BACKGROUND: Oncologists use patients' life expectancy to guide decisions and may benefit from a tool that accurately predicts prognosis. Existing prognostic models generally use only a few predictor variables. We used an electronic medical record dataset to train a prognostic model for patients with metastatic cancer. METHODS: The model was trained and tested using 12 588 patients treated for metastatic cancer in the Stanford Health Care system from 2008 to 2017. Data sources included provider note text, labs, vital signs, procedures, medication orders, and diagnosis codes. Patients were divided randomly into a training set used to fit the model coefficients and a test set used to evaluate model performance (80%/20% split). A regularized Cox model with 4126 predictor variables was used. A landmarking approach was used due to the multiple observations per patient, with t0 set to the time of metastatic cancer diagnosis. Performance was also evaluated using 399 palliative radiation courses in test set patients. RESULTS: The C-index for overall survival was 0.786 in the test set (averaged across landmark times). For palliative radiation courses, the C-index was 0.745 (95% confidence interval [CI] = 0.715 to 0.775) compared with 0.635 (95% CI = 0.601 to 0.669) for a published model using performance status, primary tumor site, and treated site (two-sided P < .001). Our model's predictions were well-calibrated. CONCLUSIONS: The model showed high predictive performance, which will need to be validated using external data. Because it is fully automated, the model can be used to examine providers' practice patterns and could be deployed in a decision support tool to help improve quality of care.
BACKGROUND: Oncologists use patients' life expectancy to guide decisions and may benefit from a tool that accurately predicts prognosis. Existing prognostic models generally use only a few predictor variables. We used an electronic medical record dataset to train a prognostic model for patients with metastatic cancer. METHODS: The model was trained and tested using 12 588 patients treated for metastatic cancer in the Stanford Health Care system from 2008 to 2017. Data sources included provider note text, labs, vital signs, procedures, medication orders, and diagnosis codes. Patients were divided randomly into a training set used to fit the model coefficients and a test set used to evaluate model performance (80%/20% split). A regularized Cox model with 4126 predictor variables was used. A landmarking approach was used due to the multiple observations per patient, with t0 set to the time of metastatic cancer diagnosis. Performance was also evaluated using 399 palliative radiation courses in test set patients. RESULTS: The C-index for overall survival was 0.786 in the test set (averaged across landmark times). For palliative radiation courses, the C-index was 0.745 (95% confidence interval [CI] = 0.715 to 0.775) compared with 0.635 (95% CI = 0.601 to 0.669) for a published model using performance status, primary tumor site, and treated site (two-sided P < .001). Our model's predictions were well-calibrated. CONCLUSIONS: The model showed high predictive performance, which will need to be validated using external data. Because it is fully automated, the model can be used to examine providers' practice patterns and could be deployed in a decision support tool to help improve quality of care.
Authors: George W Sledge; Clifford A Hudis; Sandra M Swain; Peter M Yu; Joshua T Mann; Robert S Hauser; Allen S Lichter Journal: J Oncol Pract Date: 2013-05 Impact factor: 3.840
Authors: Monica S Krishnan; Zachary Epstein-Peterson; Yu-Hui Chen; Yolanda D Tseng; Alexi A Wright; Jennifer S Temel; Paul Catalano; Tracy A Balboni Journal: Cancer Date: 2013-10-02 Impact factor: 6.860
Authors: William F Hartsell; Charles B Scott; Deborah Watkins Bruner; Charles W Scarantino; Robert A Ivker; Mack Roach; John H Suh; William F Demas; Benjamin Movsas; Ivy A Petersen; Andre A Konski; Charles S Cleeland; Nora A Janjan; Michelle DeSilvio Journal: J Natl Cancer Inst Date: 2005-06-01 Impact factor: 13.506
Authors: Justin E Bekelman; Scott D Halpern; Carl Rudolf Blankart; Julie P Bynum; Joachim Cohen; Robert Fowler; Stein Kaasa; Lukas Kwietniewski; Hans Olav Melberg; Bregje Onwuteaka-Philipsen; Mariska Oosterveld-Vlug; Andrew Pring; Jonas Schreyögg; Connie M Ulrich; Julia Verne; Hannah Wunsch; Ezekiel J Emanuel Journal: JAMA Date: 2016-01-19 Impact factor: 56.272
Authors: Michael Spratt; James Carpenter; Jonathan A C Sterne; John B Carlin; Jon Heron; John Henderson; Kate Tilling Journal: Am J Epidemiol Date: 2010-07-08 Impact factor: 4.897
Authors: Edward Chow; Lori Davis; Tony Panzarella; Charles Hayter; Ewa Szumacher; Andrew Loblaw; Rebecca Wong; Cyril Danjoux Journal: Int J Radiat Oncol Biol Phys Date: 2005-03-01 Impact factor: 7.038
Authors: Alysa Fairchild; Elizabeth Barnes; Sunita Ghosh; Edgar Ben-Josef; Daniel Roos; William Hartsell; Tanya Holt; Jackson Wu; Nora Janjan; Edward Chow Journal: Int J Radiat Oncol Biol Phys Date: 2009-05-21 Impact factor: 7.038
Authors: Guergana K Savova; Ioana Danciu; Folami Alamudun; Timothy Miller; Chen Lin; Danielle S Bitterman; Georgia Tourassi; Jeremy L Warner Journal: Cancer Res Date: 2019-08-08 Impact factor: 12.701
Authors: Michael F Gensheimer; Sonya Aggarwal; Kathryn R K Benson; Justin N Carter; A Solomon Henry; Douglas J Wood; Scott G Soltys; Steven Hancock; Erqi Pollom; Nigam H Shah; Daniel T Chang Journal: J Am Med Inform Assoc Date: 2021-06-12 Impact factor: 4.497
Authors: Kunal Bhanot; Jessica Widdifield; Anjie Huang; J Michael Paterson; David B Shultz; Joel Finkelstein Journal: Can J Surg Date: 2022-08-04 Impact factor: 2.840