Search

Background: Clinician-rated adverse event data from pivotal trials of the CDK4/6 inhibitor palbociclib (palbo) in patients (pts) with HR+ HER2- metastatic breast cancer (MBC) describe fatigue as a common non-hematologic toxicity. While palbo and endocrine therapy (ET) significantly improve outcomes compared to ET alone, in a pooled analysis of the PALOMA trials, rates of incident Common Terminology Criteria for Adverse Events (CTCAE) all-grade fatigue over 4.2 years of treatment approached 39.2%, with grade 3/4 at 2.5%. As these studies included only provider-rated CTCAE toxicity, it is important to quantify pts’ ratings of fatigue severity, which may differ from clinician assessments. Methods: Eligible pts with HR+ HER2- MBC, initiating standard-dose palbo with ET (aromatase inhibitor or fulvestrant), and without clinically meaningful fatigue prior to initiation of palbo, were followed for the 6 initial treatment cycles. The absence of baseline fatigue was established using the patient-reported Functional Assessment of Chronic Illness Therapy Fatigue Scale (FACIT-F), a 13-item scale (range 0-52, lower score = more fatigue) validated against anemia to indicate clinically meaningful fatigue if FACIT-F score =34; PRO-CTCAE fatigue severity grade 3/4 vs. Citation Format: Shadab A Rahman, Erica L Mayer, Hanneke Poort, Deborah Schrag, Stephanie C Tung, Eric S Zhou, Aleta Wiley, Lauren Finkelstein, Elkhansaa Elguenaoui, Moira Nolan, Hadine Joffe. Incidence of patient-reported fatigue developing in patients receiving palbociclib and endocrine therapy for advanced HR+ HER2- breast cancer [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P4-09-01.

Anticancer therapy changes tumor physiology and genomics, making it a key variable in cancer studies. Although antineoplastics given at a single institution may be available in research-ready format, treatment at external institutions prior to receiving care at academic medical centers, common among patients at these centers, is often only described in free-text clinical notes, necessitating manual curation for downstream analysis. To overcome this bottleneck, we trained and validated natural language processing (NLP) models using initial consult notes to identify whether patients had received treatment at external institutions and studied the impact of these putative treatments on tumor genomics. Training data were derived from the AACR Project GENIE Biopharma Collaborative (BPC) for 2,663 patients at Memorial Sloan Kettering (MSK) across four cancer types. For each patient, we selected initial visits with medical and radiation oncologists based on an a priori note prioritization scheme and determined “ground-truth” prior external medications based on manually curated BPC administration records, whitelisting MSK-given medications. We trained logistic regression and clinical longformer models to identify external treatment receipt and evaluated model performance with 5-fold cross-validation. The clinical longformer model performed best across evaluation metrics, with an average area under the receiver operating characteristic curve of 0.972, macro-averaged precision/recall of 0.854/0.902 and macro-averaged F1 score of 0.876. Re-review of discrepant cases suggested that 75% of “false positives” may be due to curation error. We used our model to infer treatment status in a pan-cancer cohort with tumor genomic profiling using our institutional sequencing platform. Out of 48,447 patients, 11,900 were predicted to have received external treatment. Patients with putative external treatment had higher alteration frequencies in resistance-related genes than untreated patients and comparable to known pre-treated patients, including ESR1 in patients with breast cancer, AR in patients with prostate cancer, and EGFR T790M in patients with EGFR-mutated non-small cell lung cancer. Patients with putative external treatments, similar to known pre-treated patients, had shorter survival compared to treatment-naïve patients of the same cancer type. NLP can abstract external treatment status from clinical notes. When applied at scale, our model could help mitigate confounding variables and identify relationships between clinicogenomic variables and anticancer therapy. Citation Format: Thinh N. Tran, Karl B. Pichotta, Si-Yang Liu, Christopher Fong, Anisha Luthra, Brooke Mastrogiacomo, Steven Maron, Deborah Schrag, Sohrab P. Shah, Pedram Razavi, Bob T. Li, Gregory J. Riely, Nikolaus Schultz, Justin Jee. Identification of anti-neoplastic therapy given before initial visit at a referral center using natural language processing applied to medical oncology initial consultation notes. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 4259.

Obtaining information regarding cancer recurrence from a retrospective, EHR-based dataset poses several challenges primarily due to the lack of structured data. Patients are at risk for cancer recurrence beginning at a time point at which they are characterized as having no evidence of disease. The absence of cancer may be indicated on a radiology report or a medical oncologist assessment, requiring manual review and interpretation of potentially ambiguous free text. Further, the recurrence event itself can be defined based on several distinct data sources including pathology, imaging, clinician assessments, or tumor markers. The likelihood of ascertaining recurrence is dependent on the frequency and type of surveillance performed and varies based on tumor type and based on clinicians' thresholds for pursuing workup of borderline or suspicious findings; if follow up assessments are infrequent, there are fewer opportunities to detect recurrence. Given these challenges, there is currently no standardized approach to evaluating cancer recurrence in EHR data, impeding analyses of rare molecular tumor subtypes in multi-institutional linked clinico-genomic databases. For this analysis, we leveraged the AACR Project GENIE Biopharma Collaborative data based on the PRISSMM curation model to develop an algorithm for identifying recurrence among patients diagnosed with stage I-III non-small cell lung cancer or with stage I-III colorectal cancer. This algorithm involves using curated pathology report data to identify a definitive surgery as the time at which patients have completed curative intent treatment. Subsequent imaging reports, pathology reports, medical oncologist assessments and tumor marker data are then evaluated in order to characterize the timing of specific recurrence events. We will present the real-world recurrence algorithm, its underlying rationale and discuss applications of recurrence endpoints. Beyond enabling estimates of recurrence-free survival, identifying cancer recurrence will allow for estimation of progression-free survival among stage I-III patients in addition to estimation of PFS among de novo stage IV patients. Estimating PFS in a large cohort of patients with linked phenomic and genomic data has historically been a limitation of these types of datasets. Overcoming this limitation will allow for precision medicine advances in oncology by facilitating data pooling across institutions and enabling examination of rare molecular subtypes in relation to clinically meaningful endpoints. Citation Format: Jessica A. Lavery, Samantha Brown, Eva Lepisto, Michele L. Lenoue-Newton, Caroline McCarthy, Hira Rizvi, Celeste Yu, Kenneth L. Kehl, Shawn M. Sweeney, Julia E. Rudolph, Nikolaus Schultz, Brooke Mastrogiacomo, Ritika Kundra, Jeremy Warner, Philippe Bedard, Gregory J. Riely, Katherine S. Panageas, Deborah Schrag, AACR Project GENIE Consortium. Defining real-world recurrence in the AACR Project GENIE Biopharma Collaborative Data [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2619.

Studies linking genomic and phenomic data are subject to selection biases, including delayed entry or immortal time bias. Delayed entry can be problematic for time-to-event analyses, but utilization of appropriate statistical methods to account for delayed entry are underutilized. Delayed entry commonly occurs when genomic sequencing results are obtained after the start time for survival estimation. To evaluate the impact of left truncation on overall survival (OS) estimates, we explored outcomes in patients with de novo stage IV non-small cell lung cancer (NSCLC) and colorectal cancer (CRC) from the AACR GENIE Biopharma Collaborative, who had genomic sequencing within a specified timeframe. We analyzed OS from diagnosis and from start of the most common first-line regimen, carboplatin/pemetrexed for NSCLC (N = 212 patients) and FOLFOX for CRC (N = 369 patients). We compared median OS using standard Kaplan-Meier methods to median OS using left truncation methods to account for delayed entry. All NSCLC and CRC patients underwent genomic sequencing after their diagnosis date. Among NSCLC patients on carboplatin/pemetrexed, 41% and among CRC patients on FOLFOX, 14% had sequencing determined after starting first-line regimen. The survfit function in R package survival was used, and the absolute differences and percent differences in median OS estimates were calculated. Failure to account for delayed entry leads to an overestimation of OS, regardless of cohort and start date. Adjusting