Dataset Information

Interactive process mining of cancer treatment sequences with melanoma real-world data.

ABSTRACT: The growing availability of clinical real-world data (RWD) represents a formidable opportunity to complement evidence from randomized clinical trials and observe how oncological treatments perform in real-life conditions. In particular, RWD can provide insights on questions for which no clinical trials exist, such as comparing outcomes from different sequences of treatments. To this end, process mining is a particularly suitable methodology for analyzing different treatment paths and their associated outcomes. Here, we describe an implementation of process mining algorithms directly within our hospital information system with an interactive application that allows oncologists to compare sequences of treatments in terms of overall survival, progression-free survival and best overall response. As an application example, we first performed a RWD descriptive analysis of 303 patients with advanced melanoma and reproduced findings observed in two notorious clinical trials: CheckMate-067 and DREAMseq. Then, we explored the outcomes of an immune-checkpoint inhibitor rechallenge after a first progression on immunotherapy versus switching to a BRAF targeted treatment. By using interactive process-oriented RWD analysis, we observed that patients still derive long-term survival benefits from immune-checkpoint inhibitors rechallenge, which could have direct implications on treatment guidelines for patients able to carry on immune-checkpoint therapy, if confirmed by external RWD and randomized clinical trials. Overall, our results highlight how an interactive implementation of process mining can lead to clinically relevant insights from RWD with a framework that can be ported to other centers or networks of centers.

SUBMITTER: Wicky A

PROVIDER: S-EPMC10072205 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Interactive process mining of cancer treatment sequences with melanoma real-world data.

Wicky Alexandre A Gatta Roberto R Latifyan Sofiya S Micheli Rita De R Gerard Camille C Pradervand Sylvain S Michielin Olivier O Cuendet Michel A MA

Frontiers in oncology 20230321

The growing availability of clinical real-world data (RWD) represents a formidable opportunity to complement evidence from randomized clinical trials and observe how oncological treatments perform in real-life conditions. In particular, RWD can provide insights on questions for which no clinical trials exist, such as comparing outcomes from different sequences of treatments. To this end, process mining is a particularly suitable methodology for analyzing different treatment paths and their assoc ...[more]

PMID: 37025593

Similar Datasets

Project description:ObjectivesThe treatment landscape for metastatic renal cell carcinoma changed a lot in the last few years. This study aimed to assess the treatment sequences and outcomes for metastatic renal cell carcinoma in a real-world setting.Materials and methodsWe enrolled patients with metastatic renal cell carcinomawho received first-line systemic treatment with tyrosin kinase inhibitors monotherapy, ipilimumab plus nivolumab, or pembrolizumab plus axitinibbetween January2009 and May 2023 on the database of TriNetX network. Overall survival, time on treatment and time to next treatment were evaluated using Kaplan-Meiermethod.ResultsTotally, 4183 received tyrosine kinase inhibitor monotherapy, 1555 received ipilimumab plus nivolumab, and 559 received axitinib plus pembrolizumab. Median time on treatment was 2.5 months for the tyrosine kinase inhibitor monotherapy cohort, 5.4 months for the ipilimumab plus nivolumab cohort, and 8.3 months for the pembrolizumab plus axitinib cohort. Median time to next treatment was 16.6 months for both the tyrosine kinase inhibitor monotherapy and ipilimumab plus nivolumab cohorts, and 22.1 months for the pembrolizumab plus axitinib cohort. Median overall survival was 42.2 months for the tyrosine kinase inhibitor monotherapy cohort, 39.7monthsfor the ipilimumab plus nivolumab cohort, and not reached for the pembrolizumab plus axitinib cohort. In comparison with the tyrosine kinase inhibitor monotherapy cohort, patients in the pembrolizumab plus axitinib cohort showed survival benefit (log-rank p = 0.0168) in overall survival, but not the case in the ipilimumab plus nivolumab cohort.ConclusionThere was a trend toward using first-line immuno-oncology based therapy for patients with metastatic renal cell carcinoma in a real-world practice. Axitinib plus pembrolizumuab cohort had survival benefits over tyrosine kinase inhibitor and ipilimumab plus nivolumab cohorts, while patients in the ipilimumab plus nivolumab cohort had more distant metastases and comorbidities.

Project description:BackgroundImmune checkpoint inhibitors (ICIs) and BRAF/MEK inhibitors (BRAF/MEKi) have drastically changed the outcomes of advanced melanoma patients in both the resectable/adjuvant and unresectable/metastatic setting. In this follow-up analysis of real-world data, we aimed to investigate the clinical management and outcomes of advanced melanoma patients in a tertiary referral center in Switzerland approximately a decade after the introduction of ICIs and BRAF/MEKi into clinical use. Moreover, we aimed to compare the results with seminal phase 3 trials and to identify areas of high unmet clinical need.MethodsThis single-center retrospective cohort study analyzed the melanoma registry of the University Hospital Zurich, a tertiary cancer center in Switzerland, and included patients treated in the resectable/adjuvant (n = 331) or unresectable/metastatic setting (n = 375).ResultsIn the resectable setting, adjuvant anti-PD1 or BRAF/MEKi showed a 3-year relapse-free survival (RFS) of 53% and 67.6%, respectively, and the overall median RFS was 50 months. Patients with lymph node plus in-transit metastases or with distant metastases prior to commencing adjuvant treatment had a significantly reduced overall survival (OS). In 10.9% of patients, the treatment was stopped due to toxicity, which did not affect RFS/OS, unless the duration of the treatment was <3 months. Following a relapse of the disease during the first adjuvant treatment, the median progression-free survival (PFS2) was only 6.6 months; outcomes were particularly poor for relapses that were unresectable (median PFS2 3.9 months) or occurred within the first 2 months (median PFS2 2.7 months). A second adjuvant treatment for patients with resectable relapses still showed efficacy (median RFS2 43.7 months). Elevated LDH levels in patients with an unresectable relapse was correlated with a strong reduction in OS2 (HR 9.84, p = 0.018). In the unresectable setting, first-line anti-PD1, anti-CTLA4/PD1 combination, or BRAF/MEKi showed a 5-year OS of 46.5%, 52.4%, and 49.2%, respectively. In a multivariate analysis, elevated LDH levels or the presence of brain metastases substantially shortened OS (HR > 1.78, p < 0.035). There was a non-significant trend for the improved survival of patients treated with anti-CTLA4/PD1 compared to anti-PD1 (HR 0.64, p = 0.15). After a progression on first-line therapy, the median OS2 was reduced to below two years. Elevated LDH (HR 4.65, p < 0.001) levels and widespread disease with at least three metastatic sites, particularly bone metastases (HR 2.62, p = 0.026), affected OS2.ConclusionOur study offers real-world insights into the clinical management, treatment patterns, and outcomes of advanced melanoma patients in both the adjuvant and unresectable setting. Early relapses in patients undergoing adjuvant treatment pose a particular challenge but these patients are generally excluded from first-line trials. The approved first-line metastatic treatments are highly effective in the real-world setting with 5-year OS rates around 50%. However, outcomes remain poor for patients with brain metastases or who fail first-line treatment.

Dataset Information

Interactive process mining of cancer treatment sequences with melanoma real-world data.

Publications

Interactive process mining of cancer treatment sequences with melanoma real-world data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets