RESUMO
PURPOSE: Real 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. METHODS: We performed a narrative review of the major current trends and recent literature in artificial intelligence applications in oncology. RESULTS: Artificial 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. CONCLUSIONS: Despite 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.
Assuntos
Inteligência Artificial , Oncologia , Neoplasias , Humanos , Oncologia/métodos , Oncologia/tendências , Neoplasias/terapiaRESUMO
BACKGROUND: Despite randomized trials demonstrating a mortality benefit to low-dose computed tomography screening to detect lung cancer, uptake of lung cancer screening (LCS) has been slow, and the benefits of screening remain unclear in clinical practice. METHODS: This study aimed to assess the impact of screening among patients in the Veterans Health Administration (VA) health care system diagnosed with lung cancer between 2011 and 2018. Lung cancer stage at diagnosis, lung cancer-specific survival, and overall survival between patients with cancer who did and did not receive screening before diagnosis were evaluated. We used Cox regression modeling and inverse propensity weighting analyses with lead time bias adjustment to correlate LCS exposure with patient outcomes. RESULTS: Of 57,919 individuals diagnosed with lung cancer in the VA system between 2011 and 2018, 2167 (3.9%) underwent screening before diagnosis. Patients with screening had higher rates of stage I diagnoses (52% vs. 27%; p ≤ .0001) compared to those who had no screening. Screened patients had improved 5-year overall survival rates (50.2% vs. 27.9%) and 5-year lung cancer-specific survival (59.0% vs. 29.7%) compared to unscreened patients. Among screening-eligible patients who underwent National Comprehensive Cancer Network guideline-concordant treatment, screening resulted in substantial reductions in all-cause mortality (adjusted hazard ratio [aHR], 0.79; 95% confidence interval [CI], 0.67-0.92; p = .003) and lung-specific mortality (aHR, 0.61; 95% CI, 0.50-0.74; p < .001). CONCLUSIONS: While LCS uptake remains limited, screening was associated with earlier stage diagnoses and improved survival. This large national study corroborates the value of LCS in clinical practice; efforts to widely adopt this vital intervention are needed.
Assuntos
Detecção Precoce de Câncer , Neoplasias Pulmonares , Estadiamento de Neoplasias , United States Department of Veterans Affairs , Humanos , Neoplasias Pulmonares/mortalidade , Neoplasias Pulmonares/diagnóstico , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/diagnóstico por imagem , Masculino , Feminino , Detecção Precoce de Câncer/métodos , Idoso , Pessoa de Meia-Idade , Estados Unidos/epidemiologia , United States Department of Veterans Affairs/estatística & dados numéricos , Tomografia Computadorizada por Raios X , Taxa de Sobrevida , Saúde dos Veteranos/estatística & dados numéricos , Programas de Rastreamento/métodos , Veteranos/estatística & dados numéricosRESUMO
PURPOSE: Adjuvant durvalumab after definitive chemoradiotherapy (CRT) for unresectable stage III non-small cell lung cancer (NSCLC) is well-tolerated in clinical trials. However, pneumonitis rates outside of clinical trials remain poorly defined with CRT followed by durvalumab. We aimed to describe the influence of durvalumab on pneumonitis rates among a large cohort of patients with stage III NSCLC. METHODS AND MATERIALS: We studied patients with stage III NSCLC in the national Veterans Health Administration from 2015 to 2021 who received concurrent CRT alone or with adjuvant durvalumab. We defined pneumonitis as worsening respiratory symptoms with radiographic changes within 2 years of CRT and graded events according to National Cancer Institute Common Terminology Criteria for Adverse Events version 4.03. We used Cox regression to analyze risk factors for pneumonitis and the effect of postbaseline pneumonitis on overall survival. RESULTS: Among 1994 patients (989 CRT alone, 1005 CRT followed by adjuvant durvalumab), the 2-year incidence of grade 2 or higher pneumonitis was 13.9% for CRT alone versus 22.1% for CRT plus durvalumab (unadjusted P < .001). On multivariable analysis, durvalumab was associated with higher risk of grade 2 pneumonitis (hazard ratio, 1.45; 95% CI, 1.09-1.93; P = .012) but not grade 3 to 5 pneumonitis (P = .2). Grade 3 pneumonitis conferred worse overall survival (hazard ratio, 2.51; 95% CI, 2.06-3.05; P < .001) but grade 2 pneumonitis did not (P = .4). CONCLUSIONS: Adjuvant durvalumab use was associated with increased risk of low-grade but not higher-grade pneumonitis. Reassuringly, low-grade pneumonitis did not increase mortality risk. We observed increased rates of high-grade pneumonitis relative to clinical trials; the reasons for this require further study.