survival outcomes using left truncation methods reduces the influence of some aspects of selection bias and results in better estimates of time to event outcomes. Analyses from these cohorts can provide meaningful insights about survival outcomes outside the clinical trial setting and may support trial design and reliable selection of control arms. As such, it is imperative that analytic methods to account for the inflated survival estimates are incorporated. EstimateCRC Stage IV (N = 658)NSCLC Stage IV (N = 722)Unadjusted Median (IQR) Overall Survival from Diagnosis (Years)3.2 (2.9, 3.4)2.3 (2.0, 2.5)Median (IQR) Overall Survival from Diagnosis in Years, Adjusting for Delayed Entry2.1 (1.9, 2.4)1.3 (1.1, 1.6)Difference in Medians (Years)1.11.0% Difference in Medians34%44%EstimateCRC Stage IV (N = 369)NSCLC Stage IV (N = 212)Unadjusted Median (IQR) Overall Survival from Most Common First-Line Regimen (Years)2.9 (2.6, 3.4)1.3 (1.0, 1.6)Median (IQR) Overall Survival from Most Common First-Line Regimen in Years, Adjusting for Delayed Entry2.1 (1.8, 2.5)0.9 (0.7, 1.2)Difference in Medians (Years)0.80.4% Difference in Medians28%31% Citation Format: Samantha Brown, Jessica A. Lavery, Eva M. Lepisto, Caroline McCarthy, Hira Rizvi, Celeste Yu, Kenneth L. Kehl, Shawn M. Sweeney, Julia E. Rudolph, Nikolaus Schultz, Ritika Kundra, Brooke Mastrogiacomo, Phillipe Bedard, Jeremy L. Warner, Gregory J. Riely, Deborah Schrag, Katherine S. Panageas, The AACR Project GENIE Consortium. Ignoring left truncation in overall survival within real-world genomic-phenomic data leads to inflated survival estimates [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2620.

Introduction: Clinical research using genomic datasets, such as AACR Project GENIE, requires outcomes such as cancer progression and response to contextualize molecular information. We are developing the “PRISSMM” (Pathology, Radiology/Imaging, Signs/Symptoms, Medical oncologist assessment, and tumor Markers) framework for clinical curation of genomic data. Natural language processing (NLP) models based on this framework could accelerate curation of reproducible endpoints. However, the application of NLP at scale to extract outcomes from oncologist notes, which mix historical and current information, has been limited to date. Methods: Medical oncologists' progress notes were reviewed for patients with lung cancer whose tumors were sequenced through an institutional precision medicine study from 2013-2018. For each note, curators recorded whether the assessment/plan indicated the presence of (a) any cancer, (b) progression/worsening of disease, and/or (c) response to therapy/improvement of disease. Next, a recurrent neural network was trained to extract the assessment/plan from each note. Finally, convolutional neural networks were trained on the assessments/plans to predict the probability that each curated outcome was present. Model performance was evaluated among a held-out 10% test subset of patients using the area under the receiver-operating characteristic curve (AUC) and area under the precision-recall curve (AUPRC). Associations between curated response or progression endpoints (generated using 10-fold cross-validation) and overall survival were measured using Cox models, treating the endpoints as time-varying covariates, among patients receiving palliative-intent systemic therapy. Results: Results among 7,597 curated notes for 919 patients are indicated in the Table. EndpointAUC of NLP models for identifying endpoint in the test setProportion of manually curated notes with endpointAUPRC of NLP models for identifying endpoint in the test setHR (95% CI) for mortality associated with endpoint, as manually curated, among patients receiving palliative- intent treatmentHR (95% CI) for mortality associated with endpoint, as predicted using NLP models using F1-optimal threshold probabilitiesAny evidence of lung cancer0.940.770.97N/AN/AProgression0.860.200.652.93 (2.33-3.67)2.49 (2.00-3.09)Response to treatment0.900.120.570.70 (0.47-1.03)0.45 (0.30-0.67) Conclusion: Neural network NLP models can extract meaningful outcomes from oncologist notes for clinical curation of electronic health records at scale. Citation Format: Kenneth L. Kehl, Wenxin Xu, Haitham A. Elmarakeby, Michael J. Hassett, Jackson Nyman, Bruce E. Johnson, Eliezer M. Van Allen, Deb Schrag. Deep natural language processing for automated ascertainment of cancer outcomes from clinician progress notes [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 2063.

