A Source Data Verification-Based Data Quality Analysis Within the Network of a German Comprehensive Cancer Center

Borner, Martina; Schweizer, Diana; Fey, Theres; Nasseh, Daniel; Dengler, Robert J.

doi:10.1007/978-3-658-33740-7_11

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…0% 25% 50% 75% 100% Criteria coverage with the current oBDS dataset 0.1 0.448 0.546 0.639 1 Criteria coverage after adding laboratory, pregnancy and comorbidities 0.3 0.556 0.625 0.757 1 available in time. 24 This might prompt the question of why even consider tumor documentation data for trial recruitment. However, due to being manually curated, a tumor dataset inherently comprises structured information of comparatively high data and content quality, setting it apart from typical Electronic Health Record (EHR) entries.…”

Section: Discussionmentioning

confidence: 99%

“…Overall, it should be noted that tumor documentation in Germany is usually delayed by multiple months and therefore data may not be available in time. 24 This might prompt the question of why even consider tumor documentation data for trial recruitment. However, due to being manually curated, a tumor dataset inherently comprises structured information of comparatively high data and content quality, setting it apart from typical Electronic Health Record (EHR) entries.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

How can current oncological datasets be adjusted to support the automated patient recruitment in clinical trials?

Marino,

Kazmaier,

Krendelsberger

et al. 2024

Health Informatics J

Self Cite

View full text Add to dashboard Cite

Objectives: This study aims to identify necessary adjustments required in existing oncological datasets to effectively support automated patient recruitment. Methods: We extracted and categorized the inclusion and exclusion criteria from 115 oncological trials registered on ClinicalTrials.gov in 2022. These criteria were then compared with the content of the oBDS (Oncological Base Dataset version 3.0), Germany’s legally mandated oncological data standard. Results: The analysis revealed that 42.9% of generalized inclusion and exclusion criteria are typically present as data fields in the oBDS. On average, 54.6% of all criteria per trial were covered. Notably, certain criteria such as comorbidities, pregnancy status, and laboratory values frequently appeared in trial protocols but were absent in the oBDS. Conclusion: The omission of criteria, notably comorbidities, within the oBDS restricts its functionality to support trial recruitment. Addressing this limitation would enhance its overall effectiveness. Furthermore, the implications of these findings extend beyond Germany, suggesting potential relevance and applicability to oncological datasets globally.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

How can current oncological datasets be adjusted to support the automated patient recruitment in clinical trials?

Marino,

Kazmaier,

Krendelsberger

et al. 2024

Health Informatics J

Self Cite

View full text Add to dashboard Cite

show abstract

Supporting the decision to perform molecular profiling for cancer patients based on routinely collected data through the use of machine learning

Kasprzak,

Westphalen,

Frey

et al. 2024

Clin Exp Med

Self Cite

View full text Add to dashboard Cite

Background Personalized medicine offers targeted therapy options for cancer treatment. However, the decision whether to include a patient into next-generation sequencing (NGS) testing is not standardized. This may result in some patients receiving unnecessary testing while others who could benefit from it are not tested. Typically, patients who have exhausted conventional treatment options are of interest for consideration in molecularly targeted therapy. To assist clinicians in decision-making, we developed a decision support tool using routine data from a precision oncology program. Methods We trained a machine learning model on clinical data to determine whether molecular profiling should be performed for a patient. To validate the model, the model’s predictions were compared with decisions made by a molecular tumor board (MTB) using multiple patient case vignettes with their characteristics. Results The prediction model included 440 patients with molecular profiling and 13,587 patients without testing. High area under the curve (AUC) scores indicated the importance of engineered features in deciding on molecular profiling. Patient age, physical condition, tumor type, metastases, and previous therapies were the most important features. During the validation MTB experts made the same decision of recommending a patient for molecular profiling only in 10 out of 15 of their previous cases but there was agreement between the experts and the model in 9 out of 15 cases. Conclusion Based on a historical cohort, our predictive model has the potential to assist clinicians in deciding whether to perform molecular profiling.

show abstract

A Source Data Verification-Based Data Quality Analysis Within the Network of a German Comprehensive Cancer Center

Cited by 2 publications

References 9 publications

How can current oncological datasets be adjusted to support the automated patient recruitment in clinical trials?

How can current oncological datasets be adjusted to support the automated patient recruitment in clinical trials?

Supporting the decision to perform molecular profiling for cancer patients based on routinely collected data through the use of machine learning

Contact Info

Product

Resources

About