scholarly journals HCC and Molecular Targeting Therapies: Back to the Future

Biomedicines ◽  
2021 ◽  
Vol 9 (10) ◽  
pp. 1345
Author(s):  
Luca Rinaldi ◽  
Erica Vetrano ◽  
Barbara Rinaldi ◽  
Raffaele Galiero ◽  
Alfredo Caturano ◽  
...  
Keyword(s):  
Causes Of Death ◽  
Checkpoint Inhibitors ◽  
Target Therapy ◽  
Progression Free Survival ◽  
Multikinase Inhibitor ◽  
Free Survival ◽  
Hbv Vaccine ◽  
Antiviral Therapies ◽  
Emerging Risk ◽  
Line Of Therapy

Hepatocellular carcinoma (HCC) is one of the leading causes of death from cancer in the world. Recently, the effectiveness of new antiviral therapies and the HBV vaccine have reduced HCC’s incidence, while non-alcoholic steato-hepatitis is an emerging risk factor. This review focuses on antiangiogenic molecules and immune checkpoint inhibitors approved for HCC treatment and possible future approaches. Sorafenib was the first drug approved for the treatment of advanced HCC (aHCC) and it has been shown to increase survival by a few months. Lenvatinib, a multikinase inhibitor, has shown non-inferiority in survival compared with sorafenib and an improvement in progression-free survival (PFS). The combination of atezolizumab (an anti-PDL1 antibody) and bevacizumab (an anti-VEGF antibody) was the first drug combination approved for HCC, demonstrating improved survival compared with sorafenib (19.2 vs. 13.4 months). As a second line of therapy, three regimens (regorafenib, cabozantinib, and ramucirumab) have been approved for the treatment of aHCC after progression on sorafenib according to guidelines. Furthermore, nivolumab, pembrolizumab, and nivolumab plus ipilimumab have been approved by the FDA (2017, 2018, and 2020, respectively). Finally, immune target therapy, cancer vaccines, and epigenetic drugs represent three new possible weapons for the treatment of HCC.

Baseline and early change of neutrophil to lymphocyte ratio (bNLR and ΔNLR) as prognostic factors in metastatic renal cell carcinoma (mRCC) patients treated with nivolumab: Preliminary results of the Meet-URO 15 (I-BIO-REC) study.

2020 ◽  
Vol 38 (6_suppl) ◽  
pp. 752-752
Author(s):  
Sara Elena Rebuzzi ◽  
Sebastiano Buti ◽  
Luca Galli ◽  
Giuseppe Procopio ◽  
Ugo De Giorgi ◽  
...  
Keyword(s):  
Median Overall Survival ◽  
Complete Blood Count ◽  
Checkpoint Inhibitors ◽  
Progression Free Survival ◽  
Prognostic Role ◽  
Free Survival ◽  
The Difference ◽  
Line Of Therapy ◽  
Metastatic Sites

752 Background: Biomarkers to select mRCC patients most likely to benefit to immune-checkpoint inhibitors are still needed. The ongoing retrospective multicentre Meet-URO 15 (I-BIO-REC) study evaluates the prognostic role of peripheral blood cells in mRCC patients treated with nivolumab. Methods:The primary endpoint of the study was median overall survival (mOS) according to bNLR. Complete blood count was collected at the first four cycles of nivolumab. NLR was defined as the ratio of neutrophil to lymphocyte (cutoff = 3) and ΔNLR the difference between NLR at 2nd cycle and bNLR (median used as cutoff = 0.3). Here we reported preliminary analyses on bNLR and DNLR. Results: From May 2016 to January 2019 189 patients started nivolumab as 2nd (62%), 3rd (25%) and > 3rd (13%) line. Median age was 69 years, 67% were male and 87% had clear cell histology. Baseline IMDC group was favorable in 26%, intermediate in 63% and poor in 11%. Lymph-nodes, visceral and bone metastases were present in 55%, 92% and 37%. mOS and progression-free survival (PFS) were 30.5 months and 9.5 months. Overall response rate (ORR) and disease control rate (DCR) were 28% and 57%. bNLR was available in 162 patients: bNLR < 3 (52%) correlated with statistically significant longer PFS [11.5 vs 5.6 months; HR 1.61 (1.09-2.39), p = 0.017] and OS [NR vs 22.4 months; HR 2.61 (1.53-4.46), p < 0.001], with similar ORR (32% vs 32%) but higher DCR (66% vs 55%) compared to NLR ≥ 3. ΔNLR was available in 136 patients: ΔNLR < 0.3 (50%) correlated with statistically significant longer PFS [17.1 vs 8.5 months; HR 1.57 (1.02-2.43) p = 0.04] and OS [medians not reached; HR 1.91 (1.04-3.51) p = 0.038], with similar ORR (39% vs 32%) but higher DCR (73% vs 56%) compared to ΔNLR ≥ 0.3. Univariate and multivariate analyses adjusted for IMDC group, line of therapy and metastatic sites, confirmed the statistically significant correlation between ΔNLR with PFS and OS and NLR with OS but not with PFS. Conclusions: Preliminary analyses of our study showed a prognostic role of bNLR and early ΔNLR in mRCC patients treated with nivolumab.