Background: Early detection decreases patient mortality for many cancers, but prevailing paradigms focus on distinct screening modalities for each cancer type. A minimally invasive test that detects multiple tumor types could substantially reduce cancer mortality and improve screening efficiency. In preliminary studies, we showed that a targeted methylation cell-free DNA (cfDNA) test can detect cancer and determine the tissue of origin (TOO) of abnormally methylated cfDNA with high sensitivity and specificity; however, blood was collected at the time of diagnosis and results were not disclosed to inform care. The current study includes disclosure of results to the study investigator to understand the care pathways prompted by a “signal detected” test result, and the benefits, harms, and burdens associated with a multi-cancer detection test. Methods: PATHFINDER (NCT04241796) is a prospective, longitudinal, multi-center clinical study. Approximately 6,200 participants with varying levels of cancer risk will be enrolled at 5-10 clinical sites in the United States. Participants must be ≥50 years of age. If participants have at least 1 of the following–a smoking history of ≥100 cigarettes, a genetic cancer predisposition, or a history of invasive or hematologic malignancy with definitive treatment completed >3 years prior to enrollment–they are eligible for the Elevated Risk Cohort (n = 4340); otherwise, they are eligible for the Non-Elevated Risk Cohort (n = 1860). Individuals being evaluated for cancer or who have a history of invasive or hematologic malignancy within 3 years of enrollment will be excluded. Blood drawn at study sites will be analyzed at GRAIL, Inc. (Menlo Park, CA). Participants and study investigators will be informed of the test results. Participants with “signal not detected” results will be advised to continue routine clinical care, including age- and risk-based cancer screening. Those with “signal detected” test results will be informed of the predicted origin and undergo diagnostic evaluation. The primary study objective is to determine the extent of diagnostic testing required to achieve diagnostic resolution following a “signal detected” test result, defined as the date when the study investigator determines to end diagnostic evaluation triggered by a “signal detected” test result. Health resource utilization, the number and types of tests and time required to reach this point, is the primary endpoint. Secondary objectives include evaluation of test performance (specificity, positive predictive value, and TOO accuracy), and assessment of participants' perceptions about the test and changes in anxiety and health-related quality of life. Exploratory aims include assessment of the number and types of invasive cancer diagnoses among participants with “signal not detected” test results and changes in attitude toward adherence to guideline-recommended screening. Citation Format: Lincoln Nadauld, Charles H. McDonnell III, Minetta C. Liu, Eric Klein, Tomasz M. Beer, Deborah Schrag, Andrew G. Hudnut, Richard Whittington, Bruce Taylor, Joanna Tierney, Catherine Marinac, Jafi Lipson, Margarita Lopatin, Karen C. Chung, Eric Fung, Anne-Renee Hartman, Geoffrey R. Oxnard. The PATHFINDER Study: Assessment of the implementation of an investigational multi-cancer early detection test into clinical practice [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr CT291.

