
|
Sensitivity as measured by retrieved relevant treatment options divided by all relevant treatment options with 1 indicating identification of all relevant treatment options. |
immediately after the intervention (which is the molecular tumor board MTB; standard-of-care intervention)
|
次要结果测量
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
Fraction of relevant treatment options among all retrieved treatment options (Precision)
大体时间：immediately after the intervention (MTB SOC intervention)
|
Positive predictive value as measured by retrieved relevant treatment options divided by all identified treatment options with 1 indicating the highest positive predictive value |
immediately after the intervention (MTB SOC intervention)
|
|
Harmonic mean of precision and recall (F1-Score)
大体时间：immediately after the intervention (MTB SOC intervention)
|
Analysis of F1 score as harmonic mean between precision and recall with 0 indicating the lowest and 1 the highest possible score. |
immediately after the intervention (MTB SOC intervention)
|
|
clinical trial identification
大体时间：immediately after the intervention (MTB SOC intervention)
|
Number of correctly identified clinical trials |
immediately after the intervention (MTB SOC intervention)
|
|
time of manual and automatic annotation
大体时间：immediately after the intervention (MTB SOC intervention)
|
Comparison of time spent (in minutes) for manual and automatic molecular tumor result annotation |
immediately after the intervention (MTB SOC intervention)
|
|
therapy implementation
大体时间：3 months after MTB (SOC intervention)
|
Number of patients receiving recommended therapy and outcome |
3 months after MTB (SOC intervention)
|
合作者和调查者
研究记录日期
研究主要日期
学习开始 (实际的)
初级完成 (估计的)
研究完成 (估计的)
研究注册日期
首次提交
首先提交符合 QC 标准的
首次发布 (实际的)
研究记录更新
最后更新发布 (实际的)
上次提交的符合 QC 标准的更新
最后验证
更多信息
此信息直接从 clinicaltrials.gov 网站检索，没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求，请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改，我们的网站上也会自动更新.