Baseline lymphocyte to monocyte ratio (LMR) and systemic inflammation index (SII) as prognostic factors in metastatic renal cell carcinoma (mRCC) patients treated with nivolumab: Preliminary results of the Meet-URO 15 (I-BIO-REC) study.

2020 ◽  
Vol 38 (6_suppl) ◽  
pp. 751-751 ◽  
Author(s):  
Sara Elena Rebuzzi ◽  
Sebastiano Buti ◽  
Andrea Sbrana ◽  
Giuseppe Procopio ◽  
Ugo De Giorgi ◽  
...  
Keyword(s):  
Median Overall Survival ◽  
Checkpoint Inhibitors ◽  
Progression Free Survival ◽  
Prognostic Role ◽  
Free Survival ◽  
Lymphocyte To Monocyte Ratio ◽  
Secondary Endpoints ◽  
Line Of Therapy ◽  
Metastatic Sites

751 Background: Biomarkers to select mRCC patients most likely to benefit to immune-checkpoint inhibitors are still needed. The ongoing retrospective multicentre Meet-URO 15 (I-BIO-REC) study evaluates the prognostic role of peripheral blood cells in mRCC patients treated with nivolumab. Methods:The primary endpoint of the study was median overall survival (mOS) according to baseline neutrophil to lymphocyte ratio (NLR), but here preliminary analyses on baseline LMR and SII (secondary endpoints) are reported. LMR was defined as the ratio of lymphocyte to monocyte (cutoff = 3) and SII as platelet x neutrophil/lymphocyte (cutoff = 1375). Results: From May 2016 to January 2019 189 patients started nivolumab as 2nd (62%), 3rd (25%) and > 3rd (13%) line. Median age was 69 years, 67% were male and 87% had clear cell histology. Baseline IMDC group was favorable in 26%, intermediate in 63% and poor in 11%. Lymph-nodes, visceral and bone metastases were present in 55%, 92% and 37%. mOS and progression-free survival (PFS) were 30.5 months and 9.5 months. Overall response rate (ORR) and disease control rate (DCR) were 28% and 57%. LMR was available in 150 patients: LMR ≥ 3 (44%) correlated with statistically significant longer OS [NR vs 26.8 months, HR 0.50 (0.29-0.88); p = 0.016] but not PFS (10.3 vs 9.9 months, HR 0.87 (0.58-1.31); p = 0.5) with similar ORR (34% vs 33%) and DCR (60% vs 63%) compared to LMR < 3. SII was available in 162 patients. SII < 1375 (82%) correlated with statistically significant longer PFS [11.5 vs 3.4 months; HR 2.16 (1.36-3.43), p = 0.001] and OS [NR vs 9.5 months; HR 3.87 (2.21-6.78), p < 0.001] with higher ORR (35% vs 20%) and DCR (65% vs 40%) compared to SII ≥ 1375. Univariate and multivariate analyses adjusted for IMDC group, line of therapy and metastatic sites, confirmed the statistically significant correlation between SII with PFS and OS, but not for LMR. Conclusions: Preliminary analyses of our study showed a prognostic role of baseline SII, while it is uncertain for LMR in mRCC patients treated with nivolumab.

scholarly journals Treatment of Angiosarcoma with Pazopanib and Paclitaxel: Results of the EVA (Evaluation of Votrient® in Angiosarcoma) Phase II Trial of the German Interdisciplinary Sarcoma Group (GISG-06)

