Search

PurposeReal world evidence is crucial to understanding the diffusion of new oncologic therapies, monitoring cancer outcomes, and detecting unexpected toxicities. In practice, real world evidence is challenging to collect rapidly and comprehensively, often requiring expensive and time-consuming manual case-finding and annotation of clinical text. In this Review, we summarise recent developments in the use of artificial intelligence to collect and analyze real world evidence in oncology.MethodsWe performed a narrative review of the major current trends and recent literature in artificial intelligence applications in oncology.ResultsArtificial intelligence (AI) approaches are increasingly used to efficiently phenotype patients and tumors at large scale. These tools also may provide novel biological insights and improve risk prediction through multimodal integration of radiographic, pathological, and genomic datasets. Custom language processing pipelines and large language models hold great promise for clinical prediction and phenotyping.ConclusionsDespite rapid advances, continued progress in computation, generalizability, interpretability, and reliability as well as prospective validation are needed to integrate AI approaches into routine clinical care and real-time monitoring of novel therapies.

One year of durvalumab following concurrent chemoradiotherapy improves progression-free (PFS) and overall survival (OS) for patients with stage III non-small cell lung cancer (NSCLC). However, the real-world efficacy of durvalumab has not been determined. We conducted a multi-center observational cohort study across the Veterans Health Administration, including patients with stage III NSCLC who received concurrent chemoradiotherapy and durvalumab, compared to patients who received concurrent chemoradiotherapy alone. Kaplan-Meier and Cox regression approaches were used to identify factors associated with PFS and OS. We calculated a hazard ratio and efficacy-effectiveness factor to compare OS of veterans to the referenced clinical trial population. A total of 1006 patients with stage III NSCLC who received concurrent chemoradiotherapy and at least one dose of durvalumab from November 2017 to April 2021 were compared to 989 patients who received concurrent chemoradiotherapy alone from January 2015 to December 2016. Adjuvant durvalumab was associated with higher PFS (HR 0.62, 95% CI 0.55-0.70, p < 0.001) and OS (HR 0.57, 95% CI 0.50-0.66, p < 0.001). OS was shorter in veterans compared to PACIFIC (HR 1.24, 95% CI 1.03-1.48, p = 0.02: EE gap 0.73). OS of veterans with stage III NSCLC treated with adjuvant durvalumab is improved compared to a modern comparator but is reduced compared to the PACIFIC population.

BACKGROUND: One year of adjuvant durvalumab following concurrent chemoradiotherapy significantly improves progression-free survival (PFS) and overall survival (OS) for patients with stage III non-small cell lung cancer (NSCLC). However, the optimal length of adjuvant therapy has not been determined. METHODS: We identified patients with stage III NSCLC treated with definitive chemoradiation and adjuvant durvalumab from November 2017 to April 2021 from the United States Veterans Affairs system. Predictors of early durvalumab discontinuation were evaluated with Cox proportional hazards regression. The effect of differing durations of durvalumab treatment (up to 6, 9, and 12 months) on PFS and OS were compared with a marginal structural model and time-dependent Cox modelling. RESULTS: We included 1006 patients with stage III non-small cell lung cancer who received concurrent chemoradiotherapy and at least one dose of adjuvant durvalumab. The median duration of durvalumab treatment was 7 months (interquartile range 2.8-11.5) and 31% completed the intended durvalumab course. The most common reasons for early discontinuation were tumour progression (22%), immune-related adverse events (15%), and non-immune-related toxicity (6.0%), Marginal structural models suggested similar PFS for 9 months versus 12 months of durvalumab treatment and inferior PFS for 6 months versus 12 months. CONCLUSIONS: A substantial proportion of patients undergoing adjuvant durvalumab discontinue therapy early due to toxicity, and shorter durvalumab treatment durations may provide similar disease control to 12 months of therapy. Prospective randomised controlled studies are needed to characterise the optimal durvalumab treatment duration in locally advanced NSCLC patients.