Introduction: Efforts such as AACR Project GENIE pool genomic data across institutions to facilitate understanding of the clinical impact of genomic biomarkers in cancer. However, correlating genomic data with treatment outcomes is challenging, since outside clinical trials, outcomes such as improving or worsening cancer may be recorded only in electronic health record (EHR) free text. Automated methods could accelerate discovery by reliably characterizing treatment outcomes from unstructured EHR data. Methods: We analyzed unstructured imaging reports for patients with solid tumors (any stage) who participated in an institutional next generation sequencing study from 2013-2018 and received palliative-intent systemic therapy. A recurrent neural network was trained to predict overall survival (OS) following each report, using text from the report and the sequence of prior reports for the patient. Model performance was measured using the concordance (c)-index in a 10% held-out validation set. Next, the ‘delta prognosis, (ΔP)' was measured for each report. ‘Delta prognosis' (ΔP) captures the change in the number of months a patient is predicted to be alive out of the 12 months following each report, compared to the exponentially weighted moving average of prior prognostic predictions for that patient. Finally, a second neural network was trained to predict ΔP using each report. Ten-fold cross validation was used to annotate each report so ΔP measures for each patient would not be based on that patient's actual survival time. Using joint modeling of ΔP, biomarker status, and report frequency, associations were measured between ΔP and previously described prognostic biomarkers for cancer types in which prolonged survival with advanced disease is common, including BRAF mutations in colorectal cancer and BRCA1/2 mutations in ovarian cancer. Results: Model training was performed using 78,371 imaging reports for 4,512 patients with 273 cancer histologies. In a validation set of 9,306 reports for 595 patients, the c-index for survival prediction was 0.76. Within the first 6 months of palliative-intent therapy, among 597 patients with colorectal cancer, BRAF mutations were associated with worse mean ΔP (-0.33 months per report; 95% CI, -0.55 to -0.11 months; p = 0.003); among 395 patients with ovarian cancer, BRCA1/2 mutations were associated with better mean ΔP (+0.39 months per report; 95% CI, 0.17-0.61 months; p < 0.001). The latter association could not have been evaluated statistically using an overall survival endpoint, since no patients with BRCA1/2 mutations died within 6 months. Conclusion: Neural networks trained to identify shifts in prognosis using EHR text may enable ascertainment of improving and worsening cancer with no manual labeling, even if overall survival data are unavailable or immature at inference time. This technique could be relevant to any analysis of cancer outcomes using EHR data. Citation Format: Kenneth L. Kehl, Haitham A. Elmarakeby, Michael J. Hassett, Eliezer M. Van Allen, Deb Schrag. Delta prognosis: A novel clinical outcome based on automated analysis of unstructured cancer EHR data [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 2062.

Purpose: Treatment decisions regarding Ductal Carcinoma in Situ (DCIS) are complex, and patients often have inaccurate and incomplete understanding of the risks and benefits they face. Our objective was to create a web-based decision aid (onlineDeCISion.org) that can be used in clinical practice to guide both clinicians and their patients with these decisions. Methods: We developed a web-based clinical decision aid to provide tailored information about DCIS treatment choices including an individual patient’s risk of recurrence, likelihood of long-term breast preservation and survival outcomes following up to 6 different treatment strategies for DCIS (lumpectomy, lumpectomy with radiation, lumpectomy with tamoxifen, lumpectomy with radiation and tamoxifen, and mastectomy with or without breast reconstruction). The decision aid is populated by our previously developed simulation model of DCIS outcomes. A theoretical framework and best-practices for web-based decision tools guided the development of the decision aid including semi-structured interviews and usability testing with a diverse group of multidisciplinary clinicians and patient advocates. Results: The decision aid was designed to include these key features: 1) descriptions of treatment options; 2) ability to input patient health-adjusted age; 3) tailored likelihood of time-specific (10-year and lifetime) recurrence and survival outcomes; and 4) projections of downstream effects of each treatment. The decision aid provides default recurrence risks based on clinical trial data but allows clinicians to customize 10-year DCIS and invasive recurrence risks to retain flexibility to display expected outcomes for individual patients. These estimates can be based on the patient’s actual age, or age adjusted for health status, allowing for a more realistic expectation of the benefits each treatment holds. Conclusion: Our web-based decision aid displays tailored outcomes following different treatment strategies for DCIS, allowing patients to be better informed about the tradeoffs of treatments available to them and select treatments consonant with their personal preferences, improving the quality of decision making for DCIS. The interactive design features allow users of the decision aid the ability to address uncertainty around risks of recurrence and comorbidity risks and facilitate the use of the decision aid across diverse populations. While the decision aid warrants further evaluation, the results of our study promise to improve decision making in patients with DCIS. Citation Format: Elissa M Ozanne, Natasha K Stout, Katharine Schneider, Djøra Soeteman, Deborah Schrag, Michael Fordis, Rinaa S Punglia. onlineDeCISion.org: An interactive web-based clinical decision aid for DCIS treatment [abstract]. In: Proceedings of the Thirty-Seventh Annual CTRC-AACR San Antonio Breast Cancer Symposium: 2014 Dec 9-13; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2015;75(9 Suppl):Abstract nr P2-10-01.