Cancers ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 1223
Author(s):  
Daniel Pink ◽  
Dimosthenis Andreou ◽  
Sebastian Bauer ◽  
Thomas Brodowicz ◽  
Bernd Kasper ◽  
...  
Keyword(s):  
Immune Checkpoint Inhibitors ◽  
Median Overall Survival ◽  
Phase Ii Trial ◽  
Checkpoint Inhibitors ◽  
Progression Free Survival ◽  
Free Survival ◽  
Safety And Efficacy ◽  
Future Studies ◽  
Entire Cohort

We aimed to evaluate the efficacy and toxicity of paclitaxel combined with pazopanib in advanced angiosarcoma (AS). The primary end point was progression-free survival (PFS) rate at six months (PFSR6). Planned accrual was 44 patients in order to detect a PFSR6 of >55%, with an interim futility analysis of the first 14 patients. The study did not meet its predetermined interim target of 6/14 patients progression-free at 6 months. At the time of this finding, 26 patients had been enrolled between July 2014 and April 2016, resulting in an overrunning of 12 patients. After a median follow-up of 9.5 (IQR 7.7–15.4) months, PFSR6 amounted to 46%. Two patients had a complete and seven patients a partial response. Patients with superficial AS had a significantly higher PFSR6 (61% vs. 13%, p = 0.0247) and PFS (11.3 vs. 2.7 months, p < 0.0001) compared to patients with visceral AS. The median overall survival in the entire cohort was 21.6 months. A total of 10 drug-related serious adverse effects were reported in 5 patients, including a fatal hepatic failure. Although our study did not meet its primary endpoint, the median PFS of 11.6 months in patients with superficial AS appears to be promising. Taking recent reports into consideration, future studies should evaluate the safety and efficacy of VEGFR and immune checkpoint inhibitors with or without paclitaxel in a randomized, multiarm setting.

scholarly journals Vasculogenic mimicry, a negative indicator for progression free survival of lung adenocarcinoma irrespective of first line treatment and epithelial growth factor receptor mutation status

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Xuejun He ◽  
Jijun You ◽  
Haibing Ding ◽  
Zhisheng Zhang ◽  
Lin Cui ◽  
...  
Keyword(s):  
Lung Adenocarcinoma ◽  
Target Therapy ◽  
Vasculogenic Mimicry ◽  
Therapy Response ◽  
Progression Free Survival ◽  
Egfr Mutations ◽  
Line Treatment ◽  
First Line ◽  
Free Survival ◽  
First Line Treatment

Abstract Background Vascular mimicry (VM) was associated with the prognosis of cancers. The aim of the study was to explore the association between VM and anticancer therapy response in patients with lung adenocarcinoma. Methods This was a single-center retrospective study of patients with lung adenocarcinoma between March 1st, 2013, to April 1st, 2019, at the Second People’s Hospital of Taizhou City. All included patients were divided into the VM and no-VM groups according to whether VM was observed or not in the specimen. Vessels with positive PAS and negative CD34 staining were confirmed as VM. The main outcome was progression-free survival (PFS). Results Sixty-six (50.4%) patients were male. Eighty-one patients received chemotherapy as the first-line treatment, and 50 patients received TKIs. Forty-five (34.4%) patients were confirmed with VM. There was no difference regarding the first-line treatment between the VM and no-VM groups (P = 0.285). The 86 patients without VM had a median PFS of 279 (range, 90–1095) days, and 45 patients with VM had a median PFS of 167 (range, 90–369) days (P < 0.001). T stage (hazard ratio (HR) = 1.37, 95% confidence interval (CI): 1.10–1.71), N stage (HR = 1.43, 95%CI: 1.09–1.86), M stage (HR = 2.85, 95%CI: 1.76–4.61), differentiation (HR = 1.85, 95%CI: 1.29–2.65), therapy (HR = 0.32, 95%CI: 0.21–0.49), VM (HR = 2.12, 95%CI: 1.33–3.37), and ECOG (HR = 1.41, 95%CI: 1.09–1.84) were independently associated with PFS. Conclusion The benefits of first-line TKIs for NSCLC with EGFR mutation are possibly better than those of platinum-based regimens in patients without VM, but there is no difference in the benefit of chemotherapy or target therapy for VM-positive NSCLC harboring EGFR mutations.

scholarly journals FAS and Subsequent Therapies in Pancreatic Neuroendocrine Tumors

