Background To effectively monitor long-term outcomes among cancer patients, it is critical to accurately assess patients’ dynamic prognosis, which often involves utilizing multiple data sources (e.g., tumor registries, treatment histories, and patient-reported outcomes). However, challenges arise in selecting features to predict patient outcomes from high-dimensional data, aligning longitudinal measurements from multiple sources, and evaluating dynamic model performance. Methods We provide a framework for dynamic risk prediction using the penalized landmark supermodel (penLM) and develop novel metrics (<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12874_2024_2418_Article_IEq1.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="50" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:\overline{AUC}_{w}\:\)</EquationSource> </InlineEquation> and <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12874_2024_2418_Article_IEq2.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="36" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:\overline{BS}_{w}\:\)</EquationSource> </InlineEquation>) to evaluate and summarize model performance across different timepoints. Through simulations, we assess the coverage of the proposed metrics’ confidence intervals under various scenarios. We applied penLM to predict the updated 5-year risk of lung cancer mortality at diagnosis and for subsequent years by combining data from SEER registries (2007–2018), Medicare claims (2007–2018), Medicare Health Outcome Survey (2006–2018), and U.S. Census (1990–2010). Results The simulations confirmed valid coverage (~ 95%) of the confidence intervals of the proposed summary metrics. Of 4,670 lung cancer patients, 41.5% died from lung cancer. Using penLM, the key features to predict lung cancer mortality included long-term lung cancer treatments, minority races, regions with low education attainment or racial segregation, and various patient-reported outcomes beyond cancer staging and tumor characteristics. When evaluated using the proposed metrics, the penLM model developed using multi-source data (<InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12874_2024_2418_Article_IEq3.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="50" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:\overline{AUC}_{w}\:\)</EquationSource> </InlineEquation>of 0.77 [95% confidence interval: 0.74–0.79]) outperformed those developed using single-source data (<InlineEquation ID="IEq4"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12874_2024_2418_Article_IEq4.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="50" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:\overline{AUC}_{w}\:\)</EquationSource> </InlineEquation>range: 0.50–0.74). Conclusions The proposed penLM framework with novel evaluation metrics offers effective dynamic risk prediction when leveraging high-dimensional multi-source longitudinal data.

Penalized landmark supermodels (penLM) for dynamic prediction for time-to-event outcomes in high-dimensional data

期刊论文
出版模式：

开放获取
发表日期：

2025年1月27日

查看全文

Anya H. Fries,
Eunji Choi,
Summer S. Han

摘要

Background

To effectively monitor long-term outcomes among cancer patients, it is critical to accurately assess patients’ dynamic prognosis, which often involves utilizing multiple data sources (e.g., tumor registries, treatment histories, and patient-reported outcomes). However, challenges arise in selecting features to predict patient outcomes from high-dimensional data, aligning longitudinal measurements from multiple sources, and evaluating dynamic model performance.

Methods

We provide a framework for dynamic risk prediction using the penalized landmark supermodel (penLM) and develop novel metrics ( \(\:\overline{AUC}_{w}\:\) and \(\:\overline{BS}_{w}\:\) ) to evaluate and summarize model performance across different timepoints. Through simulations, we assess the coverage of the proposed metrics’ confidence intervals under various scenarios. We applied penLM to predict the updated 5-year risk of lung cancer mortality at diagnosis and for subsequent years by combining data from SEER registries (2007–2018), Medicare claims (2007–2018), Medicare Health Outcome Survey (2006–2018), and U.S. Census (1990–2010).

Results

The simulations confirmed valid coverage (~ 95%) of the confidence intervals of the proposed summary metrics. Of 4,670 lung cancer patients, 41.5% died from lung cancer. Using penLM, the key features to predict lung cancer mortality included long-term lung cancer treatments, minority races, regions with low education attainment or racial segregation, and various patient-reported outcomes beyond cancer staging and tumor characteristics. When evaluated using the proposed metrics, the penLM model developed using multi-source data ( \(\:\overline{AUC}_{w}\:\) of 0.77 [95% confidence interval: 0.74–0.79]) outperformed those developed using single-source data ( \(\:\overline{AUC}_{w}\:\) range: 0.50–0.74).

Conclusions

The proposed penLM framework with novel evaluation metrics offers effective dynamic risk prediction when leveraging high-dimensional multi-source longitudinal data.