Fengrui Xu1, Martín-J Sepúlveda2, Zefei Jiang3, Haibo Wang4, Jianbin Li3, Zhenzhen Liu5, Yongmei Yin6, M Christopher Roebuck7, Edward H Shortliffe8, Min Yan5, Yuhua Song4, Cuizhi Geng9, Jinhai Tang6, Gretchen Purcell Jackson10, Anita M Preininger10, Kyu Rhee10. 1. Department of Breast Cancer, Academy of Military Medical Sciences, Beijing, People's Republic of China. 2. IBM Research, Yorktown Heights, NY. 3. Department of Breast Cancer, Fifth Medical Center, Chinese People's Liberation Army General Hospital, Beijing, People's Republic of China. 4. Department of Breast Cancer Center, Affiliated Hospital of Qingdao University, Qingdao, People's Republic of China. 5. Department of Breast Cancer Center, Henan Cancer Hospital, Zhengzhou, People's Republic of China. 6. Department of Breast Cancer, Jiangsu Province Hospital, Nanjing, People's Republic of China. 7. RxEconomics, Hunt Valley, MD. 8. Department of Biomedical Informatics, Columbia University, New York, NY. 9. Department of Breast Surgery, Fourth Hospital of Hebei Medical University, Shijiazhuang, People's Republic of China. 10. IBM Watson Health, Cambridge, MA.
Abstract
PURPOSE: To examine the impact of a clinical decision support system (CDSS) on breast cancer treatment decisions and adherence to National Comprehensive Cancer Center (NCCN) guidelines. PATIENTS AND METHODS: A cross-sectional observational study was conducted involving 1,977 patients at high risk for recurrent or metastatic breast cancer from the Chinese Society of Clinical Oncology. Ten oncologists provided blinded treatment recommendations for an average of 198 patients before and after viewing therapeutic options offered by the CDSS. Univariable and bivariable analyses of treatment changes were performed, and multivariable logistic regressions were estimated to examine the effects of physician experience (years), patient age, and receptor subtype/TNM stage. RESULTS: Treatment decisions changed in 105 (5%) of 1,977 patients and were concentrated in those with hormone receptor (HR)-positive disease or stage IV disease in the first-line therapy setting (73% and 58%, respectively). Logistic regressions showed that decision changes were more likely in those with HR-positive cancer (odds ratio [OR], 1.58; P < .05) and less likely in those with stage IIA (OR, 0.29; P < .05) or IIIA cancer (OR, 0.08; P < .01). Reasons cited for changes included consideration of the CDSS therapeutic options (63% of patients), patient factors highlighted by the tool (23%), and the decision logic of the tool (13%). Patient age and oncologist experience were not associated with decision changes. Adherence to NCCN treatment guidelines increased slightly after using the CDSS (0.5%; P = .003). CONCLUSION: Use of an artificial intelligence-based CDSS had a significant impact on treatment decisions and NCCN guideline adherence in HR-positive breast cancers. Although cases of stage IV disease in the first-line therapy setting were also more likely to be changed, the effect was not statistically significant (P = .22). Additional research on decision impact, patient-physician communication, learning, and clinical outcomes is needed to establish the overall value of the technology.
PURPOSE: To examine the impact of a clinical decision support system (CDSS) on breast cancer treatment decisions and adherence to National Comprehensive Cancer Center (NCCN) guidelines. PATIENTS AND METHODS: A cross-sectional observational study was conducted involving 1,977 patients at high risk for recurrent or metastatic breast cancer from the Chinese Society of Clinical Oncology. Ten oncologists provided blinded treatment recommendations for an average of 198 patients before and after viewing therapeutic options offered by the CDSS. Univariable and bivariable analyses of treatment changes were performed, and multivariable logistic regressions were estimated to examine the effects of physician experience (years), patient age, and receptor subtype/TNM stage. RESULTS: Treatment decisions changed in 105 (5%) of 1,977 patients and were concentrated in those with hormone receptor (HR)-positive disease or stage IV disease in the first-line therapy setting (73% and 58%, respectively). Logistic regressions showed that decision changes were more likely in those with HR-positive cancer (odds ratio [OR], 1.58; P < .05) and less likely in those with stage IIA (OR, 0.29; P < .05) or IIIA cancer (OR, 0.08; P < .01). Reasons cited for changes included consideration of the CDSS therapeutic options (63% of patients), patient factors highlighted by the tool (23%), and the decision logic of the tool (13%). Patient age and oncologist experience were not associated with decision changes. Adherence to NCCN treatment guidelines increased slightly after using the CDSS (0.5%; P = .003). CONCLUSION: Use of an artificial intelligence-based CDSS had a significant impact on treatment decisions and NCCN guideline adherence in HR-positive breast cancers. Although cases of stage IV disease in the first-line therapy setting were also more likely to be changed, the effect was not statistically significant (P = .22). Additional research on decision impact, patient-physician communication, learning, and clinical outcomes is needed to establish the overall value of the technology.
Authors: Joseph A Sparano; Robert J Gray; Della F Makower; Kathy S Albain; Thomas J Saphner; Sunil S Badve; Lynne I Wagner; Virginia G Kaklamani; Maccon M Keane; Henry L Gomez; Pavan S Reddy; Timothy F Goggins; Ingrid A Mayer; Deborah L Toppmeyer; Adam M Brufsky; Matthew P Goetz; Jeffrey L Berenberg; Catalin Mahalcioiu; Christine Desbiens; Daniel F Hayes; Elizabeth C Dees; Charles E Geyer; John A Olson; William C Wood; Tracy Lively; Soonmyung Paik; Matthew J Ellis; Jeffrey Abrams; George W Sledge Journal: JAMA Oncol Date: 2020-03-01 Impact factor: 31.777
Authors: Melissa Anne Mallory; Katya Losk; Nancy U Lin; Yasuaki Sagara; Robyn L Birdwell; Linda Cutone; Kristen Camuso; Craig Bunnell; Fatih Aydogan; Mehra Golshan Journal: Ann Surg Oncol Date: 2015-07-23 Impact factor: 5.344
Authors: Tiffani J Bright; Anthony Wong; Ravi Dhurjati; Erin Bristow; Lori Bastian; Remy R Coeytaux; Gregory Samsa; Vic Hasselblad; John W Williams; Michael D Musty; Liz Wing; Amy S Kendrick; Gillian D Sanders; David Lobach Journal: Ann Intern Med Date: 2012-07-03 Impact factor: 25.391
Authors: J H Chang; E Vines; H Bertsch; D L Fraker; B J Czerniecki; E F Rosato; T Lawton; E F Conant; S G Orel; L Schuchter; K R Fox; N Zieber; J H Glick; L J Solin Journal: Cancer Date: 2001-04-01 Impact factor: 6.860
Authors: Tait D Shanafelt; William J Gradishar; Michael Kosty; Daniel Satele; Helen Chew; Leora Horn; Ben Clark; Amy E Hanley; Quyen Chu; John Pippen; Jeff Sloan; Marilyn Raymond Journal: J Clin Oncol Date: 2014-01-27 Impact factor: 44.544