2021 ◽  
Author(s):  
Jane E. Rogers ◽  
Michael Lam ◽  
Daniel M. Halperin ◽  
Cecile G. Dagohoy ◽  
James C. Yao ◽  
...  
Keyword(s):  
Neuroendocrine Tumors ◽  
Cox Regression ◽  
Progression Free Survival ◽  
Pancreatic Neuroendocrine Tumors ◽  
Free Survival ◽  
Prior Therapy ◽  
Well Differentiated ◽  
Grade 3 ◽  
Line Of Therapy

We evaluated outcomes of treatment with 5-fluorouracil (5-FU), doxorubicin, and streptozocin (FAS) in well-differentiated pancreatic neuroendocrine tumors (PanNETs) and its impact on subsequent therapy (everolimus or temozolomide). Advanced PanNET patients treated at our center from 1992 to 2013 were retrospectively reviewed. Patients received bolus 5-FU (400 mg/m2), streptozocin (400 mg/m2) (both IV, days 1-5) and doxorubicin (40 mg/m2 IV, day 1) every 28 days. Overall response rate (ORR) was assessed using RECIST version 1.1. Of 243 eligible patients, 220 were evaluable for ORR, progression-free survival (PFS), and toxicity. Most (90%) had metastatic, nonfunctional PanNETs; 14% had prior therapy. ORR to FAS was 41% (95% confidence interval [CI]: 36-48%). Median follow-up was 61 months. Median PFS was 20 (95% CI: 15-23) months; median overall survival (OS) was 63 (95% CI: 60-71) months. Cox regression analyses suggested improvement with first-line vs subsequent lines of FAS therapy. Main adverse events ≥ grade 3 were neutropenia (10%) and nausea/vomiting (5.5%). Dose reductions were required in 32% of patients. Post-FAS everolimus (n=108; 68% second line) had a median PFS of 10 (95% CI: 8-14) months. Post-FAS temozolomide (n=60; 53% > fourth line) had an ORR of 13% and median PFS of 5.2 (95% CI: 4-12) months. In this largest reported cohort of PanNETs treated with chemotherapy, FAS demonstrated activity without significant safety concerns. FAS did not appear to affect subsequent PFS with everolimus; this sequence is being evaluated prospectively. Responses were noted with subsequent temozolomide-based regimens although PFS was possibly limited by line of therapy.

637 Immune-related adverse events (irAEs) may indicate a favorable prognosis in metastatic renal cell carcinoma (mRCC) patients treated with immune checkpoint inhibitors (ICI)

2020 ◽  
Vol 8 (Suppl 3) ◽  
pp. A672-A673
Author(s):  
Dylan Martini ◽  
Sean Evans ◽  
Subir Goyal ◽  
Yuan Liu ◽  
T Anders Olsen ◽  
...  
Keyword(s):  
Renal Cell Carcinoma ◽  
Overall Survival ◽  
Adverse Events ◽  
Clinical Outcomes ◽  
Immune Checkpoint Inhibitors ◽  
Checkpoint Inhibitors ◽  
Progression Free Survival ◽  
Free Survival ◽  
Kaplan Meier ◽  
Emory University