Background The risk of peripherally inserted central catheter (PICC)-related complications in patients hospitalized with solid tumors remains unclear. Existing studies are limited by single-center, outpatient designs and include heterogenous patients. Methods A retrospective cohort study was designed and included adult patients with solid organ cancers who were admitted to a general medicine ward or intensive care unit and received a PICC. Data were collected from November 2013 to December 2019 at 50 Michigan hospitals. Major complications were defined as central line-associated bloodstream infection, deep vein thrombosis, pulmonary embolism, and catheter occlusion. Hospital variation in PICC use and outcomes was examined. Results Data included 3235 hospitalized patients with solid tumors who had PICCs placed for 51,047 catheter days. Most catheters were double-lumen devices (57.0%). Notably, 17.5% of patients had another central venous catheter at the time of PICC insertion. The most common indications for PICC use were antibiotics (34.5%) and difficult access or blood draws (21.6%); chemotherapy was the primary indication in only 15.7% of patients. A major PICC-related complication occurred in 491 patients (15.2%); catheter occlusion was the most prevalent complication (n = 322; 10.0%) followed by deep vein thrombosis (n = 116; 3.6%), central line-associated bloodstream infection (n = 82; 2.5%), and pulmonary embolism (n = 20; 0.6%). Significant variation in indications for PICC use, device characteristics, and frequency of major complications across hospitals was observed (p < .001). Conclusions PICCs were associated with significant complications in hospitalized patients who had solid malignancies and were often used for reasons other than chemotherapy. Policies and guidance for the appropriate use of PICCs in oncologic patients appear necessary. Lay summary Peripherally inserted central catheters (PICCs) are devices placed in peripheral veins to deliver, Funding Agencies|Blue Cross and Blue Shield of Michigan (BCBSM); Blue Care Network as part of the BCBSM Value Partnerships Program

Current cell-free DNA (cfDNA) next generation sequencing (NGS) precision oncology workflows are typically limited to targeted and/or disease-specific applications. In advanced cancer, disease burden and cfDNA tumor content are often elevated, yielding unique precision oncology opportunities. We sought to demonstrate the utility of a pan-cancer, rapid, inexpensive, whole genome NGS of cfDNA approach (PRINCe) as a precision oncology screening strategy via ultra-low coverage (~0.01x) tumor content determination through genome-wide copy number alteration (CNA) profiling. We applied PRINCe to a retrospective cohort of 124 cfDNA samples from 100 patients with advanced cancers, including 76 men with metastatic castration-resistant prostate cancer (mCRPC), enabling cfDNA tumor content approximation and actionable focal CNA detection, while facilitating concordance analyses between cfDNA and tissue-based NGS profiles and assessment of cfDNA alteration associations with mCRPC treatment outcomes. Therapeutically relevant focal CNAs were present in 42 (34%) cfDNA samples, including 36 of 93 (39%) mCRPC patient samples harboring AR amplification. PRINCe identified pre-treatment cfDNA CNA profiles facilitating disease monitoring. Combining PRINCe with routine targeted NGS of cfDNA enabled mutation and CNA assessment with coverages tuned to cfDNA tumor content. In mCRPC, genome-wide PRINCe cfDNA and matched tissue CNA profiles showed high concordance (median Pearson correlation = 0.87), and PRINCe detectable AR amplifications predicted reduced time on therapy, independent of therapy type (Kaplan-Meier log-rank test, chi-square = 24.9, p < 0.0001). Our screening approach enables robust, broadly applicable cfDNA-based precision oncology for patients with advanced cancer through scalable identification of therapeutically relevant CNAs and pre-/post-treatment genomic profiles, enabling cfDNA- or tissue-based precision oncology workflow optimization.

Current cell-free DNA (cfDNA) next generation sequencing (NGS) precision oncology workflows are typically limited to targeted and/or disease-specific applications. In advanced cancer, disease burden and cfDNA tumor content are often elevated, yielding unique precision oncology opportunities. We sought to demonstrate the utility of a pan-cancer, rapid, inexpensive, whole genome NGS of cfDNA approach (PRINCe) as a precision oncology screening strategy via ultra-low coverage (~0.01x) tumor content determination through genome-wide copy number alteration (CNA) profiling. We applied PRINCe to a retrospective cohort of 124 cfDNA samples from 100 patients with advanced cancers, including 76 men with metastatic castration-resistant prostate cancer (mCRPC), enabling cfDNA tumor content approximation and actionable focal CNA detection, while facilitating concordance analyses between cfDNA and tissue-based NGS profiles and assessment of cfDNA alteration associations with mCRPC treatment outcomes. Therapeutically relevant focal CNAs were present in 42 (34%) cfDNA samples, including 36 of 93 (39%) mCRPC patient samples harboring AR amplification. PRINCe identified pre-treatment cfDNA CNA profiles facilitating disease monitoring. Combining PRINCe with routine targeted NGS of cfDNA enabled mutation and CNA assessment with coverages tuned to cfDNA tumor content. In mCRPC, genome-wide PRINCe cfDNA and matched tissue CNA profiles showed high concordance (median Pearson correlation = 0.87), and PRINCe detectable AR amplifications predicted reduced time on therapy, independent of therapy type (Kaplan-Meier log-rank test, chi-square = 24.9, p < 0.0001). Our screening approach enables robust, broadly applicable cfDNA-based precision oncology for patients with advanced cancer through scalable identification of therapeutically relevant CNAs and pre-/post-treatment genomic profiles, enabling cfDNA- or tissue-based precision oncology workflow optimization.