Cary Oberije1, Georgi Nalbantov2, Andre Dekker2, Liesbeth Boersma2, Jacques Borger2, Bart Reymen2, Angela van Baardwijk2, Rinus Wanders2, Dirk De Ruysscher3, Ewout Steyerberg4, Anne-Marie Dingemans5, Philippe Lambin2. 1. Department of Radiation Oncology (MAASTRO), GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre, The Netherlands. Electronic address: cary.oberije@maastro.nl. 2. Department of Radiation Oncology (MAASTRO), GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre, The Netherlands. 3. Department of Radiation Oncology, University Hospital Leuven/KU Leuven, Belgium. 4. Department of Public Health, Erasmus Medical Center, Rotterdam, The Netherlands. 5. Department of Pulmonology, GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre, The Netherlands.
Abstract
BACKGROUND: Decision Support Systems, based on statistical prediction models, have the potential to change the way medicine is being practiced, but their application is currently hampered by the astonishing lack of impact studies. Showing the theoretical benefit of using these models could stimulate conductance of such studies. In addition, it would pave the way for developing more advanced models, based on genomics, proteomics and imaging information, to further improve the performance of the models. PURPOSE: In this prospective single-center study, previously developed and validated statistical models were used to predict the two-year survival (2yrS), dyspnea (DPN), and dysphagia (DPH) outcomes for lung cancer patients treated with chemo radiation. These predictions were compared to probabilities provided by doctors and guideline-based recommendations currently used. We hypothesized that model predictions would significantly outperform predictions from doctors. MATERIALS AND METHODS: Experienced radiation oncologists (ROs) predicted all outcomes at two timepoints: (1) after the first consultation of the patient, and (2) after the radiation treatment plan was made. Differences in the performances of doctors and models were assessed using Area Under the Curve (AUC) analysis. RESULTS: A total number of 155 patients were included. At timepoint #1 the differences in AUCs between the ROs and the models were 0.15, 0.17, and 0.20 (for 2yrS, DPN, and DPH, respectively), with p-values of 0.02, 0.07, and 0.03. Comparable differences at timepoint #2 were not statistically significant due to the limited number of patients. Comparison to guideline-based recommendations also favored the models. CONCLUSION: The models substantially outperformed ROs' predictions and guideline-based recommendations currently used in clinical practice. Identification of risk groups on the basis of the models facilitates individualized treatment, and should be further investigated in clinical impact studies.
BACKGROUND: Decision Support Systems, based on statistical prediction models, have the potential to change the way medicine is being practiced, but their application is currently hampered by the astonishing lack of impact studies. Showing the theoretical benefit of using these models could stimulate conductance of such studies. In addition, it would pave the way for developing more advanced models, based on genomics, proteomics and imaging information, to further improve the performance of the models. PURPOSE: In this prospective single-center study, previously developed and validated statistical models were used to predict the two-year survival (2yrS), dyspnea (DPN), and dysphagia (DPH) outcomes for lung cancerpatients treated with chemo radiation. These predictions were compared to probabilities provided by doctors and guideline-based recommendations currently used. We hypothesized that model predictions would significantly outperform predictions from doctors. MATERIALS AND METHODS: Experienced radiation oncologists (ROs) predicted all outcomes at two timepoints: (1) after the first consultation of the patient, and (2) after the radiation treatment plan was made. Differences in the performances of doctors and models were assessed using Area Under the Curve (AUC) analysis. RESULTS: A total number of 155 patients were included. At timepoint #1 the differences in AUCs between the ROs and the models were 0.15, 0.17, and 0.20 (for 2yrS, DPN, and DPH, respectively), with p-values of 0.02, 0.07, and 0.03. Comparable differences at timepoint #2 were not statistically significant due to the limited number of patients. Comparison to guideline-based recommendations also favored the models. CONCLUSION: The models substantially outperformed ROs' predictions and guideline-based recommendations currently used in clinical practice. Identification of risk groups on the basis of the models facilitates individualized treatment, and should be further investigated in clinical impact studies.
Authors: Klaus-Rüdiger Trott; Wolfgang Doerr; Angelica Facoetti; John Hopewell; Johannes Langendijk; Peter van Luijk; Andrea Ottolenghi; Vere Smyth Journal: Radiother Oncol Date: 2012-06-29 Impact factor: 6.280
Authors: Phillip L Ross; Claudia Gerigk; Mithat Gonen; Ofer Yossepowitch; Ilias Cagiannos; Pramod C Sogani; Peter T Scardino; Michael W Kattan Journal: Semin Urol Oncol Date: 2002-05
Authors: William J Catalona; Jerome P Richie; Frederick R Ahmann; M'Liss A Hudson; Peter T Scardino; Robert C Flanigan; Jean B DeKernion; Timothy L Ratliff; Louis R Kavoussi; Bruce L Dalkin; W Bedford Waters; Michael T MacFarlane; Paula C Southwick Journal: J Urol Date: 1994-05 Impact factor: 7.450
Authors: Maria Werner-Wasik; R Suzanne Swann; Jeffrey Bradley; Mary Graham; Bahman Emami; James Purdy; William Sause Journal: Int J Radiat Oncol Biol Phys Date: 2007-09-14 Impact factor: 7.038
Authors: Ian M Thompson; Donna K Pauler; Phyllis J Goodman; Catherine M Tangen; M Scott Lucia; Howard L Parnes; Lori M Minasian; Leslie G Ford; Scott M Lippman; E David Crawford; John J Crowley; Charles A Coltman Journal: N Engl J Med Date: 2004-05-27 Impact factor: 91.245
Authors: Alyson L Mahar; Carolyn Compton; Lisa M McShane; Susan Halabi; Hisao Asamura; Ramon Rami-Porta; Patti A Groome Journal: J Thorac Oncol Date: 2015-11 Impact factor: 15.609
Authors: D C Norvell; M L Thompson; E J Boyko; G Landry; A J Littman; W G Henderson; A P Turner; C Maynard; K P Moore; J M Czerniecki Journal: Br J Surg Date: 2019-03-13 Impact factor: 6.939
Authors: Issam El Naqa; Dan Ruan; Gilmer Valdes; Andre Dekker; Todd McNutt; Yaorong Ge; Q Jackie Wu; Jung Hun Oh; Maria Thor; Wade Smith; Arvind Rao; Clifton Fuller; Ying Xiao; Frank Manion; Matthew Schipper; Charles Mayo; Jean M Moran; Randall Ten Haken Journal: Med Phys Date: 2018-08-24 Impact factor: 4.071
Authors: Chintan Parmar; Patrick Grossmann; Derek Rietveld; Michelle M Rietbergen; Philippe Lambin; Hugo J W L Aerts Journal: Front Oncol Date: 2015-12-03 Impact factor: 6.244