Abstract 923P
Background
Patients with cancer of unknown primary (CUP) have a poor prognosis due to delays in diagnostic workup and empirically-selected platinum-based regimens that may not be the most active first line for the primary disease. The Tempus Tumor Origin (TO) test is a machine learning classifier that uses RNA-Seq data to identify the most likely cancer type or subtype from 68 possible diagnoses. Despite the importance of cancer type identification in advising guideline-based treatment, prior studies of molecular classifiers have found unclear clinical impact in the CUP setting.
Methods
We retrospectively analyzed de-identified records from 289 patients who received a diagnosis of uncertain/unknown primary; all had NGS and TO testing ordered by the original treating clinician. Two oncologists separately reviewed patient clinical information—including imaging, pathology, and NGS reports—to determine the course of treatment before they reviewed TO testing and evaluated whether the algorithm’s predicted diagnosis would change treatment. Disagreement was adjudicated by a third reviewer.
Results
The most common cancer types predicted by the TO test were cholangiocarcinoma (n=58), lung adenocarcinoma (n=41), and pancreatic adenocarcinoma (n=22). The TO test results would have altered the treatment plan in 235 out of 289 cases (81%) and led to follow-up site-specific testing in 140 cases (48%). When treatments changed, the drugs that were most often removed as treatments were: 5-FU (n=46), oxaliplatin (n=42), and carboplatin (n=41). Gemcitabine and cisplatin were added as treatment recommendations in 54 and 49 cases, respectively. Additionally, non-chemotherapy changes include checkpoint inhibitors (CPI; added in 26 cases, removed in 4), surgery (added in 4 cases), and radiation (added in 3 cases, removed in 1).
Conclusions
In our study, we demonstrate that the TO test can specify a diagnosis that alters the therapeutic management for up to 81% of patients with unknown primary. These changes include the addition and removal of chemotherapy and CPI, as well as alterations in radiation and surgical treatments, highlighting the potential of molecular classifiers to provide clinical insight into the management of CUP patients.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
Duke Clinical Research Institute.
Funding
Duke Clinical Research Institute funded by Tempus Labs.
Disclosure
D.J. George: Financial Interests, Personal, Other, Consultant: Advanced Accelerator Applications SA/Novartis, Aveo Pharmaceuticals, Eisai, IdeoOncology, Merck Sharp & Dohme, Myovant Sciences, Inc., Propella Therapeutics, RevHealth, LLC, Seattle Genetics, WebMD, Xcures; Financial Interests, Personal, Other, Sr. Editor: American Association for Cancer Research; Financial Interests, Personal, Advisory Board: Astellas; Financial Interests, Personal, Advisory Board, CAPI-281 Steering Committee member: AstraZeneca; Financial Interests, Personal, Invited Speaker, and Consultant: Bayer H/C Pharmaceuticals, Exelixis, Inc; Financial Interests, Personal, Other, Consultant/IDMC member: Janssen Pharmaceuticals; Financial Interests, Personal, Other, Contributor: Medscape Education; Financial Interests, Personal, Other, Honorarium, Consultant: Michael J Hennessey Associates; Financial Interests, Personal, Other, Co-Editor-in-Chief: Millennium Medical Publishing, Clinical Advances in Hematology & Oncology; Financial Interests, Personal, Other, Steering Committee member: NCI Genitourinary (Leidos biomedical Research); Financial Interests, Personal, Other, Consultant, Steering Committee member, Honorarium: Pfizer; Financial Interests, Personal, Other, Consultant, Speaker, Honorarium: Sanofi; Financial Interests, Personal, Other, Honorarium: UroGPO; Financial Interests, Personal, Other, Honorarium, Travel Accommodations: UroToday; Financial Interests, Personal, Expert Testimony: WilmerHale Attorneys; Financial Interests, Institutional, Funding: Astellas, AstraZeneca, Bristol Meyers Squibb, Calithera, Exelixis, Janssen Pharmaceuticals, Novartis, Pfizer, Sanofi. E. Moore: Financial Interests, Personal, Full or part-time Employment: Tempus Labs; Financial Interests, Personal, Stocks/Shares: Tempus Labs. N. DeVito: Financial Interests, Personal, Invited Speaker, Speaker engagement for immunotherapy continuing medical education where I received honoraria: Society for Immunotherapy in Cancer; Financial Interests, Institutional, Full or part-time Employment, Employment: Private Diagnostic Clinic PLLC, Duke University. B.A. Hanks: Financial Interests, Personal, Invited Speaker: Novartis, Merck; Financial Interests, Personal, Advisory Board: G1 Therapeutics; Financial Interests, Institutional, Research Grant: Merck, Tempest Therapeutics, Leap Therapeutics, A*STAR Singapore, OncoMed Pharmaceuticals, AstraZeneca, GSK; Financial Interests, Institutional, Invited Speaker: Exicure, Sanofi. M.R. Harrison: Financial Interests, Personal, Invited Speaker: Exelixis, Eisai, Gilead Sciences, Myovant Sciences; Financial Interests, Personal, Advisory Board: Fujifilm, Pfizer, Bristol Myers Squibb, Seattle Genetics, Gilead Sciences, Myovant Sciences; Financial Interests, Institutional, Invited Speaker: Bristol Myers Squibb, Genentech, Pfizer, Merck, Astellas Pharma, Bayer, Exelixis, Seattle Genetics, Propella Therapeutics. C.J. Hoimes: Financial Interests, Personal, Invited Speaker: Eisai, BMS; Financial Interests, Personal, Advisory Board: Tempus, Foundation Medicine, BMS, Merck &Co, Seagen, Astellas; Financial Interests, Institutional, Advisory Board: Dynavax; Financial Interests, Personal and Institutional, Invited Speaker: Merck &Co, Seagen; Financial Interests, Institutional, Invited Speaker: Dynavax, Genentech, BioNTech, Astellas, BMS, Prometheus, Janssen, NeoImmune Tech, Bellicum, Pfizer, Mirati, Phosplatin, AbbVie, Bayer. J. Jia: Financial Interests, Invited Speaker: Genentech; Financial Interests, Funding: Xilis. M. Morse: Financial Interests, Personal, Invited Speaker: Genentech, Servier, Eisai, Exelixis, TerSera, Ipsen, AstraZeneca, Daiichi Sankyo; Financial Interests, Institutional, Invited Speaker: BMS, Merck, Ipsen. P. Jayaprakasan: Financial Interests, Personal, Full or part-time Employment: Duke Clinical Research Institute. A. MacKelfresh: Financial Interests, Personal, Full or part-time Employment: Duke Clinical Research Institute. H. Mulder: Financial Interests, Personal, Full or part-time Employment: Duke Clinical Research Institute. K. Beauchamp: Financial Interests, Personal, Full or part-time Employment: Tempus Labs, Inc.; Financial Interests, Personal, Stocks/Shares: Tempus Labs, Inc. J. Michuda: Financial Interests, Personal, Full or part-time Employment: Tempus; Financial Interests, Personal, Other, RSUs: Tempus. M.C. Stumpe: Financial Interests, Personal, Full or part-time Employment, Chief of AI at Tempus: Tempus Labs; Financial Interests, Personal, Stocks/Shares: Tempus Labs, Alphabet; Non-Financial Interests, Officer, C-suite leadership member, lead the AI & Data Science Department: Tempus Labs; Non-Financial Interests, Leadership Role, Led Google Cancer AI team from 2016-2019: Google. E. Perakslis: Financial Interests, Personal, Full or part-time Employment: Duke Clinical Research Institute. T. Taxter: Financial Interests, Personal, Full or part-time Employment, Senior medical director, Algorithmic Diagnostics: Tempus Lab; Financial Interests, Personal, Ownership Interest: Tempus Lab. All other authors have declared no conflicts of interest.