Assuntos
Anticorpos Monoclonais , Carcinoma Pulmonar de Células não Pequenas , Neoplasias Pulmonares , Pneumonia , Humanos , Carcinoma Pulmonar de Células não Pequenas/terapia , Neoplasias Pulmonares/terapia , Adjuvantes Imunológicos , Pneumonia/induzido quimicamente , Pneumonia/epidemiologia , Quimiorradioterapia/efeitos adversosRESUMO
Importance: As the field of medicine strives for equity in care, research showing the association of social determinants of health (SDOH) with poorer health care outcomes is needed to better inform quality improvement strategies. Objective: To evaluate the association of SDOH with prostate cancer-specific mortality (PCSM) and overall survival (OS) among Black and White patients with prostate cancer. Data Sources: A MEDLINE search was performed of prostate cancer comparative effectiveness research from January 1, 1960, to June 5, 2020. Study Selection: Two authors independently selected studies conducted among patients within the United States and performed comparative outcome analysis between Black and White patients. Studies were required to report time-to-event outcomes. A total of 251 studies were identified for review. Data Extraction and Synthesis: Three authors independently screened and extracted data. End point meta-analyses were performed using both fixed-effects and random-effects models. The Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guideline was followed, and 2 authors independently reviewed all steps. All conflicts were resolved by consensus. Main Outcomes and Measures: The primary outcome was PCSM, and the secondary outcome was OS. With the US Department of Health and Human Services Healthy People 2030 initiative, an SDOH scoring system was incorporated to evaluate the association of SDOH with the predefined end points. The covariables included in the scoring system were age, comorbidities, insurance status, income status, extent of disease, geography, standardized treatment, and equitable and harmonized insurance benefits. The scoring system was discretized into 3 categories: high (≥10 points), intermediate (5-9 points), and low (<5 points). Results: The 47 studies identified comprised 1â¯019â¯908 patients (176â¯028 Black men and 843â¯880 White men; median age, 66.4 years [IQR, 64.8-69.0 years]). The median follow-up was 66.0 months (IQR, 41.5-91.4 months). Pooled estimates found no statistically significant difference in PCSM for Black patients compared with White patients (hazard ratio [HR], 1.08 [95% CI, 0.99-1.19]; P = .08); results were similar for OS (HR, 1.01 [95% CI, 0.95-1.07]; P = .68). There was a significant race-SDOH interaction for both PCSM (regression coefficient, -0.041 [95% CI, -0.059 to 0.023]; P < .001) and OS (meta-regression coefficient, -0.017 [95% CI, -0.033 to -0.002]; P = .03). In studies with minimal accounting for SDOH (<5-point score), Black patients had significantly higher PCSM compared with White patients (HR, 1.29; 95% CI, 1.17-1.41; P < .001). In studies with greater accounting for SDOH variables (≥10-point score), PCSM was significantly lower among Black patients compared with White patients (HR, 0.86; 95% CI, 0.77-0.96; P = .02). Conclusions and Relevance: The findings of this meta-analysis suggest that there is a significant interaction between race and SDOH with respect to PCSM and OS among men with prostate cancer. Incorporating SDOH variables into data collection and analyses are vital to developing strategies for achieving equity.
Assuntos
Neoplasias da Próstata , Determinantes Sociais da Saúde , Idoso , Humanos , Masculino , Próstata , Neoplasias da Próstata/epidemiologia , Neoplasias da Próstata/terapia , Estados Unidos/epidemiologia , Brancos , Negro ou Afro-AmericanoRESUMO
PURPOSE: Men with locally advanced prostate cancer who undergo radical prostatectomy (RP) often develop recurrence and require postoperative radiotherapy. We aimed to determine the safety of neoadjuvant stereotactic body radiotherapy (SBRT) before RP in this population. METHODS AND PATIENTS: A single-institution phase 1 trial (NCT02946008) of men with high-risk or node-positive prostate cancer were enrolled between March and October 2017. The primary endpoint was to determine the maximum tolerated dose of SBRT based on a composite 30-day post-RP toxicity goal of ≤28% of patients experiencing a dose-limiting toxicity (DLT). Secondary outcomes included toxicity, efficacy, and multiple quality of life (QoL) inventories. SBRT (30-35 Gy/5 fractions) was delivered to the prostate and seminal vesicles, and 25 Gy/5 fractions to the pelvic lymph nodes. RP was performed for a median of 6 weeks post-SBRT. Hormone therapy was not allowed. RESULTS: Median follow-up was 40 months (range, 33-44). Twenty-five percent of the patients (n = 4) experienced a DLT within 30 days post-RP; however, the trial was stopped early (n = 16 of planned 38 patients) owing to the proportion and severity of the late adverse events. Post-RP grade 3 genitourinary and gastrointestinal toxicities occurred in 75% (n = 12) and 25% (n = 4) of patients, respectively. Two patients required cystectomy and urinary diversion ≥2 years post-RP. At 24 months post-RP, 75% (n = 12) of men used ≥1 pad/d and 0% had erections suitable for intercourse. Surgical margins were negative in all patients and 31% (n = 5) had complete or partial (pre-RP) MRI-response to SBRT. Three-year biochemical recurrence and distant metastasis were 45% (95% CI, 5%-68%) and 28% (95% CI, 0%-49%), respectively. CONCLUSIONS: Neoadjuvant SBRT followed by RP resulted in unacceptably high toxicity and severe QoL declines.