BackgroundImmune checkpoint inhibitors (ICI) have become an increasingly utilized treatment in metastatic renal cell carcinoma (mRCC). Although they have a favorable toxicity profile, immune-related adverse events (irAEs) can have a significant impact on patients‘ quality of life. It is not well understood whether irAEs are associated with improved clinical outcomes. We investigated the relationship between irAEs and clinical outcomes in mRCC patients treated with ICI.MethodsWe performed a retrospective study of 200 patients with mRCC who received ICI at Winship Cancer Institute of Emory University from 2015–2020. Clinical outcomes were measured by overall survival (OS), progression-free survival (PFS), and clinical benefit (CB). OS and PFS were calculated from ICI-initiation to date of death and radiographic or clinical progression, respectively. CB was defined as a best radiographic response of complete response (CR), partial response (PR), or stable disease (SD) for >6 months per response evaluation criteria in solid tumors (RECIST) version 1.1. Toxicity data was collected from clinic notes and laboratory values. The association with OS and PFS was modeled by Cox proportional hazards model. Kaplan-Meier curves were created for survival estimates.ResultsMost patients were males (71%), and 78% had clear-cell RCC (ccRCC). Most patients (58%) received anti-PD-1 monotherapy. The majority were international mRCC database consortium (IMDC) intermediate (57%) or poor-risk (26%). Anti-PD-1 monotherapy was the most common (58%) treatment regimen and most patients received ICI as first (38%) or second-line (42%) treatment. One-third of patients (33%) experienced an irAE, with the most common being endocrine (13%), gastrointestinal (11%), and dermatologic (10%). Patients who experienced irAEs had significantly longer OS (HR: 0.52, 95% CI: 0.32–0.87, p=0.013), higher chance of CB (OR: 2.10, 95% CI: 1.11–4.00, p=0.023) and showed a trend towards longer PFS (HR: 0.71, 95% CI: 0.49–1.02, p=0.065) in MVA (table 1). Patients who had thyroid irAEs had significantly longer OS, PFS, and higher chance of CB in MVA (table 1). The objective response rate was higher for patients who experienced irAEs (34% vs. 18%). Patients who experienced irAEs had significantly longer median OS (44.5 vs. 18.2 months, p=0.005) and PFS (7.5 vs 3.6 months, p=0.0028) compared to patients who did not (figure 1).Abstract 637 Table 1MVA* of association between irAEs and clinical outcomesAbstract 637 Figure 1Kaplan-Meier curves of association between immune-related adverse events (irAEs) and overall survival (OS, top panel) and progression-free survival (PFS, bottom panel)ConclusionsWe showed that mRCC patients who experienced irAEs, particularly thyroid irAEs, had improved clinical outcomes. This suggests that irAEs may be prognostic of favorable outcomes in mRCC patients treated with ICI. Larger, prospective studies are needed to validate these findings.AcknowledgementsResearch reported in this publication was supported in part by the Breen Foundation and the Biostatistics Shared Resource of Winship Cancer Institute of Emory University and NIH/NCI under award number P30CA138292. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.Trial RegistrationNot applicableEthics ApprovalThis retrospective study was approved by the Emory University Institutional Review Board.ConsentNot applicableReferencesNot applicable

The association between albumin-globulin ratio (AGR) and survival in patients treated with immune checkpoint inhibitors

2021 ◽  
pp. 1-11
Author(s):  
Deniz Can Guven ◽  
Oktay Halit Aktepe ◽  
Melek Seren Aksun ◽  
Taha Koray Sahin ◽  
Gozde Kavgaci ◽  
...  
Keyword(s):  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Multivariate Analyses ◽  
Checkpoint Inhibitors ◽  
Progression Free Survival ◽  
Free Survival ◽  
Patients With Cancer ◽  
Early Progression ◽  
Term Benefit

BACKGROUND: The albumin-globulin ratio (AGR) could be a prognostic biomarker in patients with cancer, although the data is limited in patients treated with immune-checkpoint inhibitors (ICIs). OBJECTIVES: We aimed to evaluate the association between AGR and survival in ICI-treated patients. METHODS: The data of 212 advanced-stage patients were retrospectively evaluated in this cohort study. The association between AGR with overall (OS) and progression-free survival (PFS) were evaluated with multivariate analyses. Additionally, receptor operating curve (ROC) analysis was conducted to assess the AGR’s predictive power in the very early progression (progression within two months) and long-term benefit (more than twelve months survival). RESULTS: The median AGR was calculated as 1.21, and patients were classified into AGR-low and high subgroups according to the median. In the multivariate analyses, patients with lower AGR (< 1.21) had decreased OS (HR: 1.530, 95% CI: 1.100–2.127, p= 0.011) and PFS (HR: 1.390, 95% CI: 1.020–1.895, p= 0.037). The area under curve of AGR to detect early progression and long-term benefit were 0.654 (95% CI: 0.562–0.747, p= 0.001) and 0.671 (95% CI: 0.598–0.744, p< 0.001), respectively. CONCLUSIONS: In our experience, survival with ICIs was impaired in patients with lower AGR. Additionally, the AGR values could detect the very early progression and long-term benefit ICIs.

scholarly journals Phase Ib/II trial evaluating the safety, tolerability and immunological activity of durvalumab (MEDI4736) (anti-PD-L1) plus tremelimumab (anti-CTLA-4) combined with FOLFOX in patients with metastatic colorectal cancer