Background: AACR GENIE is an international data-sharing project that aggregates clinical-grade cancer genomic data. As a demonstration of utility, we evaluated the landscape of ERBB2 mutations in the first 18,486 patients included in this registry and compared it to the first 100 patients enrolled in an ongoing international Phase 2 SUMMIT ‘basket’ study of the pan-HER inhibitor neratinib in ERBB2 mutant solid tumors (NCT01953926). Results: ERBB2 mutations were identified in 2.8% (519/18,486) of patients in the GENIE cohort and observed at all participating centers. In total, there were 482 missense, 66 indels, 19 truncating mutations, and 14 structural variants. A total of 263 unique missense mutations were observed including 12 at previously identified hotspots which accounted for 69.2% of all missense mutations. 35 unique cancer types were represented. The tumor types with the highest proportion of ERBB2 mutations were bladder (12.8%, 82/641), breast (3.9%, 87/2230), colorectal (3.3%, 70/2102), and NSCLC (3%, 90/3006). Among patients with copy number data available (91%) 11% had concurrent ERBB2 amplification, most often in breast cancer. The most frequently observed alterations in ERBB2, adjusted for differing exon coverage between panels, was S310F/Y in 0.46% of the GENIE cohort (12.6% of samples with ERBB2 alterations), Y772_A775dup in 0.21% (6.9%), R678Q in 0.17% (4.5%), L755S in 0.16% (5.2%), V777L in 0.12% (3.8%), and V842I in 0.09% (3.1%). The distribution of specific ERBB2 variants differed significantly by tumor type with exon 20 insertions being most common in NSCLC (44.4%, 40/90), L755S (18.9%, 11/92) in breast, S310F/Y (26.9%, 28/104) in bladder, and V842I (13.9%, 10/72) in colorectal cancer. Structural variants included intragenic deletions (n=4) and fusions involving various partners including GRB7 (n=2), and one each of C1orf87, PPIL6, HEXIM2, THRA, ASIC2, BCA3, WIPF2. The frequencies of ERBB2 mutant cancer types observed in the GENIE cohort were generally comparable to those enrolled to the neratinib basket study including NSCLC (17 vs 22%, respectively), breast (16.4 vs 24%), bladder (15.5 vs 14%), colorectal (13.2 vs 17%), and endometrial (4.2 vs 6%). At the variant level, S310F/Y was less prevalent in GENIE compared to the neratinib study (12.6 vs 24%) while all other mutations were generally similar including L755S (5.2 vs 9%), R678Q (4.5 vs 2%), Y772_A775dup (6.9 vs 13%), V777L (3.8 vs 9%), and V842I (3.1 vs 6%). Conclusion: GENIE confirms that a diversity of ERBB2 mutations are prevalent across a variety of tumor types in patients with advanced cancer. The genomic landscape of ERBB2 mutations was largely similar in the population based GENIE cohort and the neratinib SUMMIT study, providing the first direct evidence that basket study enrollment accurately reflects the true landscape of the target alteration. Citation Format: Alison Schram, Helen H. Won, Fabrice Andre, Monica Arnedos, Funda Meric - Bernstam, Philippe L. Bedard, Kenna R. Shaw, Hugo Horlings, Christine Micheel, Ben Ho Park, Grace Mann, Alshad S. Lalani, Lillian Smyth, David B. Solit, Deborah Schrag, Mia A. Levy, Barrett J. Rollins, Mark Routbort, Charles L. Sawyers, Eva Lepisto, Michael F. Berger, David M. Hyman, on behalf of the AACR Project GENIE Consortium. Landscape of somatic ERBB2 Mutations: Findings from AACR GENIE and comparison to ongoing ERBB2 mutant basket study [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2017; 2017 Apr 1-5; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2017;77(13 Suppl):Abstract nr LB-103. doi:10.1158/1538-7445.AM2017-LB-103