Assuntos
Neoplasias da Próstata , Radiocirurgia , Masculino , Humanos , Radiocirurgia/efeitos adversos , Radiocirurgia/métodos , Terapia Neoadjuvante/efeitos adversos , Qualidade de Vida , Próstata/patologia , Glândulas Seminais/patologia , Prostatectomia/métodos , Neoplasias da Próstata/radioterapia , Neoplasias da Próstata/cirurgia , Neoplasias da Próstata/tratamento farmacológicoRESUMO
BACKGROUND: The Intermediate Clinical Endpoints in Cancer of the Prostate (ICECaP) working group identified metastasis-free survival as a valid surrogate end point for overall survival (OS) for patients with localized prostate cancer. No comparably validated surrogate end points exist in advanced prostate cancer. METHODS: We searched for trials in advanced prostate cancer, defined as node-positive, metastatic castration-sensitive, nonmetastatic, or metastatic castration-resistant prostate cancer. Eligible randomized trials reported OS and one or more intermediate clinical end points, including biochemical failure (BF), clinical failure, biochemical failurefree survival (BFS), progression-free survival (PFS), and radiographic PFS. Candidacy for surrogacy was assessed by using the second condition of the meta-analytic approach; R2 was weighted by the inverse variance of the log intermediate clinical end point hazard ratio and defined as R2>0.70. RESULTS: A total of 143 randomized trials (n=75,601 patients) were included. No candidate end points met the criteria for surrogacy (R2 BF [n=28,922], 0.42 [95% confidence interval (CI), 0.18 to 0.64]; BFS [n=25,741], 0.57 [95% CI, 0.37 to 0.73]; clinical failure [n=22,616], 0.31 [95% CI, 0.075 to 0.56]; PFS [n=52,639], 0.50 [95% CI, 0.35 to 0.63]; and radiographic PFS [n=52,548], 0.50 [95% CI, 0.35 to 0.63]). Within preplanned subgroups according to castration-sensitive or castration-resistant disease or according to treatment type, neither BFS nor PFS consistently met criteria for surrogacy. Sensitivity analyses showed that candidacy for surrogacy of all end points tested did not change over time. CONCLUSIONS: Our aggregate screening method for surrogate end points in advanced prostate cancer showed that commonly used clinical end points are not clear valid surrogate end points for OS. (Funded by the Prostate Cancer Foundation and the National Cancer Institute.)
Assuntos
Neoplasias da Próstata , Masculino , Humanos , Biomarcadores , PróstataRESUMO
Grade 2 and higher radiation pneumonitis (RP2) is a potentially fatal toxicity that limits efficacy of radiation therapy (RT). We wished to identify a combined biomarker signature of circulating miRNAs and cytokines which, along with radiobiological and clinical parameters, may better predict a targetable RP2 pathway. In a prospective clinical trial of response-adapted RT for patients (n = 39) with locally advanced non-small cell lung cancer, we analyzed patients' plasma, collected pre- and during RT, for microRNAs (miRNAs) and cytokines using array and multiplex enzyme linked immunosorbent assay (ELISA), respectively. Interactions between candidate biomarkers, radiobiological, and clinical parameters were analyzed using data-driven Bayesian network (DD-BN) analysis. We identified alterations in specific miRNAs (miR-532, -99b and -495, let-7c, -451 and -139-3p) correlating with lung toxicity. High levels of soluble tumor necrosis factor alpha receptor 1 (sTNFR1) were detected in a majority of lung cancer patients. However, among RP patients, within 2 weeks of RT initiation, we noted a trend of temporary decline in sTNFR1 (a physiological scavenger of TNFα) and ADAM17 (a shedding protease that cleaves both membrane-bound TNFα and TNFR1) levels. Cytokine signature identified activation of inflammatory pathway. Using DD-BN we combined miRNA and cytokine data along with generalized equivalent uniform dose (gEUD) to identify pathways with better accuracy of predicting RP2 as compared to either miRNA or cytokines alone. This signature suggests that activation of the TNFα-NFκB inflammatory pathway plays a key role in RP which could be specifically ameliorated by etanercept rather than current therapy of non-specific leukotoxic corticosteroids.
RESUMO
BACKGROUND: Decipher Biopsy is a commercially available gene expression classifier used in risk stratification of newly diagnosed prostate cancer (PCa). Currently, there are no prospective data evaluating its clinical utility. We seek to assess the clinical utility of Decipher Biopsy in localized PCa patients. METHODS: A multi-institutional study of 855 men who underwent Decipher Biopsy testing between February 2015 and October 2019. All patients were tracked through the prospective Michigan Urological Surgery Improvement Collaborative and linked to the Decipher Genomics Resource Information Database (GRID®; NCT02609269). Patient matching was performed by an independent third-party (ArborMetrix Inc.) using two or more unique identifiers. Cumulative incidence curves for time to treatment (TTT) and time to failure (TTF) were constructed using Kaplan-Meier estimates. Multivariable Cox proportional hazard models were used to evaluate the independent association of high-risk Decipher scores with the conversion from AS to radical therapy and treatment failure (biochemical failure or receipt of salvage therapy). RESULTS AND LIMITATIONS: Eight hundred fifty-five patients underwent Decipher Biopsy testing during the study period. Of the 855 men, 264 proceeded to AS (31%), and 454 (53%) received radical therapy. In men electing AS, after adjusting for NCCN risk group, age, PSA, prostate volume, body mass index, and percent positive cores, a high-risk Decipher score was independently associated with shorter TTT (HR 2.51, 95% CI 1.52-4.13 p < 0.001). Similarly, in patients that underwent radical therapy, a high-risk Decipher score was independently associated with TTF (HR 2.98, 95% CI 1.22-7.29, p = 0.01) on multivariable analysis. Follow-up time was a limitation. CONCLUSION: In a prospective statewide registry, high-risk Decipher Biopsy score was strongly and independently associated with conversion from AS to definitive treatment and treatment failure. These real-world data support the clinical utility of Decipher Biopsy. An ongoing phase 3 randomized trial (NCT04396808) will provide level 1 evidence of the clinical impact of Decipher biopsy testing.
Assuntos
Neoplasias da Próstata , Humanos , Masculino , Biópsia , Modelos de Riscos Proporcionais , Antígeno Prostático Específico , Prostatectomia/efeitos adversos , Neoplasias da Próstata/diagnóstico , Neoplasias da Próstata/epidemiologia , Neoplasias da Próstata/terapia , Fatores de RiscoRESUMO
BACKGROUND: The international Intermediate Clinical Endpoints in Cancer of the Prostate working group has established metastasis-free survival as a surrogate for overall survival in localised prostate cancer based on the findings of 19 predominantly radiotherapy-based trials. We sought to comprehensively assess aggregate trial-level performance of commonly reported intermediate clinical endpoints across all randomised trials in localised prostate cancer. METHODS: For this meta-analysis, we searched PubMed for all trials in localised or biochemically recurrent prostate cancer published between Jan 1, 1970, and Jan 15, 2020. Eligible trials had to be randomised, therapeutic, reporting overall survival and at least one intermediate clinical endpoint, and with a sample size of at least 70 participants. Trials of metastatic disease were excluded. Intermediate clinical endpoints included biochemical failure, local failure, distant metastases, biochemical failure-free survival, progression-free survival, and metastasis-free survival. Candidacy for surrogacy was assessed using the second condition of the meta-analytical approach (ie, correlation of the treatment effect of the intermediate clinical endpoint and overall survival), using R2 weighted by the inverse variance of the log intermediate clinical endpoint hazard ratio. The intermediate clinical endpoint was deemed to be a surrogate for overall survival if R2 was 0·7 or greater. FINDINGS: 75 trials (53â631 patients) were included in our analysis. Median follow-up was 9·1 years (IQR 5·7-10·6). Biochemical failure (R2 0·38 [95% CI 0·11-0·64]), biochemical failure-free survival (R2 0·12 [0·0030-0·33]), biochemical failure and clinical failure (R2 0·28 [0·0045-0·65]), and local failure (R2 0·085 [0·00-0·37]) correlated poorly with overall survival. Progression-free survival (R2 0·46 [95% CI 0·22-0·67]) showed moderate correlation with overall survival, and metastasis-free survival (R2 0·78 [0·59-0·89]) correlated strongly. INTERPRETATION: Intermediate clinical endpoints based on biochemical and local failure did not meet the second condition of the meta-analytical approach and are not surrogate endpoints for overall survival in localised prostate cancer. Our findings validate metastasis-free survival as the only identified surrogate endpoint for overall survival to date. FUNDING: Prostate Cancer Foundation and National Institutes of Health.