ESMO Open ◽  
2018 ◽  
Vol 3 (4) ◽  
pp. e000375 ◽  
Author(s):  
Jean-David Fumet ◽  
Nicolas Isambert ◽  
Alice Hervieu ◽  
Sylvie Zanetta ◽  
Jean-Florian Guion ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Metastatic Colorectal Cancer ◽  
Checkpoint Inhibitors ◽  
Target Therapy ◽  
Performance Status ◽  
Human Monoclonal Antibody ◽  
Eastern Cooperative Oncology Group ◽  
Predictive Biomarkers ◽  
Progression Free Survival ◽  
Mutational Status

Background5-Fluorouracil plus irinotecan or oxaliplatin alone or in association with target therapy are standard first-line therapy for metastatic colorectal cancer (mCRC). Checkpoint inhibitors targeting PD-1/PD-L1 demonstrated efficacy on mCRC with microsatellite instability but remain ineffective alone in microsatellite stable tumour. 5-Fluorouracil and oxaliplatin were known to present immunogenic properties. Durvalumab (D) is a human monoclonal antibody (mAb) that inhibits binding of programmed cell death ligand 1 (PD-L1) to its receptor. Tremelimumab (T) is a mAb directed against the cytotoxic T-lymphocyte-associated protein 4 (CTLA-4). This study is designed to evaluate whether the addition of PD-L1 and CTLA-4 inhibition to oxaliplatin, fluorouracil and leucovorin (FOLFOX) increases treatment efficacy.MethodsThis phase II study (ClinicalTrials.gov NCT03202758) will assess the efficacy and safety of FOLFOX/D/T association in patients with mCRC (n=48). Good performance status patients (Eastern Cooperative Oncology Group <2) with untreated, RAS mutational status mCRC will be eligible. Prior adjuvant therapy is allowed provided recurrence is >6 months postcompletion. There is a safety lead in nine patients receiving FOLFOX/D/T. Assuming no safety concerns the study will go on to include 39 additional patients. Patients will receive folinic acid (400 mg/m²)/5-fluorouracil (400 mg/m² as bolus followed by 2400 mg/m2 as a 46-hour infusion)/oxaliplatin (85 mg/m2) every 14 days with D (750 mg) D1 every 14 days and T (75 mg) D1 every 28 days. After six cycles of FOLFOX only D/T will continue until disease progression, death, intolerable toxicity, or patient/investigator decision to stop. Primary endpoint is safety and efficacy according to progression-free survival (PFS); secondary endpoints include overall response rate and quality of life. Hypothesis is that a PFS of 50% at 6 months is insufficient and a PFS of 70.7% is expected (with α=10%, β=10%). Blood, plasma and tumour tissue will be collected and assessed for potential prognostic and predictive biomarkers.

scholarly journals Artificial intelligence-aided clinical annotation of a large multi-cancer genomic dataset

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Kenneth L. Kehl ◽  
Wenxin Xu ◽  
Alexander Gusev ◽  
Ziad Bakouny ◽  
Toni K. Choueiri ◽  
...  
Keyword(s):  
Cancer Progression ◽  
Language Processing ◽  
Checkpoint Inhibitors ◽  
Progression Free Survival ◽  
Precision Oncology ◽  
Free Survival ◽  
Clinical Endpoints ◽  
Mutation Burden ◽  
Clinical Annotation ◽  
Cancer Types

AbstractTo accelerate cancer research that correlates biomarkers with clinical endpoints, methods are needed to ascertain outcomes from electronic health records at scale. Here, we train deep natural language processing (NLP) models to extract outcomes for participants with any of 7 solid tumors in a precision oncology study. Outcomes are extracted from 305,151 imaging reports for 13,130 patients and 233,517 oncologist notes for 13,511 patients, including patients with 6 additional cancer types. NLP models recapitulate outcome annotation from these documents, including the presence of cancer, progression/worsening, response/improvement, and metastases, with excellent discrimination (AUROC > 0.90). Models generalize to cancers excluded from training and yield outcomes correlated with survival. Among patients receiving checkpoint inhibitors, we confirm that high tumor mutation burden is associated with superior progression-free survival ascertained using NLP. Here, we show that deep NLP can accelerate annotation of molecular cancer datasets with clinically meaningful endpoints to facilitate discovery.

Sign in / Sign up

Export Citation Format